From 2a93a4fac7b6051d3be7cd1b015fe7320cd0404d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 13 May 2026 11:37:18 -0700 Subject: [PATCH 0001/1518] ptrace: slightly saner 'get_dumpable()' logic commit 31e62c2ebbfdc3fe3dbdf5e02c92a9dc67087a3a upstream. The 'dumpability' of a task is fundamentally about the memory image of the task - the concept comes from whether it can core dump or not - and makes no sense when you don't have an associated mm. And almost all users do in fact use it only for the case where the task has a mm pointer. But we have one odd special case: ptrace_may_access() uses 'dumpable' to check various other things entirely independently of the MM (typically explicitly using flags like PTRACE_MODE_READ_FSCREDS). Including for threads that no longer have a VM (and maybe never did, like most kernel threads). It's not what this flag was designed for, but it is what it is. The ptrace code does check that the uid/gid matches, so you do have to be uid-0 to see kernel thread details, but this means that the traditional "drop capabilities" model doesn't make any difference for this all. Make it all make a *bit* more sense by saying that if you don't have a MM pointer, we'll use a cached "last dumpability" flag if the thread ever had a MM (it will be zero for kernel threads since it is never set), and require a proper CAP_SYS_PTRACE capability to override. Reported-by: Qualys Security Advisory Cc: Oleg Nesterov Cc: Kees Cook Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 3 +++ kernel/exit.c | 1 + kernel/ptrace.c | 22 ++++++++++++++++------ 3 files changed, 20 insertions(+), 6 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 2a540a9065dea..5dea369fcfc96 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1003,6 +1003,9 @@ struct task_struct { unsigned sched_rt_mutex:1; #endif + /* Save user-dumpable when mm goes away */ + unsigned user_dumpable:1; + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/kernel/exit.c b/kernel/exit.c index c97db291c5d1c..c832946823f48 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -572,6 +572,7 @@ static void exit_mm(void) */ smp_mb__after_spinlock(); local_irq_disable(); + current->user_dumpable = (get_dumpable(mm) == SUID_DUMP_USER); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 75a84efad40f1..22b8be2fc43d5 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -272,11 +272,24 @@ static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) return ns_capable(ns, CAP_SYS_PTRACE); } +static bool task_still_dumpable(struct task_struct *task, unsigned int mode) +{ + struct mm_struct *mm = task->mm; + if (mm) { + if (get_dumpable(mm) == SUID_DUMP_USER) + return true; + return ptrace_has_cap(mm->user_ns, mode); + } + + if (task->user_dumpable) + return true; + return ptrace_has_cap(&init_user_ns, mode); +} + /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; - struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; @@ -337,11 +350,8 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) * Pairs with a write barrier in commit_creds(). */ smp_rmb(); - mm = task->mm; - if (mm && - ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(mm->user_ns, mode))) - return -EPERM; + if (!task_still_dumpable(task, mode)) + return -EPERM; return security_ptrace_access_check(task, mode); } From 6c1de6e6aa8cf45b3b3dba510ad0f72df7c61618 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 15 May 2026 14:52:18 +0200 Subject: [PATCH 0002/1518] Linux 6.18.31 Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index f4706ffa9b1ad..89c614db52409 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 30 +SUBLEVEL = 31 EXTRAVERSION = NAME = Baby Opossum Posse From 7812694752a5f295eaa05a093b90a2c332666051 Mon Sep 17 00:00:00 2001 From: "T.J. Mercier" Date: Fri, 17 Apr 2026 08:47:02 -0700 Subject: [PATCH 0003/1518] HID: playstation: Clamp num_touch_reports commit cac61b58a3b6340c52afa06bb15eac033158db2f upstream. A device would never lie about the number of touch reports would it? If it does the loop in dualshock4_parse_report will read off the end of the touch_reports array, up to about 2 KiB for the maximum number of 256 loop iteraions. The data that is read is emitted via evdev if the DS4_TOUCH_POINT_INACTIVE bit happens to be set. Protect against this by clamping the num_touch_reports value provided by the device to the maximum size of the touch_reports array. Fixes: 752038248808 ("HID: playstation: add DualShock4 touchpad support.") Cc: stable@vger.kernel.org Reported-by: Xingyu Jin Signed-off-by: T.J. Mercier Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-playstation.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index 2ec6d4445e84b..12fad45ac1065 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -2378,7 +2378,8 @@ static int dualshock4_parse_report(struct ps_device *ps_dev, struct hid_report * (struct dualshock4_input_report_usb *)data; ds4_report = &usb->common; - num_touch_reports = usb->num_touch_reports; + num_touch_reports = min_t(u8, usb->num_touch_reports, + ARRAY_SIZE(usb->touch_reports)); touch_reports = usb->touch_reports; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS4_INPUT_REPORT_BT && size == DS4_INPUT_REPORT_BT_SIZE) { @@ -2392,7 +2393,8 @@ static int dualshock4_parse_report(struct ps_device *ps_dev, struct hid_report * } ds4_report = &bt->common; - num_touch_reports = bt->num_touch_reports; + num_touch_reports = min_t(u8, bt->num_touch_reports, + ARRAY_SIZE(bt->touch_reports)); touch_reports = bt->touch_reports; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS4_INPUT_REPORT_BT_MINIMAL && From 59a79938ca5541fe55d675304116b7ea684afef0 Mon Sep 17 00:00:00 2001 From: Sangyun Kim Date: Mon, 20 Apr 2026 14:13:17 +0900 Subject: [PATCH 0004/1518] HID: appletb-kbd: fix UAF in inactivity-timer cleanup path commit 4db2af929279c799b5653a39eb0795c72baffca4 upstream. Commit 38224c472a03 ("HID: appletb-kbd: fix slab use-after-free bug in appletb_kbd_probe") added timer_delete_sync(&kbd->inactivity_timer) to both the probe close_hw error path and appletb_kbd_remove(), but the way it was wired in left the inactivity timer reachable during driver tear-down via two distinct windows. Window A -- put_device() before timer_delete_sync(): put_device(&kbd->backlight_dev->dev); timer_delete_sync(&kbd->inactivity_timer); The inactivity_timer softirq reads kbd->backlight_dev and calls backlight_device_set_brightness() -> mutex_lock(&ops_lock). If a concurrent hid_appletb_bl unbind drops the last devm reference between these two calls, the backlight_device is freed and the mutex_lock() touches freed memory. Window B -- backlight cleanup before hid_hw_stop(): if (kbd->backlight_dev) { timer_delete_sync(...); put_device(...); } hid_hw_close(hdev); hid_hw_stop(hdev); Even after Window A is closed, hid_hw_close()/hid_hw_stop() still run afterwards, so a late ".event" callback from the HID core (USB URB completion on real Apple hardware) can arrive after timer_delete_sync() drained the softirq but before put_device() drops the reference. That callback reaches reset_inactivity_timer(), which calls mod_timer() and re-arms the timer. The freshly re-armed timer can then fire on the about-to-be-freed backlight_device. Both windows produce the same KASAN slab-use-after-free: BUG: KASAN: slab-use-after-free in __mutex_lock+0x1aab/0x21c0 Read of size 8 at addr ffff88803ee9a108 by task swapper/0/0 Call Trace: __mutex_lock backlight_device_set_brightness appletb_inactivity_timer call_timer_fn run_timer_softirq handle_softirqs Allocated by task N: devm_backlight_device_register appletb_bl_probe Freed by task M: (concurrent hid_appletb_bl unbind path) Close both windows at once by reworking the tear-down in appletb_kbd_remove() and in the probe close_hw error path so that 1) hid_hw_close()/hid_hw_stop() run before the backlight cleanup, guaranteeing no further .event callback can fire and re-arm the timer, and 2) inside the "if (kbd->backlight_dev)" block, timer_delete_sync() runs before put_device(), so the softirq is drained before the final reference is dropped. Fixes: 38224c472a03 ("HID: appletb-kbd: fix slab use-after-free bug in appletb_kbd_probe") Cc: stable@vger.kernel.org Signed-off-by: Sangyun Kim Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-appletb-kbd.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c index 0b10cff465e17..711403441e308 100644 --- a/drivers/hid/hid-appletb-kbd.c +++ b/drivers/hid/hid-appletb-kbd.c @@ -440,13 +440,13 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id unregister_handler: input_unregister_handler(&kbd->inp_handler); close_hw: - if (kbd->backlight_dev) { - put_device(&kbd->backlight_dev->dev); - timer_delete_sync(&kbd->inactivity_timer); - } hid_hw_close(hdev); stop_hw: hid_hw_stop(hdev); + if (kbd->backlight_dev) { + timer_delete_sync(&kbd->inactivity_timer); + put_device(&kbd->backlight_dev->dev); + } return ret; } @@ -457,13 +457,13 @@ static void appletb_kbd_remove(struct hid_device *hdev) appletb_kbd_set_mode(kbd, APPLETB_KBD_MODE_OFF); input_unregister_handler(&kbd->inp_handler); + hid_hw_close(hdev); + hid_hw_stop(hdev); + if (kbd->backlight_dev) { - put_device(&kbd->backlight_dev->dev); timer_delete_sync(&kbd->inactivity_timer); + put_device(&kbd->backlight_dev->dev); } - - hid_hw_close(hdev); - hid_hw_stop(hdev); } #ifdef CONFIG_PM From 5c0830323689ef15224f0025276176988861b3b0 Mon Sep 17 00:00:00 2001 From: Sangyun Kim Date: Mon, 20 Apr 2026 14:13:18 +0900 Subject: [PATCH 0005/1518] HID: appletb-kbd: run inactivity autodim from workqueues commit 1654e53349d4e657b331de354313461f401f5063 upstream. The autodim code in hid-appletb-kbd takes backlight_device->ops_lock via backlight_device_set_brightness() -> mutex_lock() from two different atomic contexts: * appletb_inactivity_timer() is a struct timer_list callback, so it runs in softirq context. Every expiry triggers BUG: sleeping function called from invalid context at kernel/locking/mutex.c:591 Call Trace: __might_resched __mutex_lock backlight_device_set_brightness appletb_inactivity_timer call_timer_fn run_timer_softirq * reset_inactivity_timer() is called from appletb_kbd_hid_event() and appletb_kbd_inp_event(). On real USB hardware these run in softirq/IRQ context (URB completion and input-event dispatch). When the Touch Bar has already been dimmed or turned off, the reset path calls backlight_device_set_brightness() directly to restore brightness, producing the same warning. Both call sites hit the same mutex_lock()-from-atomic bug. Fix them together by moving the blocking work onto the system workqueue: * Convert the inactivity timer from struct timer_list to struct delayed_work; the callback (appletb_inactivity_work) now runs in process context where mutex_lock() is legal. * Add a dedicated struct work_struct restore_brightness_work and have reset_inactivity_timer() schedule it instead of calling backlight_device_set_brightness() directly. Cancel both works synchronously during driver tear-down alongside the existing backlight reference drop. The semantics are unchanged (same delays, same state transitions on dim, turn-off and user activity); only the execution context of the sleeping call changes. The timer field and callback are renamed to match their new type; reset_inactivity_timer() keeps its name because it is invoked from input event paths that read naturally as "reset the inactivity timer". Fixes: 93a0fc489481 ("HID: hid-appletb-kbd: add support for automatic brightness control while using the touchbar") Cc: stable@vger.kernel.org Signed-off-by: Sangyun Kim Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-appletb-kbd.c | 44 ++++++++++++++++++++++++----------- 1 file changed, 30 insertions(+), 14 deletions(-) diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c index 711403441e308..c96423a531f6f 100644 --- a/drivers/hid/hid-appletb-kbd.c +++ b/drivers/hid/hid-appletb-kbd.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include "hid-ids.h" @@ -62,7 +62,8 @@ struct appletb_kbd { struct input_handle kbd_handle; struct input_handle tpd_handle; struct backlight_device *backlight_dev; - struct timer_list inactivity_timer; + struct delayed_work inactivity_work; + struct work_struct restore_brightness_work; bool has_dimmed; bool has_turned_off; u8 saved_mode; @@ -164,16 +165,18 @@ static int appletb_tb_key_to_slot(unsigned int code) } } -static void appletb_inactivity_timer(struct timer_list *t) +static void appletb_inactivity_work(struct work_struct *work) { - struct appletb_kbd *kbd = timer_container_of(kbd, t, inactivity_timer); + struct appletb_kbd *kbd = container_of(to_delayed_work(work), + struct appletb_kbd, + inactivity_work); if (kbd->backlight_dev && appletb_tb_autodim) { if (!kbd->has_dimmed) { backlight_device_set_brightness(kbd->backlight_dev, 1); kbd->has_dimmed = true; - mod_timer(&kbd->inactivity_timer, - jiffies + secs_to_jiffies(appletb_tb_idle_timeout)); + mod_delayed_work(system_wq, &kbd->inactivity_work, + secs_to_jiffies(appletb_tb_idle_timeout)); } else if (!kbd->has_turned_off) { backlight_device_set_brightness(kbd->backlight_dev, 0); kbd->has_turned_off = true; @@ -181,16 +184,25 @@ static void appletb_inactivity_timer(struct timer_list *t) } } +static void appletb_restore_brightness_work(struct work_struct *work) +{ + struct appletb_kbd *kbd = container_of(work, struct appletb_kbd, + restore_brightness_work); + + if (kbd->backlight_dev) + backlight_device_set_brightness(kbd->backlight_dev, 2); +} + static void reset_inactivity_timer(struct appletb_kbd *kbd) { if (kbd->backlight_dev && appletb_tb_autodim) { if (kbd->has_dimmed || kbd->has_turned_off) { - backlight_device_set_brightness(kbd->backlight_dev, 2); kbd->has_dimmed = false; kbd->has_turned_off = false; + schedule_work(&kbd->restore_brightness_work); } - mod_timer(&kbd->inactivity_timer, - jiffies + secs_to_jiffies(appletb_tb_dim_timeout)); + mod_delayed_work(system_wq, &kbd->inactivity_work, + secs_to_jiffies(appletb_tb_dim_timeout)); } } @@ -408,9 +420,11 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id dev_err_probe(dev, -ENODEV, "Failed to get backlight device\n"); } else { backlight_device_set_brightness(kbd->backlight_dev, 2); - timer_setup(&kbd->inactivity_timer, appletb_inactivity_timer, 0); - mod_timer(&kbd->inactivity_timer, - jiffies + secs_to_jiffies(appletb_tb_dim_timeout)); + INIT_DELAYED_WORK(&kbd->inactivity_work, appletb_inactivity_work); + INIT_WORK(&kbd->restore_brightness_work, + appletb_restore_brightness_work); + mod_delayed_work(system_wq, &kbd->inactivity_work, + secs_to_jiffies(appletb_tb_dim_timeout)); } kbd->inp_handler.event = appletb_kbd_inp_event; @@ -444,7 +458,8 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id stop_hw: hid_hw_stop(hdev); if (kbd->backlight_dev) { - timer_delete_sync(&kbd->inactivity_timer); + cancel_delayed_work_sync(&kbd->inactivity_work); + cancel_work_sync(&kbd->restore_brightness_work); put_device(&kbd->backlight_dev->dev); } return ret; @@ -461,7 +476,8 @@ static void appletb_kbd_remove(struct hid_device *hdev) hid_hw_stop(hdev); if (kbd->backlight_dev) { - timer_delete_sync(&kbd->inactivity_timer); + cancel_delayed_work_sync(&kbd->inactivity_work); + cancel_work_sync(&kbd->restore_brightness_work); put_device(&kbd->backlight_dev->dev); } } From 80d8cc29d3b68d65a991c44aedc2f5e5a4e014fe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Tomasz=20Paku=C5=82a?= Date: Sun, 10 May 2026 14:23:52 +0200 Subject: [PATCH 0006/1518] HID: pidff: Fix integer overflow in pidff_rescale MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 48d1677779ad6816978ad4a4f7588aec5ec960fe upstream. Rescaling values close to the max (U16_MAX) temporarily creates values that exceed the s32 range. This caused value overflow in case when, for example, a periodic effect phase was higer than 180 degrees. In turn, rescale function could return values outised of the logical range of the HID field. Fix by using 64 bit signed integer to store the value during calculation but still return only 32 bit integer. Closes: https://github.com/JacKeTUs/universal-pidff/issues/116 Fixes: 224ee88fe395 ("Input: add force feedback driver for PID devices") Cc: stable@vger.kernel.org Signed-off-by: Tomasz Pakuła Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/usbhid/hid-pidff.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index 56d6af39ba81e..c06b1913f5baf 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -11,6 +11,7 @@ #include "hid-pidff.h" #include #include +#include #include #include #include @@ -325,8 +326,10 @@ static s32 pidff_clamp(s32 i, struct hid_field *field) */ static int pidff_rescale(int i, int max, struct hid_field *field) { - return i * (field->logical_maximum - field->logical_minimum) / max + - field->logical_minimum; + /* 64 bits needed for big values during rescale */ + s64 result = field->logical_maximum - field->logical_minimum; + + return div_s64(result * i, max) + field->logical_minimum; } /* From 06d99af8db1127fec0a587b654bda1fc2d41f746 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Mon, 9 Mar 2026 15:01:54 +0000 Subject: [PATCH 0007/1518] media: uvcvideo: Enable VB2_DMABUF for metadata stream commit fbac03467e53d8d72e5099c03df26d9adae11416 upstream. The UVC driver has two video streams, one for the frames and another one for the metadata. Both streams share most of the codebase, but only the data stream declares support for DMABUF transfer mode. I have tried the DMABUF transfer mode with CONFIG_DMABUF_HEAPS_SYSTEM and the frames looked correct. This patch announces the support for DMABUF for the metadata stream. This is useful for apps/HALs that only want to support DMABUF. Cc: stable@vger.kernel.org Fixes: 088ead2552458 ("media: uvcvideo: Add a metadata device node") Signed-off-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Reviewed-by: Hans de Goede Link: https://patch.msgid.link/20260309-uvc-metadata-dmabuf-v1-1-fc8b87bd29c5@chromium.org Signed-off-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_queue.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c index e838c6c1893a6..085abdb116af4 100644 --- a/drivers/media/usb/uvc/uvc_queue.c +++ b/drivers/media/usb/uvc/uvc_queue.c @@ -243,7 +243,7 @@ int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type) int ret; queue->queue.type = type; - queue->queue.io_modes = VB2_MMAP | VB2_USERPTR; + queue->queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF; queue->queue.drv_priv = queue; queue->queue.buf_struct_size = sizeof(struct uvc_buffer); queue->queue.mem_ops = &vb2_vmalloc_memops; @@ -256,7 +256,6 @@ int uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type) queue->queue.ops = &uvc_meta_queue_qops; break; default: - queue->queue.io_modes |= VB2_DMABUF; queue->queue.ops = &uvc_queue_qops; break; } From 0ac9ec121d89254bf1812025316439ed62aae71f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 11 Mar 2026 20:16:21 +0100 Subject: [PATCH 0008/1518] drm/msm/hdmi: Fix wrong CTRL1 register used in writing info frames commit 8c6c93b7db42d15c6e8c2540a648d32986a04b1a upstream. Commit 384d2b03d0a1 ("drm/msm/hdmi: make use of the drm_connector_hdmi framework") changed the unconditional register writes in few places to updates: read, apply mask, write. The new code reads REG_HDMI_INFOFRAME_CTRL1 register, applies fields/mask for HDMI_INFOFRAME_CTRL0 register and finally writes to HDMI_INFOFRAME_CTRL0. This difference between CTRL1 and CTRL0 looks unintended and may result in wrong data being written to HDMI bridge registers. Cc: Fixes: 384d2b03d0a1 ("drm/msm/hdmi: make use of the drm_connector_hdmi framework") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/711156/ Link: https://lore.kernel.org/r/20260311191620.245394-2-krzysztof.kozlowski@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/msm/hdmi/hdmi_bridge.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 46fd58646d32f..93a491a103e0a 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -80,7 +80,7 @@ static int msm_hdmi_config_avi_infoframe(struct hdmi *hdmi, for (i = 0; i < ARRAY_SIZE(buf); i++) hdmi_write(hdmi, REG_HDMI_AVI_INFO(i), buf[i]); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); val |= HDMI_INFOFRAME_CTRL0_AVI_SEND | HDMI_INFOFRAME_CTRL0_AVI_CONT; hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); @@ -116,7 +116,7 @@ static int msm_hdmi_config_audio_infoframe(struct hdmi *hdmi, buffer[9] << 16 | buffer[10] << 24); - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); val |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | From 4d6e8496486d7da3d047c8061b24864a6ed6c7b0 Mon Sep 17 00:00:00 2001 From: Guoniu Zhou Date: Thu, 12 Mar 2026 11:12:34 +0800 Subject: [PATCH 0009/1518] media: nxp: imx8-isi: Reduce minimum queued buffers from 2 to 0 commit 2f38622d0f85f317be9e6b131da6cd511db94fd2 upstream. Fix a hang issue when capturing a single frame with applications like cam in libcamera. It would hang waiting for the driver to complete the buffer, but streaming never starts because min_queued_buffers was set to 2. The ISI module uses a ping-pong buffer mechanism that requires two buffers to be programmed at all times. However, when fewer than 2 user buffers are available, the driver use internal discard buffers to fill the remaining slot(s). Reduce minimum queued buffers from 2 to 0 allows streaming to start without any queued buffers. Fixes: cf21f328fcaf ("media: nxp: Add i.MX8 ISI driver") Cc: stable@vger.kernel.org Signed-off-by: Guoniu Zhou Reviewed-by: Laurent Pinchart Link: https://patch.msgid.link/20260312-isi_min_buffers-v2-1-d5ea1c79ad81@nxp.com Signed-off-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c index 13682bf6e9f88..1be3a728f32f8 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c @@ -1410,7 +1410,7 @@ int mxc_isi_video_register(struct mxc_isi_pipe *pipe, q->mem_ops = &vb2_dma_contig_memops; q->buf_struct_size = sizeof(struct mxc_isi_buffer); q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - q->min_queued_buffers = 2; + q->min_queued_buffers = 0; q->lock = &video->lock; q->dev = pipe->isi->dev; From bfb2081ba00afbbd15a5ed1ed1acdc3edeea5a98 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Thu, 15 Jan 2026 11:22:35 +0200 Subject: [PATCH 0010/1518] media: renesas: vsp1: Fix NULL pointer deref on module unload commit 58b1e9664d8f74d55d8411cc7a7b275a76a6f24f upstream. When unloading the module on gen 4, we hit a NULL pointer dereference. This is caused by the cleanup code calling vsp1_drm_cleanup() where it should be calling vsp1_vspx_cleanup(). Fix this by checking the IP version and calling the drm or vspx function accordingly, the same way as the init code does. Fixes: d06c1a9f348d ("media: vsp1: Add VSPX support") Cc: stable@vger.kernel.org Signed-off-by: Tomi Valkeinen Reviewed-by: Kieran Bingham Reviewed-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/renesas/vsp1/vsp1_drv.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/renesas/vsp1/vsp1_drv.c b/drivers/media/platform/renesas/vsp1/vsp1_drv.c index 6c64657fc4f33..30df9b36642dc 100644 --- a/drivers/media/platform/renesas/vsp1/vsp1_drv.c +++ b/drivers/media/platform/renesas/vsp1/vsp1_drv.c @@ -240,8 +240,12 @@ static void vsp1_destroy_entities(struct vsp1_device *vsp1) media_device_unregister(&vsp1->media_dev); media_device_cleanup(&vsp1->media_dev); - if (!vsp1->info->uapi) - vsp1_drm_cleanup(vsp1); + if (!vsp1->info->uapi) { + if (vsp1->info->version == VI6_IP_VERSION_MODEL_VSPX_GEN4) + vsp1_vspx_cleanup(vsp1); + else + vsp1_drm_cleanup(vsp1); + } } static int vsp1_create_entities(struct vsp1_device *vsp1) From b6e5c80cc2b216e78924316bfe1191970309730c Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 27 Jan 2026 10:56:12 +0200 Subject: [PATCH 0011/1518] media: renesas: vin: Fix RAW8 (again) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 40c6da8a9c0f897f99a439330584d93ca7d41226 upstream. Commit e7376745ad5c ("media: rcar-vin: Fix stride setting for RAW8 formats") removed dividing the stride by two for RAW8 formats. It is unclear how this was tested, but in any of the recent tests this does not seem to work and produces quite distorted images. However, reverting the patch fixes the issues only partially. VNIS_REG requires alignment to 16 bytes, and when dividing the stride by 2, in some cases we end up with a non-aligned stride, producing a tilted image. This issue has to be fixed in rvin_format_bytesperline() where we do the alignment for bytesperline. Adding back the stride division and increasing the alignment for RAW8 formats to 0x20 fixes the problems related to RAW8. Fixes: e7376745ad5c ("media: rcar-vin: Fix stride setting for RAW8 formats") Cc: stable@vger.kernel.org Signed-off-by: Tomi Valkeinen Reviewed-by: Niklas Söderlund Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- .../platform/renesas/rcar-vin/rcar-dma.c | 22 +++++++++++++++++++ .../platform/renesas/rcar-vin/rcar-v4l2.c | 12 ++++++++++ 2 files changed, 34 insertions(+) diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c index b619d1436a415..f9af9177e02ff 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c @@ -676,8 +676,30 @@ void rvin_crop_scale_comp(struct rvin_dev *vin) if (vin->scaler) vin->scaler(vin); + /* + * VNIS_REG has four lowest bits always 0, i.e. the stride has to be + * aligned to 16 bytes. This is done in rvin_format_bytesperline(). + */ + fmt = rvin_format_from_pixel(vin, vin->format.pixelformat); stride = vin->format.bytesperline / fmt->bpp; + + /* + * RAW8 format bpp is 1, but the hardware process RAW8 format in 2 pixel + * units, so we need to divide the stride by 2. + */ + switch (vin->format.pixelformat) { + case V4L2_PIX_FMT_SBGGR8: + case V4L2_PIX_FMT_SGBRG8: + case V4L2_PIX_FMT_SGRBG8: + case V4L2_PIX_FMT_SRGGB8: + case V4L2_PIX_FMT_GREY: + stride /= 2; + break; + default: + break; + } + rvin_write(vin, stride, VNIS_REG); } diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c b/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c index 079dbaf016c25..9d45e11898c13 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-v4l2.c @@ -155,6 +155,18 @@ static u32 rvin_format_bytesperline(struct rvin_dev *vin, case V4L2_PIX_FMT_NV16: align = 0x20; break; + case V4L2_PIX_FMT_SBGGR8: + case V4L2_PIX_FMT_SGBRG8: + case V4L2_PIX_FMT_SGRBG8: + case V4L2_PIX_FMT_SRGGB8: + case V4L2_PIX_FMT_GREY: + /* + * RAW8 format bpp is 1, but the hardware process RAW8 format in + * 2 pixel units, and we need to align to 32 bytes. See + * rvin_crop_scale_comp(). + */ + align = 0x20; + break; default: align = 0x10; break; From 791598484fd558bb426ef5e051effa5c227d5390 Mon Sep 17 00:00:00 2001 From: Alexander Koskovich Date: Thu, 12 Mar 2026 17:16:20 +0000 Subject: [PATCH 0012/1518] media: i2c: ov8856: free control handler on error in ov8856_init_controls() commit f75e160745663ce9b13362ae6e90bd439c58df69 upstream. The control handler wasn't freed if adding controls failed, add an error exit label and convert the existing error return to use it. Fixes: 879347f0c258 ("media: ov8856: Add support for OV8856 sensor") Cc: stable@vger.kernel.org Signed-off-by: Alexander Koskovich Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/ov8856.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/media/i2c/ov8856.c b/drivers/media/i2c/ov8856.c index e2998cfa0d18a..dd01e1d515ff6 100644 --- a/drivers/media/i2c/ov8856.c +++ b/drivers/media/i2c/ov8856.c @@ -1951,12 +1951,18 @@ static int ov8856_init_controls(struct ov8856 *ov8856) V4L2_CID_HFLIP, 0, 1, 1, 0); v4l2_ctrl_new_std(ctrl_hdlr, &ov8856_ctrl_ops, V4L2_CID_VFLIP, 0, 1, 1, 0); - if (ctrl_hdlr->error) - return ctrl_hdlr->error; + if (ctrl_hdlr->error) { + ret = ctrl_hdlr->error; + goto err_ctrl_handler_free; + } ov8856->sd.ctrl_handler = ctrl_hdlr; return 0; + +err_ctrl_handler_free: + v4l2_ctrl_handler_free(ctrl_hdlr); + return ret; } static void ov8856_update_pad_format(struct ov8856 *ov8856, From 361e66fb431d905f9ec754f40ccff982fb5e90ed Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Wed, 4 Mar 2026 23:00:41 +0200 Subject: [PATCH 0013/1518] media: dt-bindings: rockchip,vdec: Add alternative reg-names order for RK35{76,88} commit 35c8178ed2bd9821a75a406d762b2f2e161f9c70 upstream. With the introduction of the RK3588 SoC, and RK3576 afterwards, three register blocks have been provided for the video decoder unit instead of just one, which are further referenced in vendor's datasheet by 'link table', 'function' and 'cache'. The former is present at the top of the listing, starting at video decoder unit base address. However, while documenting RK3588, the binding broke the convention expecting the unit address to indicate the start of the primary register range, i.e. the 'function' block got listed before the 'link' one. Since the binding changes have been already released and a fix would bring up an ABI break, mark the current 'reg-names' ordering as deprecated and introduce an alternative 'link,function,cache' listing which follows the address-based ordering according to the TRM. Additionally, drop the 'reg' description items as the order is not fixed anymore, while the information they offer is not very relevant anyway. It's worth noting there are currently no (known) users impacted by these binding changes, since the video decoder support for the aforementioned SoCs in mainline driver and devicetrees hasn't been released yet - it landed in v7.0-rc1 while all DTS updates resulting from this will be handled before v7.0 is out. Fixes: c6ffb7e1fb90 ("media: dt-bindings: rockchip: Document RK3588 Video Decoder bindings") Fixes: a5c4a6526476 ("media: dt-bindings: rockchip: Add RK3576 Video Decoder bindings") Cc: stable@vger.kernel.org Reviewed-by: Nicolas Dufresne Reviewed-by: Krzysztof Kozlowski Signed-off-by: Cristian Ciocaltea Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- .../bindings/media/rockchip,vdec.yaml | 20 +++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/Documentation/devicetree/bindings/media/rockchip,vdec.yaml b/Documentation/devicetree/bindings/media/rockchip,vdec.yaml index 96b6c89387683..e28e5c63735f5 100644 --- a/Documentation/devicetree/bindings/media/rockchip,vdec.yaml +++ b/Documentation/devicetree/bindings/media/rockchip,vdec.yaml @@ -27,16 +27,20 @@ properties: reg: minItems: 1 - items: - - description: The function configuration registers base - - description: The link table configuration registers base - - description: The cache configuration registers base + maxItems: 3 reg-names: - items: - - const: function - - const: link - - const: cache + oneOf: + - items: + - const: link + - const: function + - const: cache + - items: + - const: function + - const: link + - const: cache + deprecated: true + description: Use link,function,cache block order instead. interrupts: maxItems: 1 From 6261d5fd172b86ff331f9cd79d8113165bffc1dd Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Wed, 4 Mar 2026 23:00:40 +0200 Subject: [PATCH 0014/1518] media: dt-bindings: rockchip,vdec: Mark reg-names required for RK35{76,88} commit a11db8d8b403eba1f82728f440727128e9997edd upstream. The Rockchip Video Decoder driver expects reg-names to be mandatory for RK3576 and RK3588 SoCs, however the binding does not currently require the use of them. As a consequence, driver would fail to probe with a hypothetical devicetree that doesn't provide the reg-names for these SoCs, but which is otherwise a perfectly valid DT from the binding perspective. Update the binding and make reg-names required for the aforementioned SoCs. While this change introduces an ABI break, the expected impact on potential users would be minimal, if any, since the old SoCs are unaffected, while the video decoder support for these newer variants in mainline driver and devicetrees hasn't been released yet. Moreover, this is also a prerequisite for a subsequent binding update introducing an alternative reg-names order, according to the address-based listing in the vendor's datasheet. Reported-by: Conor Dooley Closes: https://lore.kernel.org/all/20260227-urologist-gratitude-7984733f2d41@spud/ Fixes: c6ffb7e1fb90 ("media: dt-bindings: rockchip: Document RK3588 Video Decoder bindings") Fixes: a5c4a6526476 ("media: dt-bindings: rockchip: Add RK3576 Video Decoder bindings") Cc: stable@vger.kernel.org Signed-off-by: Cristian Ciocaltea Acked-by: Conor Dooley Reviewed-by: Nicolas Dufresne Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/media/rockchip,vdec.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/media/rockchip,vdec.yaml b/Documentation/devicetree/bindings/media/rockchip,vdec.yaml index e28e5c63735f5..d0bce8bfb1b16 100644 --- a/Documentation/devicetree/bindings/media/rockchip,vdec.yaml +++ b/Documentation/devicetree/bindings/media/rockchip,vdec.yaml @@ -126,6 +126,8 @@ allOf: minItems: 5 reset-names: minItems: 5 + required: + - reg-names else: properties: reg: From b40ec65e092647203b1d240496a15a030d083670 Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Sun, 25 Jan 2026 22:19:15 +0800 Subject: [PATCH 0015/1518] media: chips-media: wave5: fix a potential memory leak in wave5_vdi_init() commit 95bd174a453f77b09ea66e1e22834680754ba501 upstream. Add wave5_vdi_free_dma_memory() in the error path of wave5_vdi_init() to prevent a potential memory leak. Fixes: 45d1a2b93277 ("media: chips-media: wave5: Add vpuapi layer") Cc: stable@vger.kernel.org Signed-off-by: Haoxiang Li Reviewed-by: Nicolas Dufresne Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/chips-media/wave5/wave5-vdi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/chips-media/wave5/wave5-vdi.c b/drivers/media/platform/chips-media/wave5/wave5-vdi.c index bb13267ced38a..8f71920a8a35c 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vdi.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vdi.c @@ -49,6 +49,7 @@ int wave5_vdi_init(struct device *dev) if (!PRODUCT_CODE_W_SERIES(vpu_dev->product_code)) { WARN_ONCE(1, "unsupported product code: 0x%x\n", vpu_dev->product_code); + wave5_vdi_free_dma_memory(vpu_dev, &vpu_dev->common_mem); return -EOPNOTSUPP; } From d71fc6874fce3b859f583968cfc42bf2c425ee4b Mon Sep 17 00:00:00 2001 From: Ziyi Guo Date: Sat, 31 Jan 2026 22:03:23 +0000 Subject: [PATCH 0016/1518] media: chips-media: wave5: add missing spinlock protection for send_eos_event() commit f48050436746be75227fbc90066a8658cbe94d17 upstream. Add spin_lock_irqsave()/spin_unlock_irqrestore() around send_eos_event() calls in the VB2 buffer queue and streamoff callbacks to fix the missing lock protection. wave5_vpu_dec_buf_queue_dst() and streamoff_output() call send_eos_event() without holding inst->state_spinlock. However, send_eos_event() has lockdep_assert_held(&inst->state_spinlock) indicating that callers must hold this lock. Other callers of send_eos_event() properly acquire the spinlock: - wave5_vpu_dec_finish_decode() acquires lock at line 431 - wave5_vpu_dec_encoder_cmd() acquires lock at line 821 - wave5_vpu_dec_device_run() acquires lock at line 1592 Signed-off-by: Ziyi Guo Reviewed-by: Nicolas Dufresne Fixes: 9707a6254a8a6b ("media: chips-media: wave5: Add the v4l2 layer") Cc: stable@vger.kernel.org Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- .../media/platform/chips-media/wave5/wave5-vpu-dec.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c index cff2fa17c3f59..4ffdacdd28a1f 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c @@ -1265,13 +1265,17 @@ static void wave5_vpu_dec_buf_queue_dst(struct vb2_buffer *vb) if (vb2_is_streaming(vb->vb2_queue) && v4l2_m2m_dst_buf_is_last(m2m_ctx)) { unsigned int i; + unsigned long flags; for (i = 0; i < vb->num_planes; i++) vb2_set_plane_payload(vb, i, 0); vbuf->field = V4L2_FIELD_NONE; + spin_lock_irqsave(&inst->state_spinlock, flags); send_eos_event(inst); + spin_unlock_irqrestore(&inst->state_spinlock, flags); + v4l2_m2m_last_buffer_done(m2m_ctx, vbuf); } else { v4l2_m2m_buf_queue(m2m_ctx, vbuf); @@ -1415,8 +1419,13 @@ static int streamoff_output(struct vb2_queue *q) inst->codec_info->dec_info.stream_rd_ptr = new_rd_ptr; inst->codec_info->dec_info.stream_wr_ptr = new_rd_ptr; - if (v4l2_m2m_has_stopped(m2m_ctx)) + if (v4l2_m2m_has_stopped(m2m_ctx)) { + unsigned long flags; + + spin_lock_irqsave(&inst->state_spinlock, flags); send_eos_event(inst); + spin_unlock_irqrestore(&inst->state_spinlock, flags); + } /* streamoff on output cancels any draining operation */ inst->eos = false; From ea28b33e1b15bae5d0a81b947d7039e4c3e7cdfc Mon Sep 17 00:00:00 2001 From: Ziyi Guo Date: Sat, 31 Jan 2026 22:19:07 +0000 Subject: [PATCH 0017/1518] media: chips-media: wave5: add missing spinlock protection for handle_dynamic_resolution_change() commit cb8bdd3ffca280d014311ab395651d33f58a8708 upstream. Add spin_lock_irqsave()/spin_unlock_irqrestore() around the handle_dynamic_resolution_change() call in initialize_sequence() to fix the missing lock protection. initialize_sequence() calls handle_dynamic_resolution_change() without holding inst->state_spinlock. However, handle_dynamic_resolution_change() has lockdep_assert_held(&inst->state_spinlock) indicating that callers must hold this lock. Other callers of handle_dynamic_resolution_change() properly acquire the spinlock: - wave5_vpu_dec_finish_decode() - wave5_vpu_dec_device_run() Signed-off-by: Ziyi Guo Reviewed-by: Nicolas Dufresne Fixes: 9707a6254a8a6b ("media: chips-media: wave5: Add the v4l2 layer") Cc: stable@vger.kernel.org Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c index 4ffdacdd28a1f..7a4625acc0478 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c @@ -1544,6 +1544,7 @@ static int initialize_sequence(struct vpu_instance *inst) { struct dec_initial_info initial_info; int ret = 0; + unsigned long flags; memset(&initial_info, 0, sizeof(struct dec_initial_info)); @@ -1565,7 +1566,9 @@ static int initialize_sequence(struct vpu_instance *inst) return ret; } + spin_lock_irqsave(&inst->state_spinlock, flags); handle_dynamic_resolution_change(inst); + spin_unlock_irqrestore(&inst->state_spinlock, flags); return 0; } From 7fbb3b4bef023903e66138c25b205b47be19612b Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Fri, 30 Jan 2026 11:49:27 -0800 Subject: [PATCH 0018/1518] drm/gpusvm: Force unmapping on error in drm_gpusvm_get_pages commit 556dba95473900073a6c03121361c11f646dc551 upstream. drm_gpusvm_get_pages() only sets the local flags prior to committing the pages. If an error occurs mid-mapping, has_dma_mapping will be clear, causing the unmap function to skip unmapping pages that were successfully mapped before the error. Fix this by forcibly setting has_dma_mapping in the error path to ensure all previously mapped pages are properly unmapped. Fixes: 99624bdff867 ("drm/gpusvm: Add support for GPU Shared Virtual Memory") Cc: stable@vger.kernel.org Signed-off-by: Matthew Brost Reviewed-by: Francois Dugast Link: https://patch.msgid.link/20260130194928.3255613-2-matthew.brost@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gpusvm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index cb906765897e1..853ca57800d3a 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1443,6 +1443,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, return 0; err_unmap: + svm_pages->flags.has_dma_mapping = true; __drm_gpusvm_unmap_pages(gpusvm, svm_pages, num_dma_mapped); drm_gpusvm_notifier_unlock(gpusvm); err_free: From c66a6f226a5f33c2fbd6ef9c29ddbd5088fbb86d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:04 +0200 Subject: [PATCH 0019/1518] spi: bcm63xx: fix controller deregistration commit c39e65a4e3b8e764efed0b2f5152a1a8547b80fd upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: b42dfed83d95 ("spi: add Broadcom BCM63xx SPI controller driver") Cc: stable@vger.kernel.org # 3.4 Cc: Florian Fainelli Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-6-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-bcm63xx.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c index 2e3c62f12bef9..cf7eefd39839f 100644 --- a/drivers/spi/spi-bcm63xx.c +++ b/drivers/spi/spi-bcm63xx.c @@ -603,7 +603,7 @@ static int bcm63xx_spi_probe(struct platform_device *pdev) goto out_clk_disable; /* register and we are done */ - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) { dev_err(dev, "spi register failed\n"); goto out_clk_disable; @@ -626,11 +626,17 @@ static void bcm63xx_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct bcm63xx_spi *bs = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + /* reset spi block */ bcm_spi_writeb(bs, 0, SPI_INT_MASK); /* HW shutdown */ clk_disable_unprepare(bs->clk); + + spi_controller_put(host); } static int bcm63xx_spi_suspend(struct device *dev) From 72972aba49dfc48cc4672247d0168402d5bd605b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:03 +0200 Subject: [PATCH 0020/1518] spi: atmel: fix controller deregistration commit 8d4de97e83520be89d0ff40610ca633b3963a7de upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 754ce4f29937 ("[PATCH] SPI: atmel_spi driver") Cc: stable@vger.kernel.org # 2.6.21 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-5-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-atmel.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 89977bff76d27..586e2fd357ed9 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1655,7 +1655,7 @@ static int atmel_spi_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) goto out_free_dma; @@ -1689,8 +1689,12 @@ static void atmel_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct atmel_spi *as = spi_controller_get_devdata(host); + spi_controller_get(host); + pm_runtime_get_sync(&pdev->dev); + spi_unregister_controller(host); + /* reset the hardware and block queue progress */ if (as->use_dma) { atmel_spi_stop_dma(host); @@ -1717,6 +1721,8 @@ static void atmel_spi_remove(struct platform_device *pdev) pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + + spi_controller_put(host); } static int atmel_spi_runtime_suspend(struct device *dev) From af2dc8b8460c0ecee0b20d608be6f1d0540b690c Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:40:55 +0100 Subject: [PATCH 0021/1518] arm64: dts: lx2160a-cex7/lx2162a-sr-som: fix usd-cd & gpio pinmux commit 70008aee892bbb5c2969bbe9e5778fc081b14bd2 upstream. Commit 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") introduced pinmux nodes for lx2160 i2c interfaces, allowing runtime change between i2c and gpio functions implementing bus recovery. However, the dynamic configuration area (overwrite MUX) used by the pinctrl-single driver initially reads as zero and does not reflect the actual hardware state set by the Reset Configuration Word (RCW) at power-on. Because multiple groups of pins are configured from a single 32-bit register, the first write from the pinctrl driver unintentionally clears all other bits to zero. For example, on the LX2162A Clearfog, RCWSR12 is initialized to 0x08000006. When any i2c pinmux is applied, it clears all other fields. This inadvertently disables SD card-detect (IIC2_PMUX) and some GPIOs (SDHC1_DIR_PMUX): LX2162-CF RCWSR12: 0b0000100000000000 0000000000000110 IIC2_PMUX ||| ||| || | ||| |||XXX : I2C/GPIO/CD-WP SDHC1_DIR_PMUX XXX ||| || | ||| ||| : SDHC/GPIO/SPI Reverting the commit in question was considered but bus recovery is an important feature. Instead add pinmux nodes for those pins that were unintentionally reconfigured on SolidRun LX2160A Clearfog-CX and LX2162A Clearfog boards. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Cc: stable@vger.kernel.org Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Greg Kroah-Hartman --- .../boot/dts/freescale/fsl-lx2160a-cex7.dtsi | 7 ++++++ .../freescale/fsl-lx2160a-clearfog-itx.dtsi | 2 ++ .../arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 24 +++++++++++++++++++ .../dts/freescale/fsl-lx2162a-clearfog.dts | 2 ++ .../dts/freescale/fsl-lx2162a-sr-som.dtsi | 7 ++++++ 5 files changed, 42 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi index eec2cd6c6d32a..7f6e39e27ce5c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi @@ -162,6 +162,8 @@ }; &fspi { + pinctrl-names = "default"; + pinctrl-0 = <&fspi_data74_pins>, <&fspi_data30_pins>, <&fspi_dqs_sck_cs10_pins>; status = "okay"; flash@0 { @@ -177,6 +179,11 @@ }; }; +&pinmux_i2crv { + pinctrl-names = "default"; + pinctrl-0 = <&gpio0_14_12_pins>; +}; + &usb0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-clearfog-itx.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a-clearfog-itx.dtsi index af6258b2fe826..580ee9b3026e3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-clearfog-itx.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-clearfog-itx.dtsi @@ -89,6 +89,8 @@ }; &esdhc0 { + pinctrl-names = "default"; + pinctrl-0 = <&esdhc0_cd_wp_pins>, <&esdhc0_cmd_data30_clk_vsel_pins>; sd-uhs-sdr104; sd-uhs-sdr50; sd-uhs-sdr25; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index c9541403bcd82..bc1d34f1cd545 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1717,6 +1717,10 @@ pinctrl-single,bits = <0x0 0x1 0x7>; }; + esdhc0_cd_wp_pins: iic2-sdhc-pins { + pinctrl-single,bits = <0x0 0x6 0x7>; + }; + i2c2_scl: i2c2-scl-pins { pinctrl-single,bits = <0x0 0 (0x7 << 3)>; }; @@ -1749,6 +1753,26 @@ pinctrl-single,bits = <0x0 (0x1 << 12) (0x7 << 12)>; }; + fspi_data74_pins: xspi1-data74-pins { + pinctrl-single,bits = <0x0 0x0 (0x7 << 15)>; + }; + + fspi_data30_pins: xspi1-data30-pins { + pinctrl-single,bits = <0x0 0x0 (0x7 << 18)>; + }; + + fspi_dqs_sck_cs10_pins: xspi1-base-pins { + pinctrl-single,bits = <0x0 0x0 (0x7 << 21)>; + }; + + esdhc0_cmd_data30_clk_vsel_pins: sdhc1-base-sdhc-vsel-pins { + pinctrl-single,bits = <0x0 0x0 (0x7 << 24)>; + }; + + gpio0_14_12_pins: sdhc1-dir-gpio-pins { + pinctrl-single,bits = <0x0 (0x1 << 27) (0x7 << 27)>; + }; + i2c6_scl: i2c6-scl-pins { pinctrl-single,bits = <0x4 0x2 0x7>; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2162a-clearfog.dts b/arch/arm64/boot/dts/freescale/fsl-lx2162a-clearfog.dts index eafef8718a0fe..8920326a06735 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2162a-clearfog.dts +++ b/arch/arm64/boot/dts/freescale/fsl-lx2162a-clearfog.dts @@ -223,6 +223,8 @@ }; &esdhc0 { + pinctrl-names = "default"; + pinctrl-0 = <&esdhc0_cd_wp_pins>, <&esdhc0_cmd_data30_clk_vsel_pins>; sd-uhs-sdr104; sd-uhs-sdr50; sd-uhs-sdr25; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2162a-sr-som.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2162a-sr-som.dtsi index e914291e63a1a..e1344942eaaee 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2162a-sr-som.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2162a-sr-som.dtsi @@ -30,6 +30,8 @@ }; &fspi { + pinctrl-names = "default"; + pinctrl-0 = <&fspi_data74_pins>, <&fspi_data30_pins>, <&fspi_dqs_sck_cs10_pins>; status = "okay"; flash@0 { @@ -80,3 +82,8 @@ reg = <0x6f>; }; }; + +&pinmux_i2crv { + pinctrl-names = "default"; + pinctrl-0 = <&gpio0_14_12_pins>; +}; From c7848b67ef10f581114b6a2f52b160fc20eb52c9 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 26 Feb 2026 15:10:54 +0200 Subject: [PATCH 0022/1518] staging: media: atomisp: Disallow all private IOCTLs commit 2b7eb2c5dc72f0fc954ac4aa155f9e285e937f7c upstream. Disallow all private IOCTLs. These aren't quite as safe as one could assume of IOCTL handlers; disable them for now. Instead of removing the code, return in the beginning of the function if cmd is non-zero in order to keep static checkers happy. Reported-by: Soufiane Dani Closes: https://lore.kernel.org/linux-staging/20260210-atomisp-fix-v1-1-024429cbff31@tutanota.com/ Cc: stable@vger.kernel.org Fixes: a49d25364dfb ("staging/atomisp: Add support for the Intel IPU v2") Fixes: ad85094b293e ("Revert "media: staging: atomisp: Remove driver"") Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/staging/media/atomisp/pci/atomisp_ioctl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c index bb8b2f2213b08..2907ef2a37ed0 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c +++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c @@ -1357,6 +1357,10 @@ static int atomisp_s_parm(struct file *file, void *fh, static long atomisp_vidioc_default(struct file *file, void *fh, bool valid_prio, unsigned int cmd, void *arg) { + /* Disable all private IOCTLs for now! */ + if (cmd) + return -EINVAL; + struct video_device *vdev = video_devdata(file); struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd; int err; From 2d51cfca84829ed26881b822c3cc55608c5ec487 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:52 +0200 Subject: [PATCH 0023/1518] regulator: mt6357: fix OF node reference imbalance commit 2f38e96c273e15f5e9f5d1fc2c0cbba703751602 upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: dafc7cde23dc ("regulator: add mt6357 regulator") Cc: stable@vger.kernel.org # 6.2 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-5-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/mt6357-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/mt6357-regulator.c b/drivers/regulator/mt6357-regulator.c index 1eb69c7a6acb3..09feb454ab6b8 100644 --- a/drivers/regulator/mt6357-regulator.c +++ b/drivers/regulator/mt6357-regulator.c @@ -410,7 +410,7 @@ static int mt6357_regulator_probe(struct platform_device *pdev) struct regulator_dev *rdev; int i; - pdev->dev.of_node = pdev->dev.parent->of_node; + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); for (i = 0; i < MT6357_MAX_REGULATOR; i++) { config.dev = &pdev->dev; From 8993d307cf2c055877ccbe5428c202149a48f4ab Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:47 +0200 Subject: [PATCH 0024/1518] spi: st-ssc4: fix controller deregistration commit 19857374010d06ca6a2f7c2c53464122eb804df0 upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 9e862375c542 ("spi: Add new driver for STMicroelectronics' SPI Controller") Cc: stable@vger.kernel.org # 4.0 Cc: Lee Jones Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-18-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-st-ssc4.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c index c07c61dc4938a..23a306901c0f5 100644 --- a/drivers/spi/spi-st-ssc4.c +++ b/drivers/spi/spi-st-ssc4.c @@ -349,7 +349,7 @@ static int spi_st_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) { dev_err(&pdev->dev, "Failed to register host\n"); goto rpm_disable; @@ -371,10 +371,16 @@ static void spi_st_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct spi_st *spi_st = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + pm_runtime_disable(&pdev->dev); clk_disable_unprepare(spi_st->clk); + spi_controller_put(host); + pinctrl_pm_select_sleep_state(&pdev->dev); } From a8ada5b761159698c11785e547427783596dfd5b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:51 +0200 Subject: [PATCH 0025/1518] regulator: max77650: fix OF node reference imbalance commit 2edaf5f7ada0ab5c9ec1f0836bd19779a8d85262 upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: bcc61f1c44fd ("regulator: max77650: add regulator support") Cc: stable@vger.kernel.org # 5.1 Reviewed-by: Bartosz Golaszewski Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-4-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/max77650-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/max77650-regulator.c b/drivers/regulator/max77650-regulator.c index 7368f54f046dc..99293bde33583 100644 --- a/drivers/regulator/max77650-regulator.c +++ b/drivers/regulator/max77650-regulator.c @@ -337,7 +337,7 @@ static int max77650_regulator_probe(struct platform_device *pdev) parent = dev->parent; if (!dev->of_node) - dev->of_node = parent->of_node; + device_set_of_node_from_dev(dev, parent); rdescs = devm_kcalloc(dev, MAX77650_REGULATOR_NUM_REGULATORS, sizeof(*rdescs), GFP_KERNEL); From 63a960b39de9c51f29ca19aa5067934f865c0bc7 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 11 Feb 2026 19:09:44 +0100 Subject: [PATCH 0026/1518] media: rc: xbox_remote: heed DMA restrictions commit e280d1e5e3f2595bbb43fe6e1bce00c59a43c0ff upstream. The buffer for IO must not be part of the device structure because that violates the DMA coherency rules. Fixes: 02d32bdad3123 ("media: rc: add driver for Xbox DVD Movie Playback Kit") Cc: stable@vger.kernel.org Signed-off-by: Oliver Neukum Signed-off-by: Sean Young Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/rc/xbox_remote.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/media/rc/xbox_remote.c b/drivers/media/rc/xbox_remote.c index a1572381d0971..0c9c855ced729 100644 --- a/drivers/media/rc/xbox_remote.c +++ b/drivers/media/rc/xbox_remote.c @@ -55,7 +55,7 @@ struct xbox_remote { struct usb_interface *interface; struct urb *irq_urb; - unsigned char inbuf[DATA_BUFSIZE] __aligned(sizeof(u16)); + u8 *inbuf; char rc_name[NAME_BUFSIZE]; char rc_phys[NAME_BUFSIZE]; @@ -218,6 +218,10 @@ static int xbox_remote_probe(struct usb_interface *interface, if (!xbox_remote || !rc_dev) goto exit_free_dev_rdev; + xbox_remote->inbuf = kzalloc(DATA_BUFSIZE, GFP_KERNEL); + if (!xbox_remote->inbuf) + goto exit_free_inbuf; + /* Allocate URB buffer */ xbox_remote->irq_urb = usb_alloc_urb(0, GFP_KERNEL); if (!xbox_remote->irq_urb) @@ -262,6 +266,8 @@ static int xbox_remote_probe(struct usb_interface *interface, usb_kill_urb(xbox_remote->irq_urb); exit_free_buffers: usb_free_urb(xbox_remote->irq_urb); +exit_free_inbuf: + kfree(xbox_remote->inbuf); exit_free_dev_rdev: rc_free_device(rc_dev); kfree(xbox_remote); @@ -286,6 +292,7 @@ static void xbox_remote_disconnect(struct usb_interface *interface) usb_kill_urb(xbox_remote->irq_urb); rc_unregister_device(xbox_remote->rdev); usb_free_urb(xbox_remote->irq_urb); + kfree(xbox_remote->inbuf); kfree(xbox_remote); } From ecd0c501bd630696244af69eb6a51f6b012a549c Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 11 Feb 2026 19:06:21 +0100 Subject: [PATCH 0027/1518] media: rc: streamzap: Error handling in probe commit 42844992664f03ef9f930e64f7370fa481e9c267 upstream. If submitting the URB fails, the device will be unusable. Probe() must fail. Fixes: 7a569f524dd36 ("V4L/DVB: IR/streamzap: functional in-kernel decoding") Cc: stable@vger.kernel.org Signed-off-by: Oliver Neukum Signed-off-by: Sean Young Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/rc/streamzap.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c index d3b48a0dd1f47..8e9b156e43002 100644 --- a/drivers/media/rc/streamzap.c +++ b/drivers/media/rc/streamzap.c @@ -219,9 +219,8 @@ static void streamzap_callback(struct urb *urb) case -ESHUTDOWN: /* * this urb is terminated, clean up. - * sz might already be invalid at this point */ - dev_err(sz->dev, "urb terminated, status: %d\n", urb->status); + dev_dbg(sz->dev, "urb terminated, status: %d\n", urb->status); return; default: break; @@ -358,11 +357,16 @@ static int streamzap_probe(struct usb_interface *intf, usb_set_intfdata(intf, sz); - if (usb_submit_urb(sz->urb_in, GFP_ATOMIC)) + retval = usb_submit_urb(sz->urb_in, GFP_ATOMIC); + if (retval < 0) { dev_err(sz->dev, "urb submit failed\n"); + goto rc_submit_fail; + } return 0; - +rc_submit_fail: + rc_free_device(sz->rdev); + usb_set_intfdata(intf, NULL); rc_dev_fail: usb_free_urb(sz->urb_in); free_buf_in: From 6c5d4c819d920b8af9e12bc7db7bfa96d8d1650b Mon Sep 17 00:00:00 2001 From: Jai Luthra Date: Sat, 14 Feb 2026 18:35:21 +0530 Subject: [PATCH 0028/1518] media: i2c: imx283: Enter full standby when stopping streaming commit bce1349dbf6348ddee47308e2ed08878356de317 upstream. Use IMX283_STANDBY (bit 0) instead of IMX283_STBLOGIC (bit 1) when stopping streaming. STBLOGIC only puts the sensor logic into standby but leaves the MIPI interface (along with other components) in an indeterminate state. This (presumably) causes the CSI receiver (e.g. Raspberry Pi's CFE) to miss the LP-11 to HS transition when streaming restarts, resulting in a hang of 10+ seconds. The issue is most visible when immediately restarting a full-resolution stream after stopping a 3x3 binned one, so that runtime suspend hasn't yet been triggered. Writing IMX283_STANDBY puts the entire sensor into standby. The imx283_standby_cancel() sequence already handles the full wakeup from this suspended state. Cc: stable@vger.kernel.org Link: https://github.com/raspberrypi/linux/issues/7153 Link: https://github.com/will127534/OneInchEye/issues/12 Fixes: ccb4eb4496fa ("media: i2c: Add imx283 camera sensor driver") Signed-off-by: Jai Luthra Tested-by: Kieran Bingham Reviewed-by: Kieran Bingham Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/imx283.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/imx283.c b/drivers/media/i2c/imx283.c index 8ab63ad8f385f..9b3094a57873c 100644 --- a/drivers/media/i2c/imx283.c +++ b/drivers/media/i2c/imx283.c @@ -1158,7 +1158,7 @@ static int imx283_disable_streams(struct v4l2_subdev *sd, if (pad != IMAGE_PAD) return -EINVAL; - ret = cci_write(imx283->cci, IMX283_REG_STANDBY, IMX283_STBLOGIC, NULL); + ret = cci_write(imx283->cci, IMX283_REG_STANDBY, IMX283_STANDBY, NULL); if (ret) dev_err(imx283->dev, "Failed to stop stream\n"); From e7374c14216988505e50fea6769c81cca748b211 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:49 +0200 Subject: [PATCH 0029/1518] regulator: bq257xx: fix OF node reference imbalance commit 7ea07bc030d8d6395524dec22ff3267441a28c0d upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: 981dd162b635 ("regulator: bq257xx: Add bq257xx boost regulator driver") Cc: stable@vger.kernel.org # 6.18 Cc: Chris Morgan Reviewed-by: Douglas Anderson Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-2-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/bq257xx-regulator.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/regulator/bq257xx-regulator.c b/drivers/regulator/bq257xx-regulator.c index dab8f1ab44503..711dbe045383c 100644 --- a/drivers/regulator/bq257xx-regulator.c +++ b/drivers/regulator/bq257xx-regulator.c @@ -142,8 +142,7 @@ static int bq257xx_regulator_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; struct regulator_config cfg = {}; - pdev->dev.of_node = pdev->dev.parent->of_node; - pdev->dev.of_node_reused = true; + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); pdata = devm_kzalloc(&pdev->dev, sizeof(struct bq257xx_reg_data), GFP_KERNEL); if (!pdata) From dd681c102b4bfea67e3f65ff48641a42cdc8c11f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:50 +0200 Subject: [PATCH 0030/1518] regulator: rk808: fix OF node reference imbalance commit 65290b24d8a5f0b8cd065201e653db824c4a4da6 upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: 647e57351f8e ("regulator: rk808: reduce 'struct rk808' usage") Cc: stable@vger.kernel.org # 6.2 Reviewed-by: Sebastian Reichel Reviewed-by: Douglas Anderson Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-3-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/rk808-regulator.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c index 1e8142479656a..94cfb66ae656c 100644 --- a/drivers/regulator/rk808-regulator.c +++ b/drivers/regulator/rk808-regulator.c @@ -1875,8 +1875,7 @@ static int rk808_regulator_probe(struct platform_device *pdev) struct regmap *regmap; int ret, i, nregulators; - pdev->dev.of_node = pdev->dev.parent->of_node; - pdev->dev.of_node_reused = true; + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); regmap = dev_get_regmap(pdev->dev.parent, NULL); if (!regmap) From 21fade52ab9fb13368a5709e60b0d9909197aeae Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Sun, 15 Feb 2026 18:42:59 +0100 Subject: [PATCH 0031/1518] media: videobuf2: Set vma_flags in vb2_dma_sg_mmap commit 7254b31a13aaa0c2c0f9ffbc335b718656117ff4 upstream. vb2_dma_contig sets VMA flags VM_DONTEXPAND and VM_DONTDUMP and I do not see a reason why vb2_dma_sg should behave differently. This avoids hitting `WARN_ON(!(vma->vm_flags & VM_DONTEXPAND));` in drm_gem_mmap_obj() during mmap() of an imported dma-buf from the out of tree Apple ISP camera capture driver which uses vb2_dma_sg_memops. gst-launch-1.0 v4l2src ! gtk4paintablesink [ 38.201528] ------------[ cut here ]------------ [ 38.202135] WARNING: CPU: 7 PID: 2362 at drivers/gpu/drm/drm_gem.c:1144 drm_gem_mmap_obj+0x1f8/0x210 [ 38.203278] Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device uinput nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables qrtr bnep nls_ascii i2c_dev loop fuse dm_multipath nfnetlink brcmfmac_wcc hid_magicmouse hci_bcm4377 brcmfmac brcmutil bluetooth ecdh_generic cfg80211 ecc btrfs xor xor_neon rfkill hid_apple raid6_pq joydev aop_als apple_nvmem_spmi industrialio snd_soc_aop apple_z2 snd_soc_cs42l84 tps6598x snd_soc_tas2764 macsmc_reboot spi_nor macsmc_hwmon rtc_macsmc gpio_macsmc macsmc_power regmap_spmi macsmc_input dockchannel_hid panel_summit appledrm nvme_apple dwc3 snd_soc_macaudio drm_client_lib nvme_core phy_apple_atc hwmon apple_sart apple_dockchannel macsmc apple_rtkit_helper spmi_apple_controller aop apple_wdt mfd_core nvmem_apple_efuses pinctrl_apple_gpio apple_isp apple_dcp videobuf2_dma_sg mux_core spi_apple [ 38.203300] videobuf2_memops i2c_pasemi_platform snd_soc_apple_mca videobuf2_v4l2 videodev clk_apple_nco videobuf2_common snd_pcm_dmaengine adpdrm asahi apple_admac adpdrm_mipi drm_dma_helper pwm_apple i2c_pasemi_core drm_display_helper mc cec apple_dart ofpart apple_soc_cpufreq leds_pwm phram [ 38.217677] CPU: 7 UID: 1000 PID: 2362 Comm: gst-launch-1.0 Tainted: G W 6.17.6+ #asahi-dev PREEMPT(full) [ 38.219040] Tainted: [W]=WARN [ 38.219398] Hardware name: Apple MacBook Pro (13-inch, M2, 2022) (DT) [ 38.220213] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 38.221088] pc : drm_gem_mmap_obj+0x1f8/0x210 [ 38.221643] lr : drm_gem_mmap_obj+0x78/0x210 [ 38.222178] sp : ffffc0008dc678e0 [ 38.222579] x29: ffffc0008dc678e0 x28: 0000000000042a97 x27: ffff8000b701b480 [ 38.223465] x26: 00000000000000fb x25: ffffc0008dc67d20 x24: ffffc0008dc67968 [ 38.224402] x23: ffff8000e3ca5600 x22: ffff8000265b7800 x21: ffff80003000c0c0 [ 38.225279] x20: 0000000000000000 x19: ffff8000b68c5200 x18: ffffc0008dc67968 [ 38.226151] x17: 0000000000000000 x16: 0000000000000000 x15: ffffc000810a30a8 [ 38.227042] x14: 00007fff637effff x13: 00005555de91ffff x12: 00007fff63293fff [ 38.227942] x11: 0000000000000000 x10: ffff8000184ecf08 x9 : ffffc0007a1900c8 [ 38.228824] x8 : ffffc0008dc67968 x7 : 0000000000000012 x6 : ffffc0015cf1c000 [ 38.229703] x5 : ffffc0008dc676a0 x4 : ffffc00081a27dc0 x3 : 0000000000000038 [ 38.230607] x2 : 0000000000000003 x1 : 0000000000000003 x0 : 00000000100000fb [ 38.231488] Call trace: [ 38.231806] drm_gem_mmap_obj+0x1f8/0x210 (P) [ 38.232342] drm_gem_mmap+0x140/0x260 [ 38.232813] __mmap_region+0x488/0x9a0 [ 38.233277] mmap_region+0xd0/0x148 [ 38.233703] do_mmap+0x350/0x5c0 [ 38.234148] vm_mmap_pgoff+0x14c/0x200 [ 38.234612] ksys_mmap_pgoff+0x150/0x208 [ 38.235107] __arm64_sys_mmap+0x34/0x50 [ 38.235611] invoke_syscall+0x50/0x120 [ 38.236075] el0_svc_common.constprop.0+0x48/0xf0 [ 38.236680] do_el0_svc+0x24/0x38 [ 38.237113] el0_svc+0x38/0x168 [ 38.237507] el0t_64_sync_handler+0xa0/0xe8 [ 38.238034] el0t_64_sync+0x198/0x1a0 [ 38.238491] ---[ end trace 0000000000000000 ]--- There were discussions in [1] at the end of 2023 that mmap() on imported dma-bufs should not be supported but as of v6.17 drm_gem_shmem_mmap() in drm_gem_shmem_helper.c still supports it. This might affect all gpu or accel drivers using drm_gem_shmem_mmap() or the wrapper drm_gem_shmem_object_mmap(). [1] https://lore.kernel.org/dri-devel/bc7f7844-0aa3-4802-b203-69d58e8be2fa@linux.intel.com/ Cc: stable@vger.kernel.org Fixes: 5ba3f757f059 ("[media] v4l: videobuf2: add DMA scatter/gather allocator") Signed-off-by: Janne Grunau Acked-by: Marek Szyprowski Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/common/videobuf2/videobuf2-dma-sg.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index b3bf2173c14e1..7c30731cb9a57 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -345,6 +345,7 @@ static int vb2_dma_sg_mmap(void *buf_priv, struct vm_area_struct *vma) return err; } + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); /* * Use common vm_area operations to track buffer refcount. */ From f43e30646fc93799f3f48530d0ccbd52902c0541 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Fri, 6 Mar 2026 21:03:55 -0600 Subject: [PATCH 0032/1518] media: intel/ipu6: fix error pointer dereference commit 8dd088b8b106f7b119664f965b691785998edcfb upstream. In a error path isp->psys is confirmed to be an error pointer not NULL so this condition is true and the error pointer is dereferenced. So isp-psys should be set to NULL before going to out_ipu6_bus_del_devices. Detected by Smatch: drivers/media/pci/intel/ipu6/ipu6.c:690 ipu6_pci_probe() error: 'isp->psys' dereferencing possible ERR_PTR() Fixes: 25fedc021985a ("media: intel/ipu6: add Intel IPU6 PCI device driver") Cc: stable@vger.kernel.org Signed-off-by: Ethan Tidmore [Sakari Ailus: Fix commit message.] Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/pci/intel/ipu6/ipu6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/intel/ipu6/ipu6.c b/drivers/media/pci/intel/ipu6/ipu6.c index a2768f44017a5..fab7783c664b9 100644 --- a/drivers/media/pci/intel/ipu6/ipu6.c +++ b/drivers/media/pci/intel/ipu6/ipu6.c @@ -686,7 +686,7 @@ static int ipu6_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) out_ipu6_rpm_put: pm_runtime_put_sync(&isp->psys->auxdev.dev); out_ipu6_bus_del_devices: - if (isp->psys) { + if (!IS_ERR_OR_NULL(isp->psys)) { ipu6_cpd_free_pkg_dir(isp->psys); ipu6_buttress_unmap_fw_image(isp->psys, &isp->psys->fw_sgt); } From 41ef27dcaa12302ad536043f6791e0fd08bc8e29 Mon Sep 17 00:00:00 2001 From: Jai Luthra Date: Sat, 14 Feb 2026 18:35:22 +0530 Subject: [PATCH 0033/1518] media: i2c: imx283: Fix hang when going from large to small resolution commit 9206359b2c396ff594adf39bc7daaadab0fcb367 upstream. When switching between modes (e.g. full resolution to binned), standby_cancel() previously cleared XMSTA (starting master mode data output) before the new mode's MDSEL, crop, and timing registers were programmed in start_streaming(). This caused the sensor to briefly output MIPI data using the previous mode's configuration. On receivers like imx-mipi-csis, this leads to FIFO overflow errors when switching from a higher to a lower resolution, as the receiver is configured for the new smaller frame size but receives stale full-resolution data. Fix this by moving the XMSTA and SYNCDRV register writes from standby_cancel() to the end of start_streaming(), after all mode, crop, and timing registers have been configured. Also explicitly stop master mode (XMSTA=1) when stopping the stream, matching the pattern used by other Sony sensor drivers (imx290, imx415). Use named macros IMX283_XMSTA_START/STOP instead of raw 0/BIT(0) for readability. Cc: stable@vger.kernel.org Fixes: ccb4eb4496fa ("media: i2c: Add imx283 camera sensor driver") Signed-off-by: Jai Luthra Tested-by: Kieran Bingham Reviewed-by: Kieran Bingham Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/imx283.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/media/i2c/imx283.c b/drivers/media/i2c/imx283.c index 9b3094a57873c..1be6164c2d155 100644 --- a/drivers/media/i2c/imx283.c +++ b/drivers/media/i2c/imx283.c @@ -129,7 +129,8 @@ /* Master Mode Operation Control */ #define IMX283_REG_XMSTA CCI_REG8(0x3105) -#define IMX283_XMSTA BIT(0) +#define IMX283_XMSTA_START 0 +#define IMX283_XMSTA_STOP BIT(0) #define IMX283_REG_SYNCDRV CCI_REG8(0x3107) #define IMX283_SYNCDRV_XHS_XVS (0xa0 | 0x02) @@ -1023,8 +1024,6 @@ static int imx283_standby_cancel(struct imx283 *imx283) usleep_range(19000, 20000); cci_write(imx283->cci, IMX283_REG_CLAMP, IMX283_CLPSQRST, &ret); - cci_write(imx283->cci, IMX283_REG_XMSTA, 0, &ret); - cci_write(imx283->cci, IMX283_REG_SYNCDRV, IMX283_SYNCDRV_XHS_XVS, &ret); return ret; } @@ -1117,6 +1116,10 @@ static int imx283_start_streaming(struct imx283 *imx283, /* Apply customized values from controls (HMAX/VMAX/SHR) */ ret = __v4l2_ctrl_handler_setup(imx283->sd.ctrl_handler); + /* Start master mode */ + cci_write(imx283->cci, IMX283_REG_XMSTA, IMX283_XMSTA_START, &ret); + cci_write(imx283->cci, IMX283_REG_SYNCDRV, IMX283_SYNCDRV_XHS_XVS, &ret); + return ret; } @@ -1153,12 +1156,14 @@ static int imx283_disable_streams(struct v4l2_subdev *sd, u64 streams_mask) { struct imx283 *imx283 = to_imx283(sd); - int ret; + int ret = 0; if (pad != IMAGE_PAD) return -EINVAL; - ret = cci_write(imx283->cci, IMX283_REG_STANDBY, IMX283_STANDBY, NULL); + cci_write(imx283->cci, IMX283_REG_XMSTA, IMX283_XMSTA_STOP, &ret); + cci_write(imx283->cci, IMX283_REG_STANDBY, IMX283_STANDBY, &ret); + if (ret) dev_err(imx283->dev, "Failed to stop stream\n"); From 890a8bcef3090f715c64b4c10f09e26aae9a60ab Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:54 +0200 Subject: [PATCH 0034/1518] regulator: act8945a: fix OF node reference imbalance commit 0d15ce31375ccef4162f960b34547a821b7619d2 upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: 38c09961048b ("regulator: act8945a: add regulator driver for ACT8945A") Cc: stable@vger.kernel.org # 4.6 Cc: Wenyou Yang Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-7-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/act8945a-regulator.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/act8945a-regulator.c b/drivers/regulator/act8945a-regulator.c index 24cbdd8338630..5bbe2bce740ea 100644 --- a/drivers/regulator/act8945a-regulator.c +++ b/drivers/regulator/act8945a-regulator.c @@ -302,8 +302,9 @@ static int act8945a_pmic_probe(struct platform_device *pdev) num_regulators = ARRAY_SIZE(act8945a_regulators); } + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); + config.dev = &pdev->dev; - config.dev->of_node = pdev->dev.parent->of_node; config.driver_data = act8945a; for (i = 0; i < num_regulators; i++) { rdev = devm_regulator_register(&pdev->dev, ®ulators[i], From 037bcca27835a2e28aea866b44777d57d7961414 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:53 +0200 Subject: [PATCH 0035/1518] regulator: s2dos05: fix OF node reference imbalance commit ebe694d67f159899b063eee61bacda4cb825ed7b upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: bb2441402392 ("regulator: add s2dos05 regulator support") Cc: stable@vger.kernel.org # 6.18 Cc: Dzmitry Sankouski Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-6-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/s2dos05-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/s2dos05-regulator.c b/drivers/regulator/s2dos05-regulator.c index 1463585c45652..a1c394ddbaff6 100644 --- a/drivers/regulator/s2dos05-regulator.c +++ b/drivers/regulator/s2dos05-regulator.c @@ -126,7 +126,7 @@ static int s2dos05_pmic_probe(struct platform_device *pdev) s2dos05->regmap = iodev->regmap_pmic; s2dos05->dev = dev; if (!dev->of_node) - dev->of_node = dev->parent->of_node; + device_set_of_node_from_dev(dev, dev->parent); config.dev = dev; config.driver_data = s2dos05; From 184dcecc952124ee8ee280d890f7c658e9305e33 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Apr 2026 09:30:55 +0200 Subject: [PATCH 0036/1518] regulator: bd9571mwv: fix OF node reference imbalance commit 8498100ee1d00422b8c5b161b3e332278b92a59a upstream. The driver reuses the OF node of the parent multi-function device but fails to take another reference to balance the one dropped by the platform bus code when unbinding the MFD and deregistering the child devices. Fix this by using the intended helper for reusing OF nodes. Fixes: e85c5a153fe2 ("regulator: Add ROHM BD9571MWV-M PMIC regulator driver") Cc: stable@vger.kernel.org # 4.12 Cc: Marek Vasut Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260408073055.5183-8-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/bd9571mwv-regulator.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c index 209beabb5c37c..f4de24a281b12 100644 --- a/drivers/regulator/bd9571mwv-regulator.c +++ b/drivers/regulator/bd9571mwv-regulator.c @@ -287,8 +287,9 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev) platform_set_drvdata(pdev, bdreg); + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); + config.dev = &pdev->dev; - config.dev->of_node = pdev->dev.parent->of_node; config.driver_data = bdreg; config.regmap = bdreg->regmap; From 6ca3eaa82812f7f8df89241e8232a450a6cc01c1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:15 +0200 Subject: [PATCH 0037/1518] spi: lantiq-ssc: fix controller deregistration commit b99206710d032c16b7f8b75e4bc18414d8e4b9f4 upstream. Make sure to deregister the controller before releasing underlying resources like clocks during driver unbind. Fixes: 17f84b793c01 ("spi: lantiq-ssc: add support for Lantiq SSC SPI controller") Cc: stable@vger.kernel.org # 4.11 Cc: Hauke Mehrtens Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-17-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-lantiq-ssc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-lantiq-ssc.c b/drivers/spi/spi-lantiq-ssc.c index 60849e07f674a..97dbd58244b1d 100644 --- a/drivers/spi/spi-lantiq-ssc.c +++ b/drivers/spi/spi-lantiq-ssc.c @@ -995,7 +995,7 @@ static int lantiq_ssc_probe(struct platform_device *pdev) "Lantiq SSC SPI controller (Rev %i, TXFS %u, RXFS %u, DMA %u)\n", revision, spi->tx_fifo_size, spi->rx_fifo_size, supports_dma); - err = devm_spi_register_controller(dev, host); + err = spi_register_controller(host); if (err) { dev_err(dev, "failed to register spi host\n"); goto err_wq_destroy; @@ -1017,6 +1017,10 @@ static void lantiq_ssc_remove(struct platform_device *pdev) { struct lantiq_ssc_spi *spi = platform_get_drvdata(pdev); + spi_controller_get(spi->host); + + spi_unregister_controller(spi->host); + lantiq_ssc_writel(spi, 0, LTQ_SPI_IRNEN); lantiq_ssc_writel(spi, 0, LTQ_SPI_CLC); rx_fifo_flush(spi); @@ -1025,6 +1029,8 @@ static void lantiq_ssc_remove(struct platform_device *pdev) destroy_workqueue(spi->wq); clk_put(spi->fpi_clk); + + spi_controller_put(spi->host); } static struct platform_driver lantiq_ssc_driver = { From 4eccd83f228f1a59bdc2a135c824f9d23fd00275 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:16 +0200 Subject: [PATCH 0038/1518] spi: meson-spicc: fix controller deregistration commit 77953c76bec9af4191f8692a10225dd816208718 upstream. Make sure to deregister the controller before disabling it to allow SPI device drivers to do I/O during deregistration. Fixes: 454fa271bc4e ("spi: Add Meson SPICC driver") Cc: stable@vger.kernel.org # 4.13 Cc: Neil Armstrong Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-18-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-meson-spicc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c index c99fab392add1..bb27a3b2bbc21 100644 --- a/drivers/spi/spi-meson-spicc.c +++ b/drivers/spi/spi-meson-spicc.c @@ -1082,7 +1082,7 @@ static int meson_spicc_probe(struct platform_device *pdev) } } - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) { dev_err(&pdev->dev, "spi registration failed\n"); goto out_host; @@ -1100,8 +1100,14 @@ static void meson_spicc_remove(struct platform_device *pdev) { struct meson_spicc_device *spicc = platform_get_drvdata(pdev); + spi_controller_get(spicc->host); + + spi_unregister_controller(spicc->host); + /* Disable SPI */ writel(0, spicc->base + SPICC_CONREG); + + spi_controller_put(spicc->host); } static const struct meson_spicc_data meson_spicc_gx_data = { From 5d707cf9c1386cdbecc6a3a42bdae413b7bf71ac Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:39 +0200 Subject: [PATCH 0039/1518] spi: qup: fix controller deregistration commit 443e3a0005a4342b218b6dbd4c6387d3c7fed85a upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 64ff247a978f ("spi: Add Qualcomm QUP SPI controller support") Cc: stable@vger.kernel.org # 3.15 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-10-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-qup.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index 7d647edf6bc31..a5c549479c7d1 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -1194,7 +1194,7 @@ static int spi_qup_probe(struct platform_device *pdev) pm_runtime_set_active(dev); pm_runtime_enable(dev); - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) goto disable_pm; @@ -1321,6 +1321,10 @@ static void spi_qup_remove(struct platform_device *pdev) struct spi_qup *controller = spi_controller_get_devdata(host); int ret; + spi_controller_get(host); + + spi_unregister_controller(host); + ret = pm_runtime_get_sync(&pdev->dev); if (ret >= 0) { @@ -1340,6 +1344,8 @@ static void spi_qup_remove(struct platform_device *pdev) pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + + spi_controller_put(host); } static const struct of_device_id spi_qup_dt_match[] = { From d6f56e66e8f4be148e2ca483704cce52932d20e6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:02 +0200 Subject: [PATCH 0040/1518] spi: at91-usart: fix controller deregistration commit 9acecc9bcff058eaef40fd7a4c3650e88b06b220 upstream. Make sure to deregister the controller before disabling and releasing underlying resources like clocks and DMA during driver unbind. Fixes: e1892546ff66 ("spi: at91-usart: Add driver for at91-usart as SPI") Cc: stable@vger.kernel.org # 4.20 Cc: Radu Pirea Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-4-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-at91-usart.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-at91-usart.c b/drivers/spi/spi-at91-usart.c index bbe97ce89a2fd..3617f538f98e2 100644 --- a/drivers/spi/spi-at91-usart.c +++ b/drivers/spi/spi-at91-usart.c @@ -556,7 +556,7 @@ static int at91_usart_spi_probe(struct platform_device *pdev) spin_lock_init(&aus->lock); init_completion(&aus->xfer_completion); - ret = devm_spi_register_controller(&pdev->dev, controller); + ret = spi_register_controller(controller); if (ret) goto at91_usart_fail_register_controller; @@ -634,8 +634,14 @@ static void at91_usart_spi_remove(struct platform_device *pdev) struct spi_controller *ctlr = platform_get_drvdata(pdev); struct at91_usart_spi *aus = spi_controller_get_devdata(ctlr); + spi_controller_get(ctlr); + + spi_unregister_controller(ctlr); + at91_usart_spi_release_dma(ctlr); clk_disable_unprepare(aus->clk); + + spi_controller_put(ctlr); } static const struct dev_pm_ops at91_usart_spi_pm_ops = { From 6047dc542fa404b5c187cc2c7906aaaaec6d11ed Mon Sep 17 00:00:00 2001 From: Wang Jun <1742789905@qq.com> Date: Mon, 16 Mar 2026 20:24:01 +0800 Subject: [PATCH 0041/1518] media: saa7164: add ioremap return checks and cleanups commit d51c60a498e83c9a79884c8e420f97e3885c9583 upstream. Add checks for ioremap return values in saa7164_dev_setup(). If ioremap for BAR0 or BAR2 fails, release the already allocated PCI memory regions, remove the device from the global list, decrement the device count, and return -ENODEV. This prevents potential null pointer dereferences and ensures proper cleanup on memory mapping failures. Fixes: 443c1228d505 ("V4L/DVB (12923): SAA7164: Add support for the NXP SAA7164 silicon") Cc: stable@vger.kernel.org Signed-off-by: Wang Jun <1742789905@qq.com> Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/pci/saa7164/saa7164-core.c | 47 ++++++++++++++++++------ 1 file changed, 35 insertions(+), 12 deletions(-) diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c index a8a004f28ca0e..ac290f5464131 100644 --- a/drivers/media/pci/saa7164/saa7164-core.c +++ b/drivers/media/pci/saa7164/saa7164-core.c @@ -888,6 +888,15 @@ static int get_resources(struct saa7164_dev *dev) return -EBUSY; } +static void release_resources(struct saa7164_dev *dev) +{ + release_mem_region(pci_resource_start(dev->pci, 0), + pci_resource_len(dev->pci, 0)); + + release_mem_region(pci_resource_start(dev->pci, 2), + pci_resource_len(dev->pci, 2)); +} + static int saa7164_port_init(struct saa7164_dev *dev, int portnr) { struct saa7164_port *port = NULL; @@ -947,9 +956,9 @@ static int saa7164_dev_setup(struct saa7164_dev *dev) snprintf(dev->name, sizeof(dev->name), "saa7164[%d]", dev->nr); - mutex_lock(&devlist); - list_add_tail(&dev->devlist, &saa7164_devlist); - mutex_unlock(&devlist); + scoped_guard(mutex, &devlist) { + list_add_tail(&dev->devlist, &saa7164_devlist); + } /* board config */ dev->board = UNSET; @@ -996,11 +1005,17 @@ static int saa7164_dev_setup(struct saa7164_dev *dev) } /* PCI/e allocations */ - dev->lmmio = ioremap(pci_resource_start(dev->pci, 0), - pci_resource_len(dev->pci, 0)); + dev->lmmio = pci_ioremap_bar(dev->pci, 0); + if (!dev->lmmio) { + dev_err(&dev->pci->dev, "Failed to remap MMIO BAR 0\n"); + goto err_ioremap_bar0; + } - dev->lmmio2 = ioremap(pci_resource_start(dev->pci, 2), - pci_resource_len(dev->pci, 2)); + dev->lmmio2 = pci_ioremap_bar(dev->pci, 2); + if (!dev->lmmio2) { + dev_err(&dev->pci->dev, "Failed to remap MMIO BAR 2\n"); + goto err_ioremap_bar2; + } dev->bmmio = (u8 __iomem *)dev->lmmio; dev->bmmio2 = (u8 __iomem *)dev->lmmio2; @@ -1019,17 +1034,25 @@ static int saa7164_dev_setup(struct saa7164_dev *dev) saa7164_pci_quirks(dev); return 0; + +err_ioremap_bar2: + iounmap(dev->lmmio); +err_ioremap_bar0: + release_resources(dev); + + scoped_guard(mutex, &devlist) { + list_del(&dev->devlist); + } + saa7164_devcount--; + + return -ENODEV; } static void saa7164_dev_unregister(struct saa7164_dev *dev) { dprintk(1, "%s()\n", __func__); - release_mem_region(pci_resource_start(dev->pci, 0), - pci_resource_len(dev->pci, 0)); - - release_mem_region(pci_resource_start(dev->pci, 2), - pci_resource_len(dev->pci, 2)); + release_resources(dev); if (!atomic_dec_and_test(&dev->refcount)) return; From 07938829cc11e6979e710db88f20a1a42c42918f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:00 +0200 Subject: [PATCH 0042/1518] spi: amlogic-spisg: fix controller deregistration commit 84d31bb1f6256eea0db6cf64a3c7a53145f92bb9 upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: cef9991e04ae ("spi: Add Amlogic SPISG driver") Cc: stable@vger.kernel.org # 6.17: b8db95529979 Cc: stable@vger.kernel.org # 6.17 Cc: Sunny Luo Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-2-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-amlogic-spisg.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-amlogic-spisg.c b/drivers/spi/spi-amlogic-spisg.c index 6045c89c37c83..56a6cf8471b9f 100644 --- a/drivers/spi/spi-amlogic-spisg.c +++ b/drivers/spi/spi-amlogic-spisg.c @@ -801,7 +801,7 @@ static int aml_spisg_probe(struct platform_device *pdev) goto out_clk; } - ret = devm_spi_register_controller(dev, ctlr); + ret = spi_register_controller(ctlr); if (ret) { dev_err(&pdev->dev, "spi controller registration failed\n"); goto out_clk; @@ -824,6 +824,8 @@ static void aml_spisg_remove(struct platform_device *pdev) { struct spisg_device *spisg = platform_get_drvdata(pdev); + spi_unregister_controller(spisg->controller); + if (!pm_runtime_suspended(&pdev->dev)) { pinctrl_pm_select_sleep_state(&spisg->pdev->dev); clk_disable_unprepare(spisg->core); From 45890a035e2b789b88ea2dfe8180a02a68850bca Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:01 +0200 Subject: [PATCH 0043/1518] spi: aspeed-smc: fix controller deregistration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1044e5a4ccd57bf5a64f90100a321b498e0267a2 upstream. Make sure to deregister the controller before disabling it to allow SPI device drivers to do I/O during deregistration. Fixes: e3228ed92893 ("spi: spi-mem: Convert Aspeed SMC driver to spi-mem") Cc: stable@vger.kernel.org # 5.19 Cc: Cédric Le Goater Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-3-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-aspeed-smc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c index 62a11142bd63c..04eebb65cfa64 100644 --- a/drivers/spi/spi-aspeed-smc.c +++ b/drivers/spi/spi-aspeed-smc.c @@ -726,7 +726,7 @@ static int aspeed_spi_probe(struct platform_device *pdev) return -ENOMEM; aspi = spi_controller_get_devdata(ctlr); - platform_set_drvdata(pdev, aspi); + platform_set_drvdata(pdev, ctlr); aspi->data = data; aspi->dev = dev; @@ -765,7 +765,7 @@ static int aspeed_spi_probe(struct platform_device *pdev) ctlr->num_chipselect = data->max_cs; ctlr->dev.of_node = dev->of_node; - ret = devm_spi_register_controller(dev, ctlr); + ret = spi_register_controller(ctlr); if (ret) dev_err(&pdev->dev, "spi_register_controller failed\n"); @@ -774,7 +774,10 @@ static int aspeed_spi_probe(struct platform_device *pdev) static void aspeed_spi_remove(struct platform_device *pdev) { - struct aspeed_spi *aspi = platform_get_drvdata(pdev); + struct spi_controller *ctlr = platform_get_drvdata(pdev); + struct aspeed_spi *aspi = spi_controller_get_devdata(ctlr); + + spi_unregister_controller(ctlr); aspeed_spi_enable(aspi, false); } From 75c38af4d919ffbf1ea7931683d6ab2e0b648c7b Mon Sep 17 00:00:00 2001 From: Krishna Chomal Date: Fri, 3 Apr 2026 13:31:55 +0530 Subject: [PATCH 0044/1518] platform/x86: hp-wmi: Ignore backlight and FnLock events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e8c597368b8500a824c639bfb5ed0044068c6870 upstream. On HP OmniBook 7 the keyboard backlight and FnLock keys are handled directly by the firmware. However, they still trigger WMI events which results in "Unknown key code" warnings in dmesg. Add these key codes to the keymap with KE_IGNORE to silence the warnings since no software action is needed. Tested-by: Artem S. Tashkinov Reported-by: Artem S. Tashkinov Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221181 Signed-off-by: Krishna Chomal Link: https://patch.msgid.link/20260403080155.169653-1-krishna.chomal108@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/hp/hp-wmi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 31d099bd8db43..550d4b39a92af 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -362,6 +362,11 @@ static const struct key_entry hp_wmi_keymap[] = { { KE_KEY, 0x21a9, { KEY_TOUCHPAD_OFF } }, { KE_KEY, 0x121a9, { KEY_TOUCHPAD_ON } }, { KE_KEY, 0x231b, { KEY_HELP } }, + { KE_IGNORE, 0x21ab, }, /* FnLock on */ + { KE_IGNORE, 0x121ab, }, /* FnLock off */ + { KE_IGNORE, 0x30021aa, }, /* kbd backlight: level 2 -> off */ + { KE_IGNORE, 0x33221aa, }, /* kbd backlight: off -> level 1 */ + { KE_IGNORE, 0x36421aa, }, /* kbd backlight: level 1 -> level 2*/ { KE_END, 0 } }; From 5167575b79e25187242a77ea5d90f8bfc2e563bc Mon Sep 17 00:00:00 2001 From: Luigi Leonardi Date: Wed, 15 Apr 2026 17:09:28 +0200 Subject: [PATCH 0045/1518] vsock/virtio: fix MSG_PEEK ignoring skb offset when calculating bytes to copy commit 080f22f5d30233faf3d83be3098f35b8be9b7a00 upstream. `virtio_transport_stream_do_peek()` does not account for the skb offset when computing the number of bytes to copy. This means that, after a partial recv() that advances the offset, a peek requesting more bytes than are available in the sk_buff causes `skb_copy_datagram_iter()` to go past the valid payload, resulting in a -EFAULT. The dequeue path already handles this correctly. Apply the same logic to the peek path. Fixes: 0df7cd3c13e4 ("vsock/virtio/vhost: read data from non-linear skb") Reviewed-by: Stefano Garzarella Acked-by: Arseniy Krasnov Signed-off-by: Luigi Leonardi Link: https://patch.msgid.link/20260415-fix_peek-v4-1-8207e872759e@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/virtio_transport_common.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index d3e26025ef589..a807a4aa62d3f 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -546,9 +546,8 @@ virtio_transport_stream_do_peek(struct vsock_sock *vsk, skb_queue_walk(&vvs->rx_queue, skb) { size_t bytes; - bytes = len - total; - if (bytes > skb->len) - bytes = skb->len; + bytes = min_t(size_t, len - total, + skb->len - VIRTIO_VSOCK_SKB_CB(skb)->offset); spin_unlock_bh(&vvs->rx_lock); From 65d7b2aecdfee65a0c85232c4d0bc130b7e5b965 Mon Sep 17 00:00:00 2001 From: Gregor Herburger Date: Thu, 26 Feb 2026 09:55:58 +0100 Subject: [PATCH 0046/1518] arm64: dts: broadcom: bcm2712-d-rpi-5-b: add fixes for pinctrl/pinctrl_aon commit aeb078cebc40d421f61a8f07b0e7919aeb44d751 upstream. On the -d revision of the bcm2712 the pinctrl differs from the c0 revision. The driver already supports both and distinguishes the two with the compatible string. Update the compatible string and reg length to reflect the different pinctrl. Signed-off-by: Gregor Herburger Link: https://lore.kernel.org/r/20260226-raspi-dts-updates-v1-5-60832d20ff04@linutronix.de Signed-off-by: Florian Fainelli Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts b/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts index 7de24d60bcd1a..cbfc82d884c82 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts @@ -35,3 +35,13 @@ "PMIC_SCL", // AON_SGPIO_04 "PMIC_SDA"; // AON_SGPIO_05 }; + +&pinctrl { + compatible = "brcm,bcm2712d0-pinctrl"; + reg = <0x7d504100 0x20>; +}; + +&pinctrl_aon { + compatible = "brcm,bcm2712d0-aon-pinctrl"; + reg = <0x7d510700 0x1c>; +}; From 84d7810692941169a671b587ce021fac9c4da294 Mon Sep 17 00:00:00 2001 From: Gregor Herburger Date: Thu, 26 Feb 2026 09:55:59 +0100 Subject: [PATCH 0047/1518] arm64: dts: broadcom: bcm2712-d-rpi-5-b: update uart10 interrupt commit 18d4a06e10051681de074a9250e54afc1f3ee312 upstream. On the -d revision of bcm2712 the uart interrupt is on 120. Update it accordingly. Signed-off-by: Gregor Herburger Link: https://lore.kernel.org/r/20260226-raspi-dts-updates-v1-6-60832d20ff04@linutronix.de Signed-off-by: Florian Fainelli Cc: Rasmus Villemoes Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts b/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts index cbfc82d884c82..127be0fc27c22 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2712-d-rpi-5-b.dts @@ -45,3 +45,7 @@ compatible = "brcm,bcm2712d0-aon-pinctrl"; reg = <0x7d510700 0x1c>; }; + +&uart10 { + interrupts = ; +}; From def939175ab8e4b13713481c4182217026e8c7e2 Mon Sep 17 00:00:00 2001 From: Abdun Nihaal Date: Thu, 12 Mar 2026 18:02:56 +0530 Subject: [PATCH 0048/1518] media: pci: zoran: fix potential memory leak in zoran_probe() commit 8ea21435fe36fb853706f4935d78bc11beb63fb4 upstream. The memory allocated for codec in videocodec_attach() is not freed in one of the error paths, due to an incorrect goto label. Fix the label to free it on error. Fixes: 8f7cc5c0b0eb ("media: staging: media: zoran: introduce zoran_i2c_init") Cc: stable@vger.kernel.org Signed-off-by: Abdun Nihaal Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/pci/zoran/zoran_card.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/zoran/zoran_card.c b/drivers/media/pci/zoran/zoran_card.c index d81facf735d92..f707bdc1fb0f1 100644 --- a/drivers/media/pci/zoran/zoran_card.c +++ b/drivers/media/pci/zoran/zoran_card.c @@ -1373,7 +1373,7 @@ static int zoran_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } if (zr->codec->type != zr->card.video_codec) { pci_err(pdev, "%s - wrong codec\n", __func__); - goto zr_unreg_videocodec; + goto zr_detach_codec; } } if (zr->card.video_vfe != 0) { From 34fe9c3c594e515f4668ea4b2233bb5b1ef8d6fd Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Fri, 6 Feb 2026 17:22:26 +0300 Subject: [PATCH 0049/1518] media: dib8000: avoid division by 0 in dib8000_set_dds() commit dde3c37af95cd6fa301c4906f33d627bc9dd874c upstream. In dib8000_set_dds(), 1 << 26 (67108864) divided by e.g. 1 apparently can't fit into 16-bit variable unit_khz_dds_val, being truncated to 0; this will cause division by 0 while calling dprintk() with debugging enabled (via the module parameter). Use s32 instead of s16 to declare the variable, getting rid of the cast to u16 in the *else* branch as well... Found by Linux Verification Center (linuxtesting.org) with the Svace static analysis tool. Fixes: 173a64cb3fcf ("[media] dib8000: enhancement") Cc: stable@vger.kernel.org Signed-off-by: Sergey Shtylyov Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-frontends/dib8000.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c index d90f1b0b2051c..f4e963cdb7f2d 100644 --- a/drivers/media/dvb-frontends/dib8000.c +++ b/drivers/media/dvb-frontends/dib8000.c @@ -2695,7 +2695,7 @@ static void dib8000_viterbi_state(struct dib8000_state *state, u8 onoff) static void dib8000_set_dds(struct dib8000_state *state, s32 offset_khz) { - s16 unit_khz_dds_val; + s32 unit_khz_dds_val; u32 abs_offset_khz = abs(offset_khz); u32 dds = state->cfg.pll->ifreq & 0x1ffffff; u8 invert = !!(state->cfg.pll->ifreq & (1 << 25)); @@ -2716,7 +2716,7 @@ static void dib8000_set_dds(struct dib8000_state *state, s32 offset_khz) dds = (1<<26) - dds; } else { ratio = 2; - unit_khz_dds_val = (u16) (67108864 / state->cfg.pll->internal); + unit_khz_dds_val = 67108864 / state->cfg.pll->internal; if (offset_khz < 0) unit_khz_dds_val *= -1; From 731d7ab8dfa2cdd197e4f77c121fd910fcdc9884 Mon Sep 17 00:00:00 2001 From: Wenmeng Liu Date: Fri, 23 Jan 2026 17:19:55 +0800 Subject: [PATCH 0050/1518] media: i2c: imx412: Assert reset GPIO during probe commit 8467c5ff5acae28513bc1e0af535e06b41b04344 upstream. Assert the reset GPIO before first power up. This avoids a mismatch where the first power up (when the reset GPIO defaults deasserted) differs from subsequent cycles. Signed-off-by: Wenmeng Liu Fixes: 9214e86c0cc1 ("media: i2c: Add imx412 camera sensor driver") Cc: stable@vger.kernel.org Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/imx412.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c index 7bbd639a9ddfa..5656b581a7172 100644 --- a/drivers/media/i2c/imx412.c +++ b/drivers/media/i2c/imx412.c @@ -925,7 +925,7 @@ static int imx412_parse_hw_config(struct imx412 *imx412) /* Request optional reset pin */ imx412->reset_gpio = devm_gpiod_get_optional(imx412->dev, "reset", - GPIOD_OUT_LOW); + GPIOD_OUT_HIGH); if (IS_ERR(imx412->reset_gpio)) { dev_err(imx412->dev, "failed to get reset gpio %ld\n", PTR_ERR(imx412->reset_gpio)); From ea91dee38b4e96c22361cbfdd4302332992ec615 Mon Sep 17 00:00:00 2001 From: Michael Tretter Date: Fri, 7 Nov 2025 11:34:33 +0100 Subject: [PATCH 0051/1518] media: staging: imx: request mbus_config in csi_start commit 9df2aaa64890c0b6226057eb6fcb6352bd2df432 upstream. Request the upstream mbus_config in csi_start, which starts the stream, instead of caching it in link_validate. This allows to get rid of the mbus_cfg field in the struct csi_priv and avoids state in the driver. Fixes: 4a34ec8e470c ("[media] media: imx: Add CSI subdev driver") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Signed-off-by: Michael Tretter Reviewed-by: Philipp Zabel Signed-off-by: Frank Li Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/staging/media/imx/imx-media-csi.c | 40 ++++++++++++++--------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c index fd7e37d803e7b..55a7d8f38465b 100644 --- a/drivers/staging/media/imx/imx-media-csi.c +++ b/drivers/staging/media/imx/imx-media-csi.c @@ -97,9 +97,6 @@ struct csi_priv { /* the mipi virtual channel number at link validate */ int vc_num; - /* media bus config of the upstream subdevice CSI is receiving from */ - struct v4l2_mbus_config mbus_cfg; - spinlock_t irqlock; /* protect eof_irq handler */ struct timer_list eof_timeout_timer; int eof_irq; @@ -403,7 +400,8 @@ static void csi_idmac_unsetup_vb2_buf(struct csi_priv *priv, } /* init the SMFC IDMAC channel */ -static int csi_idmac_setup_channel(struct csi_priv *priv) +static int csi_idmac_setup_channel(struct csi_priv *priv, + struct v4l2_mbus_config *mbus_cfg) { struct imx_media_video_dev *vdev = priv->vdev; const struct imx_media_pixfmt *incc; @@ -432,7 +430,7 @@ static int csi_idmac_setup_channel(struct csi_priv *priv) image.phys0 = phys[0]; image.phys1 = phys[1]; - passthrough = requires_passthrough(&priv->mbus_cfg, infmt, incc); + passthrough = requires_passthrough(mbus_cfg, infmt, incc); passthrough_cycles = 1; /* @@ -572,11 +570,12 @@ static void csi_idmac_unsetup(struct csi_priv *priv, csi_idmac_unsetup_vb2_buf(priv, state); } -static int csi_idmac_setup(struct csi_priv *priv) +static int csi_idmac_setup(struct csi_priv *priv, + struct v4l2_mbus_config *mbus_cfg) { int ret; - ret = csi_idmac_setup_channel(priv); + ret = csi_idmac_setup_channel(priv, mbus_cfg); if (ret) return ret; @@ -595,7 +594,8 @@ static int csi_idmac_setup(struct csi_priv *priv) return 0; } -static int csi_idmac_start(struct csi_priv *priv) +static int csi_idmac_start(struct csi_priv *priv, + struct v4l2_mbus_config *mbus_cfg) { struct imx_media_video_dev *vdev = priv->vdev; int ret; @@ -619,7 +619,7 @@ static int csi_idmac_start(struct csi_priv *priv) priv->last_eof = false; priv->nfb4eof = false; - ret = csi_idmac_setup(priv); + ret = csi_idmac_setup(priv, mbus_cfg); if (ret) { v4l2_err(&priv->sd, "csi_idmac_setup failed: %d\n", ret); goto out_free_dma_buf; @@ -701,7 +701,8 @@ static void csi_idmac_stop(struct csi_priv *priv) } /* Update the CSI whole sensor and active windows */ -static int csi_setup(struct csi_priv *priv) +static int csi_setup(struct csi_priv *priv, + struct v4l2_mbus_config *mbus_cfg) { struct v4l2_mbus_framefmt *infmt, *outfmt; const struct imx_media_pixfmt *incc; @@ -719,7 +720,7 @@ static int csi_setup(struct csi_priv *priv) * if cycles is set, we need to handle this over multiple cycles as * generic/bayer data */ - if (is_parallel_bus(&priv->mbus_cfg) && incc->cycles) { + if (is_parallel_bus(mbus_cfg) && incc->cycles) { if_fmt.width *= incc->cycles; crop.width *= incc->cycles; } @@ -730,7 +731,7 @@ static int csi_setup(struct csi_priv *priv) priv->crop.width == 2 * priv->compose.width, priv->crop.height == 2 * priv->compose.height); - ipu_csi_init_interface(priv->csi, &priv->mbus_cfg, &if_fmt, outfmt); + ipu_csi_init_interface(priv->csi, mbus_cfg, &if_fmt, outfmt); ipu_csi_set_dest(priv->csi, priv->dest); @@ -745,9 +746,17 @@ static int csi_setup(struct csi_priv *priv) static int csi_start(struct csi_priv *priv) { + struct v4l2_mbus_config mbus_cfg = { .type = 0 }; struct v4l2_fract *input_fi, *output_fi; int ret; + ret = csi_get_upstream_mbus_config(priv, &mbus_cfg); + if (ret) { + v4l2_err(&priv->sd, + "failed to get upstream media bus configuration\n"); + return ret; + } + input_fi = &priv->frame_interval[CSI_SINK_PAD]; output_fi = &priv->frame_interval[priv->active_output_pad]; @@ -758,7 +767,7 @@ static int csi_start(struct csi_priv *priv) return ret; /* Skip first few frames from a BT.656 source */ - if (priv->mbus_cfg.type == V4L2_MBUS_BT656) { + if (mbus_cfg.type == V4L2_MBUS_BT656) { u32 delay_usec, bad_frames = 20; delay_usec = DIV_ROUND_UP_ULL((u64)USEC_PER_SEC * @@ -769,12 +778,12 @@ static int csi_start(struct csi_priv *priv) } if (priv->dest == IPU_CSI_DEST_IDMAC) { - ret = csi_idmac_start(priv); + ret = csi_idmac_start(priv, &mbus_cfg); if (ret) goto stop_upstream; } - ret = csi_setup(priv); + ret = csi_setup(priv, &mbus_cfg); if (ret) goto idmac_stop; @@ -1138,7 +1147,6 @@ static int csi_link_validate(struct v4l2_subdev *sd, mutex_lock(&priv->lock); - priv->mbus_cfg = mbus_cfg; is_csi2 = !is_parallel_bus(&mbus_cfg); if (is_csi2) { /* From d9e678e8c63366f8f3eb61f035ccca2aebfe5d93 Mon Sep 17 00:00:00 2001 From: Matthias Fend Date: Tue, 24 Mar 2026 11:41:36 +0100 Subject: [PATCH 0052/1518] media: i2c: ov08d10: fix image vertical start setting commit 5d150fa0f16096d736bd24d13e04495da5116fab upstream. The current settings for the "image vertical start" register appear to be incorrect. While this only results in an incorrect start line for native modes, this faulty setting causes actual problems in binning mode. At least on an i.MX8MP test system, only corrupted frames could be received. To correct this, the recommended settings from the reference register sets are used for all modes. Since this shifts the start by one line, the Bayer pattern also changes, which has also been corrected. Fixes: 7be91e02ed57 ("media: i2c: Add ov08d10 camera sensor driver") Cc: stable@vger.kernel.org Signed-off-by: Matthias Fend Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/ov08d10.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/media/i2c/ov08d10.c b/drivers/media/i2c/ov08d10.c index 43ec2a1f2fcff..1177d21a2cc8f 100644 --- a/drivers/media/i2c/ov08d10.c +++ b/drivers/media/i2c/ov08d10.c @@ -217,7 +217,7 @@ static const struct ov08d10_reg lane_2_mode_3280x2460[] = { {0x9a, 0x30}, {0xa8, 0x02}, {0xfd, 0x02}, - {0xa1, 0x01}, + {0xa1, 0x00}, {0xa2, 0x09}, {0xa3, 0x9c}, {0xa5, 0x00}, @@ -335,7 +335,7 @@ static const struct ov08d10_reg lane_2_mode_3264x2448[] = { {0x9a, 0x30}, {0xa8, 0x02}, {0xfd, 0x02}, - {0xa1, 0x09}, + {0xa1, 0x08}, {0xa2, 0x09}, {0xa3, 0x90}, {0xa5, 0x08}, @@ -467,7 +467,7 @@ static const struct ov08d10_reg lane_2_mode_1632x1224[] = { {0xaa, 0xd0}, {0xab, 0x06}, {0xac, 0x68}, - {0xa1, 0x09}, + {0xa1, 0x04}, {0xa2, 0x04}, {0xa3, 0xc8}, {0xa5, 0x04}, @@ -613,8 +613,8 @@ static const struct ov08d10_lane_cfg lane_cfg_2 = { static u32 ov08d10_get_format_code(struct ov08d10 *ov08d10) { static const u32 codes[2][2] = { - { MEDIA_BUS_FMT_SGRBG10_1X10, MEDIA_BUS_FMT_SRGGB10_1X10}, - { MEDIA_BUS_FMT_SBGGR10_1X10, MEDIA_BUS_FMT_SGBRG10_1X10}, + { MEDIA_BUS_FMT_SBGGR10_1X10, MEDIA_BUS_FMT_SGBRG10_1X10 }, + { MEDIA_BUS_FMT_SGRBG10_1X10, MEDIA_BUS_FMT_SRGGB10_1X10 }, }; return codes[ov08d10->vflip->val][ov08d10->hflip->val]; From cedfde9f45b16ea14541f2390b195ba31bc56403 Mon Sep 17 00:00:00 2001 From: Matthias Fend Date: Tue, 24 Mar 2026 11:41:35 +0100 Subject: [PATCH 0053/1518] media: i2c: ov08d10: fix runtime PM handling in probe commit 35c7046be2be5e60be8128facb359a47f39e99cd upstream. Set the device's runtime PM status and enable runtime PM before registering the async sub-device. This is needed to avoid the case where the device is runtime PM resumed while runtime PM has not been enabled yet. Remove the related, non-driver-specific comment while at it. Fixes: 7be91e02ed57 ("media: i2c: Add ov08d10 camera sensor driver") Cc: stable@vger.kernel.org Reviewed-by: Philipp Zabel Signed-off-by: Matthias Fend Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/ov08d10.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/media/i2c/ov08d10.c b/drivers/media/i2c/ov08d10.c index 1177d21a2cc8f..5e1b8b58b3d64 100644 --- a/drivers/media/i2c/ov08d10.c +++ b/drivers/media/i2c/ov08d10.c @@ -1430,6 +1430,9 @@ static int ov08d10_probe(struct i2c_client *client) goto probe_error_v4l2_ctrl_handler_free; } + pm_runtime_set_active(ov08d10->dev); + pm_runtime_enable(ov08d10->dev); + ret = v4l2_async_register_subdev_sensor(&ov08d10->sd); if (ret < 0) { dev_err(ov08d10->dev, "failed to register V4L2 subdev: %d", @@ -1437,17 +1440,13 @@ static int ov08d10_probe(struct i2c_client *client) goto probe_error_media_entity_cleanup; } - /* - * Device is already turned on by i2c-core with ACPI domain PM. - * Enable runtime PM and turn off the device. - */ - pm_runtime_set_active(ov08d10->dev); - pm_runtime_enable(ov08d10->dev); pm_runtime_idle(ov08d10->dev); return 0; probe_error_media_entity_cleanup: + pm_runtime_disable(ov08d10->dev); + pm_runtime_set_suspended(ov08d10->dev); media_entity_cleanup(&ov08d10->sd.entity); probe_error_v4l2_ctrl_handler_free: From d172bb82f70c370912a9184cac083050657612f8 Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Mon, 26 Jan 2026 09:44:12 +0800 Subject: [PATCH 0054/1518] media: omap3isp: drop the use count of v4l2 pipeline commit 9da49bd9d4224035cff39b40d7395310abb10201 upstream. In isp_video_open(), drop the use count of v4l2 pipeline if vb2_queue_init() fails. Fixes: 8fd390b89cc8 ("media: Split v4l2_pipeline_pm_use into v4l2_pipeline_pm_{get, put}") Cc: stable@vger.kernel.org Signed-off-by: Haoxiang Li Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/ti/omap3isp/ispvideo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/ti/omap3isp/ispvideo.c b/drivers/media/platform/ti/omap3isp/ispvideo.c index eb33a776f27c9..a0549e731fbfd 100644 --- a/drivers/media/platform/ti/omap3isp/ispvideo.c +++ b/drivers/media/platform/ti/omap3isp/ispvideo.c @@ -1325,6 +1325,7 @@ static int isp_video_open(struct file *file) ret = vb2_queue_init(&handle->queue); if (ret < 0) { + v4l2_pipeline_pm_put(&video->video.entity); omap3isp_put(video->isp); goto done; } From 1920b4602ec912ac3160b799ef9ae5b936529321 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 5 Feb 2026 15:56:19 +0100 Subject: [PATCH 0055/1518] media: iris: fix QCOM_MDT_LOADER dependency commit a297c5165f91366cbc3490e630aabd1c0f70efb8 upstream. When build-testined with CONFIG_QCOM_MDT_LOADER=m and VIDEO_QCOM_IRIS=y, the kernel fails to link: x86_64-linux-ld: drivers/media/platform/qcom/iris/iris_firmware.o: in function `iris_fw_load': iris_firmware.c:(.text+0xb0): undefined reference to `qcom_mdt_get_size' iris_firmware.c:(.text+0xfd): undefined reference to `qcom_mdt_load' The problem is the conditional 'select' statement. Change this to make the driver built-in here regardless of CONFIG_ARCH_QCOM. Signed-off-by: Arnd Bergmann Reviewed-by: Konrad Dybcio Reviewed-by: Dikshita Agarwal Reviewed-by: Bryan O'Donoghue Fixes: d19b163356b8 ("media: iris: implement video firmware load/unload") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/iris/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/iris/Kconfig b/drivers/media/platform/qcom/iris/Kconfig index 3c803a05305a8..5498f48362d15 100644 --- a/drivers/media/platform/qcom/iris/Kconfig +++ b/drivers/media/platform/qcom/iris/Kconfig @@ -3,7 +3,7 @@ config VIDEO_QCOM_IRIS depends on VIDEO_DEV depends on ARCH_QCOM || COMPILE_TEST select V4L2_MEM2MEM_DEV - select QCOM_MDT_LOADER if ARCH_QCOM + select QCOM_MDT_LOADER select QCOM_SCM select VIDEOBUF2_DMA_CONTIG help From dd24998a4a4016fb9921916024399bd80f0d45c6 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Mon, 16 Feb 2026 12:37:42 +0530 Subject: [PATCH 0056/1518] media: iris: Fix use-after-free in iris_release_internal_buffers() commit f27cfdcfc916bb59297825805f4c3499f89f9e76 upstream. The recent change in commit 1dabf00ee206 ("media: iris: gen1: Destroy internal buffers after FW releases") introduced a regression where session_release_buf() may free the buffer. The caller, iris_release_internal_buffers(), continued to access `buffer` after the call, leading to a potential use-after-free. Fix this by setting BUF_ATTR_PENDING_RELEASE before calling session_release_buf(), and reverting the flag if the call fails. This ensures no dereference occurs after potential freeing. Reported-by: Dan Carpenter Closes: https://lore.kernel.org/lkml/aYXvKAX3Pg3sL37P@stanley.mountain/#r Signed-off-by: Dikshita Agarwal Reviewed-by: Vikash Garodia Fixes: 1dabf00ee206 ("media: iris: gen1: Destroy internal buffers after FW releases") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/iris/iris_buffer.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/qcom/iris/iris_buffer.c b/drivers/media/platform/qcom/iris/iris_buffer.c index 006ad855a8e51..11eb205f86460 100644 --- a/drivers/media/platform/qcom/iris/iris_buffer.c +++ b/drivers/media/platform/qcom/iris/iris_buffer.c @@ -571,10 +571,12 @@ static int iris_release_internal_buffers(struct iris_inst *inst, continue; if (!(buffer->attr & BUF_ATTR_QUEUED)) continue; + buffer->attr |= BUF_ATTR_PENDING_RELEASE; ret = hfi_ops->session_release_buf(inst, buffer); - if (ret) + if (ret) { + buffer->attr &= ~BUF_ATTR_PENDING_RELEASE; return ret; - buffer->attr |= BUF_ATTR_PENDING_RELEASE; + } } return 0; From 8744fd0835ddf4e100e97f2a7ce84d07afdd1d32 Mon Sep 17 00:00:00 2001 From: Wenmeng Liu Date: Fri, 13 Mar 2026 18:13:03 +0800 Subject: [PATCH 0057/1518] media: qcom: camss: Fix csid clock configuration for sa8775p commit fe56c674118aa46da1a3e65aa22ca709ebd7d812 upstream. Fix the mismatch between clock list and clock rate table for CSID lite instances. The current implementation has 5 clocks defined but only 2 are actually needed (vfe_lite_csid and vfe_lite_cphy_rx), while the clock rate table doesn't match this configuration. Update both clock list and rate table to maintain consistency: - Remove unused clocks: cpas_vfe_lite, vfe_lite_ahb, vfe_lite - Update clock rate table to match the remaining two clocks Signed-off-by: Wenmeng Liu Reviewed-by: Bryan O'Donoghue Fixes: ed03e99de0fa ("media: qcom: camss: Add support for CSID 690") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/camss/camss.c | 40 +++++++++-------------- 1 file changed, 15 insertions(+), 25 deletions(-) diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index fc838b3d22038..22a56672e329b 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -2782,12 +2782,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID2 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite0" }, .interrupt = { "csid_lite0" }, @@ -2801,12 +2799,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID3 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite1" }, .interrupt = { "csid_lite1" }, @@ -2820,12 +2816,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID4 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite2" }, .interrupt = { "csid_lite2" }, @@ -2839,12 +2833,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID5 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite3" }, .interrupt = { "csid_lite3" }, @@ -2858,12 +2850,10 @@ static const struct camss_subdev_resources csid_res_8775p[] = { /* CSID6 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", - "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + .clock = { "vfe_lite_csid", "vfe_lite_cphy_rx" }, .clock_rate = { - { 0, 0, 400000000, 400000000, 0}, - { 0, 0, 400000000, 480000000, 0} + { 400000000, 480000000 }, + { 400000000, 480000000 } }, .reg = { "csid_lite4" }, .interrupt = { "csid_lite4" }, From 9d6217429cd4dd51fd7178988be8581f72689bcb Mon Sep 17 00:00:00 2001 From: Wenmeng Liu Date: Fri, 13 Mar 2026 18:13:02 +0800 Subject: [PATCH 0058/1518] media: qcom: camss: Fix csid IRQ offset for sa8775p commit dd1b373941079cc102cc18bc68884e18245f5912 upstream. Fix BUF_DONE_IRQ_STATUS_RDI_OFFSET calculation for csid lite on sa8775p platform. The offset should be 0 for csid lite on sa8775p, Signed-off-by: Wenmeng Liu Reviewed-by: Bryan O'Donoghue Fixes: ed03e99de0fa ("media: qcom: camss: Add support for CSID 690") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/camss/camss-csid-gen3.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/qcom/camss/camss-csid-gen3.c b/drivers/media/platform/qcom/camss/camss-csid-gen3.c index 664245cf6eb0c..bd059243790ed 100644 --- a/drivers/media/platform/qcom/camss/camss-csid-gen3.c +++ b/drivers/media/platform/qcom/camss/camss-csid-gen3.c @@ -48,9 +48,9 @@ #define IS_CSID_690(csid) ((csid->camss->res->version == CAMSS_8775P) \ || (csid->camss->res->version == CAMSS_8300)) #define CSID_BUF_DONE_IRQ_STATUS 0x8C -#define BUF_DONE_IRQ_STATUS_RDI_OFFSET (csid_is_lite(csid) ?\ - 1 : (IS_CSID_690(csid) ?\ - 13 : 14)) +#define BUF_DONE_IRQ_STATUS_RDI_OFFSET (csid_is_lite(csid) ? \ + ((IS_CSID_690(csid) ? 0 : 1)) : \ + ((IS_CSID_690(csid) ? 13 : 14))) #define CSID_BUF_DONE_IRQ_MASK 0x90 #define CSID_BUF_DONE_IRQ_CLEAR 0x94 #define CSID_BUF_DONE_IRQ_SET 0x98 From e56a252478603938e4fe145ec8f42b740d6241cf Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 27 Mar 2026 22:19:55 +0200 Subject: [PATCH 0059/1518] media: qcom: iris: increase H265D_MAX_SLICE to fix H.265 decoding on SC7280 commit 3e0b2053751657ed2924adfe3ff25b1450231e33 upstream. Follow the commit bfe1326573ff ("venus: Fix for H265 decoding failure.") and increase H265D_MAX_SLICE following firmware requirements on that platform. Otherwise decoding of the H.265 streams fails with the "insufficient scratch_1 buffer size" from the firmware. Signed-off-by: Dmitry Baryshkov Reviewed-by: Dikshita Agarwal Reviewed-by: Vikash Garodia Reviewed-by: Konrad Dybcio [bod: Fixed commit log withthe => with the] Fixes: e1f5d32608ec ("media: iris: Add internal buffer calculation for HEVC and VP9 decoders") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/iris/iris_vpu_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/iris/iris_vpu_buffer.h b/drivers/media/platform/qcom/iris/iris_vpu_buffer.h index 04f0b7400a1e4..dfef180d32ed8 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu_buffer.h +++ b/drivers/media/platform/qcom/iris/iris_vpu_buffer.h @@ -61,7 +61,7 @@ struct iris_inst; #define SIZE_DOLBY_RPU_METADATA (41 * 1024) #define H264_CABAC_HDR_RATIO_HD_TOT 1 #define H264_CABAC_RES_RATIO_HD_TOT 3 -#define H265D_MAX_SLICE 1200 +#define H265D_MAX_SLICE 3600 #define SIZE_H265D_HW_PIC_T SIZE_H264D_HW_PIC_T #define H265_CABAC_HDR_RATIO_HD_TOT 2 #define H265_CABAC_RES_RATIO_HD_TOT 2 From 095c51bc86d30161e98bf775222bfdf829d501d8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 30 Mar 2026 12:08:21 +0100 Subject: [PATCH 0060/1518] media: venus: fix QCOM_MDT_LOADER dependency commit aa23c94cc433b145d1ce93820ecdfe16d8940e28 upstream. When build-testined with CONFIG_QCOM_MDT_LOADER=m and VIDEO_QCOM_VENUS=y, the kernel fails to link: x86_64-linux-ld: drivers/media/platform/qcom/venus/firmware.o: in function `venus_boot': firmware.c:(.text+0x1e3): undefined reference to `qcom_mdt_get_size' firmware.c:(.text+0x25a): undefined reference to `qcom_mdt_load' firmware.c:(.text+0x272): undefined reference to `qcom_mdt_load_no_init' The problem is the conditional 'select' statement. Change this to make the driver built-in here regardless of CONFIG_ARCH_QCOM, same as for the similar IRIS driver. Signed-off-by: Arnd Bergmann Reviewed-by: Konrad Dybcio Reviewed-by: Dikshita Agarwal Fixes: 0399b696f7f4 ("media: venus: fix compile-test build on non-qcom ARM platform") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/venus/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/venus/Kconfig b/drivers/media/platform/qcom/venus/Kconfig index ffb731ecd48c9..63ee8c78dc6d7 100644 --- a/drivers/media/platform/qcom/venus/Kconfig +++ b/drivers/media/platform/qcom/venus/Kconfig @@ -4,7 +4,7 @@ config VIDEO_QCOM_VENUS depends on VIDEO_DEV && QCOM_SMEM depends on (ARCH_QCOM && ARM64 && IOMMU_API) || COMPILE_TEST select OF_DYNAMIC if ARCH_QCOM - select QCOM_MDT_LOADER if ARCH_QCOM + select QCOM_MDT_LOADER select QCOM_SCM select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV From 696ac7c49c27169637e79fd9e6237bf5b42b368c Mon Sep 17 00:00:00 2001 From: Thomas Fourier Date: Fri, 13 Feb 2026 10:13:27 +0100 Subject: [PATCH 0061/1518] media: iris: Fix dma_free_attrs() size in iris_hfi_queues_init() commit 4a49ae56b0e4268d48fd96babe0cc68596bc301a upstream. The core->iface_q_table_vaddr buffer is alloc'd with size queue_size but freed with sizeof(*q_tbl_hdr) which is different. Change the dma_free_attrs() size. Signed-off-by: Thomas Fourier Reviewed-by: Dikshita Agarwal Fixes: d7378f84e94e ("media: iris: introduce iris core state management with shared queues") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/iris/iris_hfi_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/iris/iris_hfi_queue.c b/drivers/media/platform/qcom/iris/iris_hfi_queue.c index b3ed06297953b..bf6db23b53e21 100644 --- a/drivers/media/platform/qcom/iris/iris_hfi_queue.c +++ b/drivers/media/platform/qcom/iris/iris_hfi_queue.c @@ -263,7 +263,7 @@ int iris_hfi_queues_init(struct iris_core *core) GFP_KERNEL, DMA_ATTR_WRITE_COMBINE); if (!core->sfr_vaddr) { dev_err(core->dev, "sfr alloc and map failed\n"); - dma_free_attrs(core->dev, sizeof(*q_tbl_hdr), core->iface_q_table_vaddr, + dma_free_attrs(core->dev, queue_size, core->iface_q_table_vaddr, core->iface_q_table_daddr, DMA_ATTR_WRITE_COMBINE); return -ENOMEM; } From 22ee38cbf536125d4e8a0b6222ded1942f526a3b Mon Sep 17 00:00:00 2001 From: Wenmeng Liu Date: Fri, 13 Mar 2026 18:13:04 +0800 Subject: [PATCH 0062/1518] media: qcom: camss: Add missing clocks for VFE lite on sa8775p commit d31fac47b39f5e1ed85a587688ca70b793e421b4 upstream. Add missing required clocks (cpas_ahb and camnoc_axi) for VFE lite instances on sa8775p platform. These clocks are necessary for proper VFE lite operation: Reviewed-by: Bryan O'Donoghue Signed-off-by: Wenmeng Liu Fixes: e7b59e1d06fb ("media: qcom: camss: Add support for VFE 690") Cc: stable@vger.kernel.org Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/camss/camss.c | 40 ++++++++++++++--------- 1 file changed, 25 insertions(+), 15 deletions(-) diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index 22a56672e329b..c1148f6ad6b26 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -2926,15 +2926,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE2 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite0" }, .interrupt = { "vfe_lite0" }, @@ -2949,15 +2951,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE3 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite1" }, .interrupt = { "vfe_lite1" }, @@ -2972,15 +2976,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE4 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite2" }, .interrupt = { "vfe_lite2" }, @@ -2995,15 +3001,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE5 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite3" }, .interrupt = { "vfe_lite3" }, @@ -3018,15 +3026,17 @@ static const struct camss_subdev_resources vfe_res_8775p[] = { /* VFE6 (lite) */ { .regulators = {}, - .clock = { "cpas_vfe_lite", "vfe_lite_ahb", + .clock = { "cpas_ahb", "cpas_vfe_lite", "vfe_lite_ahb", "vfe_lite_csid", "vfe_lite_cphy_rx", - "vfe_lite"}, + "vfe_lite", "camnoc_axi"}, .clock_rate = { - { 0, 0, 0, 0 }, + { 0 }, + { 0 }, { 300000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 400000000, 400000000, 400000000, 400000000 }, { 480000000, 600000000, 600000000, 600000000 }, + { 400000000 }, }, .reg = { "vfe_lite4" }, .interrupt = { "vfe_lite4" }, From cc525debdfc8030959825f42beaabaaeef51d3c4 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:33 +0200 Subject: [PATCH 0063/1518] spi: mxs: fix controller deregistration commit 8b0d0011af20fb547aa67a1cefbf320992fd5e92 upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 33e195acf268 ("spi: mxs: use devm_spi_register_master()") Cc: stable@vger.kernel.org # 3.13 Cc: Jingoo Han Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-4-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mxs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c index 0ebcbdb1b1f71..d5ac5dddfbf65 100644 --- a/drivers/spi/spi-mxs.c +++ b/drivers/spi/spi-mxs.c @@ -619,7 +619,7 @@ static int mxs_spi_probe(struct platform_device *pdev) if (ret) goto out_pm_runtime_put; - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) { dev_err(&pdev->dev, "Cannot register SPI host, %d\n", ret); goto out_pm_runtime_put; @@ -650,11 +650,17 @@ static void mxs_spi_remove(struct platform_device *pdev) spi = spi_controller_get_devdata(host); ssp = &spi->ssp; + spi_controller_get(host); + + spi_unregister_controller(host); + pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) mxs_spi_runtime_suspend(&pdev->dev); dma_release_channel(ssp->dmach); + + spi_controller_put(host); } static struct platform_driver mxs_spi_driver = { From 724520793a2ed39ece0a6f984447e78e614b51fe Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:31 +0200 Subject: [PATCH 0064/1518] spi: mt65xx: fix controller deregistration commit 2ad30599cccc572ba2fc11010670eb6e01ea6bfc upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: a568231f4632 ("spi: mediatek: Add spi bus for Mediatek MT8173") Cc: stable@vger.kernel.org # 4.3: ace145802350 Cc: stable@vger.kernel.org # 4.3 Cc: Leilk Liu Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-2-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mt65xx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 90e5813cfdc33..9522d6f23788b 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -1326,7 +1326,7 @@ static int mtk_spi_probe(struct platform_device *pdev) pm_runtime_enable(dev); - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) { pm_runtime_disable(dev); return dev_err_probe(dev, ret, "failed to register host\n"); @@ -1341,6 +1341,8 @@ static void mtk_spi_remove(struct platform_device *pdev) struct mtk_spi *mdata = spi_controller_get_devdata(host); int ret; + spi_unregister_controller(host); + cpu_latency_qos_remove_request(&mdata->qos_request); if (mdata->use_spimem && !completion_done(&mdata->spimem_done)) complete(&mdata->spimem_done); From c74ba734001069bab836fa1494d340efcd80b67d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:10 +0200 Subject: [PATCH 0065/1518] spi: dln2: fix controller deregistration commit c353020fbfa8514ee91a6de2d88de4e5edca5803 upstream. Make sure to deregister the controller before disabling it to allow SPI device drivers to do I/O during deregistration. Fixes: 3d8c0d749da3 ("spi: add support for DLN-2 USB-SPI adapter") Cc: stable@vger.kernel.org # 4.0 Cc: Laurentiu Palcu Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-12-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-dln2.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-dln2.c b/drivers/spi/spi-dln2.c index 2013bc56ded8f..7260c4b969310 100644 --- a/drivers/spi/spi-dln2.c +++ b/drivers/spi/spi-dln2.c @@ -761,7 +761,7 @@ static int dln2_spi_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret < 0) { dev_err(&pdev->dev, "Failed to register host\n"); goto exit_register; @@ -786,10 +786,16 @@ static void dln2_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct dln2_spi *dln2 = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + pm_runtime_disable(&pdev->dev); if (dln2_spi_enable(dln2, false) < 0) dev_err(&pdev->dev, "Failed to disable SPI module\n"); + + spi_controller_put(host); } #ifdef CONFIG_PM_SLEEP From b99939bccae94d0eac8c86532444c11933447102 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:41 +0200 Subject: [PATCH 0066/1518] spi: s3c64xx: fix controller deregistration commit c1446b61e472da24d1547525193467b4bea4a7cb upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 91800f0e9005 ("spi/s3c64xx: Use managed registration") Cc: stable@vger.kernel.org # 3.13: 76fbad410c0f Cc: stable@vger.kernel.org # 3.13 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-12-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-s3c64xx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 33c80daec5f6b..851340f107b88 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -1370,7 +1370,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev) S3C64XX_SPI_INT_TX_OVERRUN_EN | S3C64XX_SPI_INT_TX_UNDERRUN_EN, sdd->regs + S3C64XX_SPI_INT_EN); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret != 0) { dev_err(&pdev->dev, "cannot register SPI host: %d\n", ret); goto err_pm_put; @@ -1400,6 +1400,8 @@ static void s3c64xx_spi_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); + spi_unregister_controller(host); + writel(0, sdd->regs + S3C64XX_SPI_INT_EN); pm_runtime_put_noidle(&pdev->dev); From 09ceedcebc7785f564d6afb4f1db48787431426f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:12 +0200 Subject: [PATCH 0067/1518] spi: fsl-espi: fix controller deregistration commit e506a700a7ad229f5c8f01f4b8350119cccb4158 upstream. Make sure to deregister the controller before disabling runtime PM (which can leave the controller disabled) to allow SPI device drivers to do I/O during deregistration. Fixes: e9abb4db8d10 ("spi: fsl-espi: add runtime PM") Cc: stable@vger.kernel.org # 4.3 Cc: Heiner Kallweit Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-14-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-fsl-espi.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c index f2f1d3298e6c0..cf89f36ab30b2 100644 --- a/drivers/spi/spi-fsl-espi.c +++ b/drivers/spi/spi-fsl-espi.c @@ -719,7 +719,7 @@ static int fsl_espi_probe(struct device *dev, struct resource *mem, pm_runtime_enable(dev); pm_runtime_get_sync(dev); - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret < 0) goto err_pm; @@ -783,7 +783,15 @@ static int of_fsl_espi_probe(struct platform_device *ofdev) static void of_fsl_espi_remove(struct platform_device *dev) { + struct spi_controller *host = platform_get_drvdata(dev); + + spi_controller_get(host); + + spi_unregister_controller(host); + pm_runtime_disable(&dev->dev); + + spi_controller_put(host); } #ifdef CONFIG_PM_SLEEP From 4ed7de898bbb25421865aa5e95a467239fbd7869 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:35 +0200 Subject: [PATCH 0068/1518] spi: omap2-mcspi: fix controller deregistration commit fb45f95c377e4a4bdece2c5e17643b459c9c13e7 upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: ccdc7bf92573 ("SPI: omap2_mcspi driver") Cc: stable@vger.kernel.org # 2.6.23 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-6-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-omap2-mcspi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 69c2e9d9be3c3..86b3d21e77617 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -1585,7 +1585,7 @@ static int omap2_mcspi_probe(struct platform_device *pdev) if (status < 0) goto disable_pm; - status = devm_spi_register_controller(&pdev->dev, ctlr); + status = spi_register_controller(ctlr); if (status < 0) goto disable_pm; @@ -1606,11 +1606,17 @@ static void omap2_mcspi_remove(struct platform_device *pdev) struct spi_controller *ctlr = platform_get_drvdata(pdev); struct omap2_mcspi *mcspi = spi_controller_get_devdata(ctlr); + spi_controller_get(ctlr); + + spi_unregister_controller(ctlr); + omap2_mcspi_release_dma(ctlr); pm_runtime_dont_use_autosuspend(mcspi->dev); pm_runtime_put_sync(mcspi->dev); pm_runtime_disable(&pdev->dev); + + spi_controller_put(ctlr); } /* work with hotplug and coldplug */ From 894d761a3a852c13688cd2719ebdbc6a43403d64 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:36 +0200 Subject: [PATCH 0069/1518] spi: pic32: fix controller deregistration commit 6b627bfe0c44e064aba464839e430dc1ca2b0bb8 upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 1bcb9f8ceb67 ("spi: spi-pic32: Add PIC32 SPI master driver") Cc: stable@vger.kernel.org # 4.7 Cc: Purna Chandra Mandal Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-7-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-pic32.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-pic32.c b/drivers/spi/spi-pic32.c index 369850d143136..70427e5299456 100644 --- a/drivers/spi/spi-pic32.c +++ b/drivers/spi/spi-pic32.c @@ -821,7 +821,7 @@ static int pic32_spi_probe(struct platform_device *pdev) } /* register host */ - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) { dev_err(&host->dev, "failed registering spi host\n"); goto err_bailout; @@ -840,11 +840,16 @@ static int pic32_spi_probe(struct platform_device *pdev) static void pic32_spi_remove(struct platform_device *pdev) { - struct pic32_spi *pic32s; + struct pic32_spi *pic32s = platform_get_drvdata(pdev); + + spi_controller_get(pic32s->host); + + spi_unregister_controller(pic32s->host); - pic32s = platform_get_drvdata(pdev); pic32_spi_disable(pic32s); pic32_spi_dma_unprep(pic32s); + + spi_controller_put(pic32s->host); } static const struct of_device_id pic32_spi_of_match[] = { From cc8a904cbe6de6cb8b77aea336502cfe8c4974de Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:32 +0200 Subject: [PATCH 0070/1518] spi: mtk-nor: fix controller deregistration commit 76336f24934621db286cabb20b483773ee01dcaa upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 881d1ee9fe81 ("spi: add support for mediatek spi-nor controller") Cc: stable@vger.kernel.org # 5.7 Cc: Chuanhong Guo Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-3-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mtk-nor.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c index 5cc4632e13d7a..ba41ff42f0dde 100644 --- a/drivers/spi/spi-mtk-nor.c +++ b/drivers/spi/spi-mtk-nor.c @@ -914,7 +914,7 @@ static int mtk_nor_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); pm_runtime_get_noresume(&pdev->dev); - ret = devm_spi_register_controller(&pdev->dev, ctlr); + ret = spi_register_controller(ctlr); if (ret < 0) goto err_probe; @@ -939,6 +939,8 @@ static void mtk_nor_remove(struct platform_device *pdev) struct spi_controller *ctlr = dev_get_drvdata(&pdev->dev); struct mtk_nor *sp = spi_controller_get_devdata(ctlr); + spi_unregister_controller(ctlr); + pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); From af4f58c18c4cdb050fd716b7af7a6545ef8c5ba2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:38 +0200 Subject: [PATCH 0071/1518] spi: pl022: fix controller deregistration commit 994b33366be9148240690e3e94bffe17c4d89458 upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: b43d65f7e818 ("[ARM] 5546/1: ARM PL022 SSP/SPI driver v3") Cc: stable@vger.kernel.org # 2.6.31 Cc: Linus Walleij Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-9-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-pl022.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index 9e56e87746142..da00dfa734d95 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -1957,7 +1957,7 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id) /* Register with the SPI framework */ amba_set_drvdata(adev, pl022); - status = devm_spi_register_controller(&adev->dev, host); + status = spi_register_controller(host); if (status != 0) { dev_err_probe(&adev->dev, status, "problem registering spi host\n"); @@ -1998,6 +1998,10 @@ pl022_remove(struct amba_device *adev) if (!pl022) return; + spi_controller_get(pl022->host); + + spi_unregister_controller(pl022->host); + /* * undo pm_runtime_put() in probe. I assume that we're not * accessing the primecell here. @@ -2009,6 +2013,8 @@ pl022_remove(struct amba_device *adev) pl022_dma_remove(pl022); amba_release_regions(adev); + + spi_controller_put(pl022->host); } #ifdef CONFIG_PM_SLEEP From 4422fc2411cbbdf5104a914e0596bb483faea254 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 27 Mar 2026 11:43:05 +0100 Subject: [PATCH 0072/1518] spi: ch341: fix devres lifetime commit abe572f630bc1f0e77041012ab075869036ede4f upstream. USB drivers bind to USB interfaces and any device managed resources should have their lifetime tied to the interface rather than parent USB device. This avoids issues like memory leaks when drivers are unbound without their devices being physically disconnected (e.g. on probe deferral or configuration changes). Fix the controller and driver data lifetime so that they are released on driver unbind. Note that this also makes sure that the SPI controller is placed correctly under the USB interface in the device tree. Fixes: 8846739f52af ("spi: add ch341a usb2spi driver") Cc: stable@vger.kernel.org # 6.11 Cc: Johannes Thumshirn Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260327104305.1309915-3-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-ch341.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-ch341.c b/drivers/spi/spi-ch341.c index ded0935662605..3eaa8f176f63a 100644 --- a/drivers/spi/spi-ch341.c +++ b/drivers/spi/spi-ch341.c @@ -152,7 +152,7 @@ static int ch341_probe(struct usb_interface *intf, if (ret) return ret; - ctrl = devm_spi_alloc_host(&udev->dev, sizeof(struct ch341_spi_dev)); + ctrl = devm_spi_alloc_host(&intf->dev, sizeof(struct ch341_spi_dev)); if (!ctrl) return -ENOMEM; @@ -163,7 +163,7 @@ static int ch341_probe(struct usb_interface *intf, ch341->read_pipe = usb_rcvbulkpipe(udev, usb_endpoint_num(in)); ch341->rx_len = usb_endpoint_maxp(in); - ch341->rx_buf = devm_kzalloc(&udev->dev, ch341->rx_len, GFP_KERNEL); + ch341->rx_buf = devm_kzalloc(&intf->dev, ch341->rx_len, GFP_KERNEL); if (!ch341->rx_buf) return -ENOMEM; @@ -171,8 +171,7 @@ static int ch341_probe(struct usb_interface *intf, if (!ch341->rx_urb) return -ENOMEM; - ch341->tx_buf = - devm_kzalloc(&udev->dev, CH341_PACKET_LENGTH, GFP_KERNEL); + ch341->tx_buf = devm_kzalloc(&intf->dev, CH341_PACKET_LENGTH, GFP_KERNEL); if (!ch341->tx_buf) { ret = -ENOMEM; goto err_free_urb; From d78c5ca1563c0531e01fcc127820bd0255a7a753 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:42 +0200 Subject: [PATCH 0073/1518] spi: sh-hspi: fix controller deregistration commit e63982e6392e45a6ecd68d6c317a081cc8e70143 upstream. Make sure to deregister the controller before releasing underlying resources like clocks during driver unbind. Fixes: 49e599b8595f ("spi: sh-hspi: control spi clock more correctly") Cc: stable@vger.kernel.org # 3.4 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-13-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-sh-hspi.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c index 93017faeb7b55..8253ab9b88383 100644 --- a/drivers/spi/spi-sh-hspi.c +++ b/drivers/spi/spi-sh-hspi.c @@ -258,9 +258,9 @@ static int hspi_probe(struct platform_device *pdev) ctlr->transfer_one_message = hspi_transfer_one_message; ctlr->bits_per_word_mask = SPI_BPW_MASK(8); - ret = devm_spi_register_controller(&pdev->dev, ctlr); + ret = spi_register_controller(ctlr); if (ret < 0) { - dev_err(&pdev->dev, "devm_spi_register_controller error.\n"); + dev_err(&pdev->dev, "failed to register controller\n"); goto error2; } @@ -280,9 +280,15 @@ static void hspi_remove(struct platform_device *pdev) { struct hspi_priv *hspi = platform_get_drvdata(pdev); + spi_controller_get(hspi->ctlr); + + spi_unregister_controller(hspi->ctlr); + pm_runtime_disable(&pdev->dev); clk_put(hspi->clk); + + spi_controller_put(hspi->ctlr); } static const struct of_device_id hspi_of_match[] = { From ca3195c7b88362d7c81efe685948663a9f9db0e6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 08:47:49 +0200 Subject: [PATCH 0074/1518] spi: fsl: fix controller deregistration commit 9b7abfed4c3754062d1f3ffd452e65a38667f586 upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 4178b6b1b595 ("spi: fsl-(e)spi: migrate to using devm_ functions to simplify cleanup") Cc: stable@vger.kernel.org # 4.3 Cc: Heiner Kallweit Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410064749.496888-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-fsl-spi.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 481a7b28aacd3..a516abbb6f67a 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -614,7 +614,7 @@ static struct spi_controller *fsl_spi_probe(struct device *dev, mpc8xxx_spi_write_reg(®_base->mode, regval); - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret < 0) goto err_probe; @@ -705,7 +705,13 @@ static void of_fsl_spi_remove(struct platform_device *ofdev) struct spi_controller *host = platform_get_drvdata(ofdev); struct mpc8xxx_spi *mpc8xxx_spi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + fsl_spi_cpm_free(mpc8xxx_spi); + + spi_controller_put(host); } static struct platform_driver of_fsl_spi_driver = { @@ -751,7 +757,13 @@ static void plat_mpc8xxx_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct mpc8xxx_spi *mpc8xxx_spi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + fsl_spi_cpm_free(mpc8xxx_spi); + + spi_controller_put(host); } MODULE_ALIAS("platform:mpc8xxx_spi"); From 047f939c602cfea4e44969412ad4c54e938cb8a8 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:06 +0200 Subject: [PATCH 0075/1518] spi: bcmbca-hsspi: fix controller deregistration commit c3d97c3320b9a1ebbd6119857341be034f7b3efc upstream. Make sure to deregister the controller before disabling underlying resources like interrupts during driver unbind to allow SPI drivers to do I/O during deregistration. Note that clocks were also disabled before the recent commit e532e21a246d ("spi: bcm63xx-hsspi: Simplify clock handling with devm_clk_get_enabled()"). Fixes: a38a2233f23b ("spi: bcmbca-hsspi: Add driver for newer HSSPI controller") Cc: stable@vger.kernel.org # 6.3: deb269e0394f Cc: stable@vger.kernel.org # 6.3 Cc: William Zhang Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-8-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-bcmbca-hsspi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-bcmbca-hsspi.c b/drivers/spi/spi-bcmbca-hsspi.c index f16298b752360..f0f0e6b29668e 100644 --- a/drivers/spi/spi-bcmbca-hsspi.c +++ b/drivers/spi/spi-bcmbca-hsspi.c @@ -550,7 +550,7 @@ static int bcmbca_hsspi_probe(struct platform_device *pdev) } /* register and we are done */ - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) goto out_sysgroup_disable; @@ -572,6 +572,8 @@ static void bcmbca_hsspi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct bcmbca_hsspi *bs = spi_controller_get_devdata(host); + spi_unregister_controller(host); + /* reset the hardware and block queue progress */ __raw_writel(0, bs->regs + HSSPI_INT_MASK_REG); clk_disable_unprepare(bs->pll_clk); From ee2100d08094bf6e50ecc3d58e274d915e506285 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:09 +0200 Subject: [PATCH 0076/1518] spi: coldfire-qspi: fix controller deregistration commit e7c510e192ff2a1264d999575eea39a506424264 upstream. Make sure to deregister the controller before disabling underlying resources like clocks (via runtime pm) during driver unbind. Fixes: 34b8c6617366 ("spi: Add Freescale/Motorola Coldfire QSPI driver") Cc: stable@vger.kernel.org # 2.6.34 Cc: Steven King Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-11-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-coldfire-qspi.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c index fdf37636cb9f0..b45f44de85dcd 100644 --- a/drivers/spi/spi-coldfire-qspi.c +++ b/drivers/spi/spi-coldfire-qspi.c @@ -410,9 +410,9 @@ static int mcfqspi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); pm_runtime_enable(&pdev->dev); - status = devm_spi_register_controller(&pdev->dev, host); + status = spi_register_controller(host); if (status) { - dev_dbg(&pdev->dev, "devm_spi_register_controller failed\n"); + dev_dbg(&pdev->dev, "failed to register controller\n"); goto fail1; } @@ -436,11 +436,17 @@ static void mcfqspi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct mcfqspi *mcfqspi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + pm_runtime_disable(&pdev->dev); /* disable the hardware (set the baud rate to 0) */ mcfqspi_wr_qmr(mcfqspi, MCFQSPI_QMR_MSTR); mcfqspi_cs_teardown(mcfqspi); + + spi_controller_put(host); } #ifdef CONFIG_PM_SLEEP From e84a84209b3f3f20e2c8568d0ddf9f7342c75482 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:34 +0200 Subject: [PATCH 0077/1518] spi: npcm-pspi: fix controller deregistration commit ebd81199e00e107980bf8c4d2c747ae50158f797 upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 2a22f1b30cee ("spi: npcm: add NPCM PSPI controller driver") Cc: stable@vger.kernel.org # 5.0 Cc: Tomer Maimon Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-5-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-npcm-pspi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-npcm-pspi.c b/drivers/spi/spi-npcm-pspi.c index 98b6479b961ca..ba17149237727 100644 --- a/drivers/spi/spi-npcm-pspi.c +++ b/drivers/spi/spi-npcm-pspi.c @@ -414,7 +414,7 @@ static int npcm_pspi_probe(struct platform_device *pdev) /* set to default clock rate */ npcm_pspi_set_baudrate(priv, NPCM_PSPI_DEFAULT_CLK); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) goto out_disable_clk; @@ -435,8 +435,14 @@ static void npcm_pspi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct npcm_pspi *priv = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + npcm_pspi_reset_hw(priv); clk_disable_unprepare(priv->clk); + + spi_controller_put(host); } static const struct of_device_id npcm_pspi_match[] = { From 82a95eca235b2fa65c808dfbbbe2716dc6f21379 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:08 +0200 Subject: [PATCH 0078/1518] spi: cavium-thunderx: fix controller deregistration commit dbb6b01267c0c866eaac4019cec19f414beec61d upstream. Make sure to deregister the controller before disabling it to avoid hanging or leaking resources associated with the queue when the queue non-empty. Fixes: 7347a6c7af8d ("spi: octeon: Add ThunderX driver") Cc: stable@vger.kernel.org # 4.9 Cc: Jan Glauber Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-10-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-cavium-thunderx.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-cavium-thunderx.c b/drivers/spi/spi-cavium-thunderx.c index 367ae7120bb3b..81142b3f7b412 100644 --- a/drivers/spi/spi-cavium-thunderx.c +++ b/drivers/spi/spi-cavium-thunderx.c @@ -71,7 +71,7 @@ static int thunderx_spi_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, host); - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) goto error; @@ -91,8 +91,14 @@ static void thunderx_spi_remove(struct pci_dev *pdev) if (!p) return; + spi_controller_get(host); + + spi_unregister_controller(host); + /* Put everything in a known state. */ writeq(0, p->register_base + OCTEON_SPI_CFG(p)); + + spi_controller_put(host); } static const struct pci_device_id thunderx_spi_pci_id_table[] = { From cdbf6baefff09ab042315d4ed19e1029d0de7afb Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:37 +0200 Subject: [PATCH 0079/1518] spi: pic32-sqi: fix controller deregistration commit 420df79d1a618951eb0eb4331df95c9f4f763b8b upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 3270ac230f66 ("spi: pic32-sqi: add SPI driver for PIC32 SQI controller.") Cc: stable@vger.kernel.org # 4.7 Cc: Purna Chandra Mandal Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-8-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-pic32-sqi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-pic32-sqi.c b/drivers/spi/spi-pic32-sqi.c index fa0c1ee84532c..a6b5a0ed99c9e 100644 --- a/drivers/spi/spi-pic32-sqi.c +++ b/drivers/spi/spi-pic32-sqi.c @@ -642,7 +642,7 @@ static int pic32_sqi_probe(struct platform_device *pdev) host->prepare_transfer_hardware = pic32_sqi_prepare_hardware; host->unprepare_transfer_hardware = pic32_sqi_unprepare_hardware; - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) { dev_err(&host->dev, "failed registering spi host\n"); free_irq(sqi->irq, sqi); @@ -665,9 +665,15 @@ static void pic32_sqi_remove(struct platform_device *pdev) { struct pic32_sqi *sqi = platform_get_drvdata(pdev); + spi_controller_get(sqi->host); + + spi_unregister_controller(sqi->host); + /* release resources */ free_irq(sqi->irq, sqi); ring_desc_ring_free(sqi); + + spi_controller_put(sqi->host); } static const struct of_device_id pic32_sqi_of_ids[] = { From 229cc70e4e902f904bf774527fd77d4d3777be0b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:46 +0200 Subject: [PATCH 0080/1518] spi: sprd: fix controller deregistration commit 123d17dbc5f07059752fa5e616385ca29a8f935a upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Note that the controller is suspended before disabling and releasing resources since commit de082d866cce ("spi: sprd: Add the SPI irq function for the SPI DMA mode") which avoids issues like unclocked accesses but prevents SPI device drivers from doing I/O during deregistration. Fixes: e7d973a31c24 ("spi: sprd: Add SPI driver for Spreadtrum SC9860") Cc: stable@vger.kernel.org # 4.20 Cc: Lanqing Liu Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-17-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-sprd.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index ad75f5f0f2bfc..218c38841f05f 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -978,7 +978,7 @@ static int sprd_spi_probe(struct platform_device *pdev) goto err_rpm_put; } - ret = devm_spi_register_controller(&pdev->dev, sctlr); + ret = spi_register_controller(sctlr); if (ret) goto err_rpm_put; @@ -1009,7 +1009,9 @@ static void sprd_spi_remove(struct platform_device *pdev) if (ret < 0) dev_err(ss->dev, "failed to resume SPI controller\n"); - spi_controller_suspend(sctlr); + spi_controller_get(sctlr); + + spi_unregister_controller(sctlr); if (ret >= 0) { if (ss->dma.enable) @@ -1018,6 +1020,8 @@ static void sprd_spi_remove(struct platform_device *pdev) } pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + + spi_controller_put(sctlr); } static int __maybe_unused sprd_spi_runtime_suspend(struct device *dev) From aee76c1dd189562c6678313caec12761f78a9ef3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:40 +0200 Subject: [PATCH 0081/1518] spi: rspi: fix controller deregistration commit 9944fa6726afb1e6eb7e2212764e7da0c97f2dcc upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 9e03d05eee4c ("spi: rcar: Use devm_spi_register_master()") Cc: stable@vger.kernel.org # 3.14 Cc: Jingoo Han Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-11-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-rspi.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 8e1d911b88b51..c90dfe5211542 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -1171,8 +1171,14 @@ static void rspi_remove(struct platform_device *pdev) { struct rspi_data *rspi = platform_get_drvdata(pdev); + spi_controller_get(rspi->ctlr); + + spi_unregister_controller(rspi->ctlr); + rspi_release_dma(rspi->ctlr); pm_runtime_disable(&pdev->dev); + + spi_controller_put(rspi->ctlr); } static const struct spi_ops rspi_ops = { @@ -1377,9 +1383,9 @@ static int rspi_probe(struct platform_device *pdev) if (ret < 0) dev_warn(&pdev->dev, "DMA not available, using PIO\n"); - ret = devm_spi_register_controller(&pdev->dev, ctlr); + ret = spi_register_controller(ctlr); if (ret < 0) { - dev_err(&pdev->dev, "devm_spi_register_controller error.\n"); + dev_err(&pdev->dev, "failed to register controller\n"); goto error3; } From 0df72db5a13c0f45cc8b54b29abbe288d9e1b843 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:43 +0200 Subject: [PATCH 0082/1518] spi: sh-msiof: fix controller deregistration commit 45170f67a08b912ead6ccc387ba06954d1d4e53a upstream. Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Fixes: 1bd6363bc0c6 ("spi: sh-msiof: Use core message handling instead of spi-bitbang") Cc: stable@vger.kernel.org # 3.15 Cc: Geert Uytterhoeven Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-14-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-sh-msiof.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index b695870fae8c4..7f4135a3bda23 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -1290,9 +1290,9 @@ static int sh_msiof_spi_probe(struct platform_device *pdev) if (ret < 0) dev_warn(dev, "DMA not available, using PIO\n"); - ret = devm_spi_register_controller(dev, ctlr); + ret = spi_register_controller(ctlr); if (ret < 0) { - dev_err(dev, "devm_spi_register_controller error.\n"); + dev_err(dev, "failed to register controller\n"); goto err2; } @@ -1310,8 +1310,14 @@ static void sh_msiof_spi_remove(struct platform_device *pdev) { struct sh_msiof_spi_priv *p = platform_get_drvdata(pdev); + spi_controller_get(p->ctlr); + + spi_unregister_controller(p->ctlr); + sh_msiof_release_dma(p); pm_runtime_disable(&pdev->dev); + + spi_controller_put(p->ctlr); } static const struct platform_device_id spi_driver_ids[] = { From 4b0fe572a8ea3e1b2de301eff41c8ddb3267d4ae Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 10 Apr 2026 10:17:45 +0200 Subject: [PATCH 0083/1518] spi: slave-mt27xx: fix controller deregistration commit ab840cbda4fe6c40e52f6415c47056797c663bb2 upstream. Make sure to deregister the controller before disabling underlying resources like clocks (by disabling runtime PM) during driver unbind. Fixes: 805be7ddf367 ("spi: mediatek: add spi slave for Mediatek MT2712") Cc: stable@vger.kernel.org # 4.20 Cc: Leilk Liu Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-16-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-slave-mt27xx.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-slave-mt27xx.c b/drivers/spi/spi-slave-mt27xx.c index e331df9673855..c39d8e590ad77 100644 --- a/drivers/spi/spi-slave-mt27xx.c +++ b/drivers/spi/spi-slave-mt27xx.c @@ -454,7 +454,7 @@ static int mtk_spi_slave_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); - ret = devm_spi_register_controller(&pdev->dev, ctlr); + ret = spi_register_controller(ctlr); clk_disable_unprepare(mdata->spi_clk); if (ret) { dev_err(&pdev->dev, @@ -474,7 +474,15 @@ static int mtk_spi_slave_probe(struct platform_device *pdev) static void mtk_spi_slave_remove(struct platform_device *pdev) { + struct spi_controller *ctlr = platform_get_drvdata(pdev); + + spi_controller_get(ctlr); + + spi_unregister_controller(ctlr); + pm_runtime_disable(&pdev->dev); + + spi_controller_put(ctlr); } #ifdef CONFIG_PM_SLEEP From b2bdbe293012fd640fa1406d1b36ecd9c061db8a Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:14 +0200 Subject: [PATCH 0084/1518] spi: img-spfi: fix controller deregistration commit fc3a83b0d9c16b941c9028f5a8db9541dce4ddf2 upstream. Make sure to deregister the controller before disabling and releasing underlying resources like clocks and DMA during driver unbind. Fixes: deba25800a12 ("spi: Add driver for IMG SPFI controller") Cc: stable@vger.kernel.org # 3.19 Cc: Andrew Bresticker Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260409120419.388546-16-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-img-spfi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c index 168ccf51f6d4a..a6d15b9ca5098 100644 --- a/drivers/spi/spi-img-spfi.c +++ b/drivers/spi/spi-img-spfi.c @@ -644,7 +644,7 @@ static int img_spfi_probe(struct platform_device *pdev) pm_runtime_set_active(spfi->dev); pm_runtime_enable(spfi->dev); - ret = devm_spi_register_controller(spfi->dev, host); + ret = spi_register_controller(host); if (ret) goto disable_pm; @@ -670,6 +670,10 @@ static void img_spfi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct img_spfi *spfi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + if (spfi->tx_ch) dma_release_channel(spfi->tx_ch); if (spfi->rx_ch) @@ -680,6 +684,8 @@ static void img_spfi_remove(struct platform_device *pdev) clk_disable_unprepare(spfi->spfi_clk); clk_disable_unprepare(spfi->sys_clk); } + + spi_controller_put(host); } #ifdef CONFIG_PM From 6a405d594207fa1442d8b26009e4e4e8dc415805 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 9 Apr 2026 14:04:19 +0200 Subject: [PATCH 0085/1518] spi: mpfs: fix controller deregistration commit 573c7db8fce91a1b07dd64a260bb44b9e6d05943 upstream. Make sure to deregister the controller before disabling underlying resources like interrupts during driver unbind. Fixes: 9ac8d17694b6 ("spi: add support for microchip fpga spi controllers") Cc: stable@vger.kernel.org # 6.0 Cc: Conor Dooley Signed-off-by: Johan Hovold Acked-by: Conor Dooley Link: https://patch.msgid.link/20260409120419.388546-21-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mpfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mpfs.c b/drivers/spi/spi-mpfs.c index 7e9e64d8e6c81..c41e0e55b52f2 100644 --- a/drivers/spi/spi-mpfs.c +++ b/drivers/spi/spi-mpfs.c @@ -575,7 +575,7 @@ static int mpfs_spi_probe(struct platform_device *pdev) mpfs_spi_init(host, spi); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) { mpfs_spi_disable_ints(spi); mpfs_spi_disable(spi); @@ -593,6 +593,8 @@ static void mpfs_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct mpfs_spi *spi = spi_controller_get_devdata(host); + spi_unregister_controller(host); + mpfs_spi_disable_ints(spi); mpfs_spi_disable(spi); } From 2a2973cb368220305d8169a3ae8d0e06f668bfcd Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 21 Apr 2026 14:56:32 +0200 Subject: [PATCH 0086/1518] spi: imx: fix runtime pm leak on probe deferral commit a1d50a37d3b1df84f536a982f692371039df4a48 upstream. Make sure to balance the runtime PM usage count before returning on probe failure (e.g. probe deferral) so that the controller can be suspended when a driver is later bound. Fixes: 43b6bf406cd0 ("spi: imx: fix runtime pm support for !CONFIG_PM") Cc: stable@vger.kernel.org # 5.10 Cc: Sascha Hauer Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260421125632.1537235-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-imx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index dc7ffa8cb2878..ce3c7aa53f190 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1948,6 +1948,7 @@ static int spi_imx_probe(struct platform_device *pdev) out_runtime_pm_put: pm_runtime_dont_use_autosuspend(spi_imx->dev); pm_runtime_disable(spi_imx->dev); + pm_runtime_put_noidle(spi_imx->dev); pm_runtime_set_suspended(&pdev->dev); clk_disable_unprepare(spi_imx->clk_ipg); From 5c03d52ee6ceb4be73389f5868586b0084f08f2c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 14 Apr 2026 15:43:16 +0200 Subject: [PATCH 0087/1518] spi: mxic: fix controller deregistration commit adbc595e272052181d40ec307a4c5ba98571b0fe upstream. Make sure to deregister the controller before disabling underlying resources like clocks (via runtime pm) during driver unbind. Fixes: b942d80b0a39 ("spi: Add MXIC controller driver") Cc: stable@vger.kernel.org # 5.0: cc53711b2191 Cc: stable@vger.kernel.org # 5.0 Cc: Mason Yang Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260414134319.978196-6-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mxic.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index eeaea6a5e3103..eea4a588e8a0c 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -833,9 +833,10 @@ static void mxic_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct mxic_spi *mxic = spi_controller_get_devdata(host); + spi_unregister_controller(host); + pm_runtime_disable(&pdev->dev); mxic_spi_mem_ecc_remove(mxic); - spi_unregister_controller(host); } static const struct of_device_id mxic_spi_of_ids[] = { From ec7a4cff8355c5bb0edc8e225885a92b0c9c1d93 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 14 Apr 2026 15:43:17 +0200 Subject: [PATCH 0088/1518] spi: orion: fix controller deregistration commit 220f4f11104a7f83b71543ef0e48dde1da2bc5d3 upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 60cadec9da7b ("spi: new orion_spi driver") Cc: stable@vger.kernel.org # 2.6.27 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260414134319.978196-7-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-orion.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index 43bd9f21137f9..a9a817d4c112e 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -802,10 +802,15 @@ static void orion_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct orion_spi *spi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + pm_runtime_get_sync(&pdev->dev); clk_disable_unprepare(spi->axi_clk); - spi_unregister_controller(host); + spi_controller_put(host); + pm_runtime_disable(&pdev->dev); } From b809b8d2a114384a6228f584b68d0c7767d59f4b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 21 Apr 2026 15:02:09 +0200 Subject: [PATCH 0089/1518] spi: orion: fix runtime pm leak on unbind commit 97b17dd8266d2e26d9ee3c75a0fa34ecde6944f0 upstream. Make sure to balance the runtime PM usage count on driver unbind so that the controller can be suspended when a driver is rebound. Also restore the autosuspend setting. This issue was flagged by Sashiko when reviewing a controller deregistration fix. Fixes: 5c6786945b4e ("spi: spi-orion: add runtime PM support") Cc: stable@vger.kernel.org # 3.17 Cc: Russell King Link: https://sashiko.dev/#/patchset/20260414134319.978196-1-johan%40kernel.org?part=6 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260421130211.1537628-2-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-orion.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index a9a817d4c112e..8efc17ff9f9c3 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -812,6 +812,9 @@ static void orion_spi_remove(struct platform_device *pdev) spi_controller_put(host); pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } MODULE_ALIAS("platform:" DRIVER_NAME); From 07dc76d31be43e8992c72523edd4e7af70897a52 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 21 Apr 2026 15:02:10 +0200 Subject: [PATCH 0090/1518] spi: orion: fix clock imbalance on registration failure commit 443cde0dc59c5d154156ac9f27a7dadef8ebc0c2 upstream. Make sure that the controller is not runtime suspended before disabling clocks on probe failure. Also restore the autosuspend setting. Fixes: 5c6786945b4e ("spi: spi-orion: add runtime PM support") Cc: stable@vger.kernel.org # 3.17 Cc: Russell King Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260421130211.1537628-3-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-orion.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index 8efc17ff9f9c3..eb71043300a98 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -774,6 +774,7 @@ static int orion_spi_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT); + pm_runtime_get_noresume(&pdev->dev); pm_runtime_enable(&pdev->dev); status = orion_spi_reset(spi); @@ -785,10 +786,15 @@ static int orion_spi_probe(struct platform_device *pdev) if (status < 0) goto out_rel_pm; + pm_runtime_put_autosuspend(&pdev->dev); + return status; out_rel_pm: pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); out_rel_axi_clk: clk_disable_unprepare(spi->axi_clk); out: From 336d9ad7560b3baba17af06727a888040ee93390 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 21 Apr 2026 14:58:00 +0200 Subject: [PATCH 0091/1518] spi: mpc52xx: fix use-after-free on registration failure commit f62c060272b9d7423b1650b844e8e4e7b8f9f925 upstream. Make sure to disable and free the interrupts in case controller registration fails to avoid a potential use-after-free and resource leak. This issue was flagged by Sashiko when reviewing a controller deregistration fix. Fixes: 42bbb70980f3 ("powerpc/5200: Add mpc5200-spi (non-PSC) device driver") Cc: stable@vger.kernel.org # 2.6.33 Cc: Grant Likely Link: https://sashiko.dev/#/patchset/20260414134319.978196-1-johan%40kernel.org?part=3 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260421125800.1537361-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mpc52xx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c index 6d4dde15ac545..b022688221fa5 100644 --- a/drivers/spi/spi-mpc52xx.c +++ b/drivers/spi/spi-mpc52xx.c @@ -501,6 +501,9 @@ static int mpc52xx_spi_probe(struct platform_device *op) err_register: dev_err(&ms->host->dev, "initialization failed\n"); + free_irq(ms->irq0, ms); + free_irq(ms->irq1, ms); + cancel_work_sync(&ms->work); err_gpio: while (i-- > 0) gpiod_put(ms->gpio_cs[i]); From 28f28a0f4e327f792c230493a0ea00389ff68ff5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 14 Apr 2026 15:43:14 +0200 Subject: [PATCH 0092/1518] spi: mpc52xx: fix controller deregistration commit 0f997fdae819a8c2cc83bd4ff7d935ad76c727c9 upstream. Make sure to deregister the controller before disabling and releasing underlying resources like interrupts and gpios during driver unbind. Fixes: 42bbb70980f3 ("powerpc/5200: Add mpc5200-spi (non-PSC) device driver") Fixes: b8d4e2ce60b6 ("mpc52xx_spi: add gpio chipselect") Cc: stable@vger.kernel.org # 2.6.33 Cc: Grant Likely Cc: Luotao Fu Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260414134319.978196-4-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mpc52xx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c index b022688221fa5..a8d3cecb276b2 100644 --- a/drivers/spi/spi-mpc52xx.c +++ b/drivers/spi/spi-mpc52xx.c @@ -523,6 +523,8 @@ static void mpc52xx_spi_remove(struct platform_device *op) struct mpc52xx_spi *ms = spi_controller_get_devdata(host); int i; + spi_unregister_controller(host); + cancel_work_sync(&ms->work); free_irq(ms->irq0, ms); free_irq(ms->irq1, ms); @@ -531,7 +533,6 @@ static void mpc52xx_spi_remove(struct platform_device *op) gpiod_put(ms->gpio_cs[i]); kfree(ms->gpio_cs); - spi_unregister_controller(host); iounmap(ms->regs); spi_controller_put(host); } From 6c3e413919a12627d04a31a4a5fccb9fc129bb02 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 14 Apr 2026 15:43:15 +0200 Subject: [PATCH 0093/1518] spi: mpc52xx: fix use-after-free on unbind commit 706b3dc2ac7a998c55e14b3fd2e8f934c367e6e0 upstream. The state machine work is scheduled by the interrupt handler and therefore needs to be cancelled after disabling interrupts to avoid a potential use-after-free. Fixes: 984836621aad ("spi: mpc52xx: Add cancel_work_sync before module remove") Cc: stable@vger.kernel.org Cc: Pei Xiao Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260414134319.978196-5-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-mpc52xx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c index a8d3cecb276b2..84aade1416068 100644 --- a/drivers/spi/spi-mpc52xx.c +++ b/drivers/spi/spi-mpc52xx.c @@ -525,10 +525,11 @@ static void mpc52xx_spi_remove(struct platform_device *op) spi_unregister_controller(host); - cancel_work_sync(&ms->work); free_irq(ms->irq0, ms); free_irq(ms->irq1, ms); + cancel_work_sync(&ms->work); + for (i = 0; i < ms->gpio_cs_count; i++) gpiod_put(ms->gpio_cs[i]); From 59701f07b19e462d2e684c7b5b7a2ff720eadaee Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 14 Apr 2026 15:43:12 +0200 Subject: [PATCH 0094/1518] spi: cadence: fix controller deregistration commit 666fa7e9ca98e71c880086ca24147ae843f1ed6e upstream. Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: c474b3866546 ("spi: Add driver for Cadence SPI controller") Cc: stable@vger.kernel.org # 3.16 Cc: Harini Katakam Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260414134319.978196-2-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-cadence.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 5ae09b21d23a5..2d40dfe09d735 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -698,6 +698,10 @@ static void cdns_spi_remove(struct platform_device *pdev) struct spi_controller *ctlr = platform_get_drvdata(pdev); struct cdns_spi *xspi = spi_controller_get_devdata(ctlr); + spi_controller_get(ctlr); + + spi_unregister_controller(ctlr); + cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); if (!spi_controller_is_target(ctlr)) { @@ -705,7 +709,7 @@ static void cdns_spi_remove(struct platform_device *pdev) pm_runtime_set_suspended(&pdev->dev); } - spi_unregister_controller(ctlr); + spi_controller_put(ctlr); } /** From 6ac380a0071de8c17116bd31511bc33b2dafedf0 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 21 Apr 2026 14:36:12 +0200 Subject: [PATCH 0095/1518] spi: cadence: fix unclocked access on unbind commit 5b1689a41f02955c5361944f748a4812a6ff9307 upstream. Make sure that the controller is runtime resumed before disabling it during driver unbind to avoid unclocked register access and unbalanced clock disable. Also restore the autosuspend setting. This issue was flagged by Sashiko when reviewing a controller deregistration fix. Fixes: d36ccd9f7ea4 ("spi: cadence: Runtime pm adaptation") Cc: stable@vger.kernel.org # 4.7 Cc: Shubhrajyoti Datta Link: https://sashiko.dev/#/patchset/20260414134319.978196-1-johan%40kernel.org?part=1 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260421123615.1533617-2-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-cadence.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 2d40dfe09d735..9c28677907105 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -697,16 +697,23 @@ static void cdns_spi_remove(struct platform_device *pdev) { struct spi_controller *ctlr = platform_get_drvdata(pdev); struct cdns_spi *xspi = spi_controller_get_devdata(ctlr); + int ret = 0; + + if (!spi_controller_is_target(ctlr)) + ret = pm_runtime_get_sync(&pdev->dev); spi_controller_get(ctlr); spi_unregister_controller(ctlr); - cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); + if (ret >= 0) + cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); if (!spi_controller_is_target(ctlr)) { pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } spi_controller_put(ctlr); From e9ae6590405d46a75c2f9698ba2c1d28231b683f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 21 Apr 2026 14:36:13 +0200 Subject: [PATCH 0096/1518] spi: cadence: fix clock imbalance on probe failure commit ecea4f0e9db2fb6ab4a68a59c5aba0d8f59a9566 upstream. Make sure that the controller is active before disabling clocks on probe failure to avoid unbalanced clock disable. Also drop the usage count before returning (so that the controller can be suspended after a probe deferral) and restore the autosuspend setting. Fixes: d36ccd9f7ea4 ("spi: cadence: Runtime pm adaptation") Cc: stable@vger.kernel.org # 4.7 Cc: Shubhrajyoti Datta Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260421123615.1533617-3-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-cadence.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 9c28677907105..7a745c2e0892c 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -662,7 +662,6 @@ static int cdns_spi_probe(struct platform_device *pdev) /* Set to default valid value */ ctlr->max_speed_hz = xspi->clk_rate / 4; xspi->speed_hz = ctlr->max_speed_hz; - pm_runtime_put_autosuspend(&pdev->dev); } else { ctlr->mode_bits |= SPI_NO_CS; ctlr->target_abort = cdns_target_abort; @@ -673,12 +672,17 @@ static int cdns_spi_probe(struct platform_device *pdev) goto clk_dis_all; } + if (!spi_controller_is_target(ctlr)) + pm_runtime_put_autosuspend(&pdev->dev); + return ret; clk_dis_all: if (!spi_controller_is_target(ctlr)) { pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } remove_ctlr: spi_controller_put(ctlr); From c57c861956b89f2e2528e6384d51e2dedd915809 Mon Sep 17 00:00:00 2001 From: Yasuaki Torimaru Date: Wed, 25 Mar 2026 20:46:34 +0900 Subject: [PATCH 0097/1518] drm/msm/gem: fix error handling in msm_ioctl_gem_info_get_metadata() commit 47cbfe2608314b833ad61a65827d8fb363bc2d2d upstream. msm_ioctl_gem_info_get_metadata() always returns 0 regardless of errors. When copy_to_user() fails or the user buffer is too small, the error code stored in ret is ignored because the function unconditionally returns 0. This causes userspace to believe the ioctl succeeded when it did not. Additionally, kmemdup() can return NULL on allocation failure, but the return value is not checked. This leads to a NULL pointer dereference in the subsequent copy_to_user() call. Add the missing NULL check for kmemdup() and return ret instead of 0. Note that the SET counterpart (msm_ioctl_gem_info_set_metadata) correctly returns ret. Fixes: 9902cb999e4e ("drm/msm/gem: Add metadata") Cc: stable@vger.kernel.org Signed-off-by: Yasuaki Torimaru Patchwork: https://patchwork.freedesktop.org/patch/714478/ Message-ID: <20260325114635.383241-1-yasuakitorimaru@gmail.com> Signed-off-by: Rob Clark Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/msm/msm_drv.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 7e977fec41007..94b32973cd6a1 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -536,6 +536,11 @@ static int msm_ioctl_gem_info_get_metadata(struct drm_gem_object *obj, len = msm_obj->metadata_size; buf = kmemdup(msm_obj->metadata, len, GFP_KERNEL); + if (!buf) { + msm_gem_unlock(obj); + return -ENOMEM; + } + msm_gem_unlock(obj); if (*metadata_size < len) { @@ -548,7 +553,7 @@ static int msm_ioctl_gem_info_get_metadata(struct drm_gem_object *obj, kfree(buf); - return 0; + return ret; } static int msm_ioctl_gem_info(struct drm_device *dev, void *data, From c5b5a0e418b1dc33b48dc3658f7ee5db6d5187f6 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 10 Jan 2026 18:14:10 +0100 Subject: [PATCH 0098/1518] drm/imx: parallel-display: Prefer bus format set via legacy "interface-pix-fmt" DT property commit cdf26e1462c220629bb79d487263b66f8b679eab upstream. Prefer bus format set via legacy "interface-pix-fmt" DT property over panel bus format. This is necessary to retain support for DTs which configure the IPUv3 parallel output as 24bit DPI, but connect 18bit DPI panels to it with hardware swizzling. This used to work up to Linux 6.12, but stopped working in 6.13, reinstate the behavior to support old DTs. Cc: stable@vger.kernel.org Fixes: 5f6e56d3319d ("drm/imx: parallel-display: switch to drm_panel_bridge") Signed-off-by: Marek Vasut Reviewed-by: Philipp Zabel Signed-off-by: Philipp Zabel Link: https://patch.msgid.link/20260110171510.692666-1-marex@nabladev.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/imx/ipuv3/parallel-display.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c index d5f2ee41c03fe..68cd30b0bd1b0 100644 --- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c +++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c @@ -110,8 +110,7 @@ imx_pd_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, output_fmt = imxpd->bus_format ? : MEDIA_BUS_FMT_RGB888_1X24; /* Now make sure the requested output format is supported. */ - if ((imxpd->bus_format && imxpd->bus_format != output_fmt) || - !imx_pd_format_supported(output_fmt)) { + if (!imx_pd_format_supported(output_fmt)) { *num_input_fmts = 0; return NULL; } @@ -121,7 +120,17 @@ imx_pd_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, if (!input_fmts) return NULL; - input_fmts[0] = output_fmt; + /* + * Prefer bus format set via legacy "interface-pix-fmt" DT property + * over panel bus format. This is necessary to retain support for + * DTs which configure the IPUv3 parallel output as 24bit, but + * connect 18bit DPI panels to it with hardware swizzling. + */ + if (imxpd->bus_format && imxpd->bus_format != output_fmt) + input_fmts[0] = imxpd->bus_format; + else + input_fmts[0] = output_fmt; + return input_fmts; } From 132b8d51f0ffbee6e4e1ebbe1a50330aaf2dbd5d Mon Sep 17 00:00:00 2001 From: Anna Maniscalco Date: Tue, 10 Feb 2026 17:29:42 +0100 Subject: [PATCH 0099/1518] drm/msm: always recover the gpu commit 01a0d6cd7032e9993feea19fadb03ef9d5b488f2 upstream. Previously, in case there was no more work to do, recover worker wouldn't trigger recovery and would instead rely on the gpu going to sleep and then resuming when more work is submitted. Recover_worker will first increment the fence of the hung ring so, if there's only one job submitted to a ring and that causes an hang, it will early out. There's no guarantee that the gpu will suspend and resume before more work is submitted and if the gpu is in a hung state it will stay in that state and probably trigger a timeout again. Just stop checking and always recover the gpu. Signed-off-by: Anna Maniscalco Cc: stable@vger.kernel.org Patchwork: https://patchwork.freedesktop.org/patch/704066/ Message-ID: <20260210-recovery_suspend_fix-v1-1-00ed9013da04@gmail.com> Signed-off-by: Rob Clark Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/msm/msm_gpu.c | 42 +++++++++++++++++------------------ 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index dd0605fe1243d..a4377ee84c723 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -548,32 +548,30 @@ static void recover_worker(struct kthread_work *work) msm_update_fence(ring->fctx, fence); } - if (msm_gpu_active(gpu)) { - /* retire completed submits, plus the one that hung: */ - retire_submits(gpu); + /* retire completed submits, plus the one that hung: */ + retire_submits(gpu); - gpu->funcs->recover(gpu); + gpu->funcs->recover(gpu); - /* - * Replay all remaining submits starting with highest priority - * ring - */ - for (i = 0; i < gpu->nr_rings; i++) { - struct msm_ringbuffer *ring = gpu->rb[i]; - unsigned long flags; + /* + * Replay all remaining submits starting with highest priority + * ring + */ + for (i = 0; i < gpu->nr_rings; i++) { + struct msm_ringbuffer *ring = gpu->rb[i]; + unsigned long flags; - spin_lock_irqsave(&ring->submit_lock, flags); - list_for_each_entry(submit, &ring->submits, node) { - /* - * If the submit uses an unusable vm make sure - * we don't actually run it - */ - if (to_msm_vm(submit->vm)->unusable) - submit->nr_cmds = 0; - gpu->funcs->submit(gpu, submit); - } - spin_unlock_irqrestore(&ring->submit_lock, flags); + spin_lock_irqsave(&ring->submit_lock, flags); + list_for_each_entry(submit, &ring->submits, node) { + /* + * If the submit uses an unusable vm make sure + * we don't actually run it + */ + if (to_msm_vm(submit->vm)->unusable) + submit->nr_cmds = 0; + gpu->funcs->submit(gpu, submit); } + spin_unlock_irqrestore(&ring->submit_lock, flags); } pm_runtime_put(&gpu->pdev->dev); From 48fb2213e2c27f94dccf657a2ffd3c8256ad7729 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jouni=20H=C3=B6gander?= Date: Mon, 13 Apr 2026 14:23:45 +0300 Subject: [PATCH 0100/1518] drm/i915/psr: Init variable to avoid early exit from et alignment loop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 314f6179e370988ac00dadf373a4f6166eb3db15 upstream. Uninitialized boolean variable may cause unwanted exit from et alignment loop. Fix this by initializing it as false. Fixes: 1be2fca84f52 ("drm/i915/psr: Repeat Selective Update area alignment") Cc: # v6.9+ Signed-off-by: Jouni Högander Reviewed-by: Nemesa Garg Reported-by: Dan Carpenter Reviewed-by: Andi Shyti Link: https://patch.msgid.link/20260413112345.88853-1-jouni.hogander@intel.com (cherry picked from commit 289678a90b8cf81e3514c9d6c667235cd39c7acf) Signed-off-by: Tvrtko Ursulin Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_psr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 504f6228bf35d..1da20065ea776 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2840,7 +2840,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, return ret; do { - bool cursor_in_su_area; + bool cursor_in_su_area = false; /* * Adjust su area to cover cursor fully as necessary From 77d0b5d11387071770246fd0185a69fa28e8e109 Mon Sep 17 00:00:00 2001 From: Amir Shetaia Date: Fri, 10 Apr 2026 10:38:13 -0400 Subject: [PATCH 0101/1518] drm/amdkfd: Clear VRAM on allocation to prevent stale data exposure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ad52d61d82181dbdb7f05826de38352d5e550cc2 upstream. KFD VRAM allocations set AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE but not AMDGPU_GEM_CREATE_VRAM_CLEARED, leaving freshly allocated VRAM with stale data from prior use observable by compute kernels. The GEM ioctl path already sets VRAM_CLEARED for all userspace allocations via amdgpu_gem_create_ioctl() and amdgpu_mode_dumb_create(). The KFD path was missing this flag, allowing stale page table remnants to leak into user buffers. This causes crashes in RCCL P2P transport where non-zero data in ptrExchange/head/tail fields corrupts the protocol handshake. Signed-off-by: Amir Shetaia Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d3f541d3108c5..0ab85d0a6a43e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1717,7 +1717,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( alloc_domain = AMDGPU_GEM_DOMAIN_GTT; alloc_flags = 0; } else { - alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; + alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE | + AMDGPU_GEM_CREATE_VRAM_CLEARED; alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ? AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0; From 2795d325bb5c133ff7f32d9272eea4877f42f358 Mon Sep 17 00:00:00 2001 From: "Ramalingeswara Reddy, Kanala" Date: Tue, 31 Mar 2026 17:23:22 +0530 Subject: [PATCH 0102/1518] drm/amdgpu: Use SMUIO 15.0.0 offsets for TSC upper and lower count. commit 574b3b14f7d1b329fc6e67b79328f0e6f4d4b3d4 upstream. Define and use regGOLDEN_TSC_COUNT_UPPER_smu_15_0_0 and regGOLDEN_TSC_COUNT_LOWER_smu_15_0_0 for TSC upper and lower count. Acked-by: Alex Deucher Reviewed-by: Pratik Vishwakarma Signed-off-by: Ramalingeswara Reddy, Kanala Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 31 +++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 1dd9fd486eecf..feb56b6b31c9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -64,6 +64,11 @@ #define regPC_CONFIG_CNTL_1 0x194d #define regPC_CONFIG_CNTL_1_BASE_IDX 1 +#define regGOLDEN_TSC_COUNT_UPPER_smu_15_0_0 0x0030 +#define regGOLDEN_TSC_COUNT_UPPER_smu_15_0_0_BASE_IDX 1 +#define regGOLDEN_TSC_COUNT_LOWER_smu_15_0_0 0x0031 +#define regGOLDEN_TSC_COUNT_LOWER_smu_15_0_0_BASE_IDX 1 + #define regCP_GFX_MQD_CONTROL_DEFAULT 0x00000100 #define regCP_GFX_HQD_VMID_DEFAULT 0x00000000 #define regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT 0x00000000 @@ -5174,11 +5179,27 @@ static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev) amdgpu_gfx_off_ctrl(adev, true); } else { preempt_disable(); - clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); - clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); - clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); - if (clock_counter_hi_pre != clock_counter_hi_after) - clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); + if (amdgpu_ip_version(adev, SMUIO_HWIP, 0) < IP_VERSION(15, 0, 0)) { + clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_UPPER); + clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_LOWER); + clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_UPPER); + if (clock_counter_hi_pre != clock_counter_hi_after) + clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_LOWER); + } else { + clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_UPPER_smu_15_0_0); + clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_LOWER_smu_15_0_0); + clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_UPPER_smu_15_0_0); + if (clock_counter_hi_pre != clock_counter_hi_after) + clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, + regGOLDEN_TSC_COUNT_LOWER_smu_15_0_0); + } preempt_enable(); } clock = clock_counter_lo | (clock_counter_hi_after << 32ULL); From f34eda3ff33d351a9d9c078420cbe1bd258b413e Mon Sep 17 00:00:00 2001 From: Chenglei Xie Date: Tue, 7 Apr 2026 10:51:24 -0400 Subject: [PATCH 0103/1518] drm/amdgpu: gate VM CPU HDP flush on reset lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ddda81c4d7e71e41b1be91d921fd85747eddbd12 upstream. During GPU reset, the application could still run CPU page table updates. Each commit called amdgpu_device_flush_hdp(), which on SR-IOV sends work through the KIQ ring. That can advance sync_seq while the GPU is being reset, leaving fence writeback out of sync and causing amdgpu_fence_emit_polling() to time out on later KIQ use. Fix: amdgpu_vm_cpu_commit(): Reset will flush HDP anyway, the HDP flush in amdgpu_vm_cpu_commit() can be skipped when a reset is ongoging. Take reset_domain->sem with down_read_trylock() before amdgpu_device_flush_hdp(). If the reset path holds the write lock, skip the HDP flush so no HDP-related HW access (including KIQ) runs during reset; state is re-established after reset. Signed-off-by: Chenglei Xie Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c index 22e2e5b473415..f078db3fef79e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c @@ -21,6 +21,8 @@ */ #include "amdgpu_vm.h" +#include "amdgpu.h" +#include "amdgpu_reset.h" #include "amdgpu_object.h" #include "amdgpu_trace.h" @@ -108,11 +110,19 @@ static int amdgpu_vm_cpu_update(struct amdgpu_vm_update_params *p, static int amdgpu_vm_cpu_commit(struct amdgpu_vm_update_params *p, struct dma_fence **fence) { + struct amdgpu_device *adev = p->adev; + if (p->needs_flush) atomic64_inc(&p->vm->tlb_seq); mb(); - amdgpu_device_flush_hdp(p->adev, NULL); + /* A reset flushed the HDP anyway, so that here can be skipped when a reset is ongoing */ + if (!down_read_trylock(&adev->reset_domain->sem)) + return 0; + + amdgpu_device_flush_hdp(adev, NULL); + up_read(&adev->reset_domain->sem); + return 0; } From de137adccf7ade2d06e46bf9f0960ecc6be6ef13 Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Thu, 2 Apr 2026 22:44:29 -0400 Subject: [PATCH 0104/1518] drm/amd/pm: fix incorrect FeatureCtrlMask setting on smu v14.0.x commit 504f0098ebd074ac8c0ce3471795d79f68e3d265 upstream. OverDriveTable.FanMinimumPwm and FeatureCtrlMask.PP_OD_FEATURE_FAN_LEGACY_BIT have a hard dependency. Invalid handling of this dependency leads to disabled thermal monitoring and temperature boundary validation. v2: squash in typo fix (Yang) Fixes: 9710b84e2a6a ("drm/amd/pm: add overdrive support on smu v14.0.2/3") Cc: stable@vger.kernel.org Signed-off-by: Yang Wang Acked-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 470a901926f33..3924429e1120f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2442,6 +2442,7 @@ static int smu_v14_0_2_od_restore_table_single(struct smu_context *smu, long inp } od_table->OverDriveTable.FanMode = FAN_MODE_AUTO; od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + od_table->OverDriveTable.FeatureCtrlMask &= ~BIT(PP_OD_FEATURE_FAN_LEGACY_BIT); break; case PP_OD_EDIT_FAN_ZERO_RPM_ENABLE: od_table->OverDriveTable.FanZeroRpmEnable = @@ -2470,7 +2471,8 @@ static int smu_v14_0_2_od_restore_table_single(struct smu_context *smu, long inp od_table->OverDriveTable.FanMinimumPwm = boot_overdrive_table->OverDriveTable.FanMinimumPwm; od_table->OverDriveTable.FanMode = FAN_MODE_AUTO; - od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_FAN_LEGACY_BIT); + od_table->OverDriveTable.FeatureCtrlMask &= ~BIT(PP_OD_FEATURE_FAN_CURVE_BIT); break; default: dev_info(adev->dev, "Invalid table index: %ld\n", input); @@ -2640,6 +2642,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu, od_table->OverDriveTable.FanLinearPwmPoints[input[0]] = input[2]; od_table->OverDriveTable.FanMode = FAN_MODE_MANUAL_LINEAR; od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + od_table->OverDriveTable.FeatureCtrlMask &= ~BIT(PP_OD_FEATURE_FAN_LEGACY_BIT); break; case PP_OD_EDIT_ACOUSTIC_LIMIT: @@ -2709,7 +2712,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu, break; case PP_OD_EDIT_FAN_MINIMUM_PWM: - if (!smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_FAN_CURVE_BIT)) { + if (!smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_FAN_LEGACY_BIT)) { dev_warn(adev->dev, "Fan curve setting not supported!\n"); return -ENOTSUPP; } @@ -2727,7 +2730,8 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu, od_table->OverDriveTable.FanMinimumPwm = input[0]; od_table->OverDriveTable.FanMode = FAN_MODE_AUTO; - od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_FAN_LEGACY_BIT); + od_table->OverDriveTable.FeatureCtrlMask &= ~BIT(PP_OD_FEATURE_FAN_CURVE_BIT); break; case PP_OD_EDIT_FAN_ZERO_RPM_ENABLE: From 44d5a450c04d3d734c13a03561c3131020d66edf Mon Sep 17 00:00:00 2001 From: Alysa Liu Date: Mon, 30 Mar 2026 10:50:07 -0400 Subject: [PATCH 0105/1518] drm/amdkfd: Add upper bound check for num_of_nodes commit 74b73fa56a395d46745e4f245225963e9f8be7f1 upstream. drm/amdkfd: Add upper bound check for num_of_nodes in kfd_ioctl_get_process_apertures_new. Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alysa Liu Signed-off-by: Alex Deucher (cherry picked from commit 98ff46a5ea090c14d2cdb4f5b993b05d74f3949f) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 3 +++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 1 + drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 11 +++++++++++ 3 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 0f0719528bcc6..8a10ae54cd469 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -763,6 +763,9 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, goto out_unlock; } + if (args->num_of_nodes > kfd_topology_get_num_devices()) + return -EINVAL; + /* Fill in process-aperture information for all available * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 4f4eb0791138a..6788355d3fe86 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1175,6 +1175,7 @@ static inline struct kfd_node *kfd_node_by_irq_ids(struct amdgpu_device *adev, return NULL; } int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_node **kdev); +uint32_t kfd_topology_get_num_devices(void); int kfd_numa_node_to_apic_id(int numa_node_id); /* Interrupts */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 3eb32d58a1200..02b1860cde7d2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -2295,6 +2295,17 @@ int kfd_topology_remove_device(struct kfd_node *gpu) return res; } +uint32_t kfd_topology_get_num_devices(void) +{ + uint32_t num_devices; + + down_read(&topology_lock); + num_devices = sys_props.num_devices; + up_read(&topology_lock); + + return num_devices; +} + /* kfd_topology_enum_kfd_devices - Enumerate through all devices in KFD * topology. If GPU device is found @idx, then valid kfd_dev pointer is * returned through @kdev From fec8b11b55e53ff51a741e56894fe331a516f5c6 Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Wed, 25 Mar 2026 08:39:19 -0400 Subject: [PATCH 0106/1518] drm/amdgpu: Add bounds checking to ib_{get,set}_value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 66085e206431ef88ce36f53c1f53d570790ccc9e upstream. The uvd/vce/vcn code accesses the IB at predefined offsets without checking that the IB is large enough. Check the bounds here. The caller is responsible for making sure it can handle arbitrary return values. Also make the idx a uint32_t to prevent overflows causing the condition to fail. Signed-off-by: Benjamin Cheng Reviewed-by: Christian König Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 4b46e3c26ff39..0098b1eadfc87 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -547,15 +547,18 @@ void amdgpu_debugfs_ring_init(struct amdgpu_device *adev, int amdgpu_ring_init_mqd(struct amdgpu_ring *ring); -static inline u32 amdgpu_ib_get_value(struct amdgpu_ib *ib, int idx) +static inline u32 amdgpu_ib_get_value(struct amdgpu_ib *ib, uint32_t idx) { - return ib->ptr[idx]; + if (idx < ib->length_dw) + return ib->ptr[idx]; + return 0; } -static inline void amdgpu_ib_set_value(struct amdgpu_ib *ib, int idx, +static inline void amdgpu_ib_set_value(struct amdgpu_ib *ib, uint32_t idx, uint32_t value) { - ib->ptr[idx] = value; + if (idx < ib->length_dw) + ib->ptr[idx] = value; } int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm, From a6d5563ba1f03a049561cd347574613167294e8d Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Tue, 24 Mar 2026 16:42:05 -0400 Subject: [PATCH 0107/1518] drm/amdgpu/vcn4: Prevent OOB reads when parsing IB MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2444eb0ec8283f4a3845eb7febad378476e1ba3c upstream. Rewrite the IB parsing to use amdgpu_ib_get_value() which handles the bounds checks. Signed-off-by: Benjamin Cheng Acked-by: Christian König Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 3ae666522d570..85a2c42ea691d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1912,9 +1912,10 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i; + uint32_t len; - for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { - if (ib->ptr[i + 1] == id) + for (i = start; (len = amdgpu_ib_get_value(ib, i)) >= 8; i += len / 4) { + if (amdgpu_ib_get_value(ib, i + 1) == id) return i; } return -1; @@ -1925,8 +1926,6 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_ib *ib) { struct amdgpu_ring *ring = amdgpu_job_ring(job); - struct amdgpu_vcn_decode_buffer *decode_buffer; - uint64_t addr; uint32_t val; int idx = 0, sidx; @@ -1937,20 +1936,22 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + uint32_t valid_buf_flag = amdgpu_ib_get_value(ib, idx + 6); + uint64_t msg_buffer_addr; - if (!(decode_buffer->valid_buf_flag & 0x1)) + if (!(valid_buf_flag & 0x1)) return 0; - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); + msg_buffer_addr = ((u64)amdgpu_ib_get_value(ib, idx + 7)) << 32 | + amdgpu_ib_get_value(ib, idx + 8); + return vcn_v4_0_dec_msg(p, job, msg_buffer_addr); } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); - if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + if (sidx >= 0 && + amdgpu_ib_get_value(ib, sidx + 2) == RENCODE_ENCODE_STANDARD_AV1) return vcn_v4_0_limit_sched(p, job); } - idx += ib->ptr[idx] / 4; + idx += amdgpu_ib_get_value(ib, idx) / 4; } return 0; } From b3d1a0a45c4aec484fa2a5b060b611e3d3064470 Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Mon, 30 Mar 2026 15:01:27 -0400 Subject: [PATCH 0108/1518] drm/amdgpu/vce: Prevent partial address patches commit de2a02cc28d6d5d37db07d00a9a684c754a5fd74 upstream. In the case that only one of lo/hi is valid, the patching could result in a bad address written to in FW. Signed-off-by: Benjamin Cheng Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index ce318f5de047a..3b9a9010ed354 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -656,6 +656,9 @@ static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, struct amdgpu_ib *ib, uint64_t addr; int r; + if (lo >= ib->length_dw || hi >= ib->length_dw) + return -EINVAL; + if (index == 0xffffffff) index = 0; From 63b51e8a9d54317d31cc3856c1e12407070d5fc2 Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Wed, 25 Mar 2026 09:09:27 -0400 Subject: [PATCH 0109/1518] drm/amdgpu/vcn4: Prevent OOB reads when parsing dec msg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 0a78f2bac1424deb7c9d5e09c6b8e849d8e8b648 upstream. Check bounds against the end of the BO whenever we access the msg. Signed-off-by: Benjamin Cheng Reviewed-by: Christian König Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 85a2c42ea691d..64f294fb1c7a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1825,7 +1825,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, { struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo_va_mapping *map; - uint32_t *msg, num_buffers; + uint32_t *msg, num_buffers, len_dw; struct amdgpu_bo *bo; uint64_t start, end; unsigned int i; @@ -1846,6 +1846,11 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, return -EINVAL; } + if (end - addr < 16) { + DRM_ERROR("VCN messages must be at least 4 DWORDs!\n"); + return -EINVAL; + } + bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); @@ -1862,8 +1867,8 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, msg = ptr + addr - start; - /* Check length */ if (msg[1] > end - addr) { + DRM_ERROR("VCN message header does not fit in BO!\n"); r = -EINVAL; goto out; } @@ -1871,7 +1876,16 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, if (msg[3] != RDECODE_MSG_CREATE) goto out; + len_dw = msg[1] / 4; num_buffers = msg[2]; + + /* Verify that all indices fit within the claimed length. Each index is 4 DWORDs */ + if (num_buffers > len_dw || 6 + num_buffers * 4 > len_dw) { + DRM_ERROR("VCN message has too many buffers!\n"); + r = -EINVAL; + goto out; + } + for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; @@ -1881,7 +1895,8 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (offset + size > end) { + if (size < 4 || offset + size > end - addr) { + DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; } From 638e48ee39d0f2af9336f917a6f5d6692dd64d93 Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Tue, 24 Mar 2026 16:25:56 -0400 Subject: [PATCH 0110/1518] drm/amdgpu/vcn3: Prevent OOB reads when parsing dec msg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b193019860d61e92da395eae2011f2f6716b182f upstream. Check bounds against the end of the BO whenever we access the msg. Signed-off-by: Benjamin Cheng Reviewed-by: Christian König Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index d9cf8f0feeb3e..558d3bf7fc76e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1908,7 +1908,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, { struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo_va_mapping *map; - uint32_t *msg, num_buffers; + uint32_t *msg, num_buffers, len_dw; struct amdgpu_bo *bo; uint64_t start, end; unsigned int i; @@ -1929,6 +1929,11 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, return -EINVAL; } + if (end - addr < 16) { + DRM_ERROR("VCN messages must be at least 4 DWORDs!\n"); + return -EINVAL; + } + bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); @@ -1945,8 +1950,8 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, msg = ptr + addr - start; - /* Check length */ if (msg[1] > end - addr) { + DRM_ERROR("VCN message header does not fit in BO!\n"); r = -EINVAL; goto out; } @@ -1954,7 +1959,16 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, if (msg[3] != RDECODE_MSG_CREATE) goto out; + len_dw = msg[1] / 4; num_buffers = msg[2]; + + /* Verify that all indices fit within the claimed length. Each index is 4 DWORDs */ + if (num_buffers > len_dw || 6 + num_buffers * 4 > len_dw) { + DRM_ERROR("VCN message has too many buffers!\n"); + r = -EINVAL; + goto out; + } + for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; @@ -1964,14 +1978,15 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (offset + size > end) { + if (size < 4 || offset + size > end - addr) { + DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; } create = ptr + addr + offset - start; - /* H246, HEVC and VP9 can run on any instance */ + /* H264, HEVC and VP9 can run on any instance */ if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) continue; From 158def957199b6c0b4d578f369ad05cbd7789fe9 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Sat, 21 Mar 2026 06:20:33 +0100 Subject: [PATCH 0111/1518] drm/amd/display: Change dither policy for 10 bpc output back to dithering commit d65bfb1782304b03862c8c725fac608015dffd36 upstream. Commit d5df648ec830 ("drm/amd/display: Change dither policy for 10bpc to round") degraded display of 12 bpc color precision output to 10 bpc sinks by switching 10 bpc output from dithering to "truncate to 10 bpc". I don't find the argumentation in that commit convincing, but the consequences highly unfortunate, especially for applications that require effective > 10 bpc precision output of > 10 bpc framebuffers. The argument wasn't something strong like "there are hardware design defects or limitations which require us to work around broken dithering to 10 bpc", or "there are some special use cases which do require truncation to 10 bpc", but essentially "at some point in the past we used truncation in Polaris/Vega times and it looks like it got inadvertently changed for Navi, so let's do that again". I couldn't find evidence for that in the git commit logs for this. The commit message also acknowledges that using dithering "...makes some sense for FP16... ...but not for ARGB2101010 surfaces..." The problem with this is that it makes fp16 surfaces, and especially rgba16 fixed point surfaces, less useful. These are now well supported by Mesa 25.3 and later via OpenGL + EGL, Vulkan/WSI, and by OSS AMDVLK Vulkan/WSI/display, and also by GNOME 50 mutter under Wayland, and they used to provide more than 10 bpc effective precision at the output. Even for 8 or 10 bpc surfaces, the color pipeline behind the framebuffer, e.g., gamma tables, CTM, can be used for color correction and will benefit from an effective > 10 bpc output precision via dithering, retaining some precision that would get lost on the way through the pipeline, e.g., due to non-linear gamma functions. Scientific apps rely on this for > 10 bpc display precision. Truncating to 10 bpc, instead of dithering the pipeline internal 12 bpc precision down to 10 bpc, causes a serious loss of precision. This also creates the undesirable and slightly absurd situation that using a cheap monitor with only 8 bpc input and display panel will yield roughly 12 bpc precision via dithering from 12 -> 8 bpc, whereas investment into a more expensive monitor with 10 bpc input and native 10 bpc display will only yield 10 bpc, even if a fp16 or rgb16 framebuffer and/or a properly set up color pipeline (gamma tables, CTM's etc. with more than 10 bpc out precision) would allow effective 12 bpc precision output. Therefore this patch proposes reverting that commit and going back to dithering down to 10 bpc, consistent with the behaviour for 6 bpc or 8 bpc output. Successfully tested on AMD Polaris DCE 11.2 and Raven Ridge DCN 1.0 with a native 10 bpc capable monitor, outputting a RGBA16 unorm framebuffer and measuring resulting color precision with a photometer. No apparent visual artifacts or problems were observed, and effective precision was measured to be 12 bpc again, as expected. Fixes: d5df648ec830 ("drm/amd/display: Change dither policy for 10bpc to round") Signed-off-by: Mario Kleiner Tested-by: Mario Kleiner Cc: stable@vger.kernel.org Cc: Aric Cyr Cc: Anthony Koo Cc: Rodrigo Siqueira Cc: Krunoslav Kovac Cc: Alex Deucher Reported-by: Mario Kleiner Signed-off-by: Harry Wentland Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index bc5dedf5f60c3..a614bfe50630a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -4954,7 +4954,7 @@ void resource_build_bit_depth_reduction_params(struct dc_stream_state *stream, option = DITHER_OPTION_SPATIAL8; break; case COLOR_DEPTH_101010: - option = DITHER_OPTION_TRUN10; + option = DITHER_OPTION_SPATIAL10; break; default: option = DITHER_OPTION_DISABLE; From 1a17ea9861e89585361caa8bc231bd22dc6dbe7d Mon Sep 17 00:00:00 2001 From: Ashutosh Desai Date: Mon, 20 Apr 2026 01:36:37 +0000 Subject: [PATCH 0112/1518] drm/gem: Fix inconsistent plane dimension calculation in drm_gem_fb_init_with_funcs() commit 3d4c2268bd7243c3780fe32bf24ff876da272acf upstream. drm_gem_fb_init_with_funcs() computes sub-sampled plane dimensions using plain integer division: unsigned int width = mode_cmd->width / (i ? info->hsub : 1); unsigned int height = mode_cmd->height / (i ? info->vsub : 1); However, the ioctl-level framebuffer_check() in drm_framebuffer.c uses drm_format_info_plane_width/height() which round up dimensions via DIV_ROUND_UP(). This inconsistency corrupts the subsequent GEM object size check for certain pixel format and dimension combinations. For example, with NV12 (vsub=2) and a 1-pixel-tall framebuffer the GEM size validation path sees height=0 instead of height=1. The expression (height - 1) then wraps to UINT_MAX as an unsigned int, causing min_size to overflow and wrap back to a small value. A tiny GEM object therefore passes the size guard, yet when the GPU accesses the chroma plane it will read or write memory beyond the object's bounds. Fix by replacing the open-coded divisions with drm_format_info_plane_width() and drm_format_info_plane_height(), which use DIV_ROUND_UP() and match the calculation already used in framebuffer_check(). Fixes: 4c3dbb2c312c ("drm: Add GEM backed framebuffer library") Cc: stable@vger.kernel.org # v4.14+ Reviewed-by: Thomas Zimmermann Signed-off-by: Ashutosh Desai Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260420013637.457751-1-ashutoshdesai993@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gem_framebuffer_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 4bc89d33df593..daa5471365c45 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -171,8 +171,8 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, } for (i = 0; i < info->num_planes; i++) { - unsigned int width = mode_cmd->width / (i ? info->hsub : 1); - unsigned int height = mode_cmd->height / (i ? info->vsub : 1); + unsigned int width = drm_format_info_plane_width(info, mode_cmd->width, i); + unsigned int height = drm_format_info_plane_height(info, mode_cmd->height, i); unsigned int min_size; objs[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]); From a7735b491a2d18f859e14356cb71ad096f3fdf3c Mon Sep 17 00:00:00 2001 From: Sasha Finkelstein Date: Mon, 20 Apr 2026 14:17:43 +0200 Subject: [PATCH 0113/1518] drm/appletbdrm: Use kvzalloc for big allocations commit aaaa684bab1f6d9ecfc49db328facb1771fd0eb2 upstream. This driver is attached to a ~2000x80 screen, which is a lot more than a single page. This causes out of memory errors in some rare cases. Reported-by: soopyc Closes: https://github.com/t2linux/fedora/issues/51 Signed-off-by: Sasha Finkelstein Signed-off-by: Thomas Zimmermann Reviewed-by: Aditya Garg Reviewed-by: Thomas Zimmermann Fixes: 0670c2f56e45 ("drm/tiny: add driver for Apple Touch Bars in x86 Macs") Cc: # v6.15+ Link: https://patch.msgid.link/20260420-x86-tb-vmalloc-v1-1-7757ff657223@chaosmail.tech Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/tiny/appletbdrm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/tiny/appletbdrm.c b/drivers/gpu/drm/tiny/appletbdrm.c index 751b05753c947..f596e9637a7ba 100644 --- a/drivers/gpu/drm/tiny/appletbdrm.c +++ b/drivers/gpu/drm/tiny/appletbdrm.c @@ -353,7 +353,7 @@ static int appletbdrm_primary_plane_helper_atomic_check(struct drm_plane *plane, frames_size + sizeof(struct appletbdrm_fb_request_footer), 16); - appletbdrm_state->request = kzalloc(request_size, GFP_KERNEL); + appletbdrm_state->request = kvzalloc(request_size, GFP_KERNEL); if (!appletbdrm_state->request) return -ENOMEM; @@ -543,7 +543,7 @@ static void appletbdrm_primary_plane_destroy_state(struct drm_plane *plane, { struct appletbdrm_plane_state *appletbdrm_state = to_appletbdrm_plane_state(state); - kfree(appletbdrm_state->request); + kvfree(appletbdrm_state->request); kfree(appletbdrm_state->response); __drm_gem_destroy_shadow_plane_state(&appletbdrm_state->base); From db9530a9873a7c85d2266a922589ebcf427fa631 Mon Sep 17 00:00:00 2001 From: Alysa Liu Date: Tue, 21 Apr 2026 10:18:28 -0400 Subject: [PATCH 0114/1518] drm/amdkfd: validate SVM ioctl nattr against buffer size commit 045e0ff208f0838a246c10204105126611b267a1 upstream. Validate nattr field against the buffer size, preventing out-of-bounds buffer access via user-controlled attribute count. Reviewed-by: Amir Shetaia Signed-off-by: Alysa Liu Signed-off-by: Alex Deucher (cherry picked from commit 5eca8bfdfa456c3304ca77523718fe24254c172f) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 26 ++++++++++++++++++++++-- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 +++ 2 files changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 8a10ae54cd469..5755ea9a46fdc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -1676,6 +1677,16 @@ static int kfd_ioctl_smi_events(struct file *filep, return kfd_smi_event_open(pdd->dev, &args->anon_fd); } +static int kfd_ioctl_svm_validate(void *kdata, unsigned int usize) +{ + struct kfd_ioctl_svm_args *args = kdata; + size_t expected = struct_size(args, attrs, args->nattr); + + if (expected == SIZE_MAX || usize < expected) + return -EINVAL; + return 0; +} + #if IS_ENABLED(CONFIG_HSA_AMD_SVM) static int kfd_ioctl_set_xnack_mode(struct file *filep, @@ -3122,7 +3133,11 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ - .cmd_drv = 0, .name = #ioctl} + .validate = NULL, .cmd_drv = 0, .name = #ioctl} + +#define AMDKFD_IOCTL_DEF_V(ioctl, _func, _validate, _flags) \ + [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ + .validate = _validate, .cmd_drv = 0, .name = #ioctl} /** Ioctl table */ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { @@ -3219,7 +3234,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_SMI_EVENTS, kfd_ioctl_smi_events, 0), - AMDKFD_IOCTL_DEF(AMDKFD_IOC_SVM, kfd_ioctl_svm, 0), + AMDKFD_IOCTL_DEF_V(AMDKFD_IOC_SVM, kfd_ioctl_svm, + kfd_ioctl_svm_validate, 0), AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_XNACK_MODE, kfd_ioctl_set_xnack_mode, 0), @@ -3341,6 +3357,12 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) memset(kdata, 0, usize); } + if (ioctl->validate) { + retcode = ioctl->validate(kdata, usize); + if (retcode) + goto err_i1; + } + retcode = func(filep, process, kdata); if (cmd & IOC_OUT) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 6788355d3fe86..7efcc2ce191b8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1036,10 +1036,13 @@ extern struct srcu_struct kfd_processes_srcu; typedef int amdkfd_ioctl_t(struct file *filep, struct kfd_process *p, void *data); +typedef int amdkfd_ioctl_validate_t(void *kdata, unsigned int usize); + struct amdkfd_ioctl_desc { unsigned int cmd; int flags; amdkfd_ioctl_t *func; + amdkfd_ioctl_validate_t *validate; unsigned int cmd_drv; const char *name; }; From 2b5ba326f9d0ea2555b717d45548a298529fabf9 Mon Sep 17 00:00:00 2001 From: Shixiong Ou Date: Fri, 24 Apr 2026 20:44:27 +0800 Subject: [PATCH 0115/1518] drm/udl: Increase GET_URB_TIMEOUT commit ac2c996675755c725a0065dbe3e2ebffded9080b upstream. [WHY] A situation has occurred where udl_handle_damage() executed successfully and the kernel log appears normal, but the display fails to show any output. This is because the call to udl_get_urb() in udl_crtc_helper_atomic_enable() failed without generating any error message. [HOW] 1. Increase timeout of getting urb. 2. Add error messages when calling udl_get_urb() failed in udl_crtc_helper_atomic_enable(). Signed-off-by: Shixiong Ou Reviewed-by: Thomas Zimmermann Fixes: 5320918b9a87 ("drm/udl: initial UDL driver (v4)") Signed-off-by: Thomas Zimmermann Cc: # v3.4+ Link: https://patch.msgid.link/20260424124427.657-1-oushixiong1025@163.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/udl/udl_main.c | 3 +-- drivers/gpu/drm/udl/udl_modeset.c | 5 ++++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index bc58991a6f144..b4c23dbcf3e34 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -285,13 +285,12 @@ static struct urb *udl_get_urb_locked(struct udl_device *udl, long timeout) return unode->urb; } -#define GET_URB_TIMEOUT HZ struct urb *udl_get_urb(struct udl_device *udl) { struct urb *urb; spin_lock_irq(&udl->urbs.lock); - urb = udl_get_urb_locked(udl, GET_URB_TIMEOUT); + urb = udl_get_urb_locked(udl, HZ * 2); spin_unlock_irq(&udl->urbs.lock); return urb; } diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c index 231e829bd709a..1ca073a4ecb25 100644 --- a/drivers/gpu/drm/udl/udl_modeset.c +++ b/drivers/gpu/drm/udl/udl_modeset.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -342,8 +343,10 @@ static void udl_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atom return; urb = udl_get_urb(udl); - if (!urb) + if (!urb) { + drm_err_ratelimited(dev, "get urb failed when enabling crtc\n"); goto out; + } buf = (char *)urb->transfer_buffer; buf = udl_vidreg_lock(buf); From f9ad21b90162baf1d78f8036ff3813c3ec1ac88e Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Wed, 8 Apr 2026 17:52:54 +0000 Subject: [PATCH 0116/1518] drm/xe: Fix bo leak in xe_dma_buf_init_obj() on allocation failure commit 93a528f67ce5095bcab46a69839eca97f43dd352 upstream. When drm_gpuvm_resv_object_alloc() fails, the pre-allocated storage bo is not freed. Add xe_bo_free(storage) before returning the error. xe_dma_buf_init_obj() calls xe_bo_init_locked(), which frees the bo on error. Therefore, xe_dma_buf_init_obj() must also free the bo on its own error paths. Otherwise, since xe_gem_prime_import() cannot distinguish whether the failure originated from xe_dma_buf_init_obj() or from xe_bo_init_locked(), it cannot safely decide whether the bo should be freed. Add comments documenting the ownership semantics: on success, ownership of storage is transferred to the returned drm_gem_object; on failure, storage is freed before returning. v2: Add comments to explain the free logic. Fixes: eb289a5f6cc6 ("drm/xe: Convert xe_dma_buf.c for exhaustive eviction") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Matthew Brost Link: https://patch.msgid.link/20260408175255.3402838-4-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 78a6c5f899f22338bbf48b44fb8950409c5a69b9) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_dma_buf.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 2650c5abb3654..f9fe7ca32f617 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -227,6 +227,13 @@ struct dma_buf *xe_gem_prime_export(struct drm_gem_object *obj, int flags) return buf; } +/* + * Takes ownership of @storage: on success it is transferred to the returned + * drm_gem_object; on failure it is freed before returning the error. + * This matches the contract of xe_bo_init_locked() which frees @storage on + * its error paths, so callers need not (and must not) free @storage after + * this call. + */ static struct drm_gem_object * xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, struct dma_buf *dma_buf) @@ -240,8 +247,10 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, int ret = 0; dummy_obj = drm_gpuvm_resv_object_alloc(&xe->drm); - if (!dummy_obj) + if (!dummy_obj) { + xe_bo_free(storage); return ERR_PTR(-ENOMEM); + } dummy_obj->resv = resv; xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, ret) { @@ -250,6 +259,7 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, if (ret) break; + /* xe_bo_init_locked() frees storage on error */ bo = xe_bo_init_locked(xe, storage, NULL, resv, NULL, dma_buf->size, 0, /* Will require 1way or 2way for vm_bind */ ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, &exec); From cd38e1503e671576b25f859e5277a56779eb9d06 Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Wed, 8 Apr 2026 17:52:53 +0000 Subject: [PATCH 0117/1518] drm/xe/bo: Fix bo leak on GGTT flag validation in xe_bo_init_locked() commit 1d0adf2fd94fb0c0037c643fadd8f2cf3cffc009 upstream. When XE_BO_FLAG_GGTT_ALL is set without XE_BO_FLAG_GGTT, the function returns an error without freeing a caller-provided bo, violating the documented contract that bo is freed on failure. Add xe_bo_free(bo) before returning the error. Fixes: 5a3b0df25d6a ("drm/xe: Allow bo mapping on multiple ggtts") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Matthew Brost Link: https://patch.msgid.link/20260408175255.3402838-3-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 3fbd6cf43cac7b60757f3ce3d95195d3843a902c) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_bo.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index a270aef7c4980..750ddbdd08a19 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -2112,8 +2112,10 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, } /* XE_BO_FLAG_GGTTx requires XE_BO_FLAG_GGTT also be set */ - if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT)) + if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT)) { + xe_bo_free(bo); return ERR_PTR(-EINVAL); + } if (flags & (XE_BO_FLAG_VRAM_MASK | XE_BO_FLAG_STOLEN) && !(flags & XE_BO_FLAG_IGNORE_MIN_PAGE_SIZE) && From 0afa8b1ef582ecf6fb04097fd356f8741e5005ed Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Wed, 8 Apr 2026 17:52:55 +0000 Subject: [PATCH 0118/1518] drm/xe: Fix dma-buf attachment leak in xe_gem_prime_import() commit 111ab678471bf1f90d078d5513bb086b70596c3c upstream. When xe_dma_buf_init_obj() fails, the attachment from dma_buf_dynamic_attach() is not detached. Add dma_buf_detach() before returning the error. Note: we cannot use goto out_err here because xe_dma_buf_init_obj() already frees bo on failure, and out_err would double-free it. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Mattheq Brost Link: https://patch.msgid.link/20260408175255.3402838-5-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit a828eb185aac41800df8eae4b60501ccc0dbbe51) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_dma_buf.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index f9fe7ca32f617..4cef02ff14518 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -347,12 +347,15 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, goto out_err; } - /* Errors here will take care of freeing the bo. */ + /* + * xe_dma_buf_init_obj() takes ownership of bo on both success + * and failure, so we must not touch bo after this call. + */ obj = xe_dma_buf_init_obj(dev, bo, dma_buf); - if (IS_ERR(obj)) + if (IS_ERR(obj)) { + dma_buf_detach(dma_buf, attach); return obj; - - + } get_dma_buf(dma_buf); obj->import_attach = attach; return obj; From fa449b88706e05d3e3a689cedee9d95223a628ec Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Wed, 8 Apr 2026 17:52:52 +0000 Subject: [PATCH 0119/1518] drm/xe/bo: Fix bo leak on unaligned size validation in xe_bo_init_locked() commit 09a8f3c1c11977a6e10c167f26dd298790b31c32 upstream. When type is ttm_bo_type_device and aligned_size != size, the function returns an error without freeing a caller-provided bo, violating the documented contract that bo is freed on failure. Add xe_bo_free(bo) before returning the error. Fixes: 4e03b584143e ("drm/xe/uapi: Reject bo creation of unaligned size") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Matthew Brost Link: https://patch.msgid.link/20260408175255.3402838-2-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 601c2aa087b6f21014300a3f107a08ee4dde7bdf) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_bo.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 750ddbdd08a19..0dabe85351392 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -2134,8 +2134,10 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, alignment = SZ_4K >> PAGE_SHIFT; } - if (type == ttm_bo_type_device && aligned_size != size) + if (type == ttm_bo_type_device && aligned_size != size) { + xe_bo_free(bo); return ERR_PTR(-EINVAL); + } if (!bo) { bo = xe_bo_alloc(); From 87f9b1528e1ffc1da3615d552c9a06aba5e20b00 Mon Sep 17 00:00:00 2001 From: Jia Yao Date: Fri, 17 Apr 2026 05:59:16 +0000 Subject: [PATCH 0120/1518] drm/xe/uapi: Reject coh_none PAT index for CPU cached memory in madvise MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4e5591c2fc1b30f4ea5e2eab4c3a695acc404e39 upstream. Add validation in xe_vm_madvise_ioctl() to reject PAT indices with XE_COH_NONE coherency mode when applied to CPU cached memory. Using coh_none with CPU cached buffers is a security issue. When the kernel clears pages before reallocation, the clear operation stays in CPU cache (dirty). GPU with coh_none can bypass CPU caches and read stale sensitive data directly from DRAM, potentially leaking data from previously freed pages of other processes. This aligns with the existing validation in vm_bind path (xe_vm_bind_ioctl_validate_bo). v2(Matthew brost) - Add fixes - Move one debug print to better place v3(Matthew Auld) - Should be drm/xe/uapi - More Cc v4(Shuicheng Lin) - Fix kmem leak issues by the way v5 - Remove kmem leak because it has been merged by another patch v6 - Remove the fix which is not related to current fix v7 - No change v8 - Rebase v9 - Limit the restrictions to iGPU v10 - No change Fixes: ada7486c5668 ("drm/xe: Implement madvise ioctl for xe") Cc: # v6.18+ Cc: Shuicheng Lin Cc: Mathew Alwin Cc: Michal Mrozek Cc: Matthew Brost Cc: Matthew Auld Signed-off-by: Jia Yao Reviewed-by: Matthew Auld Acked-by: Michal Mrozek Acked-by: José Roberto de Souza Signed-off-by: Matthew Auld Link: https://patch.msgid.link/20260417055917.2027459-2-jia.yao@intel.com (cherry picked from commit 016ccdb674b8c899940b3944952c96a6a490d10a) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_vm_madvise.c | 47 ++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index 9dc801f657129..da306013a0131 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -299,6 +299,45 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv return true; } +static bool check_pat_args_are_sane(struct xe_device *xe, + struct xe_vmas_in_madvise_range *madvise_range, + u16 pat_index) +{ + u16 coh_mode = xe_pat_index_get_coh_mode(xe, pat_index); + int i; + + /* + * Using coh_none with CPU cached buffers is not allowed on iGPU. + * On iGPU the GPU shares the LLC with the CPU, so with coh_none + * the GPU bypasses CPU caches and reads directly from DRAM, + * potentially seeing stale sensitive data from previously freed + * pages. On dGPU this restriction does not apply, because the + * platform does not provide a non-coherent system memory access + * path that would violate the DMA coherency contract. + */ + if (coh_mode != XE_COH_NONE || IS_DGFX(xe)) + return true; + + for (i = 0; i < madvise_range->num_vmas; i++) { + struct xe_vma *vma = madvise_range->vmas[i]; + struct xe_bo *bo = xe_vma_bo(vma); + + if (bo) { + /* BO with WB caching + COH_NONE is not allowed */ + if (XE_IOCTL_DBG(xe, bo->cpu_caching == DRM_XE_GEM_CPU_CACHING_WB)) + return false; + /* Imported dma-buf without caching info, assume cached */ + if (XE_IOCTL_DBG(xe, !bo->cpu_caching)) + return false; + } else if (XE_IOCTL_DBG(xe, xe_vma_is_cpu_addr_mirror(vma) || + xe_vma_is_userptr(vma))) + /* System memory (userptr/SVM) is always CPU cached */ + return false; + } + + return true; +} + static bool check_bo_args_are_sane(struct xe_vm *vm, struct xe_vma **vmas, int num_vmas, u32 atomic_val) { @@ -384,6 +423,14 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil if (err || !madvise_range.num_vmas) goto unlock_vm; + if (args->type == DRM_XE_MEM_RANGE_ATTR_PAT) { + if (!check_pat_args_are_sane(xe, &madvise_range, + args->pat_index.val)) { + err = -EINVAL; + goto free_vmas; + } + } + if (madvise_range.has_bo_vmas) { if (args->type == DRM_XE_MEM_RANGE_ATTR_ATOMIC) { if (!check_bo_args_are_sane(vm, madvise_range.vmas, From 672464dd53231509c9c771110798c56d4660e19e Mon Sep 17 00:00:00 2001 From: "Francis, David" Date: Tue, 28 Apr 2026 19:25:50 +0000 Subject: [PATCH 0121/1518] drm: Set old handle to NULL before prime swap in change_handle commit 5e28b7b94408897e41c63477aabc9e1db439bc8c upstream. There was a potential race condition in change_handle. The ioctl briefly had a single object with two idr entries; a concurrent gem_close could delete the object and remove one of the handles while leaving the other one dangling, which could subsequently be dereferenced for a use-after-free. To fix this, do the same dance that gem_close itself does. (f6cd7daecff5 drm: Release driver references to handle before making it available again) First idr_replace the old handle to NULL. Later, if the prime operations are successful, actually close it. create_tail required a similar dance to avoid a similar problem. (bd46cece51a3 drm/gem: Fix race in drm_gem_handle_create_tail()) It idr_allocs the new handle with NULL, then swaps in the correct object later to avoid races. We don't need to do that here, since the only operations that could race are drm_prime, and change_handle holds the prime lock for the entire duration. v2: cleanups of error paths Signed-off-by: David Francis Co-authored-by: Dave Airlie Reported-by: Puttimet Thammasaeng Tested-by: Vitaly Prosyak Cc: Simona Vetter Cc: stable@vger.kernel.org Cc: Christian Koenig Fixes: 53096728b8910 ("drm: Add DRM prime interface to reassign GEM handle") Signed-off-by: Dave Airlie Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gem.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 11e7141c1524b..6d0d27aca518b 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -969,7 +969,7 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_gem_change_handle *args = data; - struct drm_gem_object *obj; + struct drm_gem_object *obj, *idrobj; int handle, ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) @@ -992,8 +992,29 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, mutex_lock(&file_priv->prime.lock); spin_lock(&file_priv->table_lock); + + /* When create_tail allocs an obj idr, it needs to first alloc as NULL, + * then later replace with the correct object. This is not necessary + * here, because the only operations that could race are drm_prime + * bookkeeping, and we hold the prime lock. + */ ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1, GFP_NOWAIT); + + if (ret < 0) { + spin_unlock(&file_priv->table_lock); + goto out_unlock; + } + + idrobj = idr_replace(&file_priv->object_idr, NULL, handle); + if (idrobj != obj) { + idr_replace(&file_priv->object_idr, idrobj, handle); + idr_remove(&file_priv->object_idr, args->new_handle); + spin_unlock(&file_priv->table_lock); + ret = -ENOENT; + goto out_unlock; + } + spin_unlock(&file_priv->table_lock); if (ret < 0) @@ -1005,6 +1026,8 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, if (ret < 0) { spin_lock(&file_priv->table_lock); idr_remove(&file_priv->object_idr, handle); + idrobj = idr_replace(&file_priv->object_idr, obj, handle); + WARN_ON(idrobj != NULL); spin_unlock(&file_priv->table_lock); goto out_unlock; } From 264ee64cf86794353e4fcb363282e3f9cf5249b3 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 27 Apr 2026 11:40:25 -0400 Subject: [PATCH 0122/1518] drm/radeon: add missing revision check for CI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 17223816498f7b117d138d18eb0eba63604dc74e upstream. The memory level workarounds only apply to revision 0 SKUs. Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/1816 Fixes: 127e056e2a82 ("drm/radeon: fix mclk vddc configuration for cards for hawaii") Fixes: 21b8a369046f ("drm/radeon: fix dram timing for certain hawaii boards") Fixes: 90b2fee35cb9 ("drm/radeon: fix dpm mc init for certain hawaii boards") Reviewed-by: Timur Kristóf Reviewed-by: Kent Russell Signed-off-by: Alex Deucher (cherry picked from commit 4d8dcc14311515077062b5740f39f427075de5c9) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/radeon/ci_dpm.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index ba8db1d07c070..b47b91272b244 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -2461,7 +2461,8 @@ static void ci_register_patching_mc_arb(struct radeon_device *rdev, if (patch && ((rdev->pdev->device == 0x67B0) || - (rdev->pdev->device == 0x67B1))) { + (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { if ((memory_clock > 100000) && (memory_clock <= 125000)) { tmp2 = (((0x31 * engine_clock) / 125000) - 1) & 0xff; *dram_timimg2 &= ~0x00ff0000; @@ -3304,7 +3305,8 @@ static int ci_populate_all_memory_levels(struct radeon_device *rdev) pi->smc_state_table.MemoryLevel[0].EnabledForActivity = 1; if ((dpm_table->mclk_table.count >= 2) && - ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1))) { + ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { pi->smc_state_table.MemoryLevel[1].MinVddc = pi->smc_state_table.MemoryLevel[0].MinVddc; pi->smc_state_table.MemoryLevel[1].MinVddcPhases = @@ -4493,7 +4495,8 @@ static int ci_register_patching_mc_seq(struct radeon_device *rdev, if (patch && ((rdev->pdev->device == 0x67B0) || - (rdev->pdev->device == 0x67B1))) { + (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { for (i = 0; i < table->last; i++) { if (table->last >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE) return -EINVAL; From b17175d0a375b3ed5e81597dac4983fdb46e478d Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 27 Apr 2026 09:30:23 -0400 Subject: [PATCH 0123/1518] drm/amdgpu: zero-initialize GART table on allocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e6c2e6c2e1fa066968a16aca1cb66cd1bdde7741 upstream. GART TLB is flushed after unmapping but not after mapping. Since amdgpu_bo_create_kernel() does not zero-initialize the buffer, when a single PTE is written the TLB may speculatively load other uninitialized entries from the same cacheline. Those garbage entries can appear valid, and a subsequent write to another PTE in the same cacheline may cause the GPU to use a stale garbage PTE from the TLB. Fix this by calling memset_io() to zero-initialize the GART table with gart_pte_flags immediately after allocation. Using AMDGPU_GEM_CREATE_VRAM_CLEARED, SDMA-based clear will not work since SDMA needs GART to be initialized to work. Suggested-by: Felix Kuehling Signed-off-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit d9af8263b82b6eaa60c5718e0c6631c5037e4b24) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 83f3b94ed975a..3392bd930c910 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -262,12 +262,19 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev) */ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev) { + int r; + if (adev->gart.bo != NULL) return 0; - return amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, - NULL, (void *)&adev->gart.ptr); + r = amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, + NULL, (void *)&adev->gart.ptr); + if (r) + return r; + + memset_io(adev->gart.ptr, adev->gart.gart_pte_flags, adev->gart.table_size); + return 0; } /** From ed21d6e4ce03b078c84fc4684b13b6a79ec43abe Mon Sep 17 00:00:00 2001 From: Osama Abdelkader Date: Thu, 23 Apr 2026 22:06:20 +0200 Subject: [PATCH 0124/1518] drm/exynos: remove bridge when component_add fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 26f6654a9a60eb4d241f42a0ec85412e8821480b upstream. Use devm_drm_bridge_add() so the bridge is released if probe fails after registration, and drop the manual drm_bridge_remove() in remove(). Check the return value of devm_drm_bridge_add(). Signed-off-by: Osama Abdelkader Fixes: 576d72fbfb45 ("drm/exynos: mic: add a bridge at probe") Cc: stable@vger.kernel.org Reviewed-by: Raphaël Gallais-Pou Reviewed-by: Luca Ceresoli Link: https://patch.msgid.link/20260423200622.325076-2-osama.abdelkader@gmail.com Signed-off-by: Luca Ceresoli Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/exynos/exynos_drm_mic.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 29a8366513fa7..e68c954ec3e61 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -423,7 +423,9 @@ static int exynos_mic_probe(struct platform_device *pdev) mic->bridge.of_node = dev->of_node; - drm_bridge_add(&mic->bridge); + ret = devm_drm_bridge_add(dev, &mic->bridge); + if (ret) + goto err; pm_runtime_enable(dev); @@ -443,12 +445,8 @@ static int exynos_mic_probe(struct platform_device *pdev) static void exynos_mic_remove(struct platform_device *pdev) { - struct exynos_mic *mic = platform_get_drvdata(pdev); - component_del(&pdev->dev, &exynos_mic_component_ops); pm_runtime_disable(&pdev->dev); - - drm_bridge_remove(&mic->bridge); } static const struct of_device_id exynos_mic_of_match[] = { From f6dbec5bee72e210a670fc05f128790bbd2b1822 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Sun, 26 Apr 2026 00:57:51 +0800 Subject: [PATCH 0125/1518] drm/panel: himax-hx83102: restore MODE_LPM after sending disable cmds commit 2d4e80271f784aa0c7b17676e9762c7e8156be1c upstream. When preparing the panel, it seems that it always expects commands to be transferred in LP mode. However, the disable function removes the MIPI_DSI_MODE_LPM flag, and no other function re-adds it. As the unprepare function contains no DSI commands, re-adding the flag just after disabling the panel should be safe. Add the code re-adding the flag after the two commands for disabling the panel are sent. This fixes screen unblanking (after blanking once) on mt8188-geralt-ciri-sku1 device. Cc: stable@vger.kernel.org # 6.11+ Fixes: 0ef94554dc40 ("drm/panel: himax-hx83102: Break out as separate driver") Signed-off-by: Icenowy Zheng Reviewed-by: Neil Armstrong Reviewed-by: Douglas Anderson Signed-off-by: Neil Armstrong Link: https://patch.msgid.link/20260425165751.1716569-1-zhengxingda@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/panel/panel-himax-hx83102.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c index 4c432d207634d..ebbd649c67dc9 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83102.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c @@ -850,6 +850,8 @@ static int hx83102_disable(struct drm_panel *panel) mipi_dsi_dcs_set_display_off_multi(&dsi_ctx); mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx); + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + mipi_dsi_msleep(&dsi_ctx, 150); return dsi_ctx.accum_err; From 71614ab2a683490bf7f43bf25afcf0d2a57a8403 Mon Sep 17 00:00:00 2001 From: "John B. Moore" Date: Tue, 28 Apr 2026 11:35:12 -0500 Subject: [PATCH 0126/1518] drm/amdgpu/gfx9: drop unnecessary 64-bit fence flag check in KIQ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 7bbfb2559bcec39d1a4e1182d931a2046112c352 upstream. Remove the BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT) assertion from gfx_v9_0_ring_emit_fence_kiq(). The KIQ hardware supports 64-bit fence writes; the 32-bit writeback address constraint is an upper-layer convention, not a hardware limitation. The check serves no purpose and should not be present. Found by code inspection while investigating related BUG_ON assertions in the GFX and compute ring emission paths. Reviewed-by: Christian König Signed-off-by: John B. Moore Signed-off-by: Alex Deucher (cherry picked from commit 1b1101a46a426bb4328116bb5273c326a2780389) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 7d0a2d239b78d..f589457f60187 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -5640,9 +5640,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr, { struct amdgpu_device *adev = ring->adev; - /* we only allocate 32bit for each seq wb address */ - BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT); - /* write fence seq to the "addr" */ amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | From 73af14be7645f3d9d190fe3bec9e8b6bf6e8f1b9 Mon Sep 17 00:00:00 2001 From: "Kory Maincent (TI)" Date: Tue, 28 Apr 2026 11:04:56 +0200 Subject: [PATCH 0127/1518] drm/bridge: tda998x: Use __be32 for audio port OF property pointer commit 2a46a9356ba7b1bdd741c8b41e5374edcd960557 upstream. of_get_property() returns a pointer to big-endian (__be32) data, but port_data in tda998x_get_audio_ports() was declared as const u32 *, causing a sparse endianness type mismatch warning. Fix the declaration to use const __be32 *. Fixes: 7e567624dc5a4 ("drm/i2c: tda998x: Register ASoC hdmi-codec and add audio DT binding") Cc: stable@vger.kernel.org Signed-off-by: Kory Maincent (TI) Reviewed-by: Russell King (Oracle) Link: https://patch.msgid.link/20260428090457.121894-1-kory.maincent@bootlin.com Signed-off-by: Luca Ceresoli Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/bridge/tda998x_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/tda998x_drv.c b/drivers/gpu/drm/bridge/tda998x_drv.c index e636459d91857..f90b08869267a 100644 --- a/drivers/gpu/drm/bridge/tda998x_drv.c +++ b/drivers/gpu/drm/bridge/tda998x_drv.c @@ -1697,7 +1697,7 @@ static const struct drm_bridge_funcs tda998x_bridge_funcs = { static int tda998x_get_audio_ports(struct tda998x_priv *priv, struct device_node *np) { - const u32 *port_data; + const __be32 *port_data; u32 size; int i; From 46bc180e6ede1cc9bfbd72cd208ad0e742d56ec8 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Sun, 3 May 2026 17:17:08 +0800 Subject: [PATCH 0128/1518] drm/panel: boe-tv101wum-nl6: restore MODE_LPM after sending disable cmds commit 570cf799e87ae805eacfab3b4ba66676b5fccdb6 upstream. When preparing the panel, it seems that it always expects commands to be transferred in LP mode. However, the disable function removes the MIPI_DSI_MODE_LPM flag, and no other function re-adds it. As the unprepare function contains no DSI commands, re-adding the flag just after disabling the panel should be safe. Add the code re-adding the flag after the two commands for disabling the panel are sent. This fixes error messages shown in kernel log when unblanking on mt8183-kukui-kodama-sku32 device. Cc: stable@vger.kernel.org Fixes: a869b9db7adf ("drm/panel: support for boe tv101wum-nl6 wuxga dsi video mode panel") Signed-off-by: Icenowy Zheng Reviewed-by: Neil Armstrong Reviewed-by: Douglas Anderson Signed-off-by: Neil Armstrong Link: https://patch.msgid.link/20260503091708.1079962-1-zhengxingda@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index d5fe105bdbdde..658ce64c71eb2 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1324,6 +1324,8 @@ static int boe_panel_disable(struct drm_panel *panel) mipi_dsi_dcs_set_display_off_multi(&ctx); mipi_dsi_dcs_enter_sleep_mode_multi(&ctx); + boe->dsi->mode_flags |= MIPI_DSI_MODE_LPM; + mipi_dsi_msleep(&ctx, 150); return ctx.accum_err; From 6fbd52d210c15f3987e04d8fa2cf6ca3ace2d0d8 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Mon, 20 Apr 2026 11:55:57 -0400 Subject: [PATCH 0129/1518] drm/amdkfd: Make all TLB-flushes heavy-weight commit 9b4e3495d1bd2469bf94b74930c153c2d534ddb7 upstream. With only one sequence number we cannot track the need for legacy vs heavy-weight flushes reliably. Always use heavy-weight. Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Signed-off-by: Alex Deucher (cherry picked from commit c1a3ff1d327820cd9a52bc1056b98681fc088949) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++-- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++--- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 6 +++--- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 ++-- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 5755ea9a46fdc..0fcf150b9ffac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1341,7 +1341,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); if (WARN_ON_ONCE(!peer_pdd)) continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(peer_pdd); } kfree(devices_arr); @@ -1436,7 +1436,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, if (WARN_ON_ONCE(!peer_pdd)) continue; if (flush_tlb) - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); + kfd_flush_tlb(peer_pdd); /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 58c5acf50a220..51a47a91e21e5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -569,7 +569,7 @@ static int allocate_vmid(struct device_queue_manager *dqm, qpd->vmid, qpd->page_table_base); /* invalidate the VM context after pasid and vmid mapping is set up */ - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY); + kfd_flush_tlb(qpd_to_pdd(qpd)); if (dqm->dev->kfd2kgd->set_scratch_backing_va) dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev, @@ -607,7 +607,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm, if (flush_texture_cache_nocpsch(q->device, qpd)) dev_err(dev, "Failed to flush TC\n"); - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY); + kfd_flush_tlb(qpd_to_pdd(qpd)); /* Release the vmid mapping */ set_pasid_vmid_mapping(dqm, 0, qpd->vmid); @@ -1282,7 +1282,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, dqm->dev->adev, qpd->vmid, qpd->page_table_base); - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(pdd); } /* Take a safe reference to the mm_struct, which may otherwise diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 7efcc2ce191b8..24e85440473a1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1533,13 +1533,13 @@ void kfd_signal_reset_event(struct kfd_node *dev); void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid); -static inline void kfd_flush_tlb(struct kfd_process_device *pdd, - enum TLB_FLUSH_TYPE type) +static inline void kfd_flush_tlb(struct kfd_process_device *pdd) { struct amdgpu_device *adev = pdd->dev->adev; struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv); - amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask); + amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT, + pdd->dev->xcc_mask); } static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 6daa70ace261f..a24b3c00f9f0a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1391,7 +1391,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start, if (r) break; } - kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT); + kfd_flush_tlb(pdd); } return r; @@ -1525,7 +1525,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset, } } - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(pdd); } return r; From 0b91ea46bb68abf98a082bf239092253bbd6aaa2 Mon Sep 17 00:00:00 2001 From: "John B. Moore" Date: Mon, 27 Apr 2026 16:06:28 -0500 Subject: [PATCH 0130/1518] drm/amdgpu/sdma4: replace BUG_ON with WARN_ON in fence emission MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 78d2e624fa073c14970aa097adcf3ea31c157a66 upstream. sdma_v4_0_ring_emit_fence() contains two BUG_ON(addr & 0x3) assertions that verify fence writeback addresses are dword-aligned. These assertions can be reached from unprivileged userspace via crafted DRM_IOCTL_AMDGPU_CS submissions, causing a fatal kernel panic in a scheduler worker thread. Replace both BUG_ON() calls with WARN_ON() to log the condition without crashing the kernel. A misaligned fence address at this point indicates a driver bug, but crashing the kernel is never the correct response when the assertion is reachable from userspace. The CS IOCTL path is the correct place to filter invalid submissions; the ring emission callback is too late to do anything about it. Fixes: 2130f89ced2c ("drm/amdgpu: add SDMA v4.0 implementation (v2)") Reviewed-by: Christian König Signed-off-by: John B. Moore Signed-off-by: Alex Deucher (cherry picked from commit b90250bd933afd1ba94d86d6b13821997b22b18e) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index f38004e6064e5..4d0dc58c90458 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -890,7 +890,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se /* write the fence */ amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE)); /* zero in first two bits */ - BUG_ON(addr & 0x3); + WARN_ON(addr & 0x3); amdgpu_ring_write(ring, lower_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(addr)); amdgpu_ring_write(ring, lower_32_bits(seq)); @@ -900,7 +900,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se addr += 4; amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE)); /* zero in first two bits */ - BUG_ON(addr & 0x3); + WARN_ON(addr & 0x3); amdgpu_ring_write(ring, lower_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(seq)); From 6fed6e9f10622db34a18ee6ce155cbe0fa211b23 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 27 Apr 2026 11:38:58 -0400 Subject: [PATCH 0131/1518] drm/amdgpu/pm: add missing revision check for CI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2a561b361b7681509710f3cfc3d95d54c87ac69f upstream. The ci_populate_all_memory_levels() workaround only applies to revision 0 SKUs. Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/1816 Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Reviewed-by: Timur Kristóf Reviewed-by: Kent Russell Signed-off-by: Alex Deucher (cherry picked from commit 1db15ba8f72f400bbad8ae0ce24fafc43429d4bd) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index ad1fd3150d03e..8870d306adb71 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -1326,8 +1326,9 @@ static int ci_populate_all_memory_levels(struct pp_hwmgr *hwmgr) dev_id = adev->pdev->device; - if ((dpm_table->mclk_table.count >= 2) - && ((dev_id == 0x67B0) || (dev_id == 0x67B1))) { + if ((dpm_table->mclk_table.count >= 2) && + ((dev_id == 0x67B0) || (dev_id == 0x67B1)) && + (adev->pdev->revision == 0)) { smu_data->smc_state_table.MemoryLevel[1].MinVddci = smu_data->smc_state_table.MemoryLevel[0].MinVddci; smu_data->smc_state_table.MemoryLevel[1].MinMvdd = From f8f546883e8777493157ccc4fac5794c502fcbd2 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 28 Apr 2026 10:42:49 -0400 Subject: [PATCH 0132/1518] drm/amdgpu/pm: align Hawaii mclk workaround with radeon MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1987c79b4fe5789dfa14423e78b5c25f6acf3e9d upstream. Align the hawaii mclk workaround with radeon and windows. Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/1816 Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Reviewed-by: Timur Kristóf Reviewed-by: Kent Russell Signed-off-by: Alex Deucher (cherry picked from commit 9649528b637f668c5af9f2b83ca4ad8576ae2121) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 8870d306adb71..0cb7eaaba3844 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -1329,10 +1329,10 @@ static int ci_populate_all_memory_levels(struct pp_hwmgr *hwmgr) if ((dpm_table->mclk_table.count >= 2) && ((dev_id == 0x67B0) || (dev_id == 0x67B1)) && (adev->pdev->revision == 0)) { - smu_data->smc_state_table.MemoryLevel[1].MinVddci = - smu_data->smc_state_table.MemoryLevel[0].MinVddci; - smu_data->smc_state_table.MemoryLevel[1].MinMvdd = - smu_data->smc_state_table.MemoryLevel[0].MinMvdd; + smu_data->smc_state_table.MemoryLevel[1].MinVddc = + smu_data->smc_state_table.MemoryLevel[0].MinVddc; + smu_data->smc_state_table.MemoryLevel[1].MinVddcPhases = + smu_data->smc_state_table.MemoryLevel[0].MinVddcPhases; } smu_data->smc_state_table.MemoryLevel[0].ActivityLevel = 0x1F; CONVERT_FROM_HOST_TO_SMC_US(smu_data->smc_state_table.MemoryLevel[0].ActivityLevel); From 3eb7d0e2d4a08d8e721aa6a75eb07692a549ce89 Mon Sep 17 00:00:00 2001 From: Viken Dadhaniya Date: Wed, 25 Mar 2026 18:30:37 +0530 Subject: [PATCH 0133/1518] arm64: dts: qcom: lemans: Correct QUP interrupt numbers commit c5b22c88cc09b180e3a23010b29f4d02ec117a44 upstream. Fix GIC_SPI interrupt numbers for QUPv3 SE6 nodes on Lemans SoC. Using incorrect interrupt lines can prevent IRQs from triggering and break I2C, SPI, and UART operation. Fixes: 34a407316b7d3 ("arm64: dts: qcom: sa8775p: Populate additional UART DT nodes") Fixes: 1b2d7ad5ac14d ("arm64: dts: qcom: sa8775p: add missing spi nodes") Fixes: ee2f5f906d69d ("arm64: dts: qcom: sa8775p: add missing i2c nodes") Cc: stable@vger.kernel.org Signed-off-by: Viken Dadhaniya Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260325-lemans-irq-num-v1-1-a470d544966a@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/lemans.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/lemans.dtsi b/arch/arm64/boot/dts/qcom/lemans.dtsi index c2d2200d845b3..530dc1e832b70 100644 --- a/arch/arm64/boot/dts/qcom/lemans.dtsi +++ b/arch/arm64/boot/dts/qcom/lemans.dtsi @@ -1563,7 +1563,7 @@ reg = <0x0 0x898000 0x0 0x4000>; #address-cells = <1>; #size-cells = <0>; - interrupts = ; + interrupts = ; clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>; clock-names = "se"; pinctrl-0 = <&qup_i2c20_default>; @@ -1590,7 +1590,7 @@ reg = <0x0 0x898000 0x0 0x4000>; #address-cells = <1>; #size-cells = <0>; - interrupts = ; + interrupts = ; clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>; clock-names = "se"; pinctrl-0 = <&qup_spi20_default>; @@ -1615,7 +1615,7 @@ uart20: serial@898000 { compatible = "qcom,geni-uart"; reg = <0x0 0x00898000 0x0 0x4000>; - interrupts = ; + interrupts = ; clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>; clock-names = "se"; pinctrl-0 = <&qup_uart20_default>; @@ -2561,7 +2561,7 @@ reg = <0x0 0xa98000 0x0 0x4000>; #address-cells = <1>; #size-cells = <0>; - interrupts = ; + interrupts = ; clocks = <&gcc GCC_QUPV3_WRAP1_S6_CLK>; clock-names = "se"; pinctrl-0 = <&qup_i2c13_default>; From cd39452498e2714340d1f94e3c29081529aec266 Mon Sep 17 00:00:00 2001 From: Siddharth Vadapalli Date: Mon, 9 Mar 2026 10:25:32 +0530 Subject: [PATCH 0134/1518] arm64: dts: ti: k3-am62a7-sk: Fix pin name in comment from M19 to N22 commit 6ee0792d83d5c690205c350825a4c30746c0e0a2 upstream. The pin for GPMC0_CLK.GPIO0_31 at address 0x000F407C is N22 and not M19. Hence, fix the pin name in the comment to avoid confusion. Fixes: 8f023012eb4a ("arm64: dts: ti: k3-am62a: Enable UHS mode support for SD cards") Cc: stable@vger.kernel.org Signed-off-by: Siddharth Vadapalli Reviewed-by: Andrew Davis Reviewed-by: Bryan Brattlof Link: https://patch.msgid.link/20260309045539.2070793-1-s-vadapalli@ti.com Signed-off-by: Vignesh Raghavendra Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/ti/k3-am62a7-sk.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts index af591fe6ae4f0..b41d8dd159ad1 100644 --- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts @@ -394,7 +394,7 @@ vddshv_sdio_pins_default: vddshv-sdio-default-pins { pinctrl-single,pins = < - AM62AX_IOPAD(0x07c, PIN_OUTPUT, 7) /* (M19) GPMC0_CLK.GPIO0_31 */ + AM62AX_IOPAD(0x07c, PIN_OUTPUT, 7) /* (N22) GPMC0_CLK.GPIO0_31 */ >; }; From c9dadb31f36045a8cb65df4bd75e7237ef21a4b5 Mon Sep 17 00:00:00 2001 From: Ben Morris Date: Thu, 7 May 2026 17:14:55 -0700 Subject: [PATCH 0135/1518] sctp: revalidate list cursor after sctp_sendmsg_to_asoc() in SCTP_SENDALL commit abb5f36771cc4c05899b34000829a787572a8817 upstream. The SCTP_SENDALL path in sctp_sendmsg() iterates ep->asocs with list_for_each_entry_safe(), which caches the next entry in @tmp before the loop body runs. The body calls sctp_sendmsg_to_asoc(), which may drop the socket lock inside sctp_wait_for_sndbuf(). While the lock is dropped, another thread can SCTP_SOCKOPT_PEELOFF the association cached in @tmp, migrating it to a new endpoint via sctp_sock_migrate() (list_del_init() + list_add_tail() to newep->asocs), and optionally close the new socket which frees the association via kfree_rcu(). The cached @tmp can also be freed by a network ABORT for that association, processed in softirq while the lock is dropped. sctp_wait_for_sndbuf() revalidates @asoc (the current entry) on re-lock via the "sk != asoc->base.sk" and "asoc->base.dead" checks, but nothing revalidates @tmp. After a successful return, the iterator advances to the stale @tmp, yielding either a use-after-free (if the peeled socket was closed) or a list-walk onto the new endpoint's list head (type confusion of &newep->asocs as a struct sctp_association *). Both are reachable from CapEff=0; the type-confusion path gives controlled indirect call via the outqueue.sched->init_sid pointer. Fix by re-deriving @tmp from @asoc after sctp_sendmsg_to_asoc() returns. @asoc is known to still be on ep->asocs at that point: the only callers that list_del an association from ep->asocs are sctp_association_free() (which sets asoc->base.dead) and sctp_assoc_migrate() (which changes asoc->base.sk), and sctp_wait_for_sndbuf() checks both under the lock before any successful return; a tripped check propagates as err < 0 and the loop bails before the re-derive. The SCTP_ABORT path in sctp_sendmsg_check_sflags() returns 0 and the loop hits 'continue' before sctp_sendmsg_to_asoc() is ever called, so the @tmp cached by list_for_each_entry_safe() still covers the lock-held free that ba59fb027307 ("sctp: walk the list of asoc safely") was added for. Fixes: 4910280503f3 ("sctp: add support for snd flag SCTP_SENDALL process in sendmsg") Cc: stable@vger.kernel.org Signed-off-by: Ben Morris Acked-by: Xin Long Link: https://patch.msgid.link/20260508001455.3137-1-joycathacker@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sctp/socket.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d190e75e46454..c57a53192beef 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1985,6 +1985,15 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_unlock; iov_iter_revert(&msg->msg_iter, err); + + /* sctp_sendmsg_to_asoc() may have released the socket + * lock (sctp_wait_for_sndbuf), during which other + * associations on ep->asocs could have been peeled + * off or freed. @asoc itself is revalidated by the + * base.dead and base.sk checks in sctp_wait_for_sndbuf, + * so re-derive the cached cursor from it. + */ + tmp = list_next_entry(asoc, asocs); } goto out_unlock; From bf872db54f91ffe70104b98c20068b2d5910e018 Mon Sep 17 00:00:00 2001 From: Lyes Bourennani Date: Wed, 22 Apr 2026 00:20:22 +0200 Subject: [PATCH 0136/1518] batman-adv: fix integer overflow on buff_pos commit 0799e5943611006b346b8813c7daf7dd5aa26bfd upstream. Fixing an integer overflow present in batadv_iv_ogm_send_to_if. The size check is done using the int type in batadv_iv_ogm_aggr_packet whereas the buff_pos variable uses the s16 type. This could lead to an out-of-bound read. Cc: stable@vger.kernel.org Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Lyes Bourennani Signed-off-by: Alexis Pinson Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_iv_ogm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f28e9cbf8ad5f..618d1889c04e7 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -335,7 +335,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); const char *fwd_str; u8 packet_num; - s16 buff_pos; + int buff_pos; struct batadv_ogm_packet *batadv_ogm_packet; struct sk_buff *skb; u8 *packet_pos; From e1e2194cc725ec1d41f9412496212f0fa0519c36 Mon Sep 17 00:00:00 2001 From: Jiexun Wang Date: Mon, 27 Apr 2026 14:43:33 +0800 Subject: [PATCH 0137/1518] batman-adv: reject new tp_meter sessions during teardown commit 3243543592425beec83d453793e9d27caa0d8e66 upstream. Prevent tp_meter from starting new sender or receiver sessions after mesh_state has left BATADV_MESH_ACTIVE. Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Co-developed-by: Luxing Yin Signed-off-by: Luxing Yin Signed-off-by: Jiexun Wang Signed-off-by: Ren Wei Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 350b149e48beb..f3c4b5e842729 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -947,6 +947,13 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, /* look for an already existing test towards this node */ spin_lock_bh(&bat_priv->tp_list_lock); + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) { + spin_unlock_bh(&bat_priv->tp_list_lock); + batadv_tp_batctl_error_notify(BATADV_TP_REASON_DST_UNREACHABLE, + dst, bat_priv, session_cookie); + return; + } + tp_vars = batadv_tp_list_find(bat_priv, dst); if (tp_vars) { spin_unlock_bh(&bat_priv->tp_list_lock); @@ -1329,9 +1336,12 @@ static struct batadv_tp_vars * batadv_tp_init_recv(struct batadv_priv *bat_priv, const struct batadv_icmp_tp_packet *icmp) { - struct batadv_tp_vars *tp_vars; + struct batadv_tp_vars *tp_vars = NULL; spin_lock_bh(&bat_priv->tp_list_lock); + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto out_unlock; + tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, icmp->session); if (tp_vars) @@ -1464,6 +1474,9 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_icmp_tp_packet *icmp; + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto out; + icmp = (struct batadv_icmp_tp_packet *)skb->data; switch (icmp->subtype) { @@ -1478,6 +1491,8 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) "Received unknown TP Metric packet type %u\n", icmp->subtype); } + +out: consume_skb(skb); } From 03660dab86f93319178a24667f6998526dc4355d Mon Sep 17 00:00:00 2001 From: Jiexun Wang Date: Mon, 27 Apr 2026 14:43:34 +0800 Subject: [PATCH 0138/1518] batman-adv: stop tp_meter sessions during mesh teardown commit 3d3cf6a7314aca4df0a6dde28ce784a2a30d0166 upstream. TP meter sessions remain linked on bat_priv->tp_list after the netlink request has already finished. When the mesh interface is removed, batadv_mesh_free() currently tears down the mesh without first draining these sessions. A running sender thread or a late incoming tp_meter packet can then keep processing against a mesh instance which is already shutting down. Synchronize tp_meter with the mesh lifetime by stopping all active sessions from batadv_mesh_free() and waiting for sender threads to exit before teardown continues. Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Co-developed-by: Luxing Yin Signed-off-by: Luxing Yin Signed-off-by: Jiexun Wang Signed-off-by: Ren Wei Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/main.c | 1 + net/batman-adv/tp_meter.c | 94 +++++++++++++++++++++++++++++++-------- net/batman-adv/tp_meter.h | 1 + net/batman-adv/types.h | 4 ++ 4 files changed, 82 insertions(+), 18 deletions(-) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 3a35aadd8b419..a4d33ee0fda59 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -249,6 +249,7 @@ void batadv_mesh_free(struct net_device *mesh_iface) atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); batadv_purge_outstanding_packets(bat_priv, NULL); + batadv_tp_stop_all(bat_priv); batadv_gw_node_free(bat_priv); diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index f3c4b5e842729..190affbad3c94 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -365,23 +366,38 @@ static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars) } /** - * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer - * @bat_priv: the bat priv with all the mesh interface information - * @tp_vars: the private data of the current TP meter session to cleanup + * batadv_tp_list_detach() - remove tp session from mesh session list once + * @tp_vars: the private data of the current TP meter session */ -static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv, - struct batadv_tp_vars *tp_vars) +static void batadv_tp_list_detach(struct batadv_tp_vars *tp_vars) { - cancel_delayed_work(&tp_vars->finish_work); + bool detached = false; spin_lock_bh(&tp_vars->bat_priv->tp_list_lock); - hlist_del_rcu(&tp_vars->list); + if (!hlist_unhashed(&tp_vars->list)) { + hlist_del_init_rcu(&tp_vars->list); + detached = true; + } spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock); + if (!detached) + return; + + atomic_dec(&tp_vars->bat_priv->tp_num); + /* drop list reference */ batadv_tp_vars_put(tp_vars); +} - atomic_dec(&tp_vars->bat_priv->tp_num); +/** + * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer + * @tp_vars: the private data of the current TP meter session to cleanup + */ +static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) +{ + cancel_delayed_work_sync(&tp_vars->finish_work); + + batadv_tp_list_detach(tp_vars); /* kill the timer and remove its reference */ timer_delete_sync(&tp_vars->timer); @@ -886,7 +902,8 @@ static int batadv_tp_send(void *arg) batadv_orig_node_put(orig_node); batadv_tp_sender_end(bat_priv, tp_vars); - batadv_tp_sender_cleanup(bat_priv, tp_vars); + batadv_tp_sender_cleanup(tp_vars); + complete(&tp_vars->finished); batadv_tp_vars_put(tp_vars); @@ -918,7 +935,8 @@ static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars) batadv_tp_vars_put(tp_vars); /* cleanup of failed tp meter variables */ - batadv_tp_sender_cleanup(bat_priv, tp_vars); + batadv_tp_sender_cleanup(tp_vars); + complete(&tp_vars->finished); return; } @@ -1024,6 +1042,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars->start_time = jiffies; init_waitqueue_head(&tp_vars->more_bytes); + init_completion(&tp_vars->finished); spin_lock_init(&tp_vars->unacked_lock); INIT_LIST_HEAD(&tp_vars->unacked_list); @@ -1126,14 +1145,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) "Shutting down for inactivity (more than %dms) from %pM\n", BATADV_TP_RECV_TIMEOUT, tp_vars->other_end); - spin_lock_bh(&tp_vars->bat_priv->tp_list_lock); - hlist_del_rcu(&tp_vars->list); - spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock); - - /* drop list reference */ - batadv_tp_vars_put(tp_vars); - - atomic_dec(&bat_priv->tp_num); + batadv_tp_list_detach(tp_vars); spin_lock_bh(&tp_vars->unacked_lock); list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { @@ -1496,6 +1508,52 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) consume_skb(skb); } +/** + * batadv_tp_stop_all() - stop all currently running tp meter sessions + * @bat_priv: the bat priv with all the mesh interface information + */ +void batadv_tp_stop_all(struct batadv_priv *bat_priv) +{ + struct batadv_tp_vars *tp_vars[BATADV_TP_MAX_NUM]; + struct batadv_tp_vars *tp_var; + size_t count = 0; + size_t i; + + spin_lock_bh(&bat_priv->tp_list_lock); + hlist_for_each_entry(tp_var, &bat_priv->tp_list, list) { + if (WARN_ON_ONCE(count >= BATADV_TP_MAX_NUM)) + break; + + if (!kref_get_unless_zero(&tp_var->refcount)) + continue; + + tp_vars[count++] = tp_var; + } + spin_unlock_bh(&bat_priv->tp_list_lock); + + for (i = 0; i < count; i++) { + tp_var = tp_vars[i]; + + switch (tp_var->role) { + case BATADV_TP_SENDER: + batadv_tp_sender_shutdown(tp_var, + BATADV_TP_REASON_CANCEL); + wake_up(&tp_var->more_bytes); + wait_for_completion(&tp_var->finished); + break; + case BATADV_TP_RECEIVER: + batadv_tp_list_detach(tp_var); + if (timer_shutdown_sync(&tp_var->timer)) + batadv_tp_vars_put(tp_var); + break; + } + + batadv_tp_vars_put(tp_var); + } + + synchronize_net(); +} + /** * batadv_tp_meter_init() - initialize global tp_meter structures */ diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index f0046d366eac6..4e97cd10cd025 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -17,6 +17,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, u32 test_length, u32 *cookie); void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst, u8 return_value); +void batadv_tp_stop_all(struct batadv_priv *bat_priv); void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb); #endif /* _NET_BATMAN_ADV_TP_METER_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ae1d7a8dc480f..41c1d19f786bb 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -1328,6 +1329,9 @@ struct batadv_tp_vars { /** @finish_work: work item for the finishing procedure */ struct delayed_work finish_work; + /** @finished: completion signaled when a sender thread exits */ + struct completion finished; + /** @test_length: test length in milliseconds */ u32 test_length; From 09dc0d1a12222ffca6481916eab3cfea477b9620 Mon Sep 17 00:00:00 2001 From: Jiexun Wang Date: Sun, 3 May 2026 12:28:58 +0800 Subject: [PATCH 0139/1518] batman-adv: stop caching unowned originator pointers in BAT IV commit f03e8583532941b07761c5429de7d50766fa3110 upstream. BAT IV keeps the last-hop neighbor address in each neigh_node, but some paths also cache an originator pointer derived from a temporary lookup. That pointer is not owned by the neigh_node and may no longer refer to a live originator entry after purge handling runs. Stop storing the auxiliary originator pointer in the BAT IV neighbor state. When BAT IV needs the neighbor originator data, resolve it from the stored neighbor address and drop the reference again after use. Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Jiexun Wang Signed-off-by: Ren Wei [sven: avoid bonding logic for outgoing OGM] Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_iv_ogm.c | 83 ++++++++++++++++++++++++++----------- 1 file changed, 59 insertions(+), 24 deletions(-) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 618d1889c04e7..74ef7dc2b2f98 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -173,19 +173,12 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) static struct batadv_neigh_node * batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, - struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh) + struct batadv_orig_node *orig_node) { struct batadv_neigh_node *neigh_node; neigh_node = batadv_neigh_node_get_or_create(orig_node, hard_iface, neigh_addr); - if (!neigh_node) - goto out; - - neigh_node->orig_node = orig_neigh; - -out: return neigh_node; } @@ -906,6 +899,31 @@ static u8 batadv_iv_orig_ifinfo_sum(struct batadv_orig_node *orig_node, return sum; } +/** + * batadv_iv_ogm_neigh_ifinfo_sum() - Get bcast_own sum for a last-hop neighbor + * @bat_priv: the bat priv with all the mesh interface information + * @neigh_node: last-hop neighbor of an originator + * + * Return: Number of replied (rebroadcasted) OGMs for the originator currently + * announced by the neighbor. Returns 0 if the neighbor's originator entry is + * not available anymore. + */ +static u8 batadv_iv_ogm_neigh_ifinfo_sum(struct batadv_priv *bat_priv, + const struct batadv_neigh_node *neigh_node) +{ + struct batadv_orig_node *orig_neigh; + u8 sum; + + orig_neigh = batadv_orig_hash_find(bat_priv, neigh_node->addr); + if (!orig_neigh) + return 0; + + sum = batadv_iv_orig_ifinfo_sum(orig_neigh, neigh_node->if_incoming); + batadv_orig_node_put(orig_neigh); + + return sum; +} + /** * batadv_iv_ogm_orig_update() - use OGM to update corresponding data in an * originator @@ -975,17 +993,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, } if (!neigh_node) { - struct batadv_orig_node *orig_tmp; - - orig_tmp = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source); - if (!orig_tmp) - goto unlock; - neigh_node = batadv_iv_ogm_neigh_new(if_incoming, ethhdr->h_source, - orig_node, orig_tmp); - - batadv_orig_node_put(orig_tmp); + orig_node); if (!neigh_node) goto unlock; } else { @@ -1037,10 +1047,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, */ if (router_ifinfo && neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) { - sum_orig = batadv_iv_orig_ifinfo_sum(router->orig_node, - router->if_incoming); - sum_neigh = batadv_iv_orig_ifinfo_sum(neigh_node->orig_node, - neigh_node->if_incoming); + sum_orig = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, router); + sum_neigh = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, + neigh_node); if (sum_orig >= sum_neigh) goto out; } @@ -1106,7 +1115,6 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, if (!neigh_node) neigh_node = batadv_iv_ogm_neigh_new(if_incoming, orig_neigh_node->orig, - orig_neigh_node, orig_neigh_node); if (!neigh_node) @@ -1302,6 +1310,32 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, return ret; } +/** + * batadv_orig_to_direct_router() - get direct next hop neighbor to an orig address + * @bat_priv: the bat priv with all the mesh interface information + * @orig_addr: the originator MAC address to search the best next hop router for + * @if_outgoing: the interface where the OGM should be sent to + * + * Return: A neighbor node which is the best router towards the given originator + * address. Bonding candidates are ignored. + */ +static struct batadv_neigh_node * +batadv_orig_to_direct_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_orig_node *orig_node; + + orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + if (!orig_node) + return NULL; + + neigh_node = batadv_orig_router_get(orig_node, if_outgoing); + batadv_orig_node_put(orig_node); + + return neigh_node; +} + /** * batadv_iv_ogm_process_per_outif() - process a batman iv OGM for an outgoing * interface @@ -1372,8 +1406,9 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, router = batadv_orig_router_get(orig_node, if_outgoing); if (router) { - router_router = batadv_orig_router_get(router->orig_node, - if_outgoing); + router_router = batadv_orig_to_direct_router(bat_priv, + router->addr, + if_outgoing); router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); } From 00155f336a5e8b1006d2ca9ae7ad8fc4a44bb401 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 6 May 2026 22:20:50 +0200 Subject: [PATCH 0140/1518] batman-adv: bla: prevent use-after-free when deleting claims commit 4ae1709a314060a196981b344610d023ea841e57 upstream. When batadv_bla_del_backbone_claims() removes all claims for a backbone, it does this by dropping the link entry in the hash list. This list entry itself was one of the references which need to be dropped at the same time via batadv_claim_put(). But the batadv_claim_put() must not be done before the last access to the claim object in this function. Otherwise the claim might be freed already by the batadv_claim_release() function before the list entry was dropped. Cc: stable@kernel.org Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index d4f4e97a27f10..41313ea219358 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -319,8 +319,8 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) if (claim->backbone_gw != backbone_gw) continue; - batadv_claim_put(claim); hlist_del_rcu(&claim->hash_entry); + batadv_claim_put(claim); } spin_unlock_bh(list_lock); } From b65365d2b1e6095c538d49baeb140dd1c166c1b3 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 6 May 2026 22:20:51 +0200 Subject: [PATCH 0141/1518] batman-adv: bla: only purge non-released claims commit cf6b604011591865ae39ac82de8978c1120d17af upstream. When batadv_bla_purge_claims() goes through the list of claims, it is only traversing the hash list with an rcu_read_lock(). Due to a potential parallel batadv_claim_put(), it can happen that it encounters a claim which was actually in the process of being released+freed by batadv_claim_release(). In this case, backbone_gw is set to NULL before the delayed RCU kfree is started. Calling batadv_bla_claim_get_backbone_gw() is then no longer allowed because it would cause a NULL-ptr derefence. To avoid this, only claims with a valid reference counter must be purged. All others are already taken care of. Cc: stable@kernel.org Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 41313ea219358..fd5ba288c7b12 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1289,6 +1289,13 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { + /* only purge claims not currently in the process of being released. + * Such claims could otherwise have a NULL-ptr backbone_gw set because + * they already went through batadv_claim_release() + */ + if (!kref_get_unless_zero(&claim->refcount)) + continue; + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; @@ -1314,6 +1321,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, claim->addr, claim->vid); skip: batadv_backbone_gw_put(backbone_gw); + batadv_claim_put(claim); } rcu_read_unlock(); } From 0baf4b659cdc7305cf685b5a5d60f9e3816ab5d0 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 6 May 2026 22:20:52 +0200 Subject: [PATCH 0142/1518] batman-adv: bla: put backbone reference on failed claim hash insert commit ba9d20ee9076dac32c371116bacbe72480eb356c upstream. When batadv_bla_add_claim() fails to insert a new claim into the hash, it leaked a reference to the backbone_gw for which the claim was intended. Call batadv_backbone_gw_put() on the error path to release the reference and avoid leaking the backbone_gw object. Cc: stable@kernel.org Fixes: 3db0decf1185 ("batman-adv: Fix non-atomic bla_claim::backbone_gw access") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index fd5ba288c7b12..2d7971424aa0e 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -724,6 +724,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, if (unlikely(hash_added != 0)) { /* only local changes happened. */ + batadv_backbone_gw_put(backbone_gw); kfree(claim); return; } From 1a516d19100e2e987d75cd694161f40d3d60b911 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 23 Mar 2026 12:43:57 +0000 Subject: [PATCH 0143/1518] io_uring/zcrx: use guards for locking commit 898ad80d1207cbdb22b21bafb6de4adfd7627bd0 upstream. Convert last several places using manual locking to guards to simplify the code. Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/eb4667cfaf88c559700f6399da9e434889f5b04a.1774261953.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman --- io_uring/zcrx.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index d17ff07779dee..50116e7c51459 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -696,9 +696,8 @@ static void io_zcrx_return_niov_freelist(struct net_iov *niov) { struct io_zcrx_area *area = io_zcrx_iov_to_area(niov); - spin_lock_bh(&area->freelist_lock); + guard(spinlock_bh)(&area->freelist_lock); area->freelist[area->free_count++] = net_iov_idx(niov); - spin_unlock_bh(&area->freelist_lock); } static void io_zcrx_return_niov(struct net_iov *niov) @@ -829,7 +828,8 @@ static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq) { struct io_zcrx_area *area = ifq->area; - spin_lock_bh(&area->freelist_lock); + guard(spinlock_bh)(&area->freelist_lock); + while (area->free_count && pp->alloc.count < PP_ALLOC_CACHE_REFILL) { struct net_iov *niov = __io_zcrx_get_free_niov(area); netmem_ref netmem = net_iov_to_netmem(niov); @@ -838,7 +838,6 @@ static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq) io_zcrx_sync_for_device(pp, niov); net_mp_netmem_place_in_cache(pp, netmem); } - spin_unlock_bh(&area->freelist_lock); } static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) @@ -975,10 +974,10 @@ static struct net_iov *io_alloc_fallback_niov(struct io_zcrx_ifq *ifq) if (area->mem.is_dmabuf) return NULL; - spin_lock_bh(&area->freelist_lock); - if (area->free_count) - niov = __io_zcrx_get_free_niov(area); - spin_unlock_bh(&area->freelist_lock); + scoped_guard(spinlock_bh, &area->freelist_lock) { + if (area->free_count) + niov = __io_zcrx_get_free_niov(area); + } if (niov) page_pool_fragment_netmem(net_iov_to_netmem(niov), 1); From f49a00180dfc05032e2786606095ba9215db1344 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 21 Apr 2026 09:45:29 +0100 Subject: [PATCH 0144/1518] io_uring/zcrx: warn on freelist violations commit 770594e78c3964cf23cf5287f849437cdde9b7d0 upstream. The freelist is appropriately sized to always be able to take a free niov, but let's be more defensive and check the invariant with a warning. That should help to catch any double-free issues. Suggested-by: Kai Aizen Signed-off-by: Pavel Begunkov Link: https://patch.msgid.link/2f3cea363b04649755e3b6bb9ab66485a95936d5.1776760901.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman --- io_uring/zcrx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 50116e7c51459..b768f43f0fd1f 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -697,6 +697,8 @@ static void io_zcrx_return_niov_freelist(struct net_iov *niov) struct io_zcrx_area *area = io_zcrx_iov_to_area(niov); guard(spinlock_bh)(&area->freelist_lock); + if (WARN_ON_ONCE(area->free_count >= area->nia.num_niovs)) + return; area->freelist[area->free_count++] = net_iov_idx(niov); } From 20048f0b38cd74a265588c6c4e93466279f88101 Mon Sep 17 00:00:00 2001 From: Xianglai Li Date: Mon, 4 May 2026 09:00:37 +0800 Subject: [PATCH 0145/1518] LoongArch: KVM: Compile switch.S directly into the kernel commit 5203012fa6045aac4b69d4e7c212e16dcf38ef10 upstream. If we directly compile the switch.S file into the kernel, the address of the kvm_exc_entry function will definitely be within the DMW memory area. Therefore, we will no longer need to perform a copy relocation of the kvm_exc_entry. So this patch compiles switch.S directly into the kernel, and then remove the copy relocation execution logic for the kvm_exc_entry function. Cc: stable@vger.kernel.org Signed-off-by: Xianglai Li Signed-off-by: Huacai Chen Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/Kbuild | 2 +- arch/loongarch/include/asm/asm-prototypes.h | 20 ++++++++++++ arch/loongarch/include/asm/kvm_host.h | 3 -- arch/loongarch/kvm/Makefile | 3 +- arch/loongarch/kvm/main.c | 35 ++------------------- arch/loongarch/kvm/switch.S | 20 +++++++++--- 6 files changed, 41 insertions(+), 42 deletions(-) diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild index beb8499dd8ed8..1c7a0dbe5e72f 100644 --- a/arch/loongarch/Kbuild +++ b/arch/loongarch/Kbuild @@ -3,7 +3,7 @@ obj-y += mm/ obj-y += net/ obj-y += vdso/ -obj-$(CONFIG_KVM) += kvm/ +obj-$(subst m,y,$(CONFIG_KVM)) += kvm/ # for cleaning subdir- += boot diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h index 704066b4f7368..de0c17f3f49c2 100644 --- a/arch/loongarch/include/asm/asm-prototypes.h +++ b/arch/loongarch/include/asm/asm-prototypes.h @@ -20,3 +20,23 @@ asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_ struct pt_regs *regs, int (*fn)(void *), void *fn_arg); + +struct kvm_run; +struct kvm_vcpu; +struct loongarch_fpu; + +void kvm_exc_entry(void); +int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); + +void kvm_save_fpu(struct loongarch_fpu *fpu); +void kvm_restore_fpu(struct loongarch_fpu *fpu); + +#ifdef CONFIG_CPU_HAS_LSX +void kvm_save_lsx(struct loongarch_fpu *fpu); +void kvm_restore_lsx(struct loongarch_fpu *fpu); +#endif + +#ifdef CONFIG_CPU_HAS_LASX +void kvm_save_lasx(struct loongarch_fpu *fpu); +void kvm_restore_lasx(struct loongarch_fpu *fpu); +#endif diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 0cecbd038bb3c..377d7fb04bda1 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -85,7 +85,6 @@ struct kvm_context { struct kvm_world_switch { int (*exc_entry)(void); int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu); - unsigned long page_order; }; #define MAX_PGTABLE_LEVELS 4 @@ -339,8 +338,6 @@ void kvm_exc_entry(void); int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); extern unsigned long vpid_mask; -extern const unsigned long kvm_exception_size; -extern const unsigned long kvm_enter_guest_size; extern struct kvm_world_switch *kvm_loongarch_ops; #define SW_GCSR (1 << 0) diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile index cb41d9265662f..f32a170c18388 100644 --- a/arch/loongarch/kvm/Makefile +++ b/arch/loongarch/kvm/Makefile @@ -7,11 +7,12 @@ include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o +obj-y += switch.o + kvm-y += exit.o kvm-y += interrupt.o kvm-y += main.o kvm-y += mmu.o -kvm-y += switch.o kvm-y += timer.o kvm-y += tlb.o kvm-y += vcpu.o diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 80ea63d465b8e..67d234540ed4c 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -340,8 +340,7 @@ void kvm_arch_disable_virtualization_cpu(void) static int kvm_loongarch_env_init(void) { - int cpu, order, ret; - void *addr; + int cpu, ret; struct kvm_context *context; vmcs = alloc_percpu(struct kvm_context); @@ -357,30 +356,8 @@ static int kvm_loongarch_env_init(void) return -ENOMEM; } - /* - * PGD register is shared between root kernel and kvm hypervisor. - * So world switch entry should be in DMW area rather than TLB area - * to avoid page fault reenter. - * - * In future if hardware pagetable walking is supported, we won't - * need to copy world switch code to DMW area. - */ - order = get_order(kvm_exception_size + kvm_enter_guest_size); - addr = (void *)__get_free_pages(GFP_KERNEL, order); - if (!addr) { - free_percpu(vmcs); - vmcs = NULL; - kfree(kvm_loongarch_ops); - kvm_loongarch_ops = NULL; - return -ENOMEM; - } - - memcpy(addr, kvm_exc_entry, kvm_exception_size); - memcpy(addr + kvm_exception_size, kvm_enter_guest, kvm_enter_guest_size); - flush_icache_range((unsigned long)addr, (unsigned long)addr + kvm_exception_size + kvm_enter_guest_size); - kvm_loongarch_ops->exc_entry = addr; - kvm_loongarch_ops->enter_guest = addr + kvm_exception_size; - kvm_loongarch_ops->page_order = order; + kvm_loongarch_ops->exc_entry = (void *)kvm_exc_entry; + kvm_loongarch_ops->enter_guest = (void *)kvm_enter_guest; vpid_mask = read_csr_gstat(); vpid_mask = (vpid_mask & CSR_GSTAT_GIDBIT) >> CSR_GSTAT_GIDBIT_SHIFT; @@ -414,16 +391,10 @@ static int kvm_loongarch_env_init(void) static void kvm_loongarch_env_exit(void) { - unsigned long addr; - if (vmcs) free_percpu(vmcs); if (kvm_loongarch_ops) { - if (kvm_loongarch_ops->exc_entry) { - addr = (unsigned long)kvm_loongarch_ops->exc_entry; - free_pages(addr, kvm_loongarch_ops->page_order); - } kfree(kvm_loongarch_ops); } diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index 9eaad5dbed910..281daf0b78109 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -4,9 +4,11 @@ */ #include +#include #include #include #include +#include #include #include @@ -100,8 +102,13 @@ * - is still in guest mode, such as pgd table/vmid registers etc, * - will fix with hw page walk enabled in future * load kvm_vcpu from reserved CSR KVM_VCPU_KS, and save a2 to KVM_TEMP_KS + * + * PGD register is shared between root kernel and kvm hypervisor. + * So world switch entry should be in DMW area rather than TLB area + * to avoid page fault re-enter. */ .text + .p2align PAGE_SHIFT .cfi_sections .debug_frame SYM_CODE_START(kvm_exc_entry) UNWIND_HINT_END_OF_STACK @@ -190,8 +197,8 @@ ret_to_host: kvm_restore_host_gpr a2 jr ra -SYM_INNER_LABEL(kvm_exc_entry_end, SYM_L_LOCAL) SYM_CODE_END(kvm_exc_entry) +EXPORT_SYMBOL_GPL(kvm_exc_entry) /* * int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -215,8 +222,8 @@ SYM_FUNC_START(kvm_enter_guest) /* Save kvm_vcpu to kscratch */ csrwr a1, KVM_VCPU_KS kvm_switch_to_guest -SYM_INNER_LABEL(kvm_enter_guest_end, SYM_L_LOCAL) SYM_FUNC_END(kvm_enter_guest) +EXPORT_SYMBOL_GPL(kvm_enter_guest) SYM_FUNC_START(kvm_save_fpu) fpu_save_csr a0 t1 @@ -224,6 +231,7 @@ SYM_FUNC_START(kvm_save_fpu) fpu_save_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_save_fpu) +EXPORT_SYMBOL_GPL(kvm_save_fpu) SYM_FUNC_START(kvm_restore_fpu) fpu_restore_double a0 t1 @@ -231,6 +239,7 @@ SYM_FUNC_START(kvm_restore_fpu) fpu_restore_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_fpu) +EXPORT_SYMBOL_GPL(kvm_restore_fpu) #ifdef CONFIG_CPU_HAS_LSX SYM_FUNC_START(kvm_save_lsx) @@ -239,6 +248,7 @@ SYM_FUNC_START(kvm_save_lsx) lsx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lsx) +EXPORT_SYMBOL_GPL(kvm_save_lsx) SYM_FUNC_START(kvm_restore_lsx) lsx_restore_data a0 t1 @@ -246,6 +256,7 @@ SYM_FUNC_START(kvm_restore_lsx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lsx) +EXPORT_SYMBOL_GPL(kvm_restore_lsx) #endif #ifdef CONFIG_CPU_HAS_LASX @@ -255,6 +266,7 @@ SYM_FUNC_START(kvm_save_lasx) lasx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lasx) +EXPORT_SYMBOL_GPL(kvm_save_lasx) SYM_FUNC_START(kvm_restore_lasx) lasx_restore_data a0 t1 @@ -262,10 +274,8 @@ SYM_FUNC_START(kvm_restore_lasx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lasx) +EXPORT_SYMBOL_GPL(kvm_restore_lasx) #endif - .section ".rodata" -SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry) -SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest) #ifdef CONFIG_CPU_HAS_LBT STACK_FRAME_NON_STANDARD kvm_restore_fpu From 679e65ae721c9d2e2c3a52d4a3bad239f75adbe4 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Thu, 15 Jan 2026 07:20:41 -0800 Subject: [PATCH 0146/1518] mm/damon/core: implement damon_kdamond_pid() commit 4262c53236977de3ceaa3bf2aefdf772c9b874dd upstream. Patch series "mm/damon: hide kdamond and kdamond_lock from API callers". 'kdamond' and 'kdamond_lock' fields initially exposed to DAMON API callers for flexible synchronization and use cases. As DAMON API became somewhat complicated compared to the early days, Keeping those exposed could only encourage the API callers to invent more creative but complicated and difficult-to-debug use cases. Fortunately DAMON API callers didn't invent that many creative use cases. There exist only two use cases of 'kdamond' and 'kdamond_lock'. Finding whether the kdamond is actively running, and getting the pid of the kdamond. For the first use case, a dedicated API function, namely 'damon_is_running()' is provided, and all DAMON API callers are using the function for the use case. Hence only the second use case is where the fields are directly being used by DAMON API callers. To prevent future invention of complicated and erroneous use cases of the fields, hide the fields from the API callers. For that, provide new dedicated DAMON API functions for the remaining use case, namely damon_kdamond_pid(), migrate DAMON API callers to use the new function, and mark the fields as private fields. This patch (of 5): 'kdamond' and 'kdamond_lock' are directly being used by DAMON API callers for getting the pid of the corresponding kdamond. To discourage invention of creative but complicated and erroneous new usages of the fields that require careful synchronization, implement a new API function that can simply be used without the manual synchronizations. Link: https://lkml.kernel.org/r/20260115152047.68415-1-sj@kernel.org Link: https://lkml.kernel.org/r/20260115152047.68415-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/damon.h | 1 + mm/damon/core.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) diff --git a/include/linux/damon.h b/include/linux/damon.h index 6fe6f7fcf83d8..d902381950908 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -949,6 +949,7 @@ bool damon_initialized(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); bool damon_is_running(struct damon_ctx *ctx); +int damon_kdamond_pid(struct damon_ctx *ctx); int damon_call(struct damon_ctx *ctx, struct damon_call_control *control); int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control); diff --git a/mm/damon/core.c b/mm/damon/core.c index c46236b73b2d6..0ae73905fc51e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1436,6 +1436,23 @@ bool damon_is_running(struct damon_ctx *ctx) return running; } +/** + * damon_kdamond_pid() - Return pid of a given DAMON context's worker thread. + * @ctx: The DAMON context of the question. + * + * Return: pid if @ctx is running, negative error code otherwise. + */ +int damon_kdamond_pid(struct damon_ctx *ctx) +{ + int pid = -EINVAL; + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) + pid = ctx->kdamond->pid; + mutex_unlock(&ctx->kdamond_lock); + return pid; +} + /** * damon_call() - Invoke a given function on DAMON worker thread (kdamond). * @ctx: DAMON context to call the function for. From 4697ed7be9b991c9790fa322b3e7302491704668 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Sun, 19 Apr 2026 09:10:01 -0700 Subject: [PATCH 0147/1518] mm/damon/lru_sort: detect and use fresh enabled and kdamond_pid values commit b98b7ff6025ae82570d4915e083f0cbd8d48b3cf upstream. DAMON_LRU_SORT updates 'enabled' and 'kdamond_pid' parameter values, which represents the running status of its kdamond, when the user explicitly requests start/stop of the kdamond. The kdamond can, however, be stopped in events other than the explicit user request in the following three events. 1. ctx->regions_score_histogram allocation failure at beginning of the execution, 2. damon_commit_ctx() failure due to invalid user input, and 3. damon_commit_ctx() failure due to its internal allocation failures. Hence, if the kdamond is stopped by the above three events, the values of the status parameters can be stale. Users could show the stale values and be confused. This is already bad, but the real consequence is worse. DAMON_LRU_SORT avoids unnecessary damon_start() and damon_stop() calls based on the 'enabled' parameter value. And the update of 'enabled' parameter value depends on the damon_start() and damon_stop() call results. Hence, once the kdamond has stopped by the unintentional events, the user cannot restart the kdamond before the system reboot. For example, the issue can be reproduced via below steps. # cd /sys/module/damon_lru_sort/parameters # # # start DAMON_LRU_SORT # echo Y > enabled # ps -ef | grep kdamond root 806 2 0 17:53 ? 00:00:00 [kdamond.0] root 808 803 0 17:53 pts/4 00:00:00 grep kdamond # # # commit wrong input to stop kdamond withou explicit stop request # echo 3 > addr_unit # echo Y > commit_inputs bash: echo: write error: Invalid argument # # # confirm kdamond is stopped # ps -ef | grep kdamond root 811 803 0 17:53 pts/4 00:00:00 grep kdamond # # # users casn now show stable status # cat enabled Y # cat kdamond_pid 806 # # # even after fixing the wrong parameter, # # kdamond cannot be restarted. # echo 1 > addr_unit # echo Y > enabled # ps -ef | grep kdamond root 815 803 0 17:54 pts/4 00:00:00 grep kdamond The problem will only rarely happen in real and common setups for the following reasons. The allocation failures are unlikely in such setups since those allocations are arguably too small to fail. Also sane users on real production environments may not commit wrong input parameters. But once it happens, the consequence is quite bad. And the bug is a bug. The issue stems from the fact that there are multiple events that can change the status, and following all the events is challenging. Dynamically detect and use the fresh status for the parameters when those are requested. Link: https://lore.kernel.org/20260419161003.79176-3-sj@kernel.org Fixes: 40e983cca927 ("mm/damon: introduce DAMON-based LRU-lists Sorting") Co-developed-by: Liew Rui Yan Signed-off-by: Liew Rui Yan Signed-off-by: SeongJae Park Cc: # 6.0.x Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/damon/lru_sort.c | 83 ++++++++++++++++++++++++++++++--------------- 1 file changed, 55 insertions(+), 28 deletions(-) diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 42b9a656f9ded..0c2274fefd763 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -118,15 +118,6 @@ module_param(monitor_region_end, ulong, 0600); */ static unsigned long addr_unit __read_mostly = 1; -/* - * PID of the DAMON thread - * - * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. - * Else, -1. - */ -static int kdamond_pid __read_mostly = -1; -module_param(kdamond_pid, int, 0400); - static struct damos_stat damon_lru_sort_hot_stat; DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_hot_stat, lru_sort_tried_hot_regions, lru_sorted_hot_regions, @@ -288,12 +279,8 @@ static int damon_lru_sort_turn(bool on) { int err; - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + if (!on) + return damon_stop(&ctx, 1); err = damon_lru_sort_apply_parameters(); if (err) @@ -302,7 +289,6 @@ static int damon_lru_sort_turn(bool on) err = damon_start(&ctx, 1, true); if (err) return err; - kdamond_pid = ctx->kdamond->pid; return damon_call(ctx, &call_control); } @@ -330,42 +316,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600); MODULE_PARM_DESC(addr_unit, "Scale factor for DAMON_LRU_SORT to ops address conversion (default: 1)"); +static bool damon_lru_sort_enabled(void) +{ + if (!ctx) + return false; + return damon_is_running(ctx); +} + static int damon_lru_sort_enabled_store(const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; - bool enable; int err; - err = kstrtobool(val, &enable); + err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enable) + if (damon_lru_sort_enabled() == enabled) return 0; /* Called before init function. The function will handle this. */ if (!damon_initialized()) - goto set_param_out; + return 0; - err = damon_lru_sort_turn(enable); - if (err) - return err; + return damon_lru_sort_turn(enabled); +} -set_param_out: - enabled = enable; - return err; +static int damon_lru_sort_enabled_load(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_lru_sort_enabled() ? 'Y' : 'N'); } static const struct kernel_param_ops enabled_param_ops = { .set = damon_lru_sort_enabled_store, - .get = param_get_bool, + .get = damon_lru_sort_enabled_load, }; module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_LRU_SORT (default: disabled)"); +static int damon_lru_sort_kdamond_pid_store(const char *val, + const struct kernel_param *kp) +{ + /* + * kdamond_pid is read-only, but kernel command line could write it. + * Do nothing here. + */ + return 0; +} + +static int damon_lru_sort_kdamond_pid_load(char *buffer, + const struct kernel_param *kp) +{ + int kdamond_pid = -1; + + if (ctx) { + kdamond_pid = damon_kdamond_pid(ctx); + if (kdamond_pid < 0) + kdamond_pid = -1; + } + return sprintf(buffer, "%d\n", kdamond_pid); +} + +static const struct kernel_param_ops kdamond_pid_param_ops = { + .set = damon_lru_sort_kdamond_pid_store, + .get = damon_lru_sort_kdamond_pid_load, +}; + +/* + * PID of the DAMON thread + * + * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400); + static int __init damon_lru_sort_init(void) { int err; From d893804e9e3bd29e14d52813a8648a552417f826 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Sun, 19 Apr 2026 09:10:00 -0700 Subject: [PATCH 0148/1518] mm/damon/reclaim: detect and use fresh enabled and kdamond_pid values commit 64a140afa5ed1c6f5ba6d451512cbdbbab1ba339 upstream. Patch series "mm/damon/modules: detect and use fresh status", v3. DAMON modules including DAMON_RECLAIM, DAMON_LRU_SORT and DAMON_STAT commonly expose the kdamond running status via their parameters. Under certain scenarios including wrong user inputs and memory allocation failures, those parameter values can be stale. It can confuse users. For DAMON_RECLAIM and DAMON_LRU_SORT, it even makes the kdamond unable to be restarted before the system reboot. The problem comes from the fact that there are multiple events for the status changes and it is difficult to follow up all the scenarios. Fix the issue by detecting and using the status on demand, instead of using a cached status that is difficult to be updated. Patches 1-3 fix the bugs in DAMON_RECLAIM, DAMON_LRU_SORT and DAMON_STAT in the order. This patch (of 3): DAMON_RECLAIM updates 'enabled' and 'kdamond_pid' parameter values, which represents the running status of its kdamond, when the user explicitly requests start/stop of the kdamond. The kdamond can, however, be stopped in events other than the explicit user request in the following three events. 1. ctx->regions_score_histogram allocation failure at beginning of the execution, 2. damon_commit_ctx() failure due to invalid user input, and 3. damon_commit_ctx() failure due to its internal allocation failures. Hence, if the kdamond is stopped by the above three events, the values of the status parameters can be stale. Users could show the stale values and be confused. This is already bad, but the real consequence is worse. DAMON_RECLAIM avoids unnecessary damon_start() and damon_stop() calls based on the 'enabled' parameter value. And the update of 'enabled' parameter value depends on the damon_start() and damon_stop() call results. Hence, once the kdamond has stopped by the unintentional events, the user cannot restart the kdamond before the system reboot. For example, the issue can be reproduced via below steps. # cd /sys/module/damon_reclaim/parameters # # # start DAMON_RECLAIM # echo Y > enabled # ps -ef | grep kdamond root 806 2 0 17:53 ? 00:00:00 [kdamond.0] root 808 803 0 17:53 pts/4 00:00:00 grep kdamond # # # commit wrong input to stop kdamond withou explicit stop request # echo 3 > addr_unit # echo Y > commit_inputs bash: echo: write error: Invalid argument # # # confirm kdamond is stopped # ps -ef | grep kdamond root 811 803 0 17:53 pts/4 00:00:00 grep kdamond # # # users casn now show stable status # cat enabled Y # cat kdamond_pid 806 # # # even after fixing the wrong parameter, # # kdamond cannot be restarted. # echo 1 > addr_unit # echo Y > enabled # ps -ef | grep kdamond root 815 803 0 17:54 pts/4 00:00:00 grep kdamond The problem will only rarely happen in real and common setups for the following reasons. The allocation failures are unlikely in such setups since those allocations are arguably too small to fail. Also sane users on real production environments may not commit wrong input parameters. But once it happens, the consequence is quite bad. And the bug is a bug. The issue stems from the fact that there are multiple events that can change the status, and following all the events is challenging. Dynamically detect and use the fresh status for the parameters when those are requested. Link: https://lore.kernel.org/20260419161003.79176-1-sj@kernel.org Link: https://lore.kernel.org/20260419161003.79176-2-sj@kernel.org Fixes: e035c280f6df ("mm/damon/reclaim: support online inputs update") Co-developed-by: Liew Rui Yan Signed-off-by: Liew Rui Yan Signed-off-by: SeongJae Park Cc: # 5.19.x Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/damon/reclaim.c | 83 ++++++++++++++++++++++++++++++---------------- 1 file changed, 55 insertions(+), 28 deletions(-) diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 7ba3d0f9a19ac..9446e7a1b476f 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -144,15 +144,6 @@ static unsigned long addr_unit __read_mostly = 1; static bool skip_anon __read_mostly; module_param(skip_anon, bool, 0600); -/* - * PID of the DAMON thread - * - * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. - * Else, -1. - */ -static int kdamond_pid __read_mostly = -1; -module_param(kdamond_pid, int, 0400); - static struct damos_stat damon_reclaim_stat; DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_reclaim_stat, reclaim_tried_regions, reclaimed_regions, quota_exceeds); @@ -292,12 +283,8 @@ static int damon_reclaim_turn(bool on) { int err; - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + if (!on) + return damon_stop(&ctx, 1); err = damon_reclaim_apply_parameters(); if (err) @@ -306,7 +293,6 @@ static int damon_reclaim_turn(bool on) err = damon_start(&ctx, 1, true); if (err) return err; - kdamond_pid = ctx->kdamond->pid; return damon_call(ctx, &call_control); } @@ -334,42 +320,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600); MODULE_PARM_DESC(addr_unit, "Scale factor for DAMON_RECLAIM to ops address conversion (default: 1)"); +static bool damon_reclaim_enabled(void) +{ + if (!ctx) + return false; + return damon_is_running(ctx); +} + static int damon_reclaim_enabled_store(const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; - bool enable; int err; - err = kstrtobool(val, &enable); + err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enable) + if (damon_reclaim_enabled() == enabled) return 0; /* Called before init function. The function will handle this. */ if (!damon_initialized()) - goto set_param_out; + return 0; - err = damon_reclaim_turn(enable); - if (err) - return err; + return damon_reclaim_turn(enabled); +} -set_param_out: - enabled = enable; - return err; +static int damon_reclaim_enabled_load(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_reclaim_enabled() ? 'Y' : 'N'); } static const struct kernel_param_ops enabled_param_ops = { .set = damon_reclaim_enabled_store, - .get = param_get_bool, + .get = damon_reclaim_enabled_load, }; module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_RECLAIM (default: disabled)"); +static int damon_reclaim_kdamond_pid_store(const char *val, + const struct kernel_param *kp) +{ + /* + * kdamond_pid is read-only, but kernel command line could write it. + * Do nothing here. + */ + return 0; +} + +static int damon_reclaim_kdamond_pid_load(char *buffer, + const struct kernel_param *kp) +{ + int kdamond_pid = -1; + + if (ctx) { + kdamond_pid = damon_kdamond_pid(ctx); + if (kdamond_pid < 0) + kdamond_pid = -1; + } + return sprintf(buffer, "%d\n", kdamond_pid); +} + +static const struct kernel_param_ops kdamond_pid_param_ops = { + .set = damon_reclaim_kdamond_pid_store, + .get = damon_reclaim_kdamond_pid_load, +}; + +/* + * PID of the DAMON thread + * + * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400); + static int __init damon_reclaim_init(void) { int err; From 377c3d5dc952d24084721298f849801119cd60ef Mon Sep 17 00:00:00 2001 From: Amit Sunil Dhamne Date: Tue, 14 Apr 2026 00:58:32 +0000 Subject: [PATCH 0149/1518] usb: typec: tcpm: reset internal port states on soft reset AMS commit 2909f0d4994fb4306bf116df5ccee797791fce2c upstream. Reset internal port states (such as vdm_sm_running and explicit_contract) on soft reset AMS as the port needs to negotiate a new contract. The consequence of leaving the states in as-is cond are as follows: * port is in SRC power role and an explicit contract is negotiated with the port partner (in sink role) * port partner sends a Soft Reset AMS while VDM State Machine is running * port accepts the Soft Reset request and the port advertises src caps * port partner sends a Request message but since the explicit_contract and vdm_sm_running are true from previous negotiation, the port ends up sending Soft Reset instead of Accept msg. Stub Log: [ 203.653942] AMS DISCOVER_IDENTITY start [ 203.653947] PD TX, header: 0x176f [ 203.655901] PD TX complete, status: 0 [ 203.657470] PD RX, header: 0x124f [1] [ 203.657477] Rx VDM cmd 0xff008081 type 2 cmd 1 len 1 [ 203.657482] AMS DISCOVER_IDENTITY finished [ 203.657484] cc:=4 [ 204.155698] PD RX, header: 0x144f [1] [ 204.155718] Rx VDM cmd 0xeeee8001 type 0 cmd 1 len 1 [ 204.155741] PD TX, header: 0x196f [ 204.157622] PD TX complete, status: 0 [ 204.160060] PD RX, header: 0x4d [1] [ 204.160066] state change SRC_READY -> SOFT_RESET [rev2 SOFT_RESET_AMS] [ 204.160076] PD TX, header: 0x163 [ 204.162486] PD TX complete, status: 0 [ 204.162832] AMS SOFT_RESET_AMS finished [ 204.162840] cc:=4 [ 204.162891] AMS POWER_NEGOTIATION start [ 204.162896] state change SOFT_RESET -> AMS_START [rev2 POWER_NEGOTIATION] [ 204.162908] state change AMS_START -> SRC_SEND_CAPABILITIES [rev2 POWER_NEGOTIATION] [ 204.162913] PD TX, header: 0x1361 [ 204.165529] PD TX complete, status: 0 [ 204.165571] pending state change SRC_SEND_CAPABILITIES -> SRC_SEND_CAPABILITIES_TIMEOUT @ 60 ms [rev2 POWER_NEGOTIATION] [ 204.166996] PD RX, header: 0x1242 [1] [ 204.167009] state change SRC_SEND_CAPABILITIES -> SRC_SOFT_RESET_WAIT_SNK_TX [rev2 POWER_NEGOTIATION] [ 204.167019] AMS POWER_NEGOTIATION finished [ 204.167020] cc:=4 [ 204.167083] AMS SOFT_RESET_AMS start [ 204.167086] state change SRC_SOFT_RESET_WAIT_SNK_TX -> SOFT_RESET_SEND [rev2 SOFT_RESET_AMS] [ 204.167092] PD TX, header: 0x16d [ 204.168824] PD TX complete, status: 0 [ 204.168854] pending state change SOFT_RESET_SEND -> HARD_RESET_SEND @ 60 ms [rev2 SOFT_RESET_AMS] [ 204.171876] PD RX, header: 0x43 [1] [ 204.171879] AMS SOFT_RESET_AMS finished This causes COMMON.PROC.PD.11.2 check failure for TEST.PD.VDM.SRC.2_Rev2Src test on the PD compliance tester. Signed-off-by: Amit Sunil Dhamne Fixes: 8d3a0578ad1a ("usb: typec: tcpm: Respond Wait if VDM state machine is running") Fixes: f0690a25a140 ("staging: typec: USB Type-C Port Manager (tcpm)") Cc: stable Reviewed-by: Badhri Jagan Sridharan Acked-by: Heikki Krogerus Link: https://patch.msgid.link/20260414-fix-soft-reset-v1-1-01d7cb9764e2@google.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index fe5a04f4cf148..336a0de9a9119 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5526,6 +5526,8 @@ static void run_state_machine(struct tcpm_port *port) usb_power_delivery_unregister_capabilities(port->partner_source_caps); port->partner_source_caps = NULL; tcpm_pd_send_control(port, PD_CTRL_ACCEPT, TCPC_TX_SOP); + port->vdm_sm_running = false; + port->explicit_contract = false; tcpm_ams_finish(port); if (port->pwr_role == TYPEC_SOURCE) { port->upcoming_state = SRC_SEND_CAPABILITIES; From a9591e4083cc703fb3fe272b0cdcbe0a213538df Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 6 Apr 2026 17:31:52 -0700 Subject: [PATCH 0150/1518] mm/damon/core: disallow time-quota setting zero esz commit 8bbde987c2b84f80da0853f739f0a920386f8b99 upstream. When the throughput of a DAMOS scheme is very slow, DAMOS time quota can make the effective size quota smaller than damon_ctx->min_region_sz. In the case, damos_apply_scheme() will skip applying the action, because the action is tried at region level, which requires >=min_region_sz size. That is, the quota is effectively exceeded for the quota charge window. Because no action will be applied, the total_charged_sz and total_charged_ns are also not updated. damos_set_effective_quota() will try to update the effective size quota before starting the next charge window. However, because the total_charged_sz and total_charged_ns have not updated, the throughput and effective size quota are also not changed. Since effective size quota can only be decreased, other effective size quota update factors including DAMOS quota goals and size quota cannot make any change, either. As a result, the scheme is unexpectedly deactivated until the user notices and mitigates the situation. The users can mitigate this situation by changing the time quota online or re-install the scheme. While the mitigation is somewhat straightforward, finding the situation would be challenging, because DAMON is not providing good observabilities for that. Even if such observability is provided, doing the additional monitoring and the mitigation is somewhat cumbersome and not aligned to the intention of the time quota. The time quota was intended to help reduce the user's administration overhead. Fix the problem by setting time quota-modified effective size quota be at least min_region_sz always. The issue was discovered [1] by sashiko. Link: https://lore.kernel.org/20260407003153.79589-1-sj@kernel.org Link: https://lore.kernel.org/20260405192504.110014-1-sj@kernel.org [1] Fixes: 1cd243030059 ("mm/damon/schemes: implement time quota") Signed-off-by: SeongJae Park Cc: # 5.16.x Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/damon/core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 0ae73905fc51e..00c80b7c8c3f6 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2135,7 +2135,8 @@ static unsigned long damos_quota_score(struct damos_quota *quota) /* * Called only if quota->ms, or quota->sz are set, or quota->goals is not empty */ -static void damos_set_effective_quota(struct damos_quota *quota) +static void damos_set_effective_quota(struct damos_quota *quota, + struct damon_ctx *ctx) { unsigned long throughput; unsigned long esz = ULONG_MAX; @@ -2161,6 +2162,7 @@ static void damos_set_effective_quota(struct damos_quota *quota) else throughput = PAGE_SIZE * 1024; esz = min(throughput * quota->ms, esz); + esz = max(ctx->min_sz_region, esz); } if (quota->sz && quota->sz < esz) @@ -2197,7 +2199,7 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s) /* First charge window */ if (!quota->total_charged_sz && !quota->charged_from) { quota->charged_from = jiffies; - damos_set_effective_quota(quota); + damos_set_effective_quota(quota, c); } /* New charge window starts */ @@ -2211,7 +2213,7 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s) quota->charged_sz = 0; if (trace_damos_esz_enabled()) cached_esz = quota->esz; - damos_set_effective_quota(quota); + damos_set_effective_quota(quota, c); if (trace_damos_esz_enabled() && quota->esz != cached_esz) damos_trace_esz(c, s, quota); } From fd78e63459ab6fe99b9fd026c420808d09eaa8be Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Tue, 6 Jan 2026 17:00:57 +0800 Subject: [PATCH 0151/1518] drm/amdgpu: validate the flush_gpu_tlb_pasid() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f4db9913e4d3dabe9ff3ea6178f2c1bc286012b8 upstream. Validate flush_gpu_tlb_pasid() availability before flushing tlb. Signed-off-by: Prike Liang Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 1e3b8a506d1b9..de4cd3af1ee10 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -737,6 +737,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, return 0; if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { + + if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) + return 0; + if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, From 576b73b246564c8fa75572d45c1ed9b053b4be5b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 18 Jan 2026 13:57:46 +0100 Subject: [PATCH 0152/1518] drm/amdgpu: Fix validating flush_gpu_tlb_pasid() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e3a6eff92bbd960b471966d9afccb4d584546d17 upstream. When a function holds a lock and we return without unlocking it, it deadlocks the kernel. We should always unlock before returning. This commit fixes suspend/resume on SI. Tested on two Tahiti GPUs: FirePro W9000 and R9 280X. Fixes: f4db9913e4d3 ("drm/amdgpu: validate the flush_gpu_tlb_pasid()") Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202601190121.z9C0uml5-lkp@intel.com/ Signed-off-by: Timur Kristóf Signed-off-by: Prike Liang Reviewed-by: Prike Liang Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index de4cd3af1ee10..b8613888c5c33 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -738,8 +738,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { - if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) - return 0; + if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) { + r = 0; + goto error_unlock_reset; + } if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, From 13e9ea445191390269a6f092d009b68e086e601b Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Fri, 9 Jan 2026 16:15:11 +0800 Subject: [PATCH 0153/1518] Revert "drm/amdgpu: don't attach the tlb fence for SI" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 9163fe4d790fb4e16d6b0e23f55b43cddd3d4a65 upstream. This reverts commit 820b3d376e8a102c6aeab737ec6edebbbb710e04. It’s better to validate VM TLB flushes in the flush‑TLB backend rather than in the generic VM layer. Reverting this patch depends on commit fa7c231fc2b0 ("drm/amdgpu: validate the flush_gpu_tlb_pasid()") being present in the tree. Signed-off-by: Prike Liang Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 69080e3734891..9e9c0d7d35578 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1066,9 +1066,7 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked && - /* SI doesn't support pasid or KIQ/MES */ - params->adev->family > AMDGPU_FAMILY_SI) { + if (!params->unlocked) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ From f0d3bb6f5125c69ce872a7574afd6d9e1f7ea349 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 16 Mar 2026 11:04:46 -0400 Subject: [PATCH 0154/1518] drm/amdgpu: rework how we handle TLB fences MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 69c5fbd2b93b5ced77c6e79afe83371bca84c788 upstream. Add a new VM flag to indicate whether or not we need a TLB fence. Userqs (KFD or KGD) require a TLB fence. A TLB fence is not strictly required for kernel queues, but it shouldn't hurt. That said, enabling this unconditionally should be fine, but it seems to tickle some issues in KIQ/MES. Only enable them for KFD, or when KGD userq queues are enabled (currently via module parameter). Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4798 Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4749 Fixes: f3854e04b708 ("drm/amdgpu: attach tlb fence to the PTs update") Cc: Christian König Cc: Prike Liang Reviewed-by: Prike Liang Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 ++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 9e9c0d7d35578..0d7c48927f39c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1066,7 +1066,10 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked) { + /* The check for need_tlb_fence should be dropped once we + * sort out the issues with KIQ/MES TLB invalidation timeouts. + */ + if (!params->unlocked && vm->need_tlb_fence) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ @@ -2584,6 +2587,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, ttm_lru_bulk_move_init(&vm->lru_bulk_move); vm->is_compute_context = false; + vm->need_tlb_fence = amdgpu_userq_enabled(&adev->ddev); vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode & AMDGPU_VM_USE_CPU_FOR_GFX); @@ -2721,6 +2725,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) dma_fence_put(vm->last_update); vm->last_update = dma_fence_get_stub(); vm->is_compute_context = true; + vm->need_tlb_fence = true; unreserve_bo: amdgpu_bo_unreserve(vm->root.bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 70fec516a2908..076d9a3a5e624 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -439,6 +439,8 @@ struct amdgpu_vm { struct ttm_lru_bulk_move lru_bulk_move; /* Flag to indicate if VM is used for compute */ bool is_compute_context; + /* Flag to indicate if VM needs a TLB fence (KFD or KGD) */ + bool need_tlb_fence; /* Memory partition number, -1 means any partition */ int8_t mem_id; From 1817dd0c350f5918e4c66a0eb5bf6426e619b065 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 14 May 2026 13:58:44 -0400 Subject: [PATCH 0155/1518] fbcon: Rename struct fbcon_ops to struct fbcon_par [ Upstream commit a6adbbc4c32a016146e117b1e9e5242724a75e10 ] The type struct fbcon_ops contains fbcon state and callbacks. As the callbacks will be removed from struct fbcon_ops, rename the data type to struct fbcon_par. Also rename the variables from ops to par. The _par postfix ("private access registers") is used throughout the fbdev subsystem for per-driver state. The fbcon pointer within struct fb_info is also named fbcon_par. Hence, the new naming fits existing practice. v2: - rename struct fbcon_ops to struct fbcon_par - fix build for CONFIG_FB_TILEBITTING=n (kernel test robot) - fix indention Signed-off-by: Thomas Zimmermann Reviewed-by: Sam Ravnborg Link: https://lore.kernel.org/r/20250909124616.143365-3-tzimmermann@suse.de Stable-dep-of: e4ef723d8975 ("fbcon: Avoid OOB font access if console rotation fails") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/core/bitblit.c | 122 +++---- drivers/video/fbdev/core/fbcon.c | 419 ++++++++++++------------ drivers/video/fbdev/core/fbcon.h | 6 +- drivers/video/fbdev/core/fbcon_ccw.c | 146 ++++----- drivers/video/fbdev/core/fbcon_cw.c | 146 ++++----- drivers/video/fbdev/core/fbcon_rotate.c | 40 +-- drivers/video/fbdev/core/fbcon_rotate.h | 6 +- drivers/video/fbdev/core/fbcon_ud.c | 162 ++++----- drivers/video/fbdev/core/softcursor.c | 18 +- drivers/video/fbdev/core/tileblit.c | 28 +- 10 files changed, 541 insertions(+), 552 deletions(-) diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index dc5ad3fcc7be4..bed8ba18222b9 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -261,10 +261,10 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, int fg, int bg) { struct fb_cursor cursor; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; int w = DIV_ROUND_UP(vc->vc_font.width, 8), c; - int y = real_y(ops->p, vc->state.y); + int y = real_y(par->p, vc->state.y); int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1; char *src; @@ -278,10 +278,10 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, attribute = get_attribute(info, c); src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height)); - if (ops->cursor_state.image.data != src || - ops->cursor_reset) { - ops->cursor_state.image.data = src; - cursor.set |= FB_CUR_SETIMAGE; + if (par->cursor_state.image.data != src || + par->cursor_reset) { + par->cursor_state.image.data = src; + cursor.set |= FB_CUR_SETIMAGE; } if (attribute) { @@ -290,46 +290,46 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, dst = kmalloc_array(w, vc->vc_font.height, GFP_ATOMIC); if (!dst) return; - kfree(ops->cursor_data); - ops->cursor_data = dst; + kfree(par->cursor_data); + par->cursor_data = dst; update_attr(dst, src, attribute, vc); src = dst; } - if (ops->cursor_state.image.fg_color != fg || - ops->cursor_state.image.bg_color != bg || - ops->cursor_reset) { - ops->cursor_state.image.fg_color = fg; - ops->cursor_state.image.bg_color = bg; + if (par->cursor_state.image.fg_color != fg || + par->cursor_state.image.bg_color != bg || + par->cursor_reset) { + par->cursor_state.image.fg_color = fg; + par->cursor_state.image.bg_color = bg; cursor.set |= FB_CUR_SETCMAP; } - if ((ops->cursor_state.image.dx != (vc->vc_font.width * vc->state.x)) || - (ops->cursor_state.image.dy != (vc->vc_font.height * y)) || - ops->cursor_reset) { - ops->cursor_state.image.dx = vc->vc_font.width * vc->state.x; - ops->cursor_state.image.dy = vc->vc_font.height * y; + if ((par->cursor_state.image.dx != (vc->vc_font.width * vc->state.x)) || + (par->cursor_state.image.dy != (vc->vc_font.height * y)) || + par->cursor_reset) { + par->cursor_state.image.dx = vc->vc_font.width * vc->state.x; + par->cursor_state.image.dy = vc->vc_font.height * y; cursor.set |= FB_CUR_SETPOS; } - if (ops->cursor_state.image.height != vc->vc_font.height || - ops->cursor_state.image.width != vc->vc_font.width || - ops->cursor_reset) { - ops->cursor_state.image.height = vc->vc_font.height; - ops->cursor_state.image.width = vc->vc_font.width; + if (par->cursor_state.image.height != vc->vc_font.height || + par->cursor_state.image.width != vc->vc_font.width || + par->cursor_reset) { + par->cursor_state.image.height = vc->vc_font.height; + par->cursor_state.image.width = vc->vc_font.width; cursor.set |= FB_CUR_SETSIZE; } - if (ops->cursor_state.hot.x || ops->cursor_state.hot.y || - ops->cursor_reset) { - ops->cursor_state.hot.x = cursor.hot.y = 0; + if (par->cursor_state.hot.x || par->cursor_state.hot.y || + par->cursor_reset) { + par->cursor_state.hot.x = cursor.hot.y = 0; cursor.set |= FB_CUR_SETHOT; } if (cursor.set & FB_CUR_SETSIZE || - vc->vc_cursor_type != ops->p->cursor_shape || - ops->cursor_state.mask == NULL || - ops->cursor_reset) { + vc->vc_cursor_type != par->p->cursor_shape || + par->cursor_state.mask == NULL || + par->cursor_reset) { char *mask = kmalloc_array(w, vc->vc_font.height, GFP_ATOMIC); int cur_height, size, i = 0; u8 msk = 0xff; @@ -337,13 +337,13 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (!mask) return; - kfree(ops->cursor_state.mask); - ops->cursor_state.mask = mask; + kfree(par->cursor_state.mask); + par->cursor_state.mask = mask; - ops->p->cursor_shape = vc->vc_cursor_type; + par->p->cursor_shape = vc->vc_cursor_type; cursor.set |= FB_CUR_SETSHAPE; - switch (CUR_SIZE(ops->p->cursor_shape)) { + switch (CUR_SIZE(par->p->cursor_shape)) { case CUR_NONE: cur_height = 0; break; @@ -372,19 +372,19 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, mask[i++] = msk; } - ops->cursor_state.enable = enable && !use_sw; + par->cursor_state.enable = enable && !use_sw; cursor.image.data = src; - cursor.image.fg_color = ops->cursor_state.image.fg_color; - cursor.image.bg_color = ops->cursor_state.image.bg_color; - cursor.image.dx = ops->cursor_state.image.dx; - cursor.image.dy = ops->cursor_state.image.dy; - cursor.image.height = ops->cursor_state.image.height; - cursor.image.width = ops->cursor_state.image.width; - cursor.hot.x = ops->cursor_state.hot.x; - cursor.hot.y = ops->cursor_state.hot.y; - cursor.mask = ops->cursor_state.mask; - cursor.enable = ops->cursor_state.enable; + cursor.image.fg_color = par->cursor_state.image.fg_color; + cursor.image.bg_color = par->cursor_state.image.bg_color; + cursor.image.dx = par->cursor_state.image.dx; + cursor.image.dy = par->cursor_state.image.dy; + cursor.image.height = par->cursor_state.image.height; + cursor.image.width = par->cursor_state.image.width; + cursor.hot.x = par->cursor_state.hot.x; + cursor.hot.y = par->cursor_state.hot.y; + cursor.mask = par->cursor_state.mask; + cursor.enable = par->cursor_state.enable; cursor.image.depth = 1; cursor.rop = ROP_XOR; @@ -394,31 +394,31 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (err) soft_cursor(info, &cursor); - ops->cursor_reset = 0; + par->cursor_reset = 0; } static int bit_update_start(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int err; - err = fb_pan_display(info, &ops->var); - ops->var.xoffset = info->var.xoffset; - ops->var.yoffset = info->var.yoffset; - ops->var.vmode = info->var.vmode; + err = fb_pan_display(info, &par->var); + par->var.xoffset = info->var.xoffset; + par->var.yoffset = info->var.yoffset; + par->var.vmode = info->var.vmode; return err; } -void fbcon_set_bitops(struct fbcon_ops *ops) +void fbcon_set_bitops(struct fbcon_par *par) { - ops->bmove = bit_bmove; - ops->clear = bit_clear; - ops->putcs = bit_putcs; - ops->clear_margins = bit_clear_margins; - ops->cursor = bit_cursor; - ops->update_start = bit_update_start; - ops->rotate_font = NULL; - - if (ops->rotate) - fbcon_set_rotate(ops); + par->bmove = bit_bmove; + par->clear = bit_clear; + par->putcs = bit_putcs; + par->clear_margins = bit_clear_margins; + par->cursor = bit_cursor; + par->update_start = bit_update_start; + par->rotate_font = NULL; + + if (par->rotate) + fbcon_set_rotate(par); } diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 7453377f34336..8baad7ec1b856 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -200,27 +200,27 @@ static struct device *fbcon_device; #ifdef CONFIG_FRAMEBUFFER_CONSOLE_ROTATION static inline void fbcon_set_rotation(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; if (!(info->flags & FBINFO_MISC_TILEBLITTING) && - ops->p->con_rotate < 4) - ops->rotate = ops->p->con_rotate; + par->p->con_rotate < 4) + par->rotate = par->p->con_rotate; else - ops->rotate = 0; + par->rotate = 0; } static void fbcon_rotate(struct fb_info *info, u32 rotate) { - struct fbcon_ops *ops= info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_info *fb_info; - if (!ops || ops->currcon == -1) + if (!par || par->currcon == -1) return; - fb_info = fbcon_info_from_console(ops->currcon); + fb_info = fbcon_info_from_console(par->currcon); if (info == fb_info) { - struct fbcon_display *p = &fb_display[ops->currcon]; + struct fbcon_display *p = &fb_display[par->currcon]; if (rotate < 4) p->con_rotate = rotate; @@ -233,12 +233,12 @@ static void fbcon_rotate(struct fb_info *info, u32 rotate) static void fbcon_rotate_all(struct fb_info *info, u32 rotate) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct vc_data *vc; struct fbcon_display *p; int i; - if (!ops || ops->currcon < 0 || rotate > 3) + if (!par || par->currcon < 0 || rotate > 3) return; for (i = first_fb_vc; i <= last_fb_vc; i++) { @@ -256,9 +256,9 @@ static void fbcon_rotate_all(struct fb_info *info, u32 rotate) #else static inline void fbcon_set_rotation(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - ops->rotate = FB_ROTATE_UR; + par->rotate = FB_ROTATE_UR; } static void fbcon_rotate(struct fb_info *info, u32 rotate) @@ -274,9 +274,9 @@ static void fbcon_rotate_all(struct fb_info *info, u32 rotate) static int fbcon_get_rotate(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - return (ops) ? ops->rotate : 0; + return (par) ? par->rotate : 0; } static bool fbcon_skip_panic(struct fb_info *info) @@ -286,10 +286,10 @@ static bool fbcon_skip_panic(struct fb_info *info) static inline bool fbcon_is_active(struct vc_data *vc, struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; return info->state == FBINFO_STATE_RUNNING && - vc->vc_mode == KD_TEXT && !ops->graphics && !fbcon_skip_panic(info); + vc->vc_mode == KD_TEXT && !par->graphics && !fbcon_skip_panic(info); } static int get_color(struct vc_data *vc, struct fb_info *info, @@ -371,7 +371,7 @@ static int get_bg_color(struct vc_data *vc, struct fb_info *info, u16 c) static void fb_flashcursor(struct work_struct *work) { - struct fbcon_ops *ops = container_of(work, struct fbcon_ops, cursor_work.work); + struct fbcon_par *par = container_of(work, struct fbcon_par, cursor_work.work); struct fb_info *info; struct vc_data *vc = NULL; int c; @@ -386,10 +386,10 @@ static void fb_flashcursor(struct work_struct *work) return; /* protected by console_lock */ - info = ops->info; + info = par->info; - if (ops->currcon != -1) - vc = vc_cons[ops->currcon].d; + if (par->currcon != -1) + vc = vc_cons[par->currcon].d; if (!vc || !con_is_visible(vc) || fbcon_info_from_console(vc->vc_num) != info || @@ -399,30 +399,30 @@ static void fb_flashcursor(struct work_struct *work) } c = scr_readw((u16 *) vc->vc_pos); - enable = ops->cursor_flash && !ops->cursor_state.enable; - ops->cursor(vc, info, enable, + enable = par->cursor_flash && !par->cursor_state.enable; + par->cursor(vc, info, enable, get_fg_color(vc, info, c), get_bg_color(vc, info, c)); console_unlock(); - queue_delayed_work(system_power_efficient_wq, &ops->cursor_work, - ops->cur_blink_jiffies); + queue_delayed_work(system_power_efficient_wq, &par->cursor_work, + par->cur_blink_jiffies); } static void fbcon_add_cursor_work(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; if (fbcon_cursor_blink) - queue_delayed_work(system_power_efficient_wq, &ops->cursor_work, - ops->cur_blink_jiffies); + queue_delayed_work(system_power_efficient_wq, &par->cursor_work, + par->cur_blink_jiffies); } static void fbcon_del_cursor_work(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - cancel_delayed_work_sync(&ops->cursor_work); + cancel_delayed_work_sync(&par->cursor_work); } #ifndef MODULE @@ -582,7 +582,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, int cols, int rows, int new_cols, int new_rows) { /* Need to make room for the logo */ - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int cnt, erase = vc->vc_video_erase_char, step; unsigned short *save = NULL, *r, *q; int logo_height; @@ -598,7 +598,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, */ if (fb_get_color_depth(&info->var, &info->fix) == 1) erase &= ~0x400; - logo_height = fb_prepare_logo(info, ops->rotate); + logo_height = fb_prepare_logo(info, par->rotate); logo_lines = DIV_ROUND_UP(logo_height, vc->vc_font.height); q = (unsigned short *) (vc->vc_origin + vc->vc_size_row * rows); @@ -670,15 +670,15 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, #ifdef CONFIG_FB_TILEBLITTING static void set_blitting_type(struct vc_data *vc, struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - ops->p = &fb_display[vc->vc_num]; + par->p = &fb_display[vc->vc_num]; if ((info->flags & FBINFO_MISC_TILEBLITTING)) fbcon_set_tileops(vc, info); else { fbcon_set_rotation(info); - fbcon_set_bitops(ops); + fbcon_set_bitops(par); } } @@ -695,12 +695,12 @@ static int fbcon_invalid_charcount(struct fb_info *info, unsigned charcount) #else static void set_blitting_type(struct vc_data *vc, struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; info->flags &= ~FBINFO_MISC_TILEBLITTING; - ops->p = &fb_display[vc->vc_num]; + par->p = &fb_display[vc->vc_num]; fbcon_set_rotation(info); - fbcon_set_bitops(ops); + fbcon_set_bitops(par); } static int fbcon_invalid_charcount(struct fb_info *info, unsigned charcount) @@ -720,13 +720,13 @@ static void fbcon_release(struct fb_info *info) module_put(info->fbops->owner); if (info->fbcon_par) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; fbcon_del_cursor_work(info); - kfree(ops->cursor_state.mask); - kfree(ops->cursor_data); - kfree(ops->cursor_src); - kfree(ops->fontbuffer); + kfree(par->cursor_state.mask); + kfree(par->cursor_data); + kfree(par->cursor_src); + kfree(par->fontbuffer); kfree(info->fbcon_par); info->fbcon_par = NULL; } @@ -734,7 +734,7 @@ static void fbcon_release(struct fb_info *info) static int fbcon_open(struct fb_info *info) { - struct fbcon_ops *ops; + struct fbcon_par *par; if (!try_module_get(info->fbops->owner)) return -ENODEV; @@ -748,16 +748,16 @@ static int fbcon_open(struct fb_info *info) } unlock_fb_info(info); - ops = kzalloc(sizeof(struct fbcon_ops), GFP_KERNEL); - if (!ops) { + par = kzalloc(sizeof(*par), GFP_KERNEL); + if (!par) { fbcon_release(info); return -ENOMEM; } - INIT_DELAYED_WORK(&ops->cursor_work, fb_flashcursor); - ops->info = info; - info->fbcon_par = ops; - ops->cur_blink_jiffies = HZ / 5; + INIT_DELAYED_WORK(&par->cursor_work, fb_flashcursor); + par->info = info; + info->fbcon_par = par; + par->cur_blink_jiffies = HZ / 5; return 0; } @@ -804,12 +804,12 @@ static void con2fb_release_oldinfo(struct vc_data *vc, struct fb_info *oldinfo, static void con2fb_init_display(struct vc_data *vc, struct fb_info *info, int unit, int show_logo) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int ret; - ops->currcon = fg_console; + par->currcon = fg_console; - if (info->fbops->fb_set_par && !ops->initialized) { + if (info->fbops->fb_set_par && !par->initialized) { ret = info->fbops->fb_set_par(info); if (ret) @@ -818,8 +818,8 @@ static void con2fb_init_display(struct vc_data *vc, struct fb_info *info, "error code %d\n", ret); } - ops->initialized = true; - ops->graphics = 0; + par->initialized = true; + par->graphics = 0; fbcon_set_disp(info, &info->var, unit); if (show_logo) { @@ -956,7 +956,7 @@ static const char *fbcon_startup(void) struct vc_data *vc = vc_cons[fg_console].d; const struct font_desc *font = NULL; struct fb_info *info = NULL; - struct fbcon_ops *ops; + struct fbcon_par *par; int rows, cols; /* @@ -976,10 +976,10 @@ static const char *fbcon_startup(void) if (fbcon_open(info)) return NULL; - ops = info->fbcon_par; - ops->currcon = -1; - ops->graphics = 1; - ops->cur_rotate = -1; + par = info->fbcon_par; + par->currcon = -1; + par->graphics = 1; + par->cur_rotate = -1; p->con_rotate = initial_rotation; if (p->con_rotate == -1) @@ -1002,8 +1002,8 @@ static const char *fbcon_startup(void) vc->vc_font.charcount = font->charcount; } - cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + cols = FBCON_SWAP(par->rotate, info->var.xres, info->var.yres); + rows = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); @@ -1021,7 +1021,7 @@ static const char *fbcon_startup(void) static void fbcon_init(struct vc_data *vc, bool init) { struct fb_info *info; - struct fbcon_ops *ops; + struct fbcon_par *par; struct vc_data **default_mode = vc->vc_display_fg; struct vc_data *svc = *default_mode; struct fbcon_display *t, *p = &fb_display[vc->vc_num]; @@ -1096,8 +1096,8 @@ static void fbcon_init(struct vc_data *vc, bool init) if (!*vc->uni_pagedict_loc) con_copy_unimap(vc, svc); - ops = info->fbcon_par; - ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); + par = info->fbcon_par; + par->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); p->con_rotate = initial_rotation; if (p->con_rotate == -1) @@ -1109,8 +1109,8 @@ static void fbcon_init(struct vc_data *vc, bool init) cols = vc->vc_cols; rows = vc->vc_rows; - new_cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - new_rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + new_cols = FBCON_SWAP(par->rotate, info->var.xres, info->var.yres); + new_rows = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); new_cols /= vc->vc_font.width; new_rows /= vc->vc_font.height; @@ -1122,7 +1122,7 @@ static void fbcon_init(struct vc_data *vc, bool init) * We need to do it in fbcon_init() to prevent screen corruption. */ if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { - if (info->fbops->fb_set_par && !ops->initialized) { + if (info->fbops->fb_set_par && !par->initialized) { ret = info->fbops->fb_set_par(info); if (ret) @@ -1131,10 +1131,10 @@ static void fbcon_init(struct vc_data *vc, bool init) "error code %d\n", ret); } - ops->initialized = true; + par->initialized = true; } - ops->graphics = 0; + par->graphics = 0; #ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION if ((info->flags & FBINFO_HWACCEL_COPYAREA) && @@ -1158,12 +1158,12 @@ static void fbcon_init(struct vc_data *vc, bool init) if (logo) fbcon_prepare_logo(vc, info, cols, rows, new_cols, new_rows); - if (ops->rotate_font && ops->rotate_font(info, vc)) { - ops->rotate = FB_ROTATE_UR; + if (par->rotate_font && par->rotate_font(info, vc)) { + par->rotate = FB_ROTATE_UR; set_blitting_type(vc, info); } - ops->p = &fb_display[fg_console]; + par->p = &fb_display[fg_console]; } static void fbcon_free_font(struct fbcon_display *p) @@ -1201,7 +1201,7 @@ static void fbcon_deinit(struct vc_data *vc) { struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_info *info; - struct fbcon_ops *ops; + struct fbcon_par *par; int idx; fbcon_free_font(p); @@ -1215,15 +1215,15 @@ static void fbcon_deinit(struct vc_data *vc) if (!info) goto finished; - ops = info->fbcon_par; + par = info->fbcon_par; - if (!ops) + if (!par) goto finished; if (con_is_visible(vc)) fbcon_del_cursor_work(info); - ops->initialized = false; + par->initialized = false; finished: fbcon_free_font(p); @@ -1270,7 +1270,7 @@ static void __fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx, unsigned int height, unsigned int width) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int fg, bg; struct fbcon_display *p = &fb_display[vc->vc_num]; u_int y_break; @@ -1285,7 +1285,7 @@ static void __fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx, vc->vc_top = 0; /* * If the font dimensions are not an integral of the display - * dimensions then the ops->clear below won't end up clearing + * dimensions then the par->clear below won't end up clearing * the margins. Call clear_margins here in case the logo * bitmap stretched into the margin area. */ @@ -1299,11 +1299,10 @@ static void __fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx, y_break = p->vrows - p->yscroll; if (sy < y_break && sy + height - 1 >= y_break) { u_int b = y_break - sy; - ops->clear(vc, info, real_y(p, sy), sx, b, width, fg, bg); - ops->clear(vc, info, real_y(p, sy + b), sx, height - b, - width, fg, bg); + par->clear(vc, info, real_y(p, sy), sx, b, width, fg, bg); + par->clear(vc, info, real_y(p, sy + b), sx, height - b, width, fg, bg); } else - ops->clear(vc, info, real_y(p, sy), sx, height, width, fg, bg); + par->clear(vc, info, real_y(p, sy), sx, height, width, fg, bg); } static void fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx, @@ -1317,10 +1316,10 @@ static void fbcon_putcs(struct vc_data *vc, const u16 *s, unsigned int count, { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; if (fbcon_is_active(vc, info)) - ops->putcs(vc, info, s, count, real_y(p, ypos), xpos, + par->putcs(vc, info, s, count, real_y(p, ypos), xpos, get_fg_color(vc, info, scr_readw(s)), get_bg_color(vc, info, scr_readw(s))); } @@ -1328,19 +1327,19 @@ static void fbcon_putcs(struct vc_data *vc, const u16 *s, unsigned int count, static void fbcon_clear_margins(struct vc_data *vc, int bottom_only) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; if (fbcon_is_active(vc, info)) - ops->clear_margins(vc, info, margin_color, bottom_only); + par->clear_margins(vc, info, margin_color, bottom_only); } static void fbcon_cursor(struct vc_data *vc, bool enable) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int c = scr_readw((u16 *) vc->vc_pos); - ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); + par->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); if (!fbcon_is_active(vc, info) || vc->vc_deccm != 1) return; @@ -1350,12 +1349,12 @@ static void fbcon_cursor(struct vc_data *vc, bool enable) else fbcon_add_cursor_work(info); - ops->cursor_flash = enable; + par->cursor_flash = enable; - if (!ops->cursor) + if (!par->cursor) return; - ops->cursor(vc, info, enable, + par->cursor(vc, info, enable, get_fg_color(vc, info, c), get_bg_color(vc, info, c)); } @@ -1370,7 +1369,7 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, struct fbcon_display *p, *t; struct vc_data **default_mode, *vc; struct vc_data *svc; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int rows, cols; unsigned long ret = 0; @@ -1403,7 +1402,7 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, var->yoffset = info->var.yoffset; var->xoffset = info->var.xoffset; fb_set_var(info, var); - ops->var = info->var; + par->var = info->var; vc->vc_can_do_color = (fb_get_color_depth(&info->var, &info->fix)!=1); vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800; if (vc->vc_font.charcount == 256) { @@ -1419,8 +1418,8 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, if (!*vc->uni_pagedict_loc) con_copy_unimap(vc, svc); - cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + cols = FBCON_SWAP(par->rotate, info->var.xres, info->var.yres); + rows = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; ret = vc_resize(vc, cols, rows); @@ -1432,16 +1431,16 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, static __inline__ void ywrap_up(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll += count; if (p->yscroll >= p->vrows) /* Deal with wrap */ p->yscroll -= p->vrows; - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode |= FB_VMODE_YWRAP; - ops->update_start(info); + par->var.xoffset = 0; + par->var.yoffset = p->yscroll * vc->vc_font.height; + par->var.vmode |= FB_VMODE_YWRAP; + par->update_start(info); scrollback_max += count; if (scrollback_max > scrollback_phys_max) scrollback_max = scrollback_phys_max; @@ -1451,16 +1450,16 @@ static __inline__ void ywrap_up(struct vc_data *vc, int count) static __inline__ void ywrap_down(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll -= count; if (p->yscroll < 0) /* Deal with wrap */ p->yscroll += p->vrows; - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode |= FB_VMODE_YWRAP; - ops->update_start(info); + par->var.xoffset = 0; + par->var.yoffset = p->yscroll * vc->vc_font.height; + par->var.vmode |= FB_VMODE_YWRAP; + par->update_start(info); scrollback_max -= count; if (scrollback_max < 0) scrollback_max = 0; @@ -1471,19 +1470,19 @@ static __inline__ void ypan_up(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; p->yscroll += count; if (p->yscroll > p->vrows - vc->vc_rows) { - ops->bmove(vc, info, p->vrows - vc->vc_rows, + par->bmove(vc, info, p->vrows - vc->vc_rows, 0, 0, 0, vc->vc_rows, vc->vc_cols); p->yscroll -= p->vrows - vc->vc_rows; } - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); + par->var.xoffset = 0; + par->var.yoffset = p->yscroll * vc->vc_font.height; + par->var.vmode &= ~FB_VMODE_YWRAP; + par->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max += count; if (scrollback_max > scrollback_phys_max) @@ -1494,7 +1493,7 @@ static __inline__ void ypan_up(struct vc_data *vc, int count) static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll += count; @@ -1504,10 +1503,10 @@ static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) fbcon_redraw_move(vc, p, t + count, vc->vc_rows - count, t); } - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); + par->var.xoffset = 0; + par->var.yoffset = p->yscroll * vc->vc_font.height; + par->var.vmode &= ~FB_VMODE_YWRAP; + par->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max += count; if (scrollback_max > scrollback_phys_max) @@ -1519,19 +1518,19 @@ static __inline__ void ypan_down(struct vc_data *vc, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; p->yscroll -= count; if (p->yscroll < 0) { - ops->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, + par->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, 0, vc->vc_rows, vc->vc_cols); p->yscroll += p->vrows - vc->vc_rows; } - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); + par->var.xoffset = 0; + par->var.yoffset = p->yscroll * vc->vc_font.height; + par->var.vmode &= ~FB_VMODE_YWRAP; + par->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max -= count; if (scrollback_max < 0) @@ -1542,7 +1541,7 @@ static __inline__ void ypan_down(struct vc_data *vc, int count) static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; p->yscroll -= count; @@ -1552,10 +1551,10 @@ static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) fbcon_redraw_move(vc, p, t, vc->vc_rows - count, t + count); } - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); + par->var.xoffset = 0; + par->var.yoffset = p->yscroll * vc->vc_font.height; + par->var.vmode &= ~FB_VMODE_YWRAP; + par->update_start(info); fbcon_clear_margins(vc, 1); scrollback_max -= count; if (scrollback_max < 0) @@ -1604,7 +1603,7 @@ static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, unsigned short *d = (unsigned short *) (vc->vc_origin + vc->vc_size_row * line); unsigned short *s = d + offset; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; while (count--) { unsigned short *start = s; @@ -1617,8 +1616,8 @@ static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, if (c == scr_readw(d)) { if (s > start) { - ops->bmove(vc, info, line + ycount, x, - line, x, 1, s-start); + par->bmove(vc, info, line + ycount, x, + line, x, 1, s - start); x += s - start + 1; start = s + 1; } else { @@ -1633,8 +1632,7 @@ static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, d++; } while (s < le); if (s > start) - ops->bmove(vc, info, line + ycount, x, line, x, 1, - s-start); + par->bmove(vc, info, line + ycount, x, line, x, 1, s - start); console_conditional_schedule(); if (ycount > 0) line++; @@ -1705,7 +1703,7 @@ static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int dy, int dx, int height, int width, u_int y_break) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u_int b; if (sy < y_break && sy + height > y_break) { @@ -1739,8 +1737,7 @@ static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, } return; } - ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, - height, width); + par->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, height, width); } static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, @@ -1967,15 +1964,13 @@ static void updatescrollmode_accel(struct fbcon_display *p, struct vc_data *vc) { #ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int cap = info->flags; u16 t = 0; - int ypan = FBCON_SWAP(ops->rotate, info->fix.ypanstep, - info->fix.xpanstep); - int ywrap = FBCON_SWAP(ops->rotate, info->fix.ywrapstep, t); - int yres = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); - int vyres = FBCON_SWAP(ops->rotate, info->var.yres_virtual, - info->var.xres_virtual); + int ypan = FBCON_SWAP(par->rotate, info->fix.ypanstep, info->fix.xpanstep); + int ywrap = FBCON_SWAP(par->rotate, info->fix.ywrapstep, t); + int yres = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); + int vyres = FBCON_SWAP(par->rotate, info->var.yres_virtual, info->var.xres_virtual); int good_pan = (cap & FBINFO_HWACCEL_YPAN) && divides(ypan, vc->vc_font.height) && vyres > yres; int good_wrap = (cap & FBINFO_HWACCEL_YWRAP) && @@ -2008,11 +2003,10 @@ static void updatescrollmode(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int fh = vc->vc_font.height; - int yres = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); - int vyres = FBCON_SWAP(ops->rotate, info->var.yres_virtual, - info->var.xres_virtual); + int yres = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); + int vyres = FBCON_SWAP(par->rotate, info->var.yres_virtual, info->var.xres_virtual); p->vrows = vyres/fh; if (yres > (fh * (vc->vc_rows + 1))) @@ -2031,7 +2025,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, unsigned int height, bool from_user) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_var_screeninfo var = info->var; int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh; @@ -2054,12 +2048,10 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, return -EINVAL; } - virt_w = FBCON_SWAP(ops->rotate, width, height); - virt_h = FBCON_SWAP(ops->rotate, height, width); - virt_fw = FBCON_SWAP(ops->rotate, vc->vc_font.width, - vc->vc_font.height); - virt_fh = FBCON_SWAP(ops->rotate, vc->vc_font.height, - vc->vc_font.width); + virt_w = FBCON_SWAP(par->rotate, width, height); + virt_h = FBCON_SWAP(par->rotate, height, width); + virt_fw = FBCON_SWAP(par->rotate, vc->vc_font.width, vc->vc_font.height); + virt_fh = FBCON_SWAP(par->rotate, vc->vc_font.height, vc->vc_font.width); var.xres = virt_w * virt_fw; var.yres = virt_h * virt_fh; x_diff = info->var.xres - var.xres; @@ -2085,7 +2077,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, fb_set_var(info, &var); } var_to_display(p, &info->var, info); - ops->var = info->var; + par->var = info->var; } updatescrollmode(p, info, vc); return 0; @@ -2094,13 +2086,13 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, static bool fbcon_switch(struct vc_data *vc) { struct fb_info *info, *old_info = NULL; - struct fbcon_ops *ops; + struct fbcon_par *par; struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_var_screeninfo var; int i, ret, prev_console; info = fbcon_info_from_console(vc->vc_num); - ops = info->fbcon_par; + par = info->fbcon_par; if (logo_shown >= 0) { struct vc_data *conp2 = vc_cons[logo_shown].d; @@ -2111,7 +2103,7 @@ static bool fbcon_switch(struct vc_data *vc) logo_shown = FBCON_LOGO_CANSHOW; } - prev_console = ops->currcon; + prev_console = par->currcon; if (prev_console != -1) old_info = fbcon_info_from_console(prev_console); /* @@ -2124,9 +2116,9 @@ static bool fbcon_switch(struct vc_data *vc) */ fbcon_for_each_registered_fb(i) { if (fbcon_registered_fb[i]->fbcon_par) { - struct fbcon_ops *o = fbcon_registered_fb[i]->fbcon_par; + struct fbcon_par *par = fbcon_registered_fb[i]->fbcon_par; - o->currcon = vc->vc_num; + par->currcon = vc->vc_num; } } memset(&var, 0, sizeof(struct fb_var_screeninfo)); @@ -2140,7 +2132,7 @@ static bool fbcon_switch(struct vc_data *vc) info->var.activate = var.activate; var.vmode |= info->var.vmode & ~FB_VMODE_MASK; fb_set_var(info, &var); - ops->var = info->var; + par->var = info->var; if (old_info != NULL && (old_info != info || info->flags & FBINFO_MISC_ALWAYS_SETPAR)) { @@ -2157,17 +2149,16 @@ static bool fbcon_switch(struct vc_data *vc) fbcon_del_cursor_work(old_info); } - if (!fbcon_is_active(vc, info) || - ops->blank_state != FB_BLANK_UNBLANK) + if (!fbcon_is_active(vc, info) || par->blank_state != FB_BLANK_UNBLANK) fbcon_del_cursor_work(info); else fbcon_add_cursor_work(info); set_blitting_type(vc, info); - ops->cursor_reset = 1; + par->cursor_reset = 1; - if (ops->rotate_font && ops->rotate_font(info, vc)) { - ops->rotate = FB_ROTATE_UR; + if (par->rotate_font && par->rotate_font(info, vc)) { + par->rotate = FB_ROTATE_UR; set_blitting_type(vc, info); } @@ -2198,8 +2189,8 @@ static bool fbcon_switch(struct vc_data *vc) scrollback_current = 0; if (fbcon_is_active(vc, info)) { - ops->var.xoffset = ops->var.yoffset = p->yscroll = 0; - ops->update_start(info); + par->var.xoffset = par->var.yoffset = p->yscroll = 0; + par->update_start(info); } fbcon_set_palette(vc, color_table); @@ -2208,7 +2199,7 @@ static bool fbcon_switch(struct vc_data *vc) if (logo_shown == FBCON_LOGO_DRAW) { logo_shown = fg_console; - fb_show_logo(info, ops->rotate); + fb_show_logo(info, par->rotate); update_region(vc, vc->vc_origin + vc->vc_size_row * vc->vc_top, vc->vc_size_row * (vc->vc_bottom - @@ -2237,27 +2228,27 @@ static bool fbcon_blank(struct vc_data *vc, enum vesa_blank_mode blank, bool mode_switch) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; if (mode_switch) { struct fb_var_screeninfo var = info->var; - ops->graphics = 1; + par->graphics = 1; if (!blank) { var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE | FB_ACTIVATE_KD_TEXT; fb_set_var(info, &var); - ops->graphics = 0; - ops->var = info->var; + par->graphics = 0; + par->var = info->var; } } if (fbcon_is_active(vc, info)) { - if (ops->blank_state != blank) { - ops->blank_state = blank; + if (par->blank_state != blank) { + par->blank_state = blank; fbcon_cursor(vc, !blank); - ops->cursor_flash = (!blank); + par->cursor_flash = (!blank); if (fb_blank(info, blank)) fbcon_generic_blank(vc, info, blank); @@ -2267,8 +2258,7 @@ static bool fbcon_blank(struct vc_data *vc, enum vesa_blank_mode blank, update_screen(vc); } - if (mode_switch || !fbcon_is_active(vc, info) || - ops->blank_state != FB_BLANK_UNBLANK) + if (mode_switch || !fbcon_is_active(vc, info) || par->blank_state != FB_BLANK_UNBLANK) fbcon_del_cursor_work(info); else fbcon_add_cursor_work(info); @@ -2279,10 +2269,10 @@ static bool fbcon_blank(struct vc_data *vc, enum vesa_blank_mode blank, static void fbcon_debug_enter(struct vc_data *vc) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - ops->save_graphics = ops->graphics; - ops->graphics = 0; + par->save_graphics = par->graphics; + par->graphics = 0; if (info->fbops->fb_debug_enter) info->fbops->fb_debug_enter(info); fbcon_set_palette(vc, color_table); @@ -2291,9 +2281,9 @@ static void fbcon_debug_enter(struct vc_data *vc) static void fbcon_debug_leave(struct vc_data *vc) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - ops->graphics = ops->save_graphics; + par->graphics = par->save_graphics; if (info->fbops->fb_debug_leave) info->fbops->fb_debug_leave(info); } @@ -2428,7 +2418,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, const u8 * data, int userfont) { struct fb_info *info = fbcon_info_from_console(vc->vc_num); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize, ret, old_userfont, old_width, old_height, old_charcount; u8 *old_data = vc->vc_font.data; @@ -2454,8 +2444,8 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, if (resize) { int cols, rows; - cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + cols = FBCON_SWAP(par->rotate, info->var.xres, info->var.yres); + rows = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); cols /= w; rows /= h; ret = vc_resize(vc, cols, rows); @@ -2654,11 +2644,11 @@ static void fbcon_invert_region(struct vc_data *vc, u16 * p, int cnt) void fbcon_suspended(struct fb_info *info) { struct vc_data *vc = NULL; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - if (!ops || ops->currcon < 0) + if (!par || par->currcon < 0) return; - vc = vc_cons[ops->currcon].d; + vc = vc_cons[par->currcon].d; /* Clear cursor, restore saved data */ fbcon_cursor(vc, false); @@ -2667,27 +2657,27 @@ void fbcon_suspended(struct fb_info *info) void fbcon_resumed(struct fb_info *info) { struct vc_data *vc; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - if (!ops || ops->currcon < 0) + if (!par || par->currcon < 0) return; - vc = vc_cons[ops->currcon].d; + vc = vc_cons[par->currcon].d; update_screen(vc); } static void fbcon_modechanged(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct vc_data *vc; struct fbcon_display *p; int rows, cols; - if (!ops || ops->currcon < 0) + if (!par || par->currcon < 0) return; - vc = vc_cons[ops->currcon].d; + vc = vc_cons[par->currcon].d; if (vc->vc_mode != KD_TEXT || - fbcon_info_from_console(ops->currcon) != info) + fbcon_info_from_console(par->currcon) != info) return; p = &fb_display[vc->vc_num]; @@ -2695,8 +2685,8 @@ static void fbcon_modechanged(struct fb_info *info) if (con_is_visible(vc)) { var_to_display(p, &info->var, info); - cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + cols = FBCON_SWAP(par->rotate, info->var.xres, info->var.yres); + rows = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); @@ -2705,8 +2695,8 @@ static void fbcon_modechanged(struct fb_info *info) scrollback_current = 0; if (fbcon_is_active(vc, info)) { - ops->var.xoffset = ops->var.yoffset = p->yscroll = 0; - ops->update_start(info); + par->var.xoffset = par->var.yoffset = p->yscroll = 0; + par->update_start(info); } fbcon_set_palette(vc, color_table); @@ -2716,12 +2706,12 @@ static void fbcon_modechanged(struct fb_info *info) static void fbcon_set_all_vcs(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct vc_data *vc; struct fbcon_display *p; int i, rows, cols, fg = -1; - if (!ops || ops->currcon < 0) + if (!par || par->currcon < 0) return; for (i = first_fb_vc; i <= last_fb_vc; i++) { @@ -2738,8 +2728,8 @@ static void fbcon_set_all_vcs(struct fb_info *info) p = &fb_display[vc->vc_num]; set_blitting_type(vc, info); var_to_display(p, &info->var, info); - cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); - rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + cols = FBCON_SWAP(par->rotate, info->var.xres, info->var.yres); + rows = FBCON_SWAP(par->rotate, info->var.yres, info->var.xres); cols /= vc->vc_font.width; rows /= vc->vc_font.height; vc_resize(vc, cols, rows); @@ -2762,13 +2752,13 @@ EXPORT_SYMBOL(fbcon_update_vcs); /* let fbcon check if it supports a new screen resolution */ int fbcon_modechange_possible(struct fb_info *info, struct fb_var_screeninfo *var) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct vc_data *vc; unsigned int i; WARN_CONSOLE_UNLOCKED(); - if (!ops) + if (!par) return 0; /* prevent setting a screen size which is smaller than font size */ @@ -3066,15 +3056,14 @@ int fbcon_fb_registered(struct fb_info *info) void fbcon_fb_blanked(struct fb_info *info, int blank) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct vc_data *vc; - if (!ops || ops->currcon < 0) + if (!par || par->currcon < 0) return; - vc = vc_cons[ops->currcon].d; - if (vc->vc_mode != KD_TEXT || - fbcon_info_from_console(ops->currcon) != info) + vc = vc_cons[par->currcon].d; + if (vc->vc_mode != KD_TEXT || fbcon_info_from_console(par->currcon) != info) return; if (con_is_visible(vc)) { @@ -3083,7 +3072,7 @@ void fbcon_fb_blanked(struct fb_info *info, int blank) else do_unblank_screen(0); } - ops->blank_state = blank; + par->blank_state = blank; } void fbcon_new_modelist(struct fb_info *info) @@ -3273,7 +3262,7 @@ static ssize_t cursor_blink_show(struct device *device, struct device_attribute *attr, char *buf) { struct fb_info *info; - struct fbcon_ops *ops; + struct fbcon_par *par; int idx, blink = -1; console_lock(); @@ -3283,12 +3272,12 @@ static ssize_t cursor_blink_show(struct device *device, goto err; info = fbcon_registered_fb[idx]; - ops = info->fbcon_par; + par = info->fbcon_par; - if (!ops) + if (!par) goto err; - blink = delayed_work_pending(&ops->cursor_work); + blink = delayed_work_pending(&par->cursor_work); err: console_unlock(); return sysfs_emit(buf, "%d\n", blink); diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 7e21c8b336692..b22c33e278c19 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -50,7 +50,7 @@ struct fbcon_display { const struct fb_videomode *mode; }; -struct fbcon_ops { +struct fbcon_par { void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy, int sx, int dy, int dx, int height, int width); void (*clear)(struct vc_data *vc, struct fb_info *info, int sy, @@ -185,7 +185,7 @@ static inline u_short fb_scrollmode(struct fbcon_display *fb) #ifdef CONFIG_FB_TILEBLITTING extern void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info); #endif -extern void fbcon_set_bitops(struct fbcon_ops *ops); +extern void fbcon_set_bitops(struct fbcon_par *par); extern int soft_cursor(struct fb_info *info, struct fb_cursor *cursor); #define FBCON_ATTRIBUTE_UNDERLINE 1 @@ -224,7 +224,7 @@ static inline int get_attribute(struct fb_info *info, u16 c) (i == FB_ROTATE_UR || i == FB_ROTATE_UD) ? _r : _v; }) #ifdef CONFIG_FRAMEBUFFER_CONSOLE_ROTATION -extern void fbcon_set_rotate(struct fbcon_ops *ops); +extern void fbcon_set_rotate(struct fbcon_par *par); #else #define fbcon_set_rotate(x) do {} while(0) #endif /* CONFIG_FRAMEBUFFER_CONSOLE_ROTATION */ diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index 89ef4ba7e8672..2ba8ec4c3e2bc 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -63,9 +63,9 @@ static void ccw_update_attr(u8 *dst, u8 *src, int attribute, static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, int sx, int dy, int dx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_copyarea area; - u32 vyres = GETVYRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); area.sx = sy * vc->vc_font.height; area.sy = vyres - ((sx + width) * vc->vc_font.width); @@ -80,9 +80,9 @@ static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width, int fg, int bg) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_fillrect region; - u32 vyres = GETVYRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); region.color = bg; region.dx = sy * vc->vc_font.height; @@ -99,13 +99,13 @@ static inline void ccw_putcs_aligned(struct vc_data *vc, struct fb_info *info, u32 d_pitch, u32 s_pitch, u32 cellsize, struct fb_image *image, u8 *buf, u8 *dst) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; u32 idx = (vc->vc_font.height + 7) >> 3; u8 *src; while (cnt--) { - src = ops->fontbuffer + (scr_readw(s--) & charmask)*cellsize; + src = par->fontbuffer + (scr_readw(s--) & charmask) * cellsize; if (attr) { ccw_update_attr(buf, src, attr, vc); @@ -130,7 +130,7 @@ static void ccw_putcs(struct vc_data *vc, struct fb_info *info, int fg, int bg) { struct fb_image image; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u32 width = (vc->vc_font.height + 7)/8; u32 cellsize = width * vc->vc_font.width; u32 maxcnt = info->pixmap.size/cellsize; @@ -139,9 +139,9 @@ static void ccw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = GETVYRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); - if (!ops->fontbuffer) + if (!par->fontbuffer) return; image.fg_color = fg; @@ -221,28 +221,28 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, int fg, int bg) { struct fb_cursor cursor; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; int w = (vc->vc_font.height + 7) >> 3, c; - int y = real_y(ops->p, vc->state.y); + int y = real_y(par->p, vc->state.y); int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = GETVYRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); - if (!ops->fontbuffer) + if (!par->fontbuffer) return; cursor.set = 0; c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); - src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.width)); + src = par->fontbuffer + ((c & charmask) * (w * vc->vc_font.width)); - if (ops->cursor_state.image.data != src || - ops->cursor_reset) { - ops->cursor_state.image.data = src; - cursor.set |= FB_CUR_SETIMAGE; + if (par->cursor_state.image.data != src || + par->cursor_reset) { + par->cursor_state.image.data = src; + cursor.set |= FB_CUR_SETIMAGE; } if (attribute) { @@ -251,49 +251,49 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, dst = kmalloc_array(w, vc->vc_font.width, GFP_ATOMIC); if (!dst) return; - kfree(ops->cursor_data); - ops->cursor_data = dst; + kfree(par->cursor_data); + par->cursor_data = dst; ccw_update_attr(dst, src, attribute, vc); src = dst; } - if (ops->cursor_state.image.fg_color != fg || - ops->cursor_state.image.bg_color != bg || - ops->cursor_reset) { - ops->cursor_state.image.fg_color = fg; - ops->cursor_state.image.bg_color = bg; + if (par->cursor_state.image.fg_color != fg || + par->cursor_state.image.bg_color != bg || + par->cursor_reset) { + par->cursor_state.image.fg_color = fg; + par->cursor_state.image.bg_color = bg; cursor.set |= FB_CUR_SETCMAP; } - if (ops->cursor_state.image.height != vc->vc_font.width || - ops->cursor_state.image.width != vc->vc_font.height || - ops->cursor_reset) { - ops->cursor_state.image.height = vc->vc_font.width; - ops->cursor_state.image.width = vc->vc_font.height; + if (par->cursor_state.image.height != vc->vc_font.width || + par->cursor_state.image.width != vc->vc_font.height || + par->cursor_reset) { + par->cursor_state.image.height = vc->vc_font.width; + par->cursor_state.image.width = vc->vc_font.height; cursor.set |= FB_CUR_SETSIZE; } dx = y * vc->vc_font.height; dy = vyres - ((vc->state.x + 1) * vc->vc_font.width); - if (ops->cursor_state.image.dx != dx || - ops->cursor_state.image.dy != dy || - ops->cursor_reset) { - ops->cursor_state.image.dx = dx; - ops->cursor_state.image.dy = dy; + if (par->cursor_state.image.dx != dx || + par->cursor_state.image.dy != dy || + par->cursor_reset) { + par->cursor_state.image.dx = dx; + par->cursor_state.image.dy = dy; cursor.set |= FB_CUR_SETPOS; } - if (ops->cursor_state.hot.x || ops->cursor_state.hot.y || - ops->cursor_reset) { - ops->cursor_state.hot.x = cursor.hot.y = 0; + if (par->cursor_state.hot.x || par->cursor_state.hot.y || + par->cursor_reset) { + par->cursor_state.hot.x = cursor.hot.y = 0; cursor.set |= FB_CUR_SETHOT; } if (cursor.set & FB_CUR_SETSIZE || - vc->vc_cursor_type != ops->p->cursor_shape || - ops->cursor_state.mask == NULL || - ops->cursor_reset) { + vc->vc_cursor_type != par->p->cursor_shape || + par->cursor_state.mask == NULL || + par->cursor_reset) { char *tmp, *mask = kmalloc_array(w, vc->vc_font.width, GFP_ATOMIC); int cur_height, size, i = 0; @@ -309,13 +309,13 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, return; } - kfree(ops->cursor_state.mask); - ops->cursor_state.mask = mask; + kfree(par->cursor_state.mask); + par->cursor_state.mask = mask; - ops->p->cursor_shape = vc->vc_cursor_type; + par->p->cursor_shape = vc->vc_cursor_type; cursor.set |= FB_CUR_SETSHAPE; - switch (CUR_SIZE(ops->p->cursor_shape)) { + switch (CUR_SIZE(par->p->cursor_shape)) { case CUR_NONE: cur_height = 0; break; @@ -348,19 +348,19 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, kfree(tmp); } - ops->cursor_state.enable = enable && !use_sw; + par->cursor_state.enable = enable && !use_sw; cursor.image.data = src; - cursor.image.fg_color = ops->cursor_state.image.fg_color; - cursor.image.bg_color = ops->cursor_state.image.bg_color; - cursor.image.dx = ops->cursor_state.image.dx; - cursor.image.dy = ops->cursor_state.image.dy; - cursor.image.height = ops->cursor_state.image.height; - cursor.image.width = ops->cursor_state.image.width; - cursor.hot.x = ops->cursor_state.hot.x; - cursor.hot.y = ops->cursor_state.hot.y; - cursor.mask = ops->cursor_state.mask; - cursor.enable = ops->cursor_state.enable; + cursor.image.fg_color = par->cursor_state.image.fg_color; + cursor.image.bg_color = par->cursor_state.image.bg_color; + cursor.image.dx = par->cursor_state.image.dx; + cursor.image.dy = par->cursor_state.image.dy; + cursor.image.height = par->cursor_state.image.height; + cursor.image.width = par->cursor_state.image.width; + cursor.hot.x = par->cursor_state.hot.x; + cursor.hot.y = par->cursor_state.hot.y; + cursor.mask = par->cursor_state.mask; + cursor.enable = par->cursor_state.enable; cursor.image.depth = 1; cursor.rop = ROP_XOR; @@ -370,32 +370,32 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (err) soft_cursor(info, &cursor); - ops->cursor_reset = 0; + par->cursor_reset = 0; } static int ccw_update_start(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u32 yoffset; - u32 vyres = GETVYRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); int err; - yoffset = (vyres - info->var.yres) - ops->var.xoffset; - ops->var.xoffset = ops->var.yoffset; - ops->var.yoffset = yoffset; - err = fb_pan_display(info, &ops->var); - ops->var.xoffset = info->var.xoffset; - ops->var.yoffset = info->var.yoffset; - ops->var.vmode = info->var.vmode; + yoffset = (vyres - info->var.yres) - par->var.xoffset; + par->var.xoffset = par->var.yoffset; + par->var.yoffset = yoffset; + err = fb_pan_display(info, &par->var); + par->var.xoffset = info->var.xoffset; + par->var.yoffset = info->var.yoffset; + par->var.vmode = info->var.vmode; return err; } -void fbcon_rotate_ccw(struct fbcon_ops *ops) +void fbcon_rotate_ccw(struct fbcon_par *par) { - ops->bmove = ccw_bmove; - ops->clear = ccw_clear; - ops->putcs = ccw_putcs; - ops->clear_margins = ccw_clear_margins; - ops->cursor = ccw_cursor; - ops->update_start = ccw_update_start; + par->bmove = ccw_bmove; + par->clear = ccw_clear; + par->putcs = ccw_putcs; + par->clear_margins = ccw_clear_margins; + par->cursor = ccw_cursor; + par->update_start = ccw_update_start; } diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index b9dac7940fb77..4bd22d5ee5f41 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -48,9 +48,9 @@ static void cw_update_attr(u8 *dst, u8 *src, int attribute, static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, int sx, int dy, int dx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_copyarea area; - u32 vxres = GETVXRES(ops->p, info); + u32 vxres = GETVXRES(par->p, info); area.sx = vxres - ((sy + height) * vc->vc_font.height); area.sy = sx * vc->vc_font.width; @@ -65,9 +65,9 @@ static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width, int fg, int bg) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_fillrect region; - u32 vxres = GETVXRES(ops->p, info); + u32 vxres = GETVXRES(par->p, info); region.color = bg; region.dx = vxres - ((sy + height) * vc->vc_font.height); @@ -84,13 +84,13 @@ static inline void cw_putcs_aligned(struct vc_data *vc, struct fb_info *info, u32 d_pitch, u32 s_pitch, u32 cellsize, struct fb_image *image, u8 *buf, u8 *dst) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; u32 idx = (vc->vc_font.height + 7) >> 3; u8 *src; while (cnt--) { - src = ops->fontbuffer + (scr_readw(s++) & charmask)*cellsize; + src = par->fontbuffer + (scr_readw(s++) & charmask) * cellsize; if (attr) { cw_update_attr(buf, src, attr, vc); @@ -115,7 +115,7 @@ static void cw_putcs(struct vc_data *vc, struct fb_info *info, int fg, int bg) { struct fb_image image; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u32 width = (vc->vc_font.height + 7)/8; u32 cellsize = width * vc->vc_font.width; u32 maxcnt = info->pixmap.size/cellsize; @@ -124,9 +124,9 @@ static void cw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vxres = GETVXRES(ops->p, info); + u32 vxres = GETVXRES(par->p, info); - if (!ops->fontbuffer) + if (!par->fontbuffer) return; image.fg_color = fg; @@ -204,28 +204,28 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, int fg, int bg) { struct fb_cursor cursor; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; int w = (vc->vc_font.height + 7) >> 3, c; - int y = real_y(ops->p, vc->state.y); + int y = real_y(par->p, vc->state.y); int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vxres = GETVXRES(ops->p, info); + u32 vxres = GETVXRES(par->p, info); - if (!ops->fontbuffer) + if (!par->fontbuffer) return; cursor.set = 0; c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); - src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.width)); + src = par->fontbuffer + ((c & charmask) * (w * vc->vc_font.width)); - if (ops->cursor_state.image.data != src || - ops->cursor_reset) { - ops->cursor_state.image.data = src; - cursor.set |= FB_CUR_SETIMAGE; + if (par->cursor_state.image.data != src || + par->cursor_reset) { + par->cursor_state.image.data = src; + cursor.set |= FB_CUR_SETIMAGE; } if (attribute) { @@ -234,49 +234,49 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, dst = kmalloc_array(w, vc->vc_font.width, GFP_ATOMIC); if (!dst) return; - kfree(ops->cursor_data); - ops->cursor_data = dst; + kfree(par->cursor_data); + par->cursor_data = dst; cw_update_attr(dst, src, attribute, vc); src = dst; } - if (ops->cursor_state.image.fg_color != fg || - ops->cursor_state.image.bg_color != bg || - ops->cursor_reset) { - ops->cursor_state.image.fg_color = fg; - ops->cursor_state.image.bg_color = bg; + if (par->cursor_state.image.fg_color != fg || + par->cursor_state.image.bg_color != bg || + par->cursor_reset) { + par->cursor_state.image.fg_color = fg; + par->cursor_state.image.bg_color = bg; cursor.set |= FB_CUR_SETCMAP; } - if (ops->cursor_state.image.height != vc->vc_font.width || - ops->cursor_state.image.width != vc->vc_font.height || - ops->cursor_reset) { - ops->cursor_state.image.height = vc->vc_font.width; - ops->cursor_state.image.width = vc->vc_font.height; + if (par->cursor_state.image.height != vc->vc_font.width || + par->cursor_state.image.width != vc->vc_font.height || + par->cursor_reset) { + par->cursor_state.image.height = vc->vc_font.width; + par->cursor_state.image.width = vc->vc_font.height; cursor.set |= FB_CUR_SETSIZE; } dx = vxres - ((y * vc->vc_font.height) + vc->vc_font.height); dy = vc->state.x * vc->vc_font.width; - if (ops->cursor_state.image.dx != dx || - ops->cursor_state.image.dy != dy || - ops->cursor_reset) { - ops->cursor_state.image.dx = dx; - ops->cursor_state.image.dy = dy; + if (par->cursor_state.image.dx != dx || + par->cursor_state.image.dy != dy || + par->cursor_reset) { + par->cursor_state.image.dx = dx; + par->cursor_state.image.dy = dy; cursor.set |= FB_CUR_SETPOS; } - if (ops->cursor_state.hot.x || ops->cursor_state.hot.y || - ops->cursor_reset) { - ops->cursor_state.hot.x = cursor.hot.y = 0; + if (par->cursor_state.hot.x || par->cursor_state.hot.y || + par->cursor_reset) { + par->cursor_state.hot.x = cursor.hot.y = 0; cursor.set |= FB_CUR_SETHOT; } if (cursor.set & FB_CUR_SETSIZE || - vc->vc_cursor_type != ops->p->cursor_shape || - ops->cursor_state.mask == NULL || - ops->cursor_reset) { + vc->vc_cursor_type != par->p->cursor_shape || + par->cursor_state.mask == NULL || + par->cursor_reset) { char *tmp, *mask = kmalloc_array(w, vc->vc_font.width, GFP_ATOMIC); int cur_height, size, i = 0; @@ -292,13 +292,13 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, return; } - kfree(ops->cursor_state.mask); - ops->cursor_state.mask = mask; + kfree(par->cursor_state.mask); + par->cursor_state.mask = mask; - ops->p->cursor_shape = vc->vc_cursor_type; + par->p->cursor_shape = vc->vc_cursor_type; cursor.set |= FB_CUR_SETSHAPE; - switch (CUR_SIZE(ops->p->cursor_shape)) { + switch (CUR_SIZE(par->p->cursor_shape)) { case CUR_NONE: cur_height = 0; break; @@ -331,19 +331,19 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, kfree(tmp); } - ops->cursor_state.enable = enable && !use_sw; + par->cursor_state.enable = enable && !use_sw; cursor.image.data = src; - cursor.image.fg_color = ops->cursor_state.image.fg_color; - cursor.image.bg_color = ops->cursor_state.image.bg_color; - cursor.image.dx = ops->cursor_state.image.dx; - cursor.image.dy = ops->cursor_state.image.dy; - cursor.image.height = ops->cursor_state.image.height; - cursor.image.width = ops->cursor_state.image.width; - cursor.hot.x = ops->cursor_state.hot.x; - cursor.hot.y = ops->cursor_state.hot.y; - cursor.mask = ops->cursor_state.mask; - cursor.enable = ops->cursor_state.enable; + cursor.image.fg_color = par->cursor_state.image.fg_color; + cursor.image.bg_color = par->cursor_state.image.bg_color; + cursor.image.dx = par->cursor_state.image.dx; + cursor.image.dy = par->cursor_state.image.dy; + cursor.image.height = par->cursor_state.image.height; + cursor.image.width = par->cursor_state.image.width; + cursor.hot.x = par->cursor_state.hot.x; + cursor.hot.y = par->cursor_state.hot.y; + cursor.mask = par->cursor_state.mask; + cursor.enable = par->cursor_state.enable; cursor.image.depth = 1; cursor.rop = ROP_XOR; @@ -353,32 +353,32 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (err) soft_cursor(info, &cursor); - ops->cursor_reset = 0; + par->cursor_reset = 0; } static int cw_update_start(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; - u32 vxres = GETVXRES(ops->p, info); + struct fbcon_par *par = info->fbcon_par; + u32 vxres = GETVXRES(par->p, info); u32 xoffset; int err; - xoffset = vxres - (info->var.xres + ops->var.yoffset); - ops->var.yoffset = ops->var.xoffset; - ops->var.xoffset = xoffset; - err = fb_pan_display(info, &ops->var); - ops->var.xoffset = info->var.xoffset; - ops->var.yoffset = info->var.yoffset; - ops->var.vmode = info->var.vmode; + xoffset = vxres - (info->var.xres + par->var.yoffset); + par->var.yoffset = par->var.xoffset; + par->var.xoffset = xoffset; + err = fb_pan_display(info, &par->var); + par->var.xoffset = info->var.xoffset; + par->var.yoffset = info->var.yoffset; + par->var.vmode = info->var.vmode; return err; } -void fbcon_rotate_cw(struct fbcon_ops *ops) +void fbcon_rotate_cw(struct fbcon_par *par) { - ops->bmove = cw_bmove; - ops->clear = cw_clear; - ops->putcs = cw_putcs; - ops->clear_margins = cw_clear_margins; - ops->cursor = cw_cursor; - ops->update_start = cw_update_start; + par->bmove = cw_bmove; + par->clear = cw_clear; + par->putcs = cw_putcs; + par->clear_margins = cw_clear_margins; + par->cursor = cw_cursor; + par->update_start = cw_update_start; } diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c index ec3c883400f7b..380b2746451a1 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.c +++ b/drivers/video/fbdev/core/fbcon_rotate.c @@ -20,32 +20,32 @@ static int fbcon_rotate_font(struct fb_info *info, struct vc_data *vc) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int len, err = 0; int s_cellsize, d_cellsize, i; const u8 *src; u8 *dst; - if (vc->vc_font.data == ops->fontdata && - ops->p->con_rotate == ops->cur_rotate) + if (vc->vc_font.data == par->fontdata && + par->p->con_rotate == par->cur_rotate) goto finished; - src = ops->fontdata = vc->vc_font.data; - ops->cur_rotate = ops->p->con_rotate; + src = par->fontdata = vc->vc_font.data; + par->cur_rotate = par->p->con_rotate; len = vc->vc_font.charcount; s_cellsize = ((vc->vc_font.width + 7)/8) * vc->vc_font.height; d_cellsize = s_cellsize; - if (ops->rotate == FB_ROTATE_CW || - ops->rotate == FB_ROTATE_CCW) + if (par->rotate == FB_ROTATE_CW || + par->rotate == FB_ROTATE_CCW) d_cellsize = ((vc->vc_font.height + 7)/8) * vc->vc_font.width; if (info->fbops->fb_sync) info->fbops->fb_sync(info); - if (ops->fd_size < d_cellsize * len) { + if (par->fd_size < d_cellsize * len) { dst = kmalloc_array(len, d_cellsize, GFP_KERNEL); if (dst == NULL) { @@ -53,15 +53,15 @@ static int fbcon_rotate_font(struct fb_info *info, struct vc_data *vc) goto finished; } - ops->fd_size = d_cellsize * len; - kfree(ops->fontbuffer); - ops->fontbuffer = dst; + par->fd_size = d_cellsize * len; + kfree(par->fontbuffer); + par->fontbuffer = dst; } - dst = ops->fontbuffer; - memset(dst, 0, ops->fd_size); + dst = par->fontbuffer; + memset(dst, 0, par->fd_size); - switch (ops->rotate) { + switch (par->rotate) { case FB_ROTATE_UD: for (i = len; i--; ) { rotate_ud(src, dst, vc->vc_font.width, @@ -93,19 +93,19 @@ static int fbcon_rotate_font(struct fb_info *info, struct vc_data *vc) return err; } -void fbcon_set_rotate(struct fbcon_ops *ops) +void fbcon_set_rotate(struct fbcon_par *par) { - ops->rotate_font = fbcon_rotate_font; + par->rotate_font = fbcon_rotate_font; - switch(ops->rotate) { + switch (par->rotate) { case FB_ROTATE_CW: - fbcon_rotate_cw(ops); + fbcon_rotate_cw(par); break; case FB_ROTATE_UD: - fbcon_rotate_ud(ops); + fbcon_rotate_ud(par); break; case FB_ROTATE_CCW: - fbcon_rotate_ccw(ops); + fbcon_rotate_ccw(par); break; } } diff --git a/drivers/video/fbdev/core/fbcon_rotate.h b/drivers/video/fbdev/core/fbcon_rotate.h index 01cbe303b8a29..48305e1a07631 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.h +++ b/drivers/video/fbdev/core/fbcon_rotate.h @@ -90,7 +90,7 @@ static inline void rotate_ccw(const char *in, char *out, u32 width, u32 height) } } -extern void fbcon_rotate_cw(struct fbcon_ops *ops); -extern void fbcon_rotate_ud(struct fbcon_ops *ops); -extern void fbcon_rotate_ccw(struct fbcon_ops *ops); +extern void fbcon_rotate_cw(struct fbcon_par *par); +extern void fbcon_rotate_ud(struct fbcon_par *par); +extern void fbcon_rotate_ccw(struct fbcon_par *par); #endif diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 0af7913a2abdc..14b40e2bf323f 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -48,10 +48,10 @@ static void ud_update_attr(u8 *dst, u8 *src, int attribute, static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, int sx, int dy, int dx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_copyarea area; - u32 vyres = GETVYRES(ops->p, info); - u32 vxres = GETVXRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); + u32 vxres = GETVXRES(par->p, info); area.sy = vyres - ((sy + height) * vc->vc_font.height); area.sx = vxres - ((sx + width) * vc->vc_font.width); @@ -66,10 +66,10 @@ static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width, int fg, int bg) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; struct fb_fillrect region; - u32 vyres = GETVYRES(ops->p, info); - u32 vxres = GETVXRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); + u32 vxres = GETVXRES(par->p, info); region.color = bg; region.dy = vyres - ((sy + height) * vc->vc_font.height); @@ -86,13 +86,13 @@ static inline void ud_putcs_aligned(struct vc_data *vc, struct fb_info *info, u32 d_pitch, u32 s_pitch, u32 cellsize, struct fb_image *image, u8 *buf, u8 *dst) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; u32 idx = vc->vc_font.width >> 3; u8 *src; while (cnt--) { - src = ops->fontbuffer + (scr_readw(s--) & charmask)*cellsize; + src = par->fontbuffer + (scr_readw(s--) & charmask) * cellsize; if (attr) { ud_update_attr(buf, src, attr, vc); @@ -119,7 +119,7 @@ static inline void ud_putcs_unaligned(struct vc_data *vc, struct fb_image *image, u8 *buf, u8 *dst) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; u32 shift_low = 0, mod = vc->vc_font.width % 8; u32 shift_high = 8; @@ -127,7 +127,7 @@ static inline void ud_putcs_unaligned(struct vc_data *vc, u8 *src; while (cnt--) { - src = ops->fontbuffer + (scr_readw(s--) & charmask)*cellsize; + src = par->fontbuffer + (scr_readw(s--) & charmask) * cellsize; if (attr) { ud_update_attr(buf, src, attr, vc); @@ -152,7 +152,7 @@ static void ud_putcs(struct vc_data *vc, struct fb_info *info, int fg, int bg) { struct fb_image image; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; u32 width = (vc->vc_font.width + 7)/8; u32 cellsize = width * vc->vc_font.height; u32 maxcnt = info->pixmap.size/cellsize; @@ -161,10 +161,10 @@ static void ud_putcs(struct vc_data *vc, struct fb_info *info, u32 mod = vc->vc_font.width % 8, cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = GETVYRES(ops->p, info); - u32 vxres = GETVXRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); + u32 vxres = GETVXRES(par->p, info); - if (!ops->fontbuffer) + if (!par->fontbuffer) return; image.fg_color = fg; @@ -251,29 +251,29 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, bool enable, int fg, int bg) { struct fb_cursor cursor; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; int w = (vc->vc_font.width + 7) >> 3, c; - int y = real_y(ops->p, vc->state.y); + int y = real_y(par->p, vc->state.y); int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = GETVYRES(ops->p, info); - u32 vxres = GETVXRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); + u32 vxres = GETVXRES(par->p, info); - if (!ops->fontbuffer) + if (!par->fontbuffer) return; cursor.set = 0; c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); - src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.height)); + src = par->fontbuffer + ((c & charmask) * (w * vc->vc_font.height)); - if (ops->cursor_state.image.data != src || - ops->cursor_reset) { - ops->cursor_state.image.data = src; - cursor.set |= FB_CUR_SETIMAGE; + if (par->cursor_state.image.data != src || + par->cursor_reset) { + par->cursor_state.image.data = src; + cursor.set |= FB_CUR_SETIMAGE; } if (attribute) { @@ -282,49 +282,49 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, bool enable, dst = kmalloc_array(w, vc->vc_font.height, GFP_ATOMIC); if (!dst) return; - kfree(ops->cursor_data); - ops->cursor_data = dst; + kfree(par->cursor_data); + par->cursor_data = dst; ud_update_attr(dst, src, attribute, vc); src = dst; } - if (ops->cursor_state.image.fg_color != fg || - ops->cursor_state.image.bg_color != bg || - ops->cursor_reset) { - ops->cursor_state.image.fg_color = fg; - ops->cursor_state.image.bg_color = bg; + if (par->cursor_state.image.fg_color != fg || + par->cursor_state.image.bg_color != bg || + par->cursor_reset) { + par->cursor_state.image.fg_color = fg; + par->cursor_state.image.bg_color = bg; cursor.set |= FB_CUR_SETCMAP; } - if (ops->cursor_state.image.height != vc->vc_font.height || - ops->cursor_state.image.width != vc->vc_font.width || - ops->cursor_reset) { - ops->cursor_state.image.height = vc->vc_font.height; - ops->cursor_state.image.width = vc->vc_font.width; + if (par->cursor_state.image.height != vc->vc_font.height || + par->cursor_state.image.width != vc->vc_font.width || + par->cursor_reset) { + par->cursor_state.image.height = vc->vc_font.height; + par->cursor_state.image.width = vc->vc_font.width; cursor.set |= FB_CUR_SETSIZE; } dy = vyres - ((y * vc->vc_font.height) + vc->vc_font.height); dx = vxres - ((vc->state.x * vc->vc_font.width) + vc->vc_font.width); - if (ops->cursor_state.image.dx != dx || - ops->cursor_state.image.dy != dy || - ops->cursor_reset) { - ops->cursor_state.image.dx = dx; - ops->cursor_state.image.dy = dy; + if (par->cursor_state.image.dx != dx || + par->cursor_state.image.dy != dy || + par->cursor_reset) { + par->cursor_state.image.dx = dx; + par->cursor_state.image.dy = dy; cursor.set |= FB_CUR_SETPOS; } - if (ops->cursor_state.hot.x || ops->cursor_state.hot.y || - ops->cursor_reset) { - ops->cursor_state.hot.x = cursor.hot.y = 0; + if (par->cursor_state.hot.x || par->cursor_state.hot.y || + par->cursor_reset) { + par->cursor_state.hot.x = cursor.hot.y = 0; cursor.set |= FB_CUR_SETHOT; } if (cursor.set & FB_CUR_SETSIZE || - vc->vc_cursor_type != ops->p->cursor_shape || - ops->cursor_state.mask == NULL || - ops->cursor_reset) { + vc->vc_cursor_type != par->p->cursor_shape || + par->cursor_state.mask == NULL || + par->cursor_reset) { char *mask = kmalloc_array(w, vc->vc_font.height, GFP_ATOMIC); int cur_height, size, i = 0; u8 msk = 0xff; @@ -332,13 +332,13 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (!mask) return; - kfree(ops->cursor_state.mask); - ops->cursor_state.mask = mask; + kfree(par->cursor_state.mask); + par->cursor_state.mask = mask; - ops->p->cursor_shape = vc->vc_cursor_type; + par->p->cursor_shape = vc->vc_cursor_type; cursor.set |= FB_CUR_SETSHAPE; - switch (CUR_SIZE(ops->p->cursor_shape)) { + switch (CUR_SIZE(par->p->cursor_shape)) { case CUR_NONE: cur_height = 0; break; @@ -371,19 +371,19 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, bool enable, mask[i++] = ~msk; } - ops->cursor_state.enable = enable && !use_sw; + par->cursor_state.enable = enable && !use_sw; cursor.image.data = src; - cursor.image.fg_color = ops->cursor_state.image.fg_color; - cursor.image.bg_color = ops->cursor_state.image.bg_color; - cursor.image.dx = ops->cursor_state.image.dx; - cursor.image.dy = ops->cursor_state.image.dy; - cursor.image.height = ops->cursor_state.image.height; - cursor.image.width = ops->cursor_state.image.width; - cursor.hot.x = ops->cursor_state.hot.x; - cursor.hot.y = ops->cursor_state.hot.y; - cursor.mask = ops->cursor_state.mask; - cursor.enable = ops->cursor_state.enable; + cursor.image.fg_color = par->cursor_state.image.fg_color; + cursor.image.bg_color = par->cursor_state.image.bg_color; + cursor.image.dx = par->cursor_state.image.dx; + cursor.image.dy = par->cursor_state.image.dy; + cursor.image.height = par->cursor_state.image.height; + cursor.image.width = par->cursor_state.image.width; + cursor.hot.x = par->cursor_state.hot.x; + cursor.hot.y = par->cursor_state.hot.y; + cursor.mask = par->cursor_state.mask; + cursor.enable = par->cursor_state.enable; cursor.image.depth = 1; cursor.rop = ROP_XOR; @@ -393,36 +393,36 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (err) soft_cursor(info, &cursor); - ops->cursor_reset = 0; + par->cursor_reset = 0; } static int ud_update_start(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int xoffset, yoffset; - u32 vyres = GETVYRES(ops->p, info); - u32 vxres = GETVXRES(ops->p, info); + u32 vyres = GETVYRES(par->p, info); + u32 vxres = GETVXRES(par->p, info); int err; - xoffset = vxres - info->var.xres - ops->var.xoffset; - yoffset = vyres - info->var.yres - ops->var.yoffset; + xoffset = vxres - info->var.xres - par->var.xoffset; + yoffset = vyres - info->var.yres - par->var.yoffset; if (yoffset < 0) yoffset += vyres; - ops->var.xoffset = xoffset; - ops->var.yoffset = yoffset; - err = fb_pan_display(info, &ops->var); - ops->var.xoffset = info->var.xoffset; - ops->var.yoffset = info->var.yoffset; - ops->var.vmode = info->var.vmode; + par->var.xoffset = xoffset; + par->var.yoffset = yoffset; + err = fb_pan_display(info, &par->var); + par->var.xoffset = info->var.xoffset; + par->var.yoffset = info->var.yoffset; + par->var.vmode = info->var.vmode; return err; } -void fbcon_rotate_ud(struct fbcon_ops *ops) +void fbcon_rotate_ud(struct fbcon_par *par) { - ops->bmove = ud_bmove; - ops->clear = ud_clear; - ops->putcs = ud_putcs; - ops->clear_margins = ud_clear_margins; - ops->cursor = ud_cursor; - ops->update_start = ud_update_start; + par->bmove = ud_bmove; + par->clear = ud_clear; + par->putcs = ud_putcs; + par->clear_margins = ud_clear_margins; + par->cursor = ud_cursor; + par->update_start = ud_update_start; } diff --git a/drivers/video/fbdev/core/softcursor.c b/drivers/video/fbdev/core/softcursor.c index 29e5b21cf373e..900788c059153 100644 --- a/drivers/video/fbdev/core/softcursor.c +++ b/drivers/video/fbdev/core/softcursor.c @@ -21,7 +21,7 @@ int soft_cursor(struct fb_info *info, struct fb_cursor *cursor) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; unsigned int scan_align = info->pixmap.scan_align - 1; unsigned int buf_align = info->pixmap.buf_align - 1; unsigned int i, size, dsize, s_pitch, d_pitch; @@ -34,19 +34,19 @@ int soft_cursor(struct fb_info *info, struct fb_cursor *cursor) s_pitch = (cursor->image.width + 7) >> 3; dsize = s_pitch * cursor->image.height; - if (dsize + sizeof(struct fb_image) != ops->cursor_size) { - kfree(ops->cursor_src); - ops->cursor_size = dsize + sizeof(struct fb_image); + if (dsize + sizeof(struct fb_image) != par->cursor_size) { + kfree(par->cursor_src); + par->cursor_size = dsize + sizeof(struct fb_image); - ops->cursor_src = kmalloc(ops->cursor_size, GFP_ATOMIC); - if (!ops->cursor_src) { - ops->cursor_size = 0; + par->cursor_src = kmalloc(par->cursor_size, GFP_ATOMIC); + if (!par->cursor_src) { + par->cursor_size = 0; return -ENOMEM; } } - src = ops->cursor_src + sizeof(struct fb_image); - image = (struct fb_image *)ops->cursor_src; + src = par->cursor_src + sizeof(struct fb_image); + image = (struct fb_image *)par->cursor_src; *image = cursor->image; d_pitch = (s_pitch + scan_align) & ~scan_align; diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index d342b90c42b7f..4428f2bcd3f8c 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -151,34 +151,34 @@ static void tile_cursor(struct vc_data *vc, struct fb_info *info, bool enable, static int tile_update_start(struct fb_info *info) { - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; int err; - err = fb_pan_display(info, &ops->var); - ops->var.xoffset = info->var.xoffset; - ops->var.yoffset = info->var.yoffset; - ops->var.vmode = info->var.vmode; + err = fb_pan_display(info, &par->var); + par->var.xoffset = info->var.xoffset; + par->var.yoffset = info->var.yoffset; + par->var.vmode = info->var.vmode; return err; } void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info) { struct fb_tilemap map; - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_par *par = info->fbcon_par; - ops->bmove = tile_bmove; - ops->clear = tile_clear; - ops->putcs = tile_putcs; - ops->clear_margins = tile_clear_margins; - ops->cursor = tile_cursor; - ops->update_start = tile_update_start; + par->bmove = tile_bmove; + par->clear = tile_clear; + par->putcs = tile_putcs; + par->clear_margins = tile_clear_margins; + par->cursor = tile_cursor; + par->update_start = tile_update_start; - if (ops->p) { + if (par->p) { map.width = vc->vc_font.width; map.height = vc->vc_font.height; map.depth = 1; map.length = vc->vc_font.charcount; - map.data = ops->p->fontdata; + map.data = par->p->fontdata; info->tileops->fb_settile(info, &map); } } From 7105d9f1387d63b15c9a860674fc92c959181f2f Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 14 May 2026 13:58:45 -0400 Subject: [PATCH 0156/1518] fbcon: Avoid OOB font access if console rotation fails [ Upstream commit e4ef723d8975a2694cc90733a6b888a5e2841842 ] Clear the font buffer if the reallocation during console rotation fails in fbcon_rotate_font(). The putcs implementations for the rotated buffer will return early in this case. See [1] for an example. Currently, fbcon_rotate_font() keeps the old buffer, which is too small for the rotated font. Printing to the rotated console with a high-enough character code will overflow the font buffer. v2: - fix typos in commit message Signed-off-by: Thomas Zimmermann Fixes: 6cc50e1c5b57 ("[PATCH] fbcon: Console Rotation - Add support to rotate font bitmap") Cc: stable@vger.kernel.org # v2.6.15+ Link: https://elixir.bootlin.com/linux/v6.19/source/drivers/video/fbdev/core/fbcon_ccw.c#L144 # [1] Signed-off-by: Helge Deller Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/core/fbcon_rotate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c index 380b2746451a1..a3f507825eed8 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.c +++ b/drivers/video/fbdev/core/fbcon_rotate.c @@ -46,6 +46,10 @@ static int fbcon_rotate_font(struct fb_info *info, struct vc_data *vc) info->fbops->fb_sync(info); if (par->fd_size < d_cellsize * len) { + kfree(par->fontbuffer); + par->fontbuffer = NULL; + par->fd_size = 0; + dst = kmalloc_array(len, d_cellsize, GFP_KERNEL); if (dst == NULL) { @@ -54,7 +58,6 @@ static int fbcon_rotate_font(struct fb_info *info, struct vc_data *vc) } par->fd_size = d_cellsize * len; - kfree(par->fontbuffer); par->fontbuffer = dst; } From d281f3ac0d00d7ae9d409537b1a28f6957701e72 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 14 May 2026 11:52:20 -0400 Subject: [PATCH 0157/1518] block: fix zone write plug removal [ Upstream commit b7d4ffb510373cc6ecf16022dd0e510a023034fb ] Commit 7b295187287e ("block: Do not remove zone write plugs still in use") modified disk_should_remove_zone_wplug() to add a check on the reference count of a zone write plug to prevent removing zone write plugs from a disk hash table when the plugs are still being referenced by BIOs or requests in-flight. However, this check does not take into account that a BIO completion may happen right after its submission by a zone write plug BIO work, and before the zone write plug BIO work releases the zone write plug reference count. This situation leads to disk_should_remove_zone_wplug() returning false as in this case the zone write plug reference count is at least equal to 3. If the BIO that completes in such manner transitioned the zone to the FULL condition, the zone write plug for the FULL zone will remain in the disk hash table. Furthermore, relying on a particular value of a zone write plug reference count to set the BLK_ZONE_WPLUG_UNHASHED flag is fragile as reading the atomic reference count and doing a comparison with some value is not overall atomic at all. Address these issues by reworking the reference counting of zone write plugs so that removing plugs from a disk hash table can be done directly from disk_put_zone_wplug() when the last reference on a plug is dropped. To do so, replace the function disk_remove_zone_wplug() with disk_mark_zone_wplug_dead(). This new function sets the zone write plug flag BLK_ZONE_WPLUG_DEAD (which replaces BLK_ZONE_WPLUG_UNHASHED) and drops the initial reference on the zone write plug taken when the plug was added to the disk hash table. This function is called either for zones that are empty or full, or directly in the case of a forced plug removal (e.g. when the disk hash table is being destroyed on disk removal). With this change, disk_should_remove_zone_wplug() is also removed. disk_put_zone_wplug() is modified to call the function disk_free_zone_wplug() to remove a zone write plug from a disk hash table and free the plug structure (with a call_rcu()), when the last reference on a zone write plug is dropped. disk_free_zone_wplug() always checks that the BLK_ZONE_WPLUG_DEAD flag is set. In order to avoid having multiple zone write plugs for the same zone in the disk hash table, disk_get_and_lock_zone_wplug() checked for the BLK_ZONE_WPLUG_UNHASHED flag. This check is removed and a check for the new BLK_ZONE_WPLUG_DEAD flag is added to blk_zone_wplug_handle_write(). With this change, we continue preventing adding multiple zone write plugs for the same zone and at the same time re-inforce checks on the user behavior by failing new incoming write BIOs targeting a zone that is marked as dead. This case can happen only if the user erroneously issues write BIOs to zones that are full, or to zones that are currently being reset or finished. Fixes: 7b295187287e ("block: Do not remove zone write plugs still in use") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe [ dropped upstream blk_zone_set_cond() call and disk_zone_wplug_update_cond() context line ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- block/blk-zoned.c | 147 ++++++++++++++++++---------------------------- 1 file changed, 56 insertions(+), 91 deletions(-) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index e98bd9ad02329..59b7a1d14af5b 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -83,17 +83,17 @@ static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) * being executed or the zone write plug bio list is not empty. * - BLK_ZONE_WPLUG_NEED_WP_UPDATE: Indicates that we lost track of a zone * write pointer offset and need to update it. - * - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed - * from the disk hash table and that the initial reference to the zone - * write plug set when the plug was first added to the hash table has been - * dropped. This flag is set when a zone is reset, finished or become full, - * to prevent new references to the zone write plug to be taken for - * newly incoming BIOs. A zone write plug flagged with this flag will be - * freed once all remaining references from BIOs or functions are dropped. + * - BLK_ZONE_WPLUG_DEAD: Indicates that the zone write plug will be + * removed from the disk hash table of zone write plugs when the last + * reference on the zone write plug is dropped. If set, this flag also + * indicates that the initial extra reference on the zone write plug was + * dropped, meaning that the reference count indicates the current number of + * active users (code context or BIOs and requests in flight). This flag is + * set when a zone is reset, finished or becomes full. */ #define BLK_ZONE_WPLUG_PLUGGED (1U << 0) #define BLK_ZONE_WPLUG_NEED_WP_UPDATE (1U << 1) -#define BLK_ZONE_WPLUG_UNHASHED (1U << 2) +#define BLK_ZONE_WPLUG_DEAD (1U << 2) /** * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX. @@ -467,67 +467,42 @@ static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head) mempool_free(zwplug, zwplug->disk->zone_wplugs_pool); } -static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) +static void disk_free_zone_wplug(struct blk_zone_wplug *zwplug) { - if (refcount_dec_and_test(&zwplug->ref)) { - WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list)); - WARN_ON_ONCE(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); - WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_UNHASHED)); - - call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu); - } -} - -static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - lockdep_assert_held(&zwplug->lock); - - /* If the zone write plug was already removed, we are done. */ - if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) - return false; + struct gendisk *disk = zwplug->disk; + unsigned long flags; - /* If the zone write plug is still plugged, it cannot be removed. */ - if (zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) - return false; + WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_DEAD)); + WARN_ON_ONCE(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); + WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list)); - /* - * Completions of BIOs with blk_zone_write_plug_bio_endio() may - * happen after handling a request completion with - * blk_zone_write_plug_finish_request() (e.g. with split BIOs - * that are chained). In such case, disk_zone_wplug_unplug_bio() - * should not attempt to remove the zone write plug until all BIO - * completions are seen. Check by looking at the zone write plug - * reference count, which is 2 when the plug is unused (one reference - * taken when the plug was allocated and another reference taken by the - * caller context). - */ - if (refcount_read(&zwplug->ref) > 2) - return false; + spin_lock_irqsave(&disk->zone_wplugs_lock, flags); + hlist_del_init_rcu(&zwplug->node); + atomic_dec(&disk->nr_zone_wplugs); + spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); - /* We can remove zone write plugs for zones that are empty or full. */ - return !zwplug->wp_offset || disk_zone_wplug_is_full(disk, zwplug); + call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu); } -static void disk_remove_zone_wplug(struct gendisk *disk, - struct blk_zone_wplug *zwplug) +static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) { - unsigned long flags; + if (refcount_dec_and_test(&zwplug->ref)) + disk_free_zone_wplug(zwplug); +} - /* If the zone write plug was already removed, we have nothing to do. */ - if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) - return; +/* + * Flag the zone write plug as dead and drop the initial reference we got when + * the zone write plug was added to the hash table. The zone write plug will be + * unhashed when its last reference is dropped. + */ +static void disk_mark_zone_wplug_dead(struct blk_zone_wplug *zwplug) +{ + lockdep_assert_held(&zwplug->lock); - /* - * Mark the zone write plug as unhashed and drop the extra reference we - * took when the plug was inserted in the hash table. - */ - zwplug->flags |= BLK_ZONE_WPLUG_UNHASHED; - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - hlist_del_init_rcu(&zwplug->node); - atomic_dec(&disk->nr_zone_wplugs); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); - disk_put_zone_wplug(zwplug); + if (!(zwplug->flags & BLK_ZONE_WPLUG_DEAD)) { + zwplug->flags |= BLK_ZONE_WPLUG_DEAD; + disk_put_zone_wplug(zwplug); + } } static void blk_zone_wplug_bio_work(struct work_struct *work); @@ -547,18 +522,7 @@ static struct blk_zone_wplug *disk_get_and_lock_zone_wplug(struct gendisk *disk, again: zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { - /* - * Check that a BIO completion or a zone reset or finish - * operation has not already removed the zone write plug from - * the hash table and dropped its reference count. In such case, - * we need to get a new plug so start over from the beginning. - */ spin_lock_irqsave(&zwplug->lock, *flags); - if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) { - spin_unlock_irqrestore(&zwplug->lock, *flags); - disk_put_zone_wplug(zwplug); - goto again; - } return zwplug; } @@ -645,14 +609,8 @@ static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, zwplug->flags &= ~BLK_ZONE_WPLUG_NEED_WP_UPDATE; zwplug->wp_offset = wp_offset; disk_zone_wplug_abort(zwplug); - - /* - * The zone write plug now has no BIO plugged: remove it from the - * hash table so that it cannot be seen. The plug will be freed - * when the last reference is dropped. - */ - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); + if (!zwplug->wp_offset || disk_zone_wplug_is_full(disk, zwplug)) + disk_mark_zone_wplug_dead(zwplug); } static unsigned int blk_zone_wp_offset(struct blk_zone *zone) @@ -1068,6 +1026,19 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) return true; } + /* + * If we got a zone write plug marked as dead, then the user is issuing + * writes to a full zone, or without synchronizing with zone reset or + * zone finish operations. In such case, fail the BIO to signal this + * invalid usage. + */ + if (zwplug->flags & BLK_ZONE_WPLUG_DEAD) { + spin_unlock_irqrestore(&zwplug->lock, flags); + disk_put_zone_wplug(zwplug); + bio_io_error(bio); + return true; + } + /* Indicate that this BIO is being handled using zone write plugging. */ bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING); @@ -1136,7 +1107,7 @@ static void blk_zone_wplug_handle_native_zone_append(struct bio *bio) disk->disk_name, zwplug->zone_no); disk_zone_wplug_abort(zwplug); } - disk_remove_zone_wplug(disk, zwplug); + disk_mark_zone_wplug_dead(zwplug); spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); @@ -1239,14 +1210,8 @@ static void disk_zone_wplug_unplug_bio(struct gendisk *disk, } zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; - - /* - * If the zone is full (it was fully written or finished, or empty - * (it was reset), remove its zone write plug from the hash table. - */ - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); - + if (!zwplug->wp_offset || disk_zone_wplug_is_full(disk, zwplug)) + disk_mark_zone_wplug_dead(zwplug); spin_unlock_irqrestore(&zwplug->lock, flags); } @@ -1457,9 +1422,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) while (!hlist_empty(&disk->zone_wplugs_hash[i])) { zwplug = hlist_entry(disk->zone_wplugs_hash[i].first, struct blk_zone_wplug, node); - refcount_inc(&zwplug->ref); - disk_remove_zone_wplug(disk, zwplug); - disk_put_zone_wplug(zwplug); + spin_lock_irq(&zwplug->lock); + disk_mark_zone_wplug_dead(zwplug); + spin_unlock_irq(&zwplug->lock); } } From 24d2912962d087ebff7c4984f8ac34a5f23c8dbf Mon Sep 17 00:00:00 2001 From: Prasanna Kumar T S M Date: Thu, 14 May 2026 11:52:31 -0400 Subject: [PATCH 0158/1518] EDAC/versalnet: Fix device name memory leak [ Upstream commit 8cf5dd235eff6008cb04c3d8064d2acfa90616f1 ] The device name allocated via kzalloc() in init_one_mc() is assigned to dev->init_name but never freed on the normal removal path. device_register() copies init_name and then sets dev->init_name to NULL, so the name pointer becomes unreachable from the device. Thus leaking memory. Use a stack-local char array instead of using kzalloc() for name. Fixes: d5fe2fec6c40 ("EDAC: Add a driver for the AMD Versal NET DDR controller") Signed-off-by: Prasanna Kumar T S M Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260401111856.2342975-1-ptsm@linux.microsoft.com [ adapted fix from `init_one_mc()` helper to the equivalent loop in `init_versalnet()` using literal `32` instead of `MC_NAME_LEN` ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/edac/versalnet_edac.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/edac/versalnet_edac.c b/drivers/edac/versalnet_edac.c index f90723bc93d5c..4053ee2e0beef 100644 --- a/drivers/edac/versalnet_edac.c +++ b/drivers/edac/versalnet_edac.c @@ -765,9 +765,9 @@ static int init_versalnet(struct mc_priv *priv, struct platform_device *pdev) u32 num_chans, rank, dwidth, config; struct edac_mc_layer layers[2]; struct mem_ctl_info *mci; + char name[32]; struct device *dev; enum dev_type dt; - char *name; int rc, i; for (i = 0; i < NUM_CONTROLLERS; i++) { @@ -814,7 +814,6 @@ static int init_versalnet(struct mc_priv *priv, struct platform_device *pdev) dev = kzalloc(sizeof(*dev), GFP_KERNEL); dev->release = versal_edac_release; - name = kmalloc(32, GFP_KERNEL); sprintf(name, "versal-net-ddrmc5-edac-%d", i); dev->init_name = name; rc = device_register(dev); From 09c15bbbed533903e600660ea09098b3b0524f48 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 14 May 2026 11:08:19 -0400 Subject: [PATCH 0159/1518] papr-hvpipe: convert papr_hvpipe_dev_create_handle() to FD_PREPARE() [ Upstream commit 6d3789d347a7af5c4b0b2da3af47b8d9da607ab2 ] Fixes a UAF for src_info as well. Link: https://patch.msgid.link/20251123-work-fd-prepare-v4-33-b6efa1706cfd@kernel.org Signed-off-by: Christian Brauner Stable-dep-of: 7a4f0846ee6c ("pseries/papr-hvpipe: Fix race with interrupt handler") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/pseries/papr-hvpipe.c | 39 +++++--------------- 1 file changed, 9 insertions(+), 30 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c index 431f6a3da4c5a..3d8672642c251 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.c +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c @@ -484,10 +484,7 @@ static const struct file_operations papr_hvpipe_handle_ops = { static int papr_hvpipe_dev_create_handle(u32 srcID) { - struct hvpipe_source_info *src_info; - struct file *file; - long err; - int fd; + struct hvpipe_source_info *src_info __free(kfree) = NULL; spin_lock(&hvpipe_src_list_lock); /* @@ -511,20 +508,13 @@ static int papr_hvpipe_dev_create_handle(u32 srcID) src_info->tsk = current; init_waitqueue_head(&src_info->recv_wqh); - fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC); - if (fd < 0) { - err = fd; - goto free_buf; - } - - file = anon_inode_getfile("[papr-hvpipe]", - &papr_hvpipe_handle_ops, (void *)src_info, - O_RDWR); - if (IS_ERR(file)) { - err = PTR_ERR(file); - goto free_fd; - } + FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC, + anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops, + (void *)src_info, O_RDWR)); + if (fdf.err) + return fdf.err; + retain_and_null_ptr(src_info); spin_lock(&hvpipe_src_list_lock); /* * If two processes are executing ioctl() for the same @@ -533,22 +523,11 @@ static int papr_hvpipe_dev_create_handle(u32 srcID) */ if (hvpipe_find_source(srcID)) { spin_unlock(&hvpipe_src_list_lock); - err = -EALREADY; - goto free_file; + return -EALREADY; } list_add(&src_info->list, &hvpipe_src_list); spin_unlock(&hvpipe_src_list_lock); - - fd_install(fd, file); - return fd; - -free_file: - fput(file); -free_fd: - put_unused_fd(fd); -free_buf: - kfree(src_info); - return err; + return fd_publish(fdf); } /* From 6542e180fa6e1c701aba446a555c65556e6fd1a5 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Thu, 14 May 2026 11:08:20 -0400 Subject: [PATCH 0160/1518] pseries/papr-hvpipe: Fix race with interrupt handler [ Upstream commit 7a4f0846ee6cc8cf44ae0046ed42e3259d1dd45b ] While executing ->ioctl handler or ->release handler, if an interrupt fires on the same cpu, then we can enter into a deadlock. This patch fixes both these handlers to take spin_lock_irq{save|restore} versions of the lock to prevent this deadlock. Cc: stable@vger.kernel.org Fixes: 814ef095f12c9 ("powerpc/pseries: Add papr-hvpipe char driver for HVPIPE interfaces") Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/e4ed435c44fc191f2eb23c7907ba6f72f193e6aa.1777606826.git.ritesh.list@gmail.com Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/pseries/papr-hvpipe.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c index 3d8672642c251..a238db095b4ec 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.c +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c @@ -449,13 +449,14 @@ static int papr_hvpipe_handle_release(struct inode *inode, struct file *file) { struct hvpipe_source_info *src_info; + unsigned long flags; /* * Hold the lock, remove source from src_list, reset the * hvpipe status and release the lock to prevent any race * with message event IRQ. */ - spin_lock(&hvpipe_src_list_lock); + spin_lock_irqsave(&hvpipe_src_list_lock, flags); src_info = file->private_data; list_del(&src_info->list); file->private_data = NULL; @@ -466,10 +467,10 @@ static int papr_hvpipe_handle_release(struct inode *inode, */ if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) { src_info->hvpipe_status = 0; - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); hvpipe_rtas_recv_msg(NULL, 0); } else - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); kfree(src_info); return 0; @@ -485,20 +486,21 @@ static const struct file_operations papr_hvpipe_handle_ops = { static int papr_hvpipe_dev_create_handle(u32 srcID) { struct hvpipe_source_info *src_info __free(kfree) = NULL; + unsigned long flags; - spin_lock(&hvpipe_src_list_lock); + spin_lock_irqsave(&hvpipe_src_list_lock, flags); /* * Do not allow more than one process communicates with * each source. */ src_info = hvpipe_find_source(srcID); if (src_info) { - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); pr_err("pid(%d) is already using the source(%d)\n", src_info->tsk->pid, srcID); return -EALREADY; } - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); src_info = kzalloc(sizeof(*src_info), GFP_KERNEL_ACCOUNT); if (!src_info) @@ -515,18 +517,18 @@ static int papr_hvpipe_dev_create_handle(u32 srcID) return fdf.err; retain_and_null_ptr(src_info); - spin_lock(&hvpipe_src_list_lock); + spin_lock_irqsave(&hvpipe_src_list_lock, flags); /* * If two processes are executing ioctl() for the same * source ID concurrently, prevent the second process to * acquire FD. */ if (hvpipe_find_source(srcID)) { - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); return -EALREADY; } list_add(&src_info->list, &hvpipe_src_list); - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); return fd_publish(fdf); } From b0a97cb0b9ba51415d44062977f8e44eef56c161 Mon Sep 17 00:00:00 2001 From: Pei Xiao Date: Thu, 14 May 2026 00:58:32 -0400 Subject: [PATCH 0161/1518] spi: uniphier: Simplify clock handling with devm_clk_get_enabled() [ Upstream commit fdca270f8f87cae2eb5b619234b9dd11a863ce6b ] Replace devm_clk_get() followed by clk_prepare_enable() with devm_clk_get_enabled() for the clock. This removes the need for explicit clock enable and disable calls, as the managed API automatically handles clock disabling on device removal or probe failure. Remove the now-unnecessary clk_disable_unprepare() calls from the probe error path and the remove callback. Adjust error labels accordingly. Signed-off-by: Pei Xiao Reviewed-by: Kunihiko Hayashi Link: https://patch.msgid.link/b2deeefd4ef1a4bce71116aabfcb7e81400f6d37.1775546948.git.xiaopei01@kylinos.cn Signed-off-by: Mark Brown Stable-dep-of: 0245435f7772 ("spi: uniphier: fix controller deregistration") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-uniphier.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index ff2142f87277f..b517c08a13608 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -666,28 +666,24 @@ static int uniphier_spi_probe(struct platform_device *pdev) } priv->base_dma_addr = res->start; - priv->clk = devm_clk_get(&pdev->dev, NULL); + priv->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(priv->clk)) { dev_err(&pdev->dev, "failed to get clock\n"); ret = PTR_ERR(priv->clk); goto out_host_put; } - ret = clk_prepare_enable(priv->clk); - if (ret) - goto out_host_put; - irq = platform_get_irq(pdev, 0); if (irq < 0) { ret = irq; - goto out_disable_clk; + goto out_host_put; } ret = devm_request_irq(&pdev->dev, irq, uniphier_spi_handler, 0, "uniphier-spi", priv); if (ret) { dev_err(&pdev->dev, "failed to request IRQ\n"); - goto out_disable_clk; + goto out_host_put; } init_completion(&priv->xfer_done); @@ -717,7 +713,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (IS_ERR_OR_NULL(host->dma_tx)) { if (PTR_ERR(host->dma_tx) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; - goto out_disable_clk; + goto out_host_put; } host->dma_tx = NULL; dma_tx_burst = INT_MAX; @@ -767,9 +763,6 @@ static int uniphier_spi_probe(struct platform_device *pdev) host->dma_tx = NULL; } -out_disable_clk: - clk_disable_unprepare(priv->clk); - out_host_put: spi_controller_put(host); return ret; @@ -778,14 +771,11 @@ static int uniphier_spi_probe(struct platform_device *pdev) static void uniphier_spi_remove(struct platform_device *pdev) { struct spi_controller *host = platform_get_drvdata(pdev); - struct uniphier_spi_priv *priv = spi_controller_get_devdata(host); if (host->dma_tx) dma_release_channel(host->dma_tx); if (host->dma_rx) dma_release_channel(host->dma_rx); - - clk_disable_unprepare(priv->clk); } static const struct of_device_id uniphier_spi_match[] = { From fafa9a4e831b74f533b402409ff3c2b15f11c122 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 14 May 2026 00:58:33 -0400 Subject: [PATCH 0162/1518] spi: uniphier: fix controller deregistration [ Upstream commit 0245435f777264ac45945ed2f325dd095a41d1af ] Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind. Note that clocks were also disabled before the recent commit fdca270f8f87 ("spi: uniphier: Simplify clock handling with devm_clk_get_enabled()"). Fixes: 5ba155a4d4cc ("spi: add SPI controller driver for UniPhier SoC") Cc: stable@vger.kernel.org # 4.19 Cc: Keiji Hayashibara Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-25-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-uniphier.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index b517c08a13608..75b7a0d3f8657 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -747,7 +747,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) host->max_dma_len = min(dma_tx_burst, dma_rx_burst); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret) goto out_release_dma; @@ -772,10 +772,16 @@ static void uniphier_spi_remove(struct platform_device *pdev) { struct spi_controller *host = platform_get_drvdata(pdev); + spi_controller_get(host); + + spi_unregister_controller(host); + if (host->dma_tx) dma_release_channel(host->dma_tx); if (host->dma_rx) dma_release_channel(host->dma_rx); + + spi_controller_put(host); } static const struct of_device_id uniphier_spi_match[] = { From 65eafad7a6005bc221fc24610e5810f7cceea53b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 14 May 2026 00:14:46 -0400 Subject: [PATCH 0163/1518] spi: tegra20-sflash: fix controller deregistration [ Upstream commit ad7310e983327f939dd6c4e801eab13238992572 ] Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: f12f7318c44a ("spi: tegra20-sflash: use devm_spi_register_master()") Cc: stable@vger.kernel.org # 3.13 Cc: Jingoo Han Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-23-johan@kernel.org Signed-off-by: Mark Brown [ kept the redundant `host->dev.of_node = pdev->dev.of_node;` line above the registration call ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-tegra20-sflash.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c index d5c8ee20b8e5b..dc3fcab5faa95 100644 --- a/drivers/spi/spi-tegra20-sflash.c +++ b/drivers/spi/spi-tegra20-sflash.c @@ -506,7 +506,7 @@ static int tegra_sflash_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); host->dev.of_node = pdev->dev.of_node; - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret < 0) { dev_err(&pdev->dev, "can not register to host err %d\n", ret); goto exit_pm_disable; @@ -529,11 +529,17 @@ static void tegra_sflash_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct tegra_sflash_data *tsd = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + free_irq(tsd->irq, tsd); pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) tegra_sflash_runtime_suspend(&pdev->dev); + + spi_controller_put(host); } #ifdef CONFIG_PM_SLEEP From 33e5ce64b8170c6b8a64d6eb5853aa655357c417 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 13 May 2026 23:10:37 -0400 Subject: [PATCH 0164/1518] spi: tegra114: fix controller deregistration [ Upstream commit 9c9c27ff2058142d8f800de3186d6864184958de ] Make sure to deregister the controller before disabling underlying resources like clocks during driver unbind. Fixes: 5c8096439600 ("spi: tegra114: use devm_spi_register_master()") Cc: stable@vger.kernel.org # 3.13 Cc: Jingoo Han Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-22-johan@kernel.org Signed-off-by: Mark Brown [ kept `host->dev.of_node = pdev->dev.of_node;` context line above the `spi_register_controller()` conversion ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-tegra114.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c index 48fb11fea55f2..a28597b6b80d6 100644 --- a/drivers/spi/spi-tegra114.c +++ b/drivers/spi/spi-tegra114.c @@ -1416,7 +1416,7 @@ static int tegra_spi_probe(struct platform_device *pdev) } host->dev.of_node = pdev->dev.of_node; - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret < 0) { dev_err(&pdev->dev, "can not register to host err %d\n", ret); goto exit_free_irq; @@ -1442,6 +1442,10 @@ static void tegra_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct tegra_spi_data *tspi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + free_irq(tspi->irq, tspi); if (tspi->tx_dma_chan) @@ -1453,6 +1457,8 @@ static void tegra_spi_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) tegra_spi_runtime_suspend(&pdev->dev); + + spi_controller_put(host); } #ifdef CONFIG_PM_SLEEP From ed822a5696455312f7c760f1d2c333ce892e0af0 Mon Sep 17 00:00:00 2001 From: Pei Xiao Date: Wed, 13 May 2026 14:08:35 -0400 Subject: [PATCH 0165/1518] spi: zynq-qspi: Simplify clock handling with devm_clk_get_enabled() [ Upstream commit 1f8fd9490e3184e9a2394df2e682901a1d57ce71 ] Replace devm_clk_get() followed by clk_prepare_enable() with devm_clk_get_enabled() for both "pclk" and "ref_clk". This removes the need for explicit clock enable and disable calls, as the managed API automatically disables the clocks on device removal or probe failure. Remove the now-unnecessary clk_disable_unprepare() calls from the probe error paths and the remove callback. Simplify error handling by jumping directly to the remove_ctlr label. Signed-off-by: Pei Xiao Acked-by: Michal Simek Link: https://patch.msgid.link/24043625f89376da36feca2408f990a85be7ab36.1775555500.git.xiaopei01@kylinos.cn Signed-off-by: Mark Brown Stable-dep-of: c9c012706c9f ("spi: zynq-qspi: fix controller deregistration") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-zynq-qspi.c | 42 ++++++------------------------------- 1 file changed, 6 insertions(+), 36 deletions(-) diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index 5232483c4a3a8..af252500195ce 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -381,21 +381,10 @@ static int zynq_qspi_setup_op(struct spi_device *spi) { struct spi_controller *ctlr = spi->controller; struct zynq_qspi *qspi = spi_controller_get_devdata(ctlr); - int ret; if (ctlr->busy) return -EBUSY; - ret = clk_enable(qspi->refclk); - if (ret) - return ret; - - ret = clk_enable(qspi->pclk); - if (ret) { - clk_disable(qspi->refclk); - return ret; - } - zynq_qspi_write(qspi, ZYNQ_QSPI_ENABLE_OFFSET, ZYNQ_QSPI_ENABLE_ENABLE_MASK); @@ -661,7 +650,7 @@ static int zynq_qspi_probe(struct platform_device *pdev) goto remove_ctlr; } - xqspi->pclk = devm_clk_get(&pdev->dev, "pclk"); + xqspi->pclk = devm_clk_get_enabled(&pdev->dev, "pclk"); if (IS_ERR(xqspi->pclk)) { dev_err(&pdev->dev, "pclk clock not found.\n"); ret = PTR_ERR(xqspi->pclk); @@ -670,36 +659,24 @@ static int zynq_qspi_probe(struct platform_device *pdev) init_completion(&xqspi->data_completion); - xqspi->refclk = devm_clk_get(&pdev->dev, "ref_clk"); + xqspi->refclk = devm_clk_get_enabled(&pdev->dev, "ref_clk"); if (IS_ERR(xqspi->refclk)) { dev_err(&pdev->dev, "ref_clk clock not found.\n"); ret = PTR_ERR(xqspi->refclk); goto remove_ctlr; } - ret = clk_prepare_enable(xqspi->pclk); - if (ret) { - dev_err(&pdev->dev, "Unable to enable APB clock.\n"); - goto remove_ctlr; - } - - ret = clk_prepare_enable(xqspi->refclk); - if (ret) { - dev_err(&pdev->dev, "Unable to enable device clock.\n"); - goto clk_dis_pclk; - } - xqspi->irq = platform_get_irq(pdev, 0); if (xqspi->irq < 0) { ret = xqspi->irq; - goto clk_dis_all; + goto remove_ctlr; } ret = devm_request_irq(&pdev->dev, xqspi->irq, zynq_qspi_irq, 0, pdev->name, xqspi); if (ret != 0) { ret = -ENXIO; dev_err(&pdev->dev, "request_irq failed\n"); - goto clk_dis_all; + goto remove_ctlr; } ret = of_property_read_u32(np, "num-cs", @@ -709,7 +686,7 @@ static int zynq_qspi_probe(struct platform_device *pdev) } else if (num_cs > ZYNQ_QSPI_MAX_NUM_CS) { ret = -EINVAL; dev_err(&pdev->dev, "only 2 chip selects are available\n"); - goto clk_dis_all; + goto remove_ctlr; } else { ctlr->num_chipselect = num_cs; } @@ -728,15 +705,11 @@ static int zynq_qspi_probe(struct platform_device *pdev) ret = devm_spi_register_controller(&pdev->dev, ctlr); if (ret) { dev_err(&pdev->dev, "devm_spi_register_controller failed\n"); - goto clk_dis_all; + goto remove_ctlr; } return ret; -clk_dis_all: - clk_disable_unprepare(xqspi->refclk); -clk_dis_pclk: - clk_disable_unprepare(xqspi->pclk); remove_ctlr: spi_controller_put(ctlr); @@ -758,9 +731,6 @@ static void zynq_qspi_remove(struct platform_device *pdev) struct zynq_qspi *xqspi = platform_get_drvdata(pdev); zynq_qspi_write(xqspi, ZYNQ_QSPI_ENABLE_OFFSET, 0); - - clk_disable_unprepare(xqspi->refclk); - clk_disable_unprepare(xqspi->pclk); } static const struct of_device_id zynq_qspi_of_match[] = { From c0a8dca8d556b55303d6cc2716f60cdebe503567 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 13 May 2026 14:08:36 -0400 Subject: [PATCH 0166/1518] spi: zynq-qspi: fix controller deregistration [ Upstream commit c9c012706c9fa8ca6d129a9161caf92ab625a3fd ] Make sure to deregister the controller before disabling it during driver unbind. Note that clocks were also disabled before the recent commit 1f8fd9490e31 ("spi: zynq-qspi: Simplify clock handling with devm_clk_get_enabled()"). Fixes: 67dca5e580f1 ("spi: spi-mem: Add support for Zynq QSPI controller") Cc: stable@vger.kernel.org # 5.2: 8eb2fd00f65a Cc: stable@vger.kernel.org # 5.2 Cc: Naga Sureshkumar Relli Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-27-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-zynq-qspi.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index af252500195ce..406fd9d5337ee 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -643,7 +643,7 @@ static int zynq_qspi_probe(struct platform_device *pdev) xqspi = spi_controller_get_devdata(ctlr); xqspi->dev = dev; - platform_set_drvdata(pdev, xqspi); + platform_set_drvdata(pdev, ctlr); xqspi->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(xqspi->regs)) { ret = PTR_ERR(xqspi->regs); @@ -702,9 +702,9 @@ static int zynq_qspi_probe(struct platform_device *pdev) /* QSPI controller initializations */ zynq_qspi_init_hw(xqspi, ctlr->num_chipselect); - ret = devm_spi_register_controller(&pdev->dev, ctlr); + ret = spi_register_controller(ctlr); if (ret) { - dev_err(&pdev->dev, "devm_spi_register_controller failed\n"); + dev_err(&pdev->dev, "failed to register controller\n"); goto remove_ctlr; } @@ -728,9 +728,16 @@ static int zynq_qspi_probe(struct platform_device *pdev) */ static void zynq_qspi_remove(struct platform_device *pdev) { - struct zynq_qspi *xqspi = platform_get_drvdata(pdev); + struct spi_controller *ctlr = platform_get_drvdata(pdev); + struct zynq_qspi *xqspi = spi_controller_get_devdata(ctlr); + + spi_controller_get(ctlr); + + spi_unregister_controller(ctlr); zynq_qspi_write(xqspi, ZYNQ_QSPI_ENABLE_OFFSET, 0); + + spi_controller_put(ctlr); } static const struct of_device_id zynq_qspi_of_match[] = { From dc34f8d8240f25dd137dc2758ebbcc75e3779142 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Wed, 13 May 2026 13:10:03 -0400 Subject: [PATCH 0167/1518] Bluetooth: hci_conn: fix potential UAF in create_big_sync [ Upstream commit 0beddb0c380bed5f5b8e61ddbe14635bb73d0b41 ] Add hci_conn_valid() check in create_big_sync() to detect stale connections before proceeding with BIG creation. Handle the resulting -ECANCELED in create_big_complete() and re-validate the connection under hci_dev_lock() before dereferencing, matching the pattern used by create_le_conn_complete() and create_pa_complete(). Keep the hci_conn object alive across the async boundary by taking a reference via hci_conn_get() when queueing create_big_sync(), and dropping it in the completion callback. The refcount and the lock are complementary: the refcount keeps the object allocated, while hci_dev_lock() serializes hci_conn_hash_del()'s list_del_rcu() on hdev->conn_hash, as required by hci_conn_del(). hci_conn_put() is called outside hci_dev_unlock() so the final put (which resolves to kfree() via bt_link_release) does not run under hdev->lock, though the release path would be safe either way. Without this, create_big_complete() would unconditionally dereference the conn pointer on error, causing a use-after-free via hci_connect_cfm() and hci_conn_del(). Fixes: eca0ae4aea66 ("Bluetooth: Add initial implementation of BIS connections") Cc: stable@vger.kernel.org Co-developed-by: Luiz Augusto von Dentz Signed-off-by: Luiz Augusto von Dentz Signed-off-by: David Carlier Signed-off-by: Luiz Augusto von Dentz [ kept stable's `qos->bcast.out.phy == 0x02` context line instead of upstream's renamed `qos->bcast.out.phys == BIT(1)` ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_conn.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 71a24be2a6d67..1b63bc2753a24 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -2113,6 +2113,9 @@ static int create_big_sync(struct hci_dev *hdev, void *data) u32 flags = 0; int err; + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + if (qos->bcast.out.phy == 0x02) flags |= MGMT_ADV_FLAG_SEC_2M; @@ -2188,11 +2191,24 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "conn %p", conn); + if (err == -ECANCELED) + goto done; + + hci_dev_lock(hdev); + + if (!hci_conn_valid(hdev, conn)) + goto unlock; + if (err) { bt_dev_err(hdev, "Unable to create BIG: %d", err); hci_connect_cfm(conn, err); hci_conn_del(conn); } + +unlock: + hci_dev_unlock(hdev); +done: + hci_conn_put(conn); } struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid, @@ -2309,10 +2325,11 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ - err = hci_cmd_sync_queue(hdev, create_big_sync, conn, + err = hci_cmd_sync_queue(hdev, create_big_sync, hci_conn_get(conn), create_big_complete); if (err < 0) { hci_conn_drop(conn); + hci_conn_put(conn); return ERR_PTR(err); } From 30cf8e05d635680eec2eed696b9118cada1c2aa9 Mon Sep 17 00:00:00 2001 From: zhidao su Date: Wed, 13 May 2026 12:33:21 -0400 Subject: [PATCH 0168/1518] sched/ext: Implement cgroup_set_idle() callback [ Upstream commit 347ed2d566dabb06c7970fff01129c4f59995ed6 ] Implement the missing cgroup_set_idle() callback that was marked as a TODO. This allows BPF schedulers to be notified when a cgroup's idle state changes, enabling them to adjust their scheduling behavior accordingly. The implementation follows the same pattern as other cgroup callbacks like cgroup_set_weight() and cgroup_set_bandwidth(). It checks if the BPF scheduler has implemented the callback and invokes it with the appropriate parameters. Fixes a spelling error in the cgroup_set_bandwidth() documentation. tj: s/scx_cgroup_rwsem/scx_cgroup_ops_rwsem/ to fix build breakage. Signed-off-by: zhidao su Signed-off-by: Tejun Heo Stable-dep-of: 80afd4c84bc8 ("sched_ext: Read scx_root under scx_cgroup_ops_rwsem in cgroup setters") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/ext.h | 1 + kernel/sched/ext.c | 16 +++++++++++++++- kernel/sched/ext_internal.h | 13 ++++++++++++- 3 files changed, 28 insertions(+), 2 deletions(-) diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index d82b7a9b0658b..9848aeab27864 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -228,6 +228,7 @@ struct scx_task_group { u64 bw_period_us; u64 bw_quota_us; u64 bw_burst_us; + bool idle; #endif }; diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index ee031ba877d9c..423098966a291 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3118,6 +3118,7 @@ void scx_tg_init(struct task_group *tg) tg->scx.weight = CGROUP_WEIGHT_DFL; tg->scx.bw_period_us = default_bw_period_us(); tg->scx.bw_quota_us = RUNTIME_INF; + tg->scx.idle = false; } int scx_tg_online(struct task_group *tg) @@ -3266,7 +3267,18 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) void scx_group_set_idle(struct task_group *tg, bool idle) { - /* TODO: Implement ops->cgroup_set_idle() */ + struct scx_sched *sch = scx_root; + + percpu_down_read(&scx_cgroup_ops_rwsem); + + if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_idle)) + SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_idle, NULL, + tg_cgrp(tg), idle); + + /* Update the task group's idle state */ + tg->scx.idle = idle; + + percpu_up_read(&scx_cgroup_ops_rwsem); } void scx_group_set_bandwidth(struct task_group *tg, @@ -5126,6 +5138,7 @@ static void sched_ext_ops__cgroup_move(struct task_struct *p, struct cgroup *fro static void sched_ext_ops__cgroup_cancel_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {} static void sched_ext_ops__cgroup_set_weight(struct cgroup *cgrp, u32 weight) {} static void sched_ext_ops__cgroup_set_bandwidth(struct cgroup *cgrp, u64 period_us, u64 quota_us, u64 burst_us) {} +static void sched_ext_ops__cgroup_set_idle(struct cgroup *cgrp, bool idle) {} #endif static void sched_ext_ops__cpu_online(s32 cpu) {} static void sched_ext_ops__cpu_offline(s32 cpu) {} @@ -5164,6 +5177,7 @@ static struct sched_ext_ops __bpf_ops_sched_ext_ops = { .cgroup_cancel_move = sched_ext_ops__cgroup_cancel_move, .cgroup_set_weight = sched_ext_ops__cgroup_set_weight, .cgroup_set_bandwidth = sched_ext_ops__cgroup_set_bandwidth, + .cgroup_set_idle = sched_ext_ops__cgroup_set_idle, #endif .cpu_online = sched_ext_ops__cpu_online, .cpu_offline = sched_ext_ops__cpu_offline, diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 8039a750490f8..5b2dd105fa92a 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -697,12 +697,23 @@ struct sched_ext_ops { * 2_500_000. @cgrp is entitled to 2.5 CPUs. @burst_us can be * interpreted in the same fashion and specifies how much @cgrp can * burst temporarily. The specific control mechanism and thus the - * interpretation of @period_us and burstiness is upto to the BPF + * interpretation of @period_us and burstiness is up to the BPF * scheduler. */ void (*cgroup_set_bandwidth)(struct cgroup *cgrp, u64 period_us, u64 quota_us, u64 burst_us); + /** + * @cgroup_set_idle: A cgroup's idle state is being changed + * @cgrp: cgroup whose idle state is being updated + * @idle: whether the cgroup is entering or exiting idle state + * + * Update @cgrp's idle state to @idle. This callback is invoked when + * a cgroup transitions between idle and non-idle states, allowing the + * BPF scheduler to adjust its behavior accordingly. + */ + void (*cgroup_set_idle)(struct cgroup *cgrp, bool idle); + #endif /* CONFIG_EXT_GROUP_SCHED */ /* From ce9aaa3af445c391735c9d000c4db60dfd5640d4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 May 2026 12:33:22 -0400 Subject: [PATCH 0169/1518] sched_ext: Read scx_root under scx_cgroup_ops_rwsem in cgroup setters [ Upstream commit 80afd4c84bc8f5e80145ce35279f5ce53f6043db ] scx_group_set_{weight,idle,bandwidth}() cache scx_root before acquiring scx_cgroup_ops_rwsem, so the pointer can be stale by the time the op runs. If the loaded scheduler is disabled and freed (via RCU work) and another is enabled between the naked load and the rwsem acquire, the reader sees scx_cgroup_enabled=true (the new scheduler's) but dereferences the freed one - UAF on SCX_HAS_OP(sch, ...) / SCX_CALL_OP(sch, ...). scx_cgroup_enabled is toggled only under scx_cgroup_ops_rwsem write (scx_cgroup_{init,exit}), so reading scx_root inside the rwsem read section correlates @sch with the enabled snapshot. Fixes: a5bd6ba30b33 ("sched_ext: Use cgroup_lock/unlock() to synchronize against cgroup operations") Cc: stable@vger.kernel.org # v6.18+ Reported-by: Chris Mason Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/sched/ext.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 423098966a291..177bbf31116d0 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3251,9 +3251,10 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) void scx_group_set_weight(struct task_group *tg, unsigned long weight) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) && tg->scx.weight != weight) @@ -3267,9 +3268,10 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) void scx_group_set_idle(struct task_group *tg, bool idle) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_idle)) SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_idle, NULL, @@ -3284,9 +3286,10 @@ void scx_group_set_idle(struct task_group *tg, bool idle) void scx_group_set_bandwidth(struct task_group *tg, u64 period_us, u64 quota_us, u64 burst_us) { - struct scx_sched *sch = scx_root; + struct scx_sched *sch; percpu_down_read(&scx_cgroup_ops_rwsem); + sch = scx_root; if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_bandwidth) && (tg->scx.bw_period_us != period_us || From e63942da5e962968404419deec6564a397d19e68 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Wed, 13 May 2026 07:27:42 -0400 Subject: [PATCH 0170/1518] usb: dwc3: Remove of dep->regs [ Upstream commit abdd1eef04f0cb3b1707cd1fa243d574d5e07024 ] Remove dep->regs from struct dwc3_ep and reuse dwc->regs instead. Thus eliminating redundant iomem addresses and making register access more consistent across the driver. Signed-off-by: Prashanth K Acked-by: Thinh Nguyen Link: https://patch.msgid.link/20260114100748.2950103-2-prashanth.k@oss.qualcomm.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: aad35f9c926e ("usb: dwc3: Move GUID programming after PHY initialization") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 10 ++++------ drivers/usb/dwc3/debugfs.c | 12 ++++-------- drivers/usb/dwc3/gadget.c | 12 ++++++------ drivers/usb/dwc3/gadget.h | 2 +- 4 files changed, 15 insertions(+), 21 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 9cfc36d4bc259..a35b3db1f9f3e 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -165,10 +165,10 @@ #define DWC3_DCFG1 0xc740 /* DWC_usb32 only */ #define DWC3_DEP_BASE(n) (0xc800 + ((n) * 0x10)) -#define DWC3_DEPCMDPAR2 0x00 -#define DWC3_DEPCMDPAR1 0x04 -#define DWC3_DEPCMDPAR0 0x08 -#define DWC3_DEPCMD 0x0c +#define DWC3_DEPCMDPAR2(n) (DWC3_DEP_BASE(n) + 0x00) +#define DWC3_DEPCMDPAR1(n) (DWC3_DEP_BASE(n) + 0x04) +#define DWC3_DEPCMDPAR0(n) (DWC3_DEP_BASE(n) + 0x08) +#define DWC3_DEPCMD(n) (DWC3_DEP_BASE(n) + 0x0c) #define DWC3_DEV_IMOD(n) (0xca00 + ((n) * 0x4)) @@ -749,8 +749,6 @@ struct dwc3_ep { struct list_head pending_list; struct list_head started_list; - void __iomem *regs; - struct dwc3_trb *trb_pool; dma_addr_t trb_pool_dma; struct dwc3 *dwc; diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index d18bf5e32cc8c..0b45ff16f575b 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -36,23 +36,19 @@ #define dump_ep_register_set(n) \ { \ .name = "DEPCMDPAR2("__stringify(n)")", \ - .offset = DWC3_DEP_BASE(n) + \ - DWC3_DEPCMDPAR2, \ + .offset = DWC3_DEPCMDPAR2(n), \ }, \ { \ .name = "DEPCMDPAR1("__stringify(n)")", \ - .offset = DWC3_DEP_BASE(n) + \ - DWC3_DEPCMDPAR1, \ + .offset = DWC3_DEPCMDPAR1(n), \ }, \ { \ .name = "DEPCMDPAR0("__stringify(n)")", \ - .offset = DWC3_DEP_BASE(n) + \ - DWC3_DEPCMDPAR0, \ + .offset = DWC3_DEPCMDPAR0(n), \ }, \ { \ .name = "DEPCMD("__stringify(n)")", \ - .offset = DWC3_DEP_BASE(n) + \ - DWC3_DEPCMD, \ + .offset = DWC3_DEPCMD(n), \ } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index db5e5b77b1eac..04f6ab77bd7cd 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -320,6 +320,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, int cmd_status = 0; int ret = -EINVAL; + u8 epnum = dep->number; /* * When operating in USB 2.0 speeds (HS/FS), if GUSB2PHYCFG.ENBLSLPM or @@ -355,9 +356,9 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, * improve performance. */ if (DWC3_DEPCMD_CMD(cmd) != DWC3_DEPCMD_UPDATETRANSFER) { - dwc3_writel(dep->regs, DWC3_DEPCMDPAR0, params->param0); - dwc3_writel(dep->regs, DWC3_DEPCMDPAR1, params->param1); - dwc3_writel(dep->regs, DWC3_DEPCMDPAR2, params->param2); + dwc3_writel(dwc->regs, DWC3_DEPCMDPAR0(epnum), params->param0); + dwc3_writel(dwc->regs, DWC3_DEPCMDPAR1(epnum), params->param1); + dwc3_writel(dwc->regs, DWC3_DEPCMDPAR2(epnum), params->param2); } /* @@ -381,7 +382,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, else cmd |= DWC3_DEPCMD_CMDACT; - dwc3_writel(dep->regs, DWC3_DEPCMD, cmd); + dwc3_writel(dwc->regs, DWC3_DEPCMD(epnum), cmd); if (!(cmd & DWC3_DEPCMD_CMDACT) || (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_ENDTRANSFER && @@ -391,7 +392,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, } do { - reg = dwc3_readl(dep->regs, DWC3_DEPCMD); + reg = dwc3_readl(dwc->regs, DWC3_DEPCMD(epnum)); if (!(reg & DWC3_DEPCMD_CMDACT)) { cmd_status = DWC3_DEPCMD_STATUS(reg); @@ -3379,7 +3380,6 @@ static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum) dep->dwc = dwc; dep->number = epnum; dep->direction = direction; - dep->regs = dwc->regs + DWC3_DEP_BASE(epnum); dwc->eps[epnum] = dep; dep->combo_num = 0; dep->start_cmd_status = 0; diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index d73e735e40810..c3aa9638b7a53 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -132,7 +132,7 @@ static inline void dwc3_gadget_ep_get_transfer_index(struct dwc3_ep *dep) { u32 res_id; - res_id = dwc3_readl(dep->regs, DWC3_DEPCMD); + res_id = dwc3_readl(dep->dwc->regs, DWC3_DEPCMD(dep->number)); dep->resource_index = DWC3_DEPCMD_GET_RSC_IDX(res_id); } From 476ee6389120e1900290b46081b3a12b54e05672 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Wed, 13 May 2026 07:27:43 -0400 Subject: [PATCH 0171/1518] usb: dwc3: Add dwc pointer to dwc3_readl/writel [ Upstream commit 9accc68b1cf0a2b220f51d53641128bb32598070 ] Use dwc pointer in dwc3_readl() dwc3_writel() instead of passing the dwc->regs. This would help us access the dwc structure and log the base address in traces. There's no functional changes in this patch, just refactoring existing APIs. Signed-off-by: Prashanth K Acked-by: Thinh Nguyen Link: https://patch.msgid.link/20260114100748.2950103-3-prashanth.k@oss.qualcomm.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: aad35f9c926e ("usb: dwc3: Move GUID programming after PHY initialization") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 194 ++++++++++++++++++------------------- drivers/usb/dwc3/debugfs.c | 32 +++--- drivers/usb/dwc3/drd.c | 76 +++++++-------- drivers/usb/dwc3/ep0.c | 20 ++-- drivers/usb/dwc3/gadget.c | 160 +++++++++++++++--------------- drivers/usb/dwc3/gadget.h | 4 +- drivers/usb/dwc3/io.h | 7 +- drivers/usb/dwc3/ulpi.c | 10 +- 8 files changed, 253 insertions(+), 250 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index c6b7df5682b4e..c5bec0bd9cb10 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -114,23 +114,23 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) int i; for (i = 0; i < dwc->num_usb3_ports; i++) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(i)); + reg = dwc3_readl(dwc, DWC3_GUSB3PIPECTL(i)); if (enable && !dwc->dis_u3_susphy_quirk) reg |= DWC3_GUSB3PIPECTL_SUSPHY; else reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(i), reg); + dwc3_writel(dwc, DWC3_GUSB3PIPECTL(i), reg); } for (i = 0; i < dwc->num_usb2_ports; i++) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(i)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(i)); if (enable && !dwc->dis_u2_susphy_quirk) reg |= DWC3_GUSB2PHYCFG_SUSPHY; else reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(i), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(i), reg); } } @@ -139,7 +139,7 @@ void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy) unsigned int hw_mode; u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); /* * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE and @@ -154,7 +154,7 @@ void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy) reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG)); reg |= DWC3_GCTL_PRTCAPDIR(mode); - dwc3_writel(dwc->regs, DWC3_GCTL, reg); + dwc3_writel(dwc, DWC3_GCTL, reg); dwc->current_dr_role = mode; trace_dwc3_set_prtcap(mode); @@ -214,9 +214,9 @@ static void __dwc3_set_mode(struct work_struct *work) if (dwc->current_dr_role && ((DWC3_IP_IS(DWC3) || DWC3_VER_IS_PRIOR(DWC31, 190A)) && desired_dr_role != DWC3_GCTL_PRTCAP_OTG)) { - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); reg |= DWC3_GCTL_CORESOFTRESET; - dwc3_writel(dwc->regs, DWC3_GCTL, reg); + dwc3_writel(dwc, DWC3_GCTL, reg); /* * Wait for internal clocks to synchronized. DWC_usb31 and @@ -226,9 +226,9 @@ static void __dwc3_set_mode(struct work_struct *work) */ msleep(100); - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); reg &= ~DWC3_GCTL_CORESOFTRESET; - dwc3_writel(dwc->regs, DWC3_GCTL, reg); + dwc3_writel(dwc, DWC3_GCTL, reg); } spin_lock_irqsave(&dwc->lock, flags); @@ -252,9 +252,9 @@ static void __dwc3_set_mode(struct work_struct *work) phy_set_mode(dwc->usb3_generic_phy[i], PHY_MODE_USB_HOST); if (dwc->dis_split_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL3); + reg = dwc3_readl(dwc, DWC3_GUCTL3); reg |= DWC3_GUCTL3_SPLITDISABLE; - dwc3_writel(dwc->regs, DWC3_GUCTL3, reg); + dwc3_writel(dwc, DWC3_GUCTL3, reg); } } break; @@ -305,11 +305,11 @@ u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type) struct dwc3 *dwc = dep->dwc; u32 reg; - dwc3_writel(dwc->regs, DWC3_GDBGFIFOSPACE, - DWC3_GDBGFIFOSPACE_NUM(dep->number) | - DWC3_GDBGFIFOSPACE_TYPE(type)); + dwc3_writel(dwc, DWC3_GDBGFIFOSPACE, + DWC3_GDBGFIFOSPACE_NUM(dep->number) | + DWC3_GDBGFIFOSPACE_TYPE(type)); - reg = dwc3_readl(dwc->regs, DWC3_GDBGFIFOSPACE); + reg = dwc3_readl(dwc, DWC3_GDBGFIFOSPACE); return DWC3_GDBGFIFOSPACE_SPACE_AVAILABLE(reg); } @@ -331,7 +331,7 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST) return 0; - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg |= DWC3_DCTL_CSFTRST; reg &= ~DWC3_DCTL_RUN_STOP; dwc3_gadget_dctl_write_safe(dwc, reg); @@ -346,7 +346,7 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) retries = 10; do { - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (!(reg & DWC3_DCTL_CSFTRST)) goto done; @@ -386,12 +386,12 @@ static void dwc3_frame_length_adjustment(struct dwc3 *dwc) if (dwc->fladj == 0) return; - reg = dwc3_readl(dwc->regs, DWC3_GFLADJ); + reg = dwc3_readl(dwc, DWC3_GFLADJ); dft = reg & DWC3_GFLADJ_30MHZ_MASK; if (dft != dwc->fladj) { reg &= ~DWC3_GFLADJ_30MHZ_MASK; reg |= DWC3_GFLADJ_30MHZ_SDBND_SEL | dwc->fladj; - dwc3_writel(dwc->regs, DWC3_GFLADJ, reg); + dwc3_writel(dwc, DWC3_GFLADJ, reg); } } @@ -423,10 +423,10 @@ static void dwc3_ref_clk_period(struct dwc3 *dwc) return; } - reg = dwc3_readl(dwc->regs, DWC3_GUCTL); + reg = dwc3_readl(dwc, DWC3_GUCTL); reg &= ~DWC3_GUCTL_REFCLKPER_MASK; reg |= FIELD_PREP(DWC3_GUCTL_REFCLKPER_MASK, period); - dwc3_writel(dwc->regs, DWC3_GUCTL, reg); + dwc3_writel(dwc, DWC3_GUCTL, reg); if (DWC3_VER_IS_PRIOR(DWC3, 250A)) return; @@ -454,7 +454,7 @@ static void dwc3_ref_clk_period(struct dwc3 *dwc) */ decr = 480000000 / rate; - reg = dwc3_readl(dwc->regs, DWC3_GFLADJ); + reg = dwc3_readl(dwc, DWC3_GFLADJ); reg &= ~DWC3_GFLADJ_REFCLK_FLADJ_MASK & ~DWC3_GFLADJ_240MHZDECR & ~DWC3_GFLADJ_240MHZDECR_PLS1; @@ -465,7 +465,7 @@ static void dwc3_ref_clk_period(struct dwc3 *dwc) if (dwc->gfladj_refclk_lpm_sel) reg |= DWC3_GFLADJ_REFCLK_LPM_SEL; - dwc3_writel(dwc->regs, DWC3_GFLADJ, reg); + dwc3_writel(dwc, DWC3_GFLADJ, reg); } /** @@ -568,16 +568,16 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc) evt = dwc->ev_buf; evt->lpos = 0; - dwc3_writel(dwc->regs, DWC3_GEVNTADRLO(0), - lower_32_bits(evt->dma)); - dwc3_writel(dwc->regs, DWC3_GEVNTADRHI(0), - upper_32_bits(evt->dma)); - dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0), - DWC3_GEVNTSIZ_SIZE(evt->length)); + dwc3_writel(dwc, DWC3_GEVNTADRLO(0), + lower_32_bits(evt->dma)); + dwc3_writel(dwc, DWC3_GEVNTADRHI(0), + upper_32_bits(evt->dma)); + dwc3_writel(dwc, DWC3_GEVNTSIZ(0), + DWC3_GEVNTSIZ_SIZE(evt->length)); /* Clear any stale event */ - reg = dwc3_readl(dwc->regs, DWC3_GEVNTCOUNT(0)); - dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), reg); + reg = dwc3_readl(dwc, DWC3_GEVNTCOUNT(0)); + dwc3_writel(dwc, DWC3_GEVNTCOUNT(0), reg); return 0; } @@ -592,7 +592,7 @@ void dwc3_event_buffers_cleanup(struct dwc3 *dwc) * Exynos platforms may not be able to access event buffer if the * controller failed to halt on dwc3_core_exit(). */ - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); if (!(reg & DWC3_DSTS_DEVCTRLHLT)) return; @@ -600,14 +600,14 @@ void dwc3_event_buffers_cleanup(struct dwc3 *dwc) evt->lpos = 0; - dwc3_writel(dwc->regs, DWC3_GEVNTADRLO(0), 0); - dwc3_writel(dwc->regs, DWC3_GEVNTADRHI(0), 0); - dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0), DWC3_GEVNTSIZ_INTMASK + dwc3_writel(dwc, DWC3_GEVNTADRLO(0), 0); + dwc3_writel(dwc, DWC3_GEVNTADRHI(0), 0); + dwc3_writel(dwc, DWC3_GEVNTSIZ(0), DWC3_GEVNTSIZ_INTMASK | DWC3_GEVNTSIZ_SIZE(0)); /* Clear any stale event */ - reg = dwc3_readl(dwc->regs, DWC3_GEVNTCOUNT(0)); - dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), reg); + reg = dwc3_readl(dwc, DWC3_GEVNTCOUNT(0)); + dwc3_writel(dwc, DWC3_GEVNTCOUNT(0), reg); } static void dwc3_core_num_eps(struct dwc3 *dwc) @@ -621,18 +621,18 @@ static void dwc3_cache_hwparams(struct dwc3 *dwc) { struct dwc3_hwparams *parms = &dwc->hwparams; - parms->hwparams0 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS0); - parms->hwparams1 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS1); - parms->hwparams2 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS2); - parms->hwparams3 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS3); - parms->hwparams4 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS4); - parms->hwparams5 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS5); - parms->hwparams6 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS6); - parms->hwparams7 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS7); - parms->hwparams8 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS8); + parms->hwparams0 = dwc3_readl(dwc, DWC3_GHWPARAMS0); + parms->hwparams1 = dwc3_readl(dwc, DWC3_GHWPARAMS1); + parms->hwparams2 = dwc3_readl(dwc, DWC3_GHWPARAMS2); + parms->hwparams3 = dwc3_readl(dwc, DWC3_GHWPARAMS3); + parms->hwparams4 = dwc3_readl(dwc, DWC3_GHWPARAMS4); + parms->hwparams5 = dwc3_readl(dwc, DWC3_GHWPARAMS5); + parms->hwparams6 = dwc3_readl(dwc, DWC3_GHWPARAMS6); + parms->hwparams7 = dwc3_readl(dwc, DWC3_GHWPARAMS7); + parms->hwparams8 = dwc3_readl(dwc, DWC3_GHWPARAMS8); if (DWC3_IP_IS(DWC32)) - parms->hwparams9 = dwc3_readl(dwc->regs, DWC3_GHWPARAMS9); + parms->hwparams9 = dwc3_readl(dwc, DWC3_GHWPARAMS9); } static void dwc3_config_soc_bus(struct dwc3 *dwc) @@ -640,10 +640,10 @@ static void dwc3_config_soc_bus(struct dwc3 *dwc) if (dwc->gsbuscfg0_reqinfo != DWC3_GSBUSCFG0_REQINFO_UNSPECIFIED) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_GSBUSCFG0); + reg = dwc3_readl(dwc, DWC3_GSBUSCFG0); reg &= ~DWC3_GSBUSCFG0_REQINFO(~0); reg |= DWC3_GSBUSCFG0_REQINFO(dwc->gsbuscfg0_reqinfo); - dwc3_writel(dwc->regs, DWC3_GSBUSCFG0, reg); + dwc3_writel(dwc, DWC3_GSBUSCFG0, reg); } } @@ -667,7 +667,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(index)); + reg = dwc3_readl(dwc, DWC3_GUSB3PIPECTL(index)); /* * Make sure UX_EXIT_PX is cleared as that causes issues with some @@ -705,7 +705,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index) if (dwc->dis_del_phy_power_chg_quirk) reg &= ~DWC3_GUSB3PIPECTL_DEPOCHANGE; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(index), reg); + dwc3_writel(dwc, DWC3_GUSB3PIPECTL(index), reg); return 0; } @@ -714,7 +714,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(index)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(index)); /* Select the HS PHY interface */ switch (DWC3_GHWPARAMS3_HSPHY_IFC(dwc->hwparams.hwparams3)) { @@ -726,7 +726,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index) } else if (dwc->hsphy_interface && !strncmp(dwc->hsphy_interface, "ulpi", 4)) { reg |= DWC3_GUSB2PHYCFG_ULPI_UTMI; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(index), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(index), reg); } else { /* Relying on default value. */ if (!(reg & DWC3_GUSB2PHYCFG_ULPI_UTMI)) @@ -776,7 +776,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index) if (dwc->ulpi_ext_vbus_drv) reg |= DWC3_GUSB2PHYCFG_ULPIEXTVBUSDRV; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(index), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(index), reg); return 0; } @@ -989,7 +989,7 @@ static bool dwc3_core_is_valid(struct dwc3 *dwc) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_GSNPSID); + reg = dwc3_readl(dwc, DWC3_GSNPSID); dwc->ip = DWC3_GSNPS_ID(reg); if (dwc->ip == DWC4_IP) dwc->ip = DWC32_IP; @@ -998,8 +998,8 @@ static bool dwc3_core_is_valid(struct dwc3 *dwc) if (DWC3_IP_IS(DWC3)) { dwc->revision = reg; } else if (DWC3_IP_IS(DWC31) || DWC3_IP_IS(DWC32)) { - dwc->revision = dwc3_readl(dwc->regs, DWC3_VER_NUMBER); - dwc->version_type = dwc3_readl(dwc->regs, DWC3_VER_TYPE); + dwc->revision = dwc3_readl(dwc, DWC3_VER_NUMBER); + dwc->version_type = dwc3_readl(dwc, DWC3_VER_TYPE); } else { return false; } @@ -1013,7 +1013,7 @@ static void dwc3_core_setup_global_control(struct dwc3 *dwc) unsigned int hw_mode; u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); reg &= ~DWC3_GCTL_SCALEDOWN_MASK; hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); power_opt = DWC3_GHWPARAMS1_EN_PWROPT(dwc->hwparams.hwparams1); @@ -1091,7 +1091,7 @@ static void dwc3_core_setup_global_control(struct dwc3 *dwc) if (DWC3_VER_IS_PRIOR(DWC3, 190A)) reg |= DWC3_GCTL_U2RSTECN; - dwc3_writel(dwc->regs, DWC3_GCTL, reg); + dwc3_writel(dwc, DWC3_GCTL, reg); } static int dwc3_core_get_phy(struct dwc3 *dwc); @@ -1111,7 +1111,7 @@ static void dwc3_set_incr_burst_type(struct dwc3 *dwc) int ret; int i; - cfg = dwc3_readl(dwc->regs, DWC3_GSBUSCFG0); + cfg = dwc3_readl(dwc, DWC3_GSBUSCFG0); /* * Handle property "snps,incr-burst-type-adjustment". @@ -1186,7 +1186,7 @@ static void dwc3_set_incr_burst_type(struct dwc3 *dwc) break; } - dwc3_writel(dwc->regs, DWC3_GSBUSCFG0, cfg); + dwc3_writel(dwc, DWC3_GSBUSCFG0, cfg); } static void dwc3_set_power_down_clk_scale(struct dwc3 *dwc) @@ -1211,12 +1211,12 @@ static void dwc3_set_power_down_clk_scale(struct dwc3 *dwc) * (3x or more) to be within the requirement. */ scale = DIV_ROUND_UP(clk_get_rate(dwc->susp_clk), 16000); - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); if ((reg & DWC3_GCTL_PWRDNSCALE_MASK) < DWC3_GCTL_PWRDNSCALE(scale) || (reg & DWC3_GCTL_PWRDNSCALE_MASK) > DWC3_GCTL_PWRDNSCALE(scale*3)) { reg &= ~(DWC3_GCTL_PWRDNSCALE_MASK); reg |= DWC3_GCTL_PWRDNSCALE(scale); - dwc3_writel(dwc->regs, DWC3_GCTL, reg); + dwc3_writel(dwc, DWC3_GCTL, reg); } } @@ -1239,7 +1239,7 @@ static void dwc3_config_threshold(struct dwc3 *dwc) tx_maxburst = dwc->tx_max_burst_prd; if (rx_thr_num && rx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GRXTHRCFG); reg |= DWC31_RXTHRNUMPKTSEL_PRD; reg &= ~DWC31_RXTHRNUMPKT_PRD(~0); @@ -1248,11 +1248,11 @@ static void dwc3_config_threshold(struct dwc3 *dwc) reg &= ~DWC31_MAXRXBURSTSIZE_PRD(~0); reg |= DWC31_MAXRXBURSTSIZE_PRD(rx_maxburst); - dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GRXTHRCFG, reg); } if (tx_thr_num && tx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GTXTHRCFG); reg |= DWC31_TXTHRNUMPKTSEL_PRD; reg &= ~DWC31_TXTHRNUMPKT_PRD(~0); @@ -1261,7 +1261,7 @@ static void dwc3_config_threshold(struct dwc3 *dwc) reg &= ~DWC31_MAXTXBURSTSIZE_PRD(~0); reg |= DWC31_MAXTXBURSTSIZE_PRD(tx_maxburst); - dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GTXTHRCFG, reg); } } @@ -1272,7 +1272,7 @@ static void dwc3_config_threshold(struct dwc3 *dwc) if (DWC3_IP_IS(DWC3)) { if (rx_thr_num && rx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GRXTHRCFG); reg |= DWC3_GRXTHRCFG_PKTCNTSEL; reg &= ~DWC3_GRXTHRCFG_RXPKTCNT(~0); @@ -1281,11 +1281,11 @@ static void dwc3_config_threshold(struct dwc3 *dwc) reg &= ~DWC3_GRXTHRCFG_MAXRXBURSTSIZE(~0); reg |= DWC3_GRXTHRCFG_MAXRXBURSTSIZE(rx_maxburst); - dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GRXTHRCFG, reg); } if (tx_thr_num && tx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GTXTHRCFG); reg |= DWC3_GTXTHRCFG_PKTCNTSEL; reg &= ~DWC3_GTXTHRCFG_TXPKTCNT(~0); @@ -1294,11 +1294,11 @@ static void dwc3_config_threshold(struct dwc3 *dwc) reg &= ~DWC3_GTXTHRCFG_MAXTXBURSTSIZE(~0); reg |= DWC3_GTXTHRCFG_MAXTXBURSTSIZE(tx_maxburst); - dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GTXTHRCFG, reg); } } else { if (rx_thr_num && rx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GRXTHRCFG); reg |= DWC31_GRXTHRCFG_PKTCNTSEL; reg &= ~DWC31_GRXTHRCFG_RXPKTCNT(~0); @@ -1307,11 +1307,11 @@ static void dwc3_config_threshold(struct dwc3 *dwc) reg &= ~DWC31_GRXTHRCFG_MAXRXBURSTSIZE(~0); reg |= DWC31_GRXTHRCFG_MAXRXBURSTSIZE(rx_maxburst); - dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GRXTHRCFG, reg); } if (tx_thr_num && tx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GTXTHRCFG); reg |= DWC31_GTXTHRCFG_PKTCNTSEL; reg &= ~DWC31_GTXTHRCFG_TXPKTCNT(~0); @@ -1320,7 +1320,7 @@ static void dwc3_config_threshold(struct dwc3 *dwc) reg &= ~DWC31_GTXTHRCFG_MAXTXBURSTSIZE(~0); reg |= DWC31_GTXTHRCFG_MAXTXBURSTSIZE(tx_maxburst); - dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GTXTHRCFG, reg); } } } @@ -1343,7 +1343,7 @@ static int dwc3_core_init(struct dwc3 *dwc) * Write Linux Version Code to our GUID register so it's easy to figure * out which kernel version a bug was found. */ - dwc3_writel(dwc->regs, DWC3_GUID, LINUX_VERSION_CODE); + dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); ret = dwc3_phy_setup(dwc); if (ret) @@ -1408,9 +1408,9 @@ static int dwc3_core_init(struct dwc3 *dwc) * DWC_usb31 controller. */ if (DWC3_VER_IS_WITHIN(DWC3, 310A, ANY)) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL2); + reg = dwc3_readl(dwc, DWC3_GUCTL2); reg |= DWC3_GUCTL2_RST_ACTBITLATER; - dwc3_writel(dwc->regs, DWC3_GUCTL2, reg); + dwc3_writel(dwc, DWC3_GUCTL2, reg); } /* @@ -1423,9 +1423,9 @@ static int dwc3_core_init(struct dwc3 *dwc) * setting GUCTL2[19] by default; instead, use GUCTL2[19] = 0. */ if (DWC3_VER_IS(DWC3, 320A)) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL2); + reg = dwc3_readl(dwc, DWC3_GUCTL2); reg &= ~DWC3_GUCTL2_LC_TIMER; - dwc3_writel(dwc->regs, DWC3_GUCTL2, reg); + dwc3_writel(dwc, DWC3_GUCTL2, reg); } /* @@ -1438,13 +1438,13 @@ static int dwc3_core_init(struct dwc3 *dwc) * legacy ULPI PHYs. */ if (dwc->resume_hs_terminations) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL1); + reg = dwc3_readl(dwc, DWC3_GUCTL1); reg |= DWC3_GUCTL1_RESUME_OPMODE_HS_HOST; - dwc3_writel(dwc->regs, DWC3_GUCTL1, reg); + dwc3_writel(dwc, DWC3_GUCTL1, reg); } if (!DWC3_VER_IS_PRIOR(DWC3, 250A)) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL1); + reg = dwc3_readl(dwc, DWC3_GUCTL1); /* * Enable hardware control of sending remote wakeup @@ -1479,7 +1479,7 @@ static int dwc3_core_init(struct dwc3 *dwc) reg &= ~DWC3_GUCTL1_DEV_FORCE_20_CLK_FOR_30_CLK; } - dwc3_writel(dwc->regs, DWC3_GUCTL1, reg); + dwc3_writel(dwc, DWC3_GUCTL1, reg); } dwc3_config_threshold(dwc); @@ -1494,9 +1494,9 @@ static int dwc3_core_init(struct dwc3 *dwc) int i; for (i = 0; i < dwc->num_usb3_ports; i++) { - reg = dwc3_readl(dwc->regs, DWC3_LLUCTL(i)); + reg = dwc3_readl(dwc, DWC3_LLUCTL(i)); reg |= DWC3_LLUCTL_FORCE_GEN1; - dwc3_writel(dwc->regs, DWC3_LLUCTL(i), reg); + dwc3_writel(dwc, DWC3_LLUCTL(i), reg); } } @@ -1515,9 +1515,9 @@ static int dwc3_core_init(struct dwc3 *dwc) * function is available only from version 1.70a. */ if (DWC3_VER_IS_WITHIN(DWC31, 170A, 180A)) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL3); + reg = dwc3_readl(dwc, DWC3_GUCTL3); reg |= DWC3_GUCTL3_USB20_RETRY_DISABLE; - dwc3_writel(dwc->regs, DWC3_GUCTL3, reg); + dwc3_writel(dwc, DWC3_GUCTL3, reg); } return 0; @@ -2447,9 +2447,9 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) int ret; if (!pm_runtime_suspended(dwc->dev) && !PMSG_IS_AUTO(msg)) { - dwc->susphy_state = (dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)) & + dwc->susphy_state = (dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)) & DWC3_GUSB2PHYCFG_SUSPHY) || - (dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)) & + (dwc3_readl(dwc, DWC3_GUSB3PIPECTL(0)) & DWC3_GUSB3PIPECTL_SUSPHY); /* * TI AM62 platform requires SUSPHY to be @@ -2479,10 +2479,10 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) if (dwc->dis_u2_susphy_quirk || dwc->dis_enblslpm_quirk) { for (i = 0; i < dwc->num_usb2_ports; i++) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(i)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(i)); reg |= DWC3_GUSB2PHYCFG_ENBLSLPM | DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(i), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(i), reg); } /* Give some time for USB2 PHY to suspend */ @@ -2542,14 +2542,14 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) } /* Restore GUSB2PHYCFG bits that were modified in suspend */ for (i = 0; i < dwc->num_usb2_ports; i++) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(i)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(i)); if (dwc->dis_u2_susphy_quirk) reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; if (dwc->dis_enblslpm_quirk) reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(i), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(i), reg); } for (i = 0; i < dwc->num_usb2_ports; i++) @@ -2732,9 +2732,9 @@ void dwc3_pm_complete(struct dwc3 *dwc) if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST && dwc->dis_split_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUCTL3); + reg = dwc3_readl(dwc, DWC3_GUCTL3); reg |= DWC3_GUCTL3_SPLITDISABLE; - dwc3_writel(dwc->regs, DWC3_GUCTL3, reg); + dwc3_writel(dwc, DWC3_GUCTL3, reg); } } EXPORT_SYMBOL_GPL(dwc3_pm_complete); diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index 0b45ff16f575b..ffb1101f55c7b 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -296,14 +296,14 @@ static void dwc3_host_lsp(struct seq_file *s) reg = DWC3_GDBGLSPMUX_HOSTSELECT(sel); - dwc3_writel(dwc->regs, DWC3_GDBGLSPMUX, reg); - val = dwc3_readl(dwc->regs, DWC3_GDBGLSP); + dwc3_writel(dwc, DWC3_GDBGLSPMUX, reg); + val = dwc3_readl(dwc, DWC3_GDBGLSP); seq_printf(s, "GDBGLSP[%d] = 0x%08x\n", sel, val); if (dbc_enabled && sel < 256) { reg |= DWC3_GDBGLSPMUX_ENDBC; - dwc3_writel(dwc->regs, DWC3_GDBGLSPMUX, reg); - val = dwc3_readl(dwc->regs, DWC3_GDBGLSP); + dwc3_writel(dwc, DWC3_GDBGLSPMUX, reg); + val = dwc3_readl(dwc, DWC3_GDBGLSP); seq_printf(s, "GDBGLSP_DBC[%d] = 0x%08x\n", sel, val); } } @@ -316,8 +316,8 @@ static void dwc3_gadget_lsp(struct seq_file *s) for (i = 0; i < 16; i++) { reg = DWC3_GDBGLSPMUX_DEVSELECT(i); - dwc3_writel(dwc->regs, DWC3_GDBGLSPMUX, reg); - reg = dwc3_readl(dwc->regs, DWC3_GDBGLSP); + dwc3_writel(dwc, DWC3_GDBGLSPMUX, reg); + reg = dwc3_readl(dwc, DWC3_GDBGLSP); seq_printf(s, "GDBGLSP[%d] = 0x%08x\n", i, reg); } } @@ -335,7 +335,7 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) return ret; spin_lock_irqsave(&dwc->lock, flags); - reg = dwc3_readl(dwc->regs, DWC3_GSTS); + reg = dwc3_readl(dwc, DWC3_GSTS); current_mode = DWC3_GSTS_CURMOD(reg); switch (current_mode) { @@ -406,7 +406,7 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) return ret; spin_lock_irqsave(&dwc->lock, flags); - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); spin_unlock_irqrestore(&dwc->lock, flags); mode = DWC3_GCTL_PRTCAP(reg); @@ -478,7 +478,7 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) return ret; spin_lock_irqsave(&dwc->lock, flags); - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= DWC3_DCTL_TSTCTRL_MASK; reg >>= 1; spin_unlock_irqrestore(&dwc->lock, flags); @@ -577,7 +577,7 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) return ret; spin_lock_irqsave(&dwc->lock, flags); - reg = dwc3_readl(dwc->regs, DWC3_GSTS); + reg = dwc3_readl(dwc, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); @@ -585,7 +585,7 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) return 0; } - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); state = DWC3_DSTS_USBLNKST(reg); speed = reg & DWC3_DSTS_CONNECTSPD; @@ -639,14 +639,14 @@ static ssize_t dwc3_link_state_write(struct file *file, return ret; spin_lock_irqsave(&dwc->lock, flags); - reg = dwc3_readl(dwc->regs, DWC3_GSTS); + reg = dwc3_readl(dwc, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); pm_runtime_put_sync(dwc->dev); return -EINVAL; } - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); speed = reg & DWC3_DSTS_CONNECTSPD; if (speed < DWC3_DSTS_SUPERSPEED && @@ -942,10 +942,10 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); - dwc3_writel(dwc->regs, DWC3_GDBGLSPMUX, reg); + dwc3_writel(dwc, DWC3_GDBGLSPMUX, reg); - lower_32_bits = dwc3_readl(dwc->regs, DWC3_GDBGEPINFO0); - upper_32_bits = dwc3_readl(dwc->regs, DWC3_GDBGEPINFO1); + lower_32_bits = dwc3_readl(dwc, DWC3_GDBGEPINFO0); + upper_32_bits = dwc3_readl(dwc, DWC3_GDBGEPINFO1); ep_info = ((u64)upper_32_bits << 32) | lower_32_bits; seq_printf(s, "0x%016llx\n", ep_info); diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index 4c91240eb4299..b229fb1fd9327 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -18,25 +18,25 @@ static void dwc3_otg_disable_events(struct dwc3 *dwc, u32 disable_mask) { - u32 reg = dwc3_readl(dwc->regs, DWC3_OEVTEN); + u32 reg = dwc3_readl(dwc, DWC3_OEVTEN); reg &= ~(disable_mask); - dwc3_writel(dwc->regs, DWC3_OEVTEN, reg); + dwc3_writel(dwc, DWC3_OEVTEN, reg); } static void dwc3_otg_enable_events(struct dwc3 *dwc, u32 enable_mask) { - u32 reg = dwc3_readl(dwc->regs, DWC3_OEVTEN); + u32 reg = dwc3_readl(dwc, DWC3_OEVTEN); reg |= (enable_mask); - dwc3_writel(dwc->regs, DWC3_OEVTEN, reg); + dwc3_writel(dwc, DWC3_OEVTEN, reg); } static void dwc3_otg_clear_events(struct dwc3 *dwc) { - u32 reg = dwc3_readl(dwc->regs, DWC3_OEVT); + u32 reg = dwc3_readl(dwc, DWC3_OEVT); - dwc3_writel(dwc->regs, DWC3_OEVTEN, reg); + dwc3_writel(dwc, DWC3_OEVTEN, reg); } #define DWC3_OTG_ALL_EVENTS (DWC3_OEVTEN_XHCIRUNSTPSETEN | \ @@ -72,18 +72,18 @@ static irqreturn_t dwc3_otg_irq(int irq, void *_dwc) struct dwc3 *dwc = _dwc; irqreturn_t ret = IRQ_NONE; - reg = dwc3_readl(dwc->regs, DWC3_OEVT); + reg = dwc3_readl(dwc, DWC3_OEVT); if (reg) { /* ignore non OTG events, we can't disable them in OEVTEN */ if (!(reg & DWC3_OTG_ALL_EVENTS)) { - dwc3_writel(dwc->regs, DWC3_OEVT, reg); + dwc3_writel(dwc, DWC3_OEVT, reg); return IRQ_NONE; } if (dwc->current_otg_role == DWC3_OTG_ROLE_HOST && !(reg & DWC3_OEVT_DEVICEMODE)) dwc->otg_restart_host = true; - dwc3_writel(dwc->regs, DWC3_OEVT, reg); + dwc3_writel(dwc, DWC3_OEVT, reg); ret = IRQ_WAKE_THREAD; } @@ -100,23 +100,23 @@ static void dwc3_otgregs_init(struct dwc3 *dwc) * the signal outputs sent to the PHY, the OTG FSM logic of the * core and also the resets to the VBUS filters inside the core. */ - reg = dwc3_readl(dwc->regs, DWC3_OCFG); + reg = dwc3_readl(dwc, DWC3_OCFG); reg |= DWC3_OCFG_SFTRSTMASK; - dwc3_writel(dwc->regs, DWC3_OCFG, reg); + dwc3_writel(dwc, DWC3_OCFG, reg); /* Disable hibernation for simplicity */ - reg = dwc3_readl(dwc->regs, DWC3_GCTL); + reg = dwc3_readl(dwc, DWC3_GCTL); reg &= ~DWC3_GCTL_GBLHIBERNATIONEN; - dwc3_writel(dwc->regs, DWC3_GCTL, reg); + dwc3_writel(dwc, DWC3_GCTL, reg); /* * Initialize OTG registers as per * Figure 11-4 OTG Driver Overall Programming Flow */ /* OCFG.SRPCap = 0, OCFG.HNPCap = 0 */ - reg = dwc3_readl(dwc->regs, DWC3_OCFG); + reg = dwc3_readl(dwc, DWC3_OCFG); reg &= ~(DWC3_OCFG_SRPCAP | DWC3_OCFG_HNPCAP); - dwc3_writel(dwc->regs, DWC3_OCFG, reg); + dwc3_writel(dwc, DWC3_OCFG, reg); /* OEVT = FFFF */ dwc3_otg_clear_events(dwc); /* OEVTEN = 0 */ @@ -127,11 +127,11 @@ static void dwc3_otgregs_init(struct dwc3 *dwc) * OCTL.PeriMode = 1, OCTL.DevSetHNPEn = 0, OCTL.HstSetHNPEn = 0, * OCTL.HNPReq = 0 */ - reg = dwc3_readl(dwc->regs, DWC3_OCTL); + reg = dwc3_readl(dwc, DWC3_OCTL); reg |= DWC3_OCTL_PERIMODE; reg &= ~(DWC3_OCTL_DEVSETHNPEN | DWC3_OCTL_HSTSETHNPEN | DWC3_OCTL_HNPREQ); - dwc3_writel(dwc->regs, DWC3_OCTL, reg); + dwc3_writel(dwc, DWC3_OCTL, reg); } static int dwc3_otg_get_irq(struct dwc3 *dwc) @@ -175,9 +175,9 @@ void dwc3_otg_init(struct dwc3 *dwc) /* GCTL.PrtCapDir=2'b11 */ dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true); /* GUSB2PHYCFG0.SusPHY=0 */ - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); /* Initialize OTG registers */ dwc3_otgregs_init(dwc); @@ -203,17 +203,17 @@ void dwc3_otg_host_init(struct dwc3 *dwc) * OCTL.PeriMode=0, OCTL.TermSelDLPulse = 0, * OCTL.DevSetHNPEn = 0, OCTL.HstSetHNPEn = 0 */ - reg = dwc3_readl(dwc->regs, DWC3_OCTL); + reg = dwc3_readl(dwc, DWC3_OCTL); reg &= ~(DWC3_OCTL_PERIMODE | DWC3_OCTL_TERMSELIDPULSE | DWC3_OCTL_DEVSETHNPEN | DWC3_OCTL_HSTSETHNPEN); - dwc3_writel(dwc->regs, DWC3_OCTL, reg); + dwc3_writel(dwc, DWC3_OCTL, reg); /* * OCFG.DisPrtPwrCutoff = 0/1 */ - reg = dwc3_readl(dwc->regs, DWC3_OCFG); + reg = dwc3_readl(dwc, DWC3_OCFG); reg &= ~DWC3_OCFG_DISPWRCUTTOFF; - dwc3_writel(dwc->regs, DWC3_OCFG, reg); + dwc3_writel(dwc, DWC3_OCFG, reg); /* * OCFG.SRPCap = 1, OCFG.HNPCap = GHWPARAMS6.HNP_CAP @@ -229,15 +229,15 @@ void dwc3_otg_host_init(struct dwc3 *dwc) /* GUSB2PHYCFG.ULPIAutoRes = 1/0, GUSB2PHYCFG.SusPHY = 1 */ if (!dwc->dis_u2_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); reg |= DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); } /* Set Port Power to enable VBUS: OCTL.PrtPwrCtl = 1 */ - reg = dwc3_readl(dwc->regs, DWC3_OCTL); + reg = dwc3_readl(dwc, DWC3_OCTL); reg |= DWC3_OCTL_PRTPWRCTL; - dwc3_writel(dwc->regs, DWC3_OCTL, reg); + dwc3_writel(dwc, DWC3_OCTL, reg); } /* should be called after Host controller driver is stopped */ @@ -258,9 +258,9 @@ static void dwc3_otg_host_exit(struct dwc3 *dwc) */ /* OCTL.HstSetHNPEn = 0, OCTL.PrtPwrCtl=0 */ - reg = dwc3_readl(dwc->regs, DWC3_OCTL); + reg = dwc3_readl(dwc, DWC3_OCTL); reg &= ~(DWC3_OCTL_HSTSETHNPEN | DWC3_OCTL_PRTPWRCTL); - dwc3_writel(dwc->regs, DWC3_OCTL, reg); + dwc3_writel(dwc, DWC3_OCTL, reg); } /* should be called before the gadget controller driver is started */ @@ -274,27 +274,27 @@ static void dwc3_otg_device_init(struct dwc3 *dwc) * OCFG.HNPCap = GHWPARAMS6.HNP_CAP, OCFG.SRPCap = 1 * but we keep them 0 for simple dual-role operation. */ - reg = dwc3_readl(dwc->regs, DWC3_OCFG); + reg = dwc3_readl(dwc, DWC3_OCFG); /* OCFG.OTGSftRstMsk = 0/1 */ reg |= DWC3_OCFG_SFTRSTMASK; - dwc3_writel(dwc->regs, DWC3_OCFG, reg); + dwc3_writel(dwc, DWC3_OCFG, reg); /* * OCTL.PeriMode = 1 * OCTL.TermSelDLPulse = 0/1, OCTL.HNPReq = 0 * OCTL.DevSetHNPEn = 0, OCTL.HstSetHNPEn = 0 */ - reg = dwc3_readl(dwc->regs, DWC3_OCTL); + reg = dwc3_readl(dwc, DWC3_OCTL); reg |= DWC3_OCTL_PERIMODE; reg &= ~(DWC3_OCTL_TERMSELIDPULSE | DWC3_OCTL_HNPREQ | DWC3_OCTL_DEVSETHNPEN | DWC3_OCTL_HSTSETHNPEN); - dwc3_writel(dwc->regs, DWC3_OCTL, reg); + dwc3_writel(dwc, DWC3_OCTL, reg); /* OEVTEN.OTGBDevSesVldDetEvntEn = 1 */ dwc3_otg_enable_events(dwc, DWC3_OEVTEN_BDEVSESSVLDDETEN); /* GUSB2PHYCFG.ULPIAutoRes = 0, GUSB2PHYCFG0.SusPHY = 1 */ if (!dwc->dis_u2_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); reg |= DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); } /* GCTL.GblHibernationEn = 0. Already 0. */ } @@ -319,10 +319,10 @@ static void dwc3_otg_device_exit(struct dwc3 *dwc) DWC3_OEVTEN_BDEVBHOSTENDEN); /* OCTL.DevSetHNPEn = 0, OCTL.HNPReq = 0, OCTL.PeriMode=1 */ - reg = dwc3_readl(dwc->regs, DWC3_OCTL); + reg = dwc3_readl(dwc, DWC3_OCTL); reg &= ~(DWC3_OCTL_DEVSETHNPEN | DWC3_OCTL_HNPREQ); reg |= DWC3_OCTL_PERIMODE; - dwc3_writel(dwc->regs, DWC3_OCTL, reg); + dwc3_writel(dwc, DWC3_OCTL, reg); } void dwc3_otg_update(struct dwc3 *dwc, bool ignore_idstatus) @@ -341,7 +341,7 @@ void dwc3_otg_update(struct dwc3 *dwc, bool ignore_idstatus) return; if (!ignore_idstatus) { - reg = dwc3_readl(dwc->regs, DWC3_OSTS); + reg = dwc3_readl(dwc, DWC3_OSTS); id = !!(reg & DWC3_OSTS_CONIDSTS); dwc->desired_otg_role = id ? DWC3_OTG_ROLE_DEVICE : diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index e0bad57086648..a8ff8db610d34 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -361,7 +361,7 @@ static int dwc3_ep0_handle_status(struct dwc3 *dwc, if ((dwc->speed == DWC3_DSTS_SUPERSPEED) || (dwc->speed == DWC3_DSTS_SUPERSPEED_PLUS)) { - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (reg & DWC3_DCTL_INITU1ENA) usb_status |= 1 << USB_DEV_STAT_U1_ENABLED; if (reg & DWC3_DCTL_INITU2ENA) @@ -417,12 +417,12 @@ static int dwc3_ep0_handle_u1(struct dwc3 *dwc, enum usb_device_state state, if (set && dwc->dis_u1_entry_quirk) return -EINVAL; - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (set) reg |= DWC3_DCTL_INITU1ENA; else reg &= ~DWC3_DCTL_INITU1ENA; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); return 0; } @@ -441,12 +441,12 @@ static int dwc3_ep0_handle_u2(struct dwc3 *dwc, enum usb_device_state state, if (set && dwc->dis_u2_entry_quirk) return -EINVAL; - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (set) reg |= DWC3_DCTL_INITU2ENA; else reg &= ~DWC3_DCTL_INITU2ENA; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); return 0; } @@ -612,10 +612,10 @@ static int dwc3_ep0_set_address(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) return -EINVAL; } - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg &= ~(DWC3_DCFG_DEVADDR_MASK); reg |= DWC3_DCFG_DEVADDR(addr); - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); if (addr) usb_gadget_set_state(dwc->gadget, USB_STATE_ADDRESS); @@ -672,12 +672,12 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) * Enable transition to U1/U2 state when * nothing is pending from application. */ - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (!dwc->dis_u1_entry_quirk) reg |= DWC3_DCTL_ACCEPTU1ENA; if (!dwc->dis_u2_entry_quirk) reg |= DWC3_DCTL_ACCEPTU2ENA; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); } break; @@ -717,7 +717,7 @@ static void dwc3_ep0_set_sel_cmpl(struct usb_ep *ep, struct usb_request *req) dwc->u2sel = le16_to_cpu(timing.u2sel); dwc->u2pel = le16_to_cpu(timing.u2pel); - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (reg & DWC3_DCTL_INITU2ENA) param = dwc->u2pel; if (reg & DWC3_DCTL_INITU1ENA) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 04f6ab77bd7cd..89963cd77daaa 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -42,7 +42,7 @@ int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~DWC3_DCTL_TSTCTRL_MASK; switch (mode) { @@ -73,7 +73,7 @@ int dwc3_gadget_get_link_state(struct dwc3 *dwc) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); return DWC3_DSTS_USBLNKST(reg); } @@ -97,7 +97,7 @@ int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state) */ if (!DWC3_VER_IS_PRIOR(DWC3, 194A)) { while (--retries) { - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); if (reg & DWC3_DSTS_DCNRD) udelay(5); else @@ -108,15 +108,15 @@ int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state) return -ETIMEDOUT; } - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~DWC3_DCTL_ULSTCHNGREQ_MASK; /* set no action before sending new link state change */ - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); /* set requested state */ reg |= DWC3_DCTL_ULSTCHNGREQ(state); - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); /* * The following code is racy when called from dwc3_gadget_wakeup, @@ -128,7 +128,7 @@ int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state) /* wait for a change in DSTS */ retries = 10000; while (--retries) { - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); if (DWC3_DSTS_USBLNKST(reg) == state) return 0; @@ -260,11 +260,11 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd, int ret = 0; u32 reg; - dwc3_writel(dwc->regs, DWC3_DGCMDPAR, param); - dwc3_writel(dwc->regs, DWC3_DGCMD, cmd | DWC3_DGCMD_CMDACT); + dwc3_writel(dwc, DWC3_DGCMDPAR, param); + dwc3_writel(dwc, DWC3_DGCMD, cmd | DWC3_DGCMD_CMDACT); do { - reg = dwc3_readl(dwc->regs, DWC3_DGCMD); + reg = dwc3_readl(dwc, DWC3_DGCMD); if (!(reg & DWC3_DGCMD_CMDACT)) { status = DWC3_DGCMD_STATUS(reg); if (status) @@ -334,7 +334,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, */ if (dwc->gadget->speed <= USB_SPEED_HIGH || DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_ENDTRANSFER) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); if (unlikely(reg & DWC3_GUSB2PHYCFG_SUSPHY)) { saved_config |= DWC3_GUSB2PHYCFG_SUSPHY; reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; @@ -346,7 +346,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, } if (saved_config) - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); } /* @@ -356,9 +356,9 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, * improve performance. */ if (DWC3_DEPCMD_CMD(cmd) != DWC3_DEPCMD_UPDATETRANSFER) { - dwc3_writel(dwc->regs, DWC3_DEPCMDPAR0(epnum), params->param0); - dwc3_writel(dwc->regs, DWC3_DEPCMDPAR1(epnum), params->param1); - dwc3_writel(dwc->regs, DWC3_DEPCMDPAR2(epnum), params->param2); + dwc3_writel(dwc, DWC3_DEPCMDPAR0(epnum), params->param0); + dwc3_writel(dwc, DWC3_DEPCMDPAR1(epnum), params->param1); + dwc3_writel(dwc, DWC3_DEPCMDPAR2(epnum), params->param2); } /* @@ -382,7 +382,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, else cmd |= DWC3_DEPCMD_CMDACT; - dwc3_writel(dwc->regs, DWC3_DEPCMD(epnum), cmd); + dwc3_writel(dwc, DWC3_DEPCMD(epnum), cmd); if (!(cmd & DWC3_DEPCMD_CMDACT) || (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_ENDTRANSFER && @@ -392,7 +392,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, } do { - reg = dwc3_readl(dwc->regs, DWC3_DEPCMD(epnum)); + reg = dwc3_readl(dwc, DWC3_DEPCMD(epnum)); if (!(reg & DWC3_DEPCMD_CMDACT)) { cmd_status = DWC3_DEPCMD_STATUS(reg); @@ -448,9 +448,9 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, mdelay(1); if (saved_config) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); reg |= saved_config; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); } return ret; @@ -727,7 +727,7 @@ static int dwc3_gadget_calc_ram_depth(struct dwc3 *dwc) u32 reg; /* Check if TXFIFOs start at non-zero addr */ - reg = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(0)); + reg = dwc3_readl(dwc, DWC3_GTXFIFOSIZ(0)); fifo_0_start = DWC3_GTXFIFOSIZ_TXFSTADDR(reg); ram_depth -= (fifo_0_start >> 16); @@ -755,7 +755,7 @@ void dwc3_gadget_clear_tx_fifos(struct dwc3 *dwc) /* Read ep0IN related TXFIFO size */ dep = dwc->eps[1]; - size = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(0)); + size = dwc3_readl(dwc, DWC3_GTXFIFOSIZ(0)); if (DWC3_IP_IS(DWC3)) fifo_depth = DWC3_GTXFIFOSIZ_TXFDEP(size); else @@ -770,10 +770,10 @@ void dwc3_gadget_clear_tx_fifos(struct dwc3 *dwc) /* Don't change TXFRAMNUM on usb31 version */ size = DWC3_IP_IS(DWC3) ? 0 : - dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(num >> 1)) & + dwc3_readl(dwc, DWC3_GTXFIFOSIZ(num >> 1)) & DWC31_GTXFIFOSIZ_TXFRAMNUM; - dwc3_writel(dwc->regs, DWC3_GTXFIFOSIZ(num >> 1), size); + dwc3_writel(dwc, DWC3_GTXFIFOSIZ(num >> 1), size); dep->flags &= ~DWC3_EP_TXFIFO_RESIZED; } dwc->num_ep_resized = 0; @@ -876,7 +876,7 @@ static int dwc3_gadget_resize_tx_fifos(struct dwc3_ep *dep) fifo_size++; /* Check if TXFIFOs start at non-zero addr */ - tmp = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(0)); + tmp = dwc3_readl(dwc, DWC3_GTXFIFOSIZ(0)); fifo_0_start = DWC3_GTXFIFOSIZ_TXFSTADDR(tmp); fifo_size |= (fifo_0_start + (dwc->last_fifo_depth << 16)); @@ -899,7 +899,7 @@ static int dwc3_gadget_resize_tx_fifos(struct dwc3_ep *dep) return -ENOMEM; } - dwc3_writel(dwc->regs, DWC3_GTXFIFOSIZ(dep->number >> 1), fifo_size); + dwc3_writel(dwc, DWC3_GTXFIFOSIZ(dep->number >> 1), fifo_size); dep->flags |= DWC3_EP_TXFIFO_RESIZED; dwc->num_ep_resized++; @@ -943,9 +943,9 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, unsigned int action) dep->type = usb_endpoint_type(desc); dep->flags |= DWC3_EP_ENABLED; - reg = dwc3_readl(dwc->regs, DWC3_DALEPENA); + reg = dwc3_readl(dwc, DWC3_DALEPENA); reg |= DWC3_DALEPENA_EP(dep->number); - dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); + dwc3_writel(dwc, DWC3_DALEPENA, reg); dep->trb_dequeue = 0; dep->trb_enqueue = 0; @@ -1080,9 +1080,9 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) if (dep->flags & DWC3_EP_STALL) __dwc3_gadget_ep_set_halt(dep, 0, false); - reg = dwc3_readl(dwc->regs, DWC3_DALEPENA); + reg = dwc3_readl(dwc, DWC3_DALEPENA); reg &= ~DWC3_DALEPENA_EP(dep->number); - dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); + dwc3_writel(dwc, DWC3_DALEPENA, reg); dwc3_remove_requests(dwc, dep, -ESHUTDOWN); @@ -1743,7 +1743,7 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) { u32 reg; - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); return DWC3_DSTS_SOFFN(reg); } @@ -2351,13 +2351,13 @@ static void dwc3_gadget_enable_linksts_evts(struct dwc3 *dwc, bool set) if (DWC3_VER_IS_PRIOR(DWC3, 250A)) return; - reg = dwc3_readl(dwc->regs, DWC3_DEVTEN); + reg = dwc3_readl(dwc, DWC3_DEVTEN); if (set) reg |= DWC3_DEVTEN_ULSTCNGEN; else reg &= ~DWC3_DEVTEN_ULSTCNGEN; - dwc3_writel(dwc->regs, DWC3_DEVTEN, reg); + dwc3_writel(dwc, DWC3_DEVTEN, reg); } static int dwc3_gadget_get_frame(struct usb_gadget *g) @@ -2380,7 +2380,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc) * * We can check that via USB Link State bits in DSTS register. */ - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); link_state = DWC3_DSTS_USBLNKST(reg); @@ -2408,9 +2408,9 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc) /* Recent versions do this automatically */ if (DWC3_VER_IS_PRIOR(DWC3, 194A)) { /* write zeroes to Link Change Request */ - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~DWC3_DCTL_ULSTCHNGREQ_MASK; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); } /* @@ -2530,7 +2530,7 @@ static void __dwc3_gadget_set_ssp_rate(struct dwc3 *dwc) if (ssp_rate == USB_SSP_GEN_UNKNOWN) ssp_rate = dwc->max_ssp_rate; - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg &= ~DWC3_DCFG_SPEED_MASK; reg &= ~DWC3_DCFG_NUMLANES(~0); @@ -2543,7 +2543,7 @@ static void __dwc3_gadget_set_ssp_rate(struct dwc3 *dwc) dwc->max_ssp_rate != USB_SSP_GEN_2x1) reg |= DWC3_DCFG_NUMLANES(1); - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); } static void __dwc3_gadget_set_speed(struct dwc3 *dwc) @@ -2561,7 +2561,7 @@ static void __dwc3_gadget_set_speed(struct dwc3 *dwc) return; } - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg &= ~(DWC3_DCFG_SPEED_MASK); /* @@ -2612,7 +2612,7 @@ static void __dwc3_gadget_set_speed(struct dwc3 *dwc) speed < USB_SPEED_SUPER_PLUS) reg &= ~DWC3_DCFG_NUMLANES(~0); - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); } static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) @@ -2637,7 +2637,7 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) * mentioned in the dwc3 programming guide. It has been tested on an * Exynos platforms. */ - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); if (reg & DWC3_GUSB2PHYCFG_SUSPHY) { saved_config |= DWC3_GUSB2PHYCFG_SUSPHY; reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; @@ -2649,9 +2649,9 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) } if (saved_config) - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); if (is_on) { if (DWC3_VER_IS_WITHIN(DWC3, ANY, 187A)) { reg &= ~DWC3_DCTL_TRGTULST_MASK; @@ -2675,14 +2675,14 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) do { usleep_range(1000, 2000); - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); reg &= DWC3_DSTS_DEVCTRLHLT; } while (--timeout && !(!is_on ^ !reg)); if (saved_config) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); reg |= saved_config; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(0), reg); } if (!timeout) @@ -2858,13 +2858,13 @@ static void dwc3_gadget_enable_irq(struct dwc3 *dwc) if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) reg |= DWC3_DEVTEN_U3L2L1SUSPEN; - dwc3_writel(dwc->regs, DWC3_DEVTEN, reg); + dwc3_writel(dwc, DWC3_DEVTEN, reg); } static void dwc3_gadget_disable_irq(struct dwc3 *dwc) { /* mask all interrupts */ - dwc3_writel(dwc->regs, DWC3_DEVTEN, 0x00); + dwc3_writel(dwc, DWC3_DEVTEN, 0x00); } static irqreturn_t dwc3_interrupt(int irq, void *_dwc); @@ -2905,10 +2905,10 @@ static void dwc3_gadget_setup_nump(struct dwc3 *dwc) nump = min_t(u32, nump, 16); /* update NumP */ - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg &= ~DWC3_DCFG_NUMP_MASK; reg |= nump << DWC3_DCFG_NUMP_SHIFT; - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); } static int __dwc3_gadget_start(struct dwc3 *dwc) @@ -2922,10 +2922,10 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) * the core supports IMOD, disable it. */ if (dwc->imod_interval) { - dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval); - dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB); + dwc3_writel(dwc, DWC3_DEV_IMOD(0), dwc->imod_interval); + dwc3_writel(dwc, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB); } else if (dwc3_has_imod(dwc)) { - dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), 0); + dwc3_writel(dwc, DWC3_DEV_IMOD(0), 0); } /* @@ -2935,13 +2935,13 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) * This way, we maximize the chances that we'll be able to get several * bursts of data without going through any sort of endpoint throttling. */ - reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg = dwc3_readl(dwc, DWC3_GRXTHRCFG); if (DWC3_IP_IS(DWC3)) reg &= ~DWC3_GRXTHRCFG_PKTCNTSEL; else reg &= ~DWC31_GRXTHRCFG_PKTCNTSEL; - dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + dwc3_writel(dwc, DWC3_GRXTHRCFG, reg); dwc3_gadget_setup_nump(dwc); @@ -2952,15 +2952,15 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) * ACK with NumP=0 and PP=0 (for IN direction). This slightly improves * the stream performance. */ - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg |= DWC3_DCFG_IGNSTRMPP; - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); /* Enable MST by default if the device is capable of MST */ if (DWC3_MST_CAPABLE(&dwc->hwparams)) { - reg = dwc3_readl(dwc->regs, DWC3_DCFG1); + reg = dwc3_readl(dwc, DWC3_DCFG1); reg &= ~DWC3_DCFG1_DIS_MST_ENH; - dwc3_writel(dwc->regs, DWC3_DCFG1, reg); + dwc3_writel(dwc, DWC3_DCFG1, reg); } /* Start with SuperSpeed Default */ @@ -3238,7 +3238,7 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep) /* MDWIDTH is represented in bits, we need it in bytes */ mdwidth /= 8; - size = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(dep->number >> 1)); + size = dwc3_readl(dwc, DWC3_GTXFIFOSIZ(dep->number >> 1)); if (DWC3_IP_IS(DWC3)) size = DWC3_GTXFIFOSIZ_TXFDEP(size); else @@ -3287,7 +3287,7 @@ static int dwc3_gadget_init_out_endpoint(struct dwc3_ep *dep) mdwidth /= 8; /* All OUT endpoints share a single RxFIFO space */ - size = dwc3_readl(dwc->regs, DWC3_GRXFIFOSIZ(0)); + size = dwc3_readl(dwc, DWC3_GRXFIFOSIZ(0)); if (DWC3_IP_IS(DWC3)) size = DWC3_GRXFIFOSIZ_RXFDEP(size); else @@ -3740,9 +3740,9 @@ static bool dwc3_gadget_endpoint_trbs_complete(struct dwc3_ep *dep, return no_started_trb; } - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg |= dwc->u1u2; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + dwc3_writel(dwc, DWC3_DCTL, reg); dwc->u1u2 = 0; } @@ -4072,7 +4072,7 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RX_DET); - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~DWC3_DCTL_INITU1ENA; reg &= ~DWC3_DCTL_INITU2ENA; dwc3_gadget_dctl_write_safe(dwc, reg); @@ -4161,7 +4161,7 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc->connected = true; - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~DWC3_DCTL_TSTCTRL_MASK; dwc3_gadget_dctl_write_safe(dwc, reg); dwc->test_mode = false; @@ -4170,9 +4170,9 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_clear_stall_all_ep(dwc); /* Reset device address to zero */ - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg &= ~(DWC3_DCFG_DEVADDR_MASK); - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); } static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) @@ -4186,7 +4186,7 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) if (!dwc->softconnect) return; - reg = dwc3_readl(dwc->regs, DWC3_DSTS); + reg = dwc3_readl(dwc, DWC3_DSTS); speed = reg & DWC3_DSTS_CONNECTSPD; dwc->speed = speed; @@ -4261,11 +4261,11 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) !dwc->usb2_gadget_lpm_disable && (speed != DWC3_DSTS_SUPERSPEED) && (speed != DWC3_DSTS_SUPERSPEED_PLUS)) { - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg |= DWC3_DCFG_LPM_CAP; - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~(DWC3_DCTL_HIRD_THRES_MASK | DWC3_DCTL_L1_HIBER_EN); reg |= DWC3_DCTL_HIRD_THRES(dwc->hird_threshold | @@ -4288,12 +4288,12 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) dwc3_gadget_dctl_write_safe(dwc, reg); } else { if (dwc->usb2_gadget_lpm_disable) { - reg = dwc3_readl(dwc->regs, DWC3_DCFG); + reg = dwc3_readl(dwc, DWC3_DCFG); reg &= ~DWC3_DCFG_LPM_CAP; - dwc3_writel(dwc->regs, DWC3_DCFG, reg); + dwc3_writel(dwc, DWC3_DCFG, reg); } - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); reg &= ~DWC3_DCTL_HIRD_THRES_MASK; dwc3_gadget_dctl_write_safe(dwc, reg); } @@ -4399,7 +4399,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, switch (dwc->link_state) { case DWC3_LINK_STATE_U1: case DWC3_LINK_STATE_U2: - reg = dwc3_readl(dwc->regs, DWC3_DCTL); + reg = dwc3_readl(dwc, DWC3_DCTL); u1u2 = reg & (DWC3_DCTL_INITU2ENA | DWC3_DCTL_ACCEPTU2ENA | DWC3_DCTL_INITU1ENA @@ -4556,7 +4556,7 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt) ret = IRQ_HANDLED; /* Unmask interrupt */ - dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0), + dwc3_writel(dwc, DWC3_GEVNTSIZ(0), DWC3_GEVNTSIZ_SIZE(evt->length)); evt->flags &= ~DWC3_EVENT_PENDING; @@ -4567,8 +4567,8 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt) wmb(); if (dwc->imod_interval) { - dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB); - dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval); + dwc3_writel(dwc, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB); + dwc3_writel(dwc, DWC3_DEV_IMOD(0), dwc->imod_interval); } return ret; @@ -4617,7 +4617,7 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) if (evt->flags & DWC3_EVENT_PENDING) return IRQ_HANDLED; - count = dwc3_readl(dwc->regs, DWC3_GEVNTCOUNT(0)); + count = dwc3_readl(dwc, DWC3_GEVNTCOUNT(0)); count &= DWC3_GEVNTCOUNT_MASK; if (!count) return IRQ_NONE; @@ -4632,7 +4632,7 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) evt->flags |= DWC3_EVENT_PENDING; /* Mask interrupt */ - dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0), + dwc3_writel(dwc, DWC3_GEVNTSIZ(0), DWC3_GEVNTSIZ_INTMASK | DWC3_GEVNTSIZ_SIZE(evt->length)); amount = min(count, evt->length - evt->lpos); @@ -4641,7 +4641,7 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) if (amount < count) memcpy(evt->cache, evt->buf, count - amount); - dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), count); + dwc3_writel(dwc, DWC3_GEVNTCOUNT(0), count); return IRQ_WAKE_THREAD; } diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index c3aa9638b7a53..45f113b3c146c 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -132,7 +132,7 @@ static inline void dwc3_gadget_ep_get_transfer_index(struct dwc3_ep *dep) { u32 res_id; - res_id = dwc3_readl(dep->dwc->regs, DWC3_DEPCMD(dep->number)); + res_id = dwc3_readl(dep->dwc, DWC3_DEPCMD(dep->number)); dep->resource_index = DWC3_DEPCMD_GET_RSC_IDX(res_id); } @@ -147,7 +147,7 @@ static inline void dwc3_gadget_ep_get_transfer_index(struct dwc3_ep *dep) static inline void dwc3_gadget_dctl_write_safe(struct dwc3 *dwc, u32 value) { value &= ~DWC3_DCTL_ULSTCHNGREQ_MASK; - dwc3_writel(dwc->regs, DWC3_DCTL, value); + dwc3_writel(dwc, DWC3_DCTL, value); } #endif /* __DRIVERS_USB_DWC3_GADGET_H */ diff --git a/drivers/usb/dwc3/io.h b/drivers/usb/dwc3/io.h index 1e96ea339d48d..7dd0c1e0cf74f 100644 --- a/drivers/usb/dwc3/io.h +++ b/drivers/usb/dwc3/io.h @@ -16,9 +16,10 @@ #include "debug.h" #include "core.h" -static inline u32 dwc3_readl(void __iomem *base, u32 offset) +static inline u32 dwc3_readl(struct dwc3 *dwc, u32 offset) { u32 value; + void __iomem *base = dwc->regs; /* * We requested the mem region starting from the Globals address @@ -37,8 +38,10 @@ static inline u32 dwc3_readl(void __iomem *base, u32 offset) return value; } -static inline void dwc3_writel(void __iomem *base, u32 offset, u32 value) +static inline void dwc3_writel(struct dwc3 *dwc, u32 offset, u32 value) { + void __iomem *base = dwc->regs; + /* * We requested the mem region starting from the Globals address * space, see dwc3_probe in core.c. diff --git a/drivers/usb/dwc3/ulpi.c b/drivers/usb/dwc3/ulpi.c index f23f4c9a557e9..57daad15f502d 100644 --- a/drivers/usb/dwc3/ulpi.c +++ b/drivers/usb/dwc3/ulpi.c @@ -33,13 +33,13 @@ static int dwc3_ulpi_busyloop(struct dwc3 *dwc, u8 addr, bool read) if (read) ns += DWC3_ULPI_BASE_DELAY; - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0)); if (reg & DWC3_GUSB2PHYCFG_SUSPHY) usleep_range(1000, 1200); while (count--) { ndelay(ns); - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYACC(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYACC(0)); if (reg & DWC3_GUSB2PHYACC_DONE) return 0; cpu_relax(); @@ -55,13 +55,13 @@ static int dwc3_ulpi_read(struct device *dev, u8 addr) int ret; reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr); - dwc3_writel(dwc->regs, DWC3_GUSB2PHYACC(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYACC(0), reg); ret = dwc3_ulpi_busyloop(dwc, addr, true); if (ret) return ret; - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYACC(0)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYACC(0)); return DWC3_GUSB2PHYACC_DATA(reg); } @@ -73,7 +73,7 @@ static int dwc3_ulpi_write(struct device *dev, u8 addr, u8 val) reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr); reg |= DWC3_GUSB2PHYACC_WRITE | val; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYACC(0), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYACC(0), reg); return dwc3_ulpi_busyloop(dwc, addr, false); } From d784865ce48f3ccb7b9d933b7dabae1396050cbd Mon Sep 17 00:00:00 2001 From: Selvarasu Ganesan Date: Wed, 13 May 2026 07:27:44 -0400 Subject: [PATCH 0172/1518] usb: dwc3: Move GUID programming after PHY initialization [ Upstream commit aad35f9c926ec220b0742af1ada45666ae667956 ] The Linux Version Code is currently written to the GUID register before PHY initialization. Certain PHY implementations (such as Synopsys eUSB PHY performing link_sw_reset) clear the GUID register to its default value during initialization, causing the kernel version information to be lost. Move the GUID register programming to occur after PHY initialization completes to ensure the Linux version information persists. Fixes: fa0ea13e9f1c ("usb: dwc3: core: write LINUX_VERSION_CODE to our GUID register") Cc: stable Reported-by: Pritam Manohar Sutar Signed-off-by: Selvarasu Ganesan Acked-by: Thinh Nguyen Link: https://patch.msgid.link/20260417063314.2359-1-selvarasu.g@samsung.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index c5bec0bd9cb10..a1f99c3b5f378 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1339,12 +1339,6 @@ static int dwc3_core_init(struct dwc3 *dwc) hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); - /* - * Write Linux Version Code to our GUID register so it's easy to figure - * out which kernel version a bug was found. - */ - dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); - ret = dwc3_phy_setup(dwc); if (ret) return ret; @@ -1376,6 +1370,12 @@ static int dwc3_core_init(struct dwc3 *dwc) if (ret) goto err_exit_phy; + /* + * Write Linux Version Code to our GUID register so it's easy to figure + * out which kernel version a bug was found. + */ + dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); + dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); From a4b5c5d2f8c53135c1baaa52d75be83e07823c64 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 15 May 2026 08:06:14 -0400 Subject: [PATCH 0173/1518] btrfs: remove fs_info argument from btrfs_sysfs_add_space_info_type() [ Upstream commit 771af6ff72e0ed0eb8bf97e5ae4fa5094e0c5d1d ] We don't need it since we can grab fs_info from the given space_info. So remove the fs_info argument. Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: a7449edf9614 ("btrfs: fix double free in create_space_info_sub_group() error path") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/space-info.c | 4 ++-- fs/btrfs/sysfs.c | 5 ++--- fs/btrfs/sysfs.h | 3 +-- 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index a815308e2db91..c4a50550672da 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -275,7 +275,7 @@ static int create_space_info_sub_group(struct btrfs_space_info *parent, u64 flag sub_group->parent = parent; sub_group->subgroup_id = id; - ret = btrfs_sysfs_add_space_info_type(fs_info, sub_group); + ret = btrfs_sysfs_add_space_info_type(sub_group); if (ret) { kfree(sub_group); parent->sub_group[index] = NULL; @@ -309,7 +309,7 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) goto out_free; } - ret = btrfs_sysfs_add_space_info_type(info, space_info); + ret = btrfs_sysfs_add_space_info_type(space_info); if (ret) return ret; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 81f52c1f55ce5..d66681ce2b3da 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1981,13 +1981,12 @@ static const char *alloc_name(struct btrfs_space_info *space_info) * Create a sysfs entry for a space info type at path * /sys/fs/btrfs/UUID/allocation/TYPE */ -int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info) +int btrfs_sysfs_add_space_info_type(struct btrfs_space_info *space_info) { int ret; ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype, - fs_info->space_info_kobj, "%s", + space_info->fs_info->space_info_kobj, "%s", alloc_name(space_info)); if (ret) { kobject_put(&space_info->kobj); diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 0f94ae9232101..05498e5346c39 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -37,8 +37,7 @@ void __cold btrfs_exit_sysfs(void); int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info); void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info); void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache); -int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info); +int btrfs_sysfs_add_space_info_type(struct btrfs_space_info *space_info); void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info); void btrfs_sysfs_update_devid(struct btrfs_device *device); From dfd05a16b5c9d1d98b47905f37f2fccda52173d1 Mon Sep 17 00:00:00 2001 From: Guangshuo Li Date: Fri, 15 May 2026 08:06:15 -0400 Subject: [PATCH 0174/1518] btrfs: fix double free in create_space_info_sub_group() error path [ Upstream commit a7449edf96143f192606ec8647e3167e1ecbd728 ] When kobject_init_and_add() fails, the call chain is: create_space_info_sub_group() -> btrfs_sysfs_add_space_info_type() -> kobject_init_and_add() -> failure -> kobject_put(&sub_group->kobj) -> space_info_release() -> kfree(sub_group) Then control returns to create_space_info_sub_group(), where: btrfs_sysfs_add_space_info_type() returns error -> kfree(sub_group) Thus, sub_group is freed twice. Keep parent->sub_group[index] = NULL for the failure path, but after btrfs_sysfs_add_space_info_type() has called kobject_put(), let the kobject release callback handle the cleanup. Fixes: f92ee31e031c ("btrfs: introduce btrfs_space_info sub-group") CC: stable@vger.kernel.org # 6.18+ Reviewed-by: Qu Wenruo Signed-off-by: Guangshuo Li Signed-off-by: David Sterba Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/space-info.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index c4a50550672da..b3ff2e1da89ba 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -276,10 +276,8 @@ static int create_space_info_sub_group(struct btrfs_space_info *parent, u64 flag sub_group->subgroup_id = id; ret = btrfs_sysfs_add_space_info_type(sub_group); - if (ret) { - kfree(sub_group); + if (ret) parent->sub_group[index] = NULL; - } return ret; } From 5d12e0ab009ade48c1bff9324fd9bea2c773d088 Mon Sep 17 00:00:00 2001 From: Yochai Eisenrich Date: Fri, 15 May 2026 07:45:37 -0400 Subject: [PATCH 0175/1518] btrfs: fix btrfs_ioctl_space_info() slot_count TOCTOU which can lead to info-leak [ Upstream commit 973e57c726c1f8e77259d1c8e519519f1e9aea77 ] btrfs_ioctl_space_info() has a TOCTOU race between two passes over the block group RAID type lists. The first pass counts entries to determine the allocation size, then the second pass fills the buffer. The groups_sem rwlock is released between passes, allowing concurrent block group removal to reduce the entry count. When the second pass fills fewer entries than the first pass counted, copy_to_user() copies the full alloc_size bytes including trailing uninitialized kmalloc bytes to userspace. Fix by copying only total_spaces entries (the actually-filled count from the second pass) instead of alloc_size bytes, and switch to kzalloc so any future copy size mismatch cannot leak heap data. Fixes: 7fde62bffb57 ("Btrfs: buffer results in the space_info ioctl") CC: stable@vger.kernel.org # 3.0 Signed-off-by: Yochai Eisenrich Reviewed-by: David Sterba Signed-off-by: David Sterba [ adapted upstream's `return -EFAULT;` to stable's `ret = -EFAULT;` fall-through to existing `out:` cleanup label ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ioctl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bfe253c2849a5..c0691e93e0a58 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3025,7 +3025,7 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, return -ENOMEM; space_args.total_spaces = 0; - dest = kmalloc(alloc_size, GFP_KERNEL); + dest = kzalloc(alloc_size, GFP_KERNEL); if (!dest) return -ENOMEM; dest_orig = dest; @@ -3081,7 +3081,8 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, user_dest = (struct btrfs_ioctl_space_info __user *) (arg + sizeof(struct btrfs_ioctl_space_args)); - if (copy_to_user(user_dest, dest_orig, alloc_size)) + if (copy_to_user(user_dest, dest_orig, + space_args.total_spaces * sizeof(*dest_orig))) ret = -EFAULT; kfree(dest_orig); From 52277410cbede5d439c167a84e9f301a2811b605 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 15 May 2026 07:32:23 -0400 Subject: [PATCH 0176/1518] tracing: fprobe: use rhltable for fprobe_ip_table [ Upstream commit 0de4c70d04a46a3c266547dd4275ce25f623796a ] For now, all the kernel functions who are hooked by the fprobe will be added to the hash table "fprobe_ip_table". The key of it is the function address, and the value of it is "struct fprobe_hlist_node". The budget of the hash table is FPROBE_IP_TABLE_SIZE, which is 256. And this means the overhead of the hash table lookup will grow linearly if the count of the functions in the fprobe more than 256. When we try to hook all the kernel functions, the overhead will be huge. Therefore, replace the hash table with rhltable to reduce the overhead. Link: https://lore.kernel.org/all/20250819031825.55653-1-dongml2@chinatelecom.cn/ Signed-off-by: Menglong Dong Signed-off-by: Masami Hiramatsu (Google) Stable-dep-of: 845947aca681 ("tracing/fprobe: Remove fprobe from hash in failure path") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- include/linux/fprobe.h | 3 +- kernel/trace/fprobe.c | 157 ++++++++++++++++++++++++----------------- 2 files changed, 93 insertions(+), 67 deletions(-) diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 7964db96e41a9..0a3bcd1718f37 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -7,6 +7,7 @@ #include #include #include +#include #include struct fprobe; @@ -26,7 +27,7 @@ typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, * @fp: The fprobe which owns this. */ struct fprobe_hlist_node { - struct hlist_node hlist; + struct rhlist_head hlist; unsigned long addr; struct fprobe *fp; }; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 43b27f07730c2..9db0a4e331132 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -42,60 +43,67 @@ * - RCU hlist traversal under disabling preempt */ static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE]; -static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE]; +static struct rhltable fprobe_ip_table; static DEFINE_MUTEX(fprobe_mutex); -/* - * Find first fprobe in the hlist. It will be iterated twice in the entry - * probe, once for correcting the total required size, the second time is - * calling back the user handlers. - * Thus the hlist in the fprobe_table must be sorted and new probe needs to - * be added *before* the first fprobe. - */ -static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip) +static u32 fprobe_node_hashfn(const void *data, u32 len, u32 seed) { - struct fprobe_hlist_node *node; - struct hlist_head *head; + return hash_ptr(*(unsigned long **)data, 32); +} - head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; - hlist_for_each_entry_rcu(node, head, hlist, - lockdep_is_held(&fprobe_mutex)) { - if (node->addr == ip) - return node; - } - return NULL; +static int fprobe_node_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + unsigned long key = *(unsigned long *)arg->key; + const struct fprobe_hlist_node *n = ptr; + + return n->addr != key; } -NOKPROBE_SYMBOL(find_first_fprobe_node); -/* Node insertion and deletion requires the fprobe_mutex */ -static void insert_fprobe_node(struct fprobe_hlist_node *node) +static u32 fprobe_node_obj_hashfn(const void *data, u32 len, u32 seed) { - unsigned long ip = node->addr; - struct fprobe_hlist_node *next; - struct hlist_head *head; + const struct fprobe_hlist_node *n = data; + + return hash_ptr((void *)n->addr, 32); +} +static const struct rhashtable_params fprobe_rht_params = { + .head_offset = offsetof(struct fprobe_hlist_node, hlist), + .key_offset = offsetof(struct fprobe_hlist_node, addr), + .key_len = sizeof_field(struct fprobe_hlist_node, addr), + .hashfn = fprobe_node_hashfn, + .obj_hashfn = fprobe_node_obj_hashfn, + .obj_cmpfn = fprobe_node_cmp, + .automatic_shrinking = true, +}; + +/* Node insertion and deletion requires the fprobe_mutex */ +static int insert_fprobe_node(struct fprobe_hlist_node *node) +{ lockdep_assert_held(&fprobe_mutex); - next = find_first_fprobe_node(ip); - if (next) { - hlist_add_before_rcu(&node->hlist, &next->hlist); - return; - } - head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; - hlist_add_head_rcu(&node->hlist, head); + return rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params); } /* Return true if there are synonims */ static bool delete_fprobe_node(struct fprobe_hlist_node *node) { lockdep_assert_held(&fprobe_mutex); + bool ret; /* Avoid double deleting */ if (READ_ONCE(node->fp) != NULL) { WRITE_ONCE(node->fp, NULL); - hlist_del_rcu(&node->hlist); + rhltable_remove(&fprobe_ip_table, &node->hlist, + fprobe_rht_params); } - return !!find_first_fprobe_node(node->addr); + + rcu_read_lock(); + ret = !!rhltable_lookup(&fprobe_ip_table, &node->addr, + fprobe_rht_params); + rcu_read_unlock(); + + return ret; } /* Check existence of the fprobe */ @@ -247,9 +255,10 @@ static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, struct ftrace_regs *fregs) { - struct fprobe_hlist_node *node, *first; unsigned long *fgraph_data = NULL; unsigned long func = trace->func; + struct fprobe_hlist_node *node; + struct rhlist_head *head, *pos; unsigned long ret_ip; int reserved_words; struct fprobe *fp; @@ -258,14 +267,11 @@ static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, if (WARN_ON_ONCE(!fregs)) return 0; - first = node = find_first_fprobe_node(func); - if (unlikely(!first)) - return 0; - + head = rhltable_lookup(&fprobe_ip_table, &func, fprobe_rht_params); reserved_words = 0; - hlist_for_each_entry_from_rcu(node, hlist) { + rhl_for_each_entry_rcu(node, pos, head, hlist) { if (node->addr != func) - break; + continue; fp = READ_ONCE(node->fp); if (!fp || !fp->exit_handler) continue; @@ -276,13 +282,12 @@ static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, reserved_words += FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size); } - node = first; if (reserved_words) { fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long)); if (unlikely(!fgraph_data)) { - hlist_for_each_entry_from_rcu(node, hlist) { + rhl_for_each_entry_rcu(node, pos, head, hlist) { if (node->addr != func) - break; + continue; fp = READ_ONCE(node->fp); if (fp && !fprobe_disabled(fp)) fp->nmissed++; @@ -297,12 +302,12 @@ static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, */ ret_ip = ftrace_regs_get_return_address(fregs); used = 0; - hlist_for_each_entry_from_rcu(node, hlist) { + rhl_for_each_entry_rcu(node, pos, head, hlist) { int data_size; void *data; if (node->addr != func) - break; + continue; fp = READ_ONCE(node->fp); if (!fp || fprobe_disabled(fp)) continue; @@ -447,25 +452,21 @@ static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long ad return 0; } -static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head *head, - struct fprobe_addr_list *alist) +static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, + struct fprobe_addr_list *alist) { - struct fprobe_hlist_node *node; int ret = 0; - hlist_for_each_entry_rcu(node, head, hlist, - lockdep_is_held(&fprobe_mutex)) { - if (!within_module(node->addr, mod)) - continue; - if (delete_fprobe_node(node)) - continue; - /* - * If failed to update alist, just continue to update hlist. - * Therefore, at list user handler will not hit anymore. - */ - if (!ret) - ret = fprobe_addr_list_add(alist, node->addr); - } + if (!within_module(node->addr, mod)) + return; + if (delete_fprobe_node(node)) + return; + /* + * If failed to update alist, just continue to update hlist. + * Therefore, at list user handler will not hit anymore. + */ + if (!ret) + ret = fprobe_addr_list_add(alist, node->addr); } /* Handle module unloading to manage fprobe_ip_table. */ @@ -473,8 +474,9 @@ static int fprobe_module_callback(struct notifier_block *nb, unsigned long val, void *data) { struct fprobe_addr_list alist = {.size = FPROBE_IPS_BATCH_INIT}; + struct fprobe_hlist_node *node; + struct rhashtable_iter iter; struct module *mod = data; - int i; if (val != MODULE_STATE_GOING) return NOTIFY_DONE; @@ -485,8 +487,16 @@ static int fprobe_module_callback(struct notifier_block *nb, return NOTIFY_DONE; mutex_lock(&fprobe_mutex); - for (i = 0; i < FPROBE_IP_TABLE_SIZE; i++) - fprobe_remove_node_in_module(mod, &fprobe_ip_table[i], &alist); + rhltable_walk_enter(&fprobe_ip_table, &iter); + do { + rhashtable_walk_start(&iter); + + while ((node = rhashtable_walk_next(&iter)) && !IS_ERR(node)) + fprobe_remove_node_in_module(mod, node, &alist); + + rhashtable_walk_stop(&iter); + } while (node == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&iter); if (alist.index > 0) ftrace_set_filter_ips(&fprobe_graph_ops.ops, @@ -728,8 +738,16 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) ret = fprobe_graph_add_ips(addrs, num); if (!ret) { add_fprobe_hash(fp); - for (i = 0; i < hlist_array->size; i++) - insert_fprobe_node(&hlist_array->array[i]); + for (i = 0; i < hlist_array->size; i++) { + ret = insert_fprobe_node(&hlist_array->array[i]); + if (ret) + break; + } + /* fallback on insert error */ + if (ret) { + for (i--; i >= 0; i--) + delete_fprobe_node(&hlist_array->array[i]); + } } if (ret) @@ -824,3 +842,10 @@ int unregister_fprobe(struct fprobe *fp) return ret; } EXPORT_SYMBOL_GPL(unregister_fprobe); + +static int __init fprobe_initcall(void) +{ + rhltable_init(&fprobe_ip_table, &fprobe_rht_params); + return 0; +} +late_initcall(fprobe_initcall); From d83e51202fec013e5ad7ff7898dc526f33e73507 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 15 May 2026 07:32:24 -0400 Subject: [PATCH 0177/1518] tracing: fprobe: optimization for entry only case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2c67dc457bc67367dc8fcd8f471ce2d5bb5f7b2b ] For now, fgraph is used for the fprobe, even if we need trace the entry only. However, the performance of ftrace is better than fgraph, and we can use ftrace_ops for this case. Then performance of kprobe-multi increases from 54M to 69M. Before this commit: $ ./benchs/run_bench_trigger.sh kprobe-multi kprobe-multi : 54.663 ± 0.493M/s After this commit: $ ./benchs/run_bench_trigger.sh kprobe-multi kprobe-multi : 69.447 ± 0.143M/s Mitigation is disable during the bench testing above. Link: https://lore.kernel.org/all/20251015083238.2374294-2-dongml2@chinatelecom.cn/ Signed-off-by: Menglong Dong Signed-off-by: Masami Hiramatsu (Google) Stable-dep-of: 845947aca681 ("tracing/fprobe: Remove fprobe from hash in failure path") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 128 +++++++++++++++++++++++++++++++++++++++--- 1 file changed, 119 insertions(+), 9 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9db0a4e331132..66fa49b0cf27a 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -252,8 +252,106 @@ static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent return ret; } -static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, - struct ftrace_regs *fregs) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +/* ftrace_ops callback, this processes fprobes which have only entry_handler. */ +static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe_hlist_node *node; + struct rhlist_head *head, *pos; + struct fprobe *fp; + int bit; + + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + /* + * ftrace_test_recursion_trylock() disables preemption, but + * rhltable_lookup() checks whether rcu_read_lcok is held. + * So we take rcu_read_lock() here. + */ + rcu_read_lock(); + head = rhltable_lookup(&fprobe_ip_table, &ip, fprobe_rht_params); + + rhl_for_each_entry_rcu(node, pos, head, hlist) { + if (node->addr != ip) + break; + fp = READ_ONCE(node->fp); + if (unlikely(!fp || fprobe_disabled(fp) || fp->exit_handler)) + continue; + + if (fprobe_shared_with_kprobes(fp)) + __fprobe_kprobe_handler(ip, parent_ip, fp, fregs, NULL); + else + __fprobe_handler(ip, parent_ip, fp, fregs, NULL); + } + rcu_read_unlock(); + ftrace_test_recursion_unlock(bit); +} +NOKPROBE_SYMBOL(fprobe_ftrace_entry); + +static struct ftrace_ops fprobe_ftrace_ops = { + .func = fprobe_ftrace_entry, + .flags = FTRACE_OPS_FL_SAVE_REGS, +}; +static int fprobe_ftrace_active; + +static int fprobe_ftrace_add_ips(unsigned long *addrs, int num) +{ + int ret; + + lockdep_assert_held(&fprobe_mutex); + + ret = ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 0, 0); + if (ret) + return ret; + + if (!fprobe_ftrace_active) { + ret = register_ftrace_function(&fprobe_ftrace_ops); + if (ret) { + ftrace_free_filter(&fprobe_ftrace_ops); + return ret; + } + } + fprobe_ftrace_active++; + return 0; +} + +static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num) +{ + lockdep_assert_held(&fprobe_mutex); + + fprobe_ftrace_active--; + if (!fprobe_ftrace_active) + unregister_ftrace_function(&fprobe_ftrace_ops); + if (num) + ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 1, 0); +} + +static bool fprobe_is_ftrace(struct fprobe *fp) +{ + return !fp->exit_handler; +} +#else +static int fprobe_ftrace_add_ips(unsigned long *addrs, int num) +{ + return -ENOENT; +} + +static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num) +{ +} + +static bool fprobe_is_ftrace(struct fprobe *fp) +{ + return false; +} +#endif + +/* fgraph_ops callback, this processes fprobes which have exit_handler. */ +static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs) { unsigned long *fgraph_data = NULL; unsigned long func = trace->func; @@ -289,7 +387,7 @@ static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, if (node->addr != func) continue; fp = READ_ONCE(node->fp); - if (fp && !fprobe_disabled(fp)) + if (fp && !fprobe_disabled(fp) && !fprobe_is_ftrace(fp)) fp->nmissed++; } return 0; @@ -309,7 +407,7 @@ static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, if (node->addr != func) continue; fp = READ_ONCE(node->fp); - if (!fp || fprobe_disabled(fp)) + if (unlikely(!fp || fprobe_disabled(fp) || fprobe_is_ftrace(fp))) continue; data_size = fp->entry_data_size; @@ -337,7 +435,7 @@ static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, /* If any exit_handler is set, data must be used. */ return used != 0; } -NOKPROBE_SYMBOL(fprobe_entry); +NOKPROBE_SYMBOL(fprobe_fgraph_entry); static void fprobe_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, @@ -376,7 +474,7 @@ static void fprobe_return(struct ftrace_graph_ret *trace, NOKPROBE_SYMBOL(fprobe_return); static struct fgraph_ops fprobe_graph_ops = { - .entryfunc = fprobe_entry, + .entryfunc = fprobe_fgraph_entry, .retfunc = fprobe_return, }; static int fprobe_graph_active; @@ -498,9 +596,14 @@ static int fprobe_module_callback(struct notifier_block *nb, } while (node == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); - if (alist.index > 0) + if (alist.index > 0) { ftrace_set_filter_ips(&fprobe_graph_ops.ops, alist.addrs, alist.index, 1, 0); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + ftrace_set_filter_ips(&fprobe_ftrace_ops, + alist.addrs, alist.index, 1, 0); +#endif + } mutex_unlock(&fprobe_mutex); kfree(alist.addrs); @@ -735,7 +838,11 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) return ret; hlist_array = fp->hlist_array; - ret = fprobe_graph_add_ips(addrs, num); + if (fprobe_is_ftrace(fp)) + ret = fprobe_ftrace_add_ips(addrs, num); + else + ret = fprobe_graph_add_ips(addrs, num); + if (!ret) { add_fprobe_hash(fp); for (i = 0; i < hlist_array->size; i++) { @@ -830,7 +937,10 @@ int unregister_fprobe(struct fprobe *fp) } del_fprobe_hash(fp); - fprobe_graph_remove_ips(addrs, count); + if (fprobe_is_ftrace(fp)) + fprobe_ftrace_remove_ips(addrs, count); + else + fprobe_graph_remove_ips(addrs, count); kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; From a2181464a4a729fee1a9de4404991ef9bd811d72 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 15 May 2026 07:32:25 -0400 Subject: [PATCH 0178/1518] tracing/fprobe: Unregister fprobe even if memory allocation fails [ Upstream commit 1aec9e5c3e31ce1e28f914427fb7f90b91d310df ] unregister_fprobe() can fail under memory pressure because of memory allocation failure, but this maybe called from module unloading, and usually there is no way to retry it. Moreover. trace_fprobe does not check the return value. To fix this problem, unregister fprobe and fprobe_hash_node even if working memory allocation fails. Anyway, if the last fprobe is removed, the filter will be freed. Link: https://lore.kernel.org/all/177669365629.132053.8433032896213721288.stgit@mhiramat.tok.corp.google.com/ Fixes: 4346ba160409 ("fprobe: Rewrite fprobe on function-graph tracer") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Stable-dep-of: 845947aca681 ("tracing/fprobe: Remove fprobe from hash in failure path") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 66fa49b0cf27a..2e5c6b3cafc0b 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -323,9 +323,10 @@ static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_ftrace_active--; - if (!fprobe_ftrace_active) + if (!fprobe_ftrace_active) { unregister_ftrace_function(&fprobe_ftrace_ops); - if (num) + ftrace_free_filter(&fprobe_ftrace_ops); + } else if (num) ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 1, 0); } @@ -508,10 +509,10 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) fprobe_graph_active--; /* Q: should we unregister it ? */ - if (!fprobe_graph_active) + if (!fprobe_graph_active) { unregister_ftrace_graph(&fprobe_graph_ops); - - if (num) + ftrace_free_filter(&fprobe_graph_ops.ops); + } else if (num) ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } @@ -924,15 +925,19 @@ int unregister_fprobe(struct fprobe *fp) hlist_array = fp->hlist_array; addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); - if (!addrs) { - ret = -ENOMEM; /* TODO: Fallback to one-by-one loop */ - goto out; - } + /* + * This will remove fprobe_hash_node from the hash table even if + * memory allocation fails. However, ftrace_ops will not be updated. + * Anyway, when the last fprobe is unregistered, ftrace_ops is also + * unregistered. + */ + if (!addrs) + pr_warn("Failed to allocate working array. ftrace_ops may not sync.\n"); /* Remove non-synonim ips from table and hash */ count = 0; for (i = 0; i < hlist_array->size; i++) { - if (!delete_fprobe_node(&hlist_array->array[i])) + if (!delete_fprobe_node(&hlist_array->array[i]) && addrs) addrs[count++] = hlist_array->array[i].addr; } del_fprobe_hash(fp); From 5e9dfc07d061ee1fc232a692e385bca59300bedb Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 15 May 2026 07:32:26 -0400 Subject: [PATCH 0179/1518] tracing/fprobe: Remove fprobe from hash in failure path [ Upstream commit 845947aca6814f5723ed65e556eb5ee09493f05b ] When register_fprobe_ips() fails, it tries to remove a list of fprobe_hash_node from fprobe_ip_table, but it missed to remove fprobe itself from fprobe_table. Moreover, when removing the fprobe_hash_node which is added to rhltable once, it must use kfree_rcu() after removing from rhltable. To fix these issues, this reuses unregister_fprobe() internal code to rollback the half-way registered fprobe. Link: https://lore.kernel.org/all/177669366417.132053.17874946321744910456.stgit@mhiramat.tok.corp.google.com/ Fixes: 4346ba160409 ("fprobe: Rewrite fprobe on function-graph tracer") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 90 ++++++++++++++++++++++--------------------- 1 file changed, 47 insertions(+), 43 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 2e5c6b3cafc0b..8fa5bff2c26fa 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -78,20 +78,27 @@ static const struct rhashtable_params fprobe_rht_params = { }; /* Node insertion and deletion requires the fprobe_mutex */ -static int insert_fprobe_node(struct fprobe_hlist_node *node) +static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) { + int ret; + lockdep_assert_held(&fprobe_mutex); - return rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params); + ret = rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params); + /* Set the fprobe pointer if insertion was successful. */ + if (!ret) + WRITE_ONCE(node->fp, fp); + return ret; } /* Return true if there are synonims */ static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - lockdep_assert_held(&fprobe_mutex); bool ret; - /* Avoid double deleting */ + lockdep_assert_held(&fprobe_mutex); + + /* Avoid double deleting and non-inserted nodes */ if (READ_ONCE(node->fp) != NULL) { WRITE_ONCE(node->fp, NULL); rhltable_remove(&fprobe_ip_table, &node->hlist, @@ -748,7 +755,6 @@ static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num) fp->hlist_array = hlist_array; hlist_array->fp = fp; for (i = 0; i < num; i++) { - hlist_array->array[i].fp = fp; addr = ftrace_location(addrs[i]); if (!addr) { fprobe_fail_cleanup(fp); @@ -812,6 +818,8 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter } EXPORT_SYMBOL_GPL(register_fprobe); +static int unregister_fprobe_nolock(struct fprobe *fp); + /** * register_fprobe_ips() - Register fprobe to ftrace by address. * @fp: A fprobe data structure to be registered. @@ -838,28 +846,25 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) if (ret) return ret; - hlist_array = fp->hlist_array; if (fprobe_is_ftrace(fp)) ret = fprobe_ftrace_add_ips(addrs, num); else ret = fprobe_graph_add_ips(addrs, num); - - if (!ret) { - add_fprobe_hash(fp); - for (i = 0; i < hlist_array->size; i++) { - ret = insert_fprobe_node(&hlist_array->array[i]); - if (ret) - break; - } - /* fallback on insert error */ - if (ret) { - for (i--; i >= 0; i--) - delete_fprobe_node(&hlist_array->array[i]); - } + if (ret) { + fprobe_fail_cleanup(fp); + return ret; } - if (ret) - fprobe_fail_cleanup(fp); + hlist_array = fp->hlist_array; + ret = add_fprobe_hash(fp); + for (i = 0; i < hlist_array->size && !ret; i++) + ret = insert_fprobe_node(&hlist_array->array[i], fp); + + if (ret) { + unregister_fprobe_nolock(fp); + /* In error case, wait for clean up safely. */ + synchronize_rcu(); + } return ret; } @@ -903,27 +908,12 @@ bool fprobe_is_registered(struct fprobe *fp) return true; } -/** - * unregister_fprobe() - Unregister fprobe. - * @fp: A fprobe data structure to be unregistered. - * - * Unregister fprobe (and remove ftrace hooks from the function entries). - * - * Return 0 if @fp is unregistered successfully, -errno if not. - */ -int unregister_fprobe(struct fprobe *fp) +static int unregister_fprobe_nolock(struct fprobe *fp) { - struct fprobe_hlist *hlist_array; + struct fprobe_hlist *hlist_array = fp->hlist_array; unsigned long *addrs = NULL; - int ret = 0, i, count; + int i, count; - mutex_lock(&fprobe_mutex); - if (!fp || !fprobe_registered(fp)) { - ret = -EINVAL; - goto out; - } - - hlist_array = fp->hlist_array; addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); /* * This will remove fprobe_hash_node from the hash table even if @@ -949,12 +939,26 @@ int unregister_fprobe(struct fprobe *fp) kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; + kfree(addrs); -out: - mutex_unlock(&fprobe_mutex); + return 0; +} - kfree(addrs); - return ret; +/** + * unregister_fprobe() - Unregister fprobe. + * @fp: A fprobe data structure to be unregistered. + * + * Unregister fprobe (and remove ftrace hooks from the function entries). + * + * Return 0 if @fp is unregistered successfully, -errno if not. + */ +int unregister_fprobe(struct fprobe *fp) +{ + guard(mutex)(&fprobe_mutex); + if (!fp || !fprobe_registered(fp)) + return -EINVAL; + + return unregister_fprobe_nolock(fp); } EXPORT_SYMBOL_GPL(unregister_fprobe); From 8be7860537978c62e0274b463cdca1882cee20fb Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Fri, 15 May 2026 13:44:28 +0200 Subject: [PATCH 0180/1518] batman-adv: tp_meter: fix tp_num leak on kmalloc failure commit ce425dd05d0fe7594930a0fb103634f35ac47bb6 upstream. When batadv_tp_start() or batadv_tp_init_recv() fail to allocate a new tp_vars object, the previously incremented bat_priv->tp_num counter is never decremented. This causes tp_num to drift upward on each allocation failure. Since only BATADV_TP_MAX_NUM sessions can be started and the count is never reduced for these failed allocations, it causes to an exhaustion of throughput meter sessions. In worst case, no new throughput meter session can be started until the mesh interface is removed. The error handling must decrement tp_num releasing the lock and aborting the creation of an throughput meter session Cc: stable@kernel.org Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") [ Context ] Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 190affbad3c94..76ece40143840 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -994,6 +994,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars = kmalloc(sizeof(*tp_vars), GFP_ATOMIC); if (!tp_vars) { + atomic_dec(&bat_priv->tp_num); spin_unlock_bh(&bat_priv->tp_list_lock); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: %s cannot allocate list elements\n", @@ -1366,8 +1367,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, } tp_vars = kmalloc(sizeof(*tp_vars), GFP_ATOMIC); - if (!tp_vars) + if (!tp_vars) { + atomic_dec(&bat_priv->tp_num); goto out_unlock; + } ether_addr_copy(tp_vars->other_end, icmp->orig); tp_vars->role = BATADV_TP_RECEIVER; From 2602f7bb5818e92315feeaeb71d8ce4d5c9ab160 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Thu, 9 Apr 2026 18:34:12 +0200 Subject: [PATCH 0181/1518] vsock: fix buffer size clamping order commit d114bfdc9b76bf93b881e195b7ec957c14227bab upstream. In vsock_update_buffer_size(), the buffer size was being clamped to the maximum first, and then to the minimum. If a user sets a minimum buffer size larger than the maximum, the minimum check overrides the maximum check, inverting the constraint. This breaks the intended socket memory boundaries by allowing the vsk->buffer_size to grow beyond the configured vsk->buffer_max_size. Fix this by checking the minimum first, and then the maximum. This ensures the buffer size never exceeds the buffer_max_size. Fixes: b9f2b0ffde0c ("vsock: handle buffer_size sockopts in the core") Suggested-by: Stefano Garzarella Signed-off-by: Norbert Szetei Reviewed-by: Stefano Garzarella Link: https://patch.msgid.link/180118C5-8BCF-4A63-A305-4EE53A34AB9C@doyensec.com Signed-off-by: Jakub Kicinski Cc: Luigi Leonardi Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/af_vsock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index cbd649bf01459..9d0e1915abbe8 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1846,12 +1846,12 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk, const struct vsock_transport *transport, u64 val) { - if (val > vsk->buffer_max_size) - val = vsk->buffer_max_size; - if (val < vsk->buffer_min_size) val = vsk->buffer_min_size; + if (val > vsk->buffer_max_size) + val = vsk->buffer_max_size; + if (val != vsk->buffer_size && transport && transport->notify_buffer_size) transport->notify_buffer_size(vsk, &val); From a534e1f985b6472abef80437a0dc75e7a259f4fa Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 8 May 2026 18:44:10 +0200 Subject: [PATCH 0182/1518] vsock/virtio: fix length and offset in tap skb for split packets commit 5f344d809e015fba3709e5219428c00b8ac5d7df upstream. virtio_transport_build_skb() builds a new skb to be delivered to the vsockmon tap device. To build the new skb, it uses the original skb data length as payload length, but as the comment notes, the original packet stored in the skb may have been split in multiple packets, so we need to use the length in the header, which is correctly updated before the packet is delivered to the tap, and the offset for the data. This was also similar to what we did before commit 71dc9ec9ac7d ("virtio/vsock: replace virtio_vsock_pkt with sk_buff") where we probably missed something during the skb conversion. Also update the comment above, which was left stale by the skb conversion and still mentioned a buffer pointer that no longer exists. Fixes: 71dc9ec9ac7d ("virtio/vsock: replace virtio_vsock_pkt with sk_buff") Signed-off-by: Stefano Garzarella Reviewed-by: Bobby Eshleman Reviewed-by: Arseniy Krasnov Link: https://patch.msgid.link/20260508164411.261440-2-sgarzare@redhat.com Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni Cc: Luigi Leonardi Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/virtio_transport_common.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a807a4aa62d3f..57b69b7e895f7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -169,12 +169,12 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct sk_buff *skb; size_t payload_len; - /* A packet could be split to fit the RX buffer, so we can retrieve - * the payload length from the header and the buffer pointer taking - * care of the offset in the original packet. + /* A packet could be split to fit the RX buffer, so we use + * the payload length from the header, which has been updated + * by the sender to reflect the fragment size. */ pkt_hdr = virtio_vsock_hdr(pkt); - payload_len = pkt->len; + payload_len = le32_to_cpu(pkt_hdr->len); skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len, GFP_ATOMIC); @@ -222,7 +222,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) virtio_transport_copy_nonlinear_skb(pkt, data, payload_len); } else { - skb_put_data(skb, pkt->data, payload_len); + skb_put_data(skb, pkt->data + VIRTIO_VSOCK_SKB_CB(pkt)->offset, + payload_len); } } From 52da6a74ca3de0fcda60301096b71534b3b18641 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 8 May 2026 18:44:11 +0200 Subject: [PATCH 0183/1518] vsock/virtio: fix empty payload in tap skb for non-linear buffers commit 3a3e3d90cbc79600544536723911657730759af3 upstream. For non-linear skbs, virtio_transport_build_skb() goes through virtio_transport_copy_nonlinear_skb() to copy the original payload in the new skb to be delivered to the vsockmon tap device. This manually initializes an iov_iter but does not set iov_iter.count. Since the iov_iter is zero-initialized, the copy length is zero and no payload is actually copied to the monitor interface, leaving data un-initialized. Fix this by removing the linear vs non-linear split and using skb_copy_datagram_iter() with iov_iter_kvec() for all cases, as vhost-vsock already does. This handles both linear and non-linear skbs, properly initializes the iov_iter, and removes the now unused virtio_transport_copy_nonlinear_skb(). While touching this code, let's also check the return value of skb_copy_datagram_iter(), even though it's unlikely to fail. Fixes: 4b0bf10eb077 ("vsock/virtio: non-linear skb handling for tap") Reported-by: Yiqi Sun Signed-off-by: Stefano Garzarella Reviewed-by: Bobby Eshleman Reviewed-by: Arseniy Krasnov Link: https://patch.msgid.link/20260508164411.261440-3-sgarzare@redhat.com Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni Cc: Luigi Leonardi Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/virtio_transport_common.c | 40 ++++++++----------------- 1 file changed, 12 insertions(+), 28 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 57b69b7e895f7..3e148c39d1076 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -139,27 +139,6 @@ static void virtio_transport_init_hdr(struct sk_buff *skb, hdr->fwd_cnt = cpu_to_le32(0); } -static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb, - void *dst, - size_t len) -{ - struct iov_iter iov_iter = { 0 }; - struct kvec kvec; - size_t to_copy; - - kvec.iov_base = dst; - kvec.iov_len = len; - - iov_iter.iter_type = ITER_KVEC; - iov_iter.kvec = &kvec; - iov_iter.nr_segs = 1; - - to_copy = min_t(size_t, len, skb->len); - - skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, - &iov_iter, to_copy); -} - /* Packet capture */ static struct sk_buff *virtio_transport_build_skb(void *opaque) { @@ -217,13 +196,18 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr)); if (payload_len) { - if (skb_is_nonlinear(pkt)) { - void *data = skb_put(skb, payload_len); - - virtio_transport_copy_nonlinear_skb(pkt, data, payload_len); - } else { - skb_put_data(skb, pkt->data + VIRTIO_VSOCK_SKB_CB(pkt)->offset, - payload_len); + struct iov_iter iov_iter; + struct kvec kvec; + void *data = skb_put(skb, payload_len); + + kvec.iov_base = data; + kvec.iov_len = payload_len; + iov_iter_kvec(&iov_iter, ITER_DEST, &kvec, 1, payload_len); + + if (skb_copy_datagram_iter(pkt, VIRTIO_VSOCK_SKB_CB(pkt)->offset, + &iov_iter, payload_len)) { + kfree_skb(skb); + return NULL; } } From e9edf9893cf26d060705c910a9b62d8cc96ed56a Mon Sep 17 00:00:00 2001 From: Dudu Lu Date: Mon, 13 Apr 2026 21:14:09 +0800 Subject: [PATCH 0184/1518] vsock/virtio: fix accept queue count leak on transport mismatch commit 52bcb57a4e8a0865a76c587c2451906342ae1b2d upstream. virtio_transport_recv_listen() calls sk_acceptq_added() before vsock_assign_transport(). If vsock_assign_transport() fails or selects a different transport, the error path returns without calling sk_acceptq_removed(), permanently incrementing sk_ack_backlog. After approximately backlog+1 such failures, sk_acceptq_is_full() returns true, causing the listener to reject all new connections. Fix by moving sk_acceptq_added() to after the transport validation, matching the pattern used by vmci_transport and hyperv_transport. Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Signed-off-by: Dudu Lu Reviewed-by: Bobby Eshleman Reviewed-by: Luigi Leonardi Reviewed-by: Stefano Garzarella Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260413131409.19022-1-phx0fer@gmail.com Signed-off-by: Paolo Abeni Cc: Luigi Leonardi Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/virtio_transport_common.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 3e148c39d1076..41be06c4bd7ff 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1528,8 +1528,6 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, return -ENOMEM; } - sk_acceptq_added(sk); - lock_sock_nested(child, SINGLE_DEPTH_NESTING); child->sk_state = TCP_ESTABLISHED; @@ -1551,6 +1549,7 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, return ret; } + sk_acceptq_added(sk); if (virtio_transport_space_update(child, skb)) child->sk_write_space(child); From 016b64a0313ea5346cf526e30c8d3e66aca10175 Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Mon, 13 Apr 2026 09:22:15 -0400 Subject: [PATCH 0185/1518] drm/amdgpu/vcn3: Avoid overflow on msg bound check commit e6e9faba8100628990cccd13f0f044a648c303cf upstream. As pointed out by SDL, the previous condition may be vulnerable to overflow. Fixes: b193019860d6 ("drm/amdgpu/vcn3: Prevent OOB reads when parsing dec msg") Cc: SDL Signed-off-by: Benjamin Cheng Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher (cherry picked from commit db00257ac9e4a51eb2515aaea161a019f7125e10) Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 558d3bf7fc76e..8b226edfbea3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1971,6 +1971,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; + uint64_t buf_end; if (msg[0] != RDECODE_MESSAGE_CREATE) continue; @@ -1978,7 +1979,8 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (size < 4 || offset + size > end - addr) { + if (size < 4 || check_add_overflow(offset, size, &buf_end) || + buf_end > end - addr) { DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; From 271cd5429513ff9b364a9bf8903e5b65b687eb25 Mon Sep 17 00:00:00 2001 From: Benjamin Cheng Date: Mon, 13 Apr 2026 09:22:15 -0400 Subject: [PATCH 0186/1518] drm/amdgpu/vcn4: Avoid overflow on msg bound check commit 65bce27ea6192320448c30267ffc17ffa094e713 upstream. As pointed out by SDL, the previous condition may be vulnerable to overflow. Fixes: 0a78f2bac142 ("drm/amdgpu/vcn4: Prevent OOB reads when parsing dec msg") Cc: SDL Signed-off-by: Benjamin Cheng Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher (cherry picked from commit 3c5367d950140d4ec7af830b2268a5a6fdaa3885) Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 64f294fb1c7a0..64bda0e944a7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1888,6 +1888,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; + uint64_t buf_end; if (msg[0] != RDECODE_MESSAGE_CREATE) continue; @@ -1895,7 +1896,8 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (size < 4 || offset + size > end - addr) { + if (size < 4 || check_add_overflow(offset, size, &buf_end) || + buf_end > end - addr) { DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; From 52386a7b1beb0a7cb5a304935f73c157109c09ad Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 17 May 2026 17:15:37 +0200 Subject: [PATCH 0187/1518] Linux 6.18.32 Link: https://lore.kernel.org/r/20260515154657.309489048@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Pavel Machek (CIP) Tested-by: Shuah Khan Tested-by: Miguel Ojeda Tested-by: Mark Brown Tested-by: Brett A C Sheffield Link: https://lore.kernel.org/r/20260516102236.209957148@linuxfoundation.org Tested-by: Brett A C Sheffield Tested-by: Ron Economos Tested-by: Peter Schneider Tested-by: Miguel Ojeda Tested-by: Wentao Guan Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 89c614db52409..d1fcec7cf9568 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 31 +SUBLEVEL = 32 EXTRAVERSION = NAME = Baby Opossum Posse From 93383b66810740eb27fab1b31728beb0cb75c1dd Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 11 Mar 2026 11:28:37 +0800 Subject: [PATCH 0188/1518] blk-cgroup: wait for blkcg cleanup before initializing new disk [ Upstream commit 3dbaacf6ab68f81e3375fe769a2ecdbd3ce386fd ] When a queue is shared across disk rebind (e.g., SCSI unbind/bind), the previous disk's blkcg state is cleaned up asynchronously via disk_release() -> blkcg_exit_disk(). If the new disk's blkcg_init_disk() runs before that cleanup finishes, we may overwrite q->root_blkg while the old one is still alive, and radix_tree_insert() in blkg_create() fails with -EEXIST because the old blkg entries still occupy the same queue id slot in blkcg->blkg_tree. This causes the sd probe to fail with -ENOMEM. Fix it by waiting in blkcg_init_disk() for root_blkg to become NULL, which indicates the previous disk's blkcg cleanup has completed. Fixes: 1059699f87eb ("block: move blkcg initialization/destroy into disk allocation/release handler") Cc: Yi Zhang Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260311032837.2368714-1-ming.lei@redhat.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-cgroup.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 3cffb68ba5d87..890c161bee25e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -611,6 +612,8 @@ static void blkg_destroy_all(struct gendisk *disk) q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); + + wake_up_var(&q->root_blkg); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) @@ -1498,6 +1501,18 @@ int blkcg_init_disk(struct gendisk *disk) struct blkcg_gq *new_blkg, *blkg; bool preloaded; + /* + * If the queue is shared across disk rebind (e.g., SCSI), the + * previous disk's blkcg state is cleaned up asynchronously via + * disk_release() -> blkcg_exit_disk(). Wait for that cleanup to + * finish (indicated by root_blkg becoming NULL) before setting up + * new blkcg state. Otherwise, we may overwrite q->root_blkg while + * the old one is still alive, and radix_tree_insert() in + * blkg_create() will fail with -EEXIST because the old entries + * still occupy the same queue id slot in blkcg->blkg_tree. + */ + wait_var_event(&q->root_blkg, !READ_ONCE(q->root_blkg)); + new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; From 6561afc38398e3518a29c5eebb975c30468f98a6 Mon Sep 17 00:00:00 2001 From: HyungJung Joo Date: Tue, 17 Mar 2026 14:48:27 +0900 Subject: [PATCH 0189/1518] fs/omfs: reject s_sys_blocksize smaller than OMFS_DIR_START [ Upstream commit 0621c385fda1376e967f37ccd534c26c3e511d14 ] omfs_fill_super() rejects oversized s_sys_blocksize values (> PAGE_SIZE), but it does not reject values smaller than OMFS_DIR_START (0x1b8 = 440). Later, omfs_make_empty() uses sbi->s_sys_blocksize - OMFS_DIR_START as the length argument to memset(). Since s_sys_blocksize is u32, a crafted filesystem image with s_sys_blocksize < OMFS_DIR_START causes an unsigned underflow there, wrapping to a value near 2^32. That drives a ~4 GiB memset() from bh->b_data + OMFS_DIR_START and overwrites kernel memory far beyond the backing block buffer. Add the corresponding lower-bound check alongside the existing upper-bound check in omfs_fill_super(), so that malformed images are rejected during superblock validation before any filesystem data is processed. Fixes: a3ab7155ea21 ("omfs: add directory routines") Signed-off-by: Hyungjung Joo Link: https://patch.msgid.link/20260317054827.1822061-1-jhj140711@gmail.com Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/omfs/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 135c49c5d848c..31218d89b7580 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -512,6 +512,12 @@ static int omfs_fill_super(struct super_block *sb, struct fs_context *fc) goto out_brelse_bh; } + if (sbi->s_sys_blocksize < OMFS_DIR_START) { + printk(KERN_ERR "omfs: sysblock size (%d) is too small\n", + sbi->s_sys_blocksize); + goto out_brelse_bh; + } + if (sbi->s_blocksize < sbi->s_sys_blocksize || sbi->s_blocksize > OMFS_MAX_BLOCK_SIZE) { printk(KERN_ERR "omfs: block size (%d) is out of range\n", From 0e4eff315d799f5842b95872199b0f0fb8ef5f51 Mon Sep 17 00:00:00 2001 From: HyungJung Joo Date: Tue, 17 Mar 2026 14:45:56 +0900 Subject: [PATCH 0190/1518] fs/mbcache: cancel shrink work before destroying the cache [ Upstream commit d227786ab1119669df4dc333a61510c52047cce4 ] mb_cache_destroy() calls shrinker_free() and then frees all cache entries and the cache itself, but it does not cancel the pending c_shrink_work work item first. If mb_cache_entry_create() schedules c_shrink_work via schedule_work() and the work item is still pending or running when mb_cache_destroy() runs, mb_cache_shrink_worker() will access the cache after its memory has been freed, causing a use-after-free. This is only reachable by a privileged user (root or CAP_SYS_ADMIN) who can trigger the last put of a mounted ext2/ext4/ocfs2 filesystem. Cancel the work item with cancel_work_sync() before calling shrinker_free(), ensuring the worker has finished and will not be rescheduled before the cache is torn down. Fixes: c2f3140fe2ec ("mbcache2: limit cache size") Signed-off-by: Hyungjung Joo Link: https://patch.msgid.link/20260317054556.1821600-1-jhj140711@gmail.com Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/mbcache.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/mbcache.c b/fs/mbcache.c index e60a840999aa9..90b0564c62d0b 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -408,6 +408,7 @@ void mb_cache_destroy(struct mb_cache *cache) { struct mb_cache_entry *entry, *next; + cancel_work_sync(&cache->c_shrink_work); shrinker_free(cache->c_shrink); /* From c3ec2db64bfe690f29fb0019e193803ff0334852 Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Thu, 5 Mar 2026 09:18:33 +0800 Subject: [PATCH 0191/1518] md/raid1: fix the comparing region of interval tree [ Upstream commit de3544d2e5ea99064498de3c21ba490155864657 ] Interval tree uses [start, end] as a region which stores in the tree. In raid1, it uses the wrong end value. For example: bio(A,B) is too big and needs to be split to bio1(A,C-1), bio2(C,B). The region of bio1 is [A,C] and the region of bio2 is [C,B]. So bio1 and bio2 overlap which is not right. Fix this problem by using right end value of the region. Fixes: d0d2d8ba0494 ("md/raid1: introduce wait_for_serialization") Signed-off-by: Xiao Ni Link: https://lore.kernel.org/linux-raid/20260305011839.5118-2-xni@redhat.com/ Signed-off-by: Yu Kuai Signed-off-by: Sasha Levin --- drivers/md/raid1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ce7fd68869566..84dbf801e9b1b 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -62,7 +62,7 @@ static int check_and_add_serial(struct md_rdev *rdev, struct r1bio *r1_bio, unsigned long flags; int ret = 0; sector_t lo = r1_bio->sector; - sector_t hi = lo + r1_bio->sectors; + sector_t hi = lo + r1_bio->sectors - 1; struct serial_in_rdev *serial = &rdev->serial[idx]; spin_lock_irqsave(&serial->serial_lock, flags); @@ -453,7 +453,7 @@ static void raid1_end_write_request(struct bio *bio) int mirror = find_bio_disk(r1_bio, bio); struct md_rdev *rdev = conf->mirrors[mirror].rdev; sector_t lo = r1_bio->sector; - sector_t hi = r1_bio->sector + r1_bio->sectors; + sector_t hi = r1_bio->sector + r1_bio->sectors - 1; bool ignore_error = !raid1_should_handle_error(bio) || (bio->bi_status && bio_op(bio) == REQ_OP_DISCARD); From 996d279f2c985d771d6cfdd923e447d825726e06 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 26 Mar 2026 14:40:54 -0700 Subject: [PATCH 0192/1518] drbd: Balance RCU calls in drbd_adm_dump_devices() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2b31e86387e60b3689339f0f0fbb4d3623d9d494 ] Make drbd_adm_dump_devices() call rcu_read_lock() before rcu_read_unlock() is called. This has been detected by the Clang thread-safety analyzer. Tested-by: Christoph Böhmwalder Reviewed-by: Christoph Hellwig Cc: Andreas Gruenbacher Fixes: a55bbd375d18 ("drbd: Backport the "status" command") Signed-off-by: Bart Van Assche Link: https://patch.msgid.link/20260326214054.284593-1-bvanassche@acm.org Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/drbd/drbd_nl.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index b502038be0a92..0ddbf71286a91 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -3378,8 +3378,10 @@ int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) if (resource_filter) { retcode = ERR_RES_NOT_KNOWN; resource = drbd_find_resource(nla_data(resource_filter)); - if (!resource) + if (!resource) { + rcu_read_lock(); goto put_result; + } cb->args[0] = (long)resource; } } @@ -3628,8 +3630,10 @@ int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb) if (resource_filter) { retcode = ERR_RES_NOT_KNOWN; resource = drbd_find_resource(nla_data(resource_filter)); - if (!resource) + if (!resource) { + rcu_read_lock(); goto put_result; + } } cb->args[0] = (long)resource; } From 37466ec483eadd27dd3000c0900a8aa0e4cf5ebb Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Tue, 31 Mar 2026 10:51:28 +0000 Subject: [PATCH 0193/1518] loop: fix partition scan race between udev and loop_reread_partitions() [ Upstream commit 267ec4d7223a783f029a980f41b93c39b17996da ] When LOOP_CONFIGURE is called with LO_FLAGS_PARTSCAN, the following sequence occurs: 1. disk_force_media_change() sets GD_NEED_PART_SCAN 2. Uevent suppression is lifted and a KOBJ_CHANGE uevent is sent 3. loop_global_unlock() releases the lock 4. loop_reread_partitions() calls bdev_disk_changed() to scan There is a race between steps 2 and 4: when udev receives the uevent and opens the device before loop_reread_partitions() runs, blkdev_get_whole() in bdev.c sees GD_NEED_PART_SCAN set and calls bdev_disk_changed() for a first scan. Then loop_reread_partitions() does a second scan. The open_mutex serializes these two scans, but does not prevent both from running. The second scan in bdev_disk_changed() drops all partition devices from the first scan (via blk_drop_partitions()) before re-adding them, causing partition block devices to briefly disappear. This breaks any systemd unit with BindsTo= on the partition device: systemd observes the device going dead, fails the dependent units, and does not retry them when the device reappears. Fix this by removing the GD_NEED_PART_SCAN set from disk_force_media_change() entirely. None of the current callers need the lazy on-open partition scan triggered by this flag: - floppy: sets GENHD_FL_NO_PART, so disk_has_partscan() is always false and GD_NEED_PART_SCAN has no effect. - loop (loop_configure, loop_change_fd): when LO_FLAGS_PARTSCAN is set, loop_reread_partitions() performs an explicit scan. When not set, GD_SUPPRESS_PART_SCAN prevents the lazy scan path. - loop (__loop_clr_fd): calls bdev_disk_changed() explicitly if LO_FLAGS_PARTSCAN is set. - nbd (nbd_clear_sock_ioctl): capacity is set to zero immediately after; nbd manages GD_NEED_PART_SCAN explicitly elsewhere. With GD_NEED_PART_SCAN no longer set by disk_force_media_change(), udev opening the loop device after the uevent no longer triggers a redundant scan in blkdev_get_whole(), and only the single explicit scan from loop_reread_partitions() runs. A regression test for this bug has been submitted to blktests: https://github.com/linux-blktests/blktests/pull/240. Fixes: 9f65c489b68d ("loop: raise media_change event") Signed-off-by: Daan De Meyer Acked-by: Christian Brauner Link: https://patch.msgid.link/20260331105130.1077599-1-daan@amutable.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/disk-events.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/disk-events.c b/block/disk-events.c index 2f697224386aa..868823915bdc6 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -290,13 +290,14 @@ EXPORT_SYMBOL(disk_check_media_change); * Should be called when the media changes for @disk. Generates a uevent * and attempts to free all dentries and inodes and invalidates all block * device page cache entries in that case. + * + * Callers that need a partition re-scan should arrange for one explicitly. */ void disk_force_media_change(struct gendisk *disk) { disk_event_uevent(disk, DISK_EVENT_MEDIA_CHANGE); inc_diskseq(disk); bdev_mark_dead(disk->part0, true); - set_bit(GD_NEED_PART_SCAN, &disk->state); } EXPORT_SYMBOL_GPL(disk_force_media_change); From e5ff0ba4b6983cdbcc826efc201e7179ece5d46f Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Wed, 1 Apr 2026 02:52:09 +0900 Subject: [PATCH 0194/1518] nilfs2: reject zero bd_oblocknr in nilfs_ioctl_mark_blocks_dirty() [ Upstream commit be3e5d10643d3be1cbac9d9939f220a99253f980 ] nilfs_ioctl_mark_blocks_dirty() uses bd_oblocknr to detect dead blocks by comparing it with the current block number bd_blocknr. If they differ, the block is considered dead and skipped. However, bd_oblocknr should never be 0 since block 0 typically stores the primary superblock and is never a valid GC target block. A corrupted ioctl request with bd_oblocknr set to 0 causes the comparison to incorrectly match when the lookup returns -ENOENT and sets bd_blocknr to 0, bypassing the dead block check and calling nilfs_bmap_mark() on a non-existent block. This causes nilfs_btree_do_lookup() to return -ENOENT, triggering the WARN_ON(ret == -ENOENT). Fix this by rejecting ioctl requests with bd_oblocknr set to 0 at the beginning of each iteration. [ryusuke: slightly modified the commit message and comments for accuracy] Fixes: 7942b919f732 ("nilfs2: ioctl operations") Reported-by: syzbot+98a040252119df0506f8@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=98a040252119df0506f8 Suggested-by: Ryusuke Konishi Signed-off-by: Deepanshu Kartikey Reported-by: syzbot+466a45fcfb0562f5b9a0@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=466a45fcfb0562f5b9a0 Cc: Junjie Cao Signed-off-by: Ryusuke Konishi Signed-off-by: Viacheslav Dubeyko Signed-off-by: Sasha Levin --- fs/nilfs2/ioctl.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 3288c3b4be9ec..7fa02146f1e06 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -736,6 +736,12 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs, int ret, i; for (i = 0; i < nmembs; i++) { + /* + * bd_oblocknr must never be 0 as block 0 + * is never a valid GC target block + */ + if (unlikely(!bdescs[i].bd_oblocknr)) + return -EINVAL; /* XXX: use macro or inline func to check liveness */ ret = nilfs_bmap_lookup_at_level(bmap, bdescs[i].bd_offset, From b3e005f16cd98f815429a87aef4c61e9c140779f Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Tue, 31 Mar 2026 16:50:54 +0800 Subject: [PATCH 0195/1518] blk-cgroup: fix disk reference leak in blkcg_maybe_throttle_current() [ Upstream commit 23308af722fefed00af5f238024c11710938fba3 ] Add the missing put_disk() on the error path in blkcg_maybe_throttle_current(). When blkcg lookup, blkg lookup, or blkg_tryget() fails, the function jumps to the out label which only calls rcu_read_unlock() but does not release the disk reference acquired by blkcg_schedule_throttle() via get_device(). Since current->throttle_disk is already set to NULL before the lookup, blkcg_exit() cannot release this reference either, causing the disk to never be freed. Restore the reference release that was present as blk_put_queue() in the original code but was inadvertently dropped during the conversion from request_queue to gendisk. Fixes: f05837ed73d0 ("blk-cgroup: store a gendisk to throttle in struct task_struct") Signed-off-by: Jackie Liu Acked-by: Tejun Heo Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260331085054.46857-1-liu.yun@linux.dev Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-cgroup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 890c161bee25e..9a8d047be580b 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -2037,6 +2037,7 @@ void blkcg_maybe_throttle_current(void) return; out: rcu_read_unlock(); + put_disk(disk); } /** From 5263ed3dd13b32179cb94247959f3207583520ac Mon Sep 17 00:00:00 2001 From: Cole Leavitt Date: Wed, 25 Feb 2026 16:54:06 -0700 Subject: [PATCH 0196/1518] pstore/ram: fix resource leak when ioremap() fails [ Upstream commit 2ddb69f686ef7a621645e97fc7329c50edf5d0e5 ] In persistent_ram_iomap(), ioremap() or ioremap_wc() may return NULL on failure. Currently, if this happens, the function returns NULL without releasing the memory region acquired by request_mem_region(). This leads to a resource leak where the memory region remains reserved but unusable. Additionally, the caller persistent_ram_buffer_map() handles NULL correctly by returning -ENOMEM, but without this check, a NULL return combined with request_mem_region() succeeding leaves resources in an inconsistent state. This is the ioremap() counterpart to commit 05363abc7625 ("pstore: ram_core: fix incorrect success return when vmap() fails") which fixed a similar issue in the vmap() path. Fixes: 404a6043385d ("staging: android: persistent_ram: handle reserving and mapping memory") Signed-off-by: Cole Leavitt Link: https://patch.msgid.link/20260225235406.11790-1-cole@unwrap.rs Signed-off-by: Kees Cook Signed-off-by: Sasha Levin --- fs/pstore/ram_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 7b6d6378a3b87..95675d4bab141 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -489,6 +489,10 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size, else va = ioremap_wc(start, size); + /* We must release the mem region if ioremap fails. */ + if (!va) + release_mem_region(start, size); + /* * Since request_mem_region() and ioremap() are byte-granularity * there is no need handle anything special like we do when the From 46194b5ba93b7cf9d1409baa202239ff044ec852 Mon Sep 17 00:00:00 2001 From: Zhan Xusheng Date: Wed, 1 Apr 2026 14:13:42 +0800 Subject: [PATCH 0197/1518] erofs: include the trailing NUL in FS_IOC_GETFSLABEL [ Upstream commit d6250d49da4d8f11afc0d8991c84e0307949f92e ] erofs_ioctl_get_volume_label() passes strlen(sbi->volume_name) as the length to copy_to_user(), which copies the label string without the trailing NUL byte. Since FS_IOC_GETFSLABEL callers expect a NUL-terminated string in the FSLABEL_MAX-sized buffer and may not pre-zero the buffer, this can cause userspace to read past the label into uninitialised stack memory. Fix this by using strlen() + 1 to include the NUL terminator, consistent with how ext4 and xfs implement FS_IOC_GETFSLABEL. Signed-off-by: Zhan Xusheng Fixes: 1cf12c717741 ("erofs: Add support for FS_IOC_GETFSLABEL") Reviewed-by: Gao Xiang Reviewed-by: Chunhai Guo Signed-off-by: Gao Xiang Signed-off-by: Sasha Levin --- fs/erofs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index cb780c095d282..218ab22589228 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -348,7 +348,7 @@ static int erofs_ioctl_get_volume_label(struct inode *inode, void __user *arg) ret = clear_user(arg, 1); else ret = copy_to_user(arg, sbi->volume_name, - strlen(sbi->volume_name)); + strlen(sbi->volume_name) + 1); return ret ? -EFAULT : 0; } From 62c44566da7493ee48ef17e8507bb798338a07cb Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 30 Mar 2026 13:52:13 +0800 Subject: [PATCH 0198/1518] md: fix array_state=clear sysfs deadlock [ Upstream commit 2aa72276fab9851dbd59c2daeb4b590c5a113908 ] When "clear" is written to array_state, md_attr_store() breaks sysfs active protection so the array can delete itself from its own sysfs store method. However, md_attr_store() currently drops the mddev reference before calling sysfs_unbreak_active_protection(). Once do_md_stop(..., 0) has made the mddev eligible for delayed deletion, the temporary kobject reference taken by sysfs_break_active_protection() can become the last kobject reference protecting the md kobject. That allows sysfs_unbreak_active_protection() to drop the last kobject reference from the current sysfs writer context. kobject teardown then recurses into kernfs removal while the current sysfs node is still being unwound, and lockdep reports recursive locking on kn->active with kernfs_drain() in the call chain. Reproducer on an existing level: 1. Create an md0 linear array and activate it: mknod /dev/md0 b 9 0 echo none > /sys/block/md0/md/metadata_version echo linear > /sys/block/md0/md/level echo 1 > /sys/block/md0/md/raid_disks echo "$(cat /sys/class/block/sdb/dev)" > /sys/block/md0/md/new_dev echo "$(($(cat /sys/class/block/sdb/size) / 2))" > \ /sys/block/md0/md/dev-sdb/size echo 0 > /sys/block/md0/md/dev-sdb/slot echo active > /sys/block/md0/md/array_state 2. Wait briefly for the array to settle, then clear it: sleep 2 echo clear > /sys/block/md0/md/array_state The warning looks like: WARNING: possible recursive locking detected bash/588 is trying to acquire lock: (kn->active#65) at __kernfs_remove+0x157/0x1d0 but task is already holding lock: (kn->active#65) at sysfs_unbreak_active_protection+0x1f/0x40 ... Call Trace: kernfs_drain __kernfs_remove kernfs_remove_by_name_ns sysfs_remove_group sysfs_remove_groups __kobject_del kobject_put md_attr_store kernfs_fop_write_iter vfs_write ksys_write Restore active protection before mddev_put() so the extra sysfs kobject reference is dropped while the mddev is still held alive. The actual md kobject deletion is then deferred until after the sysfs write path has fully returned. Fixes: 9e59d609763f ("md: call del_gendisk in control path") Reviewed-by: Xiao Ni Link: https://lore.kernel.org/linux-raid/20260330055213.3976052-1-yukuai@fnnas.com/ Signed-off-by: Yu Kuai Signed-off-by: Sasha Levin --- drivers/md/md.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 92ec4be20db85..7560e98dc35b3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6032,10 +6032,16 @@ md_attr_store(struct kobject *kobj, struct attribute *attr, } spin_unlock(&all_mddevs_lock); rv = entry->store(mddev, page, length); - mddev_put(mddev); + /* + * For "array_state=clear", dropping the extra kobject reference from + * sysfs_break_active_protection() can trigger md kobject deletion. + * Restore active protection before mddev_put() so deletion happens + * after the sysfs write path fully unwinds. + */ if (kn) sysfs_unbreak_active_protection(kn); + mddev_put(mddev); return rv; } From d5559ac21f4a0e112a0a18292da51ba5fc402a6f Mon Sep 17 00:00:00 2001 From: Zhan Xusheng Date: Fri, 3 Apr 2026 14:36:58 +0800 Subject: [PATCH 0199/1518] erofs: handle 48-bit blocks/uniaddr for extra devices [ Upstream commit 63c2f06198ca7513433f1c92f2c654869d72417e ] erofs_init_device() only reads blocks_lo and uniaddr_lo from the on-disk device slot, ignoring blocks_hi and uniaddr_hi that were introduced alongside the 48-bit block addressing feature. For the primary device (dif0), erofs_read_superblock() already handles this correctly by combining blocks_lo with blocks_hi when 48-bit layout is enabled. But the same logic was not applied to extra devices. With a 48-bit EROFS image using extra devices whose uniaddr or blocks exceed 32-bit range, the truncated values cause erofs_map_dev() to compute wrong physical addresses, leading to silent data corruption. Fix this by reading blocks_hi and uniaddr_hi in erofs_init_device() when 48-bit layout is enabled, consistent with the primary device handling. Also fix the erofs_deviceslot on-disk definition where blocks_hi was incorrectly declared as __le32 instead of __le16. Fixes: 61ba89b57905 ("erofs: add 48-bit block addressing on-disk support") Suggested-by: Gao Xiang Signed-off-by: Zhan Xusheng Reviewed-by: Gao Xiang Signed-off-by: Gao Xiang Signed-off-by: Sasha Levin --- fs/erofs/erofs_fs.h | 4 ++-- fs/erofs/super.c | 8 ++++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 3d5738f80072e..63efadf75b1c0 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -44,9 +44,9 @@ struct erofs_deviceslot { u8 tag[64]; /* digest(sha256), etc. */ __le32 blocks_lo; /* total blocks count of this device */ __le32 uniaddr_lo; /* unified starting block of this device */ - __le32 blocks_hi; /* total blocks count MSB */ + __le16 blocks_hi; /* total blocks count MSB */ __le16 uniaddr_hi; /* unified starting block MSB */ - u8 reserved[50]; + u8 reserved[52]; }; #define EROFS_DEVT_SLOT_SIZE sizeof(struct erofs_deviceslot) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index ee37628ec99fb..f5f5d19459ecc 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -140,6 +140,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, struct erofs_fscache *fscache; struct erofs_deviceslot *dis; struct file *file; + bool _48bit; dis = erofs_read_metabuf(buf, sb, *pos, false); if (IS_ERR(dis)) @@ -186,8 +187,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, dif->file = file; } - dif->blocks = le32_to_cpu(dis->blocks_lo); - dif->uniaddr = le32_to_cpu(dis->uniaddr_lo); + _48bit = erofs_sb_has_48bit(sbi); + dif->blocks = le32_to_cpu(dis->blocks_lo) | + (_48bit ? (u64)le16_to_cpu(dis->blocks_hi) << 32 : 0); + dif->uniaddr = le32_to_cpu(dis->uniaddr_lo) | + (_48bit ? (u64)le16_to_cpu(dis->uniaddr_hi) << 32 : 0); sbi->total_blocks += dif->blocks; *pos += EROFS_DEVT_SLOT_SIZE; return 0; From 3f1e2902b5ecb821f99fe4c0c6781d93ee1a23cc Mon Sep 17 00:00:00 2001 From: Marco Crivellari Date: Tue, 13 Jan 2026 12:03:02 +0100 Subject: [PATCH 0200/1518] dm: add WQ_PERCPU to alloc_workqueue users MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d4880868670198df321627a949e7b7f2d76cf54e ] This continues the effort to refactor workqueue APIs, which began with the introduction of new workqueues and a new alloc_workqueue flag in: commit 128ea9f6ccfb ("workqueue: Add system_percpu_wq and system_dfl_wq") commit 930c2ea566af ("workqueue: Add new WQ_PERCPU flag") The refactoring is going to alter the default behavior of alloc_workqueue() to be unbound by default. With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND), any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND must now use WQ_PERCPU. For more details see the Link tag below. In order to keep alloc_workqueue() behavior identical, explicitly request WQ_PERCPU. Link: https://lore.kernel.org/all/20250221112003.1dSuoGyc@linutronix.de/ Suggested-by: Tejun Heo Signed-off-by: Marco Crivellari Signed-off-by: Mikulas Patocka Stable-dep-of: e4979f4fac4d ("md: remove unused static md_wq workqueue") Signed-off-by: Sasha Levin --- drivers/md/dm-bufio.c | 3 ++- drivers/md/dm-cache-target.c | 3 ++- drivers/md/dm-clone-target.c | 3 ++- drivers/md/dm-crypt.c | 6 ++++-- drivers/md/dm-delay.c | 4 +++- drivers/md/dm-integrity.c | 15 ++++++++++----- drivers/md/dm-kcopyd.c | 3 ++- drivers/md/dm-log-userspace-base.c | 3 ++- drivers/md/dm-mpath.c | 5 +++-- drivers/md/dm-raid1.c | 5 +++-- drivers/md/dm-snap-persistent.c | 3 ++- drivers/md/dm-stripe.c | 2 +- drivers/md/dm-verity-target.c | 4 +++- drivers/md/dm-writecache.c | 3 ++- drivers/md/dm.c | 3 ++- drivers/md/md.c | 4 ++-- 16 files changed, 45 insertions(+), 24 deletions(-) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 5235f3e4924b7..f41f649c01d4e 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -2833,7 +2833,8 @@ static int __init dm_bufio_init(void) __cache_size_refresh(); mutex_unlock(&dm_bufio_clients_lock); - dm_bufio_wq = alloc_workqueue("dm_bufio_cache", WQ_MEM_RECLAIM, 0); + dm_bufio_wq = alloc_workqueue("dm_bufio_cache", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!dm_bufio_wq) return -ENOMEM; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index a10d75a562db0..7bad7cc87d370 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2533,7 +2533,8 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - cache->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM, 0); + cache->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!cache->wq) { *error = "could not create workqueue for metadata object"; goto bad; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index e956d980672c8..b25845e362744 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1877,7 +1877,8 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv) clone->hydration_offset = 0; atomic_set(&clone->hydrations_in_flight, 0); - clone->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM, 0); + clone->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!clone->wq) { ti->error = "Failed to allocate workqueue"; r = -ENOMEM; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5ef43231fe77f..fd735155336bc 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3441,7 +3441,9 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags)) common_wq_flags |= WQ_HIGHPRI; - cc->io_queue = alloc_workqueue("kcryptd_io-%s-%d", common_wq_flags, 1, devname, wq_id); + cc->io_queue = alloc_workqueue("kcryptd_io-%s-%d", + common_wq_flags | WQ_PERCPU, 1, + devname, wq_id); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; @@ -3449,7 +3451,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) { cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d", - common_wq_flags | WQ_CPU_INTENSIVE, + common_wq_flags | WQ_CPU_INTENSIVE | WQ_PERCPU, 1, devname, wq_id); } else { /* diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 4bb6553278c74..029f04776490a 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -290,7 +290,9 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) } else { timer_setup(&dc->delay_timer, handle_delayed_timer, 0); INIT_WORK(&dc->flush_expired_bios, flush_expired_bios); - dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0); + dc->kdelayd_wq = alloc_workqueue("kdelayd", + WQ_MEM_RECLAIM | WQ_PERCPU, + 0); if (!dc->kdelayd_wq) { ret = -EINVAL; DMERR("Couldn't start kdelayd"); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index ba52631052503..a9c0157bf42fe 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -5003,7 +5003,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv } ic->metadata_wq = alloc_workqueue("dm-integrity-metadata", - WQ_MEM_RECLAIM, METADATA_WORKQUEUE_MAX_ACTIVE); + WQ_MEM_RECLAIM | WQ_PERCPU, + METADATA_WORKQUEUE_MAX_ACTIVE); if (!ic->metadata_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; @@ -5021,7 +5022,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv goto bad; } - ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM, + ic->offload_wq = alloc_workqueue("dm-integrity-offload", + WQ_MEM_RECLAIM | WQ_PERCPU, METADATA_WORKQUEUE_MAX_ACTIVE); if (!ic->offload_wq) { ti->error = "Cannot allocate workqueue"; @@ -5029,7 +5031,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv goto bad; } - ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1); + ic->commit_wq = alloc_workqueue("dm-integrity-commit", + WQ_MEM_RECLAIM | WQ_PERCPU, 1); if (!ic->commit_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; @@ -5038,7 +5041,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv INIT_WORK(&ic->commit_work, integrity_commit); if (ic->mode == 'J' || ic->mode == 'B') { - ic->writer_wq = alloc_workqueue("dm-integrity-writer", WQ_MEM_RECLAIM, 1); + ic->writer_wq = alloc_workqueue("dm-integrity-writer", + WQ_MEM_RECLAIM | WQ_PERCPU, 1); if (!ic->writer_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; @@ -5210,7 +5214,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv } if (ic->internal_hash) { - ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1); + ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", + WQ_MEM_RECLAIM | WQ_PERCPU, 1); if (!ic->recalc_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 6ea75436a433a..cec9a60227b6f 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -934,7 +934,8 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro goto bad_slab; INIT_WORK(&kc->kcopyd_work, do_work); - kc->kcopyd_wq = alloc_workqueue("kcopyd", WQ_MEM_RECLAIM, 0); + kc->kcopyd_wq = alloc_workqueue("kcopyd", WQ_MEM_RECLAIM | WQ_PERCPU, + 0); if (!kc->kcopyd_wq) { r = -ENOMEM; goto bad_workqueue; diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 9fbb4b48fb2bb..607436804a8b2 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -299,7 +299,8 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, } if (lc->integrated_flush) { - lc->dmlog_wq = alloc_workqueue("dmlogd", WQ_MEM_RECLAIM, 0); + lc->dmlog_wq = alloc_workqueue("dmlogd", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!lc->dmlog_wq) { DMERR("couldn't start dmlogd"); r = -ENOMEM; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 7d3fdd96f4edf..00df5be165759 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -2330,7 +2330,8 @@ static int __init dm_multipath_init(void) { int r = -ENOMEM; - kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM, 0); + kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM | WQ_PERCPU, + 0); if (!kmultipathd) { DMERR("failed to create workqueue kmpathd"); goto bad_alloc_kmultipathd; @@ -2349,7 +2350,7 @@ static int __init dm_multipath_init(void) goto bad_alloc_kmpath_handlerd; } - dm_mpath_wq = alloc_workqueue("dm_mpath_wq", 0, 0); + dm_mpath_wq = alloc_workqueue("dm_mpath_wq", WQ_PERCPU, 0); if (!dm_mpath_wq) { DMERR("failed to create workqueue dm_mpath_wq"); goto bad_alloc_dm_mpath_wq; diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index bc8e04f6832a6..d9ec783a37ddc 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1128,7 +1128,8 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->num_discard_bios = 1; ti->per_io_data_size = sizeof(struct dm_raid1_bio_record); - ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_MEM_RECLAIM, 0); + ms->kmirrord_wq = alloc_workqueue("kmirrord", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!ms->kmirrord_wq) { DMERR("couldn't start kmirrord"); r = -ENOMEM; @@ -1500,7 +1501,7 @@ static int __init dm_mirror_init(void) { int r; - dm_raid1_wq = alloc_workqueue("dm_raid1_wq", 0, 0); + dm_raid1_wq = alloc_workqueue("dm_raid1_wq", WQ_PERCPU, 0); if (!dm_raid1_wq) { DMERR("Failed to alloc workqueue"); return -ENOMEM; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 568d10842b1f4..0e13d60bfdd12 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -871,7 +871,8 @@ static int persistent_ctr(struct dm_exception_store *store, char *options) atomic_set(&ps->pending_count, 0); ps->callbacks = NULL; - ps->metadata_wq = alloc_workqueue("ksnaphd", WQ_MEM_RECLAIM, 0); + ps->metadata_wq = alloc_workqueue("ksnaphd", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!ps->metadata_wq) { DMERR("couldn't start header metadata update thread"); r = -ENOMEM; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 1461dc740dae6..1cff9df5b8b47 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -489,7 +489,7 @@ int __init dm_stripe_init(void) { int r; - dm_stripe_wq = alloc_workqueue("dm_stripe_wq", 0, 0); + dm_stripe_wq = alloc_workqueue("dm_stripe_wq", WQ_PERCPU, 0); if (!dm_stripe_wq) return -ENOMEM; r = dm_register_target(&stripe_target); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index c8695c079cfe0..a5cd55b2ba02f 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1549,7 +1549,9 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) * will fall-back to using it for error handling (or if the bufio cache * doesn't have required hashes). */ - v->verify_wq = alloc_workqueue("kverityd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + v->verify_wq = alloc_workqueue("kverityd", + WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, + 0); if (!v->verify_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index d8de4a3076a17..af54e289bcebe 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -2275,7 +2275,8 @@ static int writecache_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - wc->writeback_wq = alloc_workqueue("writecache-writeback", WQ_MEM_RECLAIM, 1); + wc->writeback_wq = alloc_workqueue("writecache-writeback", + WQ_MEM_RECLAIM | WQ_PERCPU, 1); if (!wc->writeback_wq) { r = -ENOMEM; ti->error = "Could not allocate writeback workqueue"; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 52f01c44e73a6..fb6bcd598c5b8 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2363,7 +2363,8 @@ static struct mapped_device *alloc_dev(int minor) format_dev_t(md->name, MKDEV(_major, minor)); - md->wq = alloc_workqueue("kdmflush/%s", WQ_MEM_RECLAIM, 0, md->name); + md->wq = alloc_workqueue("kdmflush/%s", WQ_MEM_RECLAIM | WQ_PERCPU, 0, + md->name); if (!md->wq) goto bad; diff --git a/drivers/md/md.c b/drivers/md/md.c index 7560e98dc35b3..0fc779493fa78 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -10345,11 +10345,11 @@ static int __init md_init(void) goto err_bitmap; ret = -ENOMEM; - md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM, 0); + md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!md_wq) goto err_wq; - md_misc_wq = alloc_workqueue("md_misc", 0, 0); + md_misc_wq = alloc_workqueue("md_misc", WQ_PERCPU, 0); if (!md_misc_wq) goto err_misc_wq; From f8b799e4fd97841ab23cf448fdef30cfd09b2f9d Mon Sep 17 00:00:00 2001 From: Abd-Alrhman Masalkhi Date: Sat, 28 Mar 2026 22:35:22 +0300 Subject: [PATCH 0201/1518] md: remove unused static md_wq workqueue [ Upstream commit e4979f4fac4d6bbe757be50441b45e28e6bf7360 ] The md_wq workqueue is defined as static and initialized in md_init(), but it is not used anywhere within md.c. All asynchronous and deferred work in this file is handled via md_misc_wq or dedicated md threads. Fixes: b75197e86e6d3 ("md: Remove flush handling") Signed-off-by: Abd-Alrhman Masalkhi Link: https://lore.kernel.org/linux-raid/20260328193522.3624-1-abd.masalkhi@gmail.com/ Signed-off-by: Yu Kuai Signed-off-by: Sasha Levin --- drivers/md/md.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0fc779493fa78..0a3152f21d488 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -84,7 +84,6 @@ static DEFINE_XARRAY(md_submodule); static const struct kobj_type md_ktype; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); -static struct workqueue_struct *md_wq; /* * This workqueue is used for sync_work to register new sync_thread, and for @@ -10345,10 +10344,6 @@ static int __init md_init(void) goto err_bitmap; ret = -ENOMEM; - md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM | WQ_PERCPU, 0); - if (!md_wq) - goto err_wq; - md_misc_wq = alloc_workqueue("md_misc", WQ_PERCPU, 0); if (!md_misc_wq) goto err_misc_wq; @@ -10373,8 +10368,6 @@ static int __init md_init(void) err_md: destroy_workqueue(md_misc_wq); err_misc_wq: - destroy_workqueue(md_wq); -err_wq: md_llbitmap_exit(); err_bitmap: md_bitmap_exit(); @@ -10683,7 +10676,6 @@ static __exit void md_exit(void) spin_unlock(&all_mddevs_lock); destroy_workqueue(md_misc_wq); - destroy_workqueue(md_wq); md_bitmap_exit(); } From ff6b93410192b812d73cc54062529715b2dc849f Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 27 Mar 2026 22:07:29 +0800 Subject: [PATCH 0202/1518] md: wake raid456 reshape waiters before suspend [ Upstream commit cf86bb53b9c92354904a328e947a05ffbfdd1840 ] During raid456 reshape, direct IO across the reshape position can sleep in raid5_make_request() waiting for reshape progress while still holding an active_io reference. If userspace then freezes reshape and writes md/suspend_lo or md/suspend_hi, mddev_suspend() kills active_io and waits for all in-flight IO to drain. This can deadlock: the IO needs reshape progress to continue, but the reshape thread is already frozen, so the active_io reference is never dropped and suspend never completes. raid5_prepare_suspend() already wakes wait_for_reshape for dm-raid. Do the same for normal md suspend when reshape is already interrupted, so waiting raid456 IO can abort, drop its reference, and let suspend finish. The mdadm test tests/25raid456-reshape-deadlock reproduces the hang. Fixes: 714d20150ed8 ("md: add new helpers to suspend/resume array") Link: https://lore.kernel.org/linux-raid/20260327140729.2030564-1-yukuai@fnnas.com/ Signed-off-by: Yu Kuai Signed-off-by: Sasha Levin --- drivers/md/md.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0a3152f21d488..b91ac1b7d7a15 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -486,6 +486,17 @@ int mddev_suspend(struct mddev *mddev, bool interruptible) } percpu_ref_kill(&mddev->active_io); + + /* + * RAID456 IO can sleep in wait_for_reshape while still holding an + * active_io reference. If reshape is already interrupted or frozen, + * wake those waiters so they can abort and drop the reference instead + * of deadlocking suspend. + */ + if (mddev->pers && mddev->pers->prepare_suspend && + reshape_interrupted(mddev)) + mddev->pers->prepare_suspend(mddev); + if (interruptible) err = wait_event_interruptible(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); From 9a24f0000876b8755cf21972b41632f4d6f3dafb Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Mar 2026 15:50:13 +0000 Subject: [PATCH 0203/1518] btrfs: fix deadlock between reflink and transaction commit when using flushoncommit [ Upstream commit b48c980b6a7e409050bb3067165db31cc6205e3e ] When using the flushoncommit mount option, we can have a deadlock between a transaction commit and a reflink operation that copied an inline extent to an offset beyond the current i_size of the destination node. The deadlock happens like this: 1) Task A clones an inline extent from inode X to an offset of inode Y that is beyond Y's current i_size. This means we copied the inline extent's data to a folio of inode Y that is beyond its EOF, using a call to copy_inline_to_page(); 2) Task B starts a transaction commit and calls btrfs_start_delalloc_flush() to flush delalloc; 3) The delalloc flushing sees the new dirty folio of inode Y and when it attempts to flush it, it ends up at extent_writepage() and sees that the offset of the folio is beyond the i_size of inode Y, so it attempts to invalidate the folio by calling folio_invalidate(), which ends up at btrfs' folio invalidate callback - btrfs_invalidate_folio(). There it tries to lock the folio's range in inode Y's extent io tree, but it blocks since it's currently locked by task A - during a reflink we lock the inodes and the source and destination ranges after flushing all delalloc and waiting for ordered extent completion - after that we don't expect to have dirty folios in the ranges, the exception is if we have to copy an inline extent's data (because the destination offset is not zero); 4) Task A then attempts to start a transaction to update the inode item, and then it's blocked since the current transaction is in the TRANS_STATE_COMMIT_START state. Therefore task A has to wait for the current transaction to become unblocked (its state >= TRANS_STATE_UNBLOCKED). So task A is waiting for the transaction commit done by task B, and the later waiting on the extent lock of inode Y that is currently held by task A. Syzbot recently reported this with the following stack traces: INFO: task kworker/u8:7:1053 blocked for more than 143 seconds. Not tainted syzkaller #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u8:7 state:D stack:23520 pid:1053 tgid:1053 ppid:2 task_flags:0x4208060 flags:0x00080000 Workqueue: writeback wb_workfn (flush-btrfs-46) Call Trace: context_switch kernel/sched/core.c:5298 [inline] __schedule+0x1553/0x5240 kernel/sched/core.c:6911 __schedule_loop kernel/sched/core.c:6993 [inline] schedule+0x164/0x360 kernel/sched/core.c:7008 wait_extent_bit fs/btrfs/extent-io-tree.c:811 [inline] btrfs_lock_extent_bits+0x59c/0x700 fs/btrfs/extent-io-tree.c:1914 btrfs_lock_extent fs/btrfs/extent-io-tree.h:152 [inline] btrfs_invalidate_folio+0x43d/0xc40 fs/btrfs/inode.c:7704 extent_writepage fs/btrfs/extent_io.c:1852 [inline] extent_write_cache_pages fs/btrfs/extent_io.c:2580 [inline] btrfs_writepages+0x12ff/0x2440 fs/btrfs/extent_io.c:2713 do_writepages+0x32e/0x550 mm/page-writeback.c:2554 __writeback_single_inode+0x133/0x11a0 fs/fs-writeback.c:1750 writeback_sb_inodes+0x995/0x19d0 fs/fs-writeback.c:2042 wb_writeback+0x456/0xb70 fs/fs-writeback.c:2227 wb_do_writeback fs/fs-writeback.c:2374 [inline] wb_workfn+0x41a/0xf60 fs/fs-writeback.c:2414 process_one_work kernel/workqueue.c:3276 [inline] process_scheduled_works+0xb6e/0x18c0 kernel/workqueue.c:3359 worker_thread+0xa53/0xfc0 kernel/workqueue.c:3440 kthread+0x388/0x470 kernel/kthread.c:436 ret_from_fork+0x51e/0xb90 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 INFO: task syz.4.64:6910 blocked for more than 143 seconds. Not tainted syzkaller #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz.4.64 state:D stack:22752 pid:6910 tgid:6905 ppid:5944 task_flags:0x400140 flags:0x00080002 Call Trace: context_switch kernel/sched/core.c:5298 [inline] __schedule+0x1553/0x5240 kernel/sched/core.c:6911 __schedule_loop kernel/sched/core.c:6993 [inline] schedule+0x164/0x360 kernel/sched/core.c:7008 wait_current_trans+0x39f/0x590 fs/btrfs/transaction.c:535 start_transaction+0x6a7/0x1650 fs/btrfs/transaction.c:705 clone_copy_inline_extent fs/btrfs/reflink.c:299 [inline] btrfs_clone+0x128a/0x24d0 fs/btrfs/reflink.c:529 btrfs_clone_files+0x271/0x3f0 fs/btrfs/reflink.c:750 btrfs_remap_file_range+0x76b/0x1320 fs/btrfs/reflink.c:903 vfs_copy_file_range+0xda7/0x1390 fs/read_write.c:1600 __do_sys_copy_file_range fs/read_write.c:1683 [inline] __se_sys_copy_file_range+0x2fb/0x480 fs/read_write.c:1650 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f5f73afc799 RSP: 002b:00007f5f7315e028 EFLAGS: 00000246 ORIG_RAX: 0000000000000146 RAX: ffffffffffffffda RBX: 00007f5f73d75fa0 RCX: 00007f5f73afc799 RDX: 0000000000000005 RSI: 0000000000000000 RDI: 0000000000000005 RBP: 00007f5f73b92c99 R08: 0000000000000863 R09: 0000000000000000 R10: 00002000000000c0 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5f73d76038 R14: 00007f5f73d75fa0 R15: 00007fff138a5068 INFO: task syz.4.64:6975 blocked for more than 143 seconds. Not tainted syzkaller #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz.4.64 state:D stack:24736 pid:6975 tgid:6905 ppid:5944 task_flags:0x400040 flags:0x00080002 Call Trace: context_switch kernel/sched/core.c:5298 [inline] __schedule+0x1553/0x5240 kernel/sched/core.c:6911 __schedule_loop kernel/sched/core.c:6993 [inline] schedule+0x164/0x360 kernel/sched/core.c:7008 wb_wait_for_completion+0x3e8/0x790 fs/fs-writeback.c:227 __writeback_inodes_sb_nr+0x24c/0x2d0 fs/fs-writeback.c:2838 try_to_writeback_inodes_sb+0x9a/0xc0 fs/fs-writeback.c:2886 btrfs_start_delalloc_flush fs/btrfs/transaction.c:2175 [inline] btrfs_commit_transaction+0x82e/0x31a0 fs/btrfs/transaction.c:2364 btrfs_ioctl+0xca7/0xd00 fs/btrfs/ioctl.c:5206 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl+0xff/0x170 fs/ioctl.c:583 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f5f73afc799 RSP: 002b:00007f5f7313d028 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f5f73d76090 RCX: 00007f5f73afc799 RDX: 0000000000000000 RSI: 0000000000009408 RDI: 0000000000000004 RBP: 00007f5f73b92c99 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5f73d76128 R14: 00007f5f73d76090 R15: 00007fff138a5068 Fix this by updating the i_size of the destination inode of a reflink operation after we copy an inline extent's data to an offset beyond the i_size and before attempting to start a transaction to update the inode's item. Reported-by: syzbot+63056bf627663701bbbf@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/69bba3fe.050a0220.227207.002f.GAE@google.com/ Fixes: 05a5a7621ce6 ("Btrfs: implement full reflink support for inline extents") Reviewed-by: Boris Burkov Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/reflink.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 5465a5eae9b2d..614e884c2a9bc 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -321,6 +321,51 @@ static int clone_copy_inline_extent(struct btrfs_inode *inode, ret = copy_inline_to_page(inode, new_key->offset, inline_data, size, datal, comp_type); + + /* + * If we copied the inline extent data to a page/folio beyond the i_size + * of the destination inode, then we need to increase the i_size before + * we start a transaction to update the inode item. This is to prevent a + * deadlock when the flushoncommit mount option is used, which happens + * like this: + * + * 1) Task A clones an inline extent from inode X to an offset of inode + * Y that is beyond Y's current i_size. This means we copied the + * inline extent's data to a folio of inode Y that is beyond its EOF, + * using the call above to copy_inline_to_page(); + * + * 2) Task B starts a transaction commit and calls + * btrfs_start_delalloc_flush() to flush delalloc; + * + * 3) The delalloc flushing sees the new dirty folio of inode Y and when + * it attempts to flush it, it ends up at extent_writepage() and sees + * that the offset of the folio is beyond the i_size of inode Y, so + * it attempts to invalidate the folio by calling folio_invalidate(), + * which ends up at btrfs' folio invalidate callback - + * btrfs_invalidate_folio(). There it tries to lock the folio's range + * in inode Y's extent io tree, but it blocks since it's currently + * locked by task A - during reflink we lock the inodes and the + * source and destination ranges after flushing all delalloc and + * waiting for ordered extent completion - after that we don't expect + * to have dirty folios in the ranges, the exception is if we have to + * copy an inline extent's data (because the destination offset is + * not zero); + * + * 4) Task A then does the 'goto out' below and attempts to start a + * transaction to update the inode item, and then it's blocked since + * the current transaction is in the TRANS_STATE_COMMIT_START state. + * Therefore task A has to wait for the current transaction to become + * unblocked (its state >= TRANS_STATE_UNBLOCKED). + * + * This leads to a deadlock - the task committing the transaction + * waiting for the delalloc flushing which is blocked during folio + * invalidation on the inode's extent lock and the reflink task waiting + * for the current transaction to be unblocked so that it can start a + * a new one to update the inode item (while holding the extent lock). + */ + if (ret == 0 && new_key->offset + datal > i_size_read(&inode->vfs_inode)) + i_size_write(&inode->vfs_inode, new_key->offset + datal); + goto out; } From 7cbabc3411a75fc07faa3755896ee663d7208ed1 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 30 Jan 2026 12:49:40 +0530 Subject: [PATCH 0204/1518] OPP: debugfs: Use performance level if available to distinguish between rates [ Upstream commit e560083c0467f86b72aecac377b27bd1e7d16c49 ] Some OPP tables have entries with same rate and different performance level. For these entries, using only the rate as the debugfs directory name causes below error: debugfs: 'opp:5000000' already exists in 'soc@0-1c00000.pci' Fix it by appending the performance level to the dir name if available. Reported-by: Bjorn Andersson Closes: https://lore.kernel.org/linux-arm-msm/75lzykd37zdvrks5i2bb4zb2yzjtm25kv3hegmikndkbr772mz@w2ykff3ny45u/ Fixes: 05db35963eef ("OPP: Add support to find OPP for a set of keys") Signed-off-by: Manivannan Sadhasivam Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/opp/debugfs.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c index 8fc6238b17284..61506d30d5ff0 100644 --- a/drivers/opp/debugfs.c +++ b/drivers/opp/debugfs.c @@ -130,22 +130,24 @@ void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) { struct dentry *pdentry = opp_table->dentry; struct dentry *d; - unsigned long id; - char name[25]; /* 20 chars for 64 bit value + 5 (opp:\0) */ + char name[36]; /* "opp:"(4) + u64(20) + "-" (1) + u32(10) + NULL(1) */ /* * Get directory name for OPP. * - * - Normally rate is unique to each OPP, use it to get unique opp-name. + * - Normally rate is unique to each OPP, use it to get unique opp-name, + * together with performance level if available. * - For some devices rate isn't available or there are multiple, use * index instead for them. */ - if (likely(opp_table->clk_count == 1 && opp->rates[0])) - id = opp->rates[0]; - else - id = _get_opp_count(opp_table); - - snprintf(name, sizeof(name), "opp:%lu", id); + if (likely(opp_table->clk_count == 1 && opp->rates[0])) { + if (opp->level == OPP_LEVEL_UNSET) + snprintf(name, sizeof(name), "opp:%lu", opp->rates[0]); + else + snprintf(name, sizeof(name), "opp:%lu-%u", opp->rates[0], opp->level); + } else { + snprintf(name, sizeof(name), "opp:%u", _get_opp_count(opp_table)); + } /* Create per-opp directory */ d = debugfs_create_dir(name, pdentry); From 265ab7e7d40d750b40725bea05281f77699cff0d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 23 Feb 2026 11:05:59 +0530 Subject: [PATCH 0205/1518] OPP: Move break out of scoped_guard in dev_pm_opp_xlate_required_opp() [ Upstream commit 3d2398f44a2d48fb1c575a6e0bc6b38f3e689e22 ] The commit ff9c512041f2 ("OPP: Use mutex locking guards") unintentionally made the for loop run longer than required. scoped_guard() is implemented as a for loop. The break statement now breaks out out the scoped_guard() and not out of the outer for loop. The outer loop always iterates to completion. Fix it. Fixes: ff9c512041f2 ("OPP: Use mutex locking guards") Reported-by: David Lechner Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/opp/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 775d4a36f2f54..157c84b689feb 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2741,8 +2741,8 @@ struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, break; } } - break; } + break; } if (IS_ERR(dest_opp)) { From 9f8a61db50a8739126ca247ef06436225651ee6d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 23 Feb 2026 16:28:15 +0100 Subject: [PATCH 0206/1518] ACPI: x86: cmos_rtc: Clean up address space handler driver [ Upstream commit ba0b236736dde4059bdcb8e99beaa50d6e5b6e7e ] Make multiple changes that do not alter functionality to the CMOS RTC ACPI address space handler driver, including the following: - Drop the unused .detach() callback from cmos_rtc_handler. - Rename acpi_cmos_rtc_attach_handler() to acpi_cmos_rtc_attach(). - Rearrange acpi_cmos_rtc_space_handler() to reduce the number of redundant checks and make white space follow the coding style. - Adjust an error message in acpi_install_cmos_rtc_space_handler() and make the white space follow the coding style. - Rearrange acpi_remove_cmos_rtc_space_handler() and adjust an error message in it. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/5094429.31r3eYUQgx@rafael.j.wysocki Stable-dep-of: 6cee29ad9d7e ("ACPI: x86: cmos_rtc: Improve coordination with ACPI TAD driver") Signed-off-by: Sasha Levin --- drivers/acpi/x86/cmos_rtc.c | 61 +++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 29 deletions(-) diff --git a/drivers/acpi/x86/cmos_rtc.c b/drivers/acpi/x86/cmos_rtc.c index 51643ff6fe5fc..977234da9fc11 100644 --- a/drivers/acpi/x86/cmos_rtc.c +++ b/drivers/acpi/x86/cmos_rtc.c @@ -24,31 +24,35 @@ static const struct acpi_device_id acpi_cmos_rtc_ids[] = { {} }; -static acpi_status -acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address, - u32 bits, u64 *value64, - void *handler_context, void *region_context) +static acpi_status acpi_cmos_rtc_space_handler(u32 function, + acpi_physical_address address, + u32 bits, u64 *value64, + void *handler_context, + void *region_context) { - int i; + unsigned int i, bytes = DIV_ROUND_UP(bits, 8); u8 *value = (u8 *)value64; if (address > 0xff || !value64) return AE_BAD_PARAMETER; - if (function != ACPI_WRITE && function != ACPI_READ) - return AE_BAD_PARAMETER; + guard(spinlock_irq)(&rtc_lock); + + if (function == ACPI_WRITE) { + for (i = 0; i < bytes; i++, address++, value++) + CMOS_WRITE(*value, address); - spin_lock_irq(&rtc_lock); + return AE_OK; + } - for (i = 0; i < DIV_ROUND_UP(bits, 8); ++i, ++address, ++value) - if (function == ACPI_READ) + if (function == ACPI_READ) { + for (i = 0; i < bytes; i++, address++, value++) *value = CMOS_READ(address); - else - CMOS_WRITE(*value, address); - spin_unlock_irq(&rtc_lock); + return AE_OK; + } - return AE_OK; + return AE_BAD_PARAMETER; } int acpi_install_cmos_rtc_space_handler(acpi_handle handle) @@ -56,11 +60,11 @@ int acpi_install_cmos_rtc_space_handler(acpi_handle handle) acpi_status status; status = acpi_install_address_space_handler(handle, - ACPI_ADR_SPACE_CMOS, - &acpi_cmos_rtc_space_handler, - NULL, NULL); + ACPI_ADR_SPACE_CMOS, + acpi_cmos_rtc_space_handler, + NULL, NULL); if (ACPI_FAILURE(status)) { - pr_err("Error installing CMOS-RTC region handler\n"); + pr_err("Failed to install CMOS-RTC address space handler\n"); return -ENODEV; } @@ -70,26 +74,25 @@ EXPORT_SYMBOL_GPL(acpi_install_cmos_rtc_space_handler); void acpi_remove_cmos_rtc_space_handler(acpi_handle handle) { - if (ACPI_FAILURE(acpi_remove_address_space_handler(handle, - ACPI_ADR_SPACE_CMOS, &acpi_cmos_rtc_space_handler))) - pr_err("Error removing CMOS-RTC region handler\n"); + acpi_status status; + + status = acpi_remove_address_space_handler(handle, + ACPI_ADR_SPACE_CMOS, + acpi_cmos_rtc_space_handler); + if (ACPI_FAILURE(status)) + pr_err("Failed to remove CMOS-RTC address space handler\n"); } EXPORT_SYMBOL_GPL(acpi_remove_cmos_rtc_space_handler); -static int acpi_cmos_rtc_attach_handler(struct acpi_device *adev, const struct acpi_device_id *id) +static int acpi_cmos_rtc_attach(struct acpi_device *adev, + const struct acpi_device_id *id) { return acpi_install_cmos_rtc_space_handler(adev->handle); } -static void acpi_cmos_rtc_detach_handler(struct acpi_device *adev) -{ - acpi_remove_cmos_rtc_space_handler(adev->handle); -} - static struct acpi_scan_handler cmos_rtc_handler = { .ids = acpi_cmos_rtc_ids, - .attach = acpi_cmos_rtc_attach_handler, - .detach = acpi_cmos_rtc_detach_handler, + .attach = acpi_cmos_rtc_attach, }; void __init acpi_cmos_rtc_init(void) From ae04d2e67f9ac2106f2f97a4f4b922ce7f9bcb46 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 23 Feb 2026 16:28:57 +0100 Subject: [PATCH 0207/1518] ACPI: x86: cmos_rtc: Improve coordination with ACPI TAD driver [ Upstream commit 6cee29ad9d7e400d39ae0b1a54447fedcb62eecd ] If a CMOS RTC (PNP0B00/PNP0B01/PNP0B02) device coexists with an ACPI TAD (timer and event alarm device, ACPI000E), the ACPI TAD driver will attempt to install the CMOS RTC address space hanlder that has been installed already and the TAD probing will fail. Avoid that by changing acpi_install_cmos_rtc_space_handler() to return zero and acpi_remove_cmos_rtc_space_handler() to do nothing if the CMOS RTC address space handler has been installed already. Fixes: 596ca52a56da ("ACPI: TAD: Install SystemCMOS address space handler for ACPI000E") Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/2415111.ElGaqSPkdT@rafael.j.wysocki Signed-off-by: Sasha Levin --- drivers/acpi/x86/cmos_rtc.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/x86/cmos_rtc.c b/drivers/acpi/x86/cmos_rtc.c index 977234da9fc11..45db7e51cbe60 100644 --- a/drivers/acpi/x86/cmos_rtc.c +++ b/drivers/acpi/x86/cmos_rtc.c @@ -24,6 +24,8 @@ static const struct acpi_device_id acpi_cmos_rtc_ids[] = { {} }; +static bool cmos_rtc_space_handler_present __read_mostly; + static acpi_status acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address, u32 bits, u64 *value64, @@ -59,6 +61,9 @@ int acpi_install_cmos_rtc_space_handler(acpi_handle handle) { acpi_status status; + if (cmos_rtc_space_handler_present) + return 0; + status = acpi_install_address_space_handler(handle, ACPI_ADR_SPACE_CMOS, acpi_cmos_rtc_space_handler, @@ -68,6 +73,8 @@ int acpi_install_cmos_rtc_space_handler(acpi_handle handle) return -ENODEV; } + cmos_rtc_space_handler_present = true; + return 1; } EXPORT_SYMBOL_GPL(acpi_install_cmos_rtc_space_handler); @@ -76,6 +83,9 @@ void acpi_remove_cmos_rtc_space_handler(acpi_handle handle) { acpi_status status; + if (cmos_rtc_space_handler_present) + return; + status = acpi_remove_address_space_handler(handle, ACPI_ADR_SPACE_CMOS, acpi_cmos_rtc_space_handler); @@ -87,7 +97,13 @@ EXPORT_SYMBOL_GPL(acpi_remove_cmos_rtc_space_handler); static int acpi_cmos_rtc_attach(struct acpi_device *adev, const struct acpi_device_id *id) { - return acpi_install_cmos_rtc_space_handler(adev->handle); + int ret; + + ret = acpi_install_cmos_rtc_space_handler(adev->handle); + if (ret < 0) + return ret; + + return 1; } static struct acpi_scan_handler cmos_rtc_handler = { From 01cdbf3dcf89a56362260141d39ce2d93af0939b Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 3 Feb 2026 00:48:14 +0100 Subject: [PATCH 0208/1518] devres: fix missing node debug info in devm_krealloc() [ Upstream commit f813ec9e84b4d0ca81ec1da94ab07bfb4a29266c ] Fix missing call to set_node_dbginfo() for new devres nodes created by devm_krealloc(). Fixes: f82485722e5d ("devres: provide devm_krealloc()") Reviewed-by: Greg Kroah-Hartman Link: https://patch.msgid.link/20260202235210.55176-2-dakr@kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/base/devres.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index c948c88d39560..9893d656302d9 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -940,6 +940,8 @@ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp) if (!new_dr) return NULL; + set_node_dbginfo(&new_dr->node, "devm_krealloc_release", new_size); + /* * The spinlock protects the linked list against concurrent * modifications but not the resource itself. From 5b4604cd5a9dc65a64904417c16b9933f7dfee84 Mon Sep 17 00:00:00 2001 From: Gopi Krishna Menon Date: Fri, 27 Mar 2026 14:35:24 +0530 Subject: [PATCH 0209/1518] thermal/drivers/spear: Fix error condition for reading st,thermal-flags [ Upstream commit da2c4f332a0504d9c284e7626a561d343c8d6f57 ] of_property_read_u32 returns 0 on success. The current check returns -EINVAL if the property is read successfully. Fix the check by removing ! from of_property_read_u32 Fixes: b9c7aff481f1 ("drivers/thermal/spear_thermal.c: add Device Tree probing capability") Signed-off-by: Gopi Krishna Menon Signed-off-by: Daniel Lezcano Suggested-by: Daniel Baluta Reviewed-by: Lukasz Luba Link: https://patch.msgid.link/20260327090526.59330-1-krishnagopi487@gmail.com Signed-off-by: Sasha Levin --- drivers/thermal/spear_thermal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c index 603dadcd3df58..5e3e9c1f32f8e 100644 --- a/drivers/thermal/spear_thermal.c +++ b/drivers/thermal/spear_thermal.c @@ -93,7 +93,7 @@ static int spear_thermal_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret = 0, val; - if (!np || !of_property_read_u32(np, "st,thermal-flags", &val)) { + if (!np || of_property_read_u32(np, "st,thermal-flags", &val)) { dev_err(&pdev->dev, "Failed: DT Pdata not passed\n"); return -EINVAL; } From 172b40b1468eccc9e45aa4c4acf8603f9fc6c709 Mon Sep 17 00:00:00 2001 From: Gui-Dong Han Date: Mon, 23 Mar 2026 16:58:44 +0800 Subject: [PATCH 0210/1518] debugfs: check for NULL pointer in debugfs_create_str() [ Upstream commit 31de83980d3764d784f79ff1bc93c42b324f4013 ] Passing a NULL pointer to debugfs_create_str() leads to a NULL pointer dereference when the debugfs file is read. Following upstream discussions, forbid the creation of debugfs string files with NULL pointers. Add a WARN_ON() to expose offending callers and return early. Fixes: 9af0440ec86e ("debugfs: Implement debugfs_create_str()") Reported-by: yangshiguang Closes: https://lore.kernel.org/lkml/2025122221-gag-malt-75ba@gregkh/ Suggested-by: Greg Kroah-Hartman Signed-off-by: Gui-Dong Han Link: https://patch.msgid.link/20260323085930.88894-2-hanguidong02@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- fs/debugfs/file.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 3ec3324c20603..252fca572eb76 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -1127,7 +1127,7 @@ static const struct file_operations fops_str_wo = { * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write - * from. + * from. This pointer and the string it points to must not be %NULL. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so @@ -1136,6 +1136,9 @@ static const struct file_operations fops_str_wo = { void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, char **value) { + if (WARN_ON(!value || !*value)) + return; + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str, &fops_str_ro, &fops_str_wo); } From bfe63c16fefb39bab8f67bfeecb14ceb75a8621a Mon Sep 17 00:00:00 2001 From: Gui-Dong Han Date: Mon, 23 Mar 2026 16:58:45 +0800 Subject: [PATCH 0211/1518] debugfs: fix placement of EXPORT_SYMBOL_GPL for debugfs_create_str() [ Upstream commit 4afc929c0f74c4f22b055a82b371d50586da58ca ] The EXPORT_SYMBOL_GPL() for debugfs_create_str was placed incorrectly away from the function definition. Move it immediately below the debugfs_create_str() function where it belongs. Fixes: d60b59b96795 ("debugfs: Export debugfs_create_str symbol") Signed-off-by: Gui-Dong Han Link: https://patch.msgid.link/20260323085930.88894-3-hanguidong02@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- fs/debugfs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 252fca572eb76..880a8a9deacfe 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -1047,7 +1047,6 @@ ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, return ret; } -EXPORT_SYMBOL_GPL(debugfs_create_str); static ssize_t debugfs_write_file_str(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) @@ -1142,6 +1141,7 @@ void debugfs_create_str(const char *name, umode_t mode, debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str, &fops_str_ro, &fops_str_wo); } +EXPORT_SYMBOL_GPL(debugfs_create_str); static ssize_t read_file_blob(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) From 187c8be0c48fb803ac1579d3b7962afc2e7e81f6 Mon Sep 17 00:00:00 2001 From: Gui-Dong Han Date: Mon, 23 Mar 2026 16:58:46 +0800 Subject: [PATCH 0212/1518] soundwire: debugfs: initialize firmware_file to empty string [ Upstream commit 7215e4552f31e53595eae56a834f7e286beecccc ] Passing NULL to debugfs_create_str() causes a NULL pointer dereference, and creating debugfs nodes with NULL string pointers is no longer permitted. Additionally, firmware_file is a global pointer. Previously, adding every new slave blindly overwrote it with NULL. Fix these issues by initializing firmware_file to an allocated empty string once in the subsystem init path (sdw_debugfs_init), and freeing it in the exit path. Existing driver code handles empty strings correctly. Fixes: fe46d2a4301d ("soundwire: debugfs: add interface to read/write commands") Reported-by: yangshiguang Closes: https://lore.kernel.org/lkml/17647e4c.d461.19b46144a4e.Coremail.yangshiguang1011@163.com/ Signed-off-by: Gui-Dong Han Link: https://patch.msgid.link/20260323085930.88894-4-hanguidong02@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/soundwire/debugfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/debugfs.c b/drivers/soundwire/debugfs.c index 1e0f9318b6165..feb4d15102753 100644 --- a/drivers/soundwire/debugfs.c +++ b/drivers/soundwire/debugfs.c @@ -350,8 +350,8 @@ void sdw_slave_debugfs_init(struct sdw_slave *slave) debugfs_create_file("go", 0200, d, slave, &cmd_go_fops); debugfs_create_file("read_buffer", 0400, d, slave, &read_buffer_fops); - firmware_file = NULL; - debugfs_create_str("firmware_file", 0200, d, &firmware_file); + if (firmware_file) + debugfs_create_str("firmware_file", 0200, d, &firmware_file); slave->debugfs = d; } @@ -363,10 +363,15 @@ void sdw_slave_debugfs_exit(struct sdw_slave *slave) void sdw_debugfs_init(void) { + if (!firmware_file) + firmware_file = kstrdup("", GFP_KERNEL); + sdw_debugfs_root = debugfs_create_dir("soundwire", NULL); } void sdw_debugfs_exit(void) { debugfs_remove_recursive(sdw_debugfs_root); + kfree(firmware_file); + firmware_file = NULL; } From 539aabbab190825c77eb455ec35652cb3720625f Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Thu, 26 Mar 2026 17:17:45 +0530 Subject: [PATCH 0213/1518] amd-pstate: Fix memory leak in amd_pstate_epp_cpu_init() [ Upstream commit beda3b363546a423e4e29a7395e04c0ac4ff677e ] On failure to set the epp, the function amd_pstate_epp_cpu_init() returns with an error code without freeing the cpudata object that was allocated at the beginning of the function. Ensure that the cpudata object is freed before returning from the function. This memory leak was discovered by Claude Opus 4.6 with the aid of Chris Mason's AI review-prompts (https://github.com/masoncl/review-prompts/tree/main/kernel). Assisted-by: Claude:claude-opus-4.6 review-prompts/linux Fixes: f9a378ff6443 ("cpufreq/amd-pstate: Set different default EPP policy for Epyc and Ryzen") Reviewed-by: Mario Limonciello (AMD) Signed-off-by: Gautham R. Shenoy Signed-off-by: Mario Limonciello (AMD) Signed-off-by: Sasha Levin --- drivers/cpufreq/amd-pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 602e4fa81d6c5..86d8762ac82c5 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1525,7 +1525,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) ret = amd_pstate_set_epp(policy, cpudata->epp_default); if (ret) - return ret; + goto free_cpudata1; current_pstate_driver->adjust_perf = NULL; From e6210630b24e1255de213333404d5cc1d87aaada Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Thu, 26 Mar 2026 17:17:46 +0530 Subject: [PATCH 0214/1518] amd-pstate: Update cppc_req_cached in fast_switch case [ Upstream commit fcc25a291fbdca2c06c2c6602532050873f0c9de ] The function msr_update_perf() does not cache the new value that is written to MSR_AMD_CPPC_REQ into the variable cpudata->cppc_req_cached when the update is happening from the fast path. Fix that by caching the value everytime the MSR_AMD_CPPC_REQ gets updated. This issue was discovered by Claude Opus 4.6 with the aid of Chris Mason's AI review-prompts (https://github.com/masoncl/review-prompts/tree/main/kernel). Assisted-by: Claude:claude-opus-4.6 review-prompts/linux Reviewed-by: Mario Limonciello (AMD) Fixes: fff395796917 ("cpufreq/amd-pstate: Always write EPP value when updating perf") Signed-off-by: Gautham R. Shenoy Signed-off-by: Mario Limonciello (AMD) Signed-off-by: Sasha Levin --- drivers/cpufreq/amd-pstate.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 86d8762ac82c5..39681ad1606f6 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -259,7 +259,6 @@ static int msr_update_perf(struct cpufreq_policy *policy, u8 min_perf, if (fast_switch) { wrmsrq(MSR_AMD_CPPC_REQ, value); - return 0; } else { int ret = wrmsrq_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value); From e52830bf37a2f2d972f33ffd1feaa243e40956b8 Mon Sep 17 00:00:00 2001 From: K Prateek Nayak Date: Mon, 16 Mar 2026 08:18:49 +0000 Subject: [PATCH 0215/1518] cpufreq: Pass the policy to cpufreq_driver->adjust_perf() [ Upstream commit c03791085adcd61fa9b766ab303c7d0941d7378d ] cpufreq_cpu_get() can sleep on PREEMPT_RT in presence of concurrent writer(s), however amd-pstate depends on fetching the cpudata via the policy's driver data which necessitates grabbing the reference. Since schedutil governor can call "cpufreq_driver->update_perf()" during sched_tick/enqueue/dequeue with rq_lock held and IRQs disabled, fetching the policy object using the cpufreq_cpu_get() helper in the scheduler fast-path leads to "BUG: scheduling while atomic" on PREEMPT_RT [1]. Pass the cached cpufreq policy object in sg_policy to the update_perf() instead of just the CPU. The CPU can be inferred using "policy->cpu". The lifetime of cpufreq_policy object outlasts that of the governor and the cpufreq driver (allocated when the CPU is onlined and only reclaimed when the CPU is offlined / the CPU device is removed) which makes it safe to be referenced throughout the governor's lifetime. Closes:https://lore.kernel.org/all/20250731092316.3191-1-spasswolf@web.de/ [1] Fixes: 1d215f0319c2 ("cpufreq: amd-pstate: Add fast switch function for AMD P-State") Reported-by: Bert Karwatzki Acked-by: Viresh Kumar Signed-off-by: K Prateek Nayak Acked-by: Gary Guo # Rust Reviewed-by: Gautham R. Shenoy Reviewed-by: Zhongqiu Han Link: https://lore.kernel.org/r/20260316081849.19368-3-kprateek.nayak@amd.com Signed-off-by: Mario Limonciello (AMD) Signed-off-by: Sasha Levin --- drivers/cpufreq/amd-pstate.c | 3 +-- drivers/cpufreq/cpufreq.c | 6 +++--- drivers/cpufreq/intel_pstate.c | 4 ++-- include/linux/cpufreq.h | 4 ++-- kernel/sched/cpufreq_schedutil.c | 5 +++-- rust/kernel/cpufreq.rs | 13 ++++++------- 6 files changed, 17 insertions(+), 18 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 39681ad1606f6..ce6d6b3ff58a3 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -697,13 +697,12 @@ static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy, return policy->cur; } -static void amd_pstate_adjust_perf(unsigned int cpu, +static void amd_pstate_adjust_perf(struct cpufreq_policy *policy, unsigned long _min_perf, unsigned long target_perf, unsigned long capacity) { u8 max_perf, min_perf, des_perf, cap_perf; - struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); struct amd_cpudata *cpudata; union perf_cached perf; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 852e024facc3c..1ed528e34bab4 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2222,7 +2222,7 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); /** * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go. - * @cpu: Target CPU. + * @policy: cpufreq policy object of the target CPU. * @min_perf: Minimum (required) performance level (units of @capacity). * @target_perf: Target (desired) performance level (units of @capacity). * @capacity: Capacity of the target CPU. @@ -2241,12 +2241,12 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); * parallel with either ->target() or ->target_index() or ->fast_switch() for * the same CPU. */ -void cpufreq_driver_adjust_perf(unsigned int cpu, +void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy, unsigned long min_perf, unsigned long target_perf, unsigned long capacity) { - cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity); + cpufreq_driver->adjust_perf(policy, min_perf, target_perf, capacity); } /** diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 5efda8af4b708..eb7fb25dfbefc 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3270,12 +3270,12 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, return target_pstate * cpu->pstate.scaling; } -static void intel_cpufreq_adjust_perf(unsigned int cpunum, +static void intel_cpufreq_adjust_perf(struct cpufreq_policy *policy, unsigned long min_perf, unsigned long target_perf, unsigned long capacity) { - struct cpudata *cpu = all_cpu_data[cpunum]; + struct cpudata *cpu = all_cpu_data[policy->cpu]; u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached); int old_pstate = cpu->pstate.current_pstate; int cap_pstate, min_pstate, max_pstate, target_pstate; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 0465d1e6f72ac..fd26b3a4aa286 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,7 +367,7 @@ struct cpufreq_driver { * conditions) scale invariance can be disabled, which causes the * schedutil governor to fall back to the latter. */ - void (*adjust_perf)(unsigned int cpu, + void (*adjust_perf)(struct cpufreq_policy *policy, unsigned long min_perf, unsigned long target_perf, unsigned long capacity); @@ -612,7 +612,7 @@ struct cpufreq_governor { /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); -void cpufreq_driver_adjust_perf(unsigned int cpu, +void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy, unsigned long min_perf, unsigned long target_perf, unsigned long capacity); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 0ab5f9d4bc59a..307f3076635eb 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -461,6 +461,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, unsigned int flags) { struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); + struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long prev_util = sg_cpu->util; unsigned long max_cap; @@ -482,10 +483,10 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, if (sugov_hold_freq(sg_cpu) && sg_cpu->util < prev_util) sg_cpu->util = prev_util; - cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min, + cpufreq_driver_adjust_perf(sg_policy->policy, sg_cpu->bw_min, sg_cpu->util, max_cap); - sg_cpu->sg_policy->last_freq_update_time = time; + sg_policy->last_freq_update_time = time; } static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs index df5d9f6f43f3b..19729ccb3f6d2 100644 --- a/rust/kernel/cpufreq.rs +++ b/rust/kernel/cpufreq.rs @@ -1257,18 +1257,17 @@ impl Registration { /// # Safety /// /// - This function may only be called from the cpufreq C infrastructure. + /// - The pointer arguments must be valid pointers. unsafe extern "C" fn adjust_perf_callback( - cpu: c_uint, + ptr: *mut bindings::cpufreq_policy, min_perf: c_ulong, target_perf: c_ulong, capacity: c_ulong, ) { - // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number. - let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) }; - - if let Ok(mut policy) = PolicyCpu::from_cpu(cpu_id) { - T::adjust_perf(&mut policy, min_perf, target_perf, capacity); - } + // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the + // lifetime of `policy`. + let policy = unsafe { Policy::from_raw_mut(ptr) }; + T::adjust_perf(policy, min_perf, target_perf, capacity); } /// Driver's `get_intermediate` callback. From 58a42be0d70307d765594fc581f5f5e5ef059712 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 24 Mar 2026 01:59:09 +0100 Subject: [PATCH 0216/1518] PCI: use generic driver_override infrastructure [ Upstream commit 10a4206a24013be4d558d476010cbf2eb4c9fa64 ] When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Reported-by: Gui-Dong Han Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789 Fixes: 782a985d7af2 ("PCI: Introduce new device binding path using pci_dev.driver_override") Acked-by: Bjorn Helgaas Acked-by: Alex Williamson Tested-by: Gui-Dong Han Reviewed-by: Gui-Dong Han Link: https://patch.msgid.link/20260324005919.2408620-6-dakr@kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/pci/pci-driver.c | 11 +++++++---- drivers/pci/pci-sysfs.c | 28 ---------------------------- drivers/pci/probe.c | 1 - drivers/vfio/pci/vfio_pci_core.c | 5 ++--- drivers/xen/xen-pciback/pci_stub.c | 6 ++++-- include/linux/pci.h | 6 ------ 6 files changed, 13 insertions(+), 44 deletions(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index b4111c92c9572..fba07a700508f 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -138,9 +138,11 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, { struct pci_dynid *dynid; const struct pci_device_id *found_id = NULL, *ids; + int ret; /* When driver_override is set, only bind to the matching driver */ - if (dev->driver_override && strcmp(dev->driver_override, drv->name)) + ret = device_match_driver_override(&dev->dev, &drv->driver); + if (ret == 0) return NULL; /* Look at the dynamic ids first, before the static ones */ @@ -164,7 +166,7 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, * matching. */ if (found_id->override_only) { - if (dev->driver_override) + if (ret > 0) return found_id; } else { return found_id; @@ -172,7 +174,7 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, } /* driver_override will always match, send a dummy id */ - if (dev->driver_override) + if (ret > 0) return &pci_device_id_any; return NULL; } @@ -423,7 +425,7 @@ static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev) static inline bool pci_device_can_probe(struct pci_dev *pdev) { return (!pdev->is_virtfn || pdev->physfn->sriov->drivers_autoprobe || - pdev->driver_override); + device_has_driver_override(&pdev->dev)); } #else static inline bool pci_device_can_probe(struct pci_dev *pdev) @@ -1695,6 +1697,7 @@ static const struct cpumask *pci_device_irq_get_affinity(struct device *dev, const struct bus_type pci_bus_type = { .name = "pci", + .driver_override = true, .match = pci_bus_match, .uevent = pci_uevent, .probe = pci_device_probe, diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 9d6f74bd95f8c..d36b46849fee2 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -615,33 +615,6 @@ static ssize_t devspec_show(struct device *dev, static DEVICE_ATTR_RO(devspec); #endif -static ssize_t driver_override_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - ret = driver_set_override(dev, &pdev->driver_override, buf, count); - if (ret) - return ret; - - return count; -} - -static ssize_t driver_override_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev = to_pci_dev(dev); - ssize_t len; - - device_lock(dev); - len = sysfs_emit(buf, "%s\n", pdev->driver_override); - device_unlock(dev); - return len; -} -static DEVICE_ATTR_RW(driver_override); - static struct attribute *pci_dev_attrs[] = { &dev_attr_power_state.attr, &dev_attr_resource.attr, @@ -669,7 +642,6 @@ static struct attribute *pci_dev_attrs[] = { #ifdef CONFIG_OF &dev_attr_devspec.attr, #endif - &dev_attr_driver_override.attr, &dev_attr_ari_enabled.attr, NULL, }; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 23833fd7265e2..4e4e38e626912 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2449,7 +2449,6 @@ static void pci_release_dev(struct device *dev) pci_release_of_node(pci_dev); pcibios_release_device(pci_dev); pci_bus_put(pci_dev->bus); - kfree(pci_dev->driver_override); bitmap_free(pci_dev->dma_alias_mask); dev_dbg(dev, "device released\n"); kfree(pci_dev); diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 085373d71e9c2..69476fc67ca08 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -2013,9 +2013,8 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb, pdev->is_virtfn && physfn == vdev->pdev) { pci_info(vdev->pdev, "Captured SR-IOV VF %s driver_override\n", pci_name(pdev)); - pdev->driver_override = kasprintf(GFP_KERNEL, "%s", - vdev->vdev.ops->name); - WARN_ON(!pdev->driver_override); + WARN_ON(device_set_driver_override(&pdev->dev, + vdev->vdev.ops->name)); } else if (action == BUS_NOTIFY_BOUND_DRIVER && pdev->is_virtfn && physfn == vdev->pdev) { struct pci_driver *drv = pci_dev_driver(pdev); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 045e74847fe6b..7de2fa67743c6 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -598,6 +598,8 @@ static int pcistub_seize(struct pci_dev *dev, return err; } +static struct pci_driver xen_pcibk_pci_driver; + /* Called when 'bind'. This means we must _NOT_ call pci_reset_function or * other functions that take the sysfs lock. */ static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id) @@ -609,8 +611,8 @@ static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id) match = pcistub_match(dev); - if ((dev->driver_override && - !strcmp(dev->driver_override, PCISTUB_DRIVER_NAME)) || + if (device_match_driver_override(&dev->dev, + &xen_pcibk_pci_driver.driver) > 0 || match) { if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL diff --git a/include/linux/pci.h b/include/linux/pci.h index 05aeee8c8844a..89f5a4290b6e2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -547,12 +547,6 @@ struct pci_dev { u8 supported_speeds; /* Supported Link Speeds Vector */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ - /* - * Driver name to force a match. Do not set directly, because core - * frees it. Use driver_set_override() to set or clear it. - */ - const char *driver_override; - unsigned long priv_flags; /* Private flags for the PCI driver */ /* These methods index pci_reset_fn_methods[] */ From 2c5507010fc3b8e2bd596c63c88f6ad39a69b1c4 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 24 Mar 2026 01:59:10 +0100 Subject: [PATCH 0217/1518] platform/wmi: use generic driver_override infrastructure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8a700b1fc94df4d847a04f14ebc7f8532592b367 ] When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Reported-by: Gui-Dong Han Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789 Fixes: 12046f8c77e0 ("platform/x86: wmi: Add driver_override support") Reviewed-by: Armin Wolf Acked-by: Ilpo Järvinen Link: https://patch.msgid.link/20260324005919.2408620-7-dakr@kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/platform/x86/wmi.c | 36 +++++------------------------------- include/linux/wmi.h | 4 ---- 2 files changed, 5 insertions(+), 35 deletions(-) diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 4e86a422f05f1..6f8e96476fd07 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -702,39 +702,11 @@ static ssize_t expensive_show(struct device *dev, } static DEVICE_ATTR_RO(expensive); -static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct wmi_device *wdev = to_wmi_device(dev); - ssize_t ret; - - device_lock(dev); - ret = sysfs_emit(buf, "%s\n", wdev->driver_override); - device_unlock(dev); - - return ret; -} - -static ssize_t driver_override_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - struct wmi_device *wdev = to_wmi_device(dev); - int ret; - - ret = driver_set_override(dev, &wdev->driver_override, buf, count); - if (ret < 0) - return ret; - - return count; -} -static DEVICE_ATTR_RW(driver_override); - static struct attribute *wmi_attrs[] = { &dev_attr_modalias.attr, &dev_attr_guid.attr, &dev_attr_instance_count.attr, &dev_attr_expensive.attr, - &dev_attr_driver_override.attr, NULL }; ATTRIBUTE_GROUPS(wmi); @@ -803,7 +775,6 @@ static void wmi_dev_release(struct device *dev) { struct wmi_block *wblock = dev_to_wblock(dev); - kfree(wblock->dev.driver_override); kfree(wblock); } @@ -812,10 +783,12 @@ static int wmi_dev_match(struct device *dev, const struct device_driver *driver) const struct wmi_driver *wmi_driver = to_wmi_driver(driver); struct wmi_block *wblock = dev_to_wblock(dev); const struct wmi_device_id *id = wmi_driver->id_table; + int ret; /* When driver_override is set, only bind to the matching driver */ - if (wblock->dev.driver_override) - return !strcmp(wblock->dev.driver_override, driver->name); + ret = device_match_driver_override(dev, driver); + if (ret >= 0) + return ret; if (id == NULL) return 0; @@ -936,6 +909,7 @@ static struct class wmi_bus_class = { static const struct bus_type wmi_bus_type = { .name = "wmi", .dev_groups = wmi_groups, + .driver_override = true, .match = wmi_dev_match, .uevent = wmi_dev_uevent, .probe = wmi_dev_probe, diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 10751c8e5e6a0..c20bb22133381 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -16,16 +16,12 @@ * struct wmi_device - WMI device structure * @dev: Device associated with this WMI device * @setable: True for devices implementing the Set Control Method - * @driver_override: Driver name to force a match; do not set directly, - * because core frees it; use driver_set_override() to - * set or clear it. * * This represents WMI devices discovered by the WMI driver core. */ struct wmi_device { struct device dev; bool setable; - const char *driver_override; }; /** From 654ef9c33e138ede6734ac286282df9faf83cd11 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 24 Mar 2026 01:59:12 +0100 Subject: [PATCH 0218/1518] vdpa: use generic driver_override infrastructure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 85bb534ff12aab6916058897b39c748940a7a4c6 ] When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Reported-by: Gui-Dong Han Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789 Fixes: 539fec78edb4 ("vdpa: add driver_override support") Acked-by: Eugenio Pérez Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260324005919.2408620-9-dakr@kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/vdpa/vdpa.c | 48 +++++--------------------------------------- include/linux/vdpa.h | 4 ---- 2 files changed, 5 insertions(+), 47 deletions(-) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 34874beb0152e..caf0ee5d6856c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -67,57 +67,20 @@ static void vdpa_dev_remove(struct device *d) static int vdpa_dev_match(struct device *dev, const struct device_driver *drv) { - struct vdpa_device *vdev = dev_to_vdpa(dev); + int ret; /* Check override first, and if set, only use the named driver */ - if (vdev->driver_override) - return strcmp(vdev->driver_override, drv->name) == 0; + ret = device_match_driver_override(dev, drv); + if (ret >= 0) + return ret; /* Currently devices must be supported by all vDPA bus drivers */ return 1; } -static ssize_t driver_override_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct vdpa_device *vdev = dev_to_vdpa(dev); - int ret; - - ret = driver_set_override(dev, &vdev->driver_override, buf, count); - if (ret) - return ret; - - return count; -} - -static ssize_t driver_override_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct vdpa_device *vdev = dev_to_vdpa(dev); - ssize_t len; - - device_lock(dev); - len = sysfs_emit(buf, "%s\n", vdev->driver_override); - device_unlock(dev); - - return len; -} -static DEVICE_ATTR_RW(driver_override); - -static struct attribute *vdpa_dev_attrs[] = { - &dev_attr_driver_override.attr, - NULL, -}; - -static const struct attribute_group vdpa_dev_group = { - .attrs = vdpa_dev_attrs, -}; -__ATTRIBUTE_GROUPS(vdpa_dev); - static const struct bus_type vdpa_bus = { .name = "vdpa", - .dev_groups = vdpa_dev_groups, + .driver_override = true, .match = vdpa_dev_match, .probe = vdpa_dev_probe, .remove = vdpa_dev_remove, @@ -132,7 +95,6 @@ static void vdpa_release_dev(struct device *d) ops->free(vdev); ida_free(&vdpa_index_ida, vdev->index); - kfree(vdev->driver_override); kfree(vdev); } diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 4cf21d6e9cfde..0d8373adc1e46 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -72,9 +72,6 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @vmap: the metadata passed to upper layer to be used for mapping - * @driver_override: driver name to force a match; do not set directly, - * because core frees it; use driver_set_override() to - * set or clear it. * @config: the configuration ops for this device. * @map: the map ops for this device * @cf_lock: Protects get and set access to configuration layout. @@ -90,7 +87,6 @@ struct vdpa_mgmt_dev; struct vdpa_device { struct device dev; union virtio_map vmap; - const char *driver_override; const struct vdpa_config_ops *config; const struct virtio_map_ops *map; struct rw_semaphore cf_lock; /* Protects get/set config */ From 2081957d8c323ffb58a10bc64837717ac5a042a1 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 24 Mar 2026 01:59:13 +0100 Subject: [PATCH 0219/1518] s390/cio: use generic driver_override infrastructure [ Upstream commit ac4d8bb6e2e13e8684a76ea48d13ebaaaf5c24c4 ] When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Reported-by: Gui-Dong Han Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789 Fixes: ebc3d1791503 ("s390/cio: introduce driver_override on the css bus") Reviewed-by: Vineeth Vijayan Link: https://patch.msgid.link/20260324005919.2408620-10-dakr@kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/s390/cio/cio.h | 5 ----- drivers/s390/cio/css.c | 34 ++++------------------------------ 2 files changed, 4 insertions(+), 35 deletions(-) diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h index 08a5e9380e75a..bad142c536e1e 100644 --- a/drivers/s390/cio/cio.h +++ b/drivers/s390/cio/cio.h @@ -103,11 +103,6 @@ struct subchannel { struct work_struct todo_work; struct schib_config config; u64 dma_mask; - /* - * Driver name to force a match. Do not set directly, because core - * frees it. Use driver_set_override() to set or clear it. - */ - const char *driver_override; } __attribute__ ((aligned(8))); DECLARE_PER_CPU_ALIGNED(struct irb, cio_irb); diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 8a70596a55447..629d3993144e1 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -160,7 +160,6 @@ static void css_subchannel_release(struct device *dev) sch->config.intparm = 0; cio_commit_config(sch); - kfree(sch->driver_override); kfree(sch); } @@ -324,37 +323,9 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RO(modalias); -static ssize_t driver_override_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct subchannel *sch = to_subchannel(dev); - int ret; - - ret = driver_set_override(dev, &sch->driver_override, buf, count); - if (ret) - return ret; - - return count; -} - -static ssize_t driver_override_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct subchannel *sch = to_subchannel(dev); - ssize_t len; - - device_lock(dev); - len = sysfs_emit(buf, "%s\n", sch->driver_override); - device_unlock(dev); - return len; -} -static DEVICE_ATTR_RW(driver_override); - static struct attribute *subch_attrs[] = { &dev_attr_type.attr, &dev_attr_modalias.attr, - &dev_attr_driver_override.attr, NULL, }; @@ -1358,9 +1329,11 @@ static int css_bus_match(struct device *dev, const struct device_driver *drv) struct subchannel *sch = to_subchannel(dev); const struct css_driver *driver = to_cssdriver(drv); struct css_device_id *id; + int ret; /* When driver_override is set, only bind to the matching driver */ - if (sch->driver_override && strcmp(sch->driver_override, drv->name)) + ret = device_match_driver_override(dev, drv); + if (ret == 0) return 0; for (id = driver->subchannel_type; id->match_flags; id++) { @@ -1417,6 +1390,7 @@ static int css_uevent(const struct device *dev, struct kobj_uevent_env *env) static const struct bus_type css_bus_type = { .name = "css", + .driver_override = true, .match = css_bus_match, .probe = css_probe, .remove = css_remove, From 8139ce66b52a4a5638bfb445b037c07d4abeb08e Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 24 Mar 2026 01:59:06 +0100 Subject: [PATCH 0220/1518] bus: fsl-mc: use generic driver_override infrastructure [ Upstream commit 6c8dfb0362732bf1e4829867a2a5239fedc592d0 ] When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Tested-by: Ioana Ciornei Acked-by: Ioana Ciornei Acked-by: Christophe Leroy (CS GROUP) Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Reported-by: Gui-Dong Han Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789 Fixes: 1f86a00c1159 ("bus/fsl-mc: add support for 'driver_override' in the mc-bus") Link: https://patch.msgid.link/20260324005919.2408620-3-dakr@kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/bus/fsl-mc/fsl-mc-bus.c | 43 +++++-------------------------- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 4 +-- include/linux/fsl/mc.h | 4 --- 3 files changed, 8 insertions(+), 43 deletions(-) diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index eb7b6c0ba9e7c..996379ace3764 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -86,12 +86,16 @@ static int fsl_mc_bus_match(struct device *dev, const struct device_driver *drv) struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); const struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(drv); bool found = false; + int ret; /* When driver_override is set, only bind to the matching driver */ - if (mc_dev->driver_override) { - found = !strcmp(mc_dev->driver_override, mc_drv->driver.name); + ret = device_match_driver_override(dev, drv); + if (ret > 0) { + found = true; goto out; } + if (ret == 0) + goto out; if (!mc_drv->match_id_table) goto out; @@ -181,39 +185,8 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(modalias); -static ssize_t driver_override_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); - int ret; - - if (WARN_ON(dev->bus != &fsl_mc_bus_type)) - return -EINVAL; - - ret = driver_set_override(dev, &mc_dev->driver_override, buf, count); - if (ret) - return ret; - - return count; -} - -static ssize_t driver_override_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); - ssize_t len; - - device_lock(dev); - len = sysfs_emit(buf, "%s\n", mc_dev->driver_override); - device_unlock(dev); - return len; -} -static DEVICE_ATTR_RW(driver_override); - static struct attribute *fsl_mc_dev_attrs[] = { &dev_attr_modalias.attr, - &dev_attr_driver_override.attr, NULL, }; @@ -316,6 +289,7 @@ ATTRIBUTE_GROUPS(fsl_mc_bus); const struct bus_type fsl_mc_bus_type = { .name = "fsl-mc", + .driver_override = true, .match = fsl_mc_bus_match, .uevent = fsl_mc_bus_uevent, .dma_configure = fsl_mc_dma_configure, @@ -925,9 +899,6 @@ static struct notifier_block fsl_mc_nb; */ void fsl_mc_device_remove(struct fsl_mc_device *mc_dev) { - kfree(mc_dev->driver_override); - mc_dev->driver_override = NULL; - /* * The device-specific remove callback will get invoked by device_del() */ diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 76ccbab0e3d64..84cd0eb65c471 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -430,9 +430,7 @@ static int vfio_fsl_mc_bus_notifier(struct notifier_block *nb, if (action == BUS_NOTIFY_ADD_DEVICE && vdev->mc_dev == mc_cont) { - mc_dev->driver_override = kasprintf(GFP_KERNEL, "%s", - vfio_fsl_mc_ops.name); - if (!mc_dev->driver_override) + if (device_set_driver_override(dev, vfio_fsl_mc_ops.name)) dev_warn(dev, "VFIO_FSL_MC: Setting driver override for device in dprc %s failed\n", dev_name(&mc_cont->dev)); else diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 897d6211c1635..1da63f2d70401 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -178,9 +178,6 @@ struct fsl_mc_obj_desc { * @regions: pointer to array of MMIO region entries * @irqs: pointer to array of pointers to interrupts allocated to this device * @resource: generic resource associated with this MC object device, if any. - * @driver_override: driver name to force a match; do not set directly, - * because core frees it; use driver_set_override() to - * set or clear it. * * Generic device object for MC object devices that are "attached" to a * MC bus. @@ -214,7 +211,6 @@ struct fsl_mc_device { struct fsl_mc_device_irq **irqs; struct fsl_mc_resource *resource; struct device_link *consumer_link; - const char *driver_override; }; #define to_fsl_mc_device(_dev) \ From 6b05c427a638288310c906faa8897db7340ef298 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Sun, 22 Feb 2026 18:43:44 -0500 Subject: [PATCH 0221/1518] irqchip/irq-pic32-evic: Address warning related to wrong printf() formatter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 86be659415b0ddefebc3120e309091aa215a9064 ] This driver is currently only build on 32 bit MIPS systems. When building it on x86_64, the following warning occurs: drivers/irqchip/irq-pic32-evic.c: In function ‘pic32_ext_irq_of_init’: ./include/linux/kern_levels.h:5:25: error: format ‘%d’ expects argument of type ‘int’, but argument 2 has type ‘long unsigned int’ [-Werror=format=] Update the printf() formatter in preparation for allowing this driver to be compiled on all architectures. Fixes: aaa8666ada780 ("IRQCHIP: irq-pic32-evic: Add support for PIC32 interrupt controller") Signed-off-by: Brian Masney Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260222-irqchip-pic32-v1-1-37f50d1f14af@redhat.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-pic32-evic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c index 5dfda8e8df10d..0bb664e3d7c51 100644 --- a/drivers/irqchip/irq-pic32-evic.c +++ b/drivers/irqchip/irq-pic32-evic.c @@ -196,7 +196,7 @@ static void __init pic32_ext_irq_of_init(struct irq_domain *domain) of_property_for_each_u32(node, pname, hwirq) { if (i >= ARRAY_SIZE(priv->ext_irqs)) { - pr_warn("More than %d external irq, skip rest\n", + pr_warn("More than %zu external irq, skip rest\n", ARRAY_SIZE(priv->ext_irqs)); break; } From a8759eef4951c023bbf95a31a3bd9dd40e83d772 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 Feb 2026 17:35:37 +0100 Subject: [PATCH 0222/1518] hrtimer: Avoid pointless reprogramming in __hrtimer_start_range_ns() [ Upstream commit d19ff16c11db38f3ee179d72751fb9b340174330 ] Much like hrtimer_reprogram(), skip programming if the cpu_base is running the hrtimer interrupt. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Juri Lelli Reviewed-by: Thomas Gleixner Link: https://patch.msgid.link/20260224163429.069535561@kernel.org Stable-dep-of: f2e388a019e4 ("hrtimer: Reduce trace noise in hrtimer_start()") Signed-off-by: Sasha Levin --- kernel/time/hrtimer.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 21b6d93401480..2589cd1b2ec3a 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1261,6 +1261,14 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, } first = enqueue_hrtimer(timer, new_base, mode); + + /* + * If the hrtimer interrupt is running, then it will reevaluate the + * clock bases and reprogram the clock event device. + */ + if (new_base->cpu_base->in_hrtirq) + return false; + if (!force_local) { /* * If the current CPU base is online, then the timer is From e017f5b69b7623b36b396f37ec2d13d378e33ed6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 24 Feb 2026 17:36:59 +0100 Subject: [PATCH 0223/1518] hrtimer: Reduce trace noise in hrtimer_start() [ Upstream commit f2e388a019e4cf83a15883a3d1f1384298e9a6aa ] hrtimer_start() when invoked with an already armed timer traces like: -.. [032] d.h2. 5.002263: hrtimer_cancel: hrtimer= .... -.. [032] d.h1. 5.002263: hrtimer_start: hrtimer= .... Which is incorrect as the timer doesn't get canceled. Just the expiry time changes. The internal dequeue operation which is required for that is not really interesting for trace analysis. But it makes it tedious to keep real cancellations and the above case apart. Remove the cancel tracing in hrtimer_start() and add a 'was_armed' indicator to the hrtimer start tracepoint, which clearly indicates what the state of the hrtimer is when hrtimer_start() is invoked: -.. [032] d.h1. 6.200103: hrtimer_start: hrtimer= .... was_armed=0 -.. [032] d.h1. 6.200558: hrtimer_start: hrtimer= .... was_armed=1 Fixes: c6a2a1770245 ("hrtimer: Add tracepoint for hrtimers") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260224163430.208491877@kernel.org Signed-off-by: Sasha Levin --- include/trace/events/timer.h | 11 +++++---- kernel/time/hrtimer.c | 43 +++++++++++++++++------------------- 2 files changed, 27 insertions(+), 27 deletions(-) diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 1641ae3e6ca06..ab9a9386f7b65 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -218,12 +218,13 @@ TRACE_EVENT(hrtimer_setup, * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer * @mode: the hrtimers mode + * @was_armed: Was armed when hrtimer_start*() was invoked */ TRACE_EVENT(hrtimer_start, - TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), + TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode, bool was_armed), - TP_ARGS(hrtimer, mode), + TP_ARGS(hrtimer, mode, was_armed), TP_STRUCT__entry( __field( void *, hrtimer ) @@ -231,6 +232,7 @@ TRACE_EVENT(hrtimer_start, __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) + __field( bool, was_armed ) ), TP_fast_assign( @@ -239,13 +241,14 @@ TRACE_EVENT(hrtimer_start, __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; + __entry->was_armed = was_armed; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " - "mode=%s", __entry->hrtimer, __entry->function, + "mode=%s was_armed=%d", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, - decode_hrtimer_mode(__entry->mode)) + decode_hrtimer_mode(__entry->mode), __entry->was_armed) ); /** diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 2589cd1b2ec3a..1f602deeb09a4 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -471,17 +471,10 @@ static inline void debug_setup_on_stack(struct hrtimer *timer, clockid_t clockid trace_hrtimer_setup(timer, clockid, mode); } -static inline void debug_activate(struct hrtimer *timer, - enum hrtimer_mode mode) +static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode, bool was_armed) { debug_hrtimer_activate(timer, mode); - trace_hrtimer_start(timer, mode); -} - -static inline void debug_deactivate(struct hrtimer *timer) -{ - debug_hrtimer_deactivate(timer); - trace_hrtimer_cancel(timer); + trace_hrtimer_start(timer, mode, was_armed); } static struct hrtimer_clock_base * @@ -1076,9 +1069,9 @@ EXPORT_SYMBOL_GPL(hrtimer_forward); * Returns true when the new timer is the leftmost timer in the tree. */ static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, - enum hrtimer_mode mode) + enum hrtimer_mode mode, bool was_armed) { - debug_activate(timer, mode); + debug_activate(timer, mode, was_armed); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; @@ -1138,6 +1131,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; + debug_hrtimer_deactivate(timer); + /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current @@ -1146,7 +1141,6 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ - debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* @@ -1213,15 +1207,15 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *new_base; - bool force_local, first; + bool force_local, first, was_armed; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice - * (on removal and on enqueue). To avoid that by prevent the - * reprogram on removal, keep the timer local to the current CPU - * and enforce reprogramming after it is queued no matter whether - * it is the new first expiring timer again or not. + * (on removal and on enqueue). To avoid that prevent the reprogram + * on removal, keep the timer local to the current CPU and enforce + * reprogramming after it is queued no matter whether it is the new + * first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; @@ -1243,7 +1237,7 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ - remove_hrtimer(timer, base, true, force_local); + was_armed = remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, __hrtimer_cb_get_time(base->clockid)); @@ -1260,7 +1254,7 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, new_base = base; } - first = enqueue_hrtimer(timer, new_base, mode); + first = enqueue_hrtimer(timer, new_base, mode, was_armed); /* * If the hrtimer interrupt is running, then it will reevaluate the @@ -1362,8 +1356,11 @@ int hrtimer_try_to_cancel(struct hrtimer *timer) base = lock_hrtimer_base(timer, &flags); - if (!hrtimer_callback_running(timer)) + if (!hrtimer_callback_running(timer)) { ret = remove_hrtimer(timer, base, false, false); + if (ret) + trace_hrtimer_cancel(timer); + } unlock_hrtimer_base(timer, &flags); @@ -1799,7 +1796,7 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) - enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); + enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS, false); /* * Separate the ->running assignment from the ->state assignment. @@ -2278,7 +2275,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); - debug_deactivate(timer); + debug_hrtimer_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the @@ -2295,7 +2292,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, * sort out already expired timers and reprogram the * event device. */ - enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); + enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS, true); } } From aaf2712f76747830043ef5dfd5ef2c46f01bd830 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 16 Feb 2026 04:22:14 +0000 Subject: [PATCH 0224/1518] perf/amd/ibs: Preserve PhyAddrVal bit when clearing PhyAddr MSR [ Upstream commit 723a290326e015b07931eabc603d3735999377be ] Commit 50a53b60e141 ("perf/amd/ibs: Prevent leaking sensitive data to userspace") zeroed the physical address and also cleared the PhyAddrVal flag before copying the value into a perf sample to avoid exposing physical addresses to unprivileged users. Clearing PhyAddrVal, however, has an unintended side-effect: several other IBS fields are considered valid only when this bit is set. As a result, those otherwise correct fields are discarded, reducing IBS functionality. Continue to zero the physical address, but keep the PhyAddrVal bit intact so the related fields remain usable while still preventing any address leak. Fixes: 50a53b60e141 ("perf/amd/ibs: Prevent leaking sensitive data to userspace") Signed-off-by: Ravi Bangoria Signed-off-by: Peter Zijlstra (Intel) Acked-by: Namhyung Kim Link: https://patch.msgid.link/20260216042216.1440-4-ravi.bangoria@amd.com Signed-off-by: Sasha Levin --- arch/x86/events/amd/ibs.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 112f43b23ebf8..10af127f779fe 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -1214,12 +1214,10 @@ static void perf_ibs_phyaddr_clear(struct perf_ibs *perf_ibs, struct perf_ibs_data *ibs_data) { if (perf_ibs == &perf_ibs_op) { - ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)] &= ~(1ULL << 18); ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSDCPHYSAD)] = 0; return; } - ibs_data->regs[ibs_fetch_msr_idx(MSR_AMD64_IBSFETCHCTL)] &= ~(1ULL << 52); ibs_data->regs[ibs_fetch_msr_idx(MSR_AMD64_IBSFETCHPHYSAD)] = 0; } From 2783ed2442ce69ae240b787aee6dae801cef7aec Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 16 Feb 2026 04:22:15 +0000 Subject: [PATCH 0225/1518] perf/amd/ibs: Avoid calling perf_allow_kernel() from the IBS NMI handler [ Upstream commit b0a09142622a994c4f4088c3f61db5da87cfc711 ] Calling perf_allow_kernel() from the NMI context is unsafe and could be fatal. Capture the permission at event-initialization time by storing it in event->hw.flags, and have the NMI handler rely on that cached flag instead of making the call directly. Fixes: 50a53b60e141d ("perf/amd/ibs: Prevent leaking sensitive data to userspace") Reported-by: Sadasivan Shaiju Signed-off-by: Ravi Bangoria Signed-off-by: Peter Zijlstra (Intel) Acked-by: Namhyung Kim Link: https://patch.msgid.link/20260216042216.1440-5-ravi.bangoria@amd.com Signed-off-by: Sasha Levin --- arch/x86/events/amd/ibs.c | 5 ++++- arch/x86/events/perf_event_flags.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 10af127f779fe..56918cd91115c 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -313,6 +313,9 @@ static int perf_ibs_init(struct perf_event *event) if (ret) return ret; + if (perf_allow_kernel()) + hwc->flags |= PERF_X86_EVENT_UNPRIVILEGED; + if (hwc->sample_period) { if (config & perf_ibs->cnt_mask) /* raw max_cnt may not be set */ @@ -1342,7 +1345,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) * unprivileged users. */ if ((event->attr.sample_type & PERF_SAMPLE_RAW) && - perf_allow_kernel()) { + (hwc->flags & PERF_X86_EVENT_UNPRIVILEGED)) { perf_ibs_phyaddr_clear(perf_ibs, &ibs_data); } diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h index 70078334e4a33..47f84ee8f5409 100644 --- a/arch/x86/events/perf_event_flags.h +++ b/arch/x86/events/perf_event_flags.h @@ -23,3 +23,4 @@ PERF_ARCH(PEBS_LAT_HYBRID, 0x0020000) /* ld and st lat for hybrid */ PERF_ARCH(NEEDS_BRANCH_STACK, 0x0040000) /* require branch stack setup */ PERF_ARCH(BRANCH_COUNTERS, 0x0080000) /* logs the counters in the extra space of each branch */ PERF_ARCH(ACR, 0x0100000) /* Auto counter reload */ +PERF_ARCH(UNPRIVILEGED, 0x0200000) /* Unprivileged event (wrt perf_allow_kernel()) */ From 90e8cfcd217cb07a5c22e681be8eaa87d7c8bd92 Mon Sep 17 00:00:00 2001 From: Xiaoyao Li Date: Tue, 3 Mar 2026 11:03:32 +0800 Subject: [PATCH 0226/1518] x86/tdx: Fix the typo in TDX_ATTR_MIGRTABLE [ Upstream commit 3aecb2e7b948400354399b26f3f1653bd2c1bae0 ] The TD scoped TDCS attributes are defined by bit positions. In the guest side of the TDX code, the 'tdx_attributes' string array holds pretty print names for these attributes, which are generated via macros and defines. Today these pretty print names are only used to print the attribute names to dmesg. Unfortunately there is a typo in the define for the migratable bit. Change the defines TDX_ATTR_MIGRTABLE* to TDX_ATTR_MIGRATABLE*. Update the sole user, the tdx_attributes array, to use the fixed name. Since these defines control the string printed to dmesg, the change is user visible. But the risk of breakage is almost zero since it is not exposed in any interface expected to be consumed programmatically. Fixes: 564ea84c8c14 ("x86/tdx: Dump attributes and TD_CTLS on boot") Signed-off-by: Xiaoyao Li Signed-off-by: Dave Hansen Reviewed-by: Kirill A. Shutemov Reviewed-by: Kai Huang Acked-by: Sean Christopherson Link: https://patch.msgid.link/20260303030335.766779-2-xiaoyao.li@intel.com Signed-off-by: Sasha Levin --- arch/x86/coco/tdx/debug.c | 2 +- arch/x86/include/asm/shared/tdx.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/coco/tdx/debug.c b/arch/x86/coco/tdx/debug.c index cef847c8bb67f..28990c2ab0a14 100644 --- a/arch/x86/coco/tdx/debug.c +++ b/arch/x86/coco/tdx/debug.c @@ -17,7 +17,7 @@ static __initdata const char *tdx_attributes[] = { DEF_TDX_ATTR_NAME(ICSSD), DEF_TDX_ATTR_NAME(LASS), DEF_TDX_ATTR_NAME(SEPT_VE_DISABLE), - DEF_TDX_ATTR_NAME(MIGRTABLE), + DEF_TDX_ATTR_NAME(MIGRATABLE), DEF_TDX_ATTR_NAME(PKS), DEF_TDX_ATTR_NAME(KL), DEF_TDX_ATTR_NAME(TPA), diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 8bc074c8d7c6a..11f3cf30b1ac8 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -35,8 +35,8 @@ #define TDX_ATTR_LASS BIT_ULL(TDX_ATTR_LASS_BIT) #define TDX_ATTR_SEPT_VE_DISABLE_BIT 28 #define TDX_ATTR_SEPT_VE_DISABLE BIT_ULL(TDX_ATTR_SEPT_VE_DISABLE_BIT) -#define TDX_ATTR_MIGRTABLE_BIT 29 -#define TDX_ATTR_MIGRTABLE BIT_ULL(TDX_ATTR_MIGRTABLE_BIT) +#define TDX_ATTR_MIGRATABLE_BIT 29 +#define TDX_ATTR_MIGRATABLE BIT_ULL(TDX_ATTR_MIGRATABLE_BIT) #define TDX_ATTR_PKS_BIT 30 #define TDX_ATTR_PKS BIT_ULL(TDX_ATTR_PKS_BIT) #define TDX_ATTR_KL_BIT 31 From bec2fa23eaf2a211ab1417afd7e4022fddc441ea Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 3 Mar 2026 12:16:49 -0800 Subject: [PATCH 0227/1518] rust: sync: atomic: Remove bound `T: Sync` for `Atomic::from_ptr()` [ Upstream commit 4a5dc632e0b603ec1cbbf87b78de86b4b6359cff ] Originally, `Atomic::from_ptr()` requires `T` being a `Sync` because I thought having the ability to do `from_ptr()` meant multiplle `&Atomic`s shared by different threads, which was identical (or similar) to multiple `&T`s shared by different threads. Hence `T` was required to be `Sync`. However this is not true, since `&Atomic` is not the same at `&T`. Moreover, having this bound makes `Atomic::<*mut T>::from_ptr()` impossible, which is definitely not intended. Therefore remove the `T: Sync` bound. [boqun: Fix title typo spotted by Alice & Gary] Fixes: 29c32c405e53 ("rust: sync: atomic: Add generic atomics") Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Link: https://patch.msgid.link/20260120115207.55318-2-boqun.feng@gmail.com Link: https://patch.msgid.link/20260303201701.12204-2-boqun@kernel.org Signed-off-by: Sasha Levin --- rust/kernel/sync/atomic.rs | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/rust/kernel/sync/atomic.rs b/rust/kernel/sync/atomic.rs index 016a6bcaf0807..43229f0320e92 100644 --- a/rust/kernel/sync/atomic.rs +++ b/rust/kernel/sync/atomic.rs @@ -202,10 +202,7 @@ impl Atomic { /// // no data race. /// unsafe { Atomic::from_ptr(foo_a_ptr) }.store(2, Release); /// ``` - pub unsafe fn from_ptr<'a>(ptr: *mut T) -> &'a Self - where - T: Sync, - { + pub unsafe fn from_ptr<'a>(ptr: *mut T) -> &'a Self { // CAST: `T` and `Atomic` have the same size, alignment and bit validity. // SAFETY: Per function safety requirement, `ptr` is a valid pointer and the object will // live long enough. It's safe to return a `&Atomic` because function safety requirement From 6adc01405605e03d5ddaa219d59ad2c8ea088e22 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 4 Mar 2026 08:49:01 +0100 Subject: [PATCH 0228/1518] sparc64: vdso: Link with -z noexecstack MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit acc4f131d5d57c2aa89db914aeb6f7bb0ab4eb4a ] The vDSO stack does not need to be executable. Prevent the linker from creating executable. For more background see commit ffcf9c5700e4 ("x86: link vdso and boot with -z noexecstack --no-warn-rwx-segments"). Also prevent the following warning from the linker: sparc64-linux-ld: warning: arch/sparc/vdso/vdso-note.o: missing .note.GNU-stack section implies executable stack sparc64-linux-ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker Fixes: 9a08862a5d2e ("vDSO for sparc") Suggested-by: Arnd Bergmann Signed-off-by: Thomas Weißschuh Signed-off-by: Thomas Gleixner Tested-by: Andreas Larsson Reviewed-by: Andreas Larsson Acked-by: Andreas Larsson Link: https://lore.kernel.org/lkml/20250707144726.4008707-1-arnd@kernel.org/ Link: https://patch.msgid.link/20260304-vdso-sparc64-generic-2-v6-4-d8eb3b0e1410@linutronix.de Signed-off-by: Sasha Levin --- arch/sparc/vdso/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 683b2d4082244..400529acd1c10 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -104,4 +104,4 @@ quiet_cmd_vdso = VDSO $@ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -T $(filter %.lds,$^) $(filter %.o,$^) -VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic --no-undefined +VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic --no-undefined -z noexecstack From 8e1be8f79fcaed63f649a3c9f8cdfb51e2c5c565 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh=20=28Schneider=20Electric=29?= Date: Wed, 11 Mar 2026 11:15:10 +0100 Subject: [PATCH 0229/1518] scripts/gdb: timerlist: Adapt to move of tk_core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5aa9383813aca45b914d4a7481ca417ef13114df ] tk_core is a macro today which cannot be resolved by gdb. Use the correct symbol expression to reference tk_core. Fixes: 22c62b9a84b8 ("timekeeping: Introduce auxiliary timekeepers") Signed-off-by: Thomas Weißschuh (Schneider Electric) Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260311-hrtimer-cleanups-v1-1-095357392669@linutronix.de Signed-off-by: Sasha Levin --- scripts/gdb/linux/timerlist.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/gdb/linux/timerlist.py b/scripts/gdb/linux/timerlist.py index ccc24d30de806..9fb3436a217cc 100644 --- a/scripts/gdb/linux/timerlist.py +++ b/scripts/gdb/linux/timerlist.py @@ -20,7 +20,7 @@ def ktime_get(): We can't read the hardware timer itself to add any nanoseconds that need to be added since we last stored the time in the timekeeper. But this is probably good enough for debug purposes.""" - tk_core = gdb.parse_and_eval("&tk_core") + tk_core = gdb.parse_and_eval("&timekeeper_data[TIMEKEEPER_CORE]") return tk_core['timekeeper']['tkr_mono']['base'] From 5fbefcd7c38edd0c187f5f39ef5960964e8d47a8 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 13 Mar 2026 10:15:07 -0700 Subject: [PATCH 0230/1518] locking: Fix rwlock support in [ Upstream commit 756a0e011cfca0b45a48464aa25b05d9a9c2fb0b ] Architecture support for rwlocks must be available whether or not CONFIG_DEBUG_SPINLOCK has been defined. Move the definitions of the arch_{read,write}_{lock,trylock,unlock}() macros such that these become visbile if CONFIG_DEBUG_SPINLOCK=n. This patch prepares for converting do_raw_{read,write}_trylock() into inline functions. Without this patch that conversion triggers a build failure for UP architectures, e.g. arm-ep93xx. I used the following kernel configuration to build the kernel for that architecture: CONFIG_ARCH_MULTIPLATFORM=y CONFIG_ARCH_MULTI_V7=n CONFIG_ATAGS=y CONFIG_MMU=y CONFIG_ARCH_MULTI_V4T=y CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_ARCH_EP93XX=y Fixes: fb1c8f93d869 ("[PATCH] spinlock consolidation") Signed-off-by: Bart Van Assche Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260313171510.230998-2-bvanassche@acm.org Signed-off-by: Sasha Levin --- include/linux/spinlock_up.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 1e84e71ca495e..3a50976471d71 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -48,16 +48,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) lock->slock = 1; } -/* - * Read-write spinlocks. No debug version. - */ -#define arch_read_lock(lock) do { barrier(); (void)(lock); } while (0) -#define arch_write_lock(lock) do { barrier(); (void)(lock); } while (0) -#define arch_read_trylock(lock) ({ barrier(); (void)(lock); 1; }) -#define arch_write_trylock(lock) ({ barrier(); (void)(lock); 1; }) -#define arch_read_unlock(lock) do { barrier(); (void)(lock); } while (0) -#define arch_write_unlock(lock) do { barrier(); (void)(lock); } while (0) - #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) /* for sched/core.c and kernel_lock.c: */ @@ -68,4 +58,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #define arch_spin_is_contended(lock) (((void)(lock), 0)) +/* + * Read-write spinlocks. No debug version. + */ +#define arch_read_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_read_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_write_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_read_unlock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_unlock(lock) do { barrier(); (void)(lock); } while (0) + #endif /* __LINUX_SPINLOCK_UP_H */ From 87800a0bd2fec27605dc9b733b4f922120d45803 Mon Sep 17 00:00:00 2001 From: K Prateek Nayak Date: Thu, 12 Mar 2026 04:44:26 +0000 Subject: [PATCH 0231/1518] sched/topology: Compute sd_weight considering cpuset partitions [ Upstream commit 8e8e23dea43e64ddafbd1246644c3219209be113 ] The "sd_weight" used for calculating the load balancing interval, and its limits, considers the span weight of the entire topology level without accounting for cpuset partitions. For example, consider a large system of 128CPUs divided into 8 * 16CPUs partition which is typical when deploying virtual machines: [ PKG Domain: 128CPUs ] [Partition0: 16CPUs][Partition1: 16CPUs] ... [Partition7: 16CPUs] Although each partition only contains 16CPUs, the load balancing interval is set to a minimum of 128 jiffies considering the span of the entire domain with 128CPUs which can lead to longer imbalances within the partition although balancing within is cheaper with 16CPUs. Compute the "sd_weight" after computing the "sd_span" considering the cpu_map covered by the partition, and set the load balancing interval, and its limits accordingly. For the above example, the balancing intervals for the partitions PKG domain changes as follows: before after balance_interval 128 16 min_interval 128 16 max_interval 256 32 Intervals are now proportional to the CPUs in the partitioned domain as was intended by the original formula. Fixes: cb83b629bae03 ("sched/numa: Rewrite the CONFIG_NUMA sched domain support") Signed-off-by: K Prateek Nayak Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Shrikanth Hegde Reviewed-by: Chen Yu Reviewed-by: Valentin Schneider Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Link: https://patch.msgid.link/20260312044434.1974-2-kprateek.nayak@amd.com Signed-off-by: Sasha Levin --- kernel/sched/topology.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index c7a4d2fff5718..35478aa2536fc 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1631,13 +1631,17 @@ sd_init(struct sched_domain_topology_level *tl, int sd_id, sd_weight, sd_flags = 0; struct cpumask *sd_span; - sd_weight = cpumask_weight(tl->mask(tl, cpu)); + sd_span = sched_domain_span(sd); + cpumask_and(sd_span, cpu_map, tl->mask(tl, cpu)); + sd_weight = cpumask_weight(sd_span); + sd_id = cpumask_first(sd_span); if (tl->sd_flags) sd_flags = (*tl->sd_flags)(); if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, - "wrong sd_flags in topology description\n")) + "wrong sd_flags in topology description\n")) sd_flags &= TOPOLOGY_SD_FLAGS; + sd_flags |= asym_cpu_capacity_classify(sd_span, cpu_map); *sd = (struct sched_domain){ .min_interval = sd_weight, @@ -1674,12 +1678,6 @@ sd_init(struct sched_domain_topology_level *tl, .name = tl->name, }; - sd_span = sched_domain_span(sd); - cpumask_and(sd_span, cpu_map, tl->mask(tl, cpu)); - sd_id = cpumask_first(sd_span); - - sd->flags |= asym_cpu_capacity_classify(sd_span, cpu_map); - WARN_ONCE((sd->flags & (SD_SHARE_CPUCAPACITY | SD_ASYM_CPUCAPACITY)) == (SD_SHARE_CPUCAPACITY | SD_ASYM_CPUCAPACITY), "CPU capacity asymmetry not supported on SMT\n"); From b5232c2f04e13c3cfcea63d250941de7553164de Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 23 Mar 2026 10:36:27 +0100 Subject: [PATCH 0232/1518] sched/topology: Fix sched_domain_span() [ Upstream commit e379dce8af11d8d6040b4348316a499bfd174bfb ] Commit 8e8e23dea43e ("sched/topology: Compute sd_weight considering cpuset partitions") ends up relying on the fact that structure initialization should not touch the flexible array. However, the official GCC specification for "Arrays of Length Zero" [*] says: Although the size of a zero-length array is zero, an array member of this kind may increase the size of the enclosing type as a result of tail padding. Additionally, structure initialization will zero tail padding. With the end result that since offsetof(*type, member) < sizeof(*type), array initialization will clobber the flex array. Luckily, the way flexible array sizes are calculated is: sizeof(*type) + count * sizeof(*type->member) This means we have the complete size of the flex array *outside* of sizeof(*type), so use that instead of relying on the broken flex array definition. [*] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html Fixes: 8e8e23dea43e ("sched/topology: Compute sd_weight considering cpuset partitions") Reported-by: Nathan Chancellor Debugged-by: K Prateek Nayak Signed-off-by: Peter Zijlstra (Intel) Tested-by: Jon Hunter Tested-by: Chen Yu Tested-by: K Prateek Nayak Tested-by: Nathan Chancellor Link: https://patch.msgid.link/20260323093627.GY3738010@noisy.programming.kicks-ass.net Signed-off-by: Sasha Levin --- include/linux/sched/topology.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 45c0022b91ced..6f8a4ae860da8 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -141,18 +141,30 @@ struct sched_domain { unsigned int span_weight; /* - * Span of all CPUs in this domain. + * See sched_domain_span(), on why flex arrays are broken. * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ unsigned long span[]; + */ }; static inline struct cpumask *sched_domain_span(struct sched_domain *sd) { - return to_cpumask(sd->span); + /* + * Turns out that C flexible arrays are fundamentally broken since it + * is allowed for offsetof(*sd, span) < sizeof(*sd), this means that + * structure initialzation *sd = { ... }; which writes every byte + * inside sizeof(*type), will over-write the start of the flexible + * array. + * + * Luckily, the way we allocate sched_domain is by: + * + * sizeof(*sd) + cpumask_size() + * + * this means that we have sufficient space for the whole flex array + * *outside* of sizeof(*sd). So use that, and avoid using sd->span. + */ + unsigned long *bitmap = (void *)sd + sizeof(*sd); + return to_cpumask(bitmap); } extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], From e2a2781d1ae6af658e5524f6b44e97edd3a4f392 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 25 Mar 2026 19:24:18 +0000 Subject: [PATCH 0233/1518] irqchip/renesas-rzg2l: Fix error path in rzg2l_irqc_common_probe() [ Upstream commit fb74e35f78105efd8635c89b39f4389f567edbdc ] Replace pm_runtime_put() with pm_runtime_put_sync() when irq_domain_create_hierarchy() fails to ensure the device suspends synchronously before devres cleanup disables runtime PM via pm_runtime_disable(). [ tglx: Fix up subject and change log to be precise ] Fixes: 7de11369ef30 ("irqchip/renesas-rzg2l: Use devm_pm_runtime_enable()") Signed-off-by: Biju Das Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260325192451.172562-4-biju.das.jz@bp.renesas.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-renesas-rzg2l.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c index 1bf19deb02c4e..c938ab1592895 100644 --- a/drivers/irqchip/irq-renesas-rzg2l.c +++ b/drivers/irqchip/irq-renesas-rzg2l.c @@ -573,7 +573,7 @@ static int rzg2l_irqc_common_probe(struct platform_device *pdev, struct device_n irq_domain = irq_domain_create_hierarchy(parent_domain, 0, IRQC_NUM_IRQ, dev_fwnode(dev), &rzg2l_irqc_domain_ops, rzg2l_irqc_data); if (!irq_domain) { - pm_runtime_put(dev); + pm_runtime_put_sync(dev); return -ENOMEM; } From 7e16c122695c291826634ace50f8ff909edc9541 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 27 Mar 2026 03:15:15 +0100 Subject: [PATCH 0234/1518] ASoC: Intel: avs: Check maximum valid CPUID leaf [ Upstream commit 93a1f0e61329f538cfc7122d7fa0e7a1803e326d ] The Intel AVS driver queries CPUID(0x15) before checking if the CPUID leaf is available. Check the maximum-valid CPU standard leaf beforehand. Use the CPUID_LEAF_TSC macro instead of the custom local one for the CPUID(0x15) leaf number. Fixes: cbe37a4d2b3c ("ASoC: Intel: avs: Configure basefw on TGL-based platforms") Signed-off-by: Ahmed S. Darwish Signed-off-by: Borislav Petkov (AMD) Acked-by: Cezary Rojewski Link: https://patch.msgid.link/20260327021645.555257-2-darwi@linutronix.de Signed-off-by: Sasha Levin --- sound/soc/intel/avs/tgl.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/sound/soc/intel/avs/tgl.c b/sound/soc/intel/avs/tgl.c index afb0665161010..4649d749b41e0 100644 --- a/sound/soc/intel/avs/tgl.c +++ b/sound/soc/intel/avs/tgl.c @@ -11,8 +11,6 @@ #include "debug.h" #include "messages.h" -#define CPUID_TSC_LEAF 0x15 - static int avs_tgl_dsp_core_power(struct avs_dev *adev, u32 core_mask, bool power) { core_mask &= AVS_MAIN_CORE_MASK; @@ -49,7 +47,11 @@ static int avs_tgl_config_basefw(struct avs_dev *adev) unsigned int ecx; #include - ecx = cpuid_ecx(CPUID_TSC_LEAF); + + if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) + goto no_cpuid; + + ecx = cpuid_ecx(CPUID_LEAF_TSC); if (ecx) { ret = avs_ipc_set_fw_config(adev, 1, AVS_FW_CFG_XTAL_FREQ_HZ, sizeof(ecx), &ecx); if (ret) @@ -57,6 +59,7 @@ static int avs_tgl_config_basefw(struct avs_dev *adev) } #endif +no_cpuid: hwid.device = pci->device; hwid.subsystem = pci->subsystem_vendor | (pci->subsystem_device << 16); hwid.revision = pci->revision; From d739426c2fd10fee313b6cdae6748722bb873202 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 27 Mar 2026 03:15:16 +0100 Subject: [PATCH 0235/1518] ASoC: Intel: avs: Include CPUID header at file scope [ Upstream commit 7f78e0b46e9984e955cb73ffada8dace8b4dd059 ] Commit cbe37a4d2b3c ("ASoC: Intel: avs: Configure basefw on TGL-based platforms") includes the main CPUID header from within a C function. This works by luck and forbids valid refactoring inside that header. Include the CPUID header at file scope instead. Remove the COMPILE_TEST build flag so that the CONFIG_X86 conditionals can be removed. The driver gets enough compilation testing already on x86. For clarity, refactor the CPUID(0x15) code into its own function without changing any of the driver's logic. Fixes: cbe37a4d2b3c ("ASoC: Intel: avs: Configure basefw on TGL-based platforms") Suggested-by: Borislav Petkov # CONFIG_X86 removal Signed-off-by: Ahmed S. Darwish Signed-off-by: Borislav Petkov (AMD) Acked-by: Cezary Rojewski Link: https://lore.kernel.org/all/20250612234010.572636-3-darwi@linutronix.de Signed-off-by: Sasha Levin --- sound/soc/intel/Kconfig | 2 +- sound/soc/intel/avs/tgl.c | 37 ++++++++++++++++++++++++------------- 2 files changed, 25 insertions(+), 14 deletions(-) diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index 412555e626b81..63367364916ae 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -95,7 +95,7 @@ config SND_SOC_INTEL_KEEMBAY config SND_SOC_INTEL_AVS tristate "Intel AVS driver" - depends on X86 || COMPILE_TEST + depends on X86 depends on PCI depends on COMMON_CLK select ACPI_NHLT if ACPI diff --git a/sound/soc/intel/avs/tgl.c b/sound/soc/intel/avs/tgl.c index 4649d749b41e0..a7123639de431 100644 --- a/sound/soc/intel/avs/tgl.c +++ b/sound/soc/intel/avs/tgl.c @@ -7,6 +7,7 @@ // #include +#include #include "avs.h" #include "debug.h" #include "messages.h" @@ -38,28 +39,38 @@ static int avs_tgl_dsp_core_stall(struct avs_dev *adev, u32 core_mask, bool stal return avs_dsp_core_stall(adev, core_mask, stall); } -static int avs_tgl_config_basefw(struct avs_dev *adev) +/* + * Succeed if CPUID(0x15) is not available, or if the nominal core crystal clock + * frequency cannot be enumerated from it. There is nothing to do in both cases. + */ +static int avs_tgl_set_xtal_freq(struct avs_dev *adev) { - struct pci_dev *pci = adev->base.pci; - struct avs_bus_hwid hwid; + unsigned int freq; int ret; -#ifdef CONFIG_X86 - unsigned int ecx; - -#include if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) - goto no_cpuid; + return 0; - ecx = cpuid_ecx(CPUID_LEAF_TSC); - if (ecx) { - ret = avs_ipc_set_fw_config(adev, 1, AVS_FW_CFG_XTAL_FREQ_HZ, sizeof(ecx), &ecx); + freq = cpuid_ecx(CPUID_LEAF_TSC); + if (freq) { + ret = avs_ipc_set_fw_config(adev, 1, AVS_FW_CFG_XTAL_FREQ_HZ, sizeof(freq), &freq); if (ret) return AVS_IPC_RET(ret); } -#endif -no_cpuid: + return 0; +} + +static int avs_tgl_config_basefw(struct avs_dev *adev) +{ + struct pci_dev *pci = adev->base.pci; + struct avs_bus_hwid hwid; + int ret; + + ret = avs_tgl_set_xtal_freq(adev); + if (ret) + return ret; + hwid.device = pci->device; hwid.subsystem = pci->subsystem_vendor | (pci->subsystem_device << 16); hwid.revision = pci->revision; From e5bdb8404df4a9dca83d4535496d4b1cb99fee6e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 30 Mar 2026 14:07:55 +0200 Subject: [PATCH 0236/1518] x86/vdso: Clean up remnants of VDSO32_NOTE_MASK MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6517f293b2c6774d21b6e7e26a55fae60c6ec4cf ] VDSO32_NOTE_MASK is not used or provided anymore, remove it. Fixes: a13f2ef168cb ("x86/xen: remove 32-bit Xen PV guest support") Signed-off-by: Thomas Weißschuh Signed-off-by: Ingo Molnar Cc: H. Peter Anvin Cc: Boris Ostrovsky Cc: Juergen Gross Link: https://patch.msgid.link/20260330-vdso-x86-vdso32_note_mask-v1-1-2f5c473327bf@linutronix.de Signed-off-by: Sasha Levin --- arch/x86/entry/vdso/vdso2c.c | 1 - arch/x86/include/asm/vdso.h | 1 - 2 files changed, 2 deletions(-) diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index f84e8f8fa5fe6..b8a555763f437 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -75,7 +75,6 @@ struct vdso_sym { }; struct vdso_sym required_syms[] = { - {"VDSO32_NOTE_MASK", true}, {"__kernel_vsyscall", true}, {"__kernel_sigreturn", true}, {"__kernel_rt_sigreturn", true}, diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index b7253ef3205a6..7bc290ae99334 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -18,7 +18,6 @@ struct vdso_image { unsigned long extable_base, extable_len; const void *extable; - long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; long sym___kernel_vsyscall; From 4bd99f4f86b19f76c25008a57945ea086d6b581b Mon Sep 17 00:00:00 2001 From: "Mario Limonciello (AMD)" Date: Sat, 7 Mar 2026 08:10:20 -0600 Subject: [PATCH 0237/1518] firmware: dmi: Correct an indexing error in dmi.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c064abc68e009d2cc18416e7132d9c25e03125b6 ] The entries later in enum dmi_entry_type don't match the SMBIOS specification¹. The entry for type 33: `64-Bit Memory Error Information` is not present and thus the index for all later entries is incorrect. Add it. Also, add missing entry types 43-46, while at it. ¹ Search for "System Management BIOS (SMBIOS) Reference Specification" [ bp: Drop the flaky SMBIOS spec URL. ] Fixes: 93c890dbe5287 ("firmware: Add DMI entry types to the headers") Signed-off-by: Mario Limonciello (AMD) Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Jean Delvare Reviewed-by: Yazen Ghannam Link: https://patch.msgid.link/20260307141024.819807-2-superm1@kernel.org Signed-off-by: Sasha Levin --- include/linux/dmi.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 927f8a8b7a1dd..2eedf44e68012 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -60,6 +60,7 @@ enum dmi_entry_type { DMI_ENTRY_OOB_REMOTE_ACCESS, DMI_ENTRY_BIS_ENTRY, DMI_ENTRY_SYSTEM_BOOT, + DMI_ENTRY_64_MEM_ERROR, DMI_ENTRY_MGMT_DEV, DMI_ENTRY_MGMT_DEV_COMPONENT, DMI_ENTRY_MGMT_DEV_THRES, @@ -69,6 +70,10 @@ enum dmi_entry_type { DMI_ENTRY_ADDITIONAL, DMI_ENTRY_ONBOARD_DEV_EXT, DMI_ENTRY_MGMT_CONTROLLER_HOST, + DMI_ENTRY_TPM_DEVICE, + DMI_ENTRY_PROCESSOR_ADDITIONAL, + DMI_ENTRY_FIRMWARE_INVENTORY, + DMI_ENTRY_STRING_PROPERTY, DMI_ENTRY_INACTIVE = 126, DMI_ENTRY_END_OF_TABLE = 127, }; From b4f0a37724de1d44be4737e6d8b570d382d17118 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Koutn=C3=BD?= Date: Mon, 23 Mar 2026 13:39:37 +0100 Subject: [PATCH 0238/1518] sched/rt: Skip group schedulable check with rt_group_sched=0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8b016dcec9365675be81d26be88f2c09cf983bd4 ] The warning from the commit 87f1fb77d87a6 ("sched: Add RT_GROUP WARN checks for non-root task_groups") is wrong -- it assumes that only task_groups with rt_rq are traversed, however, the schedulability check would iterate all task_groups even when rt_group_sched=0 is disabled at boot time but some non-root task_groups exist. The schedulability check is supposed to validate: a) that children don't overcommit its parent, b) no RT task group overcommits global RT limit. but with rt_group_sched=0 there is no (non-trivial) hierarchy of RT groups, therefore skip the validation altogether. Otherwise, writes to the global sched_rt_runtime_us knob will be rejected with incorrect validation error. This fix is immaterial with CONFIG_RT_GROUP_SCHED=n. Fixes: 87f1fb77d87a6 ("sched: Add RT_GROUP WARN checks for non-root task_groups") Signed-off-by: Michal Koutný Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260323-sched-rert_groups-v3-1-1e7d5ed6b249@suse.com Signed-off-by: Sasha Levin --- kernel/sched/rt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a892a01c463e5..3e81b9d83d14d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2668,9 +2668,6 @@ static int tg_rt_schedulable(struct task_group *tg, void *data) tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg)) return -EBUSY; - if (WARN_ON(!rt_group_sched_enabled() && tg != &root_task_group)) - return -EBUSY; - total = to_ratio(period, runtime); /* @@ -2814,6 +2811,8 @@ long sched_group_rt_period(struct task_group *tg) static int sched_rt_global_constraints(void) { int ret = 0; + if (!rt_group_sched_enabled()) + return ret; mutex_lock(&rt_constraints_mutex); ret = __rt_schedulable(NULL, 0, 0); From 9fe48cacab63aa1b2e81b133aab048912c09f29e Mon Sep 17 00:00:00 2001 From: Zilin Guan Date: Mon, 19 Jan 2026 09:26:25 +0000 Subject: [PATCH 0239/1518] wifi: mwifiex: Fix memory leak in mwifiex_11n_aggregate_pkt() [ Upstream commit 990a73dec3fdc145fef6c827c29205437d533ece ] In mwifiex_11n_aggregate_pkt(), skb_aggr is allocated via mwifiex_alloc_dma_align_buf(). If mwifiex_is_ralist_valid() returns false, the function currently returns -1 immediately without freeing the previously allocated skb_aggr, causing a memory leak. Since skb_aggr has not yet been queued via skb_queue_tail(), no other references to this memory exist. Therefore, it has to be freed locally before returning the error. Fix this by calling mwifiex_write_data_complete() to free skb_aggr before returning the error status. Compile tested only. Issue found using a prototype static analysis tool and code review. Fixes: 5e6e3a92b9a4 ("wireless: mwifiex: initial commit for Marvell mwifiex driver") Signed-off-by: Zilin Guan Reviewed-by: Jeff Chen Link: https://patch.msgid.link/20260119092625.1349934-1-zilin@seu.edu.cn Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/11n_aggr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/marvell/mwifiex/11n_aggr.c b/drivers/net/wireless/marvell/mwifiex/11n_aggr.c index 34b4b34276d6d..042b1fe5f0d67 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_aggr.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_aggr.c @@ -203,6 +203,7 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv, if (!mwifiex_is_ralist_valid(priv, pra_list, ptrindex)) { spin_unlock_bh(&priv->wmm.ra_list_spinlock); + mwifiex_write_data_complete(adapter, skb_aggr, 1, -1); return -1; } From aa10a452e34810987fb9f4a047995b30003fb53f Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Mon, 23 Feb 2026 12:55:22 +0800 Subject: [PATCH 0240/1518] wifi: rtlwifi: pci: fix possible use-after-free caused by unfinished irq_prepare_bcn_tasklet [ Upstream commit 039cd522dc70151da13329a5e3ae19b1736f468a ] The irq_prepare_bcn_tasklet is initialized in rtl_pci_init() and scheduled when RTL_IMR_BCNINT interrupt is triggered by hardware. But it is never killed in rtl_pci_deinit(). When the rtlwifi card probe fails or is being detached, the ieee80211_hw is deallocated. However, irq_prepare_bcn_tasklet may still be running or pending, leading to use-after-free when the freed ieee80211_hw is accessed in _rtl_pci_prepare_bcn_tasklet(). Similar to irq_tasklet, add tasklet_kill() in rtl_pci_deinit() to ensure that irq_prepare_bcn_tasklet is properly terminated before the ieee80211_hw is released. The issue was identified through static analysis. Fixes: 0c8173385e54 ("rtl8192ce: Add new driver") Signed-off-by: Duoming Zhou Acked-by: Ping-Ke Shih Signed-off-by: Ping-Ke Shih Link: https://patch.msgid.link/20260223045522.48377-1-duoming@zju.edu.cn Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index d080469264cf8..f0010336e78c1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -1674,6 +1674,7 @@ static void rtl_pci_deinit(struct ieee80211_hw *hw) synchronize_irq(rtlpci->pdev->irq); tasklet_kill(&rtlpriv->works.irq_tasklet); + tasklet_kill(&rtlpriv->works.irq_prepare_bcn_tasklet); cancel_work_sync(&rtlpriv->works.lps_change_work); } From 5500913516e071dbe23e5a404c861dd2d82c9589 Mon Sep 17 00:00:00 2001 From: Feng Yang Date: Wed, 4 Mar 2026 17:44:28 +0800 Subject: [PATCH 0241/1518] bpf: test_run: Fix the null pointer dereference issue in bpf_lwt_xmit_push_encap [ Upstream commit 972787479ee73006fddb5e59ab5c8e733810ff42 ] The bpf_lwt_xmit_push_encap helper needs to access skb_dst(skb)->dev to calculate the needed headroom: err = skb_cow_head(skb, len + LL_RESERVED_SPACE(skb_dst(skb)->dev)); But skb->_skb_refdst may not be initialized when the skb is set up by bpf_prog_test_run_skb function. Executing bpf_lwt_push_ip_encap function in this scenario will trigger null pointer dereference, causing a kernel crash as Yinhao reported: [ 105.186365] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 105.186382] #PF: supervisor read access in kernel mode [ 105.186388] #PF: error_code(0x0000) - not-present page [ 105.186393] PGD 121d3d067 P4D 121d3d067 PUD 106c83067 PMD 0 [ 105.186404] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 105.186412] CPU: 3 PID: 3250 Comm: poc Kdump: loaded Not tainted 6.19.0-rc5 #1 [ 105.186423] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 105.186427] RIP: 0010:bpf_lwt_push_ip_encap+0x1eb/0x520 [ 105.186443] Code: 0f 84 de 01 00 00 0f b7 4a 04 66 85 c9 0f 85 47 01 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e c3 cc cc cc cc 48 8b 73 58 48 83 e6 fe <48> 8b 36 0f b7 be ec 00 00 00 0f b7 b6 e6 00 00 00 01 fe 83 e6 f0 [ 105.186449] RSP: 0018:ffffbb0e0387bc50 EFLAGS: 00010246 [ 105.186455] RAX: 000000000000004e RBX: ffff94c74e036500 RCX: ffff94c74874da00 [ 105.186460] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff94c74e036500 [ 105.186463] RBP: 0000000000000001 R08: 0000000000000002 R09: 0000000000000000 [ 105.186467] R10: ffffbb0e0387bd50 R11: 0000000000000000 R12: ffffbb0e0387bc98 [ 105.186471] R13: 0000000000000014 R14: 0000000000000000 R15: 0000000000000002 [ 105.186484] FS: 00007f166aa4d680(0000) GS:ffff94c8b7780000(0000) knlGS:0000000000000000 [ 105.186490] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 105.186494] CR2: 0000000000000000 CR3: 000000015eade001 CR4: 0000000000770ee0 [ 105.186499] PKRU: 55555554 [ 105.186502] Call Trace: [ 105.186507] [ 105.186513] bpf_lwt_xmit_push_encap+0x2b/0x40 [ 105.186522] bpf_prog_a75eaad51e517912+0x41/0x49 [ 105.186536] ? kvm_clock_get_cycles+0x18/0x30 [ 105.186547] ? ktime_get+0x3c/0xa0 [ 105.186554] bpf_test_run+0x195/0x320 [ 105.186563] ? bpf_test_run+0x10f/0x320 [ 105.186579] bpf_prog_test_run_skb+0x2f5/0x4f0 [ 105.186590] __sys_bpf+0x69c/0xa40 [ 105.186603] __x64_sys_bpf+0x1e/0x30 [ 105.186611] do_syscall_64+0x59/0x110 [ 105.186620] entry_SYSCALL_64_after_hwframe+0x76/0xe0 [ 105.186649] RIP: 0033:0x7f166a97455d Temporarily add the setting of skb->_skb_refdst before bpf_test_run to resolve the issue. Fixes: 52f278774e79 ("bpf: implement BPF_LWT_ENCAP_IP mode in bpf_lwt_push_encap") Reported-by: Yinhao Hu Reported-by: Kaiyan Mei Closes: https://groups.google.com/g/hust-os-kernel-patches/c/8-a0kPpBW2s Signed-off-by: Yun Lu Signed-off-by: Feng Yang Signed-off-by: Martin KaFai Lau Tested-by: syzbot@syzkaller.appspotmail.com Link: https://patch.msgid.link/20260304094429.168521-2-yangfeng59949@163.com Signed-off-by: Sasha Levin --- net/bpf/test_run.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6b04f47301c1e..65d7f8d51823e 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1093,6 +1093,21 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb->ip_summed = CHECKSUM_COMPLETE; } + if (prog->type == BPF_PROG_TYPE_LWT_XMIT) { + if (!ipv6_bpf_stub) { + pr_warn_once("Please test this program with the IPv6 module loaded\n"); + ret = -EOPNOTSUPP; + goto out; + } +#if IS_ENABLED(CONFIG_IPV6) + /* For CONFIG_IPV6=n, ipv6_bpf_stub is NULL which is + * handled by the above if statement. + */ + dst_hold(&net->ipv6.ip6_null_entry->dst); + skb_dst_set(skb, &net->ipv6.ip6_null_entry->dst); +#endif + } + ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false); if (ret) goto out; From 3f459076b2d823cd8e52b701f7259236bde4d4bc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 Nov 2025 15:36:49 +0100 Subject: [PATCH 0242/1518] wifi: ieee80211: split mesh definitions out [ Upstream commit 69674282fc97fffd98a85ab5b4837edbc5898145 ] The ieee80211.h file has gotten very long, start splitting it by putting mesh definitions into a separate file. Link: https://patch.msgid.link/20251105153843.489713ca8b34.I3befb4bf6ace0315758a1794224ddd18c4652e32@changeid Signed-off-by: Johannes Berg Stable-dep-of: cb0caadb64ca ("wifi: ieee80211: fix definition of EHT-MCS 15 in MRU") Signed-off-by: Sasha Levin --- include/linux/ieee80211-mesh.h | 230 +++++++++++++++++++++++++++++++++ include/linux/ieee80211.h | 211 +----------------------------- 2 files changed, 232 insertions(+), 209 deletions(-) create mode 100644 include/linux/ieee80211-mesh.h diff --git a/include/linux/ieee80211-mesh.h b/include/linux/ieee80211-mesh.h new file mode 100644 index 0000000000000..4b829bcb38b61 --- /dev/null +++ b/include/linux/ieee80211-mesh.h @@ -0,0 +1,230 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 mesh definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_MESH_H +#define LINUX_IEEE80211_MESH_H + +#include +#include + +#define IEEE80211_MAX_MESH_ID_LEN 32 + +struct ieee80211s_hdr { + u8 flags; + u8 ttl; + __le32 seqnum; + u8 eaddr1[ETH_ALEN]; + u8 eaddr2[ETH_ALEN]; +} __packed __aligned(2); + +/* Mesh flags */ +#define MESH_FLAGS_AE_A4 0x1 +#define MESH_FLAGS_AE_A5_A6 0x2 +#define MESH_FLAGS_AE 0x3 +#define MESH_FLAGS_PS_DEEP 0x4 + +/** + * enum ieee80211_preq_flags - mesh PREQ element flags + * + * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield + */ +enum ieee80211_preq_flags { + IEEE80211_PREQ_PROACTIVE_PREP_FLAG = 1<<2, +}; + +/** + * enum ieee80211_preq_target_flags - mesh PREQ element per target flags + * + * @IEEE80211_PREQ_TO_FLAG: target only subfield + * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield + */ +enum ieee80211_preq_target_flags { + IEEE80211_PREQ_TO_FLAG = 1<<0, + IEEE80211_PREQ_USN_FLAG = 1<<2, +}; + +/** + * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE + * @mesh_ttl: Time To Live + * @mesh_flags: Flags + * @mesh_reason: Reason Code + * @mesh_pre_value: Precedence Value + * + * This structure represents the payload of the "Mesh Channel Switch + * Parameters element" as described in IEEE Std 802.11-2020 section + * 9.4.2.102. + */ +struct ieee80211_mesh_chansw_params_ie { + u8 mesh_ttl; + u8 mesh_flags; + __le16 mesh_reason; + __le16 mesh_pre_value; +} __packed; + +/** + * struct ieee80211_meshconf_ie - Mesh Configuration element + * @meshconf_psel: Active Path Selection Protocol Identifier + * @meshconf_pmetric: Active Path Selection Metric Identifier + * @meshconf_congest: Congestion Control Mode Identifier + * @meshconf_synch: Synchronization Method Identifier + * @meshconf_auth: Authentication Protocol Identifier + * @meshconf_form: Mesh Formation Info + * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) + * + * This structure represents the payload of the "Mesh Configuration + * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. + */ +struct ieee80211_meshconf_ie { + u8 meshconf_psel; + u8 meshconf_pmetric; + u8 meshconf_congest; + u8 meshconf_synch; + u8 meshconf_auth; + u8 meshconf_form; + u8 meshconf_cap; +} __packed; + +/** + * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags + * + * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish + * additional mesh peerings with other mesh STAs + * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs + * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure + * is ongoing + * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has + * neighbors in deep sleep mode + * + * Enumerates the "Mesh Capability" as described in IEEE Std + * 802.11-2020 section 9.4.2.97.7. + */ +enum mesh_config_capab_flags { + IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, + IEEE80211_MESHCONF_CAPAB_FORWARDING = 0x08, + IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING = 0x20, + IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL = 0x40, +}; + +#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 + +/* + * mesh channel switch parameters element's flag indicator + * + */ +#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0) +#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1) +#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) + +/** + * struct ieee80211_rann_ie - RANN (root announcement) element + * @rann_flags: Flags + * @rann_hopcount: Hop Count + * @rann_ttl: Element TTL + * @rann_addr: Root Mesh STA Address + * @rann_seq: HWMP Sequence Number + * @rann_interval: Interval + * @rann_metric: Metric + * + * This structure represents the payload of the "RANN element" as + * described in IEEE Std 802.11-2020 section 9.4.2.111. + */ +struct ieee80211_rann_ie { + u8 rann_flags; + u8 rann_hopcount; + u8 rann_ttl; + u8 rann_addr[ETH_ALEN]; + __le32 rann_seq; + __le32 rann_interval; + __le32 rann_metric; +} __packed; + +enum ieee80211_rann_flags { + RANN_FLAG_IS_GATE = 1 << 0, +}; + +/* Mesh action codes */ +enum ieee80211_mesh_actioncode { + WLAN_MESH_ACTION_LINK_METRIC_REPORT, + WLAN_MESH_ACTION_HWMP_PATH_SELECTION, + WLAN_MESH_ACTION_GATE_ANNOUNCEMENT, + WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION, + WLAN_MESH_ACTION_MCCA_SETUP_REQUEST, + WLAN_MESH_ACTION_MCCA_SETUP_REPLY, + WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST, + WLAN_MESH_ACTION_MCCA_ADVERTISEMENT, + WLAN_MESH_ACTION_MCCA_TEARDOWN, + WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST, + WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE, +}; + +/** + * enum ieee80211_mesh_sync_method - mesh synchronization method identifier + * + * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method + * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method + * that will be specified in a vendor specific information element + */ +enum ieee80211_mesh_sync_method { + IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, + IEEE80211_SYNC_METHOD_VENDOR = 255, +}; + +/** + * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier + * + * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol + * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will + * be specified in a vendor specific information element + */ +enum ieee80211_mesh_path_protocol { + IEEE80211_PATH_PROTOCOL_HWMP = 1, + IEEE80211_PATH_PROTOCOL_VENDOR = 255, +}; + +/** + * enum ieee80211_mesh_path_metric - mesh path selection metric identifier + * + * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric + * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be + * specified in a vendor specific information element + */ +enum ieee80211_mesh_path_metric { + IEEE80211_PATH_METRIC_AIRTIME = 1, + IEEE80211_PATH_METRIC_VENDOR = 255, +}; + +/** + * enum ieee80211_root_mode_identifier - root mesh STA mode identifier + * + * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode + * + * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default) + * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than + * this value + * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports + * the proactive PREQ with proactive PREP subfield set to 0 + * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA + * supports the proactive PREQ with proactive PREP subfield set to 1 + * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports + * the proactive RANN + */ +enum ieee80211_root_mode_identifier { + IEEE80211_ROOTMODE_NO_ROOT = 0, + IEEE80211_ROOTMODE_ROOT = 1, + IEEE80211_PROACTIVE_PREQ_NO_PREP = 2, + IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3, + IEEE80211_PROACTIVE_RANN = 4, +}; + +#endif /* LINUX_IEEE80211_MESH_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 1f4679092e69d..ebc12d1939273 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -252,8 +252,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_MAX_SSID_LEN 32 -#define IEEE80211_MAX_MESH_ID_LEN 32 - #define IEEE80211_FIRST_TSPEC_TSID 8 #define IEEE80211_NUM_TIDS 16 @@ -881,40 +879,6 @@ static inline u16 ieee80211_get_sn(struct ieee80211_hdr *hdr) return le16_get_bits(hdr->seq_ctrl, IEEE80211_SCTL_SEQ); } -struct ieee80211s_hdr { - u8 flags; - u8 ttl; - __le32 seqnum; - u8 eaddr1[ETH_ALEN]; - u8 eaddr2[ETH_ALEN]; -} __packed __aligned(2); - -/* Mesh flags */ -#define MESH_FLAGS_AE_A4 0x1 -#define MESH_FLAGS_AE_A5_A6 0x2 -#define MESH_FLAGS_AE 0x3 -#define MESH_FLAGS_PS_DEEP 0x4 - -/** - * enum ieee80211_preq_flags - mesh PREQ element flags - * - * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield - */ -enum ieee80211_preq_flags { - IEEE80211_PREQ_PROACTIVE_PREP_FLAG = 1<<2, -}; - -/** - * enum ieee80211_preq_target_flags - mesh PREQ element per target flags - * - * @IEEE80211_PREQ_TO_FLAG: target only subfield - * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield - */ -enum ieee80211_preq_target_flags { - IEEE80211_PREQ_TO_FLAG = 1<<0, - IEEE80211_PREQ_USN_FLAG = 1<<2, -}; - /** * struct ieee80211_quiet_ie - Quiet element * @count: Quiet Count @@ -993,24 +957,6 @@ struct ieee80211_sec_chan_offs_ie { u8 sec_chan_offs; } __packed; -/** - * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE - * @mesh_ttl: Time To Live - * @mesh_flags: Flags - * @mesh_reason: Reason Code - * @mesh_pre_value: Precedence Value - * - * This structure represents the payload of the "Mesh Channel Switch - * Parameters element" as described in IEEE Std 802.11-2020 section - * 9.4.2.102. - */ -struct ieee80211_mesh_chansw_params_ie { - u8 mesh_ttl; - u8 mesh_flags; - __le16 mesh_reason; - __le16 mesh_pre_value; -} __packed; - /** * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE * @new_channel_width: New Channel Width @@ -1051,87 +997,6 @@ struct ieee80211_tim_ie { }; } __packed; -/** - * struct ieee80211_meshconf_ie - Mesh Configuration element - * @meshconf_psel: Active Path Selection Protocol Identifier - * @meshconf_pmetric: Active Path Selection Metric Identifier - * @meshconf_congest: Congestion Control Mode Identifier - * @meshconf_synch: Synchronization Method Identifier - * @meshconf_auth: Authentication Protocol Identifier - * @meshconf_form: Mesh Formation Info - * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) - * - * This structure represents the payload of the "Mesh Configuration - * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. - */ -struct ieee80211_meshconf_ie { - u8 meshconf_psel; - u8 meshconf_pmetric; - u8 meshconf_congest; - u8 meshconf_synch; - u8 meshconf_auth; - u8 meshconf_form; - u8 meshconf_cap; -} __packed; - -/** - * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags - * - * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish - * additional mesh peerings with other mesh STAs - * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs - * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure - * is ongoing - * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has - * neighbors in deep sleep mode - * - * Enumerates the "Mesh Capability" as described in IEEE Std - * 802.11-2020 section 9.4.2.97.7. - */ -enum mesh_config_capab_flags { - IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, - IEEE80211_MESHCONF_CAPAB_FORWARDING = 0x08, - IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING = 0x20, - IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL = 0x40, -}; - -#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 - -/* - * mesh channel switch parameters element's flag indicator - * - */ -#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0) -#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1) -#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) - -/** - * struct ieee80211_rann_ie - RANN (root announcement) element - * @rann_flags: Flags - * @rann_hopcount: Hop Count - * @rann_ttl: Element TTL - * @rann_addr: Root Mesh STA Address - * @rann_seq: HWMP Sequence Number - * @rann_interval: Interval - * @rann_metric: Metric - * - * This structure represents the payload of the "RANN element" as - * described in IEEE Std 802.11-2020 section 9.4.2.111. - */ -struct ieee80211_rann_ie { - u8 rann_flags; - u8 rann_hopcount; - u8 rann_ttl; - u8 rann_addr[ETH_ALEN]; - __le32 rann_seq; - __le32 rann_interval; - __le32 rann_metric; -} __packed; - -enum ieee80211_rann_flags { - RANN_FLAG_IS_GATE = 1 << 0, -}; - enum ieee80211_ht_chanwidth_values { IEEE80211_HT_CHANWIDTH_20MHZ = 0, IEEE80211_HT_CHANWIDTH_ANY = 1, @@ -3971,21 +3836,6 @@ enum ieee80211_self_protected_actioncode { WLAN_SP_MGK_ACK = 5, }; -/* Mesh action codes */ -enum ieee80211_mesh_actioncode { - WLAN_MESH_ACTION_LINK_METRIC_REPORT, - WLAN_MESH_ACTION_HWMP_PATH_SELECTION, - WLAN_MESH_ACTION_GATE_ANNOUNCEMENT, - WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION, - WLAN_MESH_ACTION_MCCA_SETUP_REQUEST, - WLAN_MESH_ACTION_MCCA_SETUP_REPLY, - WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST, - WLAN_MESH_ACTION_MCCA_ADVERTISEMENT, - WLAN_MESH_ACTION_MCCA_TEARDOWN, - WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST, - WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE, -}; - /* Unprotected WNM action codes */ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIM = 0, @@ -4198,65 +4048,6 @@ enum ieee80211_tdls_actioncode { /* BSS Coex IE information field bits */ #define WLAN_BSS_COEX_INFORMATION_REQUEST BIT(0) -/** - * enum ieee80211_mesh_sync_method - mesh synchronization method identifier - * - * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method - * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method - * that will be specified in a vendor specific information element - */ -enum ieee80211_mesh_sync_method { - IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, - IEEE80211_SYNC_METHOD_VENDOR = 255, -}; - -/** - * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier - * - * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol - * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will - * be specified in a vendor specific information element - */ -enum ieee80211_mesh_path_protocol { - IEEE80211_PATH_PROTOCOL_HWMP = 1, - IEEE80211_PATH_PROTOCOL_VENDOR = 255, -}; - -/** - * enum ieee80211_mesh_path_metric - mesh path selection metric identifier - * - * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric - * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be - * specified in a vendor specific information element - */ -enum ieee80211_mesh_path_metric { - IEEE80211_PATH_METRIC_AIRTIME = 1, - IEEE80211_PATH_METRIC_VENDOR = 255, -}; - -/** - * enum ieee80211_root_mode_identifier - root mesh STA mode identifier - * - * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode - * - * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default) - * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than - * this value - * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports - * the proactive PREQ with proactive PREP subfield set to 0 - * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA - * supports the proactive PREQ with proactive PREP subfield set to 1 - * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports - * the proactive RANN - */ -enum ieee80211_root_mode_identifier { - IEEE80211_ROOTMODE_NO_ROOT = 0, - IEEE80211_ROOTMODE_ROOT = 1, - IEEE80211_PROACTIVE_PREQ_NO_PREP = 2, - IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3, - IEEE80211_PROACTIVE_RANN = 4, -}; - /* * IEEE 802.11-2007 7.3.2.9 Country information element * @@ -6098,4 +5889,6 @@ static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) #define NAN_DEV_CAPA_NDPE_SUPPORTED 0x08 #define NAN_DEV_CAPA_S3_SUPPORTED 0x10 +#include "ieee80211-mesh.h" + #endif /* LINUX_IEEE80211_H */ From 4d5caab09dabaf293b2fd8f9202ff4a2f3111b65 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 Nov 2025 15:36:50 +0100 Subject: [PATCH 0243/1518] wifi: ieee80211: split HT definitions out [ Upstream commit fdc1c141f3ef4dc94e3880e973061681843f62c0 ] The ieee80211.h file has gotten very long, continue splitting it by putting HT definitions into a separate file. Link: https://patch.msgid.link/20251105153843.7532471178d0.Id956a5433ad8658e4e5c0272dbcbb59587206142@changeid Signed-off-by: Johannes Berg Stable-dep-of: cb0caadb64ca ("wifi: ieee80211: fix definition of EHT-MCS 15 in MRU") Signed-off-by: Sasha Levin --- include/linux/ieee80211-ht.h | 292 +++++++++++++++++++++++++++++++++++ include/linux/ieee80211.h | 272 +------------------------------- 2 files changed, 293 insertions(+), 271 deletions(-) create mode 100644 include/linux/ieee80211-ht.h diff --git a/include/linux/ieee80211-ht.h b/include/linux/ieee80211-ht.h new file mode 100644 index 0000000000000..21bbf470540f6 --- /dev/null +++ b/include/linux/ieee80211-ht.h @@ -0,0 +1,292 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 HT definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_HT_H +#define LINUX_IEEE80211_HT_H + +#include +#include + +/* Maximal size of an A-MSDU that can be transported in a HT BA session */ +#define IEEE80211_MAX_MPDU_LEN_HT_BA 4095 + +/* Maximal size of an A-MSDU */ +#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 +#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 + +#define IEEE80211_HT_CTL_LEN 4 + +enum ieee80211_ht_chanwidth_values { + IEEE80211_HT_CHANWIDTH_20MHZ = 0, + IEEE80211_HT_CHANWIDTH_ANY = 1, +}; + +/** + * struct ieee80211_bar - Block Ack Request frame format + * @frame_control: Frame Control + * @duration: Duration + * @ra: RA + * @ta: TA + * @control: BAR Control + * @start_seq_num: Starting Sequence Number (see Figure 9-37) + * + * This structure represents the "BlockAckReq frame format" + * as described in IEEE Std 802.11-2020 section 9.3.1.7. +*/ +struct ieee80211_bar { + __le16 frame_control; + __le16 duration; + __u8 ra[ETH_ALEN]; + __u8 ta[ETH_ALEN]; + __le16 control; + __le16 start_seq_num; +} __packed; + +/* 802.11 BAR control masks */ +#define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL 0x0000 +#define IEEE80211_BAR_CTRL_MULTI_TID 0x0002 +#define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA 0x0004 +#define IEEE80211_BAR_CTRL_TID_INFO_MASK 0xf000 +#define IEEE80211_BAR_CTRL_TID_INFO_SHIFT 12 + +#define IEEE80211_HT_MCS_MASK_LEN 10 + +/** + * struct ieee80211_mcs_info - Supported MCS Set field + * @rx_mask: RX mask + * @rx_highest: highest supported RX rate. If set represents + * the highest supported RX data rate in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. + * @tx_params: TX parameters + * @reserved: Reserved bits + * + * This structure represents the "Supported MCS Set field" as + * described in IEEE Std 802.11-2020 section 9.4.2.55.4. + */ +struct ieee80211_mcs_info { + u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; + __le16 rx_highest; + u8 tx_params; + u8 reserved[3]; +} __packed; + +/* 802.11n HT capability MSC set */ +#define IEEE80211_HT_MCS_RX_HIGHEST_MASK 0x3ff +#define IEEE80211_HT_MCS_TX_DEFINED 0x01 +#define IEEE80211_HT_MCS_TX_RX_DIFF 0x02 +/* value 0 == 1 stream etc */ +#define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK 0x0C +#define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT 2 +#define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 +#define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 + +#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) + +/* + * 802.11n D5.0 20.3.5 / 20.6 says: + * - indices 0 to 7 and 32 are single spatial stream + * - 8 to 31 are multiple spatial streams using equal modulation + * [8..15 for two streams, 16..23 for three and 24..31 for four] + * - remainder are multiple spatial streams using unequal modulation + */ +#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33 +#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \ + (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) + +/** + * struct ieee80211_ht_cap - HT capabilities element + * @cap_info: HT Capability Information + * @ampdu_params_info: A-MPDU Parameters + * @mcs: Supported MCS Set + * @extended_ht_cap_info: HT Extended Capabilities + * @tx_BF_cap_info: Transmit Beamforming Capabilities + * @antenna_selection_info: ASEL Capability + * + * This structure represents the payload of the "HT Capabilities + * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. + */ +struct ieee80211_ht_cap { + __le16 cap_info; + u8 ampdu_params_info; + + /* 16 bytes MCS information */ + struct ieee80211_mcs_info mcs; + + __le16 extended_ht_cap_info; + __le32 tx_BF_cap_info; + u8 antenna_selection_info; +} __packed; + +/* 802.11n HT capabilities masks (for cap_info) */ +#define IEEE80211_HT_CAP_LDPC_CODING 0x0001 +#define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 +#define IEEE80211_HT_CAP_SM_PS 0x000C +#define IEEE80211_HT_CAP_SM_PS_SHIFT 2 +#define IEEE80211_HT_CAP_GRN_FLD 0x0010 +#define IEEE80211_HT_CAP_SGI_20 0x0020 +#define IEEE80211_HT_CAP_SGI_40 0x0040 +#define IEEE80211_HT_CAP_TX_STBC 0x0080 +#define IEEE80211_HT_CAP_RX_STBC 0x0300 +#define IEEE80211_HT_CAP_RX_STBC_SHIFT 8 +#define IEEE80211_HT_CAP_DELAY_BA 0x0400 +#define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 +#define IEEE80211_HT_CAP_DSSSCCK40 0x1000 +#define IEEE80211_HT_CAP_RESERVED 0x2000 +#define IEEE80211_HT_CAP_40MHZ_INTOLERANT 0x4000 +#define IEEE80211_HT_CAP_LSIG_TXOP_PROT 0x8000 + +/* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */ +#define IEEE80211_HT_EXT_CAP_PCO 0x0001 +#define IEEE80211_HT_EXT_CAP_PCO_TIME 0x0006 +#define IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT 1 +#define IEEE80211_HT_EXT_CAP_MCS_FB 0x0300 +#define IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT 8 +#define IEEE80211_HT_EXT_CAP_HTC_SUP 0x0400 +#define IEEE80211_HT_EXT_CAP_RD_RESPONDER 0x0800 + +/* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ +#define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 +#define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C +#define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 + +/* + * Maximum length of AMPDU that the STA can receive in high-throughput (HT). + * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) + */ +enum ieee80211_max_ampdu_length_exp { + IEEE80211_HT_MAX_AMPDU_8K = 0, + IEEE80211_HT_MAX_AMPDU_16K = 1, + IEEE80211_HT_MAX_AMPDU_32K = 2, + IEEE80211_HT_MAX_AMPDU_64K = 3 +}; + +#define IEEE80211_HT_MAX_AMPDU_FACTOR 13 + +/* Minimum MPDU start spacing */ +enum ieee80211_min_mpdu_spacing { + IEEE80211_HT_MPDU_DENSITY_NONE = 0, /* No restriction */ + IEEE80211_HT_MPDU_DENSITY_0_25 = 1, /* 1/4 usec */ + IEEE80211_HT_MPDU_DENSITY_0_5 = 2, /* 1/2 usec */ + IEEE80211_HT_MPDU_DENSITY_1 = 3, /* 1 usec */ + IEEE80211_HT_MPDU_DENSITY_2 = 4, /* 2 usec */ + IEEE80211_HT_MPDU_DENSITY_4 = 5, /* 4 usec */ + IEEE80211_HT_MPDU_DENSITY_8 = 6, /* 8 usec */ + IEEE80211_HT_MPDU_DENSITY_16 = 7 /* 16 usec */ +}; + +/** + * struct ieee80211_ht_operation - HT operation IE + * @primary_chan: Primary Channel + * @ht_param: HT Operation Information parameters + * @operation_mode: HT Operation Information operation mode + * @stbc_param: HT Operation Information STBC params + * @basic_set: Basic HT-MCS Set + * + * This structure represents the payload of the "HT Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. + */ +struct ieee80211_ht_operation { + u8 primary_chan; + u8 ht_param; + __le16 operation_mode; + __le16 stbc_param; + u8 basic_set[16]; +} __packed; + +/* for ht_param */ +#define IEEE80211_HT_PARAM_CHA_SEC_OFFSET 0x03 +#define IEEE80211_HT_PARAM_CHA_SEC_NONE 0x00 +#define IEEE80211_HT_PARAM_CHA_SEC_ABOVE 0x01 +#define IEEE80211_HT_PARAM_CHA_SEC_BELOW 0x03 +#define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY 0x04 +#define IEEE80211_HT_PARAM_RIFS_MODE 0x08 + +/* for operation_mode */ +#define IEEE80211_HT_OP_MODE_PROTECTION 0x0003 +#define IEEE80211_HT_OP_MODE_PROTECTION_NONE 0 +#define IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER 1 +#define IEEE80211_HT_OP_MODE_PROTECTION_20MHZ 2 +#define IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED 3 +#define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT 0x0004 +#define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT 0x0010 +#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT 5 +#define IEEE80211_HT_OP_MODE_CCFS2_MASK 0x1fe0 + +/* for stbc_param */ +#define IEEE80211_HT_STBC_PARAM_DUAL_BEACON 0x0040 +#define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT 0x0080 +#define IEEE80211_HT_STBC_PARAM_STBC_BEACON 0x0100 +#define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT 0x0200 +#define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE 0x0400 +#define IEEE80211_HT_STBC_PARAM_PCO_PHASE 0x0800 + + +/* block-ack parameters */ +#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 +#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 +#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C +#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 +#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000 +#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 + +/* + * A-MPDU buffer sizes + * According to HT size varies from 8 to 64 frames + * HE adds the ability to have up to 256 frames. + * EHT adds the ability to have up to 1K frames. + */ +#define IEEE80211_MIN_AMPDU_BUF 0x8 +#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 +#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 +#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 + + +/* Spatial Multiplexing Power Save Modes (for capability) */ +#define WLAN_HT_CAP_SM_PS_STATIC 0 +#define WLAN_HT_CAP_SM_PS_DYNAMIC 1 +#define WLAN_HT_CAP_SM_PS_INVALID 2 +#define WLAN_HT_CAP_SM_PS_DISABLED 3 + +/* for SM power control field lower two bits */ +#define WLAN_HT_SMPS_CONTROL_DISABLED 0 +#define WLAN_HT_SMPS_CONTROL_STATIC 1 +#define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 + +/* HT action codes */ +enum ieee80211_ht_actioncode { + WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, + WLAN_HT_ACTION_SMPS = 1, + WLAN_HT_ACTION_PSMP = 2, + WLAN_HT_ACTION_PCO_PHASE = 3, + WLAN_HT_ACTION_CSI = 4, + WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, + WLAN_HT_ACTION_COMPRESSED_BF = 6, + WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, +}; + +/* BACK action code */ +enum ieee80211_back_actioncode { + WLAN_ACTION_ADDBA_REQ = 0, + WLAN_ACTION_ADDBA_RESP = 1, + WLAN_ACTION_DELBA = 2, +}; + +/* BACK (block-ack) parties */ +enum ieee80211_back_parties { + WLAN_BACK_RECIPIENT = 0, + WLAN_BACK_INITIATOR = 1, +}; + +#endif /* LINUX_IEEE80211_HT_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ebc12d1939273..f0a7899fb6626 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -239,13 +239,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 -/* Maximal size of an A-MSDU that can be transported in a HT BA session */ -#define IEEE80211_MAX_MPDU_LEN_HT_BA 4095 - -/* Maximal size of an A-MSDU */ -#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 -#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 - #define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 #define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 #define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 @@ -302,8 +295,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT 5 -#define IEEE80211_HT_CTL_LEN 4 - /* trigger type within common_info of trigger frame */ #define IEEE80211_TRIGGER_TYPE_MASK 0xf #define IEEE80211_TRIGGER_TYPE_BASIC 0x0 @@ -997,11 +988,6 @@ struct ieee80211_tim_ie { }; } __packed; -enum ieee80211_ht_chanwidth_values { - IEEE80211_HT_CHANWIDTH_20MHZ = 0, - IEEE80211_HT_CHANWIDTH_ANY = 1, -}; - /** * enum ieee80211_vht_opmode_bits - VHT operating mode field bits * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask @@ -1677,146 +1663,6 @@ struct ieee80211_p2p_noa_attr { #define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F -/** - * struct ieee80211_bar - Block Ack Request frame format - * @frame_control: Frame Control - * @duration: Duration - * @ra: RA - * @ta: TA - * @control: BAR Control - * @start_seq_num: Starting Sequence Number (see Figure 9-37) - * - * This structure represents the "BlockAckReq frame format" - * as described in IEEE Std 802.11-2020 section 9.3.1.7. -*/ -struct ieee80211_bar { - __le16 frame_control; - __le16 duration; - __u8 ra[ETH_ALEN]; - __u8 ta[ETH_ALEN]; - __le16 control; - __le16 start_seq_num; -} __packed; - -/* 802.11 BAR control masks */ -#define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL 0x0000 -#define IEEE80211_BAR_CTRL_MULTI_TID 0x0002 -#define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA 0x0004 -#define IEEE80211_BAR_CTRL_TID_INFO_MASK 0xf000 -#define IEEE80211_BAR_CTRL_TID_INFO_SHIFT 12 - -#define IEEE80211_HT_MCS_MASK_LEN 10 - -/** - * struct ieee80211_mcs_info - Supported MCS Set field - * @rx_mask: RX mask - * @rx_highest: highest supported RX rate. If set represents - * the highest supported RX data rate in units of 1 Mbps. - * If this field is 0 this value should not be used to - * consider the highest RX data rate supported. - * @tx_params: TX parameters - * @reserved: Reserved bits - * - * This structure represents the "Supported MCS Set field" as - * described in IEEE Std 802.11-2020 section 9.4.2.55.4. - */ -struct ieee80211_mcs_info { - u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; - __le16 rx_highest; - u8 tx_params; - u8 reserved[3]; -} __packed; - -/* 802.11n HT capability MSC set */ -#define IEEE80211_HT_MCS_RX_HIGHEST_MASK 0x3ff -#define IEEE80211_HT_MCS_TX_DEFINED 0x01 -#define IEEE80211_HT_MCS_TX_RX_DIFF 0x02 -/* value 0 == 1 stream etc */ -#define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK 0x0C -#define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT 2 -#define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 -#define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 - -#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) - -/* - * 802.11n D5.0 20.3.5 / 20.6 says: - * - indices 0 to 7 and 32 are single spatial stream - * - 8 to 31 are multiple spatial streams using equal modulation - * [8..15 for two streams, 16..23 for three and 24..31 for four] - * - remainder are multiple spatial streams using unequal modulation - */ -#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33 -#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \ - (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) - -/** - * struct ieee80211_ht_cap - HT capabilities element - * @cap_info: HT Capability Information - * @ampdu_params_info: A-MPDU Parameters - * @mcs: Supported MCS Set - * @extended_ht_cap_info: HT Extended Capabilities - * @tx_BF_cap_info: Transmit Beamforming Capabilities - * @antenna_selection_info: ASEL Capability - * - * This structure represents the payload of the "HT Capabilities - * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. - */ -struct ieee80211_ht_cap { - __le16 cap_info; - u8 ampdu_params_info; - - /* 16 bytes MCS information */ - struct ieee80211_mcs_info mcs; - - __le16 extended_ht_cap_info; - __le32 tx_BF_cap_info; - u8 antenna_selection_info; -} __packed; - -/* 802.11n HT capabilities masks (for cap_info) */ -#define IEEE80211_HT_CAP_LDPC_CODING 0x0001 -#define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 -#define IEEE80211_HT_CAP_SM_PS 0x000C -#define IEEE80211_HT_CAP_SM_PS_SHIFT 2 -#define IEEE80211_HT_CAP_GRN_FLD 0x0010 -#define IEEE80211_HT_CAP_SGI_20 0x0020 -#define IEEE80211_HT_CAP_SGI_40 0x0040 -#define IEEE80211_HT_CAP_TX_STBC 0x0080 -#define IEEE80211_HT_CAP_RX_STBC 0x0300 -#define IEEE80211_HT_CAP_RX_STBC_SHIFT 8 -#define IEEE80211_HT_CAP_DELAY_BA 0x0400 -#define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 -#define IEEE80211_HT_CAP_DSSSCCK40 0x1000 -#define IEEE80211_HT_CAP_RESERVED 0x2000 -#define IEEE80211_HT_CAP_40MHZ_INTOLERANT 0x4000 -#define IEEE80211_HT_CAP_LSIG_TXOP_PROT 0x8000 - -/* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */ -#define IEEE80211_HT_EXT_CAP_PCO 0x0001 -#define IEEE80211_HT_EXT_CAP_PCO_TIME 0x0006 -#define IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT 1 -#define IEEE80211_HT_EXT_CAP_MCS_FB 0x0300 -#define IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT 8 -#define IEEE80211_HT_EXT_CAP_HTC_SUP 0x0400 -#define IEEE80211_HT_EXT_CAP_RD_RESPONDER 0x0800 - -/* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ -#define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 -#define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C -#define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 - -/* - * Maximum length of AMPDU that the STA can receive in high-throughput (HT). - * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) - */ -enum ieee80211_max_ampdu_length_exp { - IEEE80211_HT_MAX_AMPDU_8K = 0, - IEEE80211_HT_MAX_AMPDU_16K = 1, - IEEE80211_HT_MAX_AMPDU_32K = 2, - IEEE80211_HT_MAX_AMPDU_64K = 3 -}; - /* * Maximum length of AMPDU that the STA can receive in VHT. * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) @@ -1832,98 +1678,6 @@ enum ieee80211_vht_max_ampdu_length_exp { IEEE80211_VHT_MAX_AMPDU_1024K = 7 }; -#define IEEE80211_HT_MAX_AMPDU_FACTOR 13 - -/* Minimum MPDU start spacing */ -enum ieee80211_min_mpdu_spacing { - IEEE80211_HT_MPDU_DENSITY_NONE = 0, /* No restriction */ - IEEE80211_HT_MPDU_DENSITY_0_25 = 1, /* 1/4 usec */ - IEEE80211_HT_MPDU_DENSITY_0_5 = 2, /* 1/2 usec */ - IEEE80211_HT_MPDU_DENSITY_1 = 3, /* 1 usec */ - IEEE80211_HT_MPDU_DENSITY_2 = 4, /* 2 usec */ - IEEE80211_HT_MPDU_DENSITY_4 = 5, /* 4 usec */ - IEEE80211_HT_MPDU_DENSITY_8 = 6, /* 8 usec */ - IEEE80211_HT_MPDU_DENSITY_16 = 7 /* 16 usec */ -}; - -/** - * struct ieee80211_ht_operation - HT operation IE - * @primary_chan: Primary Channel - * @ht_param: HT Operation Information parameters - * @operation_mode: HT Operation Information operation mode - * @stbc_param: HT Operation Information STBC params - * @basic_set: Basic HT-MCS Set - * - * This structure represents the payload of the "HT Operation - * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. - */ -struct ieee80211_ht_operation { - u8 primary_chan; - u8 ht_param; - __le16 operation_mode; - __le16 stbc_param; - u8 basic_set[16]; -} __packed; - -/* for ht_param */ -#define IEEE80211_HT_PARAM_CHA_SEC_OFFSET 0x03 -#define IEEE80211_HT_PARAM_CHA_SEC_NONE 0x00 -#define IEEE80211_HT_PARAM_CHA_SEC_ABOVE 0x01 -#define IEEE80211_HT_PARAM_CHA_SEC_BELOW 0x03 -#define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY 0x04 -#define IEEE80211_HT_PARAM_RIFS_MODE 0x08 - -/* for operation_mode */ -#define IEEE80211_HT_OP_MODE_PROTECTION 0x0003 -#define IEEE80211_HT_OP_MODE_PROTECTION_NONE 0 -#define IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER 1 -#define IEEE80211_HT_OP_MODE_PROTECTION_20MHZ 2 -#define IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED 3 -#define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT 0x0004 -#define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT 0x0010 -#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT 5 -#define IEEE80211_HT_OP_MODE_CCFS2_MASK 0x1fe0 - -/* for stbc_param */ -#define IEEE80211_HT_STBC_PARAM_DUAL_BEACON 0x0040 -#define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT 0x0080 -#define IEEE80211_HT_STBC_PARAM_STBC_BEACON 0x0100 -#define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT 0x0200 -#define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE 0x0400 -#define IEEE80211_HT_STBC_PARAM_PCO_PHASE 0x0800 - - -/* block-ack parameters */ -#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 -#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 -#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C -#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 -#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000 -#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 - -/* - * A-MPDU buffer sizes - * According to HT size varies from 8 to 64 frames - * HE adds the ability to have up to 256 frames. - * EHT adds the ability to have up to 1K frames. - */ -#define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 -#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 -#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 - - -/* Spatial Multiplexing Power Save Modes (for capability) */ -#define WLAN_HT_CAP_SM_PS_STATIC 0 -#define WLAN_HT_CAP_SM_PS_DYNAMIC 1 -#define WLAN_HT_CAP_SM_PS_INVALID 2 -#define WLAN_HT_CAP_SM_PS_DISABLED 3 - -/* for SM power control field lower two bits */ -#define WLAN_HT_SMPS_CONTROL_DISABLED 0 -#define WLAN_HT_SMPS_CONTROL_STATIC 1 -#define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 - /** * struct ieee80211_vht_mcs_info - VHT MCS information * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams @@ -3807,18 +3561,6 @@ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; -/* HT action codes */ -enum ieee80211_ht_actioncode { - WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, - WLAN_HT_ACTION_SMPS = 1, - WLAN_HT_ACTION_PSMP = 2, - WLAN_HT_ACTION_PCO_PHASE = 3, - WLAN_HT_ACTION_CSI = 4, - WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, - WLAN_HT_ACTION_COMPRESSED_BF = 6, - WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, -}; - /* VHT action codes */ enum ieee80211_vht_actioncode { WLAN_VHT_ACTION_COMPRESSED_BF = 0, @@ -4155,19 +3897,6 @@ struct ieee80211_bss_max_idle_period_ie { u8 idle_options; } __packed; -/* BACK action code */ -enum ieee80211_back_actioncode { - WLAN_ACTION_ADDBA_REQ = 0, - WLAN_ACTION_ADDBA_RESP = 1, - WLAN_ACTION_DELBA = 2, -}; - -/* BACK (block-ack) parties */ -enum ieee80211_back_parties { - WLAN_BACK_RECIPIENT = 0, - WLAN_BACK_INITIATOR = 1, -}; - /* SA Query action */ enum ieee80211_sa_query_action { WLAN_ACTION_SA_QUERY_REQUEST = 0, @@ -5889,6 +5618,7 @@ static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) #define NAN_DEV_CAPA_NDPE_SUPPORTED 0x08 #define NAN_DEV_CAPA_S3_SUPPORTED 0x10 +#include "ieee80211-ht.h" #include "ieee80211-mesh.h" #endif /* LINUX_IEEE80211_H */ From f8d1e8038bc76ad5ff6f30aed55da0d8120444f9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 Nov 2025 15:36:51 +0100 Subject: [PATCH 0244/1518] wifi: ieee80211: split VHT definitions out [ Upstream commit 7cb14da1d7bbfa4a6417ed7f1bc07dd77bcd9c83 ] The ieee80211.h file has gotten very long, continue splitting it by putting VHT definitions into a separate file. Link: https://patch.msgid.link/20251105153843.c31cb771a250.I787a13064db7d80440101de3445be17881daf1b6@changeid Signed-off-by: Johannes Berg Stable-dep-of: cb0caadb64ca ("wifi: ieee80211: fix definition of EHT-MCS 15 in MRU") Signed-off-by: Sasha Levin --- include/linux/ieee80211-vht.h | 236 ++++++++++++++++++++++++++++++++++ include/linux/ieee80211.h | 216 +------------------------------ 2 files changed, 237 insertions(+), 215 deletions(-) create mode 100644 include/linux/ieee80211-vht.h diff --git a/include/linux/ieee80211-vht.h b/include/linux/ieee80211-vht.h new file mode 100644 index 0000000000000..898dfb561fef2 --- /dev/null +++ b/include/linux/ieee80211-vht.h @@ -0,0 +1,236 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 VHT definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_VHT_H +#define LINUX_IEEE80211_VHT_H + +#include +#include + +#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 +#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 +#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 + +/** + * enum ieee80211_vht_opmode_bits - VHT operating mode field bits + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width + * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag + * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask + * (the NSS value is the value of this field + 1) + * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift + * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU + * using a beamforming steering matrix + */ +enum ieee80211_vht_opmode_bits { + IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, + IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, + IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, + IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, + IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, +}; + +/* + * Maximum length of AMPDU that the STA can receive in VHT. + * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) + */ +enum ieee80211_vht_max_ampdu_length_exp { + IEEE80211_VHT_MAX_AMPDU_8K = 0, + IEEE80211_VHT_MAX_AMPDU_16K = 1, + IEEE80211_VHT_MAX_AMPDU_32K = 2, + IEEE80211_VHT_MAX_AMPDU_64K = 3, + IEEE80211_VHT_MAX_AMPDU_128K = 4, + IEEE80211_VHT_MAX_AMPDU_256K = 5, + IEEE80211_VHT_MAX_AMPDU_512K = 6, + IEEE80211_VHT_MAX_AMPDU_1024K = 7 +}; + +/** + * struct ieee80211_vht_mcs_info - VHT MCS information + * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams + * @rx_highest: Indicates highest long GI VHT PPDU data rate + * STA can receive. Rate expressed in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. + * The top 3 bits of this field indicate the Maximum NSTS,total + * (a beamformee capability.) + * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams + * @tx_highest: Indicates highest long GI VHT PPDU data rate + * STA can transmit. Rate expressed in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest TX data rate supported. + * The top 2 bits of this field are reserved, the + * 3rd bit from the top indiciates VHT Extended NSS BW + * Capability. + */ +struct ieee80211_vht_mcs_info { + __le16 rx_mcs_map; + __le16 rx_highest; + __le16 tx_mcs_map; + __le16 tx_highest; +} __packed; + +/* for rx_highest */ +#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 +#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) + +/* for tx_highest */ +#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) + +/** + * enum ieee80211_vht_mcs_support - VHT MCS support definitions + * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported + * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the @rx_mcs_map + * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_vht_mcs_support { + IEEE80211_VHT_MCS_SUPPORT_0_7 = 0, + IEEE80211_VHT_MCS_SUPPORT_0_8 = 1, + IEEE80211_VHT_MCS_SUPPORT_0_9 = 2, + IEEE80211_VHT_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_vht_cap - VHT capabilities + * + * This structure is the "VHT capabilities element" as + * described in 802.11ac D3.0 8.4.2.160 + * @vht_cap_info: VHT capability info + * @supp_mcs: VHT MCS supported rates + */ +struct ieee80211_vht_cap { + __le32 vht_cap_info; + struct ieee80211_vht_mcs_info supp_mcs; +} __packed; + +/** + * enum ieee80211_vht_chanwidth - VHT channel width + * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to + * determine the channel width (20 or 40 MHz) + * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth + * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth + * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth + */ +enum ieee80211_vht_chanwidth { + IEEE80211_VHT_CHANWIDTH_USE_HT = 0, + IEEE80211_VHT_CHANWIDTH_80MHZ = 1, + IEEE80211_VHT_CHANWIDTH_160MHZ = 2, + IEEE80211_VHT_CHANWIDTH_80P80MHZ = 3, +}; + +/** + * struct ieee80211_vht_operation - VHT operation IE + * + * This structure is the "VHT operation element" as + * described in 802.11ac D3.0 8.4.2.161 + * @chan_width: Operating channel width + * @center_freq_seg0_idx: center freq segment 0 index + * @center_freq_seg1_idx: center freq segment 1 index + * @basic_mcs_set: VHT Basic MCS rate set + */ +struct ieee80211_vht_operation { + u8 chan_width; + u8 center_freq_seg0_idx; + u8 center_freq_seg1_idx; + __le16 basic_mcs_set; +} __packed; + +/* 802.11ac VHT Capabilities */ +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 +#define IEEE80211_VHT_CAP_RXLDPC 0x00000010 +#define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 +#define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 +#define IEEE80211_VHT_CAP_TXSTBC 0x00000080 +#define IEEE80211_VHT_CAP_RXSTBC_1 0x00000100 +#define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 +#define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 +#define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 +#define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 +#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 +#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 +#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 +#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 +#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK \ + (7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT) +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT 16 +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK \ + (7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT) +#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 +#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 +#define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 +#define IEEE80211_VHT_CAP_HTC_VHT 0x00400000 +#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT 23 +#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK \ + (7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT) +#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB 0x08000000 +#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 +#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 +#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 + +/** + * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS + * @cap: VHT capabilities of the peer + * @bw: bandwidth to use + * @mcs: MCS index to use + * @ext_nss_bw_capable: indicates whether or not the local transmitter + * (rate scaling algorithm) can deal with the new logic + * (dot11VHTExtendedNSSBWCapable) + * @max_vht_nss: current maximum NSS as advertised by the STA in + * operating mode notification, can be 0 in which case the + * capability data will be used to derive this (from MCS support) + * Return: The maximum NSS that can be used for the given bandwidth/MCS + * combination + * + * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can + * vary for a given BW/MCS. This function parses the data. + * + * Note: This function is exported by cfg80211. + */ +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable, + unsigned int max_vht_nss); + +/* VHT action codes */ +enum ieee80211_vht_actioncode { + WLAN_VHT_ACTION_COMPRESSED_BF = 0, + WLAN_VHT_ACTION_GROUPID_MGMT = 1, + WLAN_VHT_ACTION_OPMODE_NOTIF = 2, +}; + +#endif /* LINUX_IEEE80211_VHT_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f0a7899fb6626..fb399b7833736 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -239,10 +239,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 -#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 -#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 -#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 - #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_FIRST_TSPEC_TSID 8 @@ -988,32 +984,6 @@ struct ieee80211_tim_ie { }; } __packed; -/** - * enum ieee80211_vht_opmode_bits - VHT operating mode field bits - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width - * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag - * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask - * (the NSS value is the value of this field + 1) - * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift - * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU - * using a beamforming steering matrix - */ -enum ieee80211_vht_opmode_bits { - IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, - IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, - IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, - IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, - IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, -}; - /** * enum ieee80211_s1g_chanwidth - S1G channel widths * These are defined in IEEE802.11-2016ah Table 10-20 @@ -1663,119 +1633,6 @@ struct ieee80211_p2p_noa_attr { #define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F -/* - * Maximum length of AMPDU that the STA can receive in VHT. - * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) - */ -enum ieee80211_vht_max_ampdu_length_exp { - IEEE80211_VHT_MAX_AMPDU_8K = 0, - IEEE80211_VHT_MAX_AMPDU_16K = 1, - IEEE80211_VHT_MAX_AMPDU_32K = 2, - IEEE80211_VHT_MAX_AMPDU_64K = 3, - IEEE80211_VHT_MAX_AMPDU_128K = 4, - IEEE80211_VHT_MAX_AMPDU_256K = 5, - IEEE80211_VHT_MAX_AMPDU_512K = 6, - IEEE80211_VHT_MAX_AMPDU_1024K = 7 -}; - -/** - * struct ieee80211_vht_mcs_info - VHT MCS information - * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams - * @rx_highest: Indicates highest long GI VHT PPDU data rate - * STA can receive. Rate expressed in units of 1 Mbps. - * If this field is 0 this value should not be used to - * consider the highest RX data rate supported. - * The top 3 bits of this field indicate the Maximum NSTS,total - * (a beamformee capability.) - * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams - * @tx_highest: Indicates highest long GI VHT PPDU data rate - * STA can transmit. Rate expressed in units of 1 Mbps. - * If this field is 0 this value should not be used to - * consider the highest TX data rate supported. - * The top 2 bits of this field are reserved, the - * 3rd bit from the top indiciates VHT Extended NSS BW - * Capability. - */ -struct ieee80211_vht_mcs_info { - __le16 rx_mcs_map; - __le16 rx_highest; - __le16 tx_mcs_map; - __le16 tx_highest; -} __packed; - -/* for rx_highest */ -#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 -#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) - -/* for tx_highest */ -#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) - -/** - * enum ieee80211_vht_mcs_support - VHT MCS support definitions - * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the - * number of streams - * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported - * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported - * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported - * - * These definitions are used in each 2-bit subfield of the @rx_mcs_map - * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are - * both split into 8 subfields by number of streams. These values indicate - * which MCSes are supported for the number of streams the value appears - * for. - */ -enum ieee80211_vht_mcs_support { - IEEE80211_VHT_MCS_SUPPORT_0_7 = 0, - IEEE80211_VHT_MCS_SUPPORT_0_8 = 1, - IEEE80211_VHT_MCS_SUPPORT_0_9 = 2, - IEEE80211_VHT_MCS_NOT_SUPPORTED = 3, -}; - -/** - * struct ieee80211_vht_cap - VHT capabilities - * - * This structure is the "VHT capabilities element" as - * described in 802.11ac D3.0 8.4.2.160 - * @vht_cap_info: VHT capability info - * @supp_mcs: VHT MCS supported rates - */ -struct ieee80211_vht_cap { - __le32 vht_cap_info; - struct ieee80211_vht_mcs_info supp_mcs; -} __packed; - -/** - * enum ieee80211_vht_chanwidth - VHT channel width - * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to - * determine the channel width (20 or 40 MHz) - * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth - * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth - * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth - */ -enum ieee80211_vht_chanwidth { - IEEE80211_VHT_CHANWIDTH_USE_HT = 0, - IEEE80211_VHT_CHANWIDTH_80MHZ = 1, - IEEE80211_VHT_CHANWIDTH_160MHZ = 2, - IEEE80211_VHT_CHANWIDTH_80P80MHZ = 3, -}; - -/** - * struct ieee80211_vht_operation - VHT operation IE - * - * This structure is the "VHT operation element" as - * described in 802.11ac D3.0 8.4.2.161 - * @chan_width: Operating channel width - * @center_freq_seg0_idx: center freq segment 0 index - * @center_freq_seg1_idx: center freq segment 1 index - * @basic_mcs_set: VHT Basic MCS rate set - */ -struct ieee80211_vht_operation { - u8 chan_width; - u8 center_freq_seg0_idx; - u8 center_freq_seg1_idx; - __le16 basic_mcs_set; -} __packed; - /** * struct ieee80211_he_cap_elem - HE capabilities element * @mac_cap_info: HE MAC Capabilities Information @@ -2045,71 +1902,6 @@ struct ieee80211_eht_operation_info { u8 optional[]; } __packed; -/* 802.11ac VHT Capabilities */ -#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 -#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 -#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 -#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 -#define IEEE80211_VHT_CAP_RXLDPC 0x00000010 -#define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 -#define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 -#define IEEE80211_VHT_CAP_TXSTBC 0x00000080 -#define IEEE80211_VHT_CAP_RXSTBC_1 0x00000100 -#define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 -#define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 -#define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 -#define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 -#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 -#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 -#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 -#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 -#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK \ - (7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT) -#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT 16 -#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK \ - (7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT) -#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 -#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 -#define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 -#define IEEE80211_VHT_CAP_HTC_VHT 0x00400000 -#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT 23 -#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK \ - (7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT) -#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB 0x08000000 -#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 -#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 -#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 -#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 -#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 - -/** - * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS - * @cap: VHT capabilities of the peer - * @bw: bandwidth to use - * @mcs: MCS index to use - * @ext_nss_bw_capable: indicates whether or not the local transmitter - * (rate scaling algorithm) can deal with the new logic - * (dot11VHTExtendedNSSBWCapable) - * @max_vht_nss: current maximum NSS as advertised by the STA in - * operating mode notification, can be 0 in which case the - * capability data will be used to derive this (from MCS support) - * Return: The maximum NSS that can be used for the given bandwidth/MCS - * combination - * - * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can - * vary for a given BW/MCS. This function parses the data. - * - * Note: This function is exported by cfg80211. - */ -int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, - enum ieee80211_vht_chanwidth bw, - int mcs, bool ext_nss_bw_capable, - unsigned int max_vht_nss); - /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 #define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 @@ -3561,13 +3353,6 @@ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; -/* VHT action codes */ -enum ieee80211_vht_actioncode { - WLAN_VHT_ACTION_COMPRESSED_BF = 0, - WLAN_VHT_ACTION_GROUPID_MGMT = 1, - WLAN_VHT_ACTION_OPMODE_NOTIF = 2, -}; - /* Self Protected Action codes */ enum ieee80211_self_protected_actioncode { WLAN_SP_RESERVED = 0, @@ -5619,6 +5404,7 @@ static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) #define NAN_DEV_CAPA_S3_SUPPORTED 0x10 #include "ieee80211-ht.h" +#include "ieee80211-vht.h" #include "ieee80211-mesh.h" #endif /* LINUX_IEEE80211_H */ From df5720d35848be92944767a6d5ae20ec9ed347ce Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 Nov 2025 15:36:52 +0100 Subject: [PATCH 0245/1518] wifi: ieee80211: split HE definitions out [ Upstream commit 02a2cf302557eb59794bba0b05d6755f44928d78 ] The ieee80211.h file has gotten very long, continue splitting it by putting HE definitions into a separate file. Link: https://patch.msgid.link/20251105153843.6998c0802104.I3dd7cfea6abbd118b999ecdedd48437d39cb0533@changeid Signed-off-by: Johannes Berg Stable-dep-of: cb0caadb64ca ("wifi: ieee80211: fix definition of EHT-MCS 15 in MRU") Signed-off-by: Sasha Levin --- include/linux/ieee80211-he.h | 824 +++++++++++++++++++++++++++++++++++ include/linux/ieee80211.h | 806 +--------------------------------- 2 files changed, 827 insertions(+), 803 deletions(-) create mode 100644 include/linux/ieee80211-he.h diff --git a/include/linux/ieee80211-he.h b/include/linux/ieee80211-he.h new file mode 100644 index 0000000000000..904d50db5bb80 --- /dev/null +++ b/include/linux/ieee80211-he.h @@ -0,0 +1,824 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 HE definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_HE_H +#define LINUX_IEEE80211_HE_H + +#include +#include + +#define IEEE80211_TWT_CONTROL_NDP BIT(0) +#define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) +#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) +#define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) +#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) + +#define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) +#define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) +#define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) +#define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) +#define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) +#define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) +#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) +#define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) + +enum ieee80211_twt_setup_cmd { + TWT_SETUP_CMD_REQUEST, + TWT_SETUP_CMD_SUGGEST, + TWT_SETUP_CMD_DEMAND, + TWT_SETUP_CMD_GROUPING, + TWT_SETUP_CMD_ACCEPT, + TWT_SETUP_CMD_ALTERNATE, + TWT_SETUP_CMD_DICTATE, + TWT_SETUP_CMD_REJECT, +}; + +struct ieee80211_twt_params { + __le16 req_type; + __le64 twt; + u8 min_twt_dur; + __le16 mantissa; + u8 channel; +} __packed; + +struct ieee80211_twt_setup { + u8 dialog_token; + u8 element_id; + u8 length; + u8 control; + u8 params[]; +} __packed; + +/** + * struct ieee80211_he_cap_elem - HE capabilities element + * @mac_cap_info: HE MAC Capabilities Information + * @phy_cap_info: HE PHY Capabilities Information + * + * This structure represents the fixed fields of the payload of the + * "HE capabilities element" as described in IEEE Std 802.11ax-2021 + * sections 9.4.2.248.2 and 9.4.2.248.3. + */ +struct ieee80211_he_cap_elem { + u8 mac_cap_info[6]; + u8 phy_cap_info[11]; +} __packed; + +#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 + +/** + * enum ieee80211_he_mcs_support - HE MCS support definitions + * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported + * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the rx_mcs_* + * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_he_mcs_support { + IEEE80211_HE_MCS_SUPPORT_0_7 = 0, + IEEE80211_HE_MCS_SUPPORT_0_9 = 1, + IEEE80211_HE_MCS_SUPPORT_0_11 = 2, + IEEE80211_HE_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field + * + * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field + * described in P802.11ax_D2.0 section 9.4.2.237.4 + * + * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + */ +struct ieee80211_he_mcs_nss_supp { + __le16 rx_mcs_80; + __le16 tx_mcs_80; + __le16 rx_mcs_160; + __le16 tx_mcs_160; + __le16 rx_mcs_80p80; + __le16 tx_mcs_80p80; +} __packed; + +/** + * struct ieee80211_he_operation - HE Operation element + * @he_oper_params: HE Operation Parameters + BSS Color Information + * @he_mcs_nss_set: Basic HE-MCS And NSS Set + * @optional: Optional fields VHT Operation Information, Max Co-Hosted + * BSSID Indicator, and 6 GHz Operation Information + * + * This structure represents the payload of the "HE Operation + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. + */ +struct ieee80211_he_operation { + __le32 he_oper_params; + __le16 he_mcs_nss_set; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_he_spr - Spatial Reuse Parameter Set element + * @he_sr_control: SR Control + * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD + * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color + * Bitmap, and SRG Partial BSSID Bitmap + * + * This structure represents the payload of the "Spatial Reuse + * Parameter Set element" as described in IEEE Std 802.11ax-2021 + * section 9.4.2.252. + */ +struct ieee80211_he_spr { + u8 he_sr_control; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * @aifsn: ACI/AIFSN + * @ecw_min_max: ECWmin/ECWmax + * @mu_edca_timer: MU EDCA Timer + * + * This structure represents the "MU AC Parameter Record" as described + * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. + */ +struct ieee80211_he_mu_edca_param_ac_rec { + u8 aifsn; + u8 ecw_min_max; + u8 mu_edca_timer; +} __packed; + +/** + * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * @mu_qos_info: QoS Info + * @ac_be: MU AC_BE Parameter Record + * @ac_bk: MU AC_BK Parameter Record + * @ac_vi: MU AC_VI Parameter Record + * @ac_vo: MU AC_VO Parameter Record + * + * This structure represents the payload of the "MU EDCA Parameter Set + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. + */ +struct ieee80211_mu_edca_param_set { + u8 mu_qos_info; + struct ieee80211_he_mu_edca_param_ac_rec ac_be; + struct ieee80211_he_mu_edca_param_ac_rec ac_bk; + struct ieee80211_he_mu_edca_param_ac_rec ac_vi; + struct ieee80211_he_mu_edca_param_ac_rec ac_vo; +} __packed; + +/* 802.11ax HE MAC capabilities */ +#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 +#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 +#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 + +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 + +/* Link adaptation is split between byte HE_MAC_CAP1 and + * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE + * in which case the following values apply: + * 0 = No feedback. + * 1 = reserved. + * 2 = Unsolicited feedback. + * 3 = both + */ +#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 + +#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 +#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 +#define IEEE80211_HE_MAC_CAP2_TRS 0x04 +#define IEEE80211_HE_MAC_CAP2_BSR 0x08 +#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 +#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 +#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 +#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 + +#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 +#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 + +/* The maximum length of an A-MDPU is defined by the combination of the Maximum + * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the + * same field in the HE capabilities. + */ +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 +#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 + +#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 +#define IEEE80211_HE_MAC_CAP4_QTP 0x02 +#define IEEE80211_HE_MAC_CAP4_BQR 0x04 +#define IEEE80211_HE_MAC_CAP4_PSR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 +#define IEEE80211_HE_MAC_CAP4_OPS 0x20 +#define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU 0x40 +/* Multi TID agg TX is split between byte #4 and #5 + * The value is a combination of B39,B40,B41 + */ +#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 + +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 +#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION 0x04 +#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 +#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 +#define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS 0x20 +#define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 +#define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 + +#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 +#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 +#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR 13 + +/* 802.11ax HE PHY capabilities */ +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e + +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe + +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f +#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 +#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 +#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 +/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 + +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 +#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 +#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 + +/* Note that the meaning of UL MU below is different between an AP and a non-AP + * sta, where in the AP case it indicates support for Rx and in the non-AP sta + * case it indicates support for Tx. + */ +#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 +#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 + +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 +#define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU 0x40 +#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 + +#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 +#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 + +/* Minimal allowed value of Max STS under 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c + +/* Minimal allowed value of Max STS above 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 + +#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 +#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 + +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 +#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB 0x04 +#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB 0x08 +#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 +#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 + +#define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR 0x01 +#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP 0x02 +#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 +#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 +#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 + +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 +#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242 0x00 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484 0x40 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996 0x80 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996 0xc0 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 +#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 +#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 +#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 + +/* 802.11ax HE TX/RX MCS NSS Support */ +#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 + +/* TX/RX HE MCS Support field Highest MCS subfield encoding */ +enum ieee80211_he_highest_mcs_supported_subfield_enc { + HIGHEST_MCS_SUPPORTED_MCS7 = 0, + HIGHEST_MCS_SUPPORTED_MCS8, + HIGHEST_MCS_SUPPORTED_MCS9, + HIGHEST_MCS_SUPPORTED_MCS10, + HIGHEST_MCS_SUPPORTED_MCS11, +}; + +/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ +static inline u8 +ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) +{ + u8 count = 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + count += 4; + + return count; +} + +/* 802.11ax HE PPE Thresholds */ +#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) +#define IEEE80211_PPE_THRES_NSS_POS (0) +#define IEEE80211_PPE_THRES_NSS_MASK (7) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ + (BIT(5) | BIT(6)) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) +#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) +#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) + +/* + * Calculate 802.11ax HE capabilities IE PPE field size + * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* + */ +static inline u8 +ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u8 n; + + if ((phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + return 0; + + n = hweight8(ppe_thres_hdr & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + return n; +} + +static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; + u8 needed = sizeof(*he_cap_ie_elem); + + if (len < needed) + return false; + + needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); + if (len < needed) + return false; + + if (he_cap_ie_elem->phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { + if (len < needed + 1) + return false; + needed += ieee80211_he_ppe_size(data[needed], + he_cap_ie_elem->phy_cap_info); + } + + return len >= needed; +} + +/* HE Operation defines */ +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 +#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 +#define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 +#define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 +#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 + +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD 4 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 8 + +/** + * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field + * @primary: primary channel + * @control: control flags + * @ccfs0: channel center frequency segment 0 + * @ccfs1: channel center frequency segment 1 + * @minrate: minimum rate (in 1 Mbps units) + */ +struct ieee80211_he_6ghz_oper { + u8 primary; +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 +#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x78 + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 minrate; +} __packed; + +/** + * enum ieee80211_reg_conn_bits - represents Regulatory connectivity field bits. + * + * This enumeration defines bit flags used to represent regulatory connectivity + * field bits. + * + * @IEEE80211_REG_CONN_LPI_VALID: Indicates whether the LPI bit is valid. + * @IEEE80211_REG_CONN_LPI_VALUE: Represents the value of the LPI bit. + * @IEEE80211_REG_CONN_SP_VALID: Indicates whether the SP bit is valid. + * @IEEE80211_REG_CONN_SP_VALUE: Represents the value of the SP bit. + */ +enum ieee80211_reg_conn_bits { + IEEE80211_REG_CONN_LPI_VALID = BIT(0), + IEEE80211_REG_CONN_LPI_VALUE = BIT(1), + IEEE80211_REG_CONN_SP_VALID = BIT(2), + IEEE80211_REG_CONN_SP_VALUE = BIT(3), +}; + +/* transmit power interpretation type of transmit power envelope element */ +enum ieee80211_tx_power_intrpt_type { + IEEE80211_TPE_LOCAL_EIRP, + IEEE80211_TPE_LOCAL_EIRP_PSD, + IEEE80211_TPE_REG_CLIENT_EIRP, + IEEE80211_TPE_REG_CLIENT_EIRP_PSD, +}; + +/* category type of transmit power envelope element */ +enum ieee80211_tx_power_category_6ghz { + IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0, + IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1, +}; + +/* + * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP, + * setting to 63.5 dBm means no constraint. + */ +#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT 127 + +/* + * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD, + * setting to 127 indicates no PSD limit for the 20 MHz channel. + */ +#define IEEE80211_TPE_PSD_NO_LIMIT 127 + +/** + * struct ieee80211_tx_pwr_env - Transmit Power Envelope + * @info: Transmit Power Information field + * @variable: Maximum Transmit Power field + * + * This structure represents the payload of the "Transmit Power + * Envelope element" as described in IEEE Std 802.11ax-2021 section + * 9.4.2.161 + */ +struct ieee80211_tx_pwr_env { + u8 info; + u8 variable[]; +} __packed; + +#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 +#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 +#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 + +#define IEEE80211_TX_PWR_ENV_EXT_COUNT 0xF + +static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len) +{ + const struct ieee80211_tx_pwr_env *env = (const void *)data; + u8 count, interpret, category; + u8 needed = sizeof(*env); + u8 N; /* also called N in the spec */ + + if (len < needed) + return false; + + count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); + interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); + category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); + + switch (category) { + case IEEE80211_TPE_CAT_6GHZ_DEFAULT: + case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE: + break; + default: + return false; + } + + switch (interpret) { + case IEEE80211_TPE_LOCAL_EIRP: + case IEEE80211_TPE_REG_CLIENT_EIRP: + if (count > 3) + return false; + + /* count == 0 encodes 1 value for 20 MHz, etc. */ + needed += count + 1; + + if (len < needed) + return false; + + /* there can be extension fields not accounted for in 'count' */ + + return true; + case IEEE80211_TPE_LOCAL_EIRP_PSD: + case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: + if (count > 4) + return false; + + N = count ? 1 << (count - 1) : 1; + needed += N; + + if (len < needed) + return false; + + if (len > needed) { + u8 K = u8_get_bits(env->variable[N], + IEEE80211_TX_PWR_ENV_EXT_COUNT); + + needed += 1 + K; + if (len < needed) + return false; + } + + return true; + } + + return false; +} + +/* + * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size + * @he_oper_ie: byte data of the He Operations IE, stating from the byte + * after the ext ID byte. It is assumed that he_oper_ie has at least + * sizeof(struct ieee80211_he_operation) bytes, the caller must have + * validated this. + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_oper_size(const u8 *he_oper_ie) +{ + const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; + u8 oper_len = sizeof(struct ieee80211_he_operation); + u32 he_oper_params; + + /* Make sure the input is not NULL */ + if (!he_oper_ie) + return 0; + + /* Calc required length */ + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + oper_len += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) + oper_len++; + if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) + oper_len += sizeof(struct ieee80211_he_6ghz_oper); + + /* Add the first byte (extension ID) to the total length */ + oper_len++; + + return oper_len; +} + +/** + * ieee80211_he_6ghz_oper - obtain 6 GHz operation field + * @he_oper: HE operation element (must be pre-validated for size) + * but may be %NULL + * + * Return: a pointer to the 6 GHz operation field, or %NULL + */ +static inline const struct ieee80211_he_6ghz_oper * +ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) +{ + const u8 *ret; + u32 he_oper_params; + + if (!he_oper) + return NULL; + + ret = (const void *)&he_oper->optional; + + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + + if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) + return NULL; + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + ret += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) + ret++; + + return (const void *)ret; +} + +/* HE Spatial Reuse defines */ +#define IEEE80211_HE_SPR_PSR_DISALLOWED BIT(0) +#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED BIT(1) +#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT BIT(2) +#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT BIT(3) +#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED BIT(4) + +/* + * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte + * after the ext ID byte. It is assumed that he_spr_ie has at least + * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated + * this + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_spr_size(const u8 *he_spr_ie) +{ + const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; + u8 spr_len = sizeof(struct ieee80211_he_spr); + u8 he_spr_params; + + /* Make sure the input is not NULL */ + if (!he_spr_ie) + return 0; + + /* Calc required length */ + he_spr_params = he_spr->he_sr_control; + if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + spr_len++; + if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) + spr_len += 18; + + /* Add the first byte (extension ID) to the total length */ + spr_len++; + + return spr_len; +} + +struct ieee80211_he_6ghz_capa { + /* uses IEEE80211_HE_6GHZ_CAP_* below */ + __le16 capa; +} __packed; + +/* HE 6 GHz band capabilities */ +/* uses enum ieee80211_min_mpdu_spacing values */ +#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 +/* uses enum ieee80211_vht_max_ampdu_length_exp values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 +/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 +/* WLAN_HT_CAP_SM_PS_* values */ +#define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 +#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 +#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 +#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 + +#endif /* LINUX_IEEE80211_HE_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index fb399b7833736..2f3d0412ca759 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1141,48 +1141,6 @@ ieee80211_s1g_optional_len(__le16 fc) return len; } -#define IEEE80211_TWT_CONTROL_NDP BIT(0) -#define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) -#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) -#define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) -#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) - -#define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) -#define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) -#define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) -#define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) -#define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) -#define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) -#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) -#define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) - -enum ieee80211_twt_setup_cmd { - TWT_SETUP_CMD_REQUEST, - TWT_SETUP_CMD_SUGGEST, - TWT_SETUP_CMD_DEMAND, - TWT_SETUP_CMD_GROUPING, - TWT_SETUP_CMD_ACCEPT, - TWT_SETUP_CMD_ALTERNATE, - TWT_SETUP_CMD_DICTATE, - TWT_SETUP_CMD_REJECT, -}; - -struct ieee80211_twt_params { - __le16 req_type; - __le64 twt; - u8 min_twt_dur; - __le16 mantissa; - u8 channel; -} __packed; - -struct ieee80211_twt_setup { - u8 dialog_token; - u8 element_id; - u8 length; - u8 control; - u8 params[]; -} __packed; - #define IEEE80211_TTLM_MAX_CNT 2 #define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 #define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 @@ -1633,137 +1591,6 @@ struct ieee80211_p2p_noa_attr { #define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F -/** - * struct ieee80211_he_cap_elem - HE capabilities element - * @mac_cap_info: HE MAC Capabilities Information - * @phy_cap_info: HE PHY Capabilities Information - * - * This structure represents the fixed fields of the payload of the - * "HE capabilities element" as described in IEEE Std 802.11ax-2021 - * sections 9.4.2.248.2 and 9.4.2.248.3. - */ -struct ieee80211_he_cap_elem { - u8 mac_cap_info[6]; - u8 phy_cap_info[11]; -} __packed; - -#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 - -/** - * enum ieee80211_he_mcs_support - HE MCS support definitions - * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the - * number of streams - * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported - * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported - * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported - * - * These definitions are used in each 2-bit subfield of the rx_mcs_* - * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are - * both split into 8 subfields by number of streams. These values indicate - * which MCSes are supported for the number of streams the value appears - * for. - */ -enum ieee80211_he_mcs_support { - IEEE80211_HE_MCS_SUPPORT_0_7 = 0, - IEEE80211_HE_MCS_SUPPORT_0_9 = 1, - IEEE80211_HE_MCS_SUPPORT_0_11 = 2, - IEEE80211_HE_MCS_NOT_SUPPORTED = 3, -}; - -/** - * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field - * - * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field - * described in P802.11ax_D2.0 section 9.4.2.237.4 - * - * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel - * widths less than 80MHz. - * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel - * widths less than 80MHz. - * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel - * width 160MHz. - * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel - * width 160MHz. - * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for - * channel width 80p80MHz. - * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for - * channel width 80p80MHz. - */ -struct ieee80211_he_mcs_nss_supp { - __le16 rx_mcs_80; - __le16 tx_mcs_80; - __le16 rx_mcs_160; - __le16 tx_mcs_160; - __le16 rx_mcs_80p80; - __le16 tx_mcs_80p80; -} __packed; - -/** - * struct ieee80211_he_operation - HE Operation element - * @he_oper_params: HE Operation Parameters + BSS Color Information - * @he_mcs_nss_set: Basic HE-MCS And NSS Set - * @optional: Optional fields VHT Operation Information, Max Co-Hosted - * BSSID Indicator, and 6 GHz Operation Information - * - * This structure represents the payload of the "HE Operation - * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. - */ -struct ieee80211_he_operation { - __le32 he_oper_params; - __le16 he_mcs_nss_set; - u8 optional[]; -} __packed; - -/** - * struct ieee80211_he_spr - Spatial Reuse Parameter Set element - * @he_sr_control: SR Control - * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD - * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color - * Bitmap, and SRG Partial BSSID Bitmap - * - * This structure represents the payload of the "Spatial Reuse - * Parameter Set element" as described in IEEE Std 802.11ax-2021 - * section 9.4.2.252. - */ -struct ieee80211_he_spr { - u8 he_sr_control; - u8 optional[]; -} __packed; - -/** - * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field - * @aifsn: ACI/AIFSN - * @ecw_min_max: ECWmin/ECWmax - * @mu_edca_timer: MU EDCA Timer - * - * This structure represents the "MU AC Parameter Record" as described - * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. - */ -struct ieee80211_he_mu_edca_param_ac_rec { - u8 aifsn; - u8 ecw_min_max; - u8 mu_edca_timer; -} __packed; - -/** - * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element - * @mu_qos_info: QoS Info - * @ac_be: MU AC_BE Parameter Record - * @ac_bk: MU AC_BK Parameter Record - * @ac_vi: MU AC_VI Parameter Record - * @ac_vo: MU AC_VO Parameter Record - * - * This structure represents the payload of the "MU EDCA Parameter Set - * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. - */ -struct ieee80211_mu_edca_param_set { - u8 mu_qos_info; - struct ieee80211_he_mu_edca_param_ac_rec ac_be; - struct ieee80211_he_mu_edca_param_ac_rec ac_bk; - struct ieee80211_he_mu_edca_param_ac_rec ac_vi; - struct ieee80211_he_mu_edca_param_ac_rec ac_vo; -} __packed; - #define IEEE80211_EHT_MCS_NSS_RX 0x0f #define IEEE80211_EHT_MCS_NSS_TX 0xf0 @@ -1902,618 +1729,6 @@ struct ieee80211_eht_operation_info { u8 optional[]; } __packed; -/* 802.11ax HE MAC capabilities */ -#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 -#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 -#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 - -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 - -/* Link adaptation is split between byte HE_MAC_CAP1 and - * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE - * in which case the following values apply: - * 0 = No feedback. - * 1 = reserved. - * 2 = Unsolicited feedback. - * 3 = both - */ -#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 - -#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 -#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 -#define IEEE80211_HE_MAC_CAP2_TRS 0x04 -#define IEEE80211_HE_MAC_CAP2_BSR 0x08 -#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 -#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 -#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 -#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 - -#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 -#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 - -/* The maximum length of an A-MDPU is defined by the combination of the Maximum - * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the - * same field in the HE capabilities. - */ -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0 0x00 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1 0x08 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2 0x10 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3 0x18 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 -#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 -#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 -#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 - -#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 -#define IEEE80211_HE_MAC_CAP4_QTP 0x02 -#define IEEE80211_HE_MAC_CAP4_BQR 0x04 -#define IEEE80211_HE_MAC_CAP4_PSR_RESP 0x08 -#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 -#define IEEE80211_HE_MAC_CAP4_OPS 0x20 -#define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU 0x40 -/* Multi TID agg TX is split between byte #4 and #5 - * The value is a combination of B39,B40,B41 - */ -#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 - -#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 -#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 -#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION 0x04 -#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 -#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 -#define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS 0x20 -#define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 -#define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 - -#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 -#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 -#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR 13 - -/* 802.11ax HE PHY capabilities */ -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e - -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe - -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f -#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 -#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 -#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 -/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ -#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 - -#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 -#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 -#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 -#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 -#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 -#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 - -/* Note that the meaning of UL MU below is different between an AP and a non-AP - * sta, where in the AP case it indicates support for Rx and in the non-AP sta - * case it indicates support for Tx. - */ -#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 -#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 - -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 -#define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU 0x40 -#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 - -#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 -#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 - -/* Minimal allowed value of Max STS under 80MHz is 3 */ -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c - -/* Minimal allowed value of Max STS above 80MHz is 3 */ -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 - -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 - -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 - -#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 -#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 - -#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 -#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 -#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB 0x04 -#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB 0x08 -#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 -#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 -#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 -#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 - -#define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR 0x01 -#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP 0x02 -#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 -#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 -#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 - -#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 -#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 -#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 -#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 -#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 -#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242 0x00 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484 0x40 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996 0x80 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996 0xc0 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK 0xc0 - -#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 -#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 -#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 -#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 -#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 -#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 - -#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 - -/* 802.11ax HE TX/RX MCS NSS Support */ -#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) -#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) -#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) -#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 -#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 - -/* TX/RX HE MCS Support field Highest MCS subfield encoding */ -enum ieee80211_he_highest_mcs_supported_subfield_enc { - HIGHEST_MCS_SUPPORTED_MCS7 = 0, - HIGHEST_MCS_SUPPORTED_MCS8, - HIGHEST_MCS_SUPPORTED_MCS9, - HIGHEST_MCS_SUPPORTED_MCS10, - HIGHEST_MCS_SUPPORTED_MCS11, -}; - -/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ -static inline u8 -ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) -{ - u8 count = 4; - - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) - count += 4; - - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) - count += 4; - - return count; -} - -/* 802.11ax HE PPE Thresholds */ -#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) -#define IEEE80211_PPE_THRES_NSS_POS (0) -#define IEEE80211_PPE_THRES_NSS_MASK (7) -#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ - (BIT(5) | BIT(6)) -#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 -#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) -#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) -#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) - -/* - * Calculate 802.11ax HE capabilities IE PPE field size - * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* - */ -static inline u8 -ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) -{ - u8 n; - - if ((phy_cap_info[6] & - IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) - return 0; - - n = hweight8(ppe_thres_hdr & - IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); - n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> - IEEE80211_PPE_THRES_NSS_POS)); - - /* - * Each pair is 6 bits, and we need to add the 7 "header" bits to the - * total size. - */ - n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; - n = DIV_ROUND_UP(n, 8); - - return n; -} - -static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) -{ - const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; - u8 needed = sizeof(*he_cap_ie_elem); - - if (len < needed) - return false; - - needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); - if (len < needed) - return false; - - if (he_cap_ie_elem->phy_cap_info[6] & - IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { - if (len < needed + 1) - return false; - needed += ieee80211_he_ppe_size(data[needed], - he_cap_ie_elem->phy_cap_info); - } - - return len >= needed; -} - -/* HE Operation defines */ -#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 -#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 -#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 -#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 -#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 -#define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 -#define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 -#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 -#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 - -#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 -#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 -#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 -#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 -#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD 4 -#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 8 - -/** - * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field - * @primary: primary channel - * @control: control flags - * @ccfs0: channel center frequency segment 0 - * @ccfs1: channel center frequency segment 1 - * @minrate: minimum rate (in 1 Mbps units) - */ -struct ieee80211_he_6ghz_oper { - u8 primary; -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 -#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 -#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x78 - u8 control; - u8 ccfs0; - u8 ccfs1; - u8 minrate; -} __packed; - -/** - * enum ieee80211_reg_conn_bits - represents Regulatory connectivity field bits. - * - * This enumeration defines bit flags used to represent regulatory connectivity - * field bits. - * - * @IEEE80211_REG_CONN_LPI_VALID: Indicates whether the LPI bit is valid. - * @IEEE80211_REG_CONN_LPI_VALUE: Represents the value of the LPI bit. - * @IEEE80211_REG_CONN_SP_VALID: Indicates whether the SP bit is valid. - * @IEEE80211_REG_CONN_SP_VALUE: Represents the value of the SP bit. - */ -enum ieee80211_reg_conn_bits { - IEEE80211_REG_CONN_LPI_VALID = BIT(0), - IEEE80211_REG_CONN_LPI_VALUE = BIT(1), - IEEE80211_REG_CONN_SP_VALID = BIT(2), - IEEE80211_REG_CONN_SP_VALUE = BIT(3), -}; - -/* transmit power interpretation type of transmit power envelope element */ -enum ieee80211_tx_power_intrpt_type { - IEEE80211_TPE_LOCAL_EIRP, - IEEE80211_TPE_LOCAL_EIRP_PSD, - IEEE80211_TPE_REG_CLIENT_EIRP, - IEEE80211_TPE_REG_CLIENT_EIRP_PSD, -}; - -/* category type of transmit power envelope element */ -enum ieee80211_tx_power_category_6ghz { - IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0, - IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1, -}; - -/* - * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP, - * setting to 63.5 dBm means no constraint. - */ -#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT 127 - -/* - * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD, - * setting to 127 indicates no PSD limit for the 20 MHz channel. - */ -#define IEEE80211_TPE_PSD_NO_LIMIT 127 - -/** - * struct ieee80211_tx_pwr_env - Transmit Power Envelope - * @info: Transmit Power Information field - * @variable: Maximum Transmit Power field - * - * This structure represents the payload of the "Transmit Power - * Envelope element" as described in IEEE Std 802.11ax-2021 section - * 9.4.2.161 - */ -struct ieee80211_tx_pwr_env { - u8 info; - u8 variable[]; -} __packed; - -#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 -#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 -#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 - -#define IEEE80211_TX_PWR_ENV_EXT_COUNT 0xF - -static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len) -{ - const struct ieee80211_tx_pwr_env *env = (const void *)data; - u8 count, interpret, category; - u8 needed = sizeof(*env); - u8 N; /* also called N in the spec */ - - if (len < needed) - return false; - - count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); - interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); - category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); - - switch (category) { - case IEEE80211_TPE_CAT_6GHZ_DEFAULT: - case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE: - break; - default: - return false; - } - - switch (interpret) { - case IEEE80211_TPE_LOCAL_EIRP: - case IEEE80211_TPE_REG_CLIENT_EIRP: - if (count > 3) - return false; - - /* count == 0 encodes 1 value for 20 MHz, etc. */ - needed += count + 1; - - if (len < needed) - return false; - - /* there can be extension fields not accounted for in 'count' */ - - return true; - case IEEE80211_TPE_LOCAL_EIRP_PSD: - case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: - if (count > 4) - return false; - - N = count ? 1 << (count - 1) : 1; - needed += N; - - if (len < needed) - return false; - - if (len > needed) { - u8 K = u8_get_bits(env->variable[N], - IEEE80211_TX_PWR_ENV_EXT_COUNT); - - needed += 1 + K; - if (len < needed) - return false; - } - - return true; - } - - return false; -} - -/* - * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size - * @he_oper_ie: byte data of the He Operations IE, stating from the byte - * after the ext ID byte. It is assumed that he_oper_ie has at least - * sizeof(struct ieee80211_he_operation) bytes, the caller must have - * validated this. - * @return the actual size of the IE data (not including header), or 0 on error - */ -static inline u8 -ieee80211_he_oper_size(const u8 *he_oper_ie) -{ - const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; - u8 oper_len = sizeof(struct ieee80211_he_operation); - u32 he_oper_params; - - /* Make sure the input is not NULL */ - if (!he_oper_ie) - return 0; - - /* Calc required length */ - he_oper_params = le32_to_cpu(he_oper->he_oper_params); - if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) - oper_len += 3; - if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) - oper_len++; - if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) - oper_len += sizeof(struct ieee80211_he_6ghz_oper); - - /* Add the first byte (extension ID) to the total length */ - oper_len++; - - return oper_len; -} - -/** - * ieee80211_he_6ghz_oper - obtain 6 GHz operation field - * @he_oper: HE operation element (must be pre-validated for size) - * but may be %NULL - * - * Return: a pointer to the 6 GHz operation field, or %NULL - */ -static inline const struct ieee80211_he_6ghz_oper * -ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) -{ - const u8 *ret; - u32 he_oper_params; - - if (!he_oper) - return NULL; - - ret = (const void *)&he_oper->optional; - - he_oper_params = le32_to_cpu(he_oper->he_oper_params); - - if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) - return NULL; - if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) - ret += 3; - if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) - ret++; - - return (const void *)ret; -} - -/* HE Spatial Reuse defines */ -#define IEEE80211_HE_SPR_PSR_DISALLOWED BIT(0) -#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED BIT(1) -#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT BIT(2) -#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT BIT(3) -#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED BIT(4) - -/* - * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size - * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte - * after the ext ID byte. It is assumed that he_spr_ie has at least - * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated - * this - * @return the actual size of the IE data (not including header), or 0 on error - */ -static inline u8 -ieee80211_he_spr_size(const u8 *he_spr_ie) -{ - const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; - u8 spr_len = sizeof(struct ieee80211_he_spr); - u8 he_spr_params; - - /* Make sure the input is not NULL */ - if (!he_spr_ie) - return 0; - - /* Calc required length */ - he_spr_params = he_spr->he_sr_control; - if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) - spr_len++; - if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) - spr_len += 18; - - /* Add the first byte (extension ID) to the total length */ - spr_len++; - - return spr_len; -} - /* S1G Capabilities Information field */ #define IEEE80211_S1G_CAPABILITY_LEN 15 @@ -2697,6 +1912,9 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 #define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 +/* need HE definitions for EHT functions */ +#include "ieee80211-he.h" + /* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ static inline u8 ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, @@ -3815,24 +3033,6 @@ struct ieee80211_tspec_ie { __le16 medium_time; } __packed; -struct ieee80211_he_6ghz_capa { - /* uses IEEE80211_HE_6GHZ_CAP_* below */ - __le16 capa; -} __packed; - -/* HE 6 GHz band capabilities */ -/* uses enum ieee80211_min_mpdu_spacing values */ -#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 -/* uses enum ieee80211_vht_max_ampdu_length_exp values */ -#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 -/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ -#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 -/* WLAN_HT_CAP_SM_PS_* values */ -#define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 -#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 -#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 -#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 - /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame From dd827cff429d5d20cf6a6310b6438d0d13d33028 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 Nov 2025 15:36:53 +0100 Subject: [PATCH 0246/1518] wifi: ieee80211: split EHT definitions out [ Upstream commit 86bc0c662322b4749cd666678d2fdce7015bcae3 ] The ieee80211.h file has gotten very long, continue splitting it by putting EHT definitions into a separate file. Link: https://patch.msgid.link/20251105153843.bf77fe169140.I691267e0edd914c604a5bfd447d33be00044c9b4@changeid Signed-off-by: Johannes Berg Stable-dep-of: cb0caadb64ca ("wifi: ieee80211: fix definition of EHT-MCS 15 in MRU") Signed-off-by: Sasha Levin --- include/linux/ieee80211-eht.h | 1182 +++++++++++++++++++++++++++++++++ include/linux/ieee80211.h | 1164 +------------------------------- 2 files changed, 1184 insertions(+), 1162 deletions(-) create mode 100644 include/linux/ieee80211-eht.h diff --git a/include/linux/ieee80211-eht.h b/include/linux/ieee80211-eht.h new file mode 100644 index 0000000000000..f9782e46c5e52 --- /dev/null +++ b/include/linux/ieee80211-eht.h @@ -0,0 +1,1182 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 EHT definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_EHT_H +#define LINUX_IEEE80211_EHT_H + +#include +#include +/* need HE definitions for the inlines here */ +#include + +#define IEEE80211_TTLM_MAX_CNT 2 +#define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 +#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 +#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 +#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 +#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 + +#define IEEE80211_TTLM_DIRECTION_DOWN 0 +#define IEEE80211_TTLM_DIRECTION_UP 1 +#define IEEE80211_TTLM_DIRECTION_BOTH 2 + +/** + * struct ieee80211_ttlm_elem - TID-To-Link Mapping element + * + * Defined in section 9.4.2.314 in P802.11be_D4 + * + * @control: the first part of control field + * @optional: the second part of control field + */ +struct ieee80211_ttlm_elem { + u8 control; + u8 optional[]; +} __packed; + +#define IEEE80211_EHT_MCS_NSS_RX 0x0f +#define IEEE80211_EHT_MCS_NSS_TX 0xf0 + +/** + * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max + * supported NSS for per MCS. + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 7. + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 8 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + * @rx_tx_max_nss: array of the previous fields for easier loop access + */ +struct ieee80211_eht_mcs_nss_supp_20mhz_only { + union { + struct { + u8 rx_tx_mcs7_max_nss; + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; + }; + u8 rx_tx_max_nss[4]; + }; +}; + +/** + * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except + * 20MHz only stations). + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + * @rx_tx_max_nss: array of the previous fields for easier loop access + */ +struct ieee80211_eht_mcs_nss_supp_bw { + union { + struct { + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; + }; + u8 rx_tx_max_nss[3]; + }; +}; + +/** + * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data + * + * This structure is the "EHT Capabilities element" fixed fields as + * described in P802.11be_D2.0 section 9.4.2.313. + * + * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* + * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* + */ +struct ieee80211_eht_cap_elem_fixed { + u8 mac_cap_info[2]; + u8 phy_cap_info[9]; +} __packed; + +/** + * struct ieee80211_eht_cap_elem - EHT capabilities element + * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed + * @optional: optional parts + */ +struct ieee80211_eht_cap_elem { + struct ieee80211_eht_cap_elem_fixed fixed; + + /* + * Followed by: + * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. + * EHT PPE Thresholds field: variable length. + */ + u8 optional[]; +} __packed; + +#define IEEE80211_EHT_OPER_INFO_PRESENT 0x01 +#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x02 +#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION 0x04 +#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT 0x08 +#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK 0x30 +#define IEEE80211_EHT_OPER_MCS15_DISABLE 0x40 + +/** + * struct ieee80211_eht_operation - eht operation element + * + * This structure is the "EHT Operation Element" fields as + * described in P802.11be_D2.0 section 9.4.2.311 + * + * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_* + * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in + * EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and + * receive. + * @optional: optional parts + */ +struct ieee80211_eht_operation { + u8 params; + struct ieee80211_eht_mcs_nss_supp_20mhz_only basic_mcs_nss; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_eht_operation_info - eht operation information + * + * @control: EHT operation information control. + * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz + * EHT BSS. + * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS. + * @optional: optional parts + */ +struct ieee80211_eht_operation_info { + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 optional[]; +} __packed; + +/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ +#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 +#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 +#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 +#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK 0xc0 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895 0 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991 1 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 + +#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 +#define IEEE80211_EHT_MAC_CAP1_EHT_TRS 0x02 +#define IEEE80211_EHT_MAC_CAP1_TXOP_RET 0x04 +#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS 0x08 +#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK 0x30 +#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS 0x40 + +/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ +#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 +#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 +#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 + +/* EHT beamformee number of spatial streams <= 80MHz is split */ +#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 + +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 + +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 + +/* EHT number of sounding dimensions for 320MHz is split */ +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 +#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 +#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 +#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 +#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 +#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 + +#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 +#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 +#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 + +#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 +#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 + +/* Maximum number of supported EHT LTF is split */ +#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 +#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 + +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x30 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 +#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 + +#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 + +#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 +#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 + +/* + * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311 + */ +#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 + +/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ +static inline u8 +ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, + const struct ieee80211_eht_cap_elem_fixed *eht_cap, + bool from_ap) +{ + u8 count = 0; + + /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return 3; + + /* on 2.4 GHz, these three bits are reserved, so should be 0 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + count += 3; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 3; + + if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + count += 3; + + if (count) + return count; + + return from_ap ? 3 : 4; +} + +/* 802.11be EHT PPE Thresholds */ +#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 +#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf +#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 +#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 +#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 + +/* + * Calculate 802.11be EHT capabilities IE EHT field size + */ +static inline u8 +ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u32 n; + + if (!(phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) + return 0; + + n = hweight16(ppe_thres_hdr & + IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); + + /* + * Each pair is 6 bits, and we need to add the 9 "header" bits to the + * total size. + */ + n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + + IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; + return DIV_ROUND_UP(n, 8); +} + +static inline bool +ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, + bool from_ap) +{ + const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; + u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); + + if (len < needed || !he_capa) + return false; + + needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, + (const void *)data, + from_ap); + if (len < needed) + return false; + + if (elem->phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { + u16 ppe_thres_hdr; + + if (len < needed + sizeof(ppe_thres_hdr)) + return false; + + ppe_thres_hdr = get_unaligned_le16(data + needed); + needed += ieee80211_eht_ppe_size(ppe_thres_hdr, + elem->phy_cap_info); + } + + return len >= needed; +} + +static inline bool +ieee80211_eht_oper_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_eht_operation *elem = (const void *)data; + u8 needed = sizeof(*elem); + + if (len < needed) + return false; + + if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) { + needed += 3; + + if (elem->params & + IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) + needed += 2; + } + + return len >= needed; +} + +/* must validate ieee80211_eht_oper_size_ok() first */ +static inline u16 +ieee80211_eht_oper_dis_subchan_bitmap(const struct ieee80211_eht_operation *eht_oper) +{ + const struct ieee80211_eht_operation_info *info = + (const void *)eht_oper->optional; + + if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) + return 0; + + if (!(eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) + return 0; + + return get_unaligned_le16(info->optional); +} + +#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) + +struct ieee80211_bandwidth_indication { + u8 params; + struct ieee80211_eht_operation_info info; +} __packed; + +static inline bool +ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_bandwidth_indication *bwi = (const void *)data; + + if (len < sizeof(*bwi)) + return false; + + if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && + len < sizeof(*bwi) + 2) + return false; + + return true; +} + +/* Protected EHT action codes */ +enum ieee80211_protected_eht_actioncode { + WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, + WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, + WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5, + WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6, + WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12, +}; + +/* multi-link device */ +#define IEEE80211_MLD_MAX_NUM_LINKS 15 + +#define IEEE80211_ML_CONTROL_TYPE 0x0007 +#define IEEE80211_ML_CONTROL_TYPE_BASIC 0 +#define IEEE80211_ML_CONTROL_TYPE_PREQ 1 +#define IEEE80211_ML_CONTROL_TYPE_RECONF 2 +#define IEEE80211_ML_CONTROL_TYPE_TDLS 3 +#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 +#define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 + +struct ieee80211_multi_link_elem { + __le16 control; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 +#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 +#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 +#define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 +#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 +#define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 +#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP 0x0400 + +#define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff +#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 +#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 + +/* + * Described in P802.11be_D3.0 + * dot11MSDTimerDuration should default to 5484 (i.e. 171.375) + * dot11MSDOFDMEDthreshold defaults to -72 (i.e. 0) + * dot11MSDTXOPMAX defaults to 1 + */ +#define IEEE80211_MED_SYNC_DELAY_DEFAULT 0x10ac + +#define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 +#define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 +#define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 +#define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 + +#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f +#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_NO_SUPP 0 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME 1 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_RESERVED 2 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 +#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 +#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 +#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT 0x2000 +#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT 0x4000 + +struct ieee80211_mle_basic_common_info { + u8 len; + u8 mld_mac_addr[ETH_ALEN]; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 + +struct ieee80211_mle_preq_common_info { + u8 len; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 +#define IEEE80211_MLC_RECONF_PRES_EML_CAPA 0x0020 +#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP 0x0040 +#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP 0x0080 + +/* no fixed fields in RECONF */ + +struct ieee80211_mle_tdls_common_info { + u8 len; + u8 ap_mld_mac_addr[ETH_ALEN]; +} __packed; + +#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 + +/* no fixed fields in PRIO_ACCESS */ + +/** + * ieee80211_mle_common_size - check multi-link element common size + * @data: multi-link element, must already be checked for size using + * ieee80211_mle_size_ok() + * Return: the size of the multi-link element's "common" subfield + */ +static inline u8 ieee80211_mle_common_size(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + case IEEE80211_ML_CONTROL_TYPE_PREQ: + case IEEE80211_ML_CONTROL_TYPE_TDLS: + case IEEE80211_ML_CONTROL_TYPE_RECONF: + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + /* + * The length is the first octet pointed by mle->variable so no + * need to add anything + */ + break; + default: + WARN_ON(1); + return 0; + } + + return sizeof(*mle) + mle->variable[0]; +} + +/** + * ieee80211_mle_get_link_id - returns the link ID + * @data: the basic multi link element + * Return: the link ID, or -1 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline int ieee80211_mle_get_link_id(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_LINK_ID)) + return -1; + + return *common; +} + +/** + * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count + * @data: pointer to the basic multi link element + * Return: the BSS Parameter Change Count field value, or -1 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline int +ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)) + return -1; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + + return *common; +} + +/** + * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay + * @data: pointer to the multi-link element + * Return: the medium synchronization delay field value from the multi-link + * element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT) + * if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) + return IEEE80211_MED_SYNC_DELAY_DEFAULT; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_eml_cap - returns the EML capability + * @data: pointer to the multi-link element + * Return: the EML capability field value from the multi-link element, + * or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. + * @data: pointer to the multi-link element + * Return: the MLD capabilities and operations field value from the multi-link + * element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + + return get_unaligned_le16(common); +} + +/* Defined in Figure 9-1074t in P802.11be_D7.0 */ +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE 0x0001 +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_RECO_MAX_LINKS_MASK 0x001e +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE 0x0020 +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK 0x0040 +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_BTM_MLD_RECO_MULTI_AP 0x0080 + +/** + * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities + * and operations. + * @data: pointer to the multi-link element + * Return: the extended MLD capabilities and operations field value from + * the multi-link element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_mld_id - returns the MLD ID + * @data: pointer to the multi-link element + * Return: The MLD ID in the given multi-link element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u8 ieee80211_mle_get_mld_id(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_ID)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + + return *common; +} + +/** + * ieee80211_mle_size_ok - validate multi-link element size + * @data: pointer to the element data + * @len: length of the containing element + * Return: whether or not the multi-link element size is OK + */ +static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u8 fixed = sizeof(*mle); + u8 common = 0; + bool check_common_len = false; + u16 control; + + if (!data || len < fixed) + return false; + + control = le16_to_cpu(mle->control); + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + common += sizeof(struct ieee80211_mle_basic_common_info); + check_common_len = true; + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP) + common += 2; + break; + case IEEE80211_ML_CONTROL_TYPE_PREQ: + common += sizeof(struct ieee80211_mle_preq_common_info); + if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) + common += 1; + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) + common += ETH_ALEN; + if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP) + common += 2; + break; + case IEEE80211_ML_CONTROL_TYPE_TDLS: + common += sizeof(struct ieee80211_mle_tdls_common_info); + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + common = ETH_ALEN + 1; + break; + default: + /* we don't know this type */ + return true; + } + + if (len < fixed + common) + return false; + + if (!check_common_len) + return true; + + /* if present, common length is the first octet there */ + return mle->variable[0] >= common; +} + +/** + * ieee80211_mle_type_ok - validate multi-link element type and size + * @data: pointer to the element data + * @type: expected type of the element + * @len: length of the containing element + * Return: whether or not the multi-link element type matches and size is OK + */ +static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control; + + if (!ieee80211_mle_size_ok(data, len)) + return false; + + control = le16_to_cpu(mle->control); + + if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) == type) + return true; + + return false; +} + +enum ieee80211_mle_subelems { + IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, + IEEE80211_MLE_SUBELEM_FRAGMENT = 254, +}; + +#define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f +#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 +#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 +#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 +#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 +#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 +#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 +#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 +#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 + +struct ieee80211_mle_per_sta_profile { + __le16 control; + u8 sta_info_len; + u8 variable[]; +} __packed; + +/** + * ieee80211_mle_basic_sta_prof_size_ok - validate basic multi-link element sta + * profile size + * @data: pointer to the sub element data + * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise + */ +static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, + size_t len) +{ + const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; + u16 control; + u8 fixed = sizeof(*prof); + u8 info_len = 1; + + if (len < fixed) + return false; + + control = le16_to_cpu(prof->control); + + if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) + info_len += 6; + if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) + info_len += 8; + if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && + control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { + if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) + info_len += 2; + else + info_len += 1; + } + if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT) + info_len += 1; + + return prof->sta_info_len >= info_len && + fixed + prof->sta_info_len - 1 <= len; +} + +/** + * ieee80211_mle_basic_sta_prof_bss_param_ch_cnt - get per-STA profile BSS + * parameter change count + * @prof: the per-STA profile, having been checked with + * ieee80211_mle_basic_sta_prof_size_ok() for the correct length + * + * Return: The BSS parameter change count value if present, 0 otherwise. + */ +static inline u8 +ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta_profile *prof) +{ + u16 control = le16_to_cpu(prof->control); + const u8 *pos = prof->variable; + + if (!(control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)) + return 0; + + if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) + pos += 6; + if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) + pos += 2; + if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) + pos += 8; + if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) + pos += 2; + if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && + control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { + if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) + pos += 2; + else + pos += 1; + } + + return *pos; +} + +#define IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID 0x000f +#define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 +#define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 +#define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE 0x0780 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM 0 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK 2 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK 3 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS 4 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 + +/** + * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link + * element sta profile size. + * @data: pointer to the sub element data + * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise + */ +static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, + size_t len) +{ + const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; + u16 control; + u8 fixed = sizeof(*prof); + u8 info_len = 1; + + if (len < fixed) + return false; + + control = le16_to_cpu(prof->control); + + if (control & IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT) + info_len += ETH_ALEN; + if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT) + info_len += 2; + + return prof->sta_info_len >= info_len && + fixed + prof->sta_info_len - 1 <= len; +} + +#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID 0x000f +#define IEEE80211_EPCS_ENA_RESP_BODY_LEN 3 + +static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_ttlm_elem *t2l = (const void *)data; + u8 control, fixed = sizeof(*t2l), elem_len = 0; + + if (len < fixed) + return false; + + control = t2l->control; + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) + elem_len += 2; + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) + elem_len += 3; + + if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { + u8 bm_size; + + elem_len += 1; + if (len < fixed + elem_len) + return false; + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + bm_size = 1; + else + bm_size = 2; + + elem_len += hweight8(t2l->optional[0]) * bm_size; + } + + return len >= fixed + elem_len; +} + +/** + * ieee80211_emlsr_pad_delay_in_us - Fetch the EMLSR Padding delay + * in microseconds + * @eml_cap: EML capabilities field value from common info field of + * the Multi-link element + * Return: the EMLSR Padding delay (in microseconds) encoded in the + * EML Capabilities field + */ + +static inline u32 ieee80211_emlsr_pad_delay_in_us(u16 eml_cap) +{ + /* IEEE Std 802.11be-2024 Table 9-417i—Encoding of the EMLSR + * Padding Delay subfield. + */ + u32 pad_delay = u16_get_bits(eml_cap, + IEEE80211_EML_CAP_EMLSR_PADDING_DELAY); + + if (!pad_delay || + pad_delay > IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US) + return 0; + + return 32 * (1 << (pad_delay - 1)); +} + +/** + * ieee80211_emlsr_trans_delay_in_us - Fetch the EMLSR Transition + * delay in microseconds + * @eml_cap: EML capabilities field value from common info field of + * the Multi-link element + * Return: the EMLSR Transition delay (in microseconds) encoded in the + * EML Capabilities field + */ + +static inline u32 ieee80211_emlsr_trans_delay_in_us(u16 eml_cap) +{ + /* IEEE Std 802.11be-2024 Table 9-417j—Encoding of the EMLSR + * Transition Delay subfield. + */ + u32 trans_delay = + u16_get_bits(eml_cap, + IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY); + + /* invalid values also just use 0 */ + if (!trans_delay || + trans_delay > IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US) + return 0; + + return 16 * (1 << (trans_delay - 1)); +} + +/** + * ieee80211_eml_trans_timeout_in_us - Fetch the EMLSR Transition + * timeout value in microseconds + * @eml_cap: EML capabilities field value from common info field of + * the Multi-link element + * Return: the EMLSR Transition timeout (in microseconds) encoded in + * the EML Capabilities field + */ + +static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) +{ + /* IEEE Std 802.11be-2024 Table 9-417m—Encoding of the + * Transition Timeout subfield. + */ + u8 timeout = u16_get_bits(eml_cap, + IEEE80211_EML_CAP_TRANSITION_TIMEOUT); + + /* invalid values also just use 0 */ + if (!timeout || timeout > IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU) + return 0; + + return 128 * (1 << (timeout - 1)); +} + +#define for_each_mle_subelement(_elem, _data, _len) \ + if (ieee80211_mle_size_ok(_data, _len)) \ + for_each_element(_elem, \ + _data + ieee80211_mle_common_size(_data),\ + _len - ieee80211_mle_common_size(_data)) + +#endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2f3d0412ca759..992a0c09c1e53 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1141,30 +1141,6 @@ ieee80211_s1g_optional_len(__le16 fc) return len; } -#define IEEE80211_TTLM_MAX_CNT 2 -#define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 -#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 -#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 -#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 -#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 - -#define IEEE80211_TTLM_DIRECTION_DOWN 0 -#define IEEE80211_TTLM_DIRECTION_UP 1 -#define IEEE80211_TTLM_DIRECTION_BOTH 2 - -/** - * struct ieee80211_ttlm_elem - TID-To-Link Mapping element - * - * Defined in section 9.4.2.314 in P802.11be_D4 - * - * @control: the first part of control field - * @optional: the second part of control field - */ -struct ieee80211_ttlm_elem { - u8 control; - u8 optional[]; -} __packed; - /** * struct ieee80211_bss_load_elem - BSS Load elemen * @@ -1591,144 +1567,6 @@ struct ieee80211_p2p_noa_attr { #define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) #define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F -#define IEEE80211_EHT_MCS_NSS_RX 0x0f -#define IEEE80211_EHT_MCS_NSS_TX 0xf0 - -/** - * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max - * supported NSS for per MCS. - * - * For each field below, bits 0 - 3 indicate the maximal number of spatial - * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams - * for Tx. - * - * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 0 - 7. - * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 8 - 9. - * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 10 - 11. - * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 12 - 13. - * @rx_tx_max_nss: array of the previous fields for easier loop access - */ -struct ieee80211_eht_mcs_nss_supp_20mhz_only { - union { - struct { - u8 rx_tx_mcs7_max_nss; - u8 rx_tx_mcs9_max_nss; - u8 rx_tx_mcs11_max_nss; - u8 rx_tx_mcs13_max_nss; - }; - u8 rx_tx_max_nss[4]; - }; -}; - -/** - * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except - * 20MHz only stations). - * - * For each field below, bits 0 - 3 indicate the maximal number of spatial - * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams - * for Tx. - * - * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 0 - 9. - * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 10 - 11. - * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 12 - 13. - * @rx_tx_max_nss: array of the previous fields for easier loop access - */ -struct ieee80211_eht_mcs_nss_supp_bw { - union { - struct { - u8 rx_tx_mcs9_max_nss; - u8 rx_tx_mcs11_max_nss; - u8 rx_tx_mcs13_max_nss; - }; - u8 rx_tx_max_nss[3]; - }; -}; - -/** - * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data - * - * This structure is the "EHT Capabilities element" fixed fields as - * described in P802.11be_D2.0 section 9.4.2.313. - * - * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* - * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* - */ -struct ieee80211_eht_cap_elem_fixed { - u8 mac_cap_info[2]; - u8 phy_cap_info[9]; -} __packed; - -/** - * struct ieee80211_eht_cap_elem - EHT capabilities element - * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed - * @optional: optional parts - */ -struct ieee80211_eht_cap_elem { - struct ieee80211_eht_cap_elem_fixed fixed; - - /* - * Followed by: - * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. - * EHT PPE Thresholds field: variable length. - */ - u8 optional[]; -} __packed; - -#define IEEE80211_EHT_OPER_INFO_PRESENT 0x01 -#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x02 -#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION 0x04 -#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT 0x08 -#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK 0x30 -#define IEEE80211_EHT_OPER_MCS15_DISABLE 0x40 - -/** - * struct ieee80211_eht_operation - eht operation element - * - * This structure is the "EHT Operation Element" fields as - * described in P802.11be_D2.0 section 9.4.2.311 - * - * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_* - * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in - * EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and - * receive. - * @optional: optional parts - */ -struct ieee80211_eht_operation { - u8 params; - struct ieee80211_eht_mcs_nss_supp_20mhz_only basic_mcs_nss; - u8 optional[]; -} __packed; - -/** - * struct ieee80211_eht_operation_info - eht operation information - * - * @control: EHT operation information control. - * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz - * EHT BSS. - * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS. - * @optional: optional parts - */ -struct ieee80211_eht_operation_info { - u8 control; - u8 ccfs0; - u8 ccfs1; - u8 optional[]; -} __packed; - /* S1G Capabilities Information field */ #define IEEE80211_S1G_CAPABILITY_LEN 15 @@ -1815,258 +1653,6 @@ struct ieee80211_eht_operation_info { #define S1G_2M_PRIMARY_LOCATION_LOWER 0 #define S1G_2M_PRIMARY_LOCATION_UPPER 1 -/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ -#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 -#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 -#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 -#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 -#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 -#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK 0xc0 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895 0 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991 1 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 - -#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 -#define IEEE80211_EHT_MAC_CAP1_EHT_TRS 0x02 -#define IEEE80211_EHT_MAC_CAP1_TXOP_RET 0x04 -#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS 0x08 -#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK 0x30 -#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS 0x40 - -/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ -#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 -#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 -#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 -#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 -#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 -#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 - -/* EHT beamformee number of spatial streams <= 80MHz is split */ -#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 -#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 - -#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c -#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 - -#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 -#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 - -/* EHT number of sounding dimensions for 320MHz is split */ -#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 -#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 -#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 -#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 -#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 -#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 -#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 -#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 -#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 - -#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 -#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 -#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 -#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 -#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 - -#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 -#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 -#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 -#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 - -/* Maximum number of supported EHT LTF is split */ -#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 -#define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 -#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 - -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x08 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x30 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ 0x40 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 -#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 - -#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 -#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 -#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 -#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 -#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 -#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 -#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 -#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 - -#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 -#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 - -/* - * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311 - */ -#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 - -/* need HE definitions for EHT functions */ -#include "ieee80211-he.h" - -/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ -static inline u8 -ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, - const struct ieee80211_eht_cap_elem_fixed *eht_cap, - bool from_ap) -{ - u8 count = 0; - - /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) - return 3; - - /* on 2.4 GHz, these three bits are reserved, so should be 0 */ - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) - count += 3; - - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) - count += 3; - - if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) - count += 3; - - if (count) - return count; - - return from_ap ? 3 : 4; -} - -/* 802.11be EHT PPE Thresholds */ -#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 -#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf -#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 -#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 -#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 - -/* - * Calculate 802.11be EHT capabilities IE EHT field size - */ -static inline u8 -ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) -{ - u32 n; - - if (!(phy_cap_info[5] & - IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) - return 0; - - n = hweight16(ppe_thres_hdr & - IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); - n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); - - /* - * Each pair is 6 bits, and we need to add the 9 "header" bits to the - * total size. - */ - n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + - IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; - return DIV_ROUND_UP(n, 8); -} - -static inline bool -ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, - bool from_ap) -{ - const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; - u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); - - if (len < needed || !he_capa) - return false; - - needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, - (const void *)data, - from_ap); - if (len < needed) - return false; - - if (elem->phy_cap_info[5] & - IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { - u16 ppe_thres_hdr; - - if (len < needed + sizeof(ppe_thres_hdr)) - return false; - - ppe_thres_hdr = get_unaligned_le16(data + needed); - needed += ieee80211_eht_ppe_size(ppe_thres_hdr, - elem->phy_cap_info); - } - - return len >= needed; -} - -static inline bool -ieee80211_eht_oper_size_ok(const u8 *data, u8 len) -{ - const struct ieee80211_eht_operation *elem = (const void *)data; - u8 needed = sizeof(*elem); - - if (len < needed) - return false; - - if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) { - needed += 3; - - if (elem->params & - IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) - needed += 2; - } - - return len >= needed; -} - -/* must validate ieee80211_eht_oper_size_ok() first */ -static inline u16 -ieee80211_eht_oper_dis_subchan_bitmap(const struct ieee80211_eht_operation *eht_oper) -{ - const struct ieee80211_eht_operation_info *info = - (const void *)eht_oper->optional; - - if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) - return 0; - - if (!(eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) - return 0; - - return get_unaligned_le16(info->optional); -} - -#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) - -struct ieee80211_bandwidth_indication { - u8 params; - struct ieee80211_eht_operation_info info; -} __packed; - -static inline bool -ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) -{ - const struct ieee80211_bandwidth_indication *bwi = (const void *)data; - - if (len < sizeof(*bwi)) - return false; - - if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && - len < sizeof(*bwi) + 2) - return false; - - return true; -} - #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) @@ -2587,23 +2173,6 @@ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; -/* Protected EHT action codes */ -enum ieee80211_protected_eht_actioncode { - WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, - WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, - WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, - WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3, - WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4, - WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5, - WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6, - WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7, - WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8, - WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9, - WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10, - WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11, - WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12, -}; - /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, @@ -3855,737 +3424,6 @@ struct ieee80211_tbtt_info_ge_11 { struct ieee80211_rnr_mld_params mld_params; } __packed; -/* multi-link device */ -#define IEEE80211_MLD_MAX_NUM_LINKS 15 - -#define IEEE80211_ML_CONTROL_TYPE 0x0007 -#define IEEE80211_ML_CONTROL_TYPE_BASIC 0 -#define IEEE80211_ML_CONTROL_TYPE_PREQ 1 -#define IEEE80211_ML_CONTROL_TYPE_RECONF 2 -#define IEEE80211_ML_CONTROL_TYPE_TDLS 3 -#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 -#define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 - -struct ieee80211_multi_link_elem { - __le16 control; - u8 variable[]; -} __packed; - -#define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 -#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 -#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 -#define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 -#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 -#define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 -#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP 0x0400 - -#define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff -#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 -#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 - -/* - * Described in P802.11be_D3.0 - * dot11MSDTimerDuration should default to 5484 (i.e. 171.375) - * dot11MSDOFDMEDthreshold defaults to -72 (i.e. 0) - * dot11MSDTXOPMAX defaults to 1 - */ -#define IEEE80211_MED_SYNC_DELAY_DEFAULT 0x10ac - -#define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 -#define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 -#define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 -#define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 -#define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 -#define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 -#define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 -#define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 - -#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f -#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_NO_SUPP 0 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME 1 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_RESERVED 2 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 -#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 -#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 -#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT 0x2000 -#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT 0x4000 - -struct ieee80211_mle_basic_common_info { - u8 len; - u8 mld_mac_addr[ETH_ALEN]; - u8 variable[]; -} __packed; - -#define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 - -struct ieee80211_mle_preq_common_info { - u8 len; - u8 variable[]; -} __packed; - -#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 -#define IEEE80211_MLC_RECONF_PRES_EML_CAPA 0x0020 -#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP 0x0040 -#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP 0x0080 - -/* no fixed fields in RECONF */ - -struct ieee80211_mle_tdls_common_info { - u8 len; - u8 ap_mld_mac_addr[ETH_ALEN]; -} __packed; - -#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 - -/* no fixed fields in PRIO_ACCESS */ - -/** - * ieee80211_mle_common_size - check multi-link element common size - * @data: multi-link element, must already be checked for size using - * ieee80211_mle_size_ok() - * Return: the size of the multi-link element's "common" subfield - */ -static inline u8 ieee80211_mle_common_size(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - - switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { - case IEEE80211_ML_CONTROL_TYPE_BASIC: - case IEEE80211_ML_CONTROL_TYPE_PREQ: - case IEEE80211_ML_CONTROL_TYPE_TDLS: - case IEEE80211_ML_CONTROL_TYPE_RECONF: - case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - /* - * The length is the first octet pointed by mle->variable so no - * need to add anything - */ - break; - default: - WARN_ON(1); - return 0; - } - - return sizeof(*mle) + mle->variable[0]; -} - -/** - * ieee80211_mle_get_link_id - returns the link ID - * @data: the basic multi link element - * Return: the link ID, or -1 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline int ieee80211_mle_get_link_id(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_LINK_ID)) - return -1; - - return *common; -} - -/** - * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count - * @data: pointer to the basic multi link element - * Return: the BSS Parameter Change Count field value, or -1 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline int -ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)) - return -1; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - - return *common; -} - -/** - * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay - * @data: pointer to the multi-link element - * Return: the medium synchronization delay field value from the multi-link - * element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT) - * if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) - return IEEE80211_MED_SYNC_DELAY_DEFAULT; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - - return get_unaligned_le16(common); -} - -/** - * ieee80211_mle_get_eml_cap - returns the EML capability - * @data: pointer to the multi-link element - * Return: the EML capability field value from the multi-link element, - * or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - - return get_unaligned_le16(common); -} - -/** - * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. - * @data: pointer to the multi-link element - * Return: the MLD capabilities and operations field value from the multi-link - * element, or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* - * common points now at the beginning of - * ieee80211_mle_basic_common_info - */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - - return get_unaligned_le16(common); -} - -/* Defined in Figure 9-1074t in P802.11be_D7.0 */ -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE 0x0001 -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_RECO_MAX_LINKS_MASK 0x001e -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE 0x0020 -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK 0x0040 -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_BTM_MLD_RECO_MULTI_AP 0x0080 - -/** - * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities - * and operations. - * @data: pointer to the multi-link element - * Return: the extended MLD capabilities and operations field value from - * the multi-link element, or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* - * common points now at the beginning of - * ieee80211_mle_basic_common_info - */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) - common += 1; - - return get_unaligned_le16(common); -} - -/** - * ieee80211_mle_get_mld_id - returns the MLD ID - * @data: pointer to the multi-link element - * Return: The MLD ID in the given multi-link element, or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u8 ieee80211_mle_get_mld_id(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* - * common points now at the beginning of - * ieee80211_mle_basic_common_info - */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_ID)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) - common += 2; - - return *common; -} - -/** - * ieee80211_mle_size_ok - validate multi-link element size - * @data: pointer to the element data - * @len: length of the containing element - * Return: whether or not the multi-link element size is OK - */ -static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u8 fixed = sizeof(*mle); - u8 common = 0; - bool check_common_len = false; - u16 control; - - if (!data || len < fixed) - return false; - - control = le16_to_cpu(mle->control); - - switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { - case IEEE80211_ML_CONTROL_TYPE_BASIC: - common += sizeof(struct ieee80211_mle_basic_common_info); - check_common_len = true; - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP) - common += 2; - break; - case IEEE80211_ML_CONTROL_TYPE_PREQ: - common += sizeof(struct ieee80211_mle_preq_common_info); - if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) - common += 1; - check_common_len = true; - break; - case IEEE80211_ML_CONTROL_TYPE_RECONF: - if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) - common += ETH_ALEN; - if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP) - common += 2; - if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP) - common += 2; - break; - case IEEE80211_ML_CONTROL_TYPE_TDLS: - common += sizeof(struct ieee80211_mle_tdls_common_info); - check_common_len = true; - break; - case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - common = ETH_ALEN + 1; - break; - default: - /* we don't know this type */ - return true; - } - - if (len < fixed + common) - return false; - - if (!check_common_len) - return true; - - /* if present, common length is the first octet there */ - return mle->variable[0] >= common; -} - -/** - * ieee80211_mle_type_ok - validate multi-link element type and size - * @data: pointer to the element data - * @type: expected type of the element - * @len: length of the containing element - * Return: whether or not the multi-link element type matches and size is OK - */ -static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control; - - if (!ieee80211_mle_size_ok(data, len)) - return false; - - control = le16_to_cpu(mle->control); - - if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) == type) - return true; - - return false; -} - -enum ieee80211_mle_subelems { - IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, - IEEE80211_MLE_SUBELEM_FRAGMENT = 254, -}; - -#define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f -#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 -#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 -#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 -#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 -#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 -#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 -#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 -#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 - -struct ieee80211_mle_per_sta_profile { - __le16 control; - u8 sta_info_len; - u8 variable[]; -} __packed; - -/** - * ieee80211_mle_basic_sta_prof_size_ok - validate basic multi-link element sta - * profile size - * @data: pointer to the sub element data - * @len: length of the containing sub element - * Return: %true if the STA profile is large enough, %false otherwise - */ -static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, - size_t len) -{ - const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; - u16 control; - u8 fixed = sizeof(*prof); - u8 info_len = 1; - - if (len < fixed) - return false; - - control = le16_to_cpu(prof->control); - - if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) - info_len += 6; - if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) - info_len += 2; - if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) - info_len += 8; - if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) - info_len += 2; - if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && - control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { - if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) - info_len += 2; - else - info_len += 1; - } - if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT) - info_len += 1; - - return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len - 1 <= len; -} - -/** - * ieee80211_mle_basic_sta_prof_bss_param_ch_cnt - get per-STA profile BSS - * parameter change count - * @prof: the per-STA profile, having been checked with - * ieee80211_mle_basic_sta_prof_size_ok() for the correct length - * - * Return: The BSS parameter change count value if present, 0 otherwise. - */ -static inline u8 -ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta_profile *prof) -{ - u16 control = le16_to_cpu(prof->control); - const u8 *pos = prof->variable; - - if (!(control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)) - return 0; - - if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) - pos += 6; - if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) - pos += 2; - if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) - pos += 8; - if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) - pos += 2; - if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && - control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { - if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) - pos += 2; - else - pos += 1; - } - - return *pos; -} - -#define IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID 0x000f -#define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 -#define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 -#define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE 0x0780 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM 0 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK 2 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK 3 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS 4 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 - -/** - * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link - * element sta profile size. - * @data: pointer to the sub element data - * @len: length of the containing sub element - * Return: %true if the STA profile is large enough, %false otherwise - */ -static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, - size_t len) -{ - const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; - u16 control; - u8 fixed = sizeof(*prof); - u8 info_len = 1; - - if (len < fixed) - return false; - - control = le16_to_cpu(prof->control); - - if (control & IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT) - info_len += ETH_ALEN; - if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT) - info_len += 2; - if (control & IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT) - info_len += 2; - - return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len - 1 <= len; -} - -#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID 0x000f -#define IEEE80211_EPCS_ENA_RESP_BODY_LEN 3 - -static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) -{ - const struct ieee80211_ttlm_elem *t2l = (const void *)data; - u8 control, fixed = sizeof(*t2l), elem_len = 0; - - if (len < fixed) - return false; - - control = t2l->control; - - if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) - elem_len += 2; - if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) - elem_len += 3; - - if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { - u8 bm_size; - - elem_len += 1; - if (len < fixed + elem_len) - return false; - - if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) - bm_size = 1; - else - bm_size = 2; - - elem_len += hweight8(t2l->optional[0]) * bm_size; - } - - return len >= fixed + elem_len; -} - -/** - * ieee80211_emlsr_pad_delay_in_us - Fetch the EMLSR Padding delay - * in microseconds - * @eml_cap: EML capabilities field value from common info field of - * the Multi-link element - * Return: the EMLSR Padding delay (in microseconds) encoded in the - * EML Capabilities field - */ - -static inline u32 ieee80211_emlsr_pad_delay_in_us(u16 eml_cap) -{ - /* IEEE Std 802.11be-2024 Table 9-417i—Encoding of the EMLSR - * Padding Delay subfield. - */ - u32 pad_delay = u16_get_bits(eml_cap, - IEEE80211_EML_CAP_EMLSR_PADDING_DELAY); - - if (!pad_delay || - pad_delay > IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US) - return 0; - - return 32 * (1 << (pad_delay - 1)); -} - -/** - * ieee80211_emlsr_trans_delay_in_us - Fetch the EMLSR Transition - * delay in microseconds - * @eml_cap: EML capabilities field value from common info field of - * the Multi-link element - * Return: the EMLSR Transition delay (in microseconds) encoded in the - * EML Capabilities field - */ - -static inline u32 ieee80211_emlsr_trans_delay_in_us(u16 eml_cap) -{ - /* IEEE Std 802.11be-2024 Table 9-417j—Encoding of the EMLSR - * Transition Delay subfield. - */ - u32 trans_delay = - u16_get_bits(eml_cap, - IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY); - - /* invalid values also just use 0 */ - if (!trans_delay || - trans_delay > IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US) - return 0; - - return 16 * (1 << (trans_delay - 1)); -} - -/** - * ieee80211_eml_trans_timeout_in_us - Fetch the EMLSR Transition - * timeout value in microseconds - * @eml_cap: EML capabilities field value from common info field of - * the Multi-link element - * Return: the EMLSR Transition timeout (in microseconds) encoded in - * the EML Capabilities field - */ - -static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) -{ - /* IEEE Std 802.11be-2024 Table 9-417m—Encoding of the - * Transition Timeout subfield. - */ - u8 timeout = u16_get_bits(eml_cap, - IEEE80211_EML_CAP_TRANSITION_TIMEOUT); - - /* invalid values also just use 0 */ - if (!timeout || timeout > IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU) - return 0; - - return 128 * (1 << (timeout - 1)); -} - -#define for_each_mle_subelement(_elem, _data, _len) \ - if (ieee80211_mle_size_ok(_data, _len)) \ - for_each_element(_elem, \ - _data + ieee80211_mle_common_size(_data),\ - _len - ieee80211_mle_common_size(_data)) - /* NAN operation mode, as defined in Wi-Fi Aware (TM) specification Table 81 */ #define NAN_OP_MODE_PHY_MODE_VHT 0x01 #define NAN_OP_MODE_PHY_MODE_HE 0x10 @@ -4605,6 +3443,8 @@ static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) #include "ieee80211-ht.h" #include "ieee80211-vht.h" +#include "ieee80211-he.h" +#include "ieee80211-eht.h" #include "ieee80211-mesh.h" #endif /* LINUX_IEEE80211_H */ From 0ee803fc4787a71c64aad0e1b4bc11d5b2acf963 Mon Sep 17 00:00:00 2001 From: Shayne Chen Date: Fri, 13 Mar 2026 14:21:49 +0800 Subject: [PATCH 0247/1518] wifi: ieee80211: fix definition of EHT-MCS 15 in MRU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit cb0caadb64ca0894c4a24e1a34841f260d462f90 ] According to the definition in IEEE Std 802.11be-2024, Table 9-417r, each bit indicates support for the transmission and reception of EHT-MCS 15 in: - B0: 52+26-tone and 106+26-tone MRUs. - B1: a 484+242-tone MRU if 80 MHz is supported. - B2: a 996+484-tone MRU and a 996+484+242-tone MRU if 160 MHz is supported. - B3: a 3×996-tone MRU if 320 MHz is supported. Fixes: 6239da18d2f9 ("wifi: mac80211: adjust EHT capa when lowering bandwidth") Signed-off-by: Shayne Chen Link: https://patch.msgid.link/20260313062150.3165433-1-shayne.chen@mediatek.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- include/linux/ieee80211-eht.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/ieee80211-eht.h b/include/linux/ieee80211-eht.h index f9782e46c5e52..cd9abf5193966 100644 --- a/include/linux/ieee80211-eht.h +++ b/include/linux/ieee80211-eht.h @@ -251,8 +251,8 @@ struct ieee80211_eht_operation_info { #define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 #define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x08 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x30 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x10 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x20 #define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ 0x40 #define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 #define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 From eebe930e785d5655dec24327778f744758100003 Mon Sep 17 00:00:00 2001 From: Cai Xinchen Date: Thu, 12 Mar 2026 06:59:06 +0000 Subject: [PATCH 0248/1518] dpaa2: add independent dependencies for FSL_DPAA2_SWITCH [ Upstream commit 12589892f41c4c645c80ef9f036f7451a6045624 ] Since the commit 84cba72956fd ("dpaa2-switch: integrate the MAC endpoint support") included dpaa2-mac.o in the driver, but it didn't select PCS_LYNX, PHYLINK and FSL_XGMAC_MDIO. it will lead to link error, such as undefined reference to `phylink_ethtool_ksettings_set' undefined reference to `lynx_pcs_create_fwnode' And the same reason as the commit d2624e70a2f53 ("dpaa2-eth: select XGMAC_MDIO for MDIO bus support"), enable the FSL_XGMAC_MDIO Kconfig option in order to have MDIO access to internal and external PHYs. Because dpaa2-switch uses fsl_mc_driver APIs, add depends on FSL_MC_BUS && FSL_MC_DPIO as FSL_DPAA2_SWITCH do. FSL_XGMAC_MDIO and FSL_MC_BUS depend on OF, thus the dependence of FSL_MC_BUS can satisfy FSL_XGMAC_MDIO's OF requirement. Fixes: 84cba72956fd ("dpaa2-switch: integrate the MAC endpoint support") Suggested-by: Ioana Ciornei Signed-off-by: Cai Xinchen Link: https://patch.msgid.link/20260312065907.476663-2-caixinchen1@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/dpaa2/Kconfig | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig index d029b69c3f183..36280e5d99e1f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig @@ -34,6 +34,10 @@ config FSL_DPAA2_SWITCH tristate "Freescale DPAA2 Ethernet Switch" depends on BRIDGE || BRIDGE=n depends on NET_SWITCHDEV + depends on FSL_MC_BUS && FSL_MC_DPIO + select PHYLINK + select PCS_LYNX + select FSL_XGMAC_MDIO help Driver for Freescale DPAA2 Ethernet Switch. This driver manages switch objects discovered on the Freeescale MC bus. From 3849f0ee39ea96f0ae07e354aa8b70cd00bf359e Mon Sep 17 00:00:00 2001 From: Cai Xinchen Date: Thu, 12 Mar 2026 06:59:07 +0000 Subject: [PATCH 0249/1518] dpaa2: compile dpaa2 even CONFIG_FSL_DPAA2_ETH=n [ Upstream commit 97daf00745f7f9f261b0e91418de6e79d7826c36 ] CONFIG_FSL_DPAA2_ETH and CONFIG_FSL_DPAA2_SWITCH are not associated, but the compilation of FSL_DPAA2_SWITCH depends on the compilation of the dpaa2 folder. The files controlled by CONFIG_FSL_DPAA2_SWITCH in the dpaa2 folder are not controlled by CONFIG_FSL_DPAA2_ETH, except for the files controlled by CONFIG_FSL_DPAA2_SWITCH. Therefore, removing the restriction will not affect the compilation of the files in the directory. Fixes: f48298d3fbfaa ("staging: dpaa2-switch: move the driver out of staging") Suggested-by: Ioana Ciornei Signed-off-by: Cai Xinchen Link: https://patch.msgid.link/20260312065907.476663-3-caixinchen1@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index de7b318422330..d0a259e47960f 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -22,6 +22,5 @@ ucc_geth_driver-objs := ucc_geth.o ucc_geth_ethtool.o obj-$(CONFIG_FSL_FMAN) += fman/ obj-$(CONFIG_FSL_DPAA_ETH) += dpaa/ -obj-$(CONFIG_FSL_DPAA2_ETH) += dpaa2/ - +obj-y += dpaa2/ obj-y += enetc/ From 366b0e05ee24f5ba62bdc7ec1346038258b9a797 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 13 Mar 2026 18:46:25 +0100 Subject: [PATCH 0250/1518] s390/bpf: Zero-extend bpf prog return values and kfunc arguments [ Upstream commit 202e42e4aa890172366354b233c42c73107a3f59 ] s390x ABI requires callers to zero-extend unsigned arguments and sign-extend signed arguments, and callees to zero-extend unsigned return values and sign-extend signed return values. s390 BPF JIT currently implements only sign extension. Fix this omission and implement zero extension too. Fixes: 528eb2cb87bc ("s390/bpf: Implement arch_prepare_bpf_trampoline()") Reported-by: Hari Bathini Closes: https://lore.kernel.org/bpf/20260312080113.843408-1-hbathini@linux.ibm.com/ Signed-off-by: Ilya Leoshkevich Tested-by: Ihor Solodrai Link: https://lore.kernel.org/r/20260313174807.581826-1-iii@linux.ibm.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- arch/s390/net/bpf_jit_comp.c | 39 ++++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 15 deletions(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index cf461d76e9da3..d7cdd907ac797 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -831,25 +831,34 @@ static int bpf_jit_probe_post(struct bpf_jit *jit, struct bpf_prog *fp, } /* - * Sign-extend the register if necessary + * Sign- or zero-extend the register if necessary */ -static int sign_extend(struct bpf_jit *jit, int r, u8 size, u8 flags) +static int sign_zero_extend(struct bpf_jit *jit, int r, u8 size, u8 flags) { - if (!(flags & BTF_FMODEL_SIGNED_ARG)) - return 0; - switch (size) { case 1: - /* lgbr %r,%r */ - EMIT4(0xb9060000, r, r); + if (flags & BTF_FMODEL_SIGNED_ARG) + /* lgbr %r,%r */ + EMIT4(0xb9060000, r, r); + else + /* llgcr %r,%r */ + EMIT4(0xb9840000, r, r); return 0; case 2: - /* lghr %r,%r */ - EMIT4(0xb9070000, r, r); + if (flags & BTF_FMODEL_SIGNED_ARG) + /* lghr %r,%r */ + EMIT4(0xb9070000, r, r); + else + /* llghr %r,%r */ + EMIT4(0xb9850000, r, r); return 0; case 4: - /* lgfr %r,%r */ - EMIT4(0xb9140000, r, r); + if (flags & BTF_FMODEL_SIGNED_ARG) + /* lgfr %r,%r */ + EMIT4(0xb9140000, r, r); + else + /* llgfr %r,%r */ + EMIT4(0xb9160000, r, r); return 0; case 8: return 0; @@ -1799,9 +1808,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, return -1; for (j = 0; j < m->nr_args; j++) { - if (sign_extend(jit, BPF_REG_1 + j, - m->arg_size[j], - m->arg_flags[j])) + if (sign_zero_extend(jit, BPF_REG_1 + j, + m->arg_size[j], + m->arg_flags[j])) return -1; } } @@ -2555,7 +2564,7 @@ static int invoke_bpf_prog(struct bpf_tramp_jit *tjit, EMIT6_PCREL_RILB_PTR(0xc0050000, REG_14, p->bpf_func); /* stg %r2,retval_off(%r15) */ if (save_ret) { - if (sign_extend(jit, REG_2, m->ret_size, m->ret_flags)) + if (sign_zero_extend(jit, REG_2, m->ret_size, m->ret_flags)) return -1; EMIT6_DISP_LH(0xe3000000, 0x0024, REG_2, REG_0, REG_15, tjit->retval_off); From c8b710655012a2993a9567873fb71a8a51f8459c Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Mon, 9 Mar 2026 23:44:24 +0530 Subject: [PATCH 0251/1518] powerpc/pgtable-frag: Fix bad page state in pte_frag_destroy [ Upstream commit fda4d71651f71c44b35829d13f3c8bf920032f77 ] powerpc uses pt_frag_refcount as a reference counter for tracking it's pte and pmd page table fragments. For PTE table, in case of Hash with 64K pagesize, we have 16 fragments of 4K size in one 64K page. Patch series [1] "mm: free retracted page table by RCU" added pte_free_defer() to defer the freeing of PTE tables when retract_page_tables() is called for madvise MADV_COLLAPSE on shmem range. [1]: https://lore.kernel.org/all/7cd843a9-aa80-14f-5eb2-33427363c20@google.com/ pte_free_defer() sets the active flag on the corresponding fragment's folio & calls pte_fragment_free(), which reduces the pt_frag_refcount. When pt_frag_refcount reaches 0 (no active fragment using the folio), it checks if the folio active flag is set, if set, it calls call_rcu to free the folio, it the active flag is unset then it calls pte_free_now(). Now, this can lead to following problem in a corner case... [ 265.351553][ T183] BUG: Bad page state in process a.out pfn:20d62 [ 265.353555][ T183] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x20d62 [ 265.355457][ T183] flags: 0x3ffff800000100(active|node=0|zone=0|lastcpupid=0x7ffff) [ 265.358719][ T183] raw: 003ffff800000100 0000000000000000 5deadbeef0000122 0000000000000000 [ 265.360177][ T183] raw: 0000000000000000 c0000000119caf58 00000000ffffffff 0000000000000000 [ 265.361438][ T183] page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set [ 265.362572][ T183] Modules linked in: [ 265.364622][ T183] CPU: 0 UID: 0 PID: 183 Comm: a.out Not tainted 6.18.0-rc3-00141-g1ddeaaace7ff-dirty #53 VOLUNTARY [ 265.364785][ T183] Hardware name: IBM pSeries (emulated by qemu) POWER10 (architected) 0x801200 0xf000006 of:SLOF,git-ee03ae pSeries [ 265.364908][ T183] Call Trace: [ 265.364955][ T183] [c000000011e6f7c0] [c000000001cfaa18] dump_stack_lvl+0x130/0x148 (unreliable) [ 265.365202][ T183] [c000000011e6f7f0] [c000000000794758] bad_page+0xb4/0x1c8 [ 265.365384][ T183] [c000000011e6f890] [c00000000079c020] __free_frozen_pages+0x838/0xd08 [ 265.365554][ T183] [c000000011e6f980] [c0000000000a70ac] pte_frag_destroy+0x298/0x310 [ 265.365729][ T183] [c000000011e6fa30] [c0000000000aa764] arch_exit_mmap+0x34/0x218 [ 265.365912][ T183] [c000000011e6fa80] [c000000000751698] exit_mmap+0xb8/0x820 [ 265.366080][ T183] [c000000011e6fc30] [c0000000001b1258] __mmput+0x98/0x300 [ 265.366244][ T183] [c000000011e6fc80] [c0000000001c81f8] do_exit+0x470/0x1508 [ 265.366421][ T183] [c000000011e6fd70] [c0000000001c95e4] do_group_exit+0x88/0x148 [ 265.366602][ T183] [c000000011e6fdc0] [c0000000001c96ec] pid_child_should_wake+0x0/0x178 [ 265.366780][ T183] [c000000011e6fdf0] [c00000000003a270] system_call_exception+0x1b0/0x4e0 [ 265.366958][ T183] [c000000011e6fe50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec The bad page state error occurs when such a folio gets freed (with active flag set), from do_exit() path in parallel. ... this can happen when the pte fragment was allocated from this folio, but when all the fragments get freed, the pte_frag_refcount still had some unused fragments. Now, if this process exits, with such folio as it's cached pte_frag in mm->context, then during pte_frag_destroy(), we simply call pagetable_dtor() and pagetable_free(), meaning it doesn't clear the active flag. This, can lead to the above bug. Since we are anyway in do_exit() path, then if the refcount is 0, then I guess it should be ok to simply clear the folio active flag before calling pagetable_dtor() & pagetable_free(). Fixes: 32cc0b7c9d50 ("powerpc: add pte_free_defer() for pgtables sharing page") Reviewed-by: Christophe Leroy (CS GROUP) Signed-off-by: Ritesh Harjani (IBM) Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/ee13e7f99b8f258019da2b37655b998e73e5ef8b.1773078178.git.ritesh.list@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/mm/pgtable-frag.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index 77e55eac16e42..ae742564a3d56 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -25,6 +25,7 @@ void pte_frag_destroy(void *pte_frag) count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { + folio_clear_active(ptdesc_folio(ptdesc)); pagetable_dtor(ptdesc); pagetable_free(ptdesc); } From 8f32c95a567871ba10ac5564bc737799edb900f3 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Tue, 19 Aug 2025 14:12:09 +0200 Subject: [PATCH 0252/1518] params: Replace __modinit with __init_or_module [ Upstream commit 3cb0c3bdea5388519bc1bf575dca6421b133302b ] Remove the custom __modinit macro from kernel/params.c and instead use the common __init_or_module macro from include/linux/module.h. Both provide the same functionality. Signed-off-by: Petr Pavlu Reviewed-by: Aaron Tomlin Reviewed-by: Daniel Gomez Reviewed-by: Sami Tolvanen Signed-off-by: Sami Tolvanen Stable-dep-of: deffe1edba62 ("module: Fix freeing of charp module parameters when CONFIG_SYSFS=n") Signed-off-by: Sasha Levin --- kernel/params.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/kernel/params.c b/kernel/params.c index b96cfd693c996..7c2242f64bf08 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -596,12 +596,6 @@ static ssize_t param_attr_store(const struct module_attribute *mattr, } #endif -#ifdef CONFIG_MODULES -#define __modinit -#else -#define __modinit __init -#endif - #ifdef CONFIG_SYSFS void kernel_param_lock(struct module *mod) { @@ -626,9 +620,9 @@ EXPORT_SYMBOL(kernel_param_unlock); * create file in sysfs. Returns an error on out of memory. Always cleans up * if there's an error. */ -static __modinit int add_sysfs_param(struct module_kobject *mk, - const struct kernel_param *kp, - const char *name) +static __init_or_module int add_sysfs_param(struct module_kobject *mk, + const struct kernel_param *kp, + const char *name) { struct module_param_attrs *new_mp; struct attribute **new_attrs; @@ -761,7 +755,8 @@ void destroy_params(const struct kernel_param *params, unsigned num) params[i].ops->free(params[i].arg); } -struct module_kobject __modinit * lookup_or_create_module_kobject(const char *name) +struct module_kobject * __init_or_module +lookup_or_create_module_kobject(const char *name) { struct module_kobject *mk; struct kobject *kobj; From d538795ea2ef593010b34ee12476a5ff71c02960 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Fri, 13 Mar 2026 14:48:02 +0100 Subject: [PATCH 0253/1518] module: Fix freeing of charp module parameters when CONFIG_SYSFS=n [ Upstream commit deffe1edba626d474fef38007c03646ca5876a0e ] When setting a charp module parameter, the param_set_charp() function allocates memory to store a copy of the input value. Later, when the module is potentially unloaded, the destroy_params() function is called to free this allocated memory. However, destroy_params() is available only when CONFIG_SYSFS=y, otherwise only a dummy variant is present. In the unlikely case that the kernel is configured with CONFIG_MODULES=y and CONFIG_SYSFS=n, this results in a memory leak of charp values when a module is unloaded. Fix this issue by making destroy_params() always available when CONFIG_MODULES=y. Rename the function to module_destroy_params() to clarify that it is intended for use by the module loader. Fixes: e180a6b7759a ("param: fix charp parameters set via sysfs") Signed-off-by: Petr Pavlu Signed-off-by: Sami Tolvanen Signed-off-by: Sasha Levin --- include/linux/moduleparam.h | 11 +++-------- kernel/module/main.c | 4 ++-- kernel/params.c | 27 ++++++++++++++++++--------- 3 files changed, 23 insertions(+), 19 deletions(-) diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 6907aedc4f748..77775fd821407 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -414,14 +414,9 @@ extern char *parse_args(const char *name, void *arg, parse_unknown_fn unknown); /* Called by module remove. */ -#ifdef CONFIG_SYSFS -extern void destroy_params(const struct kernel_param *params, unsigned num); -#else -static inline void destroy_params(const struct kernel_param *params, - unsigned num) -{ -} -#endif /* !CONFIG_SYSFS */ +#ifdef CONFIG_MODULES +void module_destroy_params(const struct kernel_param *params, unsigned int num); +#endif /* All the helper functions */ /* The macros to do compile-time type checking stolen from Jakub diff --git a/kernel/module/main.c b/kernel/module/main.c index 66d4efbddfffe..3745cd02c8479 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1408,7 +1408,7 @@ static void free_module(struct module *mod) module_unload_free(mod); /* Free any allocated parameters. */ - destroy_params(mod->kp, mod->num_kp); + module_destroy_params(mod->kp, mod->num_kp); if (is_livepatch_module(mod)) free_module_elf(mod); @@ -3519,7 +3519,7 @@ static int load_module(struct load_info *info, const char __user *uargs, mod_sysfs_teardown(mod); coming_cleanup: mod->state = MODULE_STATE_GOING; - destroy_params(mod->kp, mod->num_kp); + module_destroy_params(mod->kp, mod->num_kp); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); klp_module_going(mod); diff --git a/kernel/params.c b/kernel/params.c index 7c2242f64bf08..8942884e21c43 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -746,15 +746,6 @@ void module_param_sysfs_remove(struct module *mod) } #endif -void destroy_params(const struct kernel_param *params, unsigned num) -{ - unsigned int i; - - for (i = 0; i < num; i++) - if (params[i].ops->free) - params[i].ops->free(params[i].arg); -} - struct module_kobject * __init_or_module lookup_or_create_module_kobject(const char *name) { @@ -986,3 +977,21 @@ static int __init param_sysfs_builtin_init(void) late_initcall(param_sysfs_builtin_init); #endif /* CONFIG_SYSFS */ + +#ifdef CONFIG_MODULES + +/* + * module_destroy_params - free all parameters for one module + * @params: module parameters (array) + * @num: number of module parameters + */ +void module_destroy_params(const struct kernel_param *params, unsigned int num) +{ + unsigned int i; + + for (i = 0; i < num; i++) + if (params[i].ops->free) + params[i].ops->free(params[i].arg); +} + +#endif /* CONFIG_MODULES */ From a761a1539a55efe6519ce624e43d8c7779bfa811 Mon Sep 17 00:00:00 2001 From: Heitor Alves de Siqueira Date: Fri, 13 Mar 2026 18:27:57 -0300 Subject: [PATCH 0254/1518] wifi: libertas: use USB anchors for tracking in-flight URBs [ Upstream commit a57f35fc19add4dfe33703af575a2c19c2cef9c7 ] The libertas driver currently handles URB lifecycles manually, which makes it non-trivial to check if specific URBs are pending or not. Add anchors for TX/RX URBs, and use those to track in-flight requests. Signed-off-by: Heitor Alves de Siqueira Link: https://patch.msgid.link/20260313-libertas-usb-anchors-v1-1-915afbe988d7@igalia.com Signed-off-by: Johannes Berg Stable-dep-of: 7c5c2b661bdb ("wifi: libertas: don't kill URBs in interrupt context") Signed-off-by: Sasha Levin --- .../net/wireless/marvell/libertas/if_usb.c | 27 ++++++++++++------- .../net/wireless/marvell/libertas/if_usb.h | 3 +++ 2 files changed, 20 insertions(+), 10 deletions(-) diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c index 924ab93b7b671..60bfff523b918 100644 --- a/drivers/net/wireless/marvell/libertas/if_usb.c +++ b/drivers/net/wireless/marvell/libertas/if_usb.c @@ -114,8 +114,8 @@ static void if_usb_write_bulk_callback(struct urb *urb) static void if_usb_free(struct if_usb_card *cardp) { /* Unlink tx & rx urb */ - usb_kill_urb(cardp->tx_urb); - usb_kill_urb(cardp->rx_urb); + usb_kill_anchored_urbs(&cardp->tx_submitted); + usb_kill_anchored_urbs(&cardp->rx_submitted); usb_free_urb(cardp->tx_urb); cardp->tx_urb = NULL; @@ -221,6 +221,9 @@ static int if_usb_probe(struct usb_interface *intf, udev->descriptor.bDeviceSubClass, udev->descriptor.bDeviceProtocol); + init_usb_anchor(&cardp->rx_submitted); + init_usb_anchor(&cardp->tx_submitted); + for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; if (usb_endpoint_is_bulk_in(endpoint)) { @@ -426,7 +429,7 @@ static int usb_tx_block(struct if_usb_card *cardp, uint8_t *payload, uint16_t nb goto tx_ret; } - usb_kill_urb(cardp->tx_urb); + usb_kill_anchored_urbs(&cardp->tx_submitted); usb_fill_bulk_urb(cardp->tx_urb, cardp->udev, usb_sndbulkpipe(cardp->udev, @@ -435,8 +438,10 @@ static int usb_tx_block(struct if_usb_card *cardp, uint8_t *payload, uint16_t nb cardp->tx_urb->transfer_flags |= URB_ZERO_PACKET; + usb_anchor_urb(cardp->tx_urb, &cardp->tx_submitted); if ((ret = usb_submit_urb(cardp->tx_urb, GFP_ATOMIC))) { lbs_deb_usbd(&cardp->udev->dev, "usb_submit_urb failed: %d\n", ret); + usb_unanchor_urb(cardp->tx_urb); } else { lbs_deb_usb2(&cardp->udev->dev, "usb_submit_urb success\n"); ret = 0; @@ -467,8 +472,10 @@ static int __if_usb_submit_rx_urb(struct if_usb_card *cardp, cardp); lbs_deb_usb2(&cardp->udev->dev, "Pointer for rx_urb %p\n", cardp->rx_urb); + usb_anchor_urb(cardp->rx_urb, &cardp->rx_submitted); if ((ret = usb_submit_urb(cardp->rx_urb, GFP_ATOMIC))) { lbs_deb_usbd(&cardp->udev->dev, "Submit Rx URB failed: %d\n", ret); + usb_unanchor_urb(cardp->rx_urb); kfree_skb(skb); cardp->rx_skb = NULL; ret = -1; @@ -838,8 +845,8 @@ static void if_usb_prog_firmware(struct lbs_private *priv, int ret, } /* Cancel any pending usb business */ - usb_kill_urb(cardp->rx_urb); - usb_kill_urb(cardp->tx_urb); + usb_kill_anchored_urbs(&cardp->rx_submitted); + usb_kill_anchored_urbs(&cardp->tx_submitted); cardp->fwlastblksent = 0; cardp->fwdnldover = 0; @@ -869,8 +876,8 @@ static void if_usb_prog_firmware(struct lbs_private *priv, int ret, if (cardp->bootcmdresp == BOOT_CMD_RESP_NOT_SUPPORTED) { /* Return to normal operation */ ret = -EOPNOTSUPP; - usb_kill_urb(cardp->rx_urb); - usb_kill_urb(cardp->tx_urb); + usb_kill_anchored_urbs(&cardp->rx_submitted); + usb_kill_anchored_urbs(&cardp->tx_submitted); if (if_usb_submit_rx_urb(cardp) < 0) ret = -EIO; goto done; @@ -900,7 +907,7 @@ static void if_usb_prog_firmware(struct lbs_private *priv, int ret, wait_event_interruptible(cardp->fw_wq, cardp->surprise_removed || cardp->fwdnldover); timer_delete_sync(&cardp->fw_timeout); - usb_kill_urb(cardp->rx_urb); + usb_kill_anchored_urbs(&cardp->rx_submitted); if (!cardp->fwdnldover) { pr_info("failed to load fw, resetting device!\n"); @@ -960,8 +967,8 @@ static int if_usb_suspend(struct usb_interface *intf, pm_message_t message) goto out; /* Unlink tx & rx urb */ - usb_kill_urb(cardp->tx_urb); - usb_kill_urb(cardp->rx_urb); + usb_kill_anchored_urbs(&cardp->tx_submitted); + usb_kill_anchored_urbs(&cardp->rx_submitted); out: return ret; diff --git a/drivers/net/wireless/marvell/libertas/if_usb.h b/drivers/net/wireless/marvell/libertas/if_usb.h index 7d0daeb33c3f7..a0cd36197c2b0 100644 --- a/drivers/net/wireless/marvell/libertas/if_usb.h +++ b/drivers/net/wireless/marvell/libertas/if_usb.h @@ -48,6 +48,9 @@ struct if_usb_card { struct urb *rx_urb, *tx_urb; struct lbs_private *priv; + struct usb_anchor rx_submitted; + struct usb_anchor tx_submitted; + struct sk_buff *rx_skb; uint8_t ep_in; From 00c0317cebf44151df18fb647781f315268cdd98 Mon Sep 17 00:00:00 2001 From: Heitor Alves de Siqueira Date: Fri, 13 Mar 2026 18:27:58 -0300 Subject: [PATCH 0255/1518] wifi: libertas: don't kill URBs in interrupt context [ Upstream commit 7c5c2b661bdb78c1472b8833265c9ed1ee880039 ] Serialization for the TX path was enforced by calling usb_kill_urb()/usb_kill_anchored_urbs(), to prevent transmission before a previous URB was completed. usb_tx_block() can be called from interrupt context (e.g. in the HCD giveback path), so we can't always use it to kill in-flight URBs. Prevent sleeping during interrupt context by checking the tx_submitted anchor for existing URBs. We now return -EBUSY, to indicate there's a pending request. Reported-by: syzbot+74afbb6355826ffc2239@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=74afbb6355826ffc2239 Fixes: d66676e6ca96 ("wifi: libertas: fix WARNING in usb_tx_block") Signed-off-by: Heitor Alves de Siqueira Link: https://patch.msgid.link/20260313-libertas-usb-anchors-v1-2-915afbe988d7@igalia.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/libertas/if_usb.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c index 60bfff523b918..f6b9a3c43c93c 100644 --- a/drivers/net/wireless/marvell/libertas/if_usb.c +++ b/drivers/net/wireless/marvell/libertas/if_usb.c @@ -429,7 +429,12 @@ static int usb_tx_block(struct if_usb_card *cardp, uint8_t *payload, uint16_t nb goto tx_ret; } - usb_kill_anchored_urbs(&cardp->tx_submitted); + /* check if there are pending URBs */ + if (!usb_anchor_empty(&cardp->tx_submitted)) { + lbs_deb_usbd(&cardp->udev->dev, "%s failed: pending URB\n", __func__); + ret = -EBUSY; + goto tx_ret; + } usb_fill_bulk_urb(cardp->tx_urb, cardp->udev, usb_sndbulkpipe(cardp->udev, From ca5b2452d6f10b92f5e4ac2c222c77a503c44c11 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Wed, 24 Sep 2025 16:20:52 +0200 Subject: [PATCH 0256/1518] tools/nolibc: implement %m if errno is not defined MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit fbd1b7f6b322a63b21ebbf00c732a17bb8bdb5d4 ] For improved compatibility, print %m as "unknown error" when nolibc is compiled using NOLIBC_IGNORE_ERRNO. Signed-off-by: Benjamin Berg Signed-off-by: Thomas Weißschuh Stable-dep-of: 4045e7b19bbf ("tools/nolibc/printf: Move snprintf length check to callback") Signed-off-by: Sasha Levin --- tools/include/nolibc/stdio.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 724d05ce69624..1f16dab2ac884 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -321,11 +321,13 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char if (!outstr) outstr="(null)"; } -#ifndef NOLIBC_IGNORE_ERRNO else if (c == 'm') { +#ifdef NOLIBC_IGNORE_ERRNO + outstr = "unknown error"; +#else outstr = strerror(errno); - } #endif /* NOLIBC_IGNORE_ERRNO */ + } else if (c == '%') { /* queue it verbatim */ continue; From ea23d00b98f572a76b2f8243c6d4696d25cbd8ad Mon Sep 17 00:00:00 2001 From: David Laight Date: Mon, 23 Feb 2026 10:17:24 +0000 Subject: [PATCH 0257/1518] tools/nolibc/printf: Change variables 'c' to 'ch' and 'tmpbuf[]' to 'outbuf[]' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f675ae28fcdf7db93a8c1a6964f062725b1e06a0 ] Changing 'c' makes the code slightly easier to read because the variable stands out from the single character literals (especially 'c'). Change tmpbuf[] to outbuf[] because 'out' points into it. The following patches pretty much rewrite the function so the churn is limited. Signed-off-by: David Laight Acked-by: Willy Tarreau Link: https://patch.msgid.link/20260223101735.2922-7-david.laight.linux@gmail.com Signed-off-by: Thomas Weißschuh Stable-dep-of: 4045e7b19bbf ("tools/nolibc/printf: Move snprintf length check to callback") Signed-off-by: Sasha Levin --- tools/include/nolibc/stdio.h | 38 ++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 1f16dab2ac884..aff11d6069f6f 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -250,16 +250,16 @@ typedef int (*__nolibc_printf_cb)(intptr_t state, const char *buf, size_t size); static __attribute__((unused, format(printf, 4, 0))) int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char *fmt, va_list args) { - char escape, lpref, c; + char escape, lpref, ch; unsigned long long v; unsigned int written, width; size_t len, ofs, w; - char tmpbuf[21]; + char outbuf[21]; const char *outstr; written = ofs = escape = lpref = 0; while (1) { - c = fmt[ofs++]; + ch = fmt[ofs++]; width = 0; if (escape) { @@ -267,17 +267,17 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char escape = 0; /* width */ - while (c >= '0' && c <= '9') { + while (ch >= '0' && ch <= '9') { width *= 10; - width += c - '0'; + width += ch - '0'; - c = fmt[ofs++]; + ch = fmt[ofs++]; } - if (c == 'c' || c == 'd' || c == 'u' || c == 'x' || c == 'p') { - char *out = tmpbuf; + if (ch == 'c' || ch == 'd' || ch == 'u' || ch == 'x' || ch == 'p') { + char *out = outbuf; - if (c == 'p') + if (ch == 'p') v = va_arg(args, unsigned long); else if (lpref) { if (lpref > 1) @@ -287,7 +287,7 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char } else v = va_arg(args, unsigned int); - if (c == 'd') { + if (ch == 'd') { /* sign-extend the value */ if (lpref == 0) v = (long long)(int)v; @@ -295,7 +295,7 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char v = (long long)(long)v; } - switch (c) { + switch (ch) { case 'c': out[0] = v; out[1] = 0; @@ -314,30 +314,30 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char u64toh_r(v, out); break; } - outstr = tmpbuf; + outstr = outbuf; } - else if (c == 's') { + else if (ch == 's') { outstr = va_arg(args, char *); if (!outstr) outstr="(null)"; } - else if (c == 'm') { + else if (ch == 'm') { #ifdef NOLIBC_IGNORE_ERRNO outstr = "unknown error"; #else outstr = strerror(errno); #endif /* NOLIBC_IGNORE_ERRNO */ } - else if (c == '%') { + else if (ch == '%') { /* queue it verbatim */ continue; } else { /* modifiers or final 0 */ - if (c == 'l') { + if (ch == 'l') { /* long format prefix, maintain the escape */ lpref++; - } else if (c == 'j') { + } else if (ch == 'j') { lpref = 2; } escape = 1; @@ -348,7 +348,7 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char } /* not an escape sequence */ - if (c == 0 || c == '%') { + if (ch == 0 || ch == '%') { /* flush pending data on escape or end */ escape = 1; lpref = 0; @@ -369,7 +369,7 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char written += len; do_escape: - if (c == 0) + if (ch == 0) break; fmt += ofs; ofs = 0; From d902905cb7080d39a5f922df7c2daa3a877b3aa9 Mon Sep 17 00:00:00 2001 From: David Laight Date: Mon, 2 Mar 2026 10:17:54 +0000 Subject: [PATCH 0258/1518] tools/nolibc/printf: Move snprintf length check to callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4045e7b19bbf7338452cda11e64cfe7ae3361964 ] Move output truncation to the snprintf() callback. This simplifies the main code and fixes truncation of padded fields. Add a zero length callback to 'finalise' the buffer rather than doing it in snprintf() itself. Fixes: e90ce42e81381 ("tools/nolibc: implement width padding in printf()") Signed-off-by: David Laight Acked-by: Willy Tarreau Link: https://patch.msgid.link/20260302101815.3043-3-david.laight.linux@gmail.com [Thomas: clean up Fixes trailer] Signed-off-by: Thomas Weißschuh Signed-off-by: Sasha Levin --- tools/include/nolibc/stdio.h | 94 +++++++++++++++++++++++++----------- 1 file changed, 67 insertions(+), 27 deletions(-) diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index aff11d6069f6f..a2fc7c8706dfa 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -244,16 +244,25 @@ char *fgets(char *s, int size, FILE *stream) * - %[l*]{d,u,c,x,p} * - %s * - unknown modifiers are ignored. + * + * Called by vfprintf() and snprintf() to do the actual formatting. + * The callers provide a callback function to save the formatted data. + * The callback function is called multiple times: + * - for each group of literal characters in the format string. + * - for field padding. + * - for each conversion specifier. + * - with (NULL, 0) at the end of the __nolibc_printf. + * If the callback returns non-zero __nolibc_printf() immediately returns -1. */ -typedef int (*__nolibc_printf_cb)(intptr_t state, const char *buf, size_t size); +typedef int (*__nolibc_printf_cb)(void *state, const char *buf, size_t size); -static __attribute__((unused, format(printf, 4, 0))) -int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char *fmt, va_list args) +static __attribute__((unused, format(printf, 3, 0))) +int __nolibc_printf(__nolibc_printf_cb cb, void *state, const char *fmt, va_list args) { char escape, lpref, ch; unsigned long long v; unsigned int written, width; - size_t len, ofs, w; + size_t len, ofs; char outbuf[21]; const char *outstr; @@ -355,17 +364,13 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char outstr = fmt; len = ofs - 1; flush_str: - if (n) { - w = len < n ? len : n; - n -= w; - while (width-- > w) { - if (cb(state, " ", 1) != 0) - return -1; - written += 1; - } - if (cb(state, outstr, w) != 0) + while (width-- > len) { + if (cb(state, " ", 1) != 0) return -1; + written += 1; } + if (cb(state, outstr, len) != 0) + return -1; written += len; do_escape: @@ -378,18 +383,25 @@ int __nolibc_printf(__nolibc_printf_cb cb, intptr_t state, size_t n, const char /* literal char, just queue it */ } + + /* Request a final '\0' be added to the snprintf() output. + * This may be the only call of the cb() function. + */ + if (cb(state, NULL, 0) != 0) + return -1; + return written; } -static int __nolibc_fprintf_cb(intptr_t state, const char *buf, size_t size) +static int __nolibc_fprintf_cb(void *stream, const char *buf, size_t size) { - return _fwrite(buf, size, (FILE *)state); + return _fwrite(buf, size, stream); } static __attribute__((unused, format(printf, 2, 0))) int vfprintf(FILE *stream, const char *fmt, va_list args) { - return __nolibc_printf(__nolibc_fprintf_cb, (intptr_t)stream, SIZE_MAX, fmt, args); + return __nolibc_printf(__nolibc_fprintf_cb, stream, fmt, args); } static __attribute__((unused, format(printf, 1, 0))) @@ -447,26 +459,54 @@ int dprintf(int fd, const char *fmt, ...) return ret; } -static int __nolibc_sprintf_cb(intptr_t _state, const char *buf, size_t size) +struct __nolibc_sprintf_cb_state { + char *buf; + size_t space; +}; + +static int __nolibc_sprintf_cb(void *v_state, const char *buf, size_t size) { - char **state = (char **)_state; + struct __nolibc_sprintf_cb_state *state = v_state; + size_t space = state->space; + char *tgt; + + /* Truncate the request to fit in the output buffer space. + * The last byte is reserved for the terminating '\0'. + * state->space can only be zero for snprintf(NULL, 0, fmt, args) + * so this normally lets through calls with 'size == 0'. + */ + if (size >= space) { + if (space <= 1) + return 0; + size = space - 1; + } + tgt = state->buf; + + /* __nolibc_printf() ends with cb(state, NULL, 0) to request the output + * buffer be '\0' terminated. + * That will be the only cb() call for, eg, snprintf(buf, sz, ""). + * Zero lengths can occur at other times (eg "%s" for an empty string). + * Unconditionally write the '\0' byte to reduce code size, it is + * normally overwritten by the data being output. + * There is no point adding a '\0' after copied data - there is always + * another call. + */ + *tgt = '\0'; + if (size) { + state->space = space - size; + state->buf = tgt + size; + memcpy(tgt, buf, size); + } - memcpy(*state, buf, size); - *state += size; return 0; } static __attribute__((unused, format(printf, 3, 0))) int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { - char *state = buf; - int ret; + struct __nolibc_sprintf_cb_state state = { .buf = buf, .space = size }; - ret = __nolibc_printf(__nolibc_sprintf_cb, (intptr_t)&state, size, fmt, args); - if (ret < 0) - return ret; - buf[(size_t)ret < size ? (size_t)ret : size - 1] = '\0'; - return ret; + return __nolibc_printf(__nolibc_sprintf_cb, &state, fmt, args); } static __attribute__((unused, format(printf, 3, 4))) From 096b74331df26c603ef1dbb60880e392b0bad796 Mon Sep 17 00:00:00 2001 From: StanleyYP Wang Date: Mon, 15 Dec 2025 14:37:23 +0800 Subject: [PATCH 0259/1518] wifi: mt76: mt7996: fix the behavior of radar detection [ Upstream commit 45a09251d610f3b8a1fb02039146e42f1f4efe90 ] RDD_DET_MODE is a firmware command intended for testing and does not pause TX after radar detection, so remove it from the normal flow; instead, use the MAC_ENABLE_CTRL firmware command to resume TX after the radar-triggered channel switch completes. Fixes: 1529e335f93d ("wifi: mt76: mt7996: rework radar HWRDD idx") Co-developed-by: Shayne Chen Signed-off-by: Shayne Chen Signed-off-by: StanleyYP Wang Link: https://patch.msgid.link/20251215063728.3013365-2-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7996/mac.c | 8 +-- .../net/wireless/mediatek/mt76/mt7996/main.c | 20 ++++++++ .../net/wireless/mediatek/mt76/mt7996/mcu.c | 49 ++++++++++++++++--- .../net/wireless/mediatek/mt76/mt7996/mcu.h | 1 + .../wireless/mediatek/mt76/mt7996/mt7996.h | 2 + 5 files changed, 68 insertions(+), 12 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 0958961d2758e..24b404f35409b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -2944,7 +2944,7 @@ static void mt7996_dfs_stop_radar_detector(struct mt7996_phy *phy) static int mt7996_dfs_start_rdd(struct mt7996_dev *dev, int rdd_idx) { - int err, region; + int region; switch (dev->mt76.region) { case NL80211_DFS_ETSI: @@ -2959,11 +2959,7 @@ static int mt7996_dfs_start_rdd(struct mt7996_dev *dev, int rdd_idx) break; } - err = mt7996_mcu_rdd_cmd(dev, RDD_START, rdd_idx, region); - if (err < 0) - return err; - - return mt7996_mcu_rdd_cmd(dev, RDD_DET_MODE, rdd_idx, 1); + return mt7996_mcu_rdd_cmd(dev, RDD_START, rdd_idx, region); } static int mt7996_dfs_start_radar_detector(struct mt7996_phy *phy) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 2ad52ae2c5f55..2c8a088a170c6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -79,6 +79,7 @@ static void mt7996_stop_phy(struct mt7996_phy *phy) mutex_lock(&dev->mt76.mutex); + mt7996_mcu_rdd_resume_tx(phy); mt7996_mcu_set_radio_en(phy, false); clear_bit(MT76_STATE_RUNNING, &phy->mt76->state); @@ -933,6 +934,24 @@ mt7996_channel_switch_beacon(struct ieee80211_hw *hw, mutex_unlock(&dev->mt76.mutex); } +static int +mt7996_post_channel_switch(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) +{ + struct cfg80211_chan_def *chandef = &link_conf->chanreq.oper; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt7996_phy *phy = mt7996_band_phy(dev, chandef->chan->band); + int ret; + + mutex_lock(&dev->mt76.mutex); + + ret = mt7996_mcu_rdd_resume_tx(phy); + + mutex_unlock(&dev->mt76.mutex); + + return ret; +} + static int mt7996_mac_sta_init_link(struct mt7996_dev *dev, struct ieee80211_bss_conf *link_conf, @@ -2295,6 +2314,7 @@ const struct ieee80211_ops mt7996_ops = { .release_buffered_frames = mt76_release_buffered_frames, .get_txpower = mt7996_get_txpower, .channel_switch_beacon = mt7996_channel_switch_beacon, + .post_channel_switch = mt7996_post_channel_switch, .get_stats = mt7996_get_stats, .get_et_sset_count = mt7996_get_et_sset_count, .get_et_stats = mt7996_get_et_stats, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 5bde9959bbb99..321098496a39e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -413,24 +413,32 @@ mt7996_mcu_rx_radar_detected(struct mt7996_dev *dev, struct sk_buff *skb) break; case MT_RDD_IDX_BACKGROUND: if (!dev->rdd2_phy) - return; + goto err; mphy = dev->rdd2_phy->mt76; break; default: - dev_err(dev->mt76.dev, "Unknown RDD idx %d\n", r->rdd_idx); - return; + goto err; } if (!mphy) - return; + goto err; - if (r->rdd_idx == MT_RDD_IDX_BACKGROUND) + if (r->rdd_idx == MT_RDD_IDX_BACKGROUND) { cfg80211_background_radar_event(mphy->hw->wiphy, &dev->rdd2_chandef, GFP_ATOMIC); - else + } else { + struct mt7996_phy *phy = mphy->priv; + + phy->rdd_tx_paused = true; ieee80211_radar_detected(mphy->hw, NULL); + } dev->hw_pattern++; + + return; + +err: + dev_err(dev->mt76.dev, "Invalid RDD idx %d\n", r->rdd_idx); } static void @@ -4554,6 +4562,35 @@ int mt7996_mcu_set_radio_en(struct mt7996_phy *phy, bool enable) &req, sizeof(req), true); } +int mt7996_mcu_rdd_resume_tx(struct mt7996_phy *phy) +{ + struct { + u8 band_idx; + u8 _rsv[3]; + + __le16 tag; + __le16 len; + u8 mac_enable; + u8 _rsv2[3]; + } __packed req = { + .band_idx = phy->mt76->band_idx, + .tag = cpu_to_le16(UNI_BAND_CONFIG_MAC_ENABLE_CTRL), + .len = cpu_to_le16(sizeof(req) - 4), + .mac_enable = 2, + }; + int ret; + + if (!phy->rdd_tx_paused) + return 0; + + ret = mt76_mcu_send_msg(&phy->dev->mt76, MCU_WM_UNI_CMD(BAND_CONFIG), + &req, sizeof(req), true); + if (!ret) + phy->rdd_tx_paused = false; + + return ret; +} + int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 rdd_idx, u8 val) { struct { diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h index c841da1c60e5d..abfd7e5a775b3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h @@ -837,6 +837,7 @@ enum { enum { UNI_BAND_CONFIG_RADIO_ENABLE, UNI_BAND_CONFIG_RTS_THRESHOLD = 0x08, + UNI_BAND_CONFIG_MAC_ENABLE_CTRL = 0x0c, }; enum { diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index b942928c79e28..6190fbcd4df7e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -376,6 +376,7 @@ struct mt7996_phy { bool has_aux_rx; bool counter_reset; + bool rdd_tx_paused; }; struct mt7996_dev { @@ -725,6 +726,7 @@ int mt7996_mcu_get_temperature(struct mt7996_phy *phy); int mt7996_mcu_set_thermal_throttling(struct mt7996_phy *phy, u8 state); int mt7996_mcu_set_thermal_protect(struct mt7996_phy *phy, bool enable); int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy); +int mt7996_mcu_rdd_resume_tx(struct mt7996_phy *phy); int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 rdd_idx, u8 val); int mt7996_mcu_rdd_background_enable(struct mt7996_phy *phy, struct cfg80211_chan_def *chandef); From 900579479395f9e8da4bf3fd569e4b259f045214 Mon Sep 17 00:00:00 2001 From: Shayne Chen Date: Mon, 15 Dec 2025 14:37:28 +0800 Subject: [PATCH 0260/1518] wifi: mt76: mt7996: fix iface combination for different chipsets [ Upstream commit 5ef0e8e2653b1ba325eb883ffb94073f19cb669a ] MT7992 and MT7990 support up to 19 interfaces per band and 32 in total. Fixes: 8df63a4bbe3d ("wifi: mt76: mt7996: adjust interface num and wtbl size for mt7992") Signed-off-by: Shayne Chen Link: https://patch.msgid.link/20251215063728.3013365-7-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7996/init.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index b136b9a669769..e26f8e9e4f8fc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -34,6 +34,20 @@ static const struct ieee80211_iface_combination if_comb_global = { BIT(NL80211_CHAN_WIDTH_40) | BIT(NL80211_CHAN_WIDTH_80) | BIT(NL80211_CHAN_WIDTH_160), + .beacon_int_min_gcd = 100, +}; + +static const struct ieee80211_iface_combination if_comb_global_7992 = { + .limits = &if_limits_global, + .n_limits = 1, + .max_interfaces = 32, + .num_different_channels = MT7996_MAX_RADIOS - 1, + .radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) | + BIT(NL80211_CHAN_WIDTH_20) | + BIT(NL80211_CHAN_WIDTH_40) | + BIT(NL80211_CHAN_WIDTH_80) | + BIT(NL80211_CHAN_WIDTH_160), + .beacon_int_min_gcd = 100, }; static const struct ieee80211_iface_limit if_limits[] = { @@ -485,7 +499,8 @@ mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed) hw->vif_data_size = sizeof(struct mt7996_vif); hw->chanctx_data_size = sizeof(struct mt76_chanctx); - wiphy->iface_combinations = &if_comb_global; + wiphy->iface_combinations = is_mt7996(&dev->mt76) ? &if_comb_global : + &if_comb_global_7992; wiphy->n_iface_combinations = 1; wiphy->radio = dev->radios; From 15205c72f1eceee1f31af3f1c7edda8151f097a0 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 5 Dec 2025 11:24:36 +0100 Subject: [PATCH 0261/1518] wifi: mt76: mt7996: Set mtxq->wcid just for primary link [ Upstream commit 654abcbe4528f74428b69292fad5c4224414fa1b ] Set WCID index in mt76_txq struct just for the primary link in mt7996_vif_link_add routine. Fixes: 69d54ce7491d0 ("wifi: mt76: mt7996: switch to single multi-radio wiphy") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251205-mt76-txq-wicd-fix-v2-1-f19ba48af7c1@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/main.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 2c8a088a170c6..44c52062c640b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -301,7 +301,6 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, .cmd = SET_KEY, .link_id = link_conf->link_id, }; - struct mt76_txq *mtxq; int mld_idx, idx, ret; mlink->idx = __ffs64(~dev->mt76.vif_mask); @@ -344,11 +343,6 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, mt7996_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); - if (vif->txq) { - mtxq = (struct mt76_txq *)vif->txq->drv_priv; - mtxq->wcid = idx; - } - if (vif->type != NL80211_IFTYPE_AP && (!mlink->omac_idx || mlink->omac_idx > 3)) vif->offload_flags = 0; @@ -371,9 +365,13 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, &it); - if (!mlink->wcid->offchannel && - mvif->mt76.deflink_id == IEEE80211_LINK_UNSPECIFIED) + if (vif->txq && !mlink->wcid->offchannel && + mvif->mt76.deflink_id == IEEE80211_LINK_UNSPECIFIED) { + struct mt76_txq *mtxq = (struct mt76_txq *)vif->txq->drv_priv; + mvif->mt76.deflink_id = link_conf->link_id; + mtxq->wcid = idx; + } return 0; } From 6d7f231d5fffcea326d74a7471709c95f9d21061 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 5 Dec 2025 11:24:37 +0100 Subject: [PATCH 0262/1518] wifi: mt76: mt7996: Reset mtxq->idx if primary link is removed in mt7996_vif_link_remove() [ Upstream commit 751a2679b15e3a0fa8fc9175862f0ec40643db68 ] Reset WCID index in mt76_txq struct if primary link is removed in mt7996_vif_link_remove routine. Fixes: a3316d2fc669f ("wifi: mt76: mt7996: set vif default link_id adding/removing vif links") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251205-mt76-txq-wicd-fix-v2-2-f19ba48af7c1@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7996/main.c | 21 ++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 44c52062c640b..5d4b1d8f3335b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -402,17 +402,28 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, rcu_assign_pointer(dev->mt76.wcid[idx], NULL); - if (!mlink->wcid->offchannel && + if (vif->txq && !mlink->wcid->offchannel && mvif->mt76.deflink_id == link_conf->link_id) { struct ieee80211_bss_conf *iter; + struct mt76_txq *mtxq; unsigned int link_id; mvif->mt76.deflink_id = IEEE80211_LINK_UNSPECIFIED; + mtxq = (struct mt76_txq *)vif->txq->drv_priv; + /* Primary link will be removed, look for a new one */ for_each_vif_active_link(vif, iter, link_id) { - if (link_id != IEEE80211_LINK_UNSPECIFIED) { - mvif->mt76.deflink_id = link_id; - break; - } + struct mt7996_vif_link *link; + + if (link_id == link_conf->link_id) + continue; + + link = mt7996_vif_link(dev, vif, link_id); + if (!link) + continue; + + mtxq->wcid = link->msta_link.wcid.idx; + mvif->mt76.deflink_id = link_id; + break; } } From 455a48685feebf2d9c1656caad77f9ba1da7b06e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 5 Dec 2025 11:24:39 +0100 Subject: [PATCH 0263/1518] wifi: mt76: mt7996: Clear wcid pointer in mt7996_mac_sta_deinit_link() [ Upstream commit 88973240dc7c976dd320b36a9e6d925c9be083ae ] Clear WCID pointer removing the sta link in mt7996_mac_sta_deinit_link routine. Fixes: dd82a9e02c054 ("wifi: mt76: mt7996: Rely on mt7996_sta_link in sta_add/sta_remove callbacks") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251205-mt76-txq-wicd-fix-v2-4-f19ba48af7c1@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 5d4b1d8f3335b..589b228a4eb0c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -1032,6 +1032,7 @@ void mt7996_mac_sta_deinit_link(struct mt7996_dev *dev, list_del_init(&msta_link->rc_list); spin_unlock_bh(&dev->mt76.sta_poll_lock); + rcu_assign_pointer(dev->mt76.wcid[msta_link->wcid.idx], NULL); mt76_wcid_cleanup(&dev->mt76, &msta_link->wcid); mt76_wcid_mask_clear(dev->mt76.wcid_mask, msta_link->wcid.idx); } From 1e16b0a9b988b7961669f00c1e5254710aae67a2 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 14 Dec 2025 10:55:30 +0100 Subject: [PATCH 0264/1518] wifi: mt76: mt7996: Reset ampdu_state state in case of failure in mt7996_tx_check_aggr() [ Upstream commit c0747db7c10c2dfbdcff0e8e97021e3df1f1e362 ] Reset the ampdu_state configured state if ieee80211_start_tx_ba_session routine fails in mt7996_tx_check_aggr() Fixes: 98686cd21624c ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251214-mt7996-aggr-check-fix-v1-1-33a8b62ec0fc@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 24b404f35409b..15d796702a589 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1243,8 +1243,9 @@ mt7996_tx_check_aggr(struct ieee80211_link_sta *link_sta, if (unlikely(fc != (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA))) return; - if (!test_and_set_bit(tid, &wcid->ampdu_state)) - ieee80211_start_tx_ba_session(link_sta->sta, tid, 0); + if (!test_and_set_bit(tid, &wcid->ampdu_state) && + ieee80211_start_tx_ba_session(link_sta->sta, tid, 0)) + clear_bit(tid, &wcid->ampdu_state); } static void From 3880639cec09a8a59b4c19d47670b07c29069930 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 15 Dec 2025 18:59:30 -0600 Subject: [PATCH 0265/1518] wifi: mt76: mt7921: Reset ampdu_state state in case of failure in mt76_connac2_tx_check_aggr() [ Upstream commit 53ffffeb9624ffab6d9a3b1da8635a23f1172b5e ] Reset ampdu_state if ieee80211_start_tx_ba_session() fails in mt76_connac2_tx_check_aggr(), otherwise the driver may incorrectly assume aggregation is active and skip future BA setup attempts. Fixes: 163f4d22c118 ("mt76: mt7921: add MAC support") Signed-off-by: Sean Wang Link: https://patch.msgid.link/20251216005930.9412-1-sean.wang@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 837bd0f136fa1..b78cfa1324f3f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -1150,8 +1150,10 @@ void mt76_connac2_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi) return; wcid = (struct mt76_wcid *)sta->drv_priv; - if (!test_and_set_bit(tid, &wcid->ampdu_state)) - ieee80211_start_tx_ba_session(sta, tid, 0); + if (!test_and_set_bit(tid, &wcid->ampdu_state)) { + if (ieee80211_start_tx_ba_session(sta, tid, 0)) + clear_bit(tid, &wcid->ampdu_state); + } } EXPORT_SYMBOL_GPL(mt76_connac2_tx_check_aggr); From 9aa3b49e1c5bf2d7aad941a931afe0b26f9a5e6a Mon Sep 17 00:00:00 2001 From: Leon Yen Date: Thu, 11 Dec 2025 20:38:36 +0800 Subject: [PATCH 0266/1518] wifi: mt76: mt7925: Fix incorrect MLO mode in firmware control [ Upstream commit 1695f662329faa07c860c73453c097823852df28 ] The selection of MLO mode should depend on the capabilities of the STA rather than those of the peer AP to avoid compatibility issues with certain APs, such as Xiaomi BE5000 WiFi7 router. Fixes: 69acd6d910b0c ("wifi: mt76: mt7925: add mt7925_change_vif_links") Signed-off-by: Leon Yen Link: https://patch.msgid.link/20251211123836.4169436-1-leon.yen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7925/main.c | 2 +- drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 9 ++++++--- drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h | 4 ++-- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index ac3d485a2f78f..d1f63c81ceb99 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -533,7 +533,7 @@ static int mt7925_set_mlo_roc(struct mt792x_phy *phy, phy->roc_grant = false; - err = mt7925_mcu_set_mlo_roc(mconf, sel_links, 5, ++phy->roc_token_id); + err = mt7925_mcu_set_mlo_roc(phy, mconf, sel_links, 5, ++phy->roc_token_id); if (err < 0) { clear_bit(MT76_STATE_ROC, &phy->mt76->state); goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index e44c9ba168878..130f1742546bc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -1243,8 +1243,8 @@ int mt7925_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, return mt76_mcu_skb_send_msg(dev, skb, mcu_cmd, true); } -int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, - int duration, u8 token_id) +int mt7925_mcu_set_mlo_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, + u16 sel_links, int duration, u8 token_id) { struct mt792x_vif *mvif = mconf->vif; struct ieee80211_vif *vif = container_of((void *)mvif, @@ -1279,6 +1279,8 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, .roc[1].len = cpu_to_le16(sizeof(struct roc_acquire_tlv)) }; + struct wiphy *wiphy = phy->mt76->hw->wiphy; + if (!mconf || hweight16(vif->valid_links) < 2 || hweight16(sel_links) != 2) return -EPERM; @@ -1301,7 +1303,8 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, is_AG_band |= links[i].chan->band == NL80211_BAND_2GHZ; } - if (vif->cfg.eml_cap & IEEE80211_EML_CAP_EMLSR_SUPP) + if (!(wiphy->iftype_ext_capab[0].mld_capa_and_ops & + IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS)) type = is_AG_band ? MT7925_ROC_REQ_MLSR_AG : MT7925_ROC_REQ_MLSR_AA; else diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h index 1b165d0d8bd39..1c5ab3ea247d8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h @@ -345,8 +345,8 @@ int mt7925_set_tx_sar_pwr(struct ieee80211_hw *hw, int mt7925_mcu_regval(struct mt792x_dev *dev, u32 regidx, u32 *val, bool set); int mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2, enum environment_cap env_cap); -int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links, - int duration, u8 token_id); +int mt7925_mcu_set_mlo_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, + u16 sel_links, int duration, u8 token_id); int mt7925_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf, struct ieee80211_channel *chan, int duration, enum mt7925_roc_req type, u8 token_id); From 729b4adad19187c7699622217ebaa174ab7278fa Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Wed, 21 Jan 2026 09:41:56 -0800 Subject: [PATCH 0267/1518] wifi: mt76: mt7615: fix use_cts_prot support [ Upstream commit 1974a67d9b65c29a0a9426e32e8cd8c056de48b7 ] Driver should not directly write WTBL to prevent overwritten issues. With this fix, when driver needs to adjust its behavior for compatibility, especially concerning older 11g/n devices, by enabling or disabling CTS protection frames, often for hidden SSIDs or to manage legacy clients. Fixes: e34235ccc5e3 ("wifi: mt76: mt7615: enable use_cts_prot support") Signed-off-by: Ryder Lee Link: https://patch.msgid.link/edb87088b0111b32fafc6c4179f54a5286dd37d8.1768879119.git.ryder.lee@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7615/mac.c | 15 ------ .../net/wireless/mediatek/mt76/mt7615/main.c | 7 +-- .../net/wireless/mediatek/mt76/mt7615/mcu.c | 47 +++++++++++++++++++ .../wireless/mediatek/mt76/mt7615/mt7615.h | 5 +- .../net/wireless/mediatek/mt76/mt7615/regs.h | 2 - 5 files changed, 53 insertions(+), 23 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index f8d2cc94b742c..13c9dbeaee84e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -1167,21 +1167,6 @@ void mt7615_mac_set_rates(struct mt7615_phy *phy, struct mt7615_sta *sta, } EXPORT_SYMBOL_GPL(mt7615_mac_set_rates); -void mt7615_mac_enable_rtscts(struct mt7615_dev *dev, - struct ieee80211_vif *vif, bool enable) -{ - struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; - u32 addr; - - addr = mt7615_mac_wtbl_addr(dev, mvif->sta.wcid.idx) + 3 * 4; - - if (enable) - mt76_set(dev, addr, MT_WTBL_W3_RTS); - else - mt76_clear(dev, addr, MT_WTBL_W3_RTS); -} -EXPORT_SYMBOL_GPL(mt7615_mac_enable_rtscts); - static int mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, struct ieee80211_key_conf *key, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 15fe155ac3f3b..87a2e5163699c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -583,9 +583,6 @@ static void mt7615_bss_info_changed(struct ieee80211_hw *hw, } } - if (changed & BSS_CHANGED_ERP_CTS_PROT) - mt7615_mac_enable_rtscts(dev, vif, info->use_cts_prot); - if (changed & BSS_CHANGED_BEACON_ENABLED && info->enable_beacon) { mt7615_mcu_add_bss_info(phy, vif, NULL, true); mt7615_mcu_sta_add(phy, vif, NULL, true); @@ -598,6 +595,10 @@ static void mt7615_bss_info_changed(struct ieee80211_hw *hw, BSS_CHANGED_BEACON_ENABLED)) mt7615_mcu_add_beacon(dev, hw, vif, info->enable_beacon); + if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT) + mt7615_mcu_set_protection(phy, vif, info->ht_operation_mode, + info->use_cts_prot); + if (changed & BSS_CHANGED_PS) mt76_connac_mcu_set_vif_ps(&dev->mt76, vif); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index 08ee2e861c4e2..91c9d787d553c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -2564,3 +2564,50 @@ int mt7615_mcu_set_roc(struct mt7615_phy *phy, struct ieee80211_vif *vif, return mt76_mcu_send_msg(&dev->mt76, MCU_CE_CMD(SET_ROC), &req, sizeof(req), false); } + +int mt7615_mcu_set_protection(struct mt7615_phy *phy, struct ieee80211_vif *vif, + u8 ht_mode, bool use_cts_prot) +{ + struct mt7615_dev *dev = phy->dev; + struct { + u8 prot_idx; + u8 band; + u8 rsv[2]; + + bool long_nav; + bool prot_mm; + bool prot_gf; + bool prot_bw40; + bool prot_rifs; + bool prot_bw80; + bool prot_bw160; + u8 prot_erp_mask; + } __packed req = { + .prot_idx = 0x2, + .band = phy != &dev->phy, + }; + + switch (ht_mode & IEEE80211_HT_OP_MODE_PROTECTION) { + case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: + case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: + req.prot_mm = true; + req.prot_gf = true; + fallthrough; + case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: + req.prot_bw40 = true; + break; + } + + if (ht_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) + req.prot_gf = true; + + if (use_cts_prot) { + struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; + u8 i = mvif->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : mvif->mt76.omac_idx; + + req.prot_erp_mask = BIT(i); + } + + return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(PROTECT_CTRL), &req, + sizeof(req), true); +} diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index 9bdd29e8d25e9..c655f64772de2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -466,8 +466,6 @@ void mt7615_mac_reset_counters(struct mt7615_phy *phy); void mt7615_mac_cca_stats_reset(struct mt7615_phy *phy); void mt7615_mac_set_scs(struct mt7615_phy *phy, bool enable); void mt7615_mac_enable_nf(struct mt7615_dev *dev, bool ext_phy); -void mt7615_mac_enable_rtscts(struct mt7615_dev *dev, - struct ieee80211_vif *vif, bool enable); void mt7615_mac_sta_poll(struct mt7615_dev *dev); int mt7615_mac_write_txwi(struct mt7615_dev *dev, __le32 *txwi, struct sk_buff *skb, struct mt76_wcid *wcid, @@ -522,7 +520,8 @@ int mt7615_mcu_set_sku_en(struct mt7615_phy *phy, bool enable); int mt7615_mcu_apply_rx_dcoc(struct mt7615_phy *phy); int mt7615_mcu_apply_tx_dpd(struct mt7615_phy *phy); int mt7615_dfs_init_radar_detector(struct mt7615_phy *phy); - +int mt7615_mcu_set_protection(struct mt7615_phy *phy, struct ieee80211_vif *vif, + u8 ht_mode, bool use_cts_prot); int mt7615_mcu_set_roc(struct mt7615_phy *phy, struct ieee80211_vif *vif, struct ieee80211_channel *chan, int duration); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h index 806b3887c541c..9e6d55c91b269 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h @@ -455,8 +455,6 @@ enum mt7615_reg_base { #define MT_WTBL_RIUCR3_RATE6 GENMASK(19, 8) #define MT_WTBL_RIUCR3_RATE7 GENMASK(31, 20) -#define MT_WTBL_W3_RTS BIT(22) - #define MT_WTBL_W5_CHANGE_BW_RATE GENMASK(7, 5) #define MT_WTBL_W5_SHORT_GI_20 BIT(8) #define MT_WTBL_W5_SHORT_GI_40 BIT(9) From b81a93dc0aedbaf63aacde8cfeb4a8967c6ad99c Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Wed, 21 Jan 2026 09:41:57 -0800 Subject: [PATCH 0268/1518] wifi: mt76: mt7915: fix use_cts_prot support [ Upstream commit 8b2c26562b95c6397e132d21f2bd3d73aaee0c0a ] With this fix, when driver needs to adjust its behavior for compatibility, especially concerning older 11g/n devices, by enabling or disabling CTS protection frames, often for hidden SSIDs or to manage legacy clients. Fixes: 150b91419d3d ("wifi: mt76: mt7915: enable use_cts_prot support") Signed-off-by: Ryder Lee Link: https://patch.msgid.link/eb8db4d0bf1c89b7486e89facb788ae3e510dd8b.1768879119.git.ryder.lee@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7915/mac.c | 13 ---- .../net/wireless/mediatek/mt76/mt7915/main.c | 7 ++- .../net/wireless/mediatek/mt76/mt7915/mcu.c | 62 +++++++++++++++++++ .../net/wireless/mediatek/mt76/mt7915/mcu.h | 11 ++++ .../wireless/mediatek/mt76/mt7915/mt7915.h | 4 ++ 5 files changed, 81 insertions(+), 16 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 5caf818e82834..9364e8673eb9d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -232,19 +232,6 @@ static void mt7915_mac_sta_poll(struct mt7915_dev *dev) rcu_read_unlock(); } -void mt7915_mac_enable_rtscts(struct mt7915_dev *dev, - struct ieee80211_vif *vif, bool enable) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - u32 addr; - - addr = mt7915_mac_wtbl_lmac_addr(dev, mvif->sta.wcid.idx, 5); - if (enable) - mt76_set(dev, addr, BIT(5)); - else - mt76_clear(dev, addr, BIT(5)); -} - static void mt7915_wed_check_ppe(struct mt7915_dev *dev, struct mt76_queue *q, struct mt7915_sta *msta, struct sk_buff *skb, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index fe0639c14bf9b..6f594677474b0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -68,7 +68,7 @@ int mt7915_run(struct ieee80211_hw *hw) if (ret) goto out; - ret = mt76_connac_mcu_set_rts_thresh(&dev->mt76, 0x92b, + ret = mt76_connac_mcu_set_rts_thresh(&dev->mt76, MT7915_RTS_LEN_THRES, phy->mt76->band_idx); if (ret) goto out; @@ -633,8 +633,9 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw, if (set_sta == 1) mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_PORT_SECURE, false); - if (changed & BSS_CHANGED_ERP_CTS_PROT) - mt7915_mac_enable_rtscts(dev, vif, info->use_cts_prot); + if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT) + mt7915_mcu_set_protection(phy, vif, info->ht_operation_mode, + info->use_cts_prot); if (changed & BSS_CHANGED_ERP_SLOT) { int slottime = 9; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index c1fdd3c4f1ba6..79e021ac0bdbc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -3852,6 +3852,68 @@ int mt7915_mcu_get_rx_rate(struct mt7915_phy *phy, struct ieee80211_vif *vif, return ret; } +int mt7915_mcu_set_protection(struct mt7915_phy *phy, struct ieee80211_vif *vif, + u8 ht_mode, bool use_cts_prot) +{ + struct mt7915_dev *dev = phy->dev; + int len = sizeof(struct sta_req_hdr) + sizeof(struct bss_info_prot); + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct bss_info_prot *prot; + struct sk_buff *skb; + struct tlv *tlv; + enum { + PROT_NONMEMBER = BIT(1), + PROT_20MHZ = BIT(2), + PROT_NONHT_MIXED = BIT(3), + PROT_LEGACY_ERP = BIT(5), + PROT_NONGF_STA = BIT(7), + }; + u32 rts_threshold; + + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + NULL, len); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_PROTECT_INFO, + sizeof(*prot)); + prot = (struct bss_info_prot *)tlv; + + switch (ht_mode & IEEE80211_HT_OP_MODE_PROTECTION) { + case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: + prot->prot_mode = cpu_to_le32(PROT_NONMEMBER); + break; + case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: + prot->prot_mode = cpu_to_le32(PROT_20MHZ); + break; + case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: + prot->prot_mode = cpu_to_le32(PROT_NONHT_MIXED); + break; + } + + if (ht_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) + prot->prot_mode |= cpu_to_le32(PROT_NONGF_STA); + + if (use_cts_prot) + prot->prot_mode |= cpu_to_le32(PROT_LEGACY_ERP); + + /* reuse current RTS setting */ + rts_threshold = phy->mt76->hw->wiphy->rts_threshold; + if (rts_threshold == (u32)-1) + prot->rts_len_thres = cpu_to_le32(MT7915_RTS_LEN_THRES); + else + prot->rts_len_thres = cpu_to_le32(rts_threshold); + + prot->rts_pkt_thres = 0x2; + + prot->he_rts_thres = cpu_to_le16(vif->bss_conf.frame_time_rts_th); + if (!prot->he_rts_thres) + prot->he_rts_thres = cpu_to_le16(DEFAULT_HE_DURATION_RTS_THRES); + + return mt76_mcu_skb_send_msg(&dev->mt76, skb, + MCU_EXT_CMD(BSS_INFO_UPDATE), true); +} + int mt7915_mcu_update_bss_color(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct cfg80211_he_bss_color *he_bss_color) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h index 086ad89ecd914..4049ed864003d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h @@ -399,6 +399,17 @@ struct bss_info_inband_discovery { __le16 prob_rsp_len; } __packed __aligned(4); +struct bss_info_prot { + __le16 tag; + __le16 len; + __le32 prot_type; + __le32 prot_mode; + __le32 rts_len_thres; + __le16 he_rts_thres; + u8 rts_pkt_thres; + u8 rsv[5]; +} __packed; + enum { BSS_INFO_BCN_CSA, BSS_INFO_BCN_BCC, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h index 2e94347c46d62..f1194d147dc89 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h @@ -83,6 +83,8 @@ #define MT7915_CRIT_TEMP 110 #define MT7915_MAX_TEMP 120 +#define MT7915_RTS_LEN_THRES 0x92b + struct mt7915_vif; struct mt7915_sta; struct mt7915_dfs_pulse; @@ -469,6 +471,8 @@ int mt7915_mcu_add_inband_discov(struct mt7915_dev *dev, struct ieee80211_vif *v u32 changed); int mt7915_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int enable, u32 changed); +int mt7915_mcu_set_protection(struct mt7915_phy *phy, struct ieee80211_vif *vif, + u8 ht_mode, bool use_cts_prot); int mt7915_mcu_add_obss_spr(struct mt7915_phy *phy, struct ieee80211_vif *vif, struct ieee80211_he_obss_pd *he_obss_pd); int mt7915_mcu_add_rate_ctrl(struct mt7915_dev *dev, struct ieee80211_vif *vif, From 93d0694fb56de4628a921244d7f100c28acd2def Mon Sep 17 00:00:00 2001 From: Ming Yen Hsieh Date: Thu, 4 Sep 2025 11:06:48 +0800 Subject: [PATCH 0269/1518] wifi: mt76: mt7925: prevent NULL pointer dereference in mt7925_tx_check_aggr() [ Upstream commit 83ae3a18ba957257b4c406273d2da2caeea2b439 ] Move the NULL check for 'sta' before dereferencing it to prevent a possible crash. Fixes: 44eb173bdd4f ("wifi: mt76: mt7925: add link handling in mt7925_txwi_free") Signed-off-by: Ming Yen Hsieh Link: https://patch.msgid.link/20250904030649.655436-4-mingyen.hsieh@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index a048ab1feef05..f12b8db739653 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -845,11 +845,14 @@ static void mt7925_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb, bool is_8023; u16 fc, tid; + if (!sta) + return; + link_sta = rcu_dereference(sta->link[wcid->link_id]); if (!link_sta) return; - if (!sta || !(link_sta->ht_cap.ht_supported || link_sta->he_cap.has_he)) + if (!(link_sta->ht_cap.ht_supported || link_sta->he_cap.has_he)) return; tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; From 815db7fd57aa81c93fc8a66c2fac5f8bd0a8d153 Mon Sep 17 00:00:00 2001 From: Ming Yen Hsieh Date: Thu, 4 Sep 2025 11:06:47 +0800 Subject: [PATCH 0270/1518] wifi: mt76: mt7925: prevent NULL vif dereference in mt7925_mac_write_txwi [ Upstream commit 962eb04e67552be406c906c83099c1d736aae3b6 ] Check for a NULL `vif` before accessing `ieee80211_vif_is_mld(vif)` to avoid a potential kernel panic in scenarios where `vif` might not be initialized. Fixes: ebb1406813c6 ("wifi: mt76: mt7925: add link handling to txwi") Signed-off-by: Ming Yen Hsieh Link: https://patch.msgid.link/20250904030649.655436-3-mingyen.hsieh@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index f12b8db739653..0608f0c1fd2c2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -803,8 +803,8 @@ mt7925_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, txwi[5] = cpu_to_le32(val); val = MT_TXD6_DAS | FIELD_PREP(MT_TXD6_MSDU_CNT, 1); - if (!ieee80211_vif_is_mld(vif) || - (q_idx >= MT_LMAC_ALTX0 && q_idx <= MT_LMAC_BCN0)) + if (vif && (!ieee80211_vif_is_mld(vif) || + (q_idx >= MT_LMAC_ALTX0 && q_idx <= MT_LMAC_BCN0))) val |= MT_TXD6_DIS_MAT; txwi[6] = cpu_to_le32(val); txwi[7] = 0; From e00c27608536845d418de8f8991cefd578e35462 Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Mon, 13 Oct 2025 02:08:24 -0700 Subject: [PATCH 0271/1518] wifi: mt76: mt7996: fix FCS error flag check in RX descriptor [ Upstream commit d8db56142e531f060c938fa0b5175ed6c8cabb11 ] The mt7996 driver currently checks the MT_RXD3_NORMAL_FCS_ERR bit in rxd1 whereas other Connac3-based drivers(mt7925) correctly check this bit in rxd3. Since the MT_RXD3_NORMAL_FCS_ERR bit is defined in the fourth RX descriptor word (rxd3), update mt7996 to use the proper descriptor field. This change aligns mt7996 with mt7925 and the rest of the Connac3 family. Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices") Signed-off-by: Alok Tiwari Reviewed-by: AngeloGioacchino Del Regno Link: https://patch.msgid.link/20251013090826.753992-1-alok.a.tiwari@oracle.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 15d796702a589..2aa8bb779b228 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -527,7 +527,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q, !(csum_status & (BIT(0) | BIT(2) | BIT(3)))) skb->ip_summed = CHECKSUM_UNNECESSARY; - if (rxd1 & MT_RXD3_NORMAL_FCS_ERR) + if (rxd3 & MT_RXD3_NORMAL_FCS_ERR) status->flag |= RX_FLAG_FAILED_FCS_CRC; if (rxd1 & MT_RXD1_NORMAL_TKIP_MIC_ERR) From 35835ff71e6e618155578b8e3905597edd5f601c Mon Sep 17 00:00:00 2001 From: Rory Little Date: Wed, 3 Sep 2025 17:07:11 -0700 Subject: [PATCH 0272/1518] wifi: mt76: mt7921: Place upper limit on station AID [ Upstream commit 4d0bf21e3e20619d51d06c0c36207aabab8b712c ] Any station configured with an AID over 20 causes a firmware crash. This situation occurred in our testing using an AP interface on 7922 hardware, with a modified hostapd, sourced from Mediatek's OpenWRT feeds. In stock hostapd, station AIDs begin counting at 1, and this configuration is prevented with an upper limit on associated stations. However, the modified hostapd began allocation at 65, which caused the firmware to crash. This fix does not allow these AIDs to work, but will prevent the firmware crash. This crash was only seen on IFTYPE_AP interfaces, and the fix does not appear to have an effect on IFTYPE_STATION behavior. Fixes: 5c14a5f944b9 ("mt76: mt7921: introduce mt7921e support") Signed-off-by: Rory Little Link: https://patch.msgid.link/20250904000711.3033860-1-rory@candelatech.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 6 ++++++ drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h | 2 ++ 2 files changed, 8 insertions(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 5e676916593d3..ea6ff4c6bc90b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -808,6 +808,9 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; int ret, idx; + if (sta->aid > MT7921_MAX_AID) + return -ENOENT; + idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT792x_WTBL_STA - 1); if (idx < 0) return -ENOSPC; @@ -851,6 +854,9 @@ int mt7921_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + if (sta->aid > MT7921_MAX_AID) + return -ENOENT; + if (ev != MT76_STA_EVENT_ASSOC) return 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h index c88793fcec643..faa0d93982144 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h @@ -7,6 +7,8 @@ #include "../mt792x.h" #include "regs.h" +#define MT7921_MAX_AID 20 + #define MT7921_TX_RING_SIZE 2048 #define MT7921_TX_MCU_RING_SIZE 256 #define MT7921_TX_FWDL_RING_SIZE 128 From dcbc13d19bef3326c72f324b10f5a3e5fc4d71de Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 8 Dec 2025 19:54:08 +0100 Subject: [PATCH 0273/1518] wifi: mt76: Fix memory leak destroying device [ Upstream commit 6b470f36616e3448d44b0ef4b1de2a3e3a31b5be ] All MT76 rx queues have an associated page_pool even if the queue is not associated to a NAPI (e.g. WED RRO queues with WED enabled). Destroy the page_pool running mt76_dma_cleanup routine during module unload. Moreover returns pages to the page pool if WED is not enabled for WED RRO queues. Fixes: 950d0abb5cd94 ("wifi: mt76: mt7996: add wed rx support") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251208-mt76-fix-memory-leak-v1-1-cba813fc62b8@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/dma.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 1fa7de1d2c45e..9ef073c27f309 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -878,7 +878,12 @@ mt76_dma_rx_cleanup(struct mt76_dev *dev, struct mt76_queue *q) if (!buf) break; - if (!mt76_queue_is_wed_rro(q)) + if (mtk_wed_device_active(&dev->mmio.wed) && + mt76_queue_is_wed_rro(q)) + continue; + + if (!mt76_queue_is_wed_rro_rxdmad_c(q) && + !mt76_queue_is_wed_rro_ind(q)) mt76_put_page_pool_buf(buf, false); } while (1); @@ -1169,10 +1174,6 @@ void mt76_dma_cleanup(struct mt76_dev *dev) mt76_for_each_q_rx(dev, i) { struct mt76_queue *q = &dev->q_rx[i]; - if (mtk_wed_device_active(&dev->mmio.wed) && - mt76_queue_is_wed_rro(q)) - continue; - netif_napi_del(&dev->napi[i]); mt76_dma_rx_cleanup(dev, q); From a1a59bd3cd1e0a21ef3bea10742922066d3c7677 Mon Sep 17 00:00:00 2001 From: Jack Kao Date: Wed, 1 Oct 2025 09:25:06 +0800 Subject: [PATCH 0274/1518] wifi: mt76: mt7925: cqm rssi low/high event notify [ Upstream commit 2a035ae2062f38dc5183002d1c5a64ca682170c1 ] The implementation amounts to setting the driver flag IEEE80211_VIF_SUPPORTS_CQM_RSSI, and then providing mechanisms for continuously updating enough information to be able to provide notifications to userspace when RSSI drops below a certain threshold Signed-off-by: Jack Kao Signed-off-by: Ming Yen Hsieh Link: https://patch.msgid.link/20251001012506.2168037-1-mingyen.hsieh@mediatek.com Signed-off-by: Felix Fietkau Stable-dep-of: 59a1864509d0 ("wifi: mt76: mt7925: drop puncturing handling from BSS change path") Signed-off-by: Sasha Levin --- .../wireless/mediatek/mt76/mt76_connac_mcu.h | 2 + .../net/wireless/mediatek/mt76/mt7925/main.c | 6 ++ .../net/wireless/mediatek/mt76/mt7925/mcu.c | 82 +++++++++++++++++++ .../net/wireless/mediatek/mt76/mt7925/mcu.h | 8 ++ .../wireless/mediatek/mt76/mt7925/mt7925.h | 7 ++ 5 files changed, 105 insertions(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h index 27daf419560a5..0b02f34c40a40 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h @@ -1062,6 +1062,7 @@ enum { MCU_UNI_EVENT_ROC = 0x27, MCU_UNI_EVENT_TX_DONE = 0x2d, MCU_UNI_EVENT_THERMAL = 0x35, + MCU_UNI_EVENT_RSSI_MONITOR = 0x41, MCU_UNI_EVENT_NIC_CAPAB = 0x43, MCU_UNI_EVENT_WED_RRO = 0x57, MCU_UNI_EVENT_PER_STA_INFO = 0x6d, @@ -1300,6 +1301,7 @@ enum { MCU_UNI_CMD_THERMAL = 0x35, MCU_UNI_CMD_VOW = 0x37, MCU_UNI_CMD_FIXED_RATE_TABLE = 0x40, + MCU_UNI_CMD_RSSI_MONITOR = 0x41, MCU_UNI_CMD_TESTMODE_CTRL = 0x46, MCU_UNI_CMD_RRO = 0x57, MCU_UNI_CMD_OFFCH_SCAN_CTRL = 0x58, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index d1f63c81ceb99..f503e861a7e63 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -430,6 +430,9 @@ mt7925_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) goto out; vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER; + if (phy->chip_cap & MT792x_CHIP_CAP_RSSI_NOTIFY_EVT_EN) + vif->driver_flags |= IEEE80211_VIF_SUPPORTS_CQM_RSSI; + out: mt792x_mutex_release(dev); @@ -1958,6 +1961,9 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw, mt7925_mcu_set_eht_pp(mvif->phy->mt76, &mconf->mt76, link_conf, NULL); + if (changed & BSS_CHANGED_CQM) + mt7925_mcu_set_rssimonitor(dev, vif); + mt792x_mutex_release(dev); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index 130f1742546bc..d887aa9a3dff7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -450,6 +450,56 @@ mt7925_mcu_tx_done_event(struct mt792x_dev *dev, struct sk_buff *skb) } } +static void +mt7925_mcu_rssi_monitor_iter(void *priv, u8 *mac, + struct ieee80211_vif *vif) +{ + struct mt7925_uni_rssi_monitor_event *event = priv; + enum nl80211_cqm_rssi_threshold_event nl_event; + s32 rssi = le32_to_cpu(event->rssi); + + if (vif->type != NL80211_IFTYPE_STATION) + return; + + if (!(vif->driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + return; + + if (rssi > vif->bss_conf.cqm_rssi_thold) + nl_event = NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH; + else + nl_event = NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW; + + ieee80211_cqm_rssi_notify(vif, nl_event, rssi, GFP_KERNEL); +} + +static void +mt7925_mcu_rssi_monitor_event(struct mt792x_dev *dev, struct sk_buff *skb) +{ + struct tlv *tlv; + u32 tlv_len; + struct mt7925_uni_rssi_monitor_event *event; + + skb_pull(skb, sizeof(struct mt7925_mcu_rxd) + 4); + tlv = (struct tlv *)skb->data; + tlv_len = skb->len; + + while (tlv_len > 0 && le16_to_cpu(tlv->len) <= tlv_len) { + switch (le16_to_cpu(tlv->tag)) { + case UNI_EVENT_RSSI_MONITOR_INFO: + event = (struct mt7925_uni_rssi_monitor_event *)skb->data; + ieee80211_iterate_active_interfaces_atomic(dev->mt76.hw, + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7925_mcu_rssi_monitor_iter, + event); + break; + default: + break; + } + tlv_len -= le16_to_cpu(tlv->len); + tlv = (struct tlv *)((char *)(tlv) + le16_to_cpu(tlv->len)); + } +} + static void mt7925_mcu_uni_debug_msg_event(struct mt792x_dev *dev, struct sk_buff *skb) { @@ -546,6 +596,9 @@ mt7925_mcu_uni_rx_unsolicited_event(struct mt792x_dev *dev, case MCU_UNI_EVENT_BSS_BEACON_LOSS: mt7925_mcu_connection_loss_event(dev, skb); break; + case MCU_UNI_EVENT_RSSI_MONITOR: + mt7925_mcu_rssi_monitor_event(dev, skb); + break; case MCU_UNI_EVENT_COREDUMP: dev->fw_assert = true; mt76_connac_mcu_coredump_event(&dev->mt76, skb, &dev->coredump); @@ -3821,3 +3874,32 @@ int mt7925_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif, return mt76_mcu_send_msg(&phy->dev->mt76, MCU_UNI_CMD(BAND_CONFIG), &req, sizeof(req), true); } + +int mt7925_mcu_set_rssimonitor(struct mt792x_dev *dev, struct ieee80211_vif *vif) +{ + struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(&vif->bss_conf); + struct { + struct { + u8 bss_idx; + u8 pad[3]; + } __packed hdr; + __le16 tag; + __le16 len; + u8 enable; + s8 cqm_rssi_high; + s8 cqm_rssi_low; + u8 rsv; + } req = { + .hdr = { + .bss_idx = mconf->mt76.idx, + }, + .tag = cpu_to_le16(UNI_CMD_RSSI_MONITOR_SET), + .len = cpu_to_le16(sizeof(req) - 4), + .enable = vif->cfg.assoc, + .cqm_rssi_high = (s8)(vif->bss_conf.cqm_rssi_thold + vif->bss_conf.cqm_rssi_hyst), + .cqm_rssi_low = (s8)(vif->bss_conf.cqm_rssi_thold - vif->bss_conf.cqm_rssi_hyst), + }; + + return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(RSSI_MONITOR), &req, + sizeof(req), false); +} diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h index a40764d89a1ff..148aa3c05c8c4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h @@ -152,6 +152,14 @@ enum { UNI_EVENT_SCAN_DONE_NLO = 3, }; +enum { + UNI_CMD_RSSI_MONITOR_SET = 0, +}; + +enum { + UNI_EVENT_RSSI_MONITOR_INFO = 0, +}; + enum connac3_mcu_cipher_type { CONNAC3_CIPHER_NONE = 0, CONNAC3_CIPHER_WEP40 = 1, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h index 1c5ab3ea247d8..7f67e0a978726 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h @@ -103,6 +103,12 @@ struct mt7925_uni_beacon_loss_event { struct mt7925_beacon_loss_tlv beacon_loss; } __packed; +struct mt7925_uni_rssi_monitor_event { + __le16 tag; + __le16 len; + __le32 rssi; +} __packed; + #define to_rssi(field, rxv) ((FIELD_GET(field, rxv) - 220) / 2) #define to_rcpi(rssi) (2 * (rssi) + 220) @@ -372,4 +378,5 @@ int mt7925_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int mt7925_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg, struct netlink_callback *cb, void *data, int len); +int mt7925_mcu_set_rssimonitor(struct mt792x_dev *dev, struct ieee80211_vif *vif); #endif From e125def8b380e43952fee720920f5fcf9e6880b0 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 15 Dec 2025 20:20:17 -0600 Subject: [PATCH 0275/1518] wifi: mt76: mt7925: drop puncturing handling from BSS change path [ Upstream commit 59a1864509d084a4b34117e693951c06b846b00a ] IEEE80211_CHANCTX_CHANGE_PUNCTURING is a channel context change flag and should not be checked in the BSS change handler, where the changed mask represents enum ieee80211_bss_change. Remove the puncturing handling from the BSS path and rely on mt7925_change_chanctx() to update puncturing configuration. Fixes: cadebdad959b ("wifi: mt76: mt7925: add EHT preamble puncturing") Signed-off-by: Sean Wang Link: https://patch.msgid.link/20251216022017.23870-1-sean.wang@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7925/main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index f503e861a7e63..ebb746f4072de 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1912,10 +1912,8 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw, struct mt792x_phy *phy = mt792x_hw_phy(hw); struct mt792x_dev *dev = mt792x_hw_dev(hw); struct mt792x_bss_conf *mconf; - struct ieee80211_bss_conf *link_conf; mconf = mt792x_vif_to_link(mvif, info->link_id); - link_conf = mt792x_vif_to_bss_conf(vif, mconf->link_id); mt792x_mutex_acquire(dev); @@ -1957,10 +1955,6 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw, mvif->mlo_pm_state = MT792x_MLO_CHANGED_PS; } - if (changed & IEEE80211_CHANCTX_CHANGE_PUNCTURING) - mt7925_mcu_set_eht_pp(mvif->phy->mt76, &mconf->mt76, - link_conf, NULL); - if (changed & BSS_CHANGED_CQM) mt7925_mcu_set_rssimonitor(dev, vif); From 153bcba36c87a1ba555b57b6c49028d5812f895b Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 15 Dec 2025 19:38:49 -0600 Subject: [PATCH 0276/1518] wifi: mt76: mt7925: fix potential deadlock in mt7925_roc_abort_sync [ Upstream commit dd08ca3f092f4185ece69ce2a835c23198b1628a ] roc_abort_sync() can deadlock with roc_work(). roc_work() holds dev->mt76.mutex, while cancel_work_sync() waits for roc_work() to finish. If the caller already owns the same mutex, both sides block and no progress is possible. This deadlock can occur during station removal when mt76_sta_state() -> mt76_sta_remove() -> mt7925_mac_sta_remove_link() -> mt7925_mac_link_sta_remove() -> mt7925_roc_abort_sync() invokes cancel_work_sync() while roc_work() is still running and holding dev->mt76.mutex. This avoids the mutex deadlock and preserves exactly-once work ownership. Fixes: 45064d19fd3a ("wifi: mt76: mt7925: fix a potential association failure upon resuming") Co-developed-by: Quan Zhou Signed-off-by: Quan Zhou Signed-off-by: Sean Wang Link: https://patch.msgid.link/20251216013849.17976-1-sean.wang@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7925/main.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index ebb746f4072de..00126f563dfd9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -452,12 +452,16 @@ void mt7925_roc_abort_sync(struct mt792x_dev *dev) { struct mt792x_phy *phy = &dev->phy; + if (!test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state)) + return; + timer_delete_sync(&phy->roc_timer); - cancel_work_sync(&phy->roc_work); - if (test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state)) - ieee80211_iterate_interfaces(mt76_hw(dev), - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7925_roc_iter, (void *)phy); + + cancel_work(&phy->roc_work); + + ieee80211_iterate_interfaces(mt76_hw(dev), + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7925_roc_iter, (void *)phy); } EXPORT_SYMBOL_GPL(mt7925_roc_abort_sync); From 35180c772f5e11e2fa4d80d3dfd50906cb6d9646 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 26 Jan 2026 12:00:13 -0600 Subject: [PATCH 0277/1518] wifi: mt76: mt7921: fix potential deadlock in mt7921_roc_abort_sync [ Upstream commit d5059e52fd8bc624ec4255c9fa01a266513d126b ] roc_abort_sync() can deadlock with roc_work(). roc_work() holds dev->mt76.mutex, while cancel_work_sync() waits for roc_work() to finish. If the caller already owns the same mutex, both sides block and no progress is possible. This deadlock can occur during station removal when mt76_sta_state() -> mt76_sta_remove() -> mt7921_mac_sta_remove() -> mt7921_roc_abort_sync() invokes cancel_work_sync() while roc_work() is still running and holding dev->mt76.mutex. This avoids the mutex deadlock and preserves exactly-once work ownership. Fixes: 352d966126e6 ("wifi: mt76: mt7921: fix a potential association failure upon resuming") Co-developed-by: Quan Zhou Signed-off-by: Quan Zhou Signed-off-by: Sean Wang Link: https://patch.msgid.link/20260126180013.8167-1-sean.wang@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index ea6ff4c6bc90b..07495c97f1c12 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -371,12 +371,15 @@ void mt7921_roc_abort_sync(struct mt792x_dev *dev) { struct mt792x_phy *phy = &dev->phy; + if (!test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state)) + return; + timer_delete_sync(&phy->roc_timer); - cancel_work_sync(&phy->roc_work); - if (test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state)) - ieee80211_iterate_interfaces(mt76_hw(dev), - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7921_roc_iter, (void *)phy); + cancel_work(&phy->roc_work); + + ieee80211_iterate_interfaces(mt76_hw(dev), + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7921_roc_iter, (void *)phy); } EXPORT_SYMBOL_GPL(mt7921_roc_abort_sync); From 5fc8c5d45e44575dda9fcabdc2aac4ad97baf0cd Mon Sep 17 00:00:00 2001 From: Chad Monroe Date: Mon, 8 Dec 2025 14:31:32 +0000 Subject: [PATCH 0278/1518] wifi: mt76: fix deadlock in remain-on-channel [ Upstream commit 6939b97ddad3cf3dfbb3b5a0a12ef79cb886747e ] mt76_remain_on_channel() and mt76_roc_complete() call mt76_set_channel() while already holding dev->mutex. Since mt76_set_channel() also acquires dev->mutex, this results in a deadlock. Use __mt76_set_channel() instead of mt76_set_channel(). Add cancel_delayed_work_sync() for mac_work before acquiring the mutex in mt76_remain_on_channel() to prevent a secondary deadlock with the mac_work workqueue. Fixes: a8f424c1287c ("wifi: mt76: add multi-radio remain_on_channel functions") Signed-off-by: Chad Monroe Link: https://patch.msgid.link/ace737e7b621af7c2adb33b0188011a5c1de2166.1765204256.git.chad@monroe.io Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/channel.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/channel.c b/drivers/net/wireless/mediatek/mt76/channel.c index 130af1b254dbf..eccaee1fd434f 100644 --- a/drivers/net/wireless/mediatek/mt76/channel.c +++ b/drivers/net/wireless/mediatek/mt76/channel.c @@ -326,7 +326,7 @@ void mt76_roc_complete(struct mt76_phy *phy) mlink->mvif->roc_phy = NULL; if (phy->main_chandef.chan && !test_bit(MT76_MCU_RESET, &dev->phy.state)) - mt76_set_channel(phy, &phy->main_chandef, false); + __mt76_set_channel(phy, &phy->main_chandef, false); mt76_put_vif_phy_link(phy, phy->roc_vif, phy->roc_link); phy->roc_vif = NULL; phy->roc_link = NULL; @@ -370,6 +370,8 @@ int mt76_remain_on_channel(struct ieee80211_hw *hw, struct ieee80211_vif *vif, if (!phy) return -EINVAL; + cancel_delayed_work_sync(&phy->mac_work); + mutex_lock(&dev->mutex); if (phy->roc_vif || dev->scan.phy == phy || @@ -388,7 +390,14 @@ int mt76_remain_on_channel(struct ieee80211_hw *hw, struct ieee80211_vif *vif, phy->roc_vif = vif; phy->roc_link = mlink; cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); - mt76_set_channel(phy, &chandef, true); + ret = __mt76_set_channel(phy, &chandef, true); + if (ret) { + mlink->mvif->roc_phy = NULL; + phy->roc_vif = NULL; + phy->roc_link = NULL; + mt76_put_vif_phy_link(phy, vif, mlink); + goto out; + } ieee80211_ready_on_channel(hw); ieee80211_queue_delayed_work(phy->hw, &phy->roc_work, msecs_to_jiffies(duration)); From 612bfcfdb993606e4d359277354c8868852841ff Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 5 Mar 2026 16:28:18 +0000 Subject: [PATCH 0279/1518] arm64: cpufeature: Make PMUVer and PerfMon unsigned [ Upstream commit d1dcc20bcc40efe1f1c71639376c91dafa489222 ] On the host, this change doesn't make a difference because the fields are defined as FTR_EXACT. However, KVM allows userspace to set these fields for a guest and overrides the type to be FTR_LOWER_SAFE. And while KVM used to do an unsigned comparison to validate that the new value is lower than what the hardware provides, since the linked commit it uses the generic sanitization framework which does a signed comparison. Fix it by defining these fields as unsigned. In theory, without this fix, userspace could set a higher PMU version than the hardware supports by providing any value with the top bit set. Fixes: c118cead07a7 ("KVM: arm64: Use generic sanitisation for ID_(AA64)DFR0_EL1") Signed-off-by: James Clark Reviewed-by: Marc Zyngier Reviewed-by: Colton Lewis Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/kernel/cpufeature.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e25b0f84a22da..39a798f74778e 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -564,7 +564,7 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { * We can instantiate multiple PMU instances with different levels * of support. */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_EL1_PMUVer_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_EL1_PMUVer_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_EL1_DebugVer_SHIFT, 4, 0x6), ARM64_FTR_END, }; @@ -708,7 +708,7 @@ static const struct arm64_ftr_bits ftr_id_pfr2[] = { static const struct arm64_ftr_bits ftr_id_dfr0[] = { /* [31:28] TraceFilt */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_EL1_PerfMon_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_EL1_PerfMon_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MProfDbg_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapTrc_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopTrc_SHIFT, 4, 0), From ae94ef093a15b1a36fff1e70d75fadeb08f5be23 Mon Sep 17 00:00:00 2001 From: Shayne Chen Date: Tue, 3 Feb 2026 23:55:29 +0800 Subject: [PATCH 0280/1518] wifi: mt76: mt7996: fix wrong DMAD length when using MAC TXP [ Upstream commit 97b9f9831bf297f3ffa62018721601ed2736f2c3 ] The struct mt76_connac_fw_txp is used for HIF TXP. Change to use the struct mt76_connac_hw_txp to fix the wrong DMAD length for MAC TXP. Fixes: cb6ebbdffef2 ("wifi: mt76: mt7996: support writing MAC TXD for AddBA Request") Signed-off-by: Shayne Chen Link: https://patch.msgid.link/20260203155532.1098290-1-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 2aa8bb779b228..0b5194e708b3a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1109,10 +1109,10 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, * req */ if (le32_to_cpu(ptr[7]) & MT_TXD7_MAC_TXD) { - u32 val; + u32 val, mac_txp_size = sizeof(struct mt76_connac_hw_txp); ptr = (__le32 *)(txwi + MT_TXD_SIZE); - memset((void *)ptr, 0, sizeof(struct mt76_connac_fw_txp)); + memset((void *)ptr, 0, mac_txp_size); val = FIELD_PREP(MT_TXP0_TOKEN_ID0, id) | MT_TXP0_TOKEN_ID0_VALID_MASK; @@ -1131,6 +1131,8 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, tx_info->buf[1].addr >> 32); #endif ptr[3] = cpu_to_le32(val); + + tx_info->buf[0].len = MT_TXD_SIZE + mac_txp_size; } else { struct mt76_connac_txp_common *txp; From 419babee9b5c87bc4bd351c7a2ff4062bd16f5fa Mon Sep 17 00:00:00 2001 From: StanleyYP Wang Date: Tue, 3 Feb 2026 23:55:30 +0800 Subject: [PATCH 0281/1518] wifi: mt76: mt7996: fix struct mt7996_mcu_uni_event [ Upstream commit efbd5bf395f4e6b45a87f3835d4c2e28170c77c5 ] The cid field is defined as a two-byte value in the firmware. Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices") Signed-off-by: StanleyYP Wang Signed-off-by: Shayne Chen Link: https://patch.msgid.link/20260203155532.1098290-2-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 2 +- drivers/net/wireless/mediatek/mt76/mt7996/mcu.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 321098496a39e..c2d15128784bc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -233,7 +233,7 @@ mt7996_mcu_parse_response(struct mt76_dev *mdev, int cmd, event = (struct mt7996_mcu_uni_event *)skb->data; ret = le32_to_cpu(event->status); /* skip invalid event */ - if (mcu_cmd != event->cid) + if (mcu_cmd != le16_to_cpu(event->cid)) ret = -EAGAIN; } else { skb_pull(skb, sizeof(struct mt7996_mcu_rxd)); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h index abfd7e5a775b3..7b51d7346bcaa 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h @@ -25,8 +25,8 @@ struct mt7996_mcu_rxd { }; struct mt7996_mcu_uni_event { - u8 cid; - u8 __rsv[3]; + __le16 cid; + u8 __rsv[2]; __le32 status; /* 0: success, others: fail */ } __packed; From 6b7cbb13c838cf2a5f2e7be0e96fe15250087939 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Fri, 30 Jan 2026 22:57:59 +0800 Subject: [PATCH 0282/1518] wifi: mt76: mt7915: fix use-after-free bugs in mt7915_mac_dump_work() [ Upstream commit 1146d0946b5358fad24812bd39d68f31cd40cc34 ] When the mt7915 pci chip is detaching, the mt7915_crash_data is released in mt7915_coredump_unregister(). However, the work item dump_work may still be running or pending, leading to UAF bugs when the already freed crash_data is dereferenced again in mt7915_mac_dump_work(). The race condition can occur as follows: CPU 0 (removal path) | CPU 1 (workqueue) mt7915_pci_remove() | mt7915_sys_recovery_set() mt7915_unregister_device() | mt7915_reset() mt7915_coredump_unregister() | queue_work() vfree(dev->coredump.crash_data) | mt7915_mac_dump_work() | crash_data-> // UAF Fix this by ensuring dump_work is properly canceled before the crash_data is deallocated. Add cancel_work_sync() in mt7915_unregister_device() to synchronize with any pending or executing dump work. Fixes: 4dbcb9125cc3 ("wifi: mt76: mt7915: enable coredump support") Signed-off-by: Duoming Zhou Link: https://patch.msgid.link/20260130145759.84272-1-duoming@zju.edu.cn Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7915/init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index 5ea8b46e092ef..d2b163a5fce5b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -1287,6 +1287,7 @@ int mt7915_register_device(struct mt7915_dev *dev) void mt7915_unregister_device(struct mt7915_dev *dev) { + cancel_work_sync(&dev->dump_work); mt7915_unregister_ext_phy(dev); mt7915_coredump_unregister(dev); mt7915_unregister_thermal(&dev->phy); From aa4a31cd89f4fde5043ac613fe0e27014a60a60b Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Sat, 31 Jan 2026 10:47:31 +0800 Subject: [PATCH 0283/1518] wifi: mt76: mt7996: fix use-after-free bugs in mt7996_mac_dump_work() [ Upstream commit c8f62f73bbced3a79894655bdb0b625462d956fc ] When the mt7996 pci chip is detaching, the mt7996_crash_data is released in mt7996_coredump_unregister(). However, the work item dump_work may still be running or pending, leading to UAF bugs when the already freed crash_data is dereferenced again in mt7996_mac_dump_work(). The race condition can occur as follows: CPU 0 (removal path) | CPU 1 (workqueue) mt7996_pci_remove() | mt7996_sys_recovery_set() mt7996_unregister_device() | mt7996_reset() mt7996_coredump_unregister() | queue_work() vfree(dev->coredump.crash_data) | mt7996_mac_dump_work() | crash_data-> // UAF Fix this by ensuring dump_work is properly canceled before the crash_data is deallocated. Add cancel_work_sync() in mt7996_unregister_device() to synchronize with any pending or executing dump work. Fixes: 878161d5d4a4 ("wifi: mt76: mt7996: enable coredump support") Signed-off-by: Duoming Zhou Link: https://patch.msgid.link/20260131024731.18741-1-duoming@zju.edu.cn Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index e26f8e9e4f8fc..ba769e6de76d2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -1732,6 +1732,7 @@ int mt7996_register_device(struct mt7996_dev *dev) void mt7996_unregister_device(struct mt7996_dev *dev) { + cancel_work_sync(&dev->dump_work); cancel_work_sync(&dev->wed_rro.work); mt7996_unregister_phy(mt7996_phy3(dev)); mt7996_unregister_phy(mt7996_phy2(dev)); From 1e0f3e5e28356da28439561b8b6139f731328903 Mon Sep 17 00:00:00 2001 From: Michael Lo Date: Wed, 11 Feb 2026 17:50:25 +0800 Subject: [PATCH 0284/1518] wifi: mt76: mt7921: fix 6GHz regulatory update on connection [ Upstream commit 3dc0c40d7806c72cfe88cf4e1e2650c1673f9db4 ] Call mt7921_regd_update() instead of mt7921_mcu_set_clc() when setting the 6GHz power type after connection, so that regulatory limits and SAR power are also applied. Fixes: 51ba0e3a15eb ("wifi: mt76: mt7921: add 6GHz power type support for clc") Signed-off-by: Michael Lo Link: https://patch.msgid.link/20260211095025.2415624-1-leon.yen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 07495c97f1c12..ce11666a32db9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -800,7 +800,8 @@ mt7921_regd_set_6ghz_power_type(struct ieee80211_vif *vif, bool is_add) } out: - mt7921_mcu_set_clc(dev, dev->mt76.alpha2, dev->country_ie_env); + if (vif->bss_conf.chanreq.oper.chan->band == NL80211_BAND_6GHZ) + mt7921_regd_update(dev); } int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, From 7da35e2d2fb749fc06a6d11210ae3729a689834a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 28 Sep 2025 18:27:01 +0200 Subject: [PATCH 0285/1518] wifi: mt76: mt7996: Add missing CHANCTX_STA_CSA property [ Upstream commit c0a47ffc4caaf5161955add553322112c3a211b0 ] Enable missing CHANCTX_STA_CSA property required for MLO. Fixes: f5160304d57c ("wifi: mt76: mt7996: Enable MLO support for client interfaces") Signed-off-by: Lorenzo Bianconi Reviewed-by: AngeloGioacchino Del Regno Link: https://patch.msgid.link/20250928-mt7996_chanctx_sta_csa-v1-1-82e455185990@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index ba769e6de76d2..817acfad31d06 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -536,6 +536,7 @@ mt7996_init_wiphy(struct ieee80211_hw *hw, struct mtk_wed_device *wed) ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD); ieee80211_hw_set(hw, NO_VIRTUAL_MONITOR); ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); + ieee80211_hw_set(hw, CHANCTX_STA_CSA); hw->max_tx_fragments = 4; From 5a3353b06387c3ccf398aefe9c19a4a0275bf8d1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 6 Mar 2026 11:27:52 +0100 Subject: [PATCH 0286/1518] wifi: mt76: mt7996: Remove link pointer dependency in mt7996_mac_sta_remove_links() [ Upstream commit 569ce4340268915911fc356ec9ad27e92fb82289 ] Remove link pointer dependency in mt7996_mac_sta_remove_links routine to get the mt7996_phy pointer since the link can be already offchannel running mt7996_mac_sta_remove_links(). Rely on __mt7996_phy routine instead. Fixes: 344dd6a4c919 ("wifi: mt76: mt7996: Move num_sta accounting in mt7996_mac_sta_{add,remove}_links") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260306-mt7996-deflink-lookup-link-remove-v1-1-7162b332873c@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/main.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 589b228a4eb0c..32d44540605fc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -1047,8 +1047,7 @@ mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { struct mt7996_sta_link *msta_link = NULL; - struct mt7996_vif_link *link; - struct mt76_phy *mphy; + struct mt7996_phy *phy; msta_link = rcu_replace_pointer(msta->link[link_id], msta_link, lockdep_is_held(&mdev->mutex)); @@ -1057,17 +1056,12 @@ mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, mt7996_mac_wtbl_update(dev, msta_link->wcid.idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); - mt7996_mac_sta_deinit_link(dev, msta_link); - link = mt7996_vif_link(dev, vif, link_id); - if (!link) - continue; - mphy = mt76_vif_link_phy(&link->mt76); - if (!mphy) - continue; + phy = __mt7996_phy(dev, msta_link->wcid.phy_idx); + if (phy) + phy->mt76->num_sta--; - mphy->num_sta--; if (msta->deflink_id == link_id) { msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; continue; From d6f6b3a65660d183ef33f5a6582fd3b47174fe5a Mon Sep 17 00:00:00 2001 From: Shayne Chen Date: Thu, 6 Nov 2025 14:41:59 +0800 Subject: [PATCH 0287/1518] wifi: mt76: mt7996: use correct link_id when filling TXD and TXP [ Upstream commit 85cd5534a3f2ec93e7d88713a77df5b4255520df ] Obtain the correct link ID and, if needed, switch to the corresponding wcid before populating the TX descriptor and TX payload. Rules for link id: - For QoS data of MLD peers (excluding EAPOL), select the primary or secondary wcid based on whether the TID is odd or even to meet FW/HW requirements - For other packets, use IEEE80211_TX_CTRL_MLO_LINK if specified (such as multicast and broadcast packets) Signed-off-by: Shayne Chen Acked-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251106064203.1000505-8-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau Stable-dep-of: e648051d52af ("wifi: mt76: mt7996: Decrement sta counter removing the link in mt7996_mac_reset_sta_iter()") Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7996/mac.c | 34 ++++++++++++++++--- .../net/wireless/mediatek/mt76/mt7996/main.c | 9 +++++ .../net/wireless/mediatek/mt76/mt7996/mcu.c | 4 +-- .../wireless/mediatek/mt76/mt7996/mt7996.h | 1 + 4 files changed, 42 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 0b5194e708b3a..13a3b521437be 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1040,15 +1040,20 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, struct ieee80211_sta *sta, struct mt76_tx_info *tx_info) { + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx_info->skb->data; struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb); struct ieee80211_key_conf *key = info->control.hw_key; struct ieee80211_vif *vif = info->control.vif; + struct mt7996_vif *mvif = vif ? (struct mt7996_vif *)vif->drv_priv : NULL; + struct mt7996_sta *msta = sta ? (struct mt7996_sta *)sta->drv_priv : NULL; + struct mt76_vif_link *mlink = NULL; struct mt76_txwi_cache *t; int id, i, pid, nbuf = tx_info->nbuf - 1; bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; __le32 *ptr = (__le32 *)txwi_ptr; u8 *txwi = (u8 *)txwi_ptr; + u8 link_id; if (unlikely(tx_info->skb->len <= ETH_HLEN)) return -EINVAL; @@ -1056,6 +1061,30 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (!wcid) wcid = &dev->mt76.global_wcid; + if ((is_8023 || ieee80211_is_data_qos(hdr->frame_control)) && sta->mlo && + likely(tx_info->skb->protocol != cpu_to_be16(ETH_P_PAE))) { + u8 tid = tx_info->skb->priority & IEEE80211_QOS_CTL_TID_MASK; + + link_id = (tid % 2) ? msta->seclink_id : msta->deflink_id; + } else { + link_id = u32_get_bits(info->control.flags, + IEEE80211_TX_CTRL_MLO_LINK); + } + + if (link_id != wcid->link_id && link_id != IEEE80211_LINK_UNSPECIFIED) { + if (msta) { + struct mt7996_sta_link *msta_link = + rcu_dereference(msta->link[link_id]); + + if (msta_link) + wcid = &msta_link->wcid; + } else if (mvif) { + mlink = rcu_dereference(mvif->mt76.link[link_id]); + if (mlink && mlink->wcid) + wcid = mlink->wcid; + } + } + t = (struct mt76_txwi_cache *)(txwi + mdev->drv->txwi_size); t->skb = tx_info->skb; @@ -1162,10 +1191,7 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (!is_8023 && mt7996_tx_use_mgmt(dev, tx_info->skb)) txp->fw.flags |= cpu_to_le16(MT_CT_INFO_MGMT_FRAME); - if (vif) { - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; - struct mt76_vif_link *mlink = NULL; - + if (mvif) { if (wcid->offchannel) mlink = rcu_dereference(mvif->mt76.offchannel_link); if (!mlink) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 32d44540605fc..af322f505f8ab 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -982,6 +982,7 @@ mt7996_mac_sta_init_link(struct mt7996_dev *dev, msta_link = &msta->deflink; msta->deflink_id = link_id; + msta->seclink_id = msta->deflink_id; for (i = 0; i < ARRAY_SIZE(sta->txq); i++) { struct mt76_txq *mtxq; @@ -996,6 +997,11 @@ mt7996_mac_sta_init_link(struct mt7996_dev *dev, msta_link = kzalloc(sizeof(*msta_link), GFP_KERNEL); if (!msta_link) return -ENOMEM; + + if (msta->seclink_id == msta->deflink_id && + (sta->valid_links & ~BIT(msta->deflink_id))) + msta->seclink_id = __ffs(sta->valid_links & + ~BIT(msta->deflink_id)); } INIT_LIST_HEAD(&msta_link->rc_list); @@ -1065,6 +1071,8 @@ mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, if (msta->deflink_id == link_id) { msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; continue; + } else if (msta->seclink_id == link_id) { + msta->seclink_id = IEEE80211_LINK_UNSPECIFIED; } kfree_rcu(msta_link, rcu_head); @@ -1160,6 +1168,7 @@ mt7996_mac_sta_add(struct mt7996_dev *dev, struct ieee80211_vif *vif, mutex_lock(&dev->mt76.mutex); msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; + msta->seclink_id = IEEE80211_LINK_UNSPECIFIED; msta->vif = mvif; err = mt7996_mac_sta_add_links(dev, vif, sta, links); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index c2d15128784bc..38b8743409a0c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -2399,8 +2399,8 @@ mt7996_mcu_sta_mld_setup_tlv(struct mt7996_dev *dev, struct sk_buff *skb, mld_setup->primary_id = cpu_to_le16(msta_link->wcid.idx); if (nlinks > 1) { - link_id = __ffs(sta->valid_links & ~BIT(msta->deflink_id)); - msta_link = mt76_dereference(msta->link[link_id], &dev->mt76); + msta_link = mt76_dereference(msta->link[msta->seclink_id], + &dev->mt76); if (!msta_link) return; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index 6190fbcd4df7e..6793161ed198c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -243,6 +243,7 @@ struct mt7996_sta { struct mt7996_sta_link deflink; /* must be first */ struct mt7996_sta_link __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; u8 deflink_id; + u8 seclink_id; struct mt7996_vif *vif; }; From e54c6440114d9aa7b14ee140388560aa493c5ed2 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 5 Dec 2025 11:24:38 +0100 Subject: [PATCH 0288/1518] wifi: mt76: mt7996: Switch to the secondary link if the default one is removed [ Upstream commit 5ef44c200618430b004233cbfc1b0929a13d5ac8 ] Switch to the secondary link if available in mt7996_mac_sta_remove_links routine if the primary one is removed. Moreover reset secondary link index for single link scenario. Fixes: 85cd5534a3f2e ("wifi: mt76: mt7996: use correct link_id when filling TXD and TXP") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251205-mt76-txq-wicd-fix-v2-3-f19ba48af7c1@kernel.org Signed-off-by: Felix Fietkau Stable-dep-of: e648051d52af ("wifi: mt76: mt7996: Decrement sta counter removing the link in mt7996_mac_reset_sta_iter()") Signed-off-by: Sasha Levin --- .../net/wireless/mediatek/mt76/mt7996/mac.c | 12 ++--- .../net/wireless/mediatek/mt76/mt7996/main.c | 51 +++++++++++++------ 2 files changed, 41 insertions(+), 22 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 13a3b521437be..3280446f7caa8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -2406,14 +2406,12 @@ mt7996_mac_reset_sta_iter(void *data, struct ieee80211_sta *sta) continue; mt7996_mac_sta_deinit_link(dev, msta_link); - - if (msta->deflink_id == i) { - msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; - continue; - } - - kfree_rcu(msta_link, rcu_head); + if (msta_link != &msta->deflink) + kfree_rcu(msta_link, rcu_head); } + + msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; + msta->seclink_id = msta->deflink_id; } static void diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index af322f505f8ab..d714b7f3efe56 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -961,6 +961,22 @@ mt7996_post_channel_switch(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return ret; } +static void +mt7996_sta_init_txq_wcid(struct ieee80211_sta *sta, int idx) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(sta->txq); i++) { + struct mt76_txq *mtxq; + + if (!sta->txq[i]) + continue; + + mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv; + mtxq->wcid = idx; + } +} + static int mt7996_mac_sta_init_link(struct mt7996_dev *dev, struct ieee80211_bss_conf *link_conf, @@ -978,21 +994,10 @@ mt7996_mac_sta_init_link(struct mt7996_dev *dev, return -ENOSPC; if (msta->deflink_id == IEEE80211_LINK_UNSPECIFIED) { - int i; - msta_link = &msta->deflink; msta->deflink_id = link_id; msta->seclink_id = msta->deflink_id; - - for (i = 0; i < ARRAY_SIZE(sta->txq); i++) { - struct mt76_txq *mtxq; - - if (!sta->txq[i]) - continue; - - mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv; - mtxq->wcid = idx; - } + mt7996_sta_init_txq_wcid(sta, idx); } else { msta_link = kzalloc(sizeof(*msta_link), GFP_KERNEL); if (!msta_link) @@ -1070,12 +1075,28 @@ mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_vif *vif, if (msta->deflink_id == link_id) { msta->deflink_id = IEEE80211_LINK_UNSPECIFIED; - continue; + if (msta->seclink_id == link_id) { + /* no secondary link available */ + msta->seclink_id = msta->deflink_id; + } else { + struct mt7996_sta_link *msta_seclink; + + /* switch to the secondary link */ + msta_seclink = mt76_dereference( + msta->link[msta->seclink_id], + mdev); + if (msta_seclink) { + msta->deflink_id = msta->seclink_id; + mt7996_sta_init_txq_wcid(sta, + msta_seclink->wcid.idx); + } + } } else if (msta->seclink_id == link_id) { - msta->seclink_id = IEEE80211_LINK_UNSPECIFIED; + msta->seclink_id = msta->deflink_id; } - kfree_rcu(msta_link, rcu_head); + if (msta_link != &msta->deflink) + kfree_rcu(msta_link, rcu_head); } } From 98e0118ab51c6b30f069f185c6651381a12c6eb6 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 8 Mar 2026 14:25:20 +0100 Subject: [PATCH 0289/1518] wifi: mt76: mt7996: Decrement sta counter removing the link in mt7996_mac_reset_sta_iter() [ Upstream commit e648051d52afbdb360bd586218961f5fffff63e8 ] Fixes tracking per-phy stations for offchannel switching. Fixes: ace5d3b6b49e8 ("wifi: mt76: mt7996: improve hardware restart reliability") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260308-mt7996_mac_reset_vif_iter-fix-v1-1-57f640aa2dcf@kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 3280446f7caa8..dce9f48637927 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -2399,6 +2399,7 @@ mt7996_mac_reset_sta_iter(void *data, struct ieee80211_sta *sta) for (i = 0; i < ARRAY_SIZE(msta->link); i++) { struct mt7996_sta_link *msta_link = NULL; + struct mt7996_phy *phy; msta_link = rcu_replace_pointer(msta->link[i], msta_link, lockdep_is_held(&dev->mt76.mutex)); @@ -2406,6 +2407,10 @@ mt7996_mac_reset_sta_iter(void *data, struct ieee80211_sta *sta) continue; mt7996_mac_sta_deinit_link(dev, msta_link); + phy = __mt7996_phy(dev, msta_link->wcid.phy_idx); + if (phy) + phy->mt76->num_sta--; + if (msta_link != &msta->deflink) kfree_rcu(msta_link, rcu_head); } From a2cde15af3782d407a69bdd43ba455fc1dc5bff3 Mon Sep 17 00:00:00 2001 From: Chad Monroe Date: Mon, 9 Mar 2026 06:07:20 +0000 Subject: [PATCH 0290/1518] wifi: mt76: fix multi-radio on-channel scanning [ Upstream commit 0420180df092419a96351fb2afec1e2a74d385c3 ] avoid unnecessary channel switch when performing an on-channel scan using a multi-radio device. Fixes: c56d6edebc1f ("wifi: mt76: mt7996: use emulated hardware scan support") Signed-off-by: Chad Monroe Link: https://patch.msgid.link/20251118102723.47997-1-nbd@nbd.name Link: https://patch.msgid.link/20260309060730.87840-1-nbd@nbd.name Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/scan.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/scan.c b/drivers/net/wireless/mediatek/mt76/scan.c index 3d9cf6f5e137f..efcf79d9d60e0 100644 --- a/drivers/net/wireless/mediatek/mt76/scan.c +++ b/drivers/net/wireless/mediatek/mt76/scan.c @@ -16,7 +16,7 @@ static void mt76_scan_complete(struct mt76_dev *dev, bool abort) clear_bit(MT76_SCANNING, &phy->state); - if (dev->scan.chan && phy->main_chandef.chan && + if (dev->scan.chan && phy->main_chandef.chan && phy->offchannel && !test_bit(MT76_MCU_RESET, &dev->phy.state)) mt76_set_channel(phy, &phy->main_chandef, false); mt76_put_vif_phy_link(phy, dev->scan.vif, dev->scan.mlink); @@ -85,6 +85,7 @@ void mt76_scan_work(struct work_struct *work) struct cfg80211_chan_def chandef = {}; struct mt76_phy *phy = dev->scan.phy; int duration = HZ / 9; /* ~110 ms */ + bool offchannel = true; int i; if (dev->scan.chan_idx >= req->n_channels) { @@ -92,7 +93,7 @@ void mt76_scan_work(struct work_struct *work) return; } - if (dev->scan.chan && phy->num_sta) { + if (dev->scan.chan && phy->num_sta && phy->offchannel) { dev->scan.chan = NULL; mt76_set_channel(phy, &phy->main_chandef, false); goto out; @@ -100,20 +101,26 @@ void mt76_scan_work(struct work_struct *work) dev->scan.chan = req->channels[dev->scan.chan_idx++]; cfg80211_chandef_create(&chandef, dev->scan.chan, NL80211_CHAN_HT20); - mt76_set_channel(phy, &chandef, true); + if (phy->main_chandef.chan == dev->scan.chan) { + chandef = phy->main_chandef; + offchannel = false; + } + + mt76_set_channel(phy, &chandef, offchannel); if (!req->n_ssids || chandef.chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) goto out; - duration = HZ / 16; /* ~60 ms */ + if (phy->offchannel) + duration = HZ / 16; /* ~60 ms */ local_bh_disable(); for (i = 0; i < req->n_ssids; i++) mt76_scan_send_probe(dev, &req->ssids[i]); local_bh_enable(); out: - if (dev->scan.chan) + if (dev->scan.chan && phy->offchannel) duration = max_t(int, duration, msecs_to_jiffies(req->duration + (req->duration >> 5))); From dc34c01521bf025615a588fe296038d69a67e459 Mon Sep 17 00:00:00 2001 From: Chad Monroe Date: Mon, 9 Mar 2026 06:07:21 +0000 Subject: [PATCH 0291/1518] wifi: mt76: support upgrading passive scans to active [ Upstream commit 360552c8592dab3c69e0bbff786b55137f1a81bb ] On channels with NO_IR or RADAR flags, wait for beacon before sending probe requests. Allows active scanning and WPS on restricted channels if another AP is already present. Fixes: c56d6edebc1f ("wifi: mt76: mt7996: use emulated hardware scan support") Tested-by: Piotr Kubik Signed-off-by: Chad Monroe Link: https://patch.msgid.link/20251118102723.47997-2-nbd@nbd.name Link: https://patch.msgid.link/20260309060730.87840-2-nbd@nbd.name Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mac80211.c | 1 + drivers/net/wireless/mediatek/mt76/mt76.h | 4 ++ .../net/wireless/mediatek/mt76/mt7996/mac.c | 3 ++ drivers/net/wireless/mediatek/mt76/scan.c | 51 +++++++++++++++++-- 4 files changed, 56 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 5e75861bf6f99..76eb740428b8d 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -724,6 +724,7 @@ mt76_alloc_device(struct device *pdev, unsigned int size, INIT_LIST_HEAD(&dev->rxwi_cache); dev->token_size = dev->drv->token_size; INIT_DELAYED_WORK(&dev->scan_work, mt76_scan_work); + spin_lock_init(&dev->scan_lock); for (i = 0; i < ARRAY_SIZE(dev->q_rx); i++) skb_queue_head_init(&dev->rx_skb[i]); diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 7753afa3d883d..125ac1eb2d541 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -985,6 +985,7 @@ struct mt76_dev { u32 rxfilter; struct delayed_work scan_work; + spinlock_t scan_lock; struct { struct cfg80211_scan_request *req; struct ieee80211_channel *chan; @@ -992,6 +993,8 @@ struct mt76_dev { struct mt76_vif_link *mlink; struct mt76_phy *phy; int chan_idx; + bool beacon_wait; + bool beacon_received; } scan; #ifdef CONFIG_NL80211_TESTMODE @@ -1571,6 +1574,7 @@ int mt76_get_rate(struct mt76_dev *dev, int mt76_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_scan_request *hw_req); void mt76_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif); +void mt76_scan_rx_beacon(struct mt76_dev *dev, struct ieee80211_channel *chan); void mt76_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac); void mt76_sw_scan_complete(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index dce9f48637927..c375b4dd68a20 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -554,6 +554,9 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q, qos_ctl = FIELD_GET(MT_RXD10_QOS_CTL, v2); seq_ctrl = FIELD_GET(MT_RXD10_SEQ_CTRL, v2); + if (ieee80211_is_beacon(fc)) + mt76_scan_rx_beacon(&dev->mt76, mphy->chandef.chan); + rxd += 4; if ((u8 *)rxd - skb->data >= skb->len) return -EINVAL; diff --git a/drivers/net/wireless/mediatek/mt76/scan.c b/drivers/net/wireless/mediatek/mt76/scan.c index efcf79d9d60e0..6cfca5108bc7e 100644 --- a/drivers/net/wireless/mediatek/mt76/scan.c +++ b/drivers/net/wireless/mediatek/mt76/scan.c @@ -27,6 +27,10 @@ static void mt76_scan_complete(struct mt76_dev *dev, bool abort) void mt76_abort_scan(struct mt76_dev *dev) { + spin_lock_bh(&dev->scan_lock); + dev->scan.beacon_wait = false; + spin_unlock_bh(&dev->scan_lock); + cancel_delayed_work_sync(&dev->scan_work); mt76_scan_complete(dev, true); } @@ -77,6 +81,28 @@ mt76_scan_send_probe(struct mt76_dev *dev, struct cfg80211_ssid *ssid) rcu_read_unlock(); } +void mt76_scan_rx_beacon(struct mt76_dev *dev, struct ieee80211_channel *chan) +{ + struct mt76_phy *phy; + + spin_lock(&dev->scan_lock); + + if (!dev->scan.beacon_wait || dev->scan.beacon_received || + dev->scan.chan != chan) + goto out; + + phy = dev->scan.phy; + if (!phy) + goto out; + + dev->scan.beacon_received = true; + ieee80211_queue_delayed_work(phy->hw, &dev->scan_work, 0); + +out: + spin_unlock(&dev->scan_lock); +} +EXPORT_SYMBOL_GPL(mt76_scan_rx_beacon); + void mt76_scan_work(struct work_struct *work) { struct mt76_dev *dev = container_of(work, struct mt76_dev, @@ -85,9 +111,20 @@ void mt76_scan_work(struct work_struct *work) struct cfg80211_chan_def chandef = {}; struct mt76_phy *phy = dev->scan.phy; int duration = HZ / 9; /* ~110 ms */ - bool offchannel = true; + bool beacon_rx, offchannel = true; int i; + if (!phy || !req) + return; + + spin_lock_bh(&dev->scan_lock); + beacon_rx = dev->scan.beacon_wait && dev->scan.beacon_received; + dev->scan.beacon_wait = false; + spin_unlock_bh(&dev->scan_lock); + + if (beacon_rx) + goto probe; + if (dev->scan.chan_idx >= req->n_channels) { mt76_scan_complete(dev, false); return; @@ -108,10 +145,18 @@ void mt76_scan_work(struct work_struct *work) mt76_set_channel(phy, &chandef, offchannel); - if (!req->n_ssids || - chandef.chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) + if (!req->n_ssids) goto out; + if (chandef.chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) { + spin_lock_bh(&dev->scan_lock); + dev->scan.beacon_received = false; + dev->scan.beacon_wait = true; + spin_unlock_bh(&dev->scan_lock); + goto out; + } + +probe: if (phy->offchannel) duration = HZ / 16; /* ~60 ms */ local_bh_disable(); From a1a8a8bdfa2171a7e2fe79ea8c481db1cd3fadf0 Mon Sep 17 00:00:00 2001 From: Peter Chiu Date: Thu, 12 Mar 2026 17:57:19 +0800 Subject: [PATCH 0292/1518] wifi: mt76: mt7996: fix RRO EMU configuration [ Upstream commit 73b46379e5231138025b271ce8e158d2a8aa0768 ] Use the correct helper to update specific bitfields instead of overwriting the entire register. Fixes: eedb427eb260 ("wifi: mt76: mt7996: Enable HW RRO for MT7992 chipset") Signed-off-by: Peter Chiu Signed-off-by: Shayne Chen Acked-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260312095724.2117448-1-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7996/init.c | 3 +-- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index 817acfad31d06..efbd46d649017 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -857,8 +857,7 @@ void mt7996_rro_hw_init(struct mt7996_dev *dev) } } else { /* set emul 3.0 function */ - mt76_wr(dev, MT_RRO_3_0_EMU_CONF, - MT_RRO_3_0_EMU_CONF_EN_MASK); + mt76_set(dev, MT_RRO_3_0_EMU_CONF, MT_RRO_3_0_EMU_CONF_EN_MASK); mt76_wr(dev, MT_RRO_ADDR_ARRAY_BASE0, dev->wed_rro.addr_elem[0].phy_addr); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index c375b4dd68a20..149d8d711fc4c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -2597,7 +2597,7 @@ void mt7996_mac_reset_work(struct work_struct *work) mt7996_dma_start(dev, false, false); if (!is_mt7996(&dev->mt76) && dev->mt76.hwrro_mode == MT76_HWRRO_V3) - mt76_wr(dev, MT_RRO_3_0_EMU_CONF, MT_RRO_3_0_EMU_CONF_EN_MASK); + mt76_set(dev, MT_RRO_3_0_EMU_CONF, MT_RRO_3_0_EMU_CONF_EN_MASK); if (mtk_wed_device_active(&dev->mt76.mmio.wed)) { u32 wed_irq_mask = MT_INT_TX_DONE_BAND2 | From 0b69217310ee43ec44d7efb4a6e31ea0393fcb79 Mon Sep 17 00:00:00 2001 From: Keisuke Nishimura Date: Fri, 20 Mar 2026 14:02:20 +0100 Subject: [PATCH 0293/1518] bpf: Fix refcount check in check_struct_ops_btf_id() [ Upstream commit 25e3e1f1096089a64901ae1faa7b7b13446653db ] The current implementation only checks whether the first argument is refcounted. Fix this by iterating over all arguments. Signed-off-by: Keisuke Nishimura Fixes: 38f1e66abd184 ("bpf: Do not allow tail call in strcut_ops program with __ref argument") Reviewed-by: Emil Tsalapatis Acked-by: Amery Hung Link: https://lore.kernel.org/r/20260320130219.63711-1-keisuke.nishimura@inria.fr Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index db1c591a1da3b..76503ed088b5d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -23687,7 +23687,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } for (i = 0; i < st_ops_desc->arg_info[member_idx].cnt; i++) { - if (st_ops_desc->arg_info[member_idx].info->refcounted) { + if (st_ops_desc->arg_info[member_idx].info[i].refcounted) { has_refcounted_arg = true; break; } From d4c4bd231ebad70e6f30db429e9640bf378b2f52 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 20 Mar 2026 07:26:45 +0000 Subject: [PATCH 0294/1518] bpf: Use RCU-safe iteration in dev_map_redirect_multi() SKB path [ Upstream commit 8ed82f807bb09d2c8455aaa665f2c6cb17bc6a19 ] The DEVMAP_HASH branch in dev_map_redirect_multi() uses hlist_for_each_entry_safe() to iterate hash buckets, but this function runs under RCU protection (called from xdp_do_generic_redirect_map() in softirq context). Concurrent writers (__dev_map_hash_update_elem, dev_map_hash_delete_elem) modify the list using RCU primitives (hlist_add_head_rcu, hlist_del_rcu). hlist_for_each_entry_safe() performs plain pointer dereferences without rcu_dereference(), missing the acquire barrier needed to pair with writers' rcu_assign_pointer(). On weakly-ordered architectures (ARM64, POWER), a reader can observe a partially-constructed node. It also defeats CONFIG_PROVE_RCU lockdep validation and KCSAN data-race detection. Replace with hlist_for_each_entry_rcu() using rcu_read_lock_bh_held() as the lockdep condition, consistent with the rcu_dereference_check() used in the DEVMAP (non-hash) branch of the same functions. Also fix the same incorrect lockdep_is_held(&dtab->index_lock) condition in dev_map_enqueue_multi(), where the lock is not held either. Fixes: e624d4ed4aa8 ("xdp: Extend xdp_redirect_map with broadcast support") Signed-off-by: David Carlier Signed-off-by: Martin KaFai Lau Link: https://patch.msgid.link/20260320072645.16731-1-devnexen@gmail.com Signed-off-by: Sasha Levin --- kernel/bpf/devmap.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 3d619d01088e3..cc0a43ebab6b9 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -665,7 +665,7 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, - lockdep_is_held(&dtab->index_lock)) { + rcu_read_lock_bh_held()) { if (!is_valid_dst(dst, xdpf)) continue; @@ -747,7 +747,6 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; - struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; @@ -787,7 +786,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); - hlist_for_each_entry_safe(dst, next, head, index_hlist) { + hlist_for_each_entry_rcu(dst, head, index_hlist, rcu_read_lock_bh_held()) { if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; From 1391ecf3a99a087e49a974717b4c589ce49f8872 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 24 Mar 2026 14:59:36 -0700 Subject: [PATCH 0295/1518] bpf: Fix variable length stack write over spilled pointers [ Upstream commit 4639eb9e30ab10c7935c7c19e872facf9a94713f ] Scrub slots if variable-offset stack write goes over spilled pointers. Otherwise is_spilled_reg() may == true && spilled_ptr.type == NOT_INIT and valid program is rejected by check_stack_read_fixed_off() with obscure "invalid size of register fill" message. Fixes: 01f810ace9ed ("bpf: Allow variable-offset stack access") Acked-by: Eduard Zingerman Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260324215938.81733-1-alexei.starovoitov@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 76503ed088b5d..0d1ec2b5d469a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5095,6 +5095,18 @@ static void check_fastcall_stack_contract(struct bpf_verifier_env *env, } } +static void scrub_special_slot(struct bpf_func_state *state, int spi) +{ + int i; + + /* regular write of data into stack destroys any spilled ptr */ + state->stack[spi].spilled_ptr.type = NOT_INIT; + /* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */ + if (is_stack_slot_special(&state->stack[spi])) + for (i = 0; i < BPF_REG_SIZE; i++) + scrub_spilled_slot(&state->stack[spi].slot_type[i]); +} + /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -5192,12 +5204,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, } else { u8 type = STACK_MISC; - /* regular write of data into stack destroys any spilled ptr */ - state->stack[spi].spilled_ptr.type = NOT_INIT; - /* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */ - if (is_stack_slot_special(&state->stack[spi])) - for (i = 0; i < BPF_REG_SIZE; i++) - scrub_spilled_slot(&state->stack[spi].slot_type[i]); + scrub_special_slot(state, spi); /* when we zero initialize stack slots mark them as such */ if ((reg && register_is_null(reg)) || @@ -5321,8 +5328,13 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, } } - /* Erase all other spilled pointers. */ - state->stack[spi].spilled_ptr.type = NOT_INIT; + /* + * Scrub slots if variable-offset stack write goes over spilled pointers. + * Otherwise is_spilled_reg() may == true && spilled_ptr.type == NOT_INIT + * and valid program is rejected by check_stack_read_fixed_off() + * with obscure "invalid size of register fill" message. + */ + scrub_special_slot(state, spi); /* Update the slot type. */ new_type = STACK_MISC; From 97757d231bc64fba69525b01b562187e4c619854 Mon Sep 17 00:00:00 2001 From: "haoyu.lu" Date: Tue, 24 Mar 2026 20:27:02 +0800 Subject: [PATCH 0296/1518] bpf,arc_jit: Fix missing newline in pr_err messages [ Upstream commit b6b5e0ebd429d66ce37ae5af649a74ea1f041d92 ] Add missing newline to pr_err messages in ARC JIT. Fixes: f122668ddcce ("ARC: Add eBPF JIT support") Signed-off-by: haoyu.lu Link: https://lore.kernel.org/r/20260324122703.641-1-hechushiguitu666@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- arch/arc/net/bpf_jit_arcv2.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 6d989b6d88c69..7ee50aeae5a45 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -2427,7 +2427,7 @@ u8 arc_prologue(u8 *buf, u32 usage, u16 frame_size) #ifdef ARC_BPF_JIT_DEBUG if ((usage & BIT(ARC_R_FP)) && frame_size == 0) { - pr_err("FP is being saved while there is no frame."); + pr_err("FP is being saved while there is no frame.\n"); BUG(); } #endif @@ -2454,7 +2454,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size) #ifdef ARC_BPF_JIT_DEBUG if ((usage & BIT(ARC_R_FP)) && frame_size == 0) { - pr_err("FP is being saved while there is no frame."); + pr_err("FP is being saved while there is no frame.\n"); BUG(); } #endif @@ -2868,7 +2868,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) break; default: #ifdef ARC_BPF_JIT_DEBUG - pr_err("64-bit jump condition is not known."); + pr_err("64-bit jump condition is not known.\n"); BUG(); #endif } @@ -2948,7 +2948,7 @@ u8 gen_jmp_32(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) */ if (cond >= ARC_CC_LAST) { #ifdef ARC_BPF_JIT_DEBUG - pr_err("32-bit jump condition is not known."); + pr_err("32-bit jump condition is not known.\n"); BUG(); #endif return 0; From 6b9694702c379ef71c89114bc39baee547557393 Mon Sep 17 00:00:00 2001 From: Alexey Velichayshiy Date: Mon, 23 Mar 2026 17:05:53 +0300 Subject: [PATCH 0297/1518] wifi: rtw89: phy: fix uninitialized variable access in rtw89_phy_cfo_set_crystal_cap() [ Upstream commit 047cddf88c611e616d49a00311d4722e46286234 ] In the rtw89_phy_cfo_set_crystal_cap() function, for chips other than RTL8852A/RTL8851B, the values read by rtw89_mac_read_xtal_si() are stored into the local variables sc_xi_val and sc_xo_val. If either read fails, these variables remain uninitialized, they are later used to update cfo->crystal_cap and in debug print statements. This can lead to undefined behavior. Fix the issue by initializing sc_xi_val and sc_xo_val to zero, like is implemented in vendor driver. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 8379fa611536 ("rtw89: 8852c: add write/read crystal function in CFO tracking") Signed-off-by: Alexey Velichayshiy Acked-by: Ping-Ke Shih Signed-off-by: Ping-Ke Shih Link: https://patch.msgid.link/20260323140613.1615574-1-a.velichayshiy@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtw89/phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c index ba7feadd75828..36dee482bc34b 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.c +++ b/drivers/net/wireless/realtek/rtw89/phy.c @@ -4499,7 +4499,7 @@ static void rtw89_phy_cfo_set_crystal_cap(struct rtw89_dev *rtwdev, { struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking; const struct rtw89_chip_info *chip = rtwdev->chip; - u8 sc_xi_val, sc_xo_val; + u8 sc_xi_val = 0, sc_xo_val = 0; if (!force && cfo->crystal_cap == crystal_cap) return; From fa3b3e43e8834617ab4980eeeab9352ab9dd46c0 Mon Sep 17 00:00:00 2001 From: Ankit Agrawal Date: Thu, 27 Nov 2025 17:06:27 +0000 Subject: [PATCH 0298/1518] vfio: refactor vfio_pci_mmap_huge_fault function [ Upstream commit 9b92bc7554b543dc00a0a0b62904a9ef2ad5c4b0 ] Refactor vfio_pci_mmap_huge_fault to take out the implementation to map the VMA to the PTE/PMD/PUD as a separate function. Export the new function to be used by nvgrace-gpu module. Move the alignment check code to verify that pfn and VMA VA is aligned to the page order to the header file and make it inline. No functional change is intended. Cc: Shameer Kolothum Cc: Alex Williamson Cc: Jason Gunthorpe Reviewed-by: Shameer Kolothum Signed-off-by: Ankit Agrawal Link: https://lore.kernel.org/r/20251127170632.3477-2-ankita@nvidia.com Signed-off-by: Alex Williamson Stable-dep-of: 948b71aa81cd ("drivers/vfio_pci_core: Change PXD_ORDER check from switch case to if/else block") Signed-off-by: Sasha Levin --- drivers/vfio/pci/vfio_pci_core.c | 54 ++++++++++++++++---------------- include/linux/vfio_pci_core.h | 13 ++++++++ 2 files changed, 40 insertions(+), 27 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 69476fc67ca08..d07f0ede5d731 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1677,49 +1677,49 @@ static unsigned long vma_to_pfn(struct vm_area_struct *vma) return (pci_resource_start(vdev->pdev, index) >> PAGE_SHIFT) + pgoff; } -static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, - unsigned int order) +vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev, + struct vm_fault *vmf, + unsigned long pfn, + unsigned int order) { - struct vm_area_struct *vma = vmf->vma; - struct vfio_pci_core_device *vdev = vma->vm_private_data; - unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1); - unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; - unsigned long pfn = vma_to_pfn(vma) + pgoff; - vm_fault_t ret = VM_FAULT_SIGBUS; - - if (order && (addr < vma->vm_start || - addr + (PAGE_SIZE << order) > vma->vm_end || - pfn & ((1 << order) - 1))) { - ret = VM_FAULT_FALLBACK; - goto out; - } - - down_read(&vdev->memory_lock); + lockdep_assert_held_read(&vdev->memory_lock); if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) - goto out_unlock; + return VM_FAULT_SIGBUS; switch (order) { case 0: - ret = vmf_insert_pfn(vma, vmf->address, pfn); - break; + return vmf_insert_pfn(vmf->vma, vmf->address, pfn); #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP case PMD_ORDER: - ret = vmf_insert_pfn_pmd(vmf, pfn, false); - break; + return vmf_insert_pfn_pmd(vmf, pfn, false); #endif #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP case PUD_ORDER: - ret = vmf_insert_pfn_pud(vmf, pfn, false); + return vmf_insert_pfn_pud(vmf, pfn, false); break; #endif default: - ret = VM_FAULT_FALLBACK; + return VM_FAULT_FALLBACK; + } +} +EXPORT_SYMBOL_GPL(vfio_pci_vmf_insert_pfn); + +static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, + unsigned int order) +{ + struct vm_area_struct *vma = vmf->vma; + struct vfio_pci_core_device *vdev = vma->vm_private_data; + unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1); + unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; + unsigned long pfn = vma_to_pfn(vma) + pgoff; + vm_fault_t ret = VM_FAULT_FALLBACK; + + if (is_aligned_for_order(vma, addr, pfn, order)) { + scoped_guard(rwsem_read, &vdev->memory_lock) + ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); } -out_unlock: - up_read(&vdev->memory_lock); -out: dev_dbg_ratelimited(&vdev->pdev->dev, "%s(,order = %d) BAR %ld page offset 0x%lx: 0x%x\n", __func__, order, diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 7aa29428982aa..0ddc42732647e 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -132,6 +132,9 @@ ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, size_t count, loff_t *ppos); +vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev, + struct vm_fault *vmf, unsigned long pfn, + unsigned int order); int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma); void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count); int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); @@ -175,4 +178,14 @@ VFIO_IOREAD_DECLARATION(32) VFIO_IOREAD_DECLARATION(64) #endif +static inline bool is_aligned_for_order(struct vm_area_struct *vma, + unsigned long addr, + unsigned long pfn, + unsigned int order) +{ + return !(order && (addr < vma->vm_start || + addr + (PAGE_SIZE << order) > vma->vm_end || + !IS_ALIGNED(pfn, 1 << order))); +} + #endif /* VFIO_PCI_CORE_H */ From ae5f83c0809f3442bb69f2284e44557e3b9d074d Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Mon, 9 Mar 2026 18:08:37 +0530 Subject: [PATCH 0299/1518] drivers/vfio_pci_core: Change PXD_ORDER check from switch case to if/else block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 948b71aa81cd89b222942db6055e8d9c51c54e78 ] Architectures like PowerPC uses runtime defined values for PMD_ORDER/PUD_ORDER. This is because it can use either RADIX or HASH MMU at runtime using kernel cmdline. So the pXd_index_size is not known at compile time. Without this fix, when we add huge pfn support on powerpc in the next patch, vfio_pci_core driver compilation can fail with the following errors. CC [M] drivers/vfio/vfio_main.o CC [M] drivers/vfio/group.o CC [M] drivers/vfio/container.o CC [M] drivers/vfio/virqfd.o CC [M] drivers/vfio/vfio_iommu_spapr_tce.o CC [M] drivers/vfio/pci/vfio_pci_core.o CC [M] drivers/vfio/pci/vfio_pci_intrs.o CC [M] drivers/vfio/pci/vfio_pci_rdwr.o CC [M] drivers/vfio/pci/vfio_pci_config.o CC [M] drivers/vfio/pci/vfio_pci.o AR kernel/built-in.a ../drivers/vfio/pci/vfio_pci_core.c: In function ‘vfio_pci_vmf_insert_pfn’: ../drivers/vfio/pci/vfio_pci_core.c:1678:9: error: case label does not reduce to an integer constant 1678 | case PMD_ORDER: | ^~~~ ../drivers/vfio/pci/vfio_pci_core.c:1682:9: error: case label does not reduce to an integer constant 1682 | case PUD_ORDER: | ^~~~ make[6]: *** [../scripts/Makefile.build:289: drivers/vfio/pci/vfio_pci_core.o] Error 1 make[6]: *** Waiting for unfinished jobs.... make[5]: *** [../scripts/Makefile.build:546: drivers/vfio/pci] Error 2 make[5]: *** Waiting for unfinished jobs.... make[4]: *** [../scripts/Makefile.build:546: drivers/vfio] Error 2 make[3]: *** [../scripts/Makefile.build:546: drivers] Error 2 Fixes: f9e54c3a2f5b7 ("vfio/pci: implement huge_fault support") Signed-off-by: Ritesh Harjani (IBM) Tested-by: Venkat Rao Bagalkote Reviewed-by: Alex Williamson Reviewed-by: Christophe Leroy (CS GROUP) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/b155e19993ee1f5584c72050192eb468b31c5029.1773058761.git.ritesh.list@gmail.com Signed-off-by: Sasha Levin --- drivers/vfio/pci/vfio_pci_core.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index d07f0ede5d731..53a846d3e6758 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1687,21 +1687,16 @@ vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev, if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) return VM_FAULT_SIGBUS; - switch (order) { - case 0: + if (!order) return vmf_insert_pfn(vmf->vma, vmf->address, pfn); -#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP - case PMD_ORDER: + + if (IS_ENABLED(CONFIG_ARCH_SUPPORTS_PMD_PFNMAP) && order == PMD_ORDER) return vmf_insert_pfn_pmd(vmf, pfn, false); -#endif -#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP - case PUD_ORDER: + + if (IS_ENABLED(CONFIG_ARCH_SUPPORTS_PUD_PFNMAP) && order == PUD_ORDER) return vmf_insert_pfn_pud(vmf, pfn, false); - break; -#endif - default: - return VM_FAULT_FALLBACK; - } + + return VM_FAULT_FALLBACK; } EXPORT_SYMBOL_GPL(vfio_pci_vmf_insert_pfn); From 50c601805fe3b0547fb963e6f47969ab4c5da40b Mon Sep 17 00:00:00 2001 From: Chih Kai Hsu Date: Thu, 26 Mar 2026 15:39:23 +0800 Subject: [PATCH 0300/1518] r8152: fix incorrect register write to USB_UPHY_XTAL [ Upstream commit 48afd5124fd6129c46fd12cb06155384b1c4a0c4 ] The old code used ocp_write_byte() to clear the OOBS_POLLING bit (BIT(8)) in the USB_UPHY_XTAL register, but this doesn't correctly clear a bit in the upper byte of the 16-bit register. Fix this by using ocp_write_word() instead. Fixes: 195aae321c82 ("r8152: support new chips") Signed-off-by: Chih Kai Hsu Reviewed-by: Hayes Wang Link: https://patch.msgid.link/20260326073925.32976-454-nic_swsd@realtek.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/usb/r8152.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 357f5c733d0b5..d610741782794 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3896,7 +3896,7 @@ static void r8156_ups_en(struct r8152 *tp, bool enable) case RTL_VER_15: ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPHY_XTAL); ocp_data &= ~OOBS_POLLING; - ocp_write_byte(tp, MCU_TYPE_USB, USB_UPHY_XTAL, ocp_data); + ocp_write_word(tp, MCU_TYPE_USB, USB_UPHY_XTAL, ocp_data); break; default: break; From eef879190a1f2365d403219cc94f101c3d04144c Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Thu, 12 Mar 2026 14:00:49 +0530 Subject: [PATCH 0301/1518] powerpc/crash: fix backup region offset update to elfcorehdr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 789335cacdf37da93bb7c70322dff8c7e82881df ] update_backup_region_phdr() in file_load_64.c iterates over all the program headers in the kdump kernel’s elfcorehdr and updates the p_offset of the program header whose physical address starts at 0. However, the loop logic is incorrect because the program header pointer is not updated during iteration. Since elfcorehdr typically contains PT_NOTE entries first, the PT_LOAD program header with physical address 0 is never reached. As a result, its p_offset is not updated to point to the backup region. Because of this behavior, the capture kernel exports the first 64 KB of the crashed kernel’s memory at offset 0, even though that memory actually lives in the backup region. When a crash happens, purgatory copies the first 64 KB of the crashed kernel’s memory into the backup region so the capture kernel can safely use it. This has not caused problems so far because the first 64 KB is usually identical in both the crashed and capture kernels. However, this is just an assumption and is not guaranteed to always hold true. Fix update_backup_region_phdr() to correctly update the p_offset of the program header with a starting physical address of 0 by correcting the logic used to iterate over the program headers. Fixes: cb350c1f1f86 ("powerpc/kexec_file: Prepare elfcore header for crashing kernel") Reviewed-by: Aditya Gupta Signed-off-by: Sourabh Jain Reviewed-by: Hari Bathini Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260312083051.1935737-2-sourabhjain@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kexec/file_load_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 5f6d50e4c3d45..a7db7eca0481b 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -391,7 +391,7 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) unsigned int i; phdr = (Elf64_Phdr *)(ehdr + 1); - for (i = 0; i < ehdr->e_phnum; i++) { + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { if (phdr->p_paddr == BACKUP_SRC_START) { phdr->p_offset = image->arch.backup_start; kexec_dprintk("Backup region offset updated to 0x%lx\n", From 9103787054c685b6bbe242d4e3911714092b4c2b Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Thu, 12 Mar 2026 14:00:50 +0530 Subject: [PATCH 0302/1518] powerpc/crash: Update backup region offset in elfcorehdr on memory hotplug [ Upstream commit f53b24d1fa263f56155213eabab734c18d884aff ] When elfcorehdr is prepared for kdump, the program header representing the first 64 KB of memory is expected to have its offset point to the backup region. This is required because purgatory copies the first 64 KB of the crashed kernel memory to this backup region following a kernel crash. This allows the capture kernel to use the first 64 KB of memory to place the exception vectors and other required data. When elfcorehdr is recreated due to memory hotplug, the offset of the program header representing the first 64 KB is not updated. As a result, the capture kernel exports the first 64 KB at offset 0, even though the data actually resides in the backup region. Fix this by calling sync_backup_region_phdr() to update the program header offset in the elfcorehdr created during memory hotplug. sync_backup_region_phdr() works for images loaded via the kexec_file_load syscall. However, it does not work for kexec_load, because image->arch.backup_start is not initialized in that case. So introduce machine_kexec_post_load() to process the elfcorehdr prepared by kexec-tools and initialize image->arch.backup_start for kdump images loaded via kexec_load syscall. Rename update_backup_region_phdr() to sync_backup_region_phdr() and extend it to synchronize the backup region offset between the kdump image and the ELF core header. The helper now supports updating either the kdump image from the ELF program header or updating the ELF program header from the kdump image, avoiding code duplication. Define ARCH_HAS_KIMAGE_ARCH and struct kimage_arch when CONFIG_KEXEC_FILE or CONFIG_CRASH_DUMP is enabled so that kimage->arch.backup_start is available with the kexec_load system call. This patch depends on the patch titled "powerpc/crash: fix backup region offset update to elfcorehdr". Fixes: 849599b702ef ("powerpc/crash: add crash memory hotplug support") Reviewed-by: Aditya Gupta Signed-off-by: Sourabh Jain Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260312083051.1935737-3-sourabhjain@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/kexec.h | 14 +++++-- arch/powerpc/kexec/crash.c | 64 +++++++++++++++++++++++++++++++ arch/powerpc/kexec/file_load_64.c | 29 +------------- 3 files changed, 76 insertions(+), 31 deletions(-) diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 4bbf9f699aaaf..d3b5028102cdd 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -66,11 +66,9 @@ void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_co unsigned long start_address) __noreturn; void kexec_copy_flush(struct kimage *image); -#ifdef CONFIG_KEXEC_FILE -extern const struct kexec_file_ops kexec_elf64_ops; +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) #define ARCH_HAS_KIMAGE_ARCH - struct kimage_arch { struct crash_mem *exclude_ranges; @@ -78,6 +76,10 @@ struct kimage_arch { void *backup_buf; void *fdt; }; +#endif + +#ifdef CONFIG_KEXEC_FILE +extern const struct kexec_file_ops kexec_elf64_ops; char *setup_kdump_cmdline(struct kimage *image, char *cmdline, unsigned long cmdline_len); @@ -143,6 +145,10 @@ int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); unsigned int arch_crash_get_elfcorehdr_size(void); #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size + +int machine_kexec_post_load(struct kimage *image); +#define machine_kexec_post_load machine_kexec_post_load + #endif /* CONFIG_CRASH_HOTPLUG */ extern int crashing_cpu; @@ -157,6 +163,8 @@ extern void default_machine_crash_shutdown(struct pt_regs *regs); extern void crash_kexec_prepare(void); extern void crash_kexec_secondary(struct pt_regs *regs); +extern void sync_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr, + bool phdr_to_kimage); static inline bool kdump_in_progress(void) { return crashing_cpu >= 0; diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index a325c1c02f96d..e6539f213b3d1 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * The primary CPU waits a while for all secondary CPUs to enter. This is to @@ -399,7 +400,68 @@ void default_machine_crash_shutdown(struct pt_regs *regs) ppc_md.kexec_cpu_down(1, 0); } +#ifdef CONFIG_CRASH_DUMP +/** + * sync_backup_region_phdr - synchronize backup region offset between + * kexec image and ELF core header. + * @image: Kexec image. + * @ehdr: ELF core header. + * @phdr_to_kimage: If true, read the offset from the ELF program header + * and update the kimage backup region. If false, update + * the ELF program header offset from the kimage backup + * region. + * + * Note: During kexec_load, this is called with phdr_to_kimage = true. For + * kexec_file_load and ELF core header recreation during memory hotplug + * events, it is called with phdr_to_kimage = false. + * + * Returns nothing. + */ +void sync_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr, bool phdr_to_kimage) +{ + Elf64_Phdr *phdr; + unsigned int i; + + phdr = (Elf64_Phdr *)(ehdr + 1); + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { + if (phdr->p_paddr == BACKUP_SRC_START) { + if (phdr_to_kimage) + image->arch.backup_start = phdr->p_offset; + else + phdr->p_offset = image->arch.backup_start; + + kexec_dprintk("Backup region offset updated to 0x%lx\n", + image->arch.backup_start); + return; + } + } +} +#endif /* CONFIG_CRASH_DUMP */ + #ifdef CONFIG_CRASH_HOTPLUG + +int machine_kexec_post_load(struct kimage *image) +{ + int i; + unsigned long mem; + unsigned char *ptr; + + if (image->type != KEXEC_TYPE_CRASH) + return 0; + + if (image->file_mode) + return 0; + + for (i = 0; i < image->nr_segments; i++) { + mem = image->segment[i].mem; + ptr = (char *)__va(mem); + + if (ptr && memcmp(ptr, ELFMAG, SELFMAG) == 0) + sync_backup_region_phdr(image, (Elf64_Ehdr *) ptr, true); + } + return 0; +} + #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt @@ -474,6 +536,8 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * goto out; } + sync_backup_region_phdr(image, (Elf64_Ehdr *) elfbuf, false); + ptr = __va(mem); if (ptr) { /* Temporarily invalidate the crash image while it is replaced */ diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index a7db7eca0481b..8c72e12ea44e5 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -374,33 +374,6 @@ static int load_backup_segment(struct kimage *image, struct kexec_buf *kbuf) return 0; } -/** - * update_backup_region_phdr - Update backup region's offset for the core to - * export the region appropriately. - * @image: Kexec image. - * @ehdr: ELF core header. - * - * Assumes an exclusive program header is setup for the backup region - * in the ELF headers - * - * Returns nothing. - */ -static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) -{ - Elf64_Phdr *phdr; - unsigned int i; - - phdr = (Elf64_Phdr *)(ehdr + 1); - for (i = 0; i < ehdr->e_phnum; i++, phdr++) { - if (phdr->p_paddr == BACKUP_SRC_START) { - phdr->p_offset = image->arch.backup_start; - kexec_dprintk("Backup region offset updated to 0x%lx\n", - image->arch.backup_start); - return; - } - } -} - static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem) { #if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG) @@ -445,7 +418,7 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) } /* Fix the offset for backup region in the ELF header */ - update_backup_region_phdr(image, headers); + sync_backup_region_phdr(image, headers, false); kbuf->buffer = headers; kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; From d41508adff0125f75df03290000cb1d615983650 Mon Sep 17 00:00:00 2001 From: Amit Machhiwal Date: Fri, 13 Mar 2026 22:24:26 +0530 Subject: [PATCH 0303/1518] selftests/powerpc: Suppress -Wmaybe-uninitialized with GCC 15 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6e65886fceb23605eff952d6b1975737b4c4b154 ] GCC 15 reports the below false positive '-Wmaybe-uninitialized' warning in vphn_unpack_associativity() when building the powerpc selftests. # make -C tools/testing/selftests TARGETS="powerpc" [...] CC test-vphn In file included from test-vphn.c:3: In function ‘vphn_unpack_associativity’, inlined from ‘test_one’ at test-vphn.c:371:2, inlined from ‘test_vphn’ at test-vphn.c:399:9: test-vphn.c:10:33: error: ‘be_packed’ may be used uninitialized [-Werror=maybe-uninitialized] 10 | #define be16_to_cpup(x) bswap_16(*x) | ^~~~~~~~ vphn.c:42:27: note: in expansion of macro ‘be16_to_cpup’ 42 | u16 new = be16_to_cpup(field++); | ^~~~~~~~~~~~ In file included from test-vphn.c:19: vphn.c: In function ‘test_vphn’: vphn.c:27:16: note: ‘be_packed’ declared here 27 | __be64 be_packed[VPHN_REGISTER_COUNT]; | ^~~~~~~~~ cc1: all warnings being treated as errors When vphn_unpack_associativity() is called from hcall_vphn() in kernel the error is not seen while building vphn.c during kernel compilation. This is because the top level Makefile includes '-fno-strict-aliasing' flag always. The issue here is that GCC 15 emits '-Wmaybe-uninitialized' due to type punning between __be64[] and __b16* when accessing the buffer via be16_to_cpup(). The underlying object is fully initialized but GCC 15 fails to track the aliasing due to the strict aliasing violation here. Please refer [1] and [2]. This results in a false positive warning which is promoted to an error under '-Werror'. This problem is not seen when the compilation is performed with GCC 13 and 14. An issue [1] has also been created on GCC bugzilla. The selftest compiles fine with '-fno-strict-aliasing'. Since this GCC flag is used to compile vphn.c in kernel too, the same flag should be used to build vphn tests when compiling vphn.c in the selftest as well. Fix this by including '-fno-strict-aliasing' during vphn.c compilation in the selftest. This keeps the build working while limiting the scope of the suppression to building vphn tests. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124427 [2] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99768 Fixes: 58dae82843f5 ("selftests/powerpc: Add test for VPHN") Reviewed-by: Vaibhav Jain Signed-off-by: Amit Machhiwal Tested-by: Venkat Rao Bagalkote Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260313165426.43259-1-amachhiw@linux.ibm.com Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/vphn/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile index 61d519a076c6f..778fc396340db 100644 --- a/tools/testing/selftests/powerpc/vphn/Makefile +++ b/tools/testing/selftests/powerpc/vphn/Makefile @@ -5,7 +5,7 @@ top_srcdir = ../../../../.. include ../../lib.mk include ../flags.mk -CFLAGS += -m64 -I$(CURDIR) +CFLAGS += -m64 -I$(CURDIR) -fno-strict-aliasing $(TEST_GEN_PROGS): ../harness.c From b312cf41b9e43f442613053f6cad39898e1baf96 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Tue, 31 Mar 2026 22:53:52 +0800 Subject: [PATCH 0304/1518] bpf: Fix abuse of kprobe_write_ctx via freplace [ Upstream commit 611fe4b79af72d00d80f2223354284447daafae9 ] uprobe programs are allowed to modify struct pt_regs. Since the actual program type of uprobe is KPROBE, it can be abused to modify struct pt_regs via kprobe+freplace when the kprobe attaches to kernel functions. For example, SEC("?kprobe") int kprobe(struct pt_regs *regs) { return 0; } SEC("?freplace") int freplace_kprobe(struct pt_regs *regs) { regs->di = 0; return 0; } freplace_kprobe prog will attach to kprobe prog. kprobe prog will attach to a kernel function. Without this patch, when the kernel function runs, its first arg will always be set as 0 via the freplace_kprobe prog. To fix the abuse of kprobe_write_ctx=true via kprobe+freplace, disallow attaching freplace programs on kprobe programs with different kprobe_write_ctx values. Fixes: 7384893d970e ("bpf: Allow uprobe program to change context registers") Acked-by: Jiri Olsa Acked-by: Song Liu Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260331145353.87606-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/syscall.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 586ece78f783a..ff268fd2ff8b5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3708,6 +3708,23 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, tr = prog->aux->dst_trampoline; tgt_prog = prog->aux->dst_prog; } + /* + * It is to prevent modifying struct pt_regs via kprobe_write_ctx=true + * freplace prog. Without this check, kprobe_write_ctx=true freplace + * prog is allowed to attach to kprobe_write_ctx=false kprobe prog, and + * then modify the registers of the kprobe prog's target kernel + * function. + * + * This also blocks the combination of uprobe+freplace, because it is + * unable to recognize the use of the tgt_prog as an uprobe or a kprobe + * by tgt_prog itself. At attach time, uprobe/kprobe is recognized by + * the target perf event flags in __perf_event_set_bpf_prog(). + */ + if (prog->type == BPF_PROG_TYPE_EXT && + prog->aux->kprobe_write_ctx != tgt_prog->aux->kprobe_write_ctx) { + err = -EINVAL; + goto out_unlock; + } err = bpf_link_prime(&link->link.link, &link_primer); if (err) From d3d3d2791c59d42d5c9f5759c944647edff5f8a8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 Apr 2026 10:38:08 +0000 Subject: [PATCH 0305/1518] macvlan: annotate data-races around port->bc_queue_len_used [ Upstream commit 1ef5789d9906df3771c99b7f413caaf2bf473ca5 ] port->bc_queue_len_used is read and written locklessly, add READ_ONCE()/WRITE_ONCE() annotations. While WRITE_ONCE() in macvlan_fill_info() is not yet needed, it is a prereq for future RTNL avoidance. Fixes: d4bff72c8401 ("macvlan: Support for high multicast packet rate") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260401103809.3038139-2-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/macvlan.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 4433b8e95b6ac..e9d288a05e39e 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -352,6 +352,7 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { + u32 bc_queue_len_used = READ_ONCE(port->bc_queue_len_used); struct sk_buff *nskb; int err = -ENOMEM; @@ -362,7 +363,7 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port, MACVLAN_SKB_CB(nskb)->src = src; spin_lock(&port->bc_queue.lock); - if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) { + if (skb_queue_len(&port->bc_queue) < bc_queue_len_used) { if (src) dev_hold(src->dev); __skb_queue_tail(&port->bc_queue, nskb); @@ -1727,7 +1728,8 @@ static int macvlan_fill_info(struct sk_buff *skb, } if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req)) goto nla_put_failure; - if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used)) + if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, + READ_ONCE(port->bc_queue_len_used))) goto nla_put_failure; if (port->bc_cutoff != 1 && nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, port->bc_cutoff)) @@ -1787,7 +1789,7 @@ static void update_port_bc_queue_len(struct macvlan_port *port) if (vlan->bc_queue_len_req > max_bc_queue_len_req) max_bc_queue_len_req = vlan->bc_queue_len_req; } - port->bc_queue_len_used = max_bc_queue_len_req; + WRITE_ONCE(port->bc_queue_len_used, max_bc_queue_len_req); } static int macvlan_device_event(struct notifier_block *unused, From 32ce55d424395904986f5066f8755f6cb9993377 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Fri, 3 Apr 2026 21:29:50 +0800 Subject: [PATCH 0306/1518] bpf: fix end-of-list detection in cgroup_storage_get_next_key() [ Upstream commit 5828b9e5b272ecff7cf5d345128d3de7324117f7 ] list_next_entry() never returns NULL -- when the current element is the last entry it wraps to the list head via container_of(). The subsequent NULL check is therefore dead code and get_next_key() never returns -ENOENT for the last element, instead reading storage->key from a bogus pointer that aliases internal map fields and copying the result to userspace. Replace it with list_entry_is_head() so the function correctly returns -ENOENT when there are no more entries. Fixes: de9cbbaadba5 ("bpf: introduce cgroup storage maps") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Reviewed-by: Sun Jian Acked-by: Paul Chaignon Link: https://lore.kernel.org/r/20260403132951.43533-2-bestswngs@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/local_storage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c93a756e035c0..b8db4fbd3bd2a 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -259,7 +259,7 @@ static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key, goto enoent; storage = list_next_entry(storage, list_map); - if (!storage) + if (list_entry_is_head(storage, &map->list, list_map)) goto enoent; } else { storage = list_first_entry(&map->list, From 059525cf18e69a9313baf947d8898c6ee7ca6b65 Mon Sep 17 00:00:00 2001 From: MingTao Huang Date: Thu, 2 Apr 2026 20:18:50 +0800 Subject: [PATCH 0307/1518] bpf: Fix stale offload->prog pointer after constant blinding [ Upstream commit a1aa9ef47c299c5bbc30594d3c2f0589edf908e6 ] When a dev-bound-only BPF program (BPF_F_XDP_DEV_BOUND_ONLY) undergoes JIT compilation with constant blinding enabled (bpf_jit_harden >= 2), bpf_jit_blind_constants() clones the program. The original prog is then freed in bpf_jit_prog_release_other(), which updates aux->prog to point to the surviving clone, but fails to update offload->prog. This leaves offload->prog pointing to the freed original program. When the network namespace is subsequently destroyed, cleanup_net() triggers bpf_dev_bound_netdev_unregister(), which iterates ondev->progs and calls __bpf_prog_offload_destroy(offload->prog). Accessing the freed prog causes a page fault: BUG: unable to handle page fault for address: ffffc900085f1038 Workqueue: netns cleanup_net RIP: 0010:__bpf_prog_offload_destroy+0xc/0x80 Call Trace: __bpf_offload_dev_netdev_unregister+0x257/0x350 bpf_dev_bound_netdev_unregister+0x4a/0x90 unregister_netdevice_many_notify+0x2a2/0x660 ... cleanup_net+0x21a/0x320 The test sequence that triggers this reliably is: 1. Set net.core.bpf_jit_harden=2 (echo 2 > /proc/sys/net/core/bpf_jit_harden) 2. Run xdp_metadata selftest, which creates a dev-bound-only XDP program on a veth inside a netns (./test_progs -t xdp_metadata) 3. cleanup_net -> page fault in __bpf_prog_offload_destroy Dev-bound-only programs are unique in that they have an offload structure but go through the normal JIT path instead of bpf_prog_offload_compile(). This means they are subject to constant blinding's prog clone-and-replace, while also having offload->prog that must stay in sync. Fix this by updating offload->prog in bpf_jit_prog_release_other(), alongside the existing aux->prog update. Both are back-pointers to the prog that must be kept in sync when the prog is replaced. Fixes: 2b3486bc2d23 ("bpf: Introduce device-bound XDP programs") Signed-off-by: MingTao Huang Link: https://lore.kernel.org/r/tencent_BCF692F45859CCE6C22B7B0B64827947D406@qq.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 8de006d388f67..931a4ddd8530c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1468,6 +1468,8 @@ void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) * know whether fp here is the clone or the original. */ fp->aux->prog = fp; + if (fp->aux->offload) + fp->aux->offload->prog = fp; bpf_prog_clone_free(fp_other); } From 2bbe3d5c93534927b47dc26abe23704b0f2b38b0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 2 Apr 2026 20:46:53 +0200 Subject: [PATCH 0308/1518] net: ethernet: ti-cpsw:: rename soft_reset() function [ Upstream commit 961f3c535608df64553f61d64ca086aa9f371bdd ] While looking at the glob symbols shared between the cpsw drivers, I noticed that soft_reset() is the only one that is missing a proper namespace prefix, and will pollute the kernel namespace, so rename it to be consistent with the other symbols. Reviewed-by: Alexander Sverdlin Signed-off-by: Arnd Bergmann Link: https://patch.msgid.link/20260402184726.3746487-1-arnd@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: df75bd552a87 ("net: ethernet: ti-cpsw: fix linking built-in code to modules") Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/cpsw.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index b0e18bdc2c851..aa3531e844e87 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -706,7 +706,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) struct cpsw_common *cpsw = priv->cpsw; /* soft reset the controller and initialize ale */ - soft_reset("cpsw", &cpsw->regs->soft_reset); + cpsw_soft_reset("cpsw", &cpsw->regs->soft_reset); cpsw_ale_start(cpsw->ale); /* switch to vlan aware mode */ diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index fd3931d667021..c6cf7a0375e08 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -573,7 +573,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) u32 control_reg; /* soft reset the controller and initialize ale */ - soft_reset("cpsw", &cpsw->regs->soft_reset); + cpsw_soft_reset("cpsw", &cpsw->regs->soft_reset); cpsw_ale_start(cpsw->ale); /* switch to vlan aware mode */ diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index bc4fdf17a99ec..c6eb6b785b0b5 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -275,7 +275,7 @@ void cpsw_set_slave_mac(struct cpsw_slave *slave, struct cpsw_priv *priv) slave_write(slave, mac_lo(priv->mac_addr), SA_LO); } -void soft_reset(const char *module, void __iomem *reg) +void cpsw_soft_reset(const char *module, void __iomem *reg) { unsigned long timeout = jiffies + HZ; diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index acb6181c5c9e1..fddd7a79f4b0f 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -458,7 +458,7 @@ int cpsw_tx_poll(struct napi_struct *napi_tx, int budget); int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget); int cpsw_rx_poll(struct napi_struct *napi_rx, int budget); void cpsw_rx_vlan_encap(struct sk_buff *skb); -void soft_reset(const char *module, void __iomem *reg); +void cpsw_soft_reset(const char *module, void __iomem *reg); void cpsw_set_slave_mac(struct cpsw_slave *slave, struct cpsw_priv *priv); void cpsw_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue); int cpsw_need_resplit(struct cpsw_common *cpsw); From a710df104abbb5435db4d2618aad6b09b0e81ca0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 2 Apr 2026 20:46:54 +0200 Subject: [PATCH 0309/1518] net: ethernet: ti-cpsw: fix linking built-in code to modules [ Upstream commit df75bd552a8790e83d4aeb5f112050cf3dc687bf ] There are six variants of the cpsw driver, sharing various parts of the code: davinci-emac, cpsw, cpsw-switchdev, netcp, netcp_ethss and am65-cpsw-nuss. I noticed that this means some files can be linked into more than one loadable module, or even part of vmlinux but also linked into a loadable module, both of which mess up assumptions of the build system, and causes warnings: scripts/Makefile.build:279: cpsw_ale.o is added to multiple modules: ti-am65-cpsw-nuss ti_cpsw ti_cpsw_new scripts/Makefile.build:279: cpsw_priv.o is added to multiple modules: ti_cpsw ti_cpsw_new scripts/Makefile.build:279: cpsw_sl.o is added to multiple modules: ti-am65-cpsw-nuss ti_cpsw ti_cpsw_new scripts/Makefile.build:279: cpsw_ethtool.o is added to multiple modules: ti_cpsw ti_cpsw_new scripts/Makefile.build:279: davinci_cpdma.o is added to multiple modules: ti_cpsw ti_cpsw_new ti_davinci_emac Change this back to having separate modules for each portion that can be linked standalone, exporting symbols as needed: - ti-cpsw-common.ko now contains both cpsw-common.o and davinci_cpdma.o as they are always used together - ti-cpsw-priv.ko contains cpsw_priv.o, cpsw_sl.o and cpsw_ethtool.o, which are the core of the cpsw and cpsw-new drivers. - ti-cpsw-sl.ko contains the cpsw-sl.o object and is used on ti-am65-cpsw-nuss.ko in addition to the two other cpsw variants. - ti-cpsw-ale.o is the one standalone module that is used by all except davinci_emac. Each of these will be built-in if any of its users are built-in, otherwise it's a loadable module if there is at least one module using it. I did not bring back the separate Kconfig symbols for this, but just handle it using Makefile logic. Note: ideally this is something that Kbuild complains about, but usually we just notice when something using THIS_MODULE misbehaves in a way that a user notices. Fixes: 99f6297182729 ("net: ethernet: ti: cpsw: drop TI_DAVINCI_CPDMA config option") Link: https://lore.kernel.org/lkml/20240417084400.3034104-1-arnd@kernel.org/ Signed-off-by: Arnd Bergmann Link: https://patch.msgid.link/20260402184726.3746487-2-arnd@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/Makefile | 30 ++++++++++---------- drivers/net/ethernet/ti/cpsw_ale.c | 25 +++++++++++++++++ drivers/net/ethernet/ti/cpsw_ethtool.c | 24 ++++++++++++++++ drivers/net/ethernet/ti/cpsw_priv.c | 37 +++++++++++++++++++++++++ drivers/net/ethernet/ti/cpsw_sl.c | 11 ++++++++ drivers/net/ethernet/ti/davinci_cpdma.c | 27 ++++++++++++++++++ 6 files changed, 139 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 93c0a4d0e33a6..fec6ba62c0303 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -6,30 +6,30 @@ obj-$(CONFIG_TI_PRUETH) += icssm-prueth.o icssm-prueth-y := icssm/icssm_prueth.o -obj-$(CONFIG_TI_CPSW) += cpsw-common.o -obj-$(CONFIG_TI_DAVINCI_EMAC) += cpsw-common.o -obj-$(CONFIG_TI_CPSW_SWITCHDEV) += cpsw-common.o +ti-cpsw-common-y += cpsw-common.o davinci_cpdma.o +ti-cpsw-priv-y += cpsw_priv.o cpsw_ethtool.o +ti-cpsw-ale-y += cpsw_ale.o +ti-cpsw-sl-y += cpsw_sl.o obj-$(CONFIG_TLAN) += tlan.o -obj-$(CONFIG_TI_DAVINCI_EMAC) += ti_davinci_emac.o -ti_davinci_emac-y := davinci_emac.o davinci_cpdma.o +obj-$(CONFIG_TI_DAVINCI_EMAC) += davinci_emac.o ti-cpsw-common.o obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o obj-$(CONFIG_TI_CPTS) += cpts.o -obj-$(CONFIG_TI_CPSW) += ti_cpsw.o -ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o -obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o -ti_cpsw_new-y := cpsw_switchdev.o cpsw_new.o davinci_cpdma.o cpsw_ale.o cpsw_sl.o cpsw_priv.o cpsw_ethtool.o +obj-$(CONFIG_TI_CPSW) += ti_cpsw.o ti-cpsw-common.o ti-cpsw-priv.o ti-cpsw-ale.o ti-cpsw-sl.o +ti_cpsw-y := cpsw.o +obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o ti-cpsw-common.o ti-cpsw-priv.o ti-cpsw-ale.o ti-cpsw-sl.o +ti_cpsw_new-y := cpsw_switchdev.o cpsw_new.o -obj-$(CONFIG_TI_KEYSTONE_NETCP) += keystone_netcp.o -keystone_netcp-y := netcp_core.o cpsw_ale.o -obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o -keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.o +obj-$(CONFIG_TI_KEYSTONE_NETCP) += keystone_netcp.o ti-cpsw-ale.o +keystone_netcp-y := netcp_core.o +obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o ti-cpsw-ale.o +keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o obj-$(CONFIG_TI_K3_CPPI_DESC_POOL) += k3-cppi-desc-pool.o -obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o -ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o +obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o ti-cpsw-sl.o ti-cpsw-ale.o +ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o am65-cpsw-ethtool.o ti-am65-cpsw-nuss-$(CONFIG_TI_AM65_CPSW_QOS) += am65-cpsw-qos.o ti-am65-cpsw-nuss-$(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV) += am65-cpsw-switchdev.o obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 9632ad3741de1..7fb1488ca0025 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -498,6 +498,7 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) } return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_flush_multicast); static inline void cpsw_ale_set_vlan_entry_type(u32 *ale_entry, int flags, u16 vid) @@ -535,6 +536,7 @@ int cpsw_ale_add_ucast(struct cpsw_ale *ale, const u8 *addr, int port, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_add_ucast); int cpsw_ale_del_ucast(struct cpsw_ale *ale, const u8 *addr, int port, int flags, u16 vid) @@ -550,6 +552,7 @@ int cpsw_ale_del_ucast(struct cpsw_ale *ale, const u8 *addr, int port, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_del_ucast); int cpsw_ale_add_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask, int flags, u16 vid, int mcast_state) @@ -583,6 +586,7 @@ int cpsw_ale_add_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_add_mcast); int cpsw_ale_del_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask, int flags, u16 vid) @@ -612,6 +616,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_del_mcast); /* ALE NetCP NU switch specific vlan functions */ static void cpsw_ale_set_vlan_mcast(struct cpsw_ale *ale, u32 *ale_entry, @@ -681,6 +686,7 @@ int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port_mask, int untag, cpsw_ale_write(ale, idx, ale_entry); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_add_vlan); static void cpsw_ale_vlan_del_modify_int(struct cpsw_ale *ale, u32 *ale_entry, u16 vid, int port_mask) @@ -738,6 +744,7 @@ int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask) return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_vlan_del_modify); int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) { @@ -772,6 +779,7 @@ int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_del_vlan); int cpsw_ale_vlan_add_modify(struct cpsw_ale *ale, u16 vid, int port_mask, int untag_mask, int reg_mask, int unreg_mask) @@ -811,6 +819,7 @@ int cpsw_ale_vlan_add_modify(struct cpsw_ale *ale, u16 vid, int port_mask, return ret; } +EXPORT_SYMBOL_GPL(cpsw_ale_vlan_add_modify); void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask, bool add) @@ -838,6 +847,7 @@ void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask, cpsw_ale_write(ale, idx, ale_entry); } } +EXPORT_SYMBOL_GPL(cpsw_ale_set_unreg_mcast); static void cpsw_ale_vlan_set_unreg_mcast(struct cpsw_ale *ale, u32 *ale_entry, int allmulti) @@ -903,6 +913,7 @@ void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port) cpsw_ale_write(ale, idx, ale_entry); } } +EXPORT_SYMBOL_GPL(cpsw_ale_set_allmulti); struct ale_control_info { const char *name; @@ -1160,6 +1171,7 @@ int cpsw_ale_control_set(struct cpsw_ale *ale, int port, int control, return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_control_set); int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control) { @@ -1183,6 +1195,7 @@ int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control) tmp = readl_relaxed(ale->params.ale_regs + offset) >> shift; return tmp & BITMASK(info->bits); } +EXPORT_SYMBOL_GPL(cpsw_ale_control_get); int cpsw_ale_rx_ratelimit_mc(struct cpsw_ale *ale, int port, unsigned int ratelimit_pps) @@ -1205,6 +1218,7 @@ int cpsw_ale_rx_ratelimit_mc(struct cpsw_ale *ale, int port, unsigned int rateli port, val * ALE_RATE_LIMIT_MIN_PPS); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_rx_ratelimit_mc); int cpsw_ale_rx_ratelimit_bc(struct cpsw_ale *ale, int port, unsigned int ratelimit_pps) @@ -1227,6 +1241,7 @@ int cpsw_ale_rx_ratelimit_bc(struct cpsw_ale *ale, int port, unsigned int rateli port, val * ALE_RATE_LIMIT_MIN_PPS); return 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_rx_ratelimit_bc); static void cpsw_ale_timer(struct timer_list *t) { @@ -1316,6 +1331,7 @@ void cpsw_ale_start(struct cpsw_ale *ale) cpsw_ale_aging_start(ale); } +EXPORT_SYMBOL_GPL(cpsw_ale_start); void cpsw_ale_stop(struct cpsw_ale *ale) { @@ -1323,6 +1339,7 @@ void cpsw_ale_stop(struct cpsw_ale *ale) cpsw_ale_control_set(ale, 0, ALE_CLEAR, 1); cpsw_ale_control_set(ale, 0, ALE_ENABLE, 0); } +EXPORT_SYMBOL_GPL(cpsw_ale_stop); static const struct reg_field ale_fields_cpsw[] = { /* CPSW_ALE_IDVER_REG */ @@ -1623,6 +1640,7 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params) cpsw_ale_control_set(ale, 0, ALE_CLEAR, 1); return ale; } +EXPORT_SYMBOL_GPL(cpsw_ale_create); void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data) { @@ -1633,6 +1651,7 @@ void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data) data += ALE_ENTRY_WORDS; } } +EXPORT_SYMBOL_GPL(cpsw_ale_dump); void cpsw_ale_restore(struct cpsw_ale *ale, u32 *data) { @@ -1643,11 +1662,13 @@ void cpsw_ale_restore(struct cpsw_ale *ale, u32 *data) data += ALE_ENTRY_WORDS; } } +EXPORT_SYMBOL_GPL(cpsw_ale_restore); u32 cpsw_ale_get_num_entries(struct cpsw_ale *ale) { return ale ? ale->params.ale_entries : 0; } +EXPORT_SYMBOL_GPL(cpsw_ale_get_num_entries); /* Reads the specified policer index into ALE POLICER registers */ static void cpsw_ale_policer_read_idx(struct cpsw_ale *ale, u32 idx) @@ -1750,3 +1771,7 @@ void cpsw_ale_classifier_setup_default(struct cpsw_ale *ale, int num_rx_ch) 1); } } +EXPORT_SYMBOL_GPL(cpsw_ale_classifier_setup_default); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("TI N-Port Ethernet Switch Address Lookup Engine"); diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index bdc4db0d169c4..6350031e976f7 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -144,6 +144,7 @@ u32 cpsw_get_msglevel(struct net_device *ndev) return priv->msg_enable; } +EXPORT_SYMBOL_GPL(cpsw_get_msglevel); void cpsw_set_msglevel(struct net_device *ndev, u32 value) { @@ -151,6 +152,7 @@ void cpsw_set_msglevel(struct net_device *ndev, u32 value) priv->msg_enable = value; } +EXPORT_SYMBOL_GPL(cpsw_set_msglevel); int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, struct kernel_ethtool_coalesce *kernel_coal, @@ -161,6 +163,7 @@ int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, coal->rx_coalesce_usecs = cpsw->coal_intvl; return 0; } +EXPORT_SYMBOL_GPL(cpsw_get_coalesce); int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, struct kernel_ethtool_coalesce *kernel_coal, @@ -220,6 +223,7 @@ int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, return 0; } +EXPORT_SYMBOL_GPL(cpsw_set_coalesce); int cpsw_get_sset_count(struct net_device *ndev, int sset) { @@ -234,6 +238,7 @@ int cpsw_get_sset_count(struct net_device *ndev, int sset) return -EOPNOTSUPP; } } +EXPORT_SYMBOL_GPL(cpsw_get_sset_count); static void cpsw_add_ch_strings(u8 **p, int ch_num, int rx_dir) { @@ -271,6 +276,7 @@ void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data) break; } } +EXPORT_SYMBOL_GPL(cpsw_get_strings); void cpsw_get_ethtool_stats(struct net_device *ndev, struct ethtool_stats *stats, u64 *data) @@ -303,6 +309,7 @@ void cpsw_get_ethtool_stats(struct net_device *ndev, } } } +EXPORT_SYMBOL_GPL(cpsw_get_ethtool_stats); void cpsw_get_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) @@ -313,6 +320,7 @@ void cpsw_get_pauseparam(struct net_device *ndev, pause->rx_pause = priv->rx_pause ? true : false; pause->tx_pause = priv->tx_pause ? true : false; } +EXPORT_SYMBOL_GPL(cpsw_get_pauseparam); void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { @@ -326,6 +334,7 @@ void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) if (cpsw->slaves[slave_no].phy) phy_ethtool_get_wol(cpsw->slaves[slave_no].phy, wol); } +EXPORT_SYMBOL_GPL(cpsw_get_wol); int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { @@ -338,6 +347,7 @@ int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) else return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(cpsw_set_wol); int cpsw_get_regs_len(struct net_device *ndev) { @@ -346,6 +356,7 @@ int cpsw_get_regs_len(struct net_device *ndev) return cpsw_ale_get_num_entries(cpsw->ale) * ALE_ENTRY_WORDS * sizeof(u32); } +EXPORT_SYMBOL_GPL(cpsw_get_regs_len); void cpsw_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *p) { @@ -357,6 +368,7 @@ void cpsw_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *p) cpsw_ale_dump(cpsw->ale, reg); } +EXPORT_SYMBOL_GPL(cpsw_get_regs); int cpsw_ethtool_op_begin(struct net_device *ndev) { @@ -370,6 +382,7 @@ int cpsw_ethtool_op_begin(struct net_device *ndev) return ret; } +EXPORT_SYMBOL_GPL(cpsw_ethtool_op_begin); void cpsw_ethtool_op_complete(struct net_device *ndev) { @@ -380,6 +393,7 @@ void cpsw_ethtool_op_complete(struct net_device *ndev) if (ret < 0) cpsw_err(priv, drv, "ethtool complete failed %d\n", ret); } +EXPORT_SYMBOL_GPL(cpsw_ethtool_op_complete); void cpsw_get_channels(struct net_device *ndev, struct ethtool_channels *ch) { @@ -394,6 +408,7 @@ void cpsw_get_channels(struct net_device *ndev, struct ethtool_channels *ch) ch->tx_count = cpsw->tx_ch_num; ch->combined_count = 0; } +EXPORT_SYMBOL_GPL(cpsw_get_channels); int cpsw_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *ecmd) @@ -408,6 +423,7 @@ int cpsw_get_link_ksettings(struct net_device *ndev, phy_ethtool_ksettings_get(cpsw->slaves[slave_no].phy, ecmd); return 0; } +EXPORT_SYMBOL_GPL(cpsw_get_link_ksettings); int cpsw_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *ecmd) @@ -421,6 +437,7 @@ int cpsw_set_link_ksettings(struct net_device *ndev, return phy_ethtool_ksettings_set(cpsw->slaves[slave_no].phy, ecmd); } +EXPORT_SYMBOL_GPL(cpsw_set_link_ksettings); int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { @@ -433,6 +450,7 @@ int cpsw_get_eee(struct net_device *ndev, struct ethtool_keee *edata) else return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(cpsw_get_eee); int cpsw_nway_reset(struct net_device *ndev) { @@ -445,6 +463,7 @@ int cpsw_nway_reset(struct net_device *ndev) else return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(cpsw_nway_reset); static void cpsw_suspend_data_pass(struct net_device *ndev) { @@ -642,6 +661,7 @@ int cpsw_set_channels_common(struct net_device *ndev, cpsw_fail(cpsw); return ret; } +EXPORT_SYMBOL_GPL(cpsw_set_channels_common); void cpsw_get_ringparam(struct net_device *ndev, struct ethtool_ringparam *ering, @@ -657,6 +677,7 @@ void cpsw_get_ringparam(struct net_device *ndev, ering->rx_max_pending = cpsw->descs_pool_size - CPSW_MAX_QUEUES; ering->rx_pending = cpdma_get_num_rx_descs(cpsw->dma); } +EXPORT_SYMBOL_GPL(cpsw_get_ringparam); int cpsw_set_ringparam(struct net_device *ndev, struct ethtool_ringparam *ering, @@ -703,6 +724,7 @@ int cpsw_set_ringparam(struct net_device *ndev, cpsw_fail(cpsw); return ret; } +EXPORT_SYMBOL_GPL(cpsw_set_ringparam); #if IS_ENABLED(CONFIG_TI_CPTS) int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *info) @@ -723,6 +745,7 @@ int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *inf (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); return 0; } +EXPORT_SYMBOL_GPL(cpsw_get_ts_info); #else int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *info) { @@ -732,4 +755,5 @@ int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *inf info->rx_filters = 0; return 0; } +EXPORT_SYMBOL_GPL(cpsw_get_ts_info); #endif diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index c6eb6b785b0b5..1f6f374551cb6 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -32,6 +32,7 @@ #define CPTS_N_ETX_TS 4 int (*cpsw_slave_index)(struct cpsw_common *cpsw, struct cpsw_priv *priv); +EXPORT_SYMBOL_GPL(cpsw_slave_index); void cpsw_intr_enable(struct cpsw_common *cpsw) { @@ -40,6 +41,7 @@ void cpsw_intr_enable(struct cpsw_common *cpsw) cpdma_ctlr_int_ctrl(cpsw->dma, true); } +EXPORT_SYMBOL_GPL(cpsw_intr_enable); void cpsw_intr_disable(struct cpsw_common *cpsw) { @@ -48,6 +50,7 @@ void cpsw_intr_disable(struct cpsw_common *cpsw) cpdma_ctlr_int_ctrl(cpsw->dma, false); } +EXPORT_SYMBOL_GPL(cpsw_intr_disable); void cpsw_tx_handler(void *token, int len, int status) { @@ -82,6 +85,7 @@ void cpsw_tx_handler(void *token, int len, int status) ndev->stats.tx_packets++; ndev->stats.tx_bytes += len; } +EXPORT_SYMBOL_GPL(cpsw_tx_handler); irqreturn_t cpsw_tx_interrupt(int irq, void *dev_id) { @@ -98,6 +102,7 @@ irqreturn_t cpsw_tx_interrupt(int irq, void *dev_id) napi_schedule(&cpsw->napi_tx); return IRQ_HANDLED; } +EXPORT_SYMBOL_GPL(cpsw_tx_interrupt); irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id) { @@ -114,6 +119,7 @@ irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id) napi_schedule(&cpsw->napi_rx); return IRQ_HANDLED; } +EXPORT_SYMBOL_GPL(cpsw_rx_interrupt); irqreturn_t cpsw_misc_interrupt(int irq, void *dev_id) { @@ -126,6 +132,7 @@ irqreturn_t cpsw_misc_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +EXPORT_SYMBOL_GPL(cpsw_misc_interrupt); int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget) { @@ -158,6 +165,7 @@ int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget) return num_tx; } +EXPORT_SYMBOL_GPL(cpsw_tx_mq_poll); int cpsw_tx_poll(struct napi_struct *napi_tx, int budget) { @@ -176,6 +184,7 @@ int cpsw_tx_poll(struct napi_struct *napi_tx, int budget) return num_tx; } +EXPORT_SYMBOL_GPL(cpsw_tx_poll); int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget) { @@ -208,6 +217,7 @@ int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget) return num_rx; } +EXPORT_SYMBOL_GPL(cpsw_rx_mq_poll); int cpsw_rx_poll(struct napi_struct *napi_rx, int budget) { @@ -226,6 +236,7 @@ int cpsw_rx_poll(struct napi_struct *napi_rx, int budget) return num_rx; } +EXPORT_SYMBOL_GPL(cpsw_rx_poll); void cpsw_rx_vlan_encap(struct sk_buff *skb) { @@ -268,12 +279,14 @@ void cpsw_rx_vlan_encap(struct sk_buff *skb) skb_pull(skb, VLAN_HLEN); } } +EXPORT_SYMBOL_GPL(cpsw_rx_vlan_encap); void cpsw_set_slave_mac(struct cpsw_slave *slave, struct cpsw_priv *priv) { slave_write(slave, mac_hi(priv->mac_addr), SA_HI); slave_write(slave, mac_lo(priv->mac_addr), SA_LO); } +EXPORT_SYMBOL_GPL(cpsw_set_slave_mac); void cpsw_soft_reset(const char *module, void __iomem *reg) { @@ -286,6 +299,7 @@ void cpsw_soft_reset(const char *module, void __iomem *reg) WARN(readl_relaxed(reg) & 1, "failed to soft-reset %s\n", module); } +EXPORT_SYMBOL_GPL(cpsw_soft_reset); void cpsw_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue) { @@ -305,6 +319,7 @@ void cpsw_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue) netif_trans_update(ndev); netif_tx_wake_all_queues(ndev); } +EXPORT_SYMBOL_GPL(cpsw_ndo_tx_timeout); static int cpsw_get_common_speed(struct cpsw_common *cpsw) { @@ -343,6 +358,7 @@ int cpsw_need_resplit(struct cpsw_common *cpsw) return 1; } +EXPORT_SYMBOL_GPL(cpsw_need_resplit); void cpsw_split_res(struct cpsw_common *cpsw) { @@ -428,6 +444,7 @@ void cpsw_split_res(struct cpsw_common *cpsw) if (budget) cpsw->rxv[0].budget += budget; } +EXPORT_SYMBOL_GPL(cpsw_split_res); int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs, int ale_ageout, phys_addr_t desc_mem_phys, @@ -548,6 +565,7 @@ int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs, return ret; } +EXPORT_SYMBOL_GPL(cpsw_init_common); #if IS_ENABLED(CONFIG_TI_CPTS) @@ -678,6 +696,7 @@ int cpsw_hwtstamp_set(struct net_device *dev, return 0; } +EXPORT_SYMBOL_GPL(cpsw_hwtstamp_set); int cpsw_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) @@ -695,12 +714,14 @@ int cpsw_hwtstamp_get(struct net_device *dev, return 0; } +EXPORT_SYMBOL_GPL(cpsw_hwtstamp_get); #else int cpsw_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(cpsw_hwtstamp_set); int cpsw_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, @@ -708,6 +729,7 @@ int cpsw_hwtstamp_set(struct net_device *dev, { return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(cpsw_hwtstamp_get); #endif /*CONFIG_TI_CPTS*/ int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate) @@ -758,6 +780,7 @@ int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate) cpsw_split_res(cpsw); return ret; } +EXPORT_SYMBOL_GPL(cpsw_ndo_set_tx_maxrate); static int cpsw_tc_to_fifo(int tc, int num_tc) { @@ -782,6 +805,7 @@ bool cpsw_shp_is_off(struct cpsw_priv *priv) return !val; } +EXPORT_SYMBOL_GPL(cpsw_shp_is_off); static void cpsw_fifo_shp_on(struct cpsw_priv *priv, int fifo, int on) { @@ -1043,6 +1067,7 @@ int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type, return -EOPNOTSUPP; } } +EXPORT_SYMBOL_GPL(cpsw_ndo_setup_tc); void cpsw_cbs_resume(struct cpsw_slave *slave, struct cpsw_priv *priv) { @@ -1056,6 +1081,7 @@ void cpsw_cbs_resume(struct cpsw_slave *slave, struct cpsw_priv *priv) cpsw_set_fifo_rlimit(priv, fifo, bw); } } +EXPORT_SYMBOL_GPL(cpsw_cbs_resume); void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv) { @@ -1078,6 +1104,7 @@ void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv) slave_write(slave, tx_prio_map, tx_prio_rg); } +EXPORT_SYMBOL_GPL(cpsw_mqprio_resume); int cpsw_fill_rx_channels(struct cpsw_priv *priv) { @@ -1123,6 +1150,7 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv) return 0; } +EXPORT_SYMBOL_GPL(cpsw_fill_rx_channels); static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw, int size) @@ -1208,6 +1236,7 @@ void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw) cpsw->page_pool[ch] = NULL; } } +EXPORT_SYMBOL_GPL(cpsw_destroy_xdp_rxqs); int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw) { @@ -1240,6 +1269,7 @@ int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw) return ret; } +EXPORT_SYMBOL_GPL(cpsw_create_xdp_rxqs); static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf) { @@ -1267,6 +1297,7 @@ int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf) return -EINVAL; } } +EXPORT_SYMBOL_GPL(cpsw_ndo_bpf); int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf, struct page *page, int port) @@ -1300,6 +1331,7 @@ int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf, return ret; } +EXPORT_SYMBOL_GPL(cpsw_xdp_tx_frame); int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, struct page *page, int port, int *len) @@ -1362,6 +1394,7 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, page_pool_recycle_direct(cpsw->page_pool[ch], page); return ret; } +EXPORT_SYMBOL_GPL(cpsw_run_xdp); static int cpsw_qos_clsflower_add_policer(struct cpsw_priv *priv, struct netlink_ext_ack *extack, @@ -1564,3 +1597,7 @@ void cpsw_qos_clsflower_resume(struct cpsw_priv *priv) cpsw_ale_rx_ratelimit_mc(priv->cpsw->ale, port_id, priv->ale_mc_ratelimit.rate_packet_ps); } +EXPORT_SYMBOL_GPL(cpsw_qos_clsflower_resume); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("TI CPSW Ethernet Switch Driver"); diff --git a/drivers/net/ethernet/ti/cpsw_sl.c b/drivers/net/ethernet/ti/cpsw_sl.c index 0c7531cb0f398..761719a348fa5 100644 --- a/drivers/net/ethernet/ti/cpsw_sl.c +++ b/drivers/net/ethernet/ti/cpsw_sl.c @@ -200,6 +200,7 @@ u32 cpsw_sl_reg_read(struct cpsw_sl *sl, enum cpsw_sl_regs reg) dev_dbg(sl->dev, "cpsw_sl: reg: %04X r 0x%08X\n", sl->regs[reg], val); return val; } +EXPORT_SYMBOL_GPL(cpsw_sl_reg_read); void cpsw_sl_reg_write(struct cpsw_sl *sl, enum cpsw_sl_regs reg, u32 val) { @@ -212,6 +213,7 @@ void cpsw_sl_reg_write(struct cpsw_sl *sl, enum cpsw_sl_regs reg, u32 val) dev_dbg(sl->dev, "cpsw_sl: reg: %04X w 0x%08X\n", sl->regs[reg], val); writel(val, sl->sl_base + sl->regs[reg]); } +EXPORT_SYMBOL_GPL(cpsw_sl_reg_write); static const struct cpsw_sl_dev_id *cpsw_sl_match_id( const struct cpsw_sl_dev_id *id, @@ -252,6 +254,7 @@ struct cpsw_sl *cpsw_sl_get(const char *device_id, struct device *dev, return sl; } +EXPORT_SYMBOL_GPL(cpsw_sl_get); void cpsw_sl_reset(struct cpsw_sl *sl, unsigned long tmo) { @@ -270,6 +273,7 @@ void cpsw_sl_reset(struct cpsw_sl *sl, unsigned long tmo) if (cpsw_sl_reg_read(sl, CPSW_SL_SOFT_RESET) & CPSW_SL_SOFT_RESET_BIT) dev_err(sl->dev, "cpsw_sl failed to soft-reset.\n"); } +EXPORT_SYMBOL_GPL(cpsw_sl_reset); u32 cpsw_sl_ctl_set(struct cpsw_sl *sl, u32 ctl_funcs) { @@ -287,6 +291,7 @@ u32 cpsw_sl_ctl_set(struct cpsw_sl *sl, u32 ctl_funcs) return 0; } +EXPORT_SYMBOL_GPL(cpsw_sl_ctl_set); u32 cpsw_sl_ctl_clr(struct cpsw_sl *sl, u32 ctl_funcs) { @@ -304,11 +309,13 @@ u32 cpsw_sl_ctl_clr(struct cpsw_sl *sl, u32 ctl_funcs) return 0; } +EXPORT_SYMBOL_GPL(cpsw_sl_ctl_clr); void cpsw_sl_ctl_reset(struct cpsw_sl *sl) { cpsw_sl_reg_write(sl, CPSW_SL_MACCONTROL, 0); } +EXPORT_SYMBOL_GPL(cpsw_sl_ctl_reset); int cpsw_sl_wait_for_idle(struct cpsw_sl *sl, unsigned long tmo) { @@ -326,3 +333,7 @@ int cpsw_sl_wait_for_idle(struct cpsw_sl *sl, unsigned long tmo) return 0; } +EXPORT_SYMBOL_GPL(cpsw_sl_wait_for_idle); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("TI Ethernet Switch media-access-controller (MAC) submodule"); diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index d2eab5cd1e0c9..41e89a19be537 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -531,6 +531,7 @@ struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params) ctlr->num_chan = CPDMA_MAX_CHANNELS; return ctlr; } +EXPORT_SYMBOL_GPL(cpdma_ctlr_create); int cpdma_ctlr_start(struct cpdma_ctlr *ctlr) { @@ -591,6 +592,7 @@ int cpdma_ctlr_start(struct cpdma_ctlr *ctlr) spin_unlock_irqrestore(&ctlr->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_ctlr_start); int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr) { @@ -623,6 +625,7 @@ int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr) spin_unlock_irqrestore(&ctlr->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_ctlr_stop); int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr) { @@ -640,6 +643,7 @@ int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr) cpdma_desc_pool_destroy(ctlr); return ret; } +EXPORT_SYMBOL_GPL(cpdma_ctlr_destroy); int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable) { @@ -660,21 +664,25 @@ int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable) spin_unlock_irqrestore(&ctlr->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_ctlr_int_ctrl); void cpdma_ctlr_eoi(struct cpdma_ctlr *ctlr, u32 value) { dma_reg_write(ctlr, CPDMA_MACEOIVECTOR, value); } +EXPORT_SYMBOL_GPL(cpdma_ctlr_eoi); u32 cpdma_ctrl_rxchs_state(struct cpdma_ctlr *ctlr) { return dma_reg_read(ctlr, CPDMA_RXINTSTATMASKED); } +EXPORT_SYMBOL_GPL(cpdma_ctrl_rxchs_state); u32 cpdma_ctrl_txchs_state(struct cpdma_ctlr *ctlr) { return dma_reg_read(ctlr, CPDMA_TXINTSTATMASKED); } +EXPORT_SYMBOL_GPL(cpdma_ctrl_txchs_state); static void cpdma_chan_set_descs(struct cpdma_ctlr *ctlr, int rx, int desc_num, @@ -802,6 +810,7 @@ int cpdma_chan_set_weight(struct cpdma_chan *ch, int weight) spin_unlock_irqrestore(&ctlr->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(cpdma_chan_set_weight); /* cpdma_chan_get_min_rate - get minimum allowed rate for channel * Should be called before cpdma_chan_set_rate. @@ -816,6 +825,7 @@ u32 cpdma_chan_get_min_rate(struct cpdma_ctlr *ctlr) return DIV_ROUND_UP(divident, divisor); } +EXPORT_SYMBOL_GPL(cpdma_chan_get_min_rate); /* cpdma_chan_set_rate - limits bandwidth for transmit channel. * The bandwidth * limited channels have to be in order beginning from lowest. @@ -860,6 +870,7 @@ int cpdma_chan_set_rate(struct cpdma_chan *ch, u32 rate) spin_unlock_irqrestore(&ctlr->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(cpdma_chan_set_rate); u32 cpdma_chan_get_rate(struct cpdma_chan *ch) { @@ -872,6 +883,7 @@ u32 cpdma_chan_get_rate(struct cpdma_chan *ch) return rate; } +EXPORT_SYMBOL_GPL(cpdma_chan_get_rate); struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num, cpdma_handler_fn handler, int rx_type) @@ -931,6 +943,7 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num, spin_unlock_irqrestore(&ctlr->lock, flags); return chan; } +EXPORT_SYMBOL_GPL(cpdma_chan_create); int cpdma_chan_get_rx_buf_num(struct cpdma_chan *chan) { @@ -943,6 +956,7 @@ int cpdma_chan_get_rx_buf_num(struct cpdma_chan *chan) return desc_num; } +EXPORT_SYMBOL_GPL(cpdma_chan_get_rx_buf_num); int cpdma_chan_destroy(struct cpdma_chan *chan) { @@ -964,6 +978,7 @@ int cpdma_chan_destroy(struct cpdma_chan *chan) spin_unlock_irqrestore(&ctlr->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_chan_destroy); int cpdma_chan_get_stats(struct cpdma_chan *chan, struct cpdma_chan_stats *stats) @@ -976,6 +991,7 @@ int cpdma_chan_get_stats(struct cpdma_chan *chan, spin_unlock_irqrestore(&chan->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_chan_get_stats); static void __cpdma_chan_submit(struct cpdma_chan *chan, struct cpdma_desc __iomem *desc) @@ -1100,6 +1116,7 @@ int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data, spin_unlock_irqrestore(&chan->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(cpdma_chan_idle_submit); int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token, dma_addr_t data, int len, int directed) @@ -1125,6 +1142,7 @@ int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token, spin_unlock_irqrestore(&chan->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(cpdma_chan_idle_submit_mapped); int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data, int len, int directed) @@ -1150,6 +1168,7 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data, spin_unlock_irqrestore(&chan->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(cpdma_chan_submit); int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token, dma_addr_t data, int len, int directed) @@ -1175,6 +1194,7 @@ int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token, spin_unlock_irqrestore(&chan->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(cpdma_chan_submit_mapped); bool cpdma_check_free_tx_desc(struct cpdma_chan *chan) { @@ -1189,6 +1209,7 @@ bool cpdma_check_free_tx_desc(struct cpdma_chan *chan) spin_unlock_irqrestore(&chan->lock, flags); return free_tx_desc; } +EXPORT_SYMBOL_GPL(cpdma_check_free_tx_desc); static void __cpdma_chan_free(struct cpdma_chan *chan, struct cpdma_desc __iomem *desc, @@ -1289,6 +1310,7 @@ int cpdma_chan_process(struct cpdma_chan *chan, int quota) } return used; } +EXPORT_SYMBOL_GPL(cpdma_chan_process); int cpdma_chan_start(struct cpdma_chan *chan) { @@ -1308,6 +1330,7 @@ int cpdma_chan_start(struct cpdma_chan *chan) return 0; } +EXPORT_SYMBOL_GPL(cpdma_chan_start); int cpdma_chan_stop(struct cpdma_chan *chan) { @@ -1370,6 +1393,7 @@ int cpdma_chan_stop(struct cpdma_chan *chan) spin_unlock_irqrestore(&chan->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(cpdma_chan_stop); int cpdma_chan_int_ctrl(struct cpdma_chan *chan, bool enable) { @@ -1416,11 +1440,13 @@ int cpdma_get_num_rx_descs(struct cpdma_ctlr *ctlr) { return ctlr->num_rx_desc; } +EXPORT_SYMBOL_GPL(cpdma_get_num_rx_descs); int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr) { return ctlr->num_tx_desc; } +EXPORT_SYMBOL_GPL(cpdma_get_num_tx_descs); int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc) { @@ -1442,3 +1468,4 @@ int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc) return ret; } +EXPORT_SYMBOL_GPL(cpdma_set_num_rx_descs); From cbea71b4480394708f9a6e007a0385acfe5e1ec8 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Mon, 16 Feb 2026 20:30:43 -0600 Subject: [PATCH 0310/1518] wifi: brcmfmac: Fix error pointer dereference [ Upstream commit dd8592fc6007a451c3e4b9025de365e39de8178a ] The function brcmf_chip_add_core() can return an error pointer and is not checked. Add checks for error pointer. Detected by Smatch: drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c:1010 brcmf_chip_recognition() error: 'core' dereferencing possible ERR_PTR() drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c:1013 brcmf_chip_recognition() error: 'core' dereferencing possible ERR_PTR() drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c:1016 brcmf_chip_recognition() error: 'core' dereferencing possible ERR_PTR() drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c:1019 brcmf_chip_recognition() error: 'core' dereferencing possible ERR_PTR() drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c:1022 brcmf_chip_recognition() error: 'core' dereferencing possible ERR_PTR() Fixes: cb7cf7be9eba7 ("brcmfmac: make chip related functions host interface independent") Signed-off-by: Ethan Tidmore Acked-by: Arend van Spriel Link: https://patch.msgid.link/20260217023043.73631-1-ethantidmore06@gmail.com [add missing wifi: prefix] Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- .../wireless/broadcom/brcm80211/brcmfmac/chip.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c index 4239f2b21e542..dcd8a296de106 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c @@ -1007,18 +1007,33 @@ static int brcmf_chip_recognition(struct brcmf_chip_priv *ci) core = brcmf_chip_add_core(ci, BCMA_CORE_CHIPCOMMON, SI_ENUM_BASE_DEFAULT, 0); + if (IS_ERR(core)) + return PTR_ERR(core); + brcmf_chip_sb_corerev(ci, core); core = brcmf_chip_add_core(ci, BCMA_CORE_SDIO_DEV, BCM4329_CORE_BUS_BASE, 0); + if (IS_ERR(core)) + return PTR_ERR(core); + brcmf_chip_sb_corerev(ci, core); core = brcmf_chip_add_core(ci, BCMA_CORE_INTERNAL_MEM, BCM4329_CORE_SOCRAM_BASE, 0); + if (IS_ERR(core)) + return PTR_ERR(core); + brcmf_chip_sb_corerev(ci, core); core = brcmf_chip_add_core(ci, BCMA_CORE_ARM_CM3, BCM4329_CORE_ARM_BASE, 0); + if (IS_ERR(core)) + return PTR_ERR(core); + brcmf_chip_sb_corerev(ci, core); core = brcmf_chip_add_core(ci, BCMA_CORE_80211, 0x18001000, 0); + if (IS_ERR(core)) + return PTR_ERR(core); + brcmf_chip_sb_corerev(ci, core); } else if (socitype == SOCI_AI) { ci->iscoreup = brcmf_chip_ai_iscoreup; From a9937a3ac5857f6308bf42fe43ed37870030319e Mon Sep 17 00:00:00 2001 From: Nicolas Escande Date: Fri, 27 Mar 2026 11:02:56 +0100 Subject: [PATCH 0311/1518] wifi: mac80211: handle VHT EXT NSS in ieee80211_determine_our_sta_mode() [ Upstream commit b5b8e295973083abf823fb66647a7c702a8db8a7 ] A station which has a NSS ratio on the number of streams it is capable of in 160MHz VHT operation is supposed to use the 'Extended NSS BW Support' as defined by section '9.4.2.156.2 VHT Capabilities Information field'. This was missing in ieee80211_determine_our_sta_mode() and so we would wrongfully downgrade our bandwidth when connecting to an AP that supported 160MHz with messages such as: [ 37.638346] wlan1: AP XX:XX:XX:XX:XX:XX changed bandwidth in assoc response, new used config is 5280.000 MHz, width 3 (5290.000/0 MHz) Fixes: 310c8387c638 ("wifi: mac80211: clean up connection process") Signed-off-by: Nicolas Escande Link: https://patch.msgid.link/20260327100256.3101348-1-nico.escande@gmail.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/mlme.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index deef15c074c83..bcc4090ddc1a5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5897,7 +5897,8 @@ ieee80211_determine_our_sta_mode(struct ieee80211_sub_if_data *sdata, if (is_5ghz && !(vht_cap.cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ | - IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))) { + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ | + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK))) { conn->bw_limit = IEEE80211_CONN_BW_LIMIT_80; mlme_link_id_dbg(sdata, link_id, "no VHT 160 MHz capability on 5 GHz, limiting to 80 MHz"); From 281f2a214565a5cbf8b7355a65738d80bd19b8c5 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Tue, 7 Apr 2026 20:23:33 +0800 Subject: [PATCH 0312/1518] bpf: Drop task_to_inode and inet_conn_established from lsm sleepable hooks [ Upstream commit beaf0e96b1da74549a6cabd040f9667d83b2e97e ] bpf_lsm_task_to_inode() is called under rcu_read_lock() and bpf_lsm_inet_conn_established() is called from softirq context, so neither hook can be used by sleepable LSM programs. Fixes: 423f16108c9d8 ("bpf: Augment the set of sleepable LSM hooks") Reported-by: Quan Sun <2022090917019@std.uestc.edu.cn> Reported-by: Yinhao Hu Reported-by: Kaiyan Mei Reported-by: Dongliang Mu Closes: https://lore.kernel.org/bpf/3ab69731-24d1-431a-a351-452aafaaf2a5@std.uestc.edu.cn/T/#u Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260407122334.344072-1-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/bpf_lsm.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 0a59df1c550a0..2eead789b898b 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -357,8 +357,6 @@ BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_inet_conn_established) - BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) @@ -379,7 +377,6 @@ BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) -BTF_ID(func, bpf_lsm_task_to_inode) BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) From 76f2ebaf79a9ae6d0737b87f045fe769e425d78f Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Sun, 5 Apr 2026 00:12:20 +0800 Subject: [PATCH 0313/1518] bpf: reject negative CO-RE accessor indices in bpf_core_parse_spec() [ Upstream commit 1c22483a2c4bbf747787f328392ca3e68619c4dc ] CO-RE accessor strings are colon-separated indices that describe a path from a root BTF type to a target field, e.g. "0:1:2" walks through nested struct members. bpf_core_parse_spec() parses each component with sscanf("%d"), so negative values like -1 are silently accepted. The subsequent bounds checks (access_idx >= btf_vlen(t)) only guard the upper bound and always pass for negative values because C integer promotion converts the __u16 btf_vlen result to int, making the comparison (int)(-1) >= (int)(N) false for any positive N. When -1 reaches btf_member_bit_offset() it gets cast to u32 0xffffffff, producing an out-of-bounds read far past the members array. A crafted BPF program with a negative CO-RE accessor on any struct that exists in vmlinux BTF (e.g. task_struct) crashes the kernel deterministically during BPF_PROG_LOAD on any system with CONFIG_DEBUG_INFO_BTF=y (default on major distributions). The bug is reachable with CAP_BPF: BUG: unable to handle page fault for address: ffffed11818b6626 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Oops: Oops: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 85 Comm: poc Not tainted 7.0.0-rc6 #18 PREEMPT(full) RIP: 0010:bpf_core_parse_spec (tools/lib/bpf/relo_core.c:354) RAX: 00000000ffffffff Call Trace: bpf_core_calc_relo_insn (tools/lib/bpf/relo_core.c:1321) bpf_core_apply (kernel/bpf/btf.c:9507) check_core_relo (kernel/bpf/verifier.c:19475) bpf_check (kernel/bpf/verifier.c:26031) bpf_prog_load (kernel/bpf/syscall.c:3089) __sys_bpf (kernel/bpf/syscall.c:6228) CO-RE accessor indices are inherently non-negative (struct member index, array element index, or enumerator index), so reject them immediately after parsing. Fixes: ddc7c3042614 ("libbpf: implement BPF CO-RE offset relocation algorithm") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Reviewed-by: Emil Tsalapatis Acked-by: Paul Chaignon Link: https://lore.kernel.org/r/20260404161221.961828-2-bestswngs@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/lib/bpf/relo_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 6eea5edba58a5..0ccc8f548cbaa 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -292,6 +292,8 @@ int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, ++spec_str; if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) return -EINVAL; + if (access_idx < 0) + return -EINVAL; if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) return -E2BIG; spec_str += parsed_len; From 25463350662650504636f08eb82ba2bc2fd6cd5c Mon Sep 17 00:00:00 2001 From: Baochen Qiang Date: Wed, 25 Mar 2026 11:05:01 +0800 Subject: [PATCH 0314/1518] wifi: ath10k: fix station lookup failure during disconnect [ Upstream commit 9a34a59c6086ae731a06b3e61b0951feef758648 ] Recent commit [1] moved station statistics collection to an earlier stage of the disconnect flow. With this change in place, ath10k fails to resolve the station entry when handling a peer stats event triggered during disconnect, resulting in log messages such as: wlp58s0: deauthenticating from 74:1a:e0:e7:b4:c8 by local choice (Reason: 3=DEAUTH_LEAVING) ath10k_pci 0000:3a:00.0: not found station for peer stats ath10k_pci 0000:3a:00.0: failed to parse stats info tlv: -22 The failure occurs because ath10k relies on ieee80211_find_sta_by_ifaddr() for station lookup. That function uses local->sta_hash, but by the time the peer stats request is triggered during disconnect, mac80211 has already removed the station from that hash table, leading to lookup failure. Before commit [1], this issue was not visible because the transition from IEEE80211_STA_NONE to IEEE80211_STA_NOTEXIST prevented ath10k from sending a peer stats request at all: ath10k_mac_sta_get_peer_stats_info() would fail early to find the peer and skip requesting statistics. Fix this by switching the lookup path to ath10k_peer_find(), which queries ath10k's internal peer table. At the point where the firmware emits the peer stats event, the peer entry is still present in the driver's list, ensuring lookup succeeds. Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00309-QCARMSWPZ-1 Fixes: a203dbeeca15 ("wifi: mac80211: collect station statistics earlier when disconnect") # [1] Reported-by: Paul Menzel Closes: https://lore.kernel.org/ath10k/57671b89-ec9f-4e6c-992c-45eb8e75929c@molgen.mpg.de Signed-off-by: Baochen Qiang Reviewed-by: Rameshkumar Sundaram Reviewed-by: Paul Menzel Tested-by: Paul Menzel Link: https://patch.msgid.link/20260325-ath10k-station-lookup-failure-v1-1-2e0c970f25d5@oss.qualcomm.com Signed-off-by: Jeff Johnson Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/wmi-tlv.c | 26 +++++++++++++---------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index 16d07d619b4df..ba1294c8ee39f 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -3,7 +3,7 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include "core.h" #include "debug.h" @@ -14,6 +14,7 @@ #include "wmi-tlv.h" #include "p2p.h" #include "testmode.h" +#include "txrx.h" #include /***************/ @@ -224,8 +225,9 @@ static int ath10k_wmi_tlv_parse_peer_stats_info(struct ath10k *ar, u16 tag, u16 const void *ptr, void *data) { const struct wmi_tlv_peer_stats_info *stat = ptr; - struct ieee80211_sta *sta; + u32 vdev_id = *(u32 *)data; struct ath10k_sta *arsta; + struct ath10k_peer *peer; if (tag != WMI_TLV_TAG_STRUCT_PEER_STATS_INFO) return -EPROTO; @@ -241,20 +243,20 @@ static int ath10k_wmi_tlv_parse_peer_stats_info(struct ath10k *ar, u16 tag, u16 __le32_to_cpu(stat->last_tx_rate_code), __le32_to_cpu(stat->last_tx_bitrate_kbps)); - rcu_read_lock(); - sta = ieee80211_find_sta_by_ifaddr(ar->hw, stat->peer_macaddr.addr, NULL); - if (!sta) { - rcu_read_unlock(); - ath10k_warn(ar, "not found station for peer stats\n"); + guard(spinlock_bh)(&ar->data_lock); + + peer = ath10k_peer_find(ar, vdev_id, stat->peer_macaddr.addr); + if (!peer || !peer->sta) { + ath10k_warn(ar, "not found %s with vdev id %u mac addr %pM for peer stats\n", + peer ? "sta" : "peer", vdev_id, stat->peer_macaddr.addr); return -EINVAL; } - arsta = (struct ath10k_sta *)sta->drv_priv; + arsta = (struct ath10k_sta *)peer->sta->drv_priv; arsta->rx_rate_code = __le32_to_cpu(stat->last_rx_rate_code); arsta->rx_bitrate_kbps = __le32_to_cpu(stat->last_rx_bitrate_kbps); arsta->tx_rate_code = __le32_to_cpu(stat->last_tx_rate_code); arsta->tx_bitrate_kbps = __le32_to_cpu(stat->last_tx_bitrate_kbps); - rcu_read_unlock(); return 0; } @@ -266,6 +268,7 @@ static int ath10k_wmi_tlv_op_pull_peer_stats_info(struct ath10k *ar, const struct wmi_tlv_peer_stats_info_ev *ev; const void *data; u32 num_peer_stats; + u32 vdev_id; int ret; tb = ath10k_wmi_tlv_parse_alloc(ar, skb->data, skb->len, GFP_ATOMIC); @@ -284,15 +287,16 @@ static int ath10k_wmi_tlv_op_pull_peer_stats_info(struct ath10k *ar, } num_peer_stats = __le32_to_cpu(ev->num_peers); + vdev_id = __le32_to_cpu(ev->vdev_id); ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi tlv peer stats info update peer vdev id %d peers %i more data %d\n", - __le32_to_cpu(ev->vdev_id), + vdev_id, num_peer_stats, __le32_to_cpu(ev->more_data)); ret = ath10k_wmi_tlv_iter(ar, data, ath10k_wmi_tlv_len(data), - ath10k_wmi_tlv_parse_peer_stats_info, NULL); + ath10k_wmi_tlv_parse_peer_stats_info, &vdev_id); if (ret) ath10k_warn(ar, "failed to parse stats info tlv: %d\n", ret); From 9f88b29b79a06dfd362d6f8dec51aece25683135 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Wed, 4 Feb 2026 07:17:37 -0800 Subject: [PATCH 0315/1518] bpf: Support negative offsets, BPF_SUB, and alu32 for linked register tracking [ Upstream commit 7a433e519364c3c19643e5c857f4fbfaebec441c ] Previously, the verifier only tracked positive constant deltas between linked registers using BPF_ADD. This limitation meant patterns like: r1 = r0; r1 += -4; if r1 s>= 0 goto l0_%=; // r1 >= 0 implies r0 >= 4 // verifier couldn't propagate bounds back to r0 if r0 != 0 goto l0_%=; r0 /= 0; // Verifier thinks this is reachable l0_%=: Similar limitation exists for 32-bit registers. With this change, the verifier can now track negative deltas in reg->off enabling bound propagation for the above pattern. For alu32, we make sure the destination register has the upper 32 bits as 0s before creating the link. BPF_ADD_CONST is split into BPF_ADD_CONST64 and BPF_ADD_CONST32, the latter is used in case of alu32 and sync_linked_regs uses this to zext the result if known_reg has this flag. Signed-off-by: Puranjay Mohan Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260204151741.2678118-2-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Stable-dep-of: d7f14173c0d5 ("bpf: Fix linked reg delta tracking when src_reg == dst_reg") Signed-off-by: Sasha Levin --- include/linux/bpf_verifier.h | 6 ++- kernel/bpf/verifier.c | 50 +++++++++++++++---- .../selftests/bpf/progs/verifier_bounds.c | 2 +- 3 files changed, 45 insertions(+), 13 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 4c497e839526a..4867b0e8b5d9d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -147,8 +147,12 @@ struct bpf_reg_state { * registers. Example: * r1 = r2; both will have r1->id == r2->id == N * r1 += 10; r1->id == N | BPF_ADD_CONST and r1->off == 10 + * r3 = r2; both will have r3->id == r2->id == N + * w3 += 10; r3->id == N | BPF_ADD_CONST32 and r3->off == 10 */ -#define BPF_ADD_CONST (1U << 31) +#define BPF_ADD_CONST64 (1U << 31) +#define BPF_ADD_CONST32 (1U << 30) +#define BPF_ADD_CONST (BPF_ADD_CONST64 | BPF_ADD_CONST32) u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned * from a pointer-cast helper, bpf_sk_fullsock() and diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0d1ec2b5d469a..6cf8b13db301b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -15787,6 +15787,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, verbose(env, "verifier internal error: no src_reg\n"); return -EFAULT; } + /* + * For alu32 linked register tracking, we need to check dst_reg's + * umax_value before the ALU operation. After adjust_scalar_min_max_vals(), + * alu32 ops will have zero-extended the result, making umax_value <= U32_MAX. + */ + u64 dst_umax = dst_reg->umax_value; + err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); if (err) return err; @@ -15796,26 +15803,44 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * r1 += 0x1 * if r2 < 1000 goto ... * use r1 in memory access - * So for 64-bit alu remember constant delta between r2 and r1 and - * update r1 after 'if' condition. + * So remember constant delta between r2 and r1 and update r1 after + * 'if' condition. */ if (env->bpf_capable && - BPF_OP(insn->code) == BPF_ADD && !alu32 && - dst_reg->id && is_reg_const(src_reg, false)) { - u64 val = reg_const_value(src_reg, false); + (BPF_OP(insn->code) == BPF_ADD || BPF_OP(insn->code) == BPF_SUB) && + dst_reg->id && is_reg_const(src_reg, alu32)) { + u64 val = reg_const_value(src_reg, alu32); + s32 off; + + if (!alu32 && ((s64)val < S32_MIN || (s64)val > S32_MAX)) + goto clear_id; + + if (alu32 && (dst_umax > U32_MAX)) + goto clear_id; - if ((dst_reg->id & BPF_ADD_CONST) || - /* prevent overflow in sync_linked_regs() later */ - val > (u32)S32_MAX) { + off = (s32)val; + + if (BPF_OP(insn->code) == BPF_SUB) { + /* Negating S32_MIN would overflow */ + if (off == S32_MIN) + goto clear_id; + off = -off; + } + + if (dst_reg->id & BPF_ADD_CONST) { /* * If the register already went through rX += val * we cannot accumulate another val into rx->off. */ +clear_id: dst_reg->off = 0; dst_reg->id = 0; } else { - dst_reg->id |= BPF_ADD_CONST; - dst_reg->off = val; + if (alu32) + dst_reg->id |= BPF_ADD_CONST32; + else + dst_reg->id |= BPF_ADD_CONST64; + dst_reg->off = off; } } else { /* @@ -16888,7 +16913,7 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s u32 saved_id = reg->id; fake_reg.type = SCALAR_VALUE; - __mark_reg_known(&fake_reg, (s32)reg->off - (s32)known_reg->off); + __mark_reg_known(&fake_reg, (s64)reg->off - (s64)known_reg->off); /* reg = known_reg; reg += delta */ copy_register_state(reg, known_reg); @@ -16903,6 +16928,9 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s scalar32_min_max_add(reg, &fake_reg); scalar_min_max_add(reg, &fake_reg); reg->var_off = tnum_add(reg->var_off, fake_reg.var_off); + if (known_reg->id & BPF_ADD_CONST32) + zext_32_to_64(reg); + reg_bounds_sync(reg); } } } diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index e772ae430915f..ea5db79da40ef 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1477,7 +1477,7 @@ __naked void sub64_full_overflow(void) SEC("socket") __description("64-bit subtraction, partial overflow, result in unbounded reg") __success __log_level(2) -__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar()") +__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar(id=1-1)") __retval(0) __naked void sub64_partial_overflow(void) { From d88e8e4a3b52bd5b2ff3eceba4b29d1b5506d066 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 7 Apr 2026 21:24:18 +0200 Subject: [PATCH 0316/1518] bpf: Fix linked reg delta tracking when src_reg == dst_reg [ Upstream commit d7f14173c0d5866c3cae759dee560ad1bed10d2e ] Consider the case of rX += rX where src_reg and dst_reg are pointers to the same bpf_reg_state in adjust_reg_min_max_vals(). The latter first modifies the dst_reg in-place, and later in the delta tracking, the subsequent is_reg_const(src_reg)/reg_const_value(src_reg) reads the post-{add,sub} value instead of the original source. This is problematic since it sets an incorrect delta, which sync_linked_regs() then propagates to linked registers, thus creating a verifier-vs-runtime mismatch. Fix it by just skipping this corner case. Fixes: 98d7ca374ba4 ("bpf: Track delta between "linked" registers.") Reported-by: STAR Labs SG Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20260407192421.508817-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6cf8b13db301b..6d5fc1af7a1f6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -15808,7 +15808,8 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, */ if (env->bpf_capable && (BPF_OP(insn->code) == BPF_ADD || BPF_OP(insn->code) == BPF_SUB) && - dst_reg->id && is_reg_const(src_reg, alu32)) { + dst_reg->id && is_reg_const(src_reg, alu32) && + !(BPF_SRC(insn->code) == BPF_X && insn->src_reg == insn->dst_reg)) { u64 val = reg_const_value(src_reg, alu32); s32 off; From 73ae96e2be4e28891519c0ebc23a21990fc20a80 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 7 Apr 2026 14:16:46 +0100 Subject: [PATCH 0317/1518] arm64: entry: Don't preempt with SError or Debug masked [ Upstream commit 2371bd83b3df9d833191fe58dadb0e69a794a1cd ] On arm64, involuntary kernel preemption has been subtly broken since the move to the generic irqentry code. When preemption occurs, the new task may run with SError and Debug exceptions masked unexpectedly, leading to a loss of RAS events, breakpoints, watchpoints, and single-step exceptions. Prior to moving to the generic irqentry code, involuntary preemption of kernel mode would only occur when returning from regular interrupts, in a state where interrupts were masked and all other arm64-specific exceptions (SError, Debug, and pseudo-NMI) were unmasked. This is the only state in which it is valid to switch tasks. As part of moving to the generic irqentry code, the involuntary preemption logic was moved such that involuntary preemption could occur when returning from any (non-NMI) exception. As most exception handlers mask all arm64-specific exceptions before this point, preemption could occur in a state where arm64-specific exceptions were masked. This is not a valid state to switch tasks, and resulted in the loss of exceptions described above. As a temporary bodge, avoid the loss of exceptions by avoiding involuntary preemption when SError and/or Debug exceptions are masked. Practically speaking this means that involuntary preemption will only occur when returning from regular interrupts, as was the case before moving to the generic irqentry code. Fixes: 99eb057ccd67 ("arm64: entry: Move arm64_preempt_schedule_irq() into __exit_to_kernel_mode()") Reported-by: Ada Couprie Diaz Reported-by: Vladimir Murzin Signed-off-by: Mark Rutland Cc: Andy Lutomirski Cc: Jinjie Ruan Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Reviewed-by: Jinjie Ruan Acked-by: Peter Zijlstra (Intel) Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/include/asm/entry-common.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/arch/arm64/include/asm/entry-common.h b/arch/arm64/include/asm/entry-common.h index cab8cd78f6938..20f0a7c7bde15 100644 --- a/arch/arm64/include/asm/entry-common.h +++ b/arch/arm64/include/asm/entry-common.h @@ -29,14 +29,19 @@ static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs, static inline bool arch_irqentry_exit_need_resched(void) { - /* - * DAIF.DA are cleared at the start of IRQ/FIQ handling, and when GIC - * priority masking is used the GIC irqchip driver will clear DAIF.IF - * using gic_arch_enable_irqs() for normal IRQs. If anything is set in - * DAIF we must have handled an NMI, so skip preemption. - */ - if (system_uses_irq_prio_masking() && read_sysreg(daif)) - return false; + if (system_uses_irq_prio_masking()) { + /* + * DAIF.DA are cleared at the start of IRQ/FIQ handling, and when GIC + * priority masking is used the GIC irqchip driver will clear DAIF.IF + * using gic_arch_enable_irqs() for normal IRQs. If anything is set in + * DAIF we must have handled an NMI, so skip preemption. + */ + if (read_sysreg(daif)) + return false; + } else { + if (read_sysreg(daif) & (PSR_D_BIT | PSR_A_BIT)) + return false; + } /* * Preempting a task from an IRQ means we leave copies of PSTATE From bcfdf159d128debbe31630141cb08bb5d5a02cfc Mon Sep 17 00:00:00 2001 From: Haoyu Lu Date: Tue, 7 Apr 2026 11:31:15 +0800 Subject: [PATCH 0318/1518] ACPI: AGDI: fix missing newline in error message [ Upstream commit b178330b67abb7293b6de28b2a49d49c83962db5 ] Add the missing trailing newline to the dev_err() message printed when SDEI event registration fails. This keeps the error output as a properly terminated log line. Fixes: a2a591fb76e6 ("ACPI: AGDI: Add driver for Arm Generic Diagnostic Dump and Reset device") Reviewed-by: Ilkka Koskinen Signed-off-by: Haoyu Lu Reviewed-by: Hanjun Guo Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- drivers/acpi/arm64/agdi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/arm64/agdi.c b/drivers/acpi/arm64/agdi.c index e0df3daa4abf0..abe29705744e5 100644 --- a/drivers/acpi/arm64/agdi.c +++ b/drivers/acpi/arm64/agdi.c @@ -32,7 +32,7 @@ static int agdi_sdei_probe(struct platform_device *pdev, err = sdei_event_register(adata->sdei_event, agdi_sdei_handler, pdev); if (err) { - dev_err(&pdev->dev, "Failed to register for SDEI event %d", + dev_err(&pdev->dev, "Failed to register for SDEI event %d\n", adata->sdei_event); return err; } From f33fb701ab7e709ba965d6a7da6e4141b725fdbf Mon Sep 17 00:00:00 2001 From: Wang Wensheng Date: Sun, 5 Apr 2026 19:42:31 +0800 Subject: [PATCH 0319/1518] arm64: kexec: Remove duplicate allocation for trans_pgd [ Upstream commit ee020bf6f14094c9ae434bb37e6957a1fdad513c ] trans_pgd would be allocated in trans_pgd_create_copy(), so remove the duplicate allocation before calling trans_pgd_create_copy(). Fixes: 3744b5280e67 ("arm64: kexec: install a copy of the linear-map") Signed-off-by: Wang Wensheng Reviewed-by: Pasha Tatashin Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/kernel/machine_kexec.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 6f121a0164a48..28df62051cc97 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -129,9 +129,6 @@ int machine_kexec_post_load(struct kimage *kimage) } /* Create a copy of the linear map */ - trans_pgd = kexec_page_alloc(kimage); - if (!trans_pgd) - return -ENOMEM; rc = trans_pgd_create_copy(&info, &trans_pgd, PAGE_OFFSET, PAGE_END); if (rc) return rc; From 0d8726af877e0d6256990e33ac0cdc38b51f989e Mon Sep 17 00:00:00 2001 From: Cosmin Ratiu Date: Wed, 8 Apr 2026 14:52:40 +0300 Subject: [PATCH 0320/1518] macsec: Support VLAN-filtering lower devices [ Upstream commit a363b1c8be879c79a688eaf93ba01b63f8b0e63c ] VLAN-filtering is done through two netdev features (NETIF_F_HW_VLAN_CTAG_FILTER and NETIF_F_HW_VLAN_STAG_FILTER) and two netdev ops (ndo_vlan_rx_add_vid and ndo_vlan_rx_kill_vid). Implement these and advertise the features if the lower device supports them. This allows proper VLAN filtering to work on top of MACsec devices, when the lower device is capable of VLAN filtering. As a concrete example, having this chain of interfaces now works: vlan_filtering_capable_dev(1) -> macsec_dev(2) -> macsec_vlan_dev(3) Before the mentioned commit this used to accidentally work because the MACsec device (and thus the lower device) was put in promiscuous mode and the VLAN filter was not used. But after commit [1] correctly made the macsec driver expose the IFF_UNICAST_FLT flag, promiscuous mode was no longer used and VLAN filters on dev 1 kicked in. Without support in dev 2 for propagating VLAN filters down, the register_vlan_dev -> vlan_vid_add -> __vlan_vid_add -> vlan_add_rx_filter_info call from dev 3 is silently eaten (because vlan_hw_filter_capable returns false and vlan_add_rx_filter_info silently succeeds). For MACsec, VLAN filters are only relevant for offload, otherwise the VLANs are encrypted and the lower devices don't care about them. So VLAN filters are only passed on to lower devices in offload mode. Flipping between offload modes now needs to offload/unoffload the filters with vlan_{get,drop}_rx_*_filter_info(). To avoid the back-and-forth filter updating during rollback, the setting of macsec->offload is moved after the add/del secy ops. This is safe since none of the code called from those requires macsec->offload. In case adding the filters fails, the added ones are rolled back and an error is returned to the operation toggling the offload state. Fixes: 0349659fd72f ("macsec: set IFF_UNICAST_FLT priv flag") Signed-off-by: Cosmin Ratiu Reviewed-by: Sabrina Dubroca Link: https://patch.msgid.link/20260408115240.1636047-5-cratiu@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/macsec.c | 71 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 63 insertions(+), 8 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 5200fd5a10e5c..5d820ef619469 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2584,7 +2584,9 @@ static void macsec_inherit_tso_max(struct net_device *dev) netif_inherit_tso_max(dev, macsec->real_dev); } -static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload) +static int macsec_update_offload(struct net_device *dev, + enum macsec_offload offload, + struct netlink_ext_ack *extack) { enum macsec_offload prev_offload; const struct macsec_ops *ops; @@ -2616,14 +2618,35 @@ static int macsec_update_offload(struct net_device *dev, enum macsec_offload off if (!ops) return -EOPNOTSUPP; - macsec->offload = offload; - ctx.secy = &macsec->secy; ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx) : macsec_offload(ops->mdo_add_secy, &ctx); - if (ret) { - macsec->offload = prev_offload; + if (ret) return ret; + + /* Remove VLAN filters when disabling offload. */ + if (offload == MACSEC_OFFLOAD_OFF) { + vlan_drop_rx_ctag_filter_info(dev); + vlan_drop_rx_stag_filter_info(dev); + } + macsec->offload = offload; + /* Add VLAN filters when enabling offload. */ + if (prev_offload == MACSEC_OFFLOAD_OFF) { + ret = vlan_get_rx_ctag_filter_info(dev); + if (ret) { + NL_SET_ERR_MSG_FMT(extack, + "adding ctag VLAN filters failed, err %d", + ret); + goto rollback_offload; + } + ret = vlan_get_rx_stag_filter_info(dev); + if (ret) { + NL_SET_ERR_MSG_FMT(extack, + "adding stag VLAN filters failed, err %d", + ret); + vlan_drop_rx_ctag_filter_info(dev); + goto rollback_offload; + } } macsec_set_head_tail_room(dev); @@ -2633,6 +2656,12 @@ static int macsec_update_offload(struct net_device *dev, enum macsec_offload off netdev_update_features(dev); + return 0; + +rollback_offload: + macsec->offload = prev_offload; + macsec_offload(ops->mdo_del_secy, &ctx); + return ret; } @@ -2673,7 +2702,7 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]); if (macsec->offload != offload) - ret = macsec_update_offload(dev, offload); + ret = macsec_update_offload(dev, offload, info->extack); out: rtnl_unlock(); return ret; @@ -3486,7 +3515,8 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, } #define MACSEC_FEATURES \ - (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) + (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ + NETIF_F_HW_VLAN_STAG_FILTER | NETIF_F_HW_VLAN_CTAG_FILTER) #define MACSEC_OFFLOAD_FEATURES \ (MACSEC_FEATURES | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES | \ @@ -3707,6 +3737,29 @@ static int macsec_set_mac_address(struct net_device *dev, void *p) return err; } +static int macsec_vlan_rx_add_vid(struct net_device *dev, + __be16 proto, u16 vid) +{ + struct macsec_dev *macsec = netdev_priv(dev); + + if (!macsec_is_offloaded(macsec)) + return 0; + + return vlan_vid_add(macsec->real_dev, proto, vid); +} + +static int macsec_vlan_rx_kill_vid(struct net_device *dev, + __be16 proto, u16 vid) +{ + struct macsec_dev *macsec = netdev_priv(dev); + + if (!macsec_is_offloaded(macsec)) + return 0; + + vlan_vid_del(macsec->real_dev, proto, vid); + return 0; +} + static int macsec_change_mtu(struct net_device *dev, int new_mtu) { struct macsec_dev *macsec = macsec_priv(dev); @@ -3748,6 +3801,8 @@ static const struct net_device_ops macsec_netdev_ops = { .ndo_set_rx_mode = macsec_dev_set_rx_mode, .ndo_change_rx_flags = macsec_dev_change_rx_flags, .ndo_set_mac_address = macsec_set_mac_address, + .ndo_vlan_rx_add_vid = macsec_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = macsec_vlan_rx_kill_vid, .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, @@ -3912,7 +3967,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], offload = nla_get_u8(data[IFLA_MACSEC_OFFLOAD]); if (macsec->offload != offload) { macsec_offload_state_change = true; - ret = macsec_update_offload(dev, offload); + ret = macsec_update_offload(dev, offload, extack); if (ret) goto cleanup; } From 4cab761fc51c65aef741fcece4a18f3554edbc09 Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Mon, 6 Apr 2026 10:57:54 -0700 Subject: [PATCH 0321/1518] net: bcmgenet: fix off-by-one in bcmgenet_put_txcb [ Upstream commit 57f3f53d2c9c5a9e133596e2f7bc1c50688a6d38 ] The write_ptr points to the next open tx_cb. We want to return the tx_cb that gets rewinded, so we must rewind the pointer first then return the tx_cb that it points to. That way the txcb can be correctly cleaned up. Fixes: 876dbadd53a7 ("net: bcmgenet: Fix unmapping of fragments in bcmgenet_xmit()") Signed-off-by: Justin Chen Reviewed-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260406175756.134567-2-justin.chen@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index e142939d87cbe..1791523b83383 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1815,15 +1815,15 @@ static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv, { struct enet_cb *tx_cb_ptr; - tx_cb_ptr = ring->cbs; - tx_cb_ptr += ring->write_ptr - ring->cb_ptr; - /* Rewinding local write pointer */ if (ring->write_ptr == ring->cb_ptr) ring->write_ptr = ring->end_ptr; else ring->write_ptr--; + tx_cb_ptr = ring->cbs; + tx_cb_ptr += ring->write_ptr - ring->cb_ptr; + return tx_cb_ptr; } From 25ff3a3e47ea635ec08dc93e84dd2bfe15abfebb Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Mon, 6 Apr 2026 10:57:55 -0700 Subject: [PATCH 0322/1518] net: bcmgenet: fix leaking free_bds [ Upstream commit 3f3168300efb839028328d720ab3962f91d6a0d0 ] While reclaiming the tx queue we fast forward the write pointer to drop any data in flight. These dropped frames are not added back to the pool of free bds. We also need to tell the netdev that we are dropping said data. Fixes: f1bacae8b655 ("net: bcmgenet: support reclaiming unsent Tx packets") Signed-off-by: Justin Chen Reviewed-by: Florian Fainelli Reviewed-by: Nicolai Buchwitz Tested-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260406175756.134567-3-justin.chen@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1791523b83383..7d4d394c6ab1e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1981,6 +1981,7 @@ static unsigned int bcmgenet_tx_reclaim(struct net_device *dev, drop = (ring->prod_index - ring->c_index) & DMA_C_INDEX_MASK; released += drop; ring->prod_index = ring->c_index & DMA_C_INDEX_MASK; + ring->free_bds += drop; while (drop--) { cb_ptr = bcmgenet_put_txcb(priv, ring); skb = cb_ptr->skb; @@ -1992,6 +1993,7 @@ static unsigned int bcmgenet_tx_reclaim(struct net_device *dev, } if (skb) dev_consume_skb_any(skb); + netdev_tx_reset_queue(netdev_get_tx_queue(dev, ring->index)); bcmgenet_tdma_ring_writel(priv, ring->index, ring->prod_index, TDMA_PROD_INDEX); wr_ptr = ring->write_ptr * WORDS_PER_BD(priv); From c270e2bec3e55a716d25c35341091339457ac883 Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Mon, 6 Apr 2026 10:57:56 -0700 Subject: [PATCH 0323/1518] net: bcmgenet: fix racing timeout handler [ Upstream commit 5393b2b5bee2ac51a0043dc7f4ac3475f053d08d ] The bcmgenet_timeout handler tries to take down all tx queues when a single queue times out. This is over zealous and causes many race conditions with queues that are still chugging along. Instead lets only restart the timed out queue. Fixes: 13ea657806cf ("net: bcmgenet: improve TX timeout") Signed-off-by: Justin Chen Reviewed-by: Florian Fainelli Reviewed-by: Nicolai Buchwitz Tested-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260406175756.134567-4-justin.chen@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../net/ethernet/broadcom/genet/bcmgenet.c | 22 ++++++++----------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 7d4d394c6ab1e..63cdf6d9d0772 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3475,27 +3475,23 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring) static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue) { struct bcmgenet_priv *priv = netdev_priv(dev); - u32 int1_enable = 0; - unsigned int q; + struct bcmgenet_tx_ring *ring = &priv->tx_rings[txqueue]; + struct netdev_queue *txq = netdev_get_tx_queue(dev, txqueue); netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n"); - for (q = 0; q <= priv->hw_params->tx_queues; q++) - bcmgenet_dump_tx_queue(&priv->tx_rings[q]); - - bcmgenet_tx_reclaim_all(dev); + bcmgenet_dump_tx_queue(ring); - for (q = 0; q <= priv->hw_params->tx_queues; q++) - int1_enable |= (1 << q); + bcmgenet_tx_reclaim(dev, ring, true); - /* Re-enable TX interrupts if disabled */ - bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); + /* Re-enable the TX interrupt for this ring */ + bcmgenet_intrl2_1_writel(priv, 1 << txqueue, INTRL2_CPU_MASK_CLEAR); - netif_trans_update(dev); + txq_trans_cond_update(txq); - BCMGENET_STATS64_INC((&priv->tx_rings[txqueue].stats64), errors); + BCMGENET_STATS64_INC((&ring->stats64), errors); - netif_tx_wake_all_queues(dev); + netif_tx_wake_queue(txq); } #define MAX_MDF_FILTER 17 From 6d28910c51944ffe3bf79f91b6d3b3026e159d16 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 7 Apr 2026 08:48:04 +0200 Subject: [PATCH 0324/1518] net: airoha: Add dma_rmb() and READ_ONCE() in airoha_qdma_rx_process() [ Upstream commit 4ae0604a0673e11e2075b178387151fcad5111b5 ] Add missing dma_rmb() in airoha_qdma_rx_process routine to make sure the DMA read operations are completed when the NIC reports the processing on the current descriptor is done. Moreover, add missing READ_ONCE() in airoha_qdma_rx_process() for DMA descriptor control fields in order to avoid any compiler reordering. Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260407-airoha_qdma_rx_process-fix-reordering-v3-1-91c36e9da31f@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index bdf600fea9508..060865b98880e 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -596,7 +596,7 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) static int airoha_qdma_get_gdm_port(struct airoha_eth *eth, struct airoha_qdma_desc *desc) { - u32 port, sport, msg1 = le32_to_cpu(desc->msg1); + u32 port, sport, msg1 = le32_to_cpu(READ_ONCE(desc->msg1)); sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK, msg1); switch (sport) { @@ -624,21 +624,24 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) while (done < budget) { struct airoha_queue_entry *e = &q->entry[q->tail]; struct airoha_qdma_desc *desc = &q->desc[q->tail]; - u32 hash, reason, msg1 = le32_to_cpu(desc->msg1); - struct page *page = virt_to_head_page(e->buf); - u32 desc_ctrl = le32_to_cpu(desc->ctrl); + u32 hash, reason, msg1, desc_ctrl; struct airoha_gdm_port *port; int data_len, len, p; + struct page *page; + desc_ctrl = le32_to_cpu(READ_ONCE(desc->ctrl)); if (!(desc_ctrl & QDMA_DESC_DONE_MASK)) break; + dma_rmb(); + q->tail = (q->tail + 1) % q->ndesc; q->queued--; dma_sync_single_for_cpu(eth->dev, e->dma_addr, SKB_WITH_OVERHEAD(q->buf_size), dir); + page = virt_to_head_page(e->buf); len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl); data_len = q->skb ? q->buf_size : SKB_WITH_OVERHEAD(q->buf_size); @@ -682,8 +685,8 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) * DMA descriptor. Report DSA tag to the DSA stack * via skb dst info. */ - u32 sptag = FIELD_GET(QDMA_ETH_RXMSG_SPTAG, - le32_to_cpu(desc->msg0)); + u32 msg0 = le32_to_cpu(READ_ONCE(desc->msg0)); + u32 sptag = FIELD_GET(QDMA_ETH_RXMSG_SPTAG, msg0); if (sptag < ARRAY_SIZE(port->dsa_meta) && port->dsa_meta[sptag]) @@ -691,6 +694,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) &port->dsa_meta[sptag]->dst); } + msg1 = le32_to_cpu(READ_ONCE(desc->msg1)); hash = FIELD_GET(AIROHA_RXD4_FOE_ENTRY, msg1); if (hash != AIROHA_RXD4_FOE_ENTRY) skb_set_hash(q->skb, jhash_1word(hash, 0), From b9ee2c6c076151eea8531ca5f6802b99f94de438 Mon Sep 17 00:00:00 2001 From: Mohsin Bashir Date: Tue, 7 Apr 2026 17:24:15 -0700 Subject: [PATCH 0325/1518] eth: fbnic: Use wake instead of start [ Upstream commit 12ff2a4aee6c86746623d5aed24389dbf6dffded ] fbnic_up() calls netif_tx_start_all_queues(), which only clears __QUEUE_STATE_DRV_XOFF. If qdisc backlog has accumulated on any TX queue before the reconfiguration (e.g. ring resize via ethtool -G), start does not call __netif_schedule() to kick the qdisc, so the pending backlog is never drained and the queue stalls. Switch to netif_tx_wake_all_queues(), which clears DRV_XOFF and also calls __netif_schedule() on every queue, ensuring any backlog that built up before the down/up cycle is promptly dequeued. Fixes: bc6107771bb4 ("eth: fbnic: Allocate a netdevice and napi vectors with queues") Signed-off-by: Mohsin Bashir Link: https://patch.msgid.link/20260408002415.2963915-1-mohsin.bashr@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/meta/fbnic/fbnic_pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 698b8a85afb31..99b7c0718e80e 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -139,7 +139,7 @@ void fbnic_up(struct fbnic_net *fbn) /* Enable Tx/Rx processing */ fbnic_napi_enable(fbn); - netif_tx_start_all_queues(fbn->netdev); + netif_tx_wake_all_queues(fbn->netdev); fbnic_service_task_start(fbn); } From 35a38df4085b3abe6c2d2bbcb6742a6d859cd3f1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 4 Apr 2026 12:12:59 +0200 Subject: [PATCH 0326/1518] netfilter: xt_socket: enable defrag after all other checks [ Upstream commit 542be3fa5aff54210a02954c38f07e53ea9bdafd ] Originally this did not matter because defrag was enabled once per netns and only disabled again on netns dismantle. When this got changed I should have adjusted checkentry to not leave defrag enabled on error. Fixes: de8c12110a13 ("netfilter: disable defrag once its no longer needed") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/xt_socket.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 76e01f292aaff..811e53bee4085 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -168,52 +168,41 @@ static int socket_mt_enable_defrag(struct net *net, int family) static int socket_mt_v1_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; - int err; - - err = socket_mt_enable_defrag(par->net, par->family); - if (err) - return err; if (info->flags & ~XT_SOCKET_FLAGS_V1) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); return -EINVAL; } - return 0; + + return socket_mt_enable_defrag(par->net, par->family); } static int socket_mt_v2_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo; - int err; - - err = socket_mt_enable_defrag(par->net, par->family); - if (err) - return err; if (info->flags & ~XT_SOCKET_FLAGS_V2) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); return -EINVAL; } - return 0; + + return socket_mt_enable_defrag(par->net, par->family); } static int socket_mt_v3_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo3 *info = (struct xt_socket_mtinfo3 *)par->matchinfo; - int err; - err = socket_mt_enable_defrag(par->net, par->family); - if (err) - return err; if (info->flags & ~XT_SOCKET_FLAGS_V3) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V3); return -EINVAL; } - return 0; + + return socket_mt_enable_defrag(par->net, par->family); } static void socket_mt_destroy(const struct xt_mtdtor_param *par) From b79d567fbc530efc2c3f1ed77e48b66fc8218571 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 9 Apr 2026 13:30:41 +0200 Subject: [PATCH 0327/1518] netfilter: nft_fwd_netdev: check ttl/hl before forwarding [ Upstream commit 1dfd95bdf4d18d263aa8fad06bfb9f4d9c992b18 ] Drop packets if their ttl/hl is too small for forwarding. Fixes: d32de98ea70f ("netfilter: nft_fwd_netdev: allow to forward packets via neighbour layer") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_fwd_netdev.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 152a9fb4d23af..256e832f1bb99 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -116,6 +116,11 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, goto out; } iph = ip_hdr(skb); + if (iph->ttl <= 1) { + verdict = NF_DROP; + goto out; + } + ip_decrease_ttl(iph); neigh_table = NEIGH_ARP_TABLE; break; @@ -132,6 +137,11 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, goto out; } ip6h = ipv6_hdr(skb); + if (ip6h->hop_limit <= 1) { + verdict = NF_DROP; + goto out; + } + ip6h->hop_limit--; neigh_table = NEIGH_ND_TABLE; break; From d0862de7c866c5bd7c32531f66738c21197af888 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Wed, 8 Apr 2026 08:45:35 -0700 Subject: [PATCH 0328/1518] bpf: fix mm lifecycle in open-coded task_vma iterator [ Upstream commit d8e27d2d22b6e2df3a0125b8c08e9aace38c954c ] The open-coded task_vma iterator reads task->mm locklessly and acquires mmap_read_trylock() but never calls mmget(). If the task exits concurrently, the mm_struct can be freed as it is not SLAB_TYPESAFE_BY_RCU, resulting in a use-after-free. Safely read task->mm with a trylock on alloc_lock and acquire an mm reference. Drop the reference via bpf_iter_mmput_async() in _destroy() and error paths. bpf_iter_mmput_async() is a local wrapper around mmput_async() with a fallback to mmput() on !CONFIG_MMU. Reject irqs-disabled contexts (including NMI) up front. Operations used by _next() and _destroy() (mmap_read_unlock, bpf_iter_mmput_async) take spinlocks with IRQs disabled (pool->lock, pi_lock). Running from NMI or from a tracepoint that fires with those locks held could deadlock. A trylock on alloc_lock is used instead of the blocking task_lock() (get_task_mm) to avoid a deadlock when a softirq BPF program iterates a task that already holds its alloc_lock on the same CPU. Fixes: 4ac454682158 ("bpf: Introduce task_vma open-coded iterator kfuncs") Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20260408154539.3832150-2-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/task_iter.c | 54 +++++++++++++++++++++++++++++++++++++++--- 1 file changed, 51 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 98d9b4c0daff3..c1f5fbe9dc2f3 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "mmap_unlock_work.h" static const char * const iter_task_type_names[] = { @@ -794,6 +795,15 @@ const struct bpf_func_proto bpf_find_vma_proto = { .arg5_type = ARG_ANYTHING, }; +static inline void bpf_iter_mmput_async(struct mm_struct *mm) +{ +#ifdef CONFIG_MMU + mmput_async(mm); +#else + mmput(mm); +#endif +} + struct bpf_iter_task_vma_kern_data { struct task_struct *task; struct mm_struct *mm; @@ -825,6 +835,24 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma)); BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma)); + /* bpf_iter_mmput_async() needs mmput_async() which requires CONFIG_MMU */ + if (!IS_ENABLED(CONFIG_MMU)) { + kit->data = NULL; + return -EOPNOTSUPP; + } + + /* + * Reject irqs-disabled contexts including NMI. Operations used + * by _next() and _destroy() (mmap_read_unlock, bpf_iter_mmput_async) + * can take spinlocks with IRQs disabled (pi_lock, pool->lock). + * Running from NMI or from a tracepoint that fires with those + * locks held could deadlock. + */ + if (irqs_disabled()) { + kit->data = NULL; + return -EBUSY; + } + /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized * before, so non-NULL kit->data doesn't point to previously * bpf_mem_alloc'd bpf_iter_task_vma_kern_data @@ -834,7 +862,25 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, return -ENOMEM; kit->data->task = get_task_struct(task); + /* + * Safely read task->mm and acquire an mm reference. + * + * Cannot use get_task_mm() because its task_lock() is a + * blocking spin_lock that would deadlock if the target task + * already holds alloc_lock on this CPU (e.g. a softirq BPF + * program iterating a task interrupted while holding its + * alloc_lock). + */ + if (!spin_trylock(&task->alloc_lock)) { + err = -EBUSY; + goto err_cleanup_iter; + } kit->data->mm = task->mm; + if (kit->data->mm && !(task->flags & PF_KTHREAD)) + mmget(kit->data->mm); + else + kit->data->mm = NULL; + spin_unlock(&task->alloc_lock); if (!kit->data->mm) { err = -ENOENT; goto err_cleanup_iter; @@ -844,15 +890,16 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work); if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) { err = -EBUSY; - goto err_cleanup_iter; + goto err_cleanup_mmget; } vma_iter_init(&kit->data->vmi, kit->data->mm, addr); return 0; +err_cleanup_mmget: + bpf_iter_mmput_async(kit->data->mm); err_cleanup_iter: - if (kit->data->task) - put_task_struct(kit->data->task); + put_task_struct(kit->data->task); bpf_mem_free(&bpf_global_ma, kit->data); /* NULL kit->data signals failed bpf_iter_task_vma initialization */ kit->data = NULL; @@ -875,6 +922,7 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) if (kit->data) { bpf_mmap_unlock_mm(kit->data->work, kit->data->mm); put_task_struct(kit->data->task); + bpf_iter_mmput_async(kit->data->mm); bpf_mem_free(&bpf_global_ma, kit->data); } } From 3745834cf761f88ac3a8f5e65dbaebe11b04a846 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Wed, 8 Apr 2026 08:45:36 -0700 Subject: [PATCH 0329/1518] bpf: switch task_vma iterator from mmap_lock to per-VMA locks [ Upstream commit bee9ef4a40a277bf401be43d39ba7f7f063cf39c ] The open-coded task_vma iterator holds mmap_lock for the entire duration of iteration, increasing contention on this highly contended lock. Switch to per-VMA locking. Find the next VMA via an RCU-protected maple tree walk and lock it with lock_vma_under_rcu(). lock_next_vma() is not used because its fallback takes mmap_read_lock(), and the iterator must work in non-sleepable contexts. lock_vma_under_rcu() is a point lookup (mas_walk) that finds the VMA containing a given address but cannot iterate across gaps. An RCU-protected vma_next() walk (mas_find) first locates the next VMA's vm_start to pass to lock_vma_under_rcu(). Between the RCU walk and the lock, the VMA may be removed, shrunk, or write-locked. On failure, advance past it using vm_end from the RCU walk. Because the VMA slab is SLAB_TYPESAFE_BY_RCU, vm_end may be stale; fall back to PAGE_SIZE advancement when it does not make forward progress. Concurrent VMA insertions at addresses already passed by the iterator are not detected. CONFIG_PER_VMA_LOCK is required; return -EOPNOTSUPP without it. Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20260408154539.3832150-3-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Stable-dep-of: 4cbee026db54 ("bpf: return VMA snapshot from task_vma iterator") Signed-off-by: Sasha Levin --- kernel/bpf/task_iter.c | 91 +++++++++++++++++++++++++++++++++--------- 1 file changed, 73 insertions(+), 18 deletions(-) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index c1f5fbe9dc2f3..87e87f18913d9 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include "mmap_unlock_work.h" @@ -807,8 +808,8 @@ static inline void bpf_iter_mmput_async(struct mm_struct *mm) struct bpf_iter_task_vma_kern_data { struct task_struct *task; struct mm_struct *mm; - struct mmap_unlock_irq_work *work; - struct vma_iterator vmi; + struct vm_area_struct *locked_vma; + u64 next_addr; }; struct bpf_iter_task_vma { @@ -829,21 +830,19 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, struct task_struct *task, u64 addr) { struct bpf_iter_task_vma_kern *kit = (void *)it; - bool irq_work_busy = false; int err; BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma)); BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma)); - /* bpf_iter_mmput_async() needs mmput_async() which requires CONFIG_MMU */ - if (!IS_ENABLED(CONFIG_MMU)) { + if (!IS_ENABLED(CONFIG_PER_VMA_LOCK)) { kit->data = NULL; return -EOPNOTSUPP; } /* * Reject irqs-disabled contexts including NMI. Operations used - * by _next() and _destroy() (mmap_read_unlock, bpf_iter_mmput_async) + * by _next() and _destroy() (vma_end_read, bpf_iter_mmput_async) * can take spinlocks with IRQs disabled (pi_lock, pool->lock). * Running from NMI or from a tracepoint that fires with those * locks held could deadlock. @@ -886,18 +885,10 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, goto err_cleanup_iter; } - /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */ - irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work); - if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) { - err = -EBUSY; - goto err_cleanup_mmget; - } - - vma_iter_init(&kit->data->vmi, kit->data->mm, addr); + kit->data->locked_vma = NULL; + kit->data->next_addr = addr; return 0; -err_cleanup_mmget: - bpf_iter_mmput_async(kit->data->mm); err_cleanup_iter: put_task_struct(kit->data->task); bpf_mem_free(&bpf_global_ma, kit->data); @@ -906,13 +897,76 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, return err; } +/* + * Find and lock the next VMA at or after data->next_addr. + * + * lock_vma_under_rcu() is a point lookup (mas_walk): it finds the VMA + * containing a given address but cannot iterate. An RCU-protected + * maple tree walk with vma_next() (mas_find) is needed first to locate + * the next VMA's vm_start across any gap. + * + * Between the RCU walk and the lock, the VMA may be removed, shrunk, + * or write-locked. On failure, advance past it using vm_end from the + * RCU walk. SLAB_TYPESAFE_BY_RCU can make vm_end stale, so fall back + * to PAGE_SIZE advancement to guarantee forward progress. + */ +static struct vm_area_struct * +bpf_iter_task_vma_find_next(struct bpf_iter_task_vma_kern_data *data) +{ + struct vm_area_struct *vma; + struct vma_iterator vmi; + unsigned long start, end; + +retry: + rcu_read_lock(); + vma_iter_init(&vmi, data->mm, data->next_addr); + vma = vma_next(&vmi); + if (!vma) { + rcu_read_unlock(); + return NULL; + } + start = vma->vm_start; + end = vma->vm_end; + rcu_read_unlock(); + + vma = lock_vma_under_rcu(data->mm, start); + if (!vma) { + if (end <= data->next_addr) + data->next_addr += PAGE_SIZE; + else + data->next_addr = end; + goto retry; + } + + if (unlikely(vma->vm_end <= data->next_addr)) { + data->next_addr += PAGE_SIZE; + vma_end_read(vma); + goto retry; + } + + return vma; +} + __bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) { struct bpf_iter_task_vma_kern *kit = (void *)it; + struct vm_area_struct *vma; if (!kit->data) /* bpf_iter_task_vma_new failed */ return NULL; - return vma_next(&kit->data->vmi); + + if (kit->data->locked_vma) { + vma_end_read(kit->data->locked_vma); + kit->data->locked_vma = NULL; + } + + vma = bpf_iter_task_vma_find_next(kit->data); + if (!vma) + return NULL; + + kit->data->locked_vma = vma; + kit->data->next_addr = vma->vm_end; + return vma; } __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) @@ -920,7 +974,8 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) struct bpf_iter_task_vma_kern *kit = (void *)it; if (kit->data) { - bpf_mmap_unlock_mm(kit->data->work, kit->data->mm); + if (kit->data->locked_vma) + vma_end_read(kit->data->locked_vma); put_task_struct(kit->data->task); bpf_iter_mmput_async(kit->data->mm); bpf_mem_free(&bpf_global_ma, kit->data); From 592226d138378601ae28eb890e2bbc23ec3600f7 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Wed, 8 Apr 2026 08:45:37 -0700 Subject: [PATCH 0330/1518] bpf: return VMA snapshot from task_vma iterator [ Upstream commit 4cbee026db54cad39c39db4d356100cb133412b3 ] Holding the per-VMA lock across the BPF program body creates a lock ordering problem when helpers acquire locks that depend on mmap_lock: vm_lock -> i_rwsem -> mmap_lock -> vm_lock Snapshot the VMA under the per-VMA lock in _next() via memcpy(), then drop the lock before returning. The BPF program accesses only the snapshot. The verifier only trusts vm_mm and vm_file pointers (see BTF_TYPE_SAFE_TRUSTED_OR_NULL in verifier.c). vm_file is reference- counted with get_file() under the lock and released via fput() on the next iteration or in _destroy(). vm_mm is already correct because lock_vma_under_rcu() verifies vma->vm_mm == mm. All other pointers are left as-is by memcpy() since the verifier treats them as untrusted. Fixes: 4ac454682158 ("bpf: Introduce task_vma open-coded iterator kfuncs") Signed-off-by: Puranjay Mohan Acked-by: Andrii Nakryiko Acked-by: Mykyta Yatsenko Link: https://lore.kernel.org/r/20260408154539.3832150-4-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/task_iter.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 87e87f18913d9..e791ae065c39b 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -808,7 +808,7 @@ static inline void bpf_iter_mmput_async(struct mm_struct *mm) struct bpf_iter_task_vma_kern_data { struct task_struct *task; struct mm_struct *mm; - struct vm_area_struct *locked_vma; + struct vm_area_struct snapshot; u64 next_addr; }; @@ -842,7 +842,7 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, /* * Reject irqs-disabled contexts including NMI. Operations used - * by _next() and _destroy() (vma_end_read, bpf_iter_mmput_async) + * by _next() and _destroy() (vma_end_read, fput, bpf_iter_mmput_async) * can take spinlocks with IRQs disabled (pi_lock, pool->lock). * Running from NMI or from a tracepoint that fires with those * locks held could deadlock. @@ -885,7 +885,7 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, goto err_cleanup_iter; } - kit->data->locked_vma = NULL; + kit->data->snapshot.vm_file = NULL; kit->data->next_addr = addr; return 0; @@ -947,26 +947,45 @@ bpf_iter_task_vma_find_next(struct bpf_iter_task_vma_kern_data *data) return vma; } +static void bpf_iter_task_vma_snapshot_reset(struct vm_area_struct *snap) +{ + if (snap->vm_file) { + fput(snap->vm_file); + snap->vm_file = NULL; + } +} + __bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) { struct bpf_iter_task_vma_kern *kit = (void *)it; - struct vm_area_struct *vma; + struct vm_area_struct *snap, *vma; if (!kit->data) /* bpf_iter_task_vma_new failed */ return NULL; - if (kit->data->locked_vma) { - vma_end_read(kit->data->locked_vma); - kit->data->locked_vma = NULL; - } + snap = &kit->data->snapshot; + + bpf_iter_task_vma_snapshot_reset(snap); vma = bpf_iter_task_vma_find_next(kit->data); if (!vma) return NULL; - kit->data->locked_vma = vma; + memcpy(snap, vma, sizeof(*snap)); + + /* + * The verifier only trusts vm_mm and vm_file (see + * BTF_TYPE_SAFE_TRUSTED_OR_NULL in verifier.c). Take a reference + * on vm_file; vm_mm is already correct because lock_vma_under_rcu() + * verifies vma->vm_mm == mm. All other pointers are untrusted by + * the verifier and left as-is. + */ + if (snap->vm_file) + get_file(snap->vm_file); + kit->data->next_addr = vma->vm_end; - return vma; + vma_end_read(vma); + return snap; } __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) @@ -974,8 +993,7 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) struct bpf_iter_task_vma_kern *kit = (void *)it; if (kit->data) { - if (kit->data->locked_vma) - vma_end_read(kit->data->locked_vma); + bpf_iter_task_vma_snapshot_reset(&kit->data->snapshot); put_task_struct(kit->data->task); bpf_iter_mmput_async(kit->data->mm); bpf_mem_free(&bpf_global_ma, kit->data); From e1ed678855e315f90c70c1723e94157a9a82e660 Mon Sep 17 00:00:00 2001 From: Sechang Lim Date: Tue, 7 Apr 2026 10:38:23 +0000 Subject: [PATCH 0331/1518] bpf: Fix RCU stall in bpf_fd_array_map_clear() [ Upstream commit 4406942e65ca128c56c67443832988873c21d2e9 ] Add a missing cond_resched() in bpf_fd_array_map_clear() loop. For PROG_ARRAY maps with many entries this loop calls prog_array_map_poke_run() per entry which can be expensive, and without yielding this can cause RCU stalls under load: rcu: Stack dump where RCU GP kthread last ran: CPU: 0 UID: 0 PID: 30932 Comm: kworker/0:2 Not tainted 6.14.0-13195-g967e8def1100 #2 PREEMPT(undef) Workqueue: events prog_array_map_clear_deferred RIP: 0010:write_comp_data+0x38/0x90 kernel/kcov.c:246 Call Trace: prog_array_map_poke_run+0x77/0x380 kernel/bpf/arraymap.c:1096 __fd_array_map_delete_elem+0x197/0x310 kernel/bpf/arraymap.c:925 bpf_fd_array_map_clear kernel/bpf/arraymap.c:1000 [inline] prog_array_map_clear_deferred+0x119/0x1b0 kernel/bpf/arraymap.c:1141 process_one_work+0x898/0x19d0 kernel/workqueue.c:3238 process_scheduled_works kernel/workqueue.c:3319 [inline] worker_thread+0x770/0x10b0 kernel/workqueue.c:3400 kthread+0x465/0x880 kernel/kthread.c:464 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:153 ret_from_fork_asm+0x19/0x30 arch/x86/entry/entry_64.S:245 Reviewed-by: Sun Jian Fixes: da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") Signed-off-by: Sechang Lim Link: https://lore.kernel.org/r/20260407103823.3942156-1-rhkrqnwk98@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/arraymap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 80b1765a31596..248ab6854cf24 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1006,8 +1006,10 @@ static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - for (i = 0; i < array->map.max_entries; i++) + for (i = 0; i < array->map.max_entries; i++) { __fd_array_map_delete_elem(map, &i, need_defer); + cond_resched(); + } } static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, From 987af7625ceb1ee59d70eb0abd7af11c75e45d79 Mon Sep 17 00:00:00 2001 From: Mashiro Chen Date: Wed, 8 Apr 2026 01:31:01 +0800 Subject: [PATCH 0332/1518] net: hamradio: 6pack: fix uninit-value in sixpack_receive_buf [ Upstream commit bf9a38803b2626b01cc769aaf13485d8650f576f ] sixpack_receive_buf() does not properly skip bytes with TTY error flags. The while loop iterates through the flags buffer but never advances the data pointer (cp), and passes the original count (including error bytes) to sixpack_decode(). This causes sixpack_decode() to process bytes that should have been skipped due to TTY errors. The TTY layer does not guarantee that cp[i] holds a meaningful value when fp[i] is set, so passing those positions to sixpack_decode() results in KMSAN reporting an uninit-value read. Fix this by processing bytes one at a time, advancing cp on each iteration, and only passing valid (non-error) bytes to sixpack_decode(). This matches the pattern used by slip_receive_buf() and mkiss_receive_buf() for the same purpose. Reported-by: syzbot+ecdb8c9878a81eb21e54@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ecdb8c9878a81eb21e54 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Mashiro Chen Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260407173101.107352-1-mashiro.chen@mailbox.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/hamradio/6pack.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 885992951e8a6..c8b2dc5c1becc 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -391,7 +391,6 @@ static void sixpack_receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, size_t count) { struct sixpack *sp; - size_t count1; if (!count) return; @@ -401,16 +400,16 @@ static void sixpack_receive_buf(struct tty_struct *tty, const u8 *cp, return; /* Read the characters out of the buffer */ - count1 = count; - while (count) { - count--; + while (count--) { if (fp && *fp++) { if (!test_and_set_bit(SIXPF_ERROR, &sp->flags)) sp->dev->stats.rx_errors++; + cp++; continue; } + sixpack_decode(sp, cp, 1); + cp++; } - sixpack_decode(sp, cp, count1); tty_unthrottle(tty); } From ae1b40d3abc1d1309537f95e3b0f620c22b842b9 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:12 +0200 Subject: [PATCH 0333/1518] net: airoha: Add airoha_ppe_get_num_stats_entries() and airoha_ppe_get_num_total_stats_entries() [ Upstream commit 15f357cd4581ce6e02e5e97719320600783140ec ] Introduce airoha_ppe_get_num_stats_entries and airoha_ppe_get_num_total_stats_entries routines in order to make the code more readable controlling if CONFIG_NET_AIROHA_FLOW_STATS is enabled or disabled. Modify airoha_ppe_foe_get_flow_stats_index routine signature relying on airoha_ppe_get_num_total_stats_entries(). Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-3-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 02f729643959 ("net: airoha: Fix FE_PSE_BUF_SET configuration if PPE2 is available") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.h | 10 +-- drivers/net/ethernet/airoha/airoha_ppe.c | 101 ++++++++++++++++++----- 2 files changed, 81 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index cd13c1c1224f6..3e43f01e9a652 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -50,15 +50,9 @@ #define PPE_NUM 2 #define PPE1_SRAM_NUM_ENTRIES (8 * 1024) -#define PPE_SRAM_NUM_ENTRIES (2 * PPE1_SRAM_NUM_ENTRIES) -#ifdef CONFIG_NET_AIROHA_FLOW_STATS +#define PPE_SRAM_NUM_ENTRIES (PPE_NUM * PPE1_SRAM_NUM_ENTRIES) #define PPE1_STATS_NUM_ENTRIES (4 * 1024) -#else -#define PPE1_STATS_NUM_ENTRIES 0 -#endif /* CONFIG_NET_AIROHA_FLOW_STATS */ -#define PPE_STATS_NUM_ENTRIES (2 * PPE1_STATS_NUM_ENTRIES) -#define PPE1_SRAM_NUM_DATA_ENTRIES (PPE1_SRAM_NUM_ENTRIES - PPE1_STATS_NUM_ENTRIES) -#define PPE_SRAM_NUM_DATA_ENTRIES (2 * PPE1_SRAM_NUM_DATA_ENTRIES) +#define PPE_STATS_NUM_ENTRIES (PPE_NUM * PPE1_STATS_NUM_ENTRIES) #define PPE_DRAM_NUM_ENTRIES (16 * 1024) #define PPE_NUM_ENTRIES (PPE_SRAM_NUM_ENTRIES + PPE_DRAM_NUM_ENTRIES) #define PPE_HASH_MASK (PPE_NUM_ENTRIES - 1) diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index b3632f964a580..117dfc21d6a81 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -32,6 +32,24 @@ static const struct rhashtable_params airoha_l2_flow_table_params = { .automatic_shrinking = true, }; +static int airoha_ppe_get_num_stats_entries(struct airoha_ppe *ppe) +{ + if (!IS_ENABLED(CONFIG_NET_AIROHA_FLOW_STATS)) + return -EOPNOTSUPP; + + return PPE1_STATS_NUM_ENTRIES; +} + +static int airoha_ppe_get_total_num_stats_entries(struct airoha_ppe *ppe) +{ + int num_stats = airoha_ppe_get_num_stats_entries(ppe); + + if (num_stats > 0) + num_stats = num_stats * PPE_NUM; + + return num_stats; +} + static bool airoha_ppe2_is_enabled(struct airoha_eth *eth) { return airoha_fe_rr(eth, REG_PPE_GLO_CFG(1)) & PPE_GLO_CFG_EN_MASK; @@ -48,7 +66,7 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) { u32 sram_tb_size, sram_num_entries, dram_num_entries; struct airoha_eth *eth = ppe->eth; - int i; + int i, sram_num_stats_entries; sram_tb_size = PPE_SRAM_NUM_ENTRIES * sizeof(struct airoha_foe_entry); dram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(PPE_DRAM_NUM_ENTRIES); @@ -103,8 +121,13 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) } if (airoha_ppe2_is_enabled(eth)) { - sram_num_entries = - PPE_RAM_NUM_ENTRIES_SHIFT(PPE1_SRAM_NUM_DATA_ENTRIES); + sram_num_entries = PPE1_SRAM_NUM_ENTRIES; + sram_num_stats_entries = + airoha_ppe_get_num_stats_entries(ppe); + if (sram_num_stats_entries > 0) + sram_num_entries -= sram_num_stats_entries; + sram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(sram_num_entries); + airoha_fe_rmw(eth, REG_PPE_TB_CFG(0), PPE_SRAM_TB_NUM_ENTRY_MASK | PPE_DRAM_TB_NUM_ENTRY_MASK, @@ -120,8 +143,13 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, dram_num_entries)); } else { - sram_num_entries = - PPE_RAM_NUM_ENTRIES_SHIFT(PPE_SRAM_NUM_DATA_ENTRIES); + sram_num_entries = PPE_SRAM_NUM_ENTRIES; + sram_num_stats_entries = + airoha_ppe_get_total_num_stats_entries(ppe); + if (sram_num_stats_entries > 0) + sram_num_entries -= sram_num_stats_entries; + sram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(sram_num_entries); + airoha_fe_rmw(eth, REG_PPE_TB_CFG(0), PPE_SRAM_TB_NUM_ENTRY_MASK | PPE_DRAM_TB_NUM_ENTRY_MASK, @@ -482,13 +510,21 @@ static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe) return hash; } -static u32 airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, u32 hash) +static int airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, + u32 hash, u32 *index) { - if (!airoha_ppe2_is_enabled(ppe->eth)) - return hash; + int ppe_num_stats_entries; + + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return ppe_num_stats_entries; - return hash >= PPE_STATS_NUM_ENTRIES ? hash - PPE1_STATS_NUM_ENTRIES - : hash; + *index = hash; + if (airoha_ppe2_is_enabled(ppe->eth) && + hash >= ppe_num_stats_entries) + *index = *index - PPE_STATS_NUM_ENTRIES; + + return 0; } static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe, @@ -502,9 +538,13 @@ static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe, static void airoha_ppe_foe_flow_stats_reset(struct airoha_ppe *ppe, struct airoha_npu *npu) { - int i; + int i, ppe_num_stats_entries; + + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return; - for (i = 0; i < PPE_STATS_NUM_ENTRIES; i++) + for (i = 0; i < ppe_num_stats_entries; i++) airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, i); } @@ -515,10 +555,17 @@ static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe, { int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1); u32 index, pse_port, val, *data, *ib2, *meter; + int ppe_num_stats_entries; u8 nbq; - index = airoha_ppe_foe_get_flow_stats_index(ppe, hash); - if (index >= PPE_STATS_NUM_ENTRIES) + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return; + + if (airoha_ppe_foe_get_flow_stats_index(ppe, hash, &index)) + return; + + if (index >= ppe_num_stats_entries) return; if (type == PPE_PKT_TYPE_BRIDGE) { @@ -1160,11 +1207,19 @@ static int airoha_ppe_flow_offload_destroy(struct airoha_eth *eth, void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash, struct airoha_foe_stats64 *stats) { - u32 index = airoha_ppe_foe_get_flow_stats_index(ppe, hash); struct airoha_eth *eth = ppe->eth; + int ppe_num_stats_entries; struct airoha_npu *npu; + u32 index; + + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return; - if (index >= PPE_STATS_NUM_ENTRIES) + if (airoha_ppe_foe_get_flow_stats_index(ppe, hash, &index)) + return; + + if (index >= ppe_num_stats_entries) return; rcu_read_lock(); @@ -1259,7 +1314,7 @@ static int airoha_ppe_offload_setup(struct airoha_eth *eth) { struct airoha_npu *npu = airoha_ppe_npu_get(eth); struct airoha_ppe *ppe = eth->ppe; - int err; + int err, ppe_num_stats_entries; if (IS_ERR(npu)) return PTR_ERR(npu); @@ -1268,9 +1323,10 @@ static int airoha_ppe_offload_setup(struct airoha_eth *eth) if (err) goto error_npu_put; - if (PPE_STATS_NUM_ENTRIES) { + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries > 0) { err = npu->ops.ppe_init_stats(npu, ppe->foe_stats_dma, - PPE_STATS_NUM_ENTRIES); + ppe_num_stats_entries); if (err) goto error_npu_put; } @@ -1407,8 +1463,8 @@ EXPORT_SYMBOL_GPL(airoha_ppe_put_dev); int airoha_ppe_init(struct airoha_eth *eth) { + int foe_size, err, ppe_num_stats_entries; struct airoha_ppe *ppe; - int foe_size, err; ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL); if (!ppe) @@ -1433,8 +1489,9 @@ int airoha_ppe_init(struct airoha_eth *eth) if (!ppe->foe_flow) return -ENOMEM; - foe_size = PPE_STATS_NUM_ENTRIES * sizeof(*ppe->foe_stats); - if (foe_size) { + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries > 0) { + foe_size = ppe_num_stats_entries * sizeof(*ppe->foe_stats); ppe->foe_stats = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_stats_dma, GFP_KERNEL); From 4ea17f5e51266b978a6f5b48cafe9118c0a980ab Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:13 +0200 Subject: [PATCH 0334/1518] net: airoha: Add airoha_eth_soc_data struct [ Upstream commit 5863b4e065e2253ef05684f728a04e4972046bcb ] Introduce airoha_eth_soc_data struct to contain differences between various SoC. Move XSI reset names in airoha_eth_soc_data. This is a preliminary patch to enable AN7583 ethernet controller support in airoha-eth driver. Co-developed-by: Christian Marangi Signed-off-by: Christian Marangi Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-4-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 02f729643959 ("net: airoha: Fix FE_PSE_BUF_SET configuration if PPE2 is available") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 42 +++++++++++++++++++----- drivers/net/ethernet/airoha/airoha_eth.h | 17 ++++++++-- 2 files changed, 48 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 060865b98880e..5162f2a689000 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1406,8 +1406,7 @@ static int airoha_hw_init(struct platform_device *pdev, int err, i; /* disable xsi */ - err = reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), - eth->xsi_rsts); + err = reset_control_bulk_assert(eth->soc->num_xsi_rsts, eth->xsi_rsts); if (err) return err; @@ -2943,6 +2942,7 @@ static int airoha_register_gdm_devices(struct airoha_eth *eth) static int airoha_probe(struct platform_device *pdev) { + struct reset_control_bulk_data *xsi_rsts; struct device_node *np; struct airoha_eth *eth; int i, err; @@ -2951,6 +2951,10 @@ static int airoha_probe(struct platform_device *pdev) if (!eth) return -ENOMEM; + eth->soc = of_device_get_match_data(&pdev->dev); + if (!eth->soc) + return -EINVAL; + eth->dev = &pdev->dev; err = dma_set_mask_and_coherent(eth->dev, DMA_BIT_MASK(32)); @@ -2975,13 +2979,18 @@ static int airoha_probe(struct platform_device *pdev) return err; } - eth->xsi_rsts[0].id = "xsi-mac"; - eth->xsi_rsts[1].id = "hsi0-mac"; - eth->xsi_rsts[2].id = "hsi1-mac"; - eth->xsi_rsts[3].id = "hsi-mac"; - eth->xsi_rsts[4].id = "xfp-mac"; + xsi_rsts = devm_kzalloc(eth->dev, + eth->soc->num_xsi_rsts * sizeof(*xsi_rsts), + GFP_KERNEL); + if (err) + return err; + + eth->xsi_rsts = xsi_rsts; + for (i = 0; i < eth->soc->num_xsi_rsts; i++) + eth->xsi_rsts[i].id = eth->soc->xsi_rsts_names[i]; + err = devm_reset_control_bulk_get_exclusive(eth->dev, - ARRAY_SIZE(eth->xsi_rsts), + eth->soc->num_xsi_rsts, eth->xsi_rsts); if (err) { dev_err(eth->dev, "failed to get bulk xsi reset lines\n"); @@ -3074,8 +3083,23 @@ static void airoha_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); } +static const char * const en7581_xsi_rsts_names[] = { + "xsi-mac", + "hsi0-mac", + "hsi1-mac", + "hsi-mac", + "xfp-mac", +}; + +static const struct airoha_eth_soc_data en7581_soc_data = { + .version = 0x7581, + .xsi_rsts_names = en7581_xsi_rsts_names, + .num_xsi_rsts = ARRAY_SIZE(en7581_xsi_rsts_names), + .num_ppe = 2, +}; + static const struct of_device_id of_airoha_match[] = { - { .compatible = "airoha,en7581-eth" }, + { .compatible = "airoha,en7581-eth", .data = &en7581_soc_data }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, of_airoha_match); diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 3e43f01e9a652..655bc6acd80f0 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -21,7 +21,6 @@ #define AIROHA_MAX_NUM_IRQ_BANKS 4 #define AIROHA_MAX_DSA_PORTS 7 #define AIROHA_MAX_NUM_RSTS 3 -#define AIROHA_MAX_NUM_XSI_RSTS 5 #define AIROHA_MAX_MTU 9216 #define AIROHA_MAX_PACKET_SIZE 2048 #define AIROHA_NUM_QOS_CHANNELS 4 @@ -556,9 +555,18 @@ struct airoha_ppe { struct dentry *debugfs_dir; }; +struct airoha_eth_soc_data { + u16 version; + const char * const *xsi_rsts_names; + int num_xsi_rsts; + int num_ppe; +}; + struct airoha_eth { struct device *dev; + const struct airoha_eth_soc_data *soc; + unsigned long state; void __iomem *fe_regs; @@ -568,7 +576,7 @@ struct airoha_eth { struct rhashtable flow_table; struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS]; - struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS]; + struct reset_control_bulk_data *xsi_rsts; struct net_device *napi_dev; @@ -611,6 +619,11 @@ static inline bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port) return port->id == 1; } +static inline bool airoha_is_7581(struct airoha_eth *eth) +{ + return eth->soc->version == 0x7581; +} + bool airoha_is_valid_gdm_port(struct airoha_eth *eth, struct airoha_gdm_port *port); From 83d6371570ba9d97107ed4e76cfbfe4866e6ced1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:14 +0200 Subject: [PATCH 0335/1518] net: airoha: Generalize airoha_ppe2_is_enabled routine [ Upstream commit ef9449f080b61920cdc3d3106f8ffc2d9ba8b861 ] Rename airoha_ppe2_is_enabled() in airoha_ppe_is_enabled() and generalize it in order to check if each PPE module is enabled. Rely on airoha_ppe_is_enabled routine to properly initialize PPE for AN7583 SoC since AN7583 does not support PPE2. Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-5-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 02f729643959 ("net: airoha: Fix FE_PSE_BUF_SET configuration if PPE2 is available") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 32 ++++++++++++++++-------- drivers/net/ethernet/airoha/airoha_eth.h | 1 + drivers/net/ethernet/airoha/airoha_ppe.c | 17 +++++++------ 3 files changed, 32 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 5162f2a689000..677e40001f9f2 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -297,8 +297,11 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth) int q; all_rsv = airoha_fe_get_pse_all_rsv(eth); - /* hw misses PPE2 oq rsv */ - all_rsv += PSE_RSV_PAGES * pse_port_num_queues[FE_PSE_PORT_PPE2]; + if (airoha_ppe_is_enabled(eth, 1)) { + /* hw misses PPE2 oq rsv */ + all_rsv += PSE_RSV_PAGES * + pse_port_num_queues[FE_PSE_PORT_PPE2]; + } airoha_fe_set(eth, REG_FE_PSE_BUF_SET, all_rsv); /* CMD1 */ @@ -335,13 +338,17 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth) for (q = 4; q < pse_port_num_queues[FE_PSE_PORT_CDM4]; q++) airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_CDM4, q, PSE_QUEUE_RSV_PAGES); - /* PPE2 */ - for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE2]; q++) { - if (q < pse_port_num_queues[FE_PSE_PORT_PPE2] / 2) - airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, q, - PSE_QUEUE_RSV_PAGES); - else - airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, q, 0); + if (airoha_ppe_is_enabled(eth, 1)) { + /* PPE2 */ + for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE2]; q++) { + if (q < pse_port_num_queues[FE_PSE_PORT_PPE2] / 2) + airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, + q, + PSE_QUEUE_RSV_PAGES); + else + airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, + q, 0); + } } /* GMD4 */ for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_GDM4]; q++) @@ -1781,8 +1788,11 @@ static int airoha_dev_init(struct net_device *dev) airhoha_set_gdm2_loopback(port); fallthrough; case 2: - pse_port = FE_PSE_PORT_PPE2; - break; + if (airoha_ppe_is_enabled(eth, 1)) { + pse_port = FE_PSE_PORT_PPE2; + break; + } + fallthrough; default: pse_port = FE_PSE_PORT_PPE1; break; diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 655bc6acd80f0..d76f71558f8c2 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -627,6 +627,7 @@ static inline bool airoha_is_7581(struct airoha_eth *eth) bool airoha_is_valid_gdm_port(struct airoha_eth *eth, struct airoha_gdm_port *port); +bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index); void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb, u16 hash, bool rx_wlan); int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 117dfc21d6a81..4ed244557065d 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -50,9 +50,12 @@ static int airoha_ppe_get_total_num_stats_entries(struct airoha_ppe *ppe) return num_stats; } -static bool airoha_ppe2_is_enabled(struct airoha_eth *eth) +bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index) { - return airoha_fe_rr(eth, REG_PPE_GLO_CFG(1)) & PPE_GLO_CFG_EN_MASK; + if (index >= eth->soc->num_ppe) + return false; + + return airoha_fe_rr(eth, REG_PPE_GLO_CFG(index)) & PPE_GLO_CFG_EN_MASK; } static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe) @@ -120,7 +123,7 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) AIROHA_MAX_MTU)); } - if (airoha_ppe2_is_enabled(eth)) { + if (airoha_ppe_is_enabled(eth, 1)) { sram_num_entries = PPE1_SRAM_NUM_ENTRIES; sram_num_stats_entries = airoha_ppe_get_num_stats_entries(ppe); @@ -520,7 +523,7 @@ static int airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, return ppe_num_stats_entries; *index = hash; - if (airoha_ppe2_is_enabled(ppe->eth) && + if (airoha_ppe_is_enabled(ppe->eth, 1) && hash >= ppe_num_stats_entries) *index = *index - PPE_STATS_NUM_ENTRIES; @@ -615,7 +618,7 @@ airoha_ppe_foe_get_entry_locked(struct airoha_ppe *ppe, u32 hash) u32 val; int i; - ppe2 = airoha_ppe2_is_enabled(ppe->eth) && + ppe2 = airoha_ppe_is_enabled(ppe->eth, 1) && hash >= PPE1_SRAM_NUM_ENTRIES; airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2), FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) | @@ -693,7 +696,7 @@ static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe, if (hash < PPE_SRAM_NUM_ENTRIES) { dma_addr_t addr = ppe->foe_dma + hash * sizeof(*hwe); - bool ppe2 = airoha_ppe2_is_enabled(eth) && + bool ppe2 = airoha_ppe_is_enabled(eth, 1) && hash >= PPE1_SRAM_NUM_ENTRIES; err = npu->ops.ppe_foe_commit_entry(npu, addr, sizeof(*hwe), @@ -1288,7 +1291,7 @@ static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe, int i, sram_num_entries = PPE_SRAM_NUM_ENTRIES; struct airoha_foe_entry *hwe = ppe->foe; - if (airoha_ppe2_is_enabled(ppe->eth)) + if (airoha_ppe_is_enabled(ppe->eth, 1)) sram_num_entries = sram_num_entries / 2; for (i = 0; i < sram_num_entries; i++) From 0df9abbb138f4bf2cd1caf17b6285f86590b6d9a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 8 Apr 2026 12:20:09 +0200 Subject: [PATCH 0336/1518] net: airoha: Fix FE_PSE_BUF_SET configuration if PPE2 is available [ Upstream commit 02f72964395911e7a09bb2ea2fe6f79eda4ea2c2 ] airoha_fe_set routine is used to set specified bits to 1 in the selected register. In the FE_PSE_BUF_SET case this can due to a overestimation of the required buffers for I/O queues since we can miss to set some bits of PSE_ALLRSV_MASK subfield to 0. Fix the issue relying on airoha_fe_rmw routine instead. Fixes: 8e38e08f2c560 ("net: airoha: fix PSE memory configuration in airoha_fe_pse_ports_init()") Tested-by: Xuegang Lu Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260408-airoha-reg_fe_pse_buf_set-v1-1-0c4fa8f4d1d9@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 677e40001f9f2..132a32e9e633a 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -293,16 +293,18 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth) [FE_PSE_PORT_GDM4] = 2, [FE_PSE_PORT_CDM5] = 2, }; - u32 all_rsv; int q; - all_rsv = airoha_fe_get_pse_all_rsv(eth); if (airoha_ppe_is_enabled(eth, 1)) { + u32 all_rsv; + /* hw misses PPE2 oq rsv */ + all_rsv = airoha_fe_get_pse_all_rsv(eth); all_rsv += PSE_RSV_PAGES * pse_port_num_queues[FE_PSE_PORT_PPE2]; + airoha_fe_rmw(eth, REG_FE_PSE_BUF_SET, PSE_ALLRSV_MASK, + FIELD_PREP(PSE_ALLRSV_MASK, all_rsv)); } - airoha_fe_set(eth, REG_FE_PSE_BUF_SET, all_rsv); /* CMD1 */ for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_CDM1]; q++) From adaee08e711b11a4001e9f4c9100ec02262e42df Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Tue, 3 Feb 2026 08:51:00 -0800 Subject: [PATCH 0337/1518] bpf: Relax scalar id equivalence for state pruning [ Upstream commit b0388bafa4949bd30af7b3be5ee415f2a25ac014 ] Scalar register IDs are used by the verifier to track relationships between registers and enable bounds propagation across those relationships. Once an ID becomes singular (i.e. only a single register/stack slot carries it), it can no longer contribute to bounds propagation and effectively becomes stale. The previous commit makes the verifier clear such ids before caching the state. When comparing the current and cached states for pruning, these stale IDs can cause technically equivalent states to be considered different and thus prevent pruning. For example, in the selftest added in the next commit, two registers - r6 and r7 are not linked to any other registers and get cached with id=0, in the current state, they are both linked to each other with id=A. Before this commit, check_scalar_ids would give temporary ids to r6 and r7 (say tid1 and tid2) and then check_ids() would map tid1->A, and when it would see tid2->A, it would not consider these state equivalent. Relax scalar ID equivalence by treating rold->id == 0 as "independent": if the old state did not rely on any ID relationships for a register, then any ID/linking present in the current state only adds constraints and is always safe to accept for pruning. Implement this by returning true immediately in check_scalar_ids() when old_id == 0. Maintain correctness for the opposite direction (old_id != 0 && cur_id == 0) by still allocating a temporary ID for cur_id == 0. This avoids incorrectly allowing multiple independent current registers (id==0) to satisfy a single linked old ID during mapping. Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20260203165102.2302462-5-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Stable-dep-of: 2f2ec8e7730e ("bpf: Enforce regsafe base id consistency for BPF_ADD_CONST scalars") Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 63 +++++++++++++++---- .../selftests/bpf/progs/verifier_scalar_ids.c | 8 ++- 2 files changed, 56 insertions(+), 15 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6d5fc1af7a1f6..0cf6ca1f870f7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18808,13 +18808,29 @@ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) return false; } -/* Similar to check_ids(), but allocate a unique temporary ID - * for 'old_id' or 'cur_id' of zero. - * This makes pairs like '0 vs unique ID', 'unique ID vs 0' valid. +/* + * Compare scalar register IDs for state equivalence. + * + * When old_id == 0, the old register is independent - not linked to any + * other register. Any linking in the current state only adds constraints, + * making it more restrictive. Since the old state didn't rely on any ID + * relationships for this register, it's always safe to accept cur regardless + * of its ID. Hence, return true immediately. + * + * When old_id != 0 but cur_id == 0, we need to ensure that different + * independent registers in cur don't incorrectly satisfy the ID matching + * requirements of linked registers in old. + * + * Example: if old has r6.id=X and r7.id=X (linked), but cur has r6.id=0 + * and r7.id=0 (both independent), without temp IDs both would map old_id=X + * to cur_id=0 and pass. With temp IDs: r6 maps X->temp1, r7 tries to map + * X->temp2, but X is already mapped to temp1, so the check fails correctly. */ static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { - old_id = old_id ? old_id : ++idmap->tmp_id_gen; + if (!old_id) + return true; + cur_id = cur_id ? cur_id : ++idmap->tmp_id_gen; return check_ids(old_id, cur_id, idmap); @@ -18975,11 +18991,21 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, } if (!rold->precise && exact == NOT_EXACT) return true; - if ((rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST)) - return false; - if ((rold->id & BPF_ADD_CONST) && (rold->off != rcur->off)) - return false; - /* Why check_ids() for scalar registers? + /* + * Linked register tracking uses rold->id to detect relationships. + * When rold->id == 0, the register is independent and any linking + * in rcur only adds constraints. When rold->id != 0, we must verify + * id mapping and (for BPF_ADD_CONST) offset consistency. + * + * +------------------+-----------+------------------+---------------+ + * | | rold->id | rold + ADD_CONST | rold->id == 0 | + * |------------------+-----------+------------------+---------------| + * | rcur->id | range,ids | false | range | + * | rcur + ADD_CONST | false | range,ids,off | range | + * | rcur->id == 0 | range,ids | false | range | + * +------------------+-----------+------------------+---------------+ + * + * Why check_ids() for scalar registers? * * Consider the following BPF code: * 1: r6 = ... unbound scalar, ID=a ... @@ -19003,9 +19029,22 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, * --- * Also verify that new value satisfies old value range knowledge. */ - return range_within(rold, rcur) && - tnum_in(rold->var_off, rcur->var_off) && - check_scalar_ids(rold->id, rcur->id, idmap); + + /* ADD_CONST mismatch: different linking semantics */ + if ((rold->id & BPF_ADD_CONST) && !(rcur->id & BPF_ADD_CONST)) + return false; + + if (rold->id && !(rold->id & BPF_ADD_CONST) && (rcur->id & BPF_ADD_CONST)) + return false; + + /* Both have offset linkage: offsets must match */ + if ((rold->id & BPF_ADD_CONST) && rold->off != rcur->off) + return false; + + if (!check_scalar_ids(rold->id, rcur->id, idmap)) + return false; + + return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: case PTR_TO_MEM: diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 1fdd85b4b8443..f1c17df9c4f99 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -751,9 +751,9 @@ __success __log_level(2) /* The exit instruction should be reachable from two states, * use two matches and "processed .. insns" to ensure this. */ -__msg("13: (95) exit") -__msg("13: (95) exit") -__msg("processed 18 insns") +__msg("15: (95) exit") +__msg("15: (95) exit") +__msg("processed 20 insns") __flag(BPF_F_TEST_STATE_FREQ) __naked void two_old_ids_one_cur_id(void) { @@ -762,9 +762,11 @@ __naked void two_old_ids_one_cur_id(void) "call %[bpf_ktime_get_ns];" "r0 &= 0xff;" "r6 = r0;" + "r8 = r0;" "call %[bpf_ktime_get_ns];" "r0 &= 0xff;" "r7 = r0;" + "r9 = r0;" "r0 = 0;" /* Maybe make r{6,7} IDs identical */ "if r6 > r7 goto l0_%=;" From 691adf738817275368ed56311b7d798d617823a3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 11 Apr 2026 01:26:50 +0200 Subject: [PATCH 0338/1518] bpf: Enforce regsafe base id consistency for BPF_ADD_CONST scalars [ Upstream commit 2f2ec8e7730e21fc9bd49e0de9cdd58213ea24d0 ] When regsafe() compares two scalar registers that both carry BPF_ADD_CONST, check_scalar_ids() maps their full compound id (aka base | BPF_ADD_CONST flag) as one idmap entry. However, it never verifies that the underlying base ids, that is, with the flag stripped are consistent with existing idmap mappings. This allows construction of two verifier states where the old state has R3 = R2 + 10 (both sharing base id A) while the current state has R3 = R4 + 10 (base id C, unrelated to R2). The idmap creates two independent entries: A->B (for R2) and A|flag->C|flag (for R3), without catching that A->C conflicts with A->B. State pruning then incorrectly succeeds. Fix this by additionally verifying base ID mapping consistency whenever BPF_ADD_CONST is set: after mapping the compound ids, also invoke check_ids() on the base IDs (flag bits stripped). This ensures that if A was already mapped to B from comparing the source register, any ADD_CONST derivative must also derive from B, not an unrelated C. Fixes: 98d7ca374ba4 ("bpf: Track delta between "linked" registers.") Reported-by: STAR Labs SG Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20260410232651.559778-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0cf6ca1f870f7..e8975e9761e26 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18825,6 +18825,13 @@ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) * and r7.id=0 (both independent), without temp IDs both would map old_id=X * to cur_id=0 and pass. With temp IDs: r6 maps X->temp1, r7 tries to map * X->temp2, but X is already mapped to temp1, so the check fails correctly. + * + * When old_id has BPF_ADD_CONST set, the compound id (base | flag) and the + * base id (flag stripped) must both map consistently. Example: old has + * r2.id=A, r3.id=A|flag (r3 = r2 + delta), cur has r2.id=B, r3.id=C|flag + * (r3 derived from unrelated r4). Without the base check, idmap gets two + * independent entries A->B and A|flag->C|flag, missing that A->C conflicts + * with A->B. The base ID cross-check catches this. */ static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { @@ -18833,7 +18840,15 @@ static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) cur_id = cur_id ? cur_id : ++idmap->tmp_id_gen; - return check_ids(old_id, cur_id, idmap); + if (!check_ids(old_id, cur_id, idmap)) + return false; + if (old_id & BPF_ADD_CONST) { + old_id &= ~BPF_ADD_CONST; + cur_id &= ~BPF_ADD_CONST; + if (!check_ids(old_id, cur_id, idmap)) + return false; + } + return true; } static void clean_func_state(struct bpf_verifier_env *env, From 8e1387216d6673f24aeca04133ef96766dd89748 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Sat, 11 Apr 2026 00:33:44 -0700 Subject: [PATCH 0339/1518] selftests/bpf: fix __jited_unpriv tag name [ Upstream commit cdd54fe98c00549264a92613af6bb0e9a5fd0d1c ] __jited_unpriv was using "test_jited=" as its tag name, same as the priv variant __jited. Fix by using "test_jited_unpriv=". Fixes: 7d743e4c759c ("selftests/bpf: __jited test tag to check disassembly after jit") Acked-by: Ihor Solodrai Reviewed-by: Puranjay Mohan Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260410-selftests-global-tags-ordering-v2-1-c566ec9781bf@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/progs/bpf_misc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index a7a1a684eed11..25172ca74b204 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -137,7 +137,7 @@ #define __msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" XSTR(__COUNTER__) "=" msg))) #define __not_msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_not_msg_unpriv=" XSTR(__COUNTER__) "=" msg))) #define __xlated_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" XSTR(__COUNTER__) "=" msg))) -#define __jited_unpriv(msg) __attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg))) +#define __jited_unpriv(msg) __attribute__((btf_decl_tag("comment:test_jited_unpriv=" XSTR(__COUNTER__) "=" msg))) #define __failure_unpriv __attribute__((btf_decl_tag("comment:test_expect_failure_unpriv"))) #define __success_unpriv __attribute__((btf_decl_tag("comment:test_expect_success_unpriv"))) #define __log_level(lvl) __attribute__((btf_decl_tag("comment:test_log_level="#lvl))) From 4c727c6967a41b37efe0f26332ca9ec5b74785a3 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Fri, 10 Apr 2026 07:16:27 -0400 Subject: [PATCH 0340/1518] net/sched: act_ct: Only release RCU read lock after ct_ft [ Upstream commit f462dca0c8415bf0058d0ffa476354c4476d0f09 ] When looking up a flow table in act_ct in tcf_ct_flow_table_get(), rhashtable_lookup_fast() internally opens and closes an RCU read critical section before returning ct_ft. The tcf_ct_flow_table_cleanup_work() can complete before refcount_inc_not_zero() is invoked on the returned ct_ft resulting in a UAF on the already freed ct_ft object. This vulnerability can lead to privilege escalation. Analysis from zdi-disclosures@trendmicro.com: When initializing act_ct, tcf_ct_init() is called, which internally triggers tcf_ct_flow_table_get(). static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) { struct zones_ht_key key = { .net = net, .zone = params->zone }; struct tcf_ct_flow_table *ct_ft; int err = -ENOMEM; mutex_lock(&zones_mutex); ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); // [1] if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) // [2] goto out_unlock; ... } static __always_inline void *rhashtable_lookup_fast( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { void *obj; rcu_read_lock(); obj = rhashtable_lookup(ht, key, params); rcu_read_unlock(); return obj; } At [1], rhashtable_lookup_fast() looks up and returns the corresponding ct_ft from zones_ht . The lookup is performed within an RCU read critical section through rcu_read_lock() / rcu_read_unlock(), which prevents the object from being freed. However, at the point of function return, rcu_read_unlock() has already been called, and there is nothing preventing ct_ft from being freed before reaching refcount_inc_not_zero(&ct_ft->ref) at [2]. This interval becomes the race window, during which ct_ft can be freed. Free Process: tcf_ct_flow_table_put() is executed through the path tcf_ct_cleanup() call_rcu() tcf_ct_params_free_rcu() tcf_ct_params_free() tcf_ct_flow_table_put(). static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); // [3] queue_rcu_work(act_ct_wq, &ct_ft->rwork); } } At [3], tcf_ct_flow_table_cleanup_work() is scheduled as RCU work static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { struct tcf_ct_flow_table *ct_ft; struct flow_block *block; ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, rwork); nf_flow_table_free(&ct_ft->nf_ft); block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); // [4] module_put(THIS_MODULE); } tcf_ct_flow_table_cleanup_work() frees ct_ft at [4]. When this function executes between [1] and [2], UAF occurs. This race condition has a very short race window, making it generally difficult to trigger. Therefore, to trigger the vulnerability an msleep(100) was inserted after[1] Fixes: 138470a9b2cc2 ("net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get") Reported-by: zdi-disclosures@trendmicro.com Tested-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260410111627.46611-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/act_ct.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b3c160ad590d2..f9cb8f7474ed3 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -326,9 +326,13 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) int err = -ENOMEM; mutex_lock(&zones_mutex); - ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); - if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) + rcu_read_lock(); + ct_ft = rhashtable_lookup(&zones_ht, &key, zones_params); + if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) { + rcu_read_unlock(); goto out_unlock; + } + rcu_read_unlock(); ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL); if (!ct_ft) From 64daf391198cc09d6cafc4c5ba45ffb0899ae57a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 10 Apr 2026 00:45:02 +0200 Subject: [PATCH 0341/1518] selftests: netfilter: nft_tproxy.sh: adjust to socat changes [ Upstream commit 61119542663cac70898aef532eb57ee41ea9b477 ] Like e65d8b6f3092 ("selftests: drv-net: adjust to socat changes") we need to add shut-none for this test too. The extra 0-packet can trigger a second (unexpected) reply from the server. Fixes: 7e37e0eacd22 ("selftests: netfilter: nft_tproxy.sh: add tcp tests") Reported-by: Jakub Kicinski Closes: https://lore.kernel.org/netdev/20260408152432.24b8ad0d@kernel.org/ Suggested-by: Jakub Kicinski Signed-off-by: Florian Westphal Link: https://patch.msgid.link/20260409224506.27072-1-fw@strlen.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../selftests/net/netfilter/nft_tproxy_udp.sh | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh b/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh index d16de13fe5a75..1dc7b04501459 100755 --- a/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh +++ b/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh @@ -190,13 +190,13 @@ table inet filter { } EOF - timeout "$timeout" ip netns exec "$nsrouter" socat -u "$socat_ipproto" udp-listen:12345,fork,ip-transparent,reuseport udp:"$ns1_ip_port",ip-transparent,reuseport,bind="$ns2_ip_port" 2>/dev/null & + timeout "$timeout" ip netns exec "$nsrouter" socat -u "$socat_ipproto" udp-listen:12345,fork,ip-transparent,reuseport,shut-none udp:"$ns1_ip_port",ip-transparent,reuseport,bind="$ns2_ip_port",shut-none 2>/dev/null & local tproxy_pid=$! - timeout "$timeout" ip netns exec "$ns2" socat "$socat_ipproto" udp-listen:8080,fork SYSTEM:"echo PONG_NS2" 2>/dev/null & + timeout "$timeout" ip netns exec "$ns2" socat "$socat_ipproto" udp-listen:8080,fork,shut-none SYSTEM:"echo PONG_NS2" 2>/dev/null & local server2_pid=$! - timeout "$timeout" ip netns exec "$ns3" socat "$socat_ipproto" udp-listen:8080,fork SYSTEM:"echo PONG_NS3" 2>/dev/null & + timeout "$timeout" ip netns exec "$ns3" socat "$socat_ipproto" udp-listen:8080,fork,shut-none SYSTEM:"echo PONG_NS3" 2>/dev/null & local server3_pid=$! busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter" 12345 "-u" @@ -205,7 +205,7 @@ EOF local result # request from ns1 to ns2 (forwarded traffic) - result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",sourceport=18888) + result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",sourceport=18888,shut-none) if [ "$result" == "$expect_ns1_ns2" ] ;then echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns2" else @@ -214,7 +214,7 @@ EOF fi # request from ns1 to ns3 (forwarded traffic) - result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port") + result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port",shut-none) if [ "$result" = "$expect_ns1_ns3" ] ;then echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns3" else @@ -223,7 +223,7 @@ EOF fi # request from nsrouter to ns2 (localy originated traffic) - result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port") + result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",shut-none) if [ "$result" == "$expect_nsrouter_ns2" ] ;then echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns2" else @@ -232,7 +232,7 @@ EOF fi # request from nsrouter to ns3 (localy originated traffic) - result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port") + result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port",shut-none) if [ "$result" = "$expect_nsrouter_ns3" ] ;then echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns3" else From 34dbd7b819544c99c9d96b400fe4db613f40ac4b Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Wed, 8 Apr 2026 01:12:19 -0700 Subject: [PATCH 0342/1518] net: mana: Use pci_name() for debugfs directory naming [ Upstream commit c116f07ab9d22bb6f355f3cf9e44c1e6a47fe559 ] Use pci_name(pdev) for the per-device debugfs directory instead of hardcoded "0" for PFs and pci_slot_name(pdev->slot) for VFs. The previous approach had two issues: 1. pci_slot_name() dereferences pdev->slot, which can be NULL for VFs in environments like generic VFIO passthrough or nested KVM, causing a NULL pointer dereference. 2. Multiple PFs would all use "0", and VFs across different PCI domains or buses could share the same slot name, leading to -EEXIST errors from debugfs_create_dir(). pci_name(pdev) returns the unique BDF address, is always valid, and is unique across the system. Fixes: 6607c17c6c5e ("net: mana: Enable debugfs files for MANA device") Signed-off-by: Erni Sri Satya Vennela Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260408081224.302308-2-ernis@linux.microsoft.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 962fdd29d6063..c0de20b2183a2 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1927,11 +1927,8 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) gc->dev = &pdev->dev; xa_init(&gc->irq_contexts); - if (gc->is_pf) - gc->mana_pci_debugfs = debugfs_create_dir("0", mana_debugfs_root); - else - gc->mana_pci_debugfs = debugfs_create_dir(pci_slot_name(pdev->slot), - mana_debugfs_root); + gc->mana_pci_debugfs = debugfs_create_dir(pci_name(pdev), + mana_debugfs_root); err = mana_gd_setup(pdev); if (err) From 90ebf3e9c12f7a6c0adaf997efac095ccf04cfc3 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Wed, 29 Oct 2025 13:43:10 -0700 Subject: [PATCH 0343/1518] net: mana: Support HW link state events [ Upstream commit 54133f9b4b53ffa2204eb27cfc9d50072c9a52d2 ] Handle the NIC hardware link state events received from the HW channel, then set the proper link state accordingly. And, add a feature bit, GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE, to inform the NIC hardware this handler exists. Our MANA NIC only sends out the link state down/up messages when we need to let the VM rerun DHCP client and change IP address. So, add netif_carrier_on() in the probe(), let the NIC show the right initial state in /sys/class/net/ethX/operstate. Signed-off-by: Haiyang Zhang Link: https://patch.msgid.link/1761770601-16920-1-git-send-email-haiyangz@linux.microsoft.com Signed-off-by: Jakub Kicinski Stable-dep-of: 3b7c7fc97aea ("net: mana: Move current_speed debugfs file to mana_init_port()") Signed-off-by: Sasha Levin --- .../net/ethernet/microsoft/mana/gdma_main.c | 1 + .../net/ethernet/microsoft/mana/hw_channel.c | 12 +++++ drivers/net/ethernet/microsoft/mana/mana_en.c | 54 +++++++++++++++++-- include/net/mana/gdma.h | 4 +- include/net/mana/hw_channel.h | 2 + include/net/mana/mana.h | 4 ++ 6 files changed, 71 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index c0de20b2183a2..d93cfb7f4e788 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -528,6 +528,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq) case GDMA_EQE_HWC_INIT_DONE: case GDMA_EQE_HWC_SOC_SERVICE: case GDMA_EQE_RNIC_QP_FATAL: + case GDMA_EQE_HWC_SOC_RECONFIG_DATA: if (!eq->eq.callback) break; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 21cddafba5061..840c6b8957c90 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -118,6 +118,7 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, struct gdma_dev *gd = hwc->gdma_dev; union hwc_init_type_data type_data; union hwc_init_eq_id_db eq_db; + struct mana_context *ac; u32 type, val; int ret; @@ -196,6 +197,17 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, hwc->hwc_timeout = val; break; + case HWC_DATA_HW_LINK_CONNECT: + case HWC_DATA_HW_LINK_DISCONNECT: + ac = gd->gdma_context->mana.driver_data; + if (!ac) + break; + + WRITE_ONCE(ac->link_event, type); + schedule_work(&ac->link_change_work); + + break; + default: dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type); break; diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index abb207339992b..8277a1ac0ad74 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -20,6 +20,7 @@ #include #include +#include static DEFINE_IDA(mana_adev_ida); @@ -84,7 +85,6 @@ static int mana_open(struct net_device *ndev) /* Ensure port state updated before txq state */ smp_wmb(); - netif_carrier_on(ndev); netif_tx_wake_all_queues(ndev); netdev_dbg(ndev, "%s successful\n", __func__); return 0; @@ -100,6 +100,46 @@ static int mana_close(struct net_device *ndev) return mana_detach(ndev, true); } +static void mana_link_state_handle(struct work_struct *w) +{ + struct mana_context *ac; + struct net_device *ndev; + u32 link_event; + bool link_up; + int i; + + ac = container_of(w, struct mana_context, link_change_work); + + rtnl_lock(); + + link_event = READ_ONCE(ac->link_event); + + if (link_event == HWC_DATA_HW_LINK_CONNECT) + link_up = true; + else if (link_event == HWC_DATA_HW_LINK_DISCONNECT) + link_up = false; + else + goto out; + + /* Process all ports */ + for (i = 0; i < ac->num_ports; i++) { + ndev = ac->ports[i]; + if (!ndev) + continue; + + if (link_up) { + netif_carrier_on(ndev); + + __netdev_notify_peers(ndev); + } else { + netif_carrier_off(ndev); + } + } + +out: + rtnl_unlock(); +} + static bool mana_can_tx(struct gdma_queue *wq) { return mana_gd_wq_avail_space(wq) >= MAX_TX_WQE_SIZE; @@ -3086,9 +3126,6 @@ int mana_attach(struct net_device *ndev) /* Ensure port state updated before txq state */ smp_wmb(); - if (apc->port_is_up) - netif_carrier_on(ndev); - netif_device_attach(ndev); return 0; @@ -3183,7 +3220,6 @@ int mana_detach(struct net_device *ndev, bool from_close) smp_wmb(); netif_tx_disable(ndev); - netif_carrier_off(ndev); if (apc->port_st_save) { err = mana_dealloc_queues(ndev); @@ -3272,6 +3308,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, goto free_indir; } + netif_carrier_on(ndev); + debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed); return 0; @@ -3462,6 +3500,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!resuming) { ac->num_ports = num_ports; + + INIT_WORK(&ac->link_change_work, mana_link_state_handle); } else { if (ac->num_ports != num_ports) { dev_err(dev, "The number of vPorts changed: %d->%d\n", @@ -3469,6 +3509,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) err = -EPROTO; goto out; } + + enable_work(&ac->link_change_work); } if (ac->num_ports == 0) @@ -3531,6 +3573,8 @@ void mana_remove(struct gdma_dev *gd, bool suspending) int err; int i; + disable_work_sync(&ac->link_change_work); + /* adev currently doesn't support suspending, always remove it */ if (gd->adev) remove_adev(gd); diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 57df78cfbf82c..637f42485dba6 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -590,6 +590,7 @@ enum { /* Driver can self reset on FPGA Reconfig EQE notification */ #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) +#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ @@ -599,7 +600,8 @@ enum { GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \ GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \ GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \ - GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE) + GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \ + GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h index 83cf93338eb38..16feb39616c1b 100644 --- a/include/net/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h @@ -24,6 +24,8 @@ #define HWC_INIT_DATA_PF_DEST_CQ_ID 11 #define HWC_DATA_CFG_HWC_TIMEOUT 1 +#define HWC_DATA_HW_LINK_CONNECT 2 +#define HWC_DATA_HW_LINK_DISCONNECT 3 #define HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS 30000 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 857f45a3386cc..f9f264385405c 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -477,6 +477,10 @@ struct mana_context { struct dentry *mana_eqs_debugfs; struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; + + /* Link state change work */ + struct work_struct link_change_work; + u32 link_event; }; struct mana_port_context { From 3ddf6523957a9f6991449b0101fa22dac6be0bcd Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Wed, 8 Apr 2026 01:12:20 -0700 Subject: [PATCH 0344/1518] net: mana: Move current_speed debugfs file to mana_init_port() [ Upstream commit 3b7c7fc97aea7b4048001d12f45777201c74a17f ] Move the current_speed debugfs file creation from mana_probe_port() to mana_init_port(). The file was previously created only during initial probe, but mana_cleanup_port_context() removes the entire vPort debugfs directory during detach/attach cycles. Since mana_init_port() recreates the directory on re-attach, moving current_speed here ensures it survives these cycles. Fixes: 75cabb46935b ("net: mana: Add support for net_shaper_ops") Signed-off-by: Erni Sri Satya Vennela Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260408081224.302308-3-ernis@linux.microsoft.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 8277a1ac0ad74..c770fb86fd2d3 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3038,6 +3038,8 @@ static int mana_init_port(struct net_device *ndev) eth_hw_addr_set(ndev, apc->mac_addr); sprintf(vport, "vport%d", port_idx); apc->mana_port_debugfs = debugfs_create_dir(vport, gc->mana_pci_debugfs); + debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, + &apc->speed); return 0; reset_apc: @@ -3310,8 +3312,6 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, netif_carrier_on(ndev); - debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed); - return 0; free_indir: From 9d51c86355d9da7e11e8ff794eb5dc9675a77f8d Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 8 Apr 2026 20:26:56 +0200 Subject: [PATCH 0345/1518] net: airoha: Add missing RX_CPU_IDX() configuration in airoha_qdma_cleanup_rx_queue() [ Upstream commit 656121b155030086b01cfce9bd31b0c925ee6860 ] When the descriptor index written in REG_RX_CPU_IDX() is equal to the one stored in REG_RX_DMA_IDX(), the hw will stop since the QDMA RX ring is empty. Add missing REG_RX_CPU_IDX() configuration in airoha_qdma_cleanup_rx_queue routine during QDMA RX ring cleanup. Fixes: 514aac359987 ("net: airoha: Add missing cleanup bits in airoha_qdma_cleanup_rx_queue()") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260408-airoha-cpu-idx-airoha_qdma_cleanup_rx_queue-v1-1-8efa64844308@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 132a32e9e633a..cbf21e15df6dd 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -844,6 +844,11 @@ static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q) } q->head = q->tail; + /* Set RX_DMA_IDX to RX_CPU_IDX to notify the hw the QDMA RX ring is + * empty. + */ + airoha_qdma_rmw(qdma, REG_RX_CPU_IDX(qid), RX_RING_CPU_IDX_MASK, + FIELD_PREP(RX_RING_CPU_IDX_MASK, q->head)); airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK, FIELD_PREP(RX_RING_DMA_IDX_MASK, q->tail)); } From cddf2bde8420ed6d3398ad58d292b5c1a2ed2bee Mon Sep 17 00:00:00 2001 From: Emil Tsalapatis Date: Sun, 12 Apr 2026 13:45:38 -0400 Subject: [PATCH 0346/1518] bpf: Allow instructions with arena source and non-arena dest registers [ Upstream commit ac61bffe91d4bda08806e12957c6d64756d042db ] The compiler sometimes stores the result of a PTR_TO_ARENA and SCALAR operation into the scalar register rather than the pointer register. Relax the verifier to allow operations between a source arena register and a destination non-arena register, marking the destination's value as a PTR_TO_ARENA. Signed-off-by: Emil Tsalapatis Acked-by: Song Liu Fixes: 6082b6c328b5 ("bpf: Recognize addr_space_cast instruction in the verifier.") Link: https://lore.kernel.org/r/20260412174546.18684-2-emil@etsalapatis.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e8975e9761e26..153a7c1d32069 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -15705,11 +15705,20 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, int err; dst_reg = ®s[insn->dst_reg]; - src_reg = NULL; + if (BPF_SRC(insn->code) == BPF_X) + src_reg = ®s[insn->src_reg]; + else + src_reg = NULL; - if (dst_reg->type == PTR_TO_ARENA) { + /* Case where at least one operand is an arena. */ + if (dst_reg->type == PTR_TO_ARENA || (src_reg && src_reg->type == PTR_TO_ARENA)) { struct bpf_insn_aux_data *aux = cur_aux(env); + if (dst_reg->type != PTR_TO_ARENA) + *dst_reg = *src_reg; + + dst_reg->subreg_def = env->insn_idx + 1; + if (BPF_CLASS(insn->code) == BPF_ALU64) /* * 32-bit operations zero upper bits automatically. @@ -15725,7 +15734,6 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, ptr_reg = dst_reg; if (BPF_SRC(insn->code) == BPF_X) { - src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields From bc678fa87552b06da8f9f27c843c352202406a98 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Wed, 8 Apr 2026 22:40:50 +0200 Subject: [PATCH 0347/1518] selftests/bpf: Fix reg_bounds to match new tnum-based refinement [ Upstream commit 2fefa9c81a25534464911447d51ddb44b04a8e5b ] Commit efc11a667878 ("bpf: Improve bounds when tnum has a single possible value") improved the bounds refinement to detect when the tnum and u64 range overlap in a single value (and the bounds can thus be set to that value). Eduard then noticed that it broke the slow-mode reg_bounds selftests because they don't have an equivalent logic and are therefore unable to refine the bounds as much as the verifier. The following test case illustrates this. ACTUAL TRUE1: scalar(u64=0xffffffff00000000,u32=0,s64=0xffffffff00000000,s32=0) EXPECTED TRUE1: scalar(u64=[0xfffffffe00000001; 0xffffffff00000000],u32=0,s64=[0xfffffffe00000001; 0xffffffff00000000],s32=0) [...] #323/1007 reg_bounds_gen_consts_s64_s32/(s64)[0xfffffffe00000001; 0xffffffff00000000] (s32) S64_MIN:FAIL with the verifier logs: [...] 19: w0 = w6 ; R0=scalar(smin=0,smax=umax=0xffffffff, var_off=(0x0; 0xffffffff)) R6=scalar(smin=0xfffffffe00000001,smax=0xffffffff00000000, umin=0xfffffffe00000001,umax=0xffffffff00000000, var_off=(0xfffffffe00000000; 0x1ffffffff)) 20: w0 = w7 ; R0=0 R7=0x8000000000000000 21: if w6 == w7 goto pc+3 [...] from 21 to 25: [...] 25: w0 = w6 ; R0=0 R6=0xffffffff00000000 ; ^ ; unexpected refined value 26: w0 = w7 ; R0=0 R7=0x8000000000000000 27: exit When w6 == w7 is true, the verifier can deduce that the R6's tnum is equal to (0xfffffffe00000000; 0x100000000) and then use that information to refine the bounds: the tnum only overlap with the u64 range in 0xffffffff00000000. The reg_bounds selftest doesn't know about tnums and therefore fails to perform the same refinement. This issue happens when the tnum carries information that cannot be represented in the ranges, as otherwise the selftest could reach the same refined value using just the ranges. The tnum thus needs to represent non-contiguous values (ex., R6's tnum above, after the condition). The only way this can happen in the reg_bounds selftest is at the boundary between the 32 and 64bit ranges. We therefore only need to handle that case. This patch fixes the selftest refinement logic by checking if the u32 and u64 ranges overlap in a single value. If so, the ranges can be set to that value. We need to handle two cases: either they overlap in umin64... u64 values matching u32 range: xxx xxx xxx xxx |--------------------------------------| u64 range: 0 xxxxx UMAX64 or in umax64: u64 values matching u32 range: xxx xxx xxx xxx |--------------------------------------| u64 range: 0 xxxxx UMAX64 To detect the first case, we decrease umax64 to the maximum value that matches the u32 range. If that happens to be umin64, then umin64 is the only overlap. We proceed similarly for the second case, increasing umin64 to the minimum value that matches the u32 range. Note this is similar to how the verifier handles the general case using tnum, but we don't need to care about a single-value overlap in the middle of the range. That case is not possible when comparing two ranges. This patch also adds two test cases reproducing this bug as part of the normal test runs (without SLOW_TESTS=1). Fixes: efc11a667878 ("bpf: Improve bounds when tnum has a single possible value") Reported-by: Eduard Zingerman Closes: https://lore.kernel.org/bpf/4e6dd64a162b3cab3635706ae6abfdd0be4db5db.camel@gmail.com/ Signed-off-by: Paul Chaignon Link: https://lore.kernel.org/r/ada9UuSQi2SE2IfB@mail.gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- .../selftests/bpf/prog_tests/reg_bounds.c | 35 +++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index 04938d0d431b3..5f57d3c923801 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -500,6 +500,39 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX) return range_intersection(x_t, x, y_cast); + if (y_t == U32 && x_t == U64) { + u64 xmin_swap, xmax_swap, xmin_lower32, xmax_lower32; + + xmin_lower32 = x.a & 0xffffffff; + xmax_lower32 = x.b & 0xffffffff; + if (xmin_lower32 < y.a || xmin_lower32 > y.b) { + /* The 32 lower bits of the umin64 are outside the u32 + * range. Let's update umin64 to match the u32 range. + * We want to *increase* the umin64 to the *minimum* + * value that matches the u32 range. + */ + xmin_swap = swap_low32(x.a, y.a); + /* We should always only increase the minimum, so if + * the new value is lower than before, we need to + * increase the 32 upper bits by 1. + */ + if (xmin_swap < x.a) + xmin_swap += 0x100000000; + if (xmin_swap == x.b) + return range(x_t, x.b, x.b); + } else if (xmax_lower32 < y.a || xmax_lower32 > y.b) { + /* Same for the umax64, but we want to *decrease* + * umax64 to the *maximum* value that matches the u32 + * range. + */ + xmax_swap = swap_low32(x.b, y.b); + if (xmax_swap > x.b) + xmax_swap -= 0x100000000; + if (xmax_swap == x.a) + return range(x_t, x.a, x.a); + } + } + /* the case when new range knowledge, *y*, is a 32-bit subregister * range, while previous range knowledge, *x*, is a full register * 64-bit range, needs special treatment to take into account upper 32 @@ -2143,6 +2176,8 @@ static struct subtest_case crafted_cases[] = { {U64, S64, {0x7fffffff00000001ULL, 0xffffffff00000000ULL}, {0, 0}}, {U64, S64, {0, 0xffffffffULL}, {1, 1}}, {U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}}, + {U64, S32, {0xfffffffe00000001, 0xffffffff00000000}, {S64_MIN, S64_MIN}}, + {U64, U32, {0xfffffffe00000000, U64_MAX - 1}, {U64_MAX, U64_MAX}}, {U64, U32, {0, 0x100000000}, {0, 0}}, {U64, U32, {0xfffffffe, 0x300000000}, {0x80000000, 0x80000000}}, From d3f880a6eb440a7d446e67bea128b1c6246d3f23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?H=C3=A5kon=20Bugge?= Date: Wed, 8 Apr 2026 01:04:19 -0700 Subject: [PATCH 0348/1518] net/rds: Optimize rds_ib_laddr_check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 236f718ac885965fa886440b9898dfae185c9733 ] rds_ib_laddr_check() creates a CM_ID and attempts to bind the address in question to it. This in order to qualify the allegedly local address as a usable IB/RoCE address. In the field, ExaWatcher runs rds-ping to all ports in the fabric from all local ports. This using all active ToS'es. In a full rack system, we have 14 cell servers and eight db servers. Typically, 6 ToS'es are used. This implies 528 rds-ping invocations per ExaWatcher's "RDSinfo" interval. Adding to this, each rds-ping invocation creates eight sockets and binds the local address to them: socket(AF_RDS, SOCK_SEQPACKET, 0) = 3 bind(3, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 4 bind(4, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 5 bind(5, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 6 bind(6, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 7 bind(7, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 8 bind(8, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 9 bind(9, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 socket(AF_RDS, SOCK_SEQPACKET, 0) = 10 bind(10, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("192.168.36.2")}, 16) = 0 So, at every interval ExaWatcher executes rds-ping's, 4224 CM_IDs are allocated, considering this full-rack system. After the a CM_ID has been allocated, rdma_bind_addr() is called, with the port number being zero. This implies that the CMA will attempt to search for an un-used ephemeral port. Simplified, the algorithm is to start at a random position in the available port space, and then if needed, iterate until an un-used port is found. The book-keeping of used ports uses the idr system, which again uses slab to allocate new struct idr_layer's. The size is 2092 bytes and slab tries to reduce the wasted space. Hence, it chooses an order:3 allocation, for which 15 idr_layer structs will fit and only 1388 bytes are wasted per the 32KiB order:3 chunk. Although this order:3 allocation seems like a good space/speed trade-off, it does not resonate well with how it used by the CMA. The combination of the randomized starting point in the port space (which has close to zero spatial locality) and the close proximity in time of the 4224 invocations of the rds-ping's, creates a memory hog for order:3 allocations. These costly allocations may need reclaims and/or compaction. At worst, they may fail and produce a stack trace such as (from uek4): [] __inc_zone_page_state+0x35/0x40 [] page_add_file_rmap+0x57/0x60 [] remove_migration_pte+0x3f/0x3c0 [ksplice_6cn872bt_vmlinux_new] [] rmap_walk+0xd8/0x340 [] remove_migration_ptes+0x40/0x50 [] migrate_pages+0x3ec/0x890 [] compact_zone+0x32d/0x9a0 [] compact_zone_order+0x6d/0x90 [] try_to_compact_pages+0x102/0x270 [] __alloc_pages_direct_compact+0x46/0x100 [] __alloc_pages_nodemask+0x74b/0xaa0 [] alloc_pages_current+0x91/0x110 [] new_slab+0x38b/0x480 [] __slab_alloc+0x3b7/0x4a0 [ksplice_s0dk66a8_vmlinux_new] [] kmem_cache_alloc+0x1fb/0x250 [] idr_layer_alloc+0x36/0x90 [] idr_get_empty_slot+0x28c/0x3d0 [] idr_alloc+0x4d/0xf0 [] cma_alloc_port+0x4d/0xa0 [rdma_cm] [] rdma_bind_addr+0x2ae/0x5b0 [rdma_cm] [] rds_ib_laddr_check+0x83/0x2c0 [ksplice_6l2xst5i_rds_rdma_new] [] rds_trans_get_preferred+0x5b/0xa0 [rds] [] rds_bind+0x212/0x280 [rds] [] SYSC_bind+0xe6/0x120 [] SyS_bind+0xe/0x10 [] system_call_fastpath+0x18/0xd4 To avoid these excessive calls to rdma_bind_addr(), we optimize rds_ib_laddr_check() by simply checking if the address in question has been used before. The rds_rdma module keeps track of addresses associated with IB devices, and the function rds_ib_get_device() is used to determine if the address already has been qualified as a valid local address. If not found, we call the legacy rds_ib_laddr_check(), now renamed to rds_ib_laddr_check_cm(). Signed-off-by: Håkon Bugge Signed-off-by: Somasundaram Krishnasamy Signed-off-by: Gerd Rausch Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260408080420.540032-2-achender@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: ebf71dd4aff4 ("net/rds: Restrict use of RDS/IB to the initial network namespace") Signed-off-by: Sasha Levin --- net/rds/ib.c | 20 ++++++++++++++++++-- net/rds/ib.h | 1 + net/rds/ib_rdma.c | 2 +- 3 files changed, 20 insertions(+), 3 deletions(-) diff --git a/net/rds/ib.c b/net/rds/ib.c index 9826fe7f9d008..996f007cd516b 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -403,8 +403,8 @@ static void rds6_ib_ic_info(struct socket *sock, unsigned int len, * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ -static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, - __u32 scope_id) +static int rds_ib_laddr_check_cm(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { int ret; struct rdma_cm_id *cm_id; @@ -489,6 +489,22 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, return ret; } +static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) +{ + struct rds_ib_device *rds_ibdev = NULL; + + if (ipv6_addr_v4mapped(addr)) { + rds_ibdev = rds_ib_get_device(addr->s6_addr32[3]); + if (rds_ibdev) { + rds_ib_dev_put(rds_ibdev); + return 0; + } + } + + return rds_ib_laddr_check_cm(net, addr, scope_id); +} + static void rds_ib_unregister_client(void) { ib_unregister_client(&rds_ib_client); diff --git a/net/rds/ib.h b/net/rds/ib.h index 8ef3178ed4d61..5ff346a1e8baa 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -381,6 +381,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, __rds_ib_conn_error(conn, KERN_WARNING "RDS/IB: " fmt) /* ib_rdma.c */ +struct rds_ib_device *rds_ib_get_device(__be32 ipaddr); int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, struct in6_addr *ipaddr); void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index dd08ccc4246da..751755cd069e0 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -43,7 +43,7 @@ struct workqueue_struct *rds_ib_mr_wq; static void rds_ib_odp_mr_worker(struct work_struct *work); -static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) +struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) { struct rds_ib_device *rds_ibdev; struct rds_ib_ipaddr *i_ipaddr; From a7494479757d60d2413bfaa087f8431a26eea032 Mon Sep 17 00:00:00 2001 From: Greg Jumper Date: Wed, 8 Apr 2026 01:04:20 -0700 Subject: [PATCH 0349/1518] net/rds: Restrict use of RDS/IB to the initial network namespace [ Upstream commit ebf71dd4aff46e8e421d455db3e231ba43d2fa8a ] Prevent using RDS/IB in network namespaces other than the initial one. The existing RDS/IB code will not work properly in non-initial network namespaces. Fixes: d5a8ac28a7ff ("RDS-TCP: Make RDS-TCP work correctly when it is set up in a netns other than init_net") Reported-by: syzbot+da8e060735ae02c8f3d1@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=da8e060735ae02c8f3d1 Signed-off-by: Greg Jumper Signed-off-by: Allison Henderson Link: https://patch.msgid.link/20260408080420.540032-3-achender@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/rds/af_rds.c | 10 ++++++++-- net/rds/ib.c | 4 ++++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 4a7217fbeab6f..7a0f5150e9103 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -357,7 +357,8 @@ static int rds_cong_monitor(struct rds_sock *rs, sockptr_t optval, int optlen) return ret; } -static int rds_set_transport(struct rds_sock *rs, sockptr_t optval, int optlen) +static int rds_set_transport(struct net *net, struct rds_sock *rs, + sockptr_t optval, int optlen) { int t_type; @@ -373,6 +374,10 @@ static int rds_set_transport(struct rds_sock *rs, sockptr_t optval, int optlen) if (t_type < 0 || t_type >= RDS_TRANS_COUNT) return -EINVAL; + /* RDS/IB is restricted to the initial network namespace */ + if (t_type != RDS_TRANS_TCP && !net_eq(net, &init_net)) + return -EPROTOTYPE; + rs->rs_transport = rds_trans_get(t_type); return rs->rs_transport ? 0 : -ENOPROTOOPT; @@ -433,6 +438,7 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); + struct net *net = sock_net(sock->sk); int ret; if (level != SOL_RDS) { @@ -461,7 +467,7 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, break; case SO_RDS_TRANSPORT: lock_sock(sock->sk); - ret = rds_set_transport(rs, optval, optlen); + ret = rds_set_transport(net, rs, optval, optlen); release_sock(sock->sk); break; case SO_TIMESTAMP_OLD: diff --git a/net/rds/ib.c b/net/rds/ib.c index 996f007cd516b..ce5be43c5fbac 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -494,6 +494,10 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, { struct rds_ib_device *rds_ibdev = NULL; + /* RDS/IB is restricted to the initial network namespace */ + if (!net_eq(net, &init_net)) + return -EPROTOTYPE; + if (ipv6_addr_v4mapped(addr)) { rds_ibdev = rds_ib_get_device(addr->s6_addr32[3]); if (rds_ibdev) { From 6086079e6d1c32ba4c4b422612b8aebb1129a96c Mon Sep 17 00:00:00 2001 From: Lang Xu Date: Thu, 2 Apr 2026 15:42:35 +0800 Subject: [PATCH 0350/1518] bpf: Fix OOB in pcpu_init_value [ Upstream commit 576afddfee8d1108ee299bf10f581593540d1a36 ] An out-of-bounds read occurs when copying element from a BPF_MAP_TYPE_CGROUP_STORAGE map to another pcpu map with the same value_size that is not rounded up to 8 bytes. The issue happens when: 1. A CGROUP_STORAGE map is created with value_size not aligned to 8 bytes (e.g., 4 bytes) 2. A pcpu map is created with the same value_size (e.g., 4 bytes) 3. Update element in 2 with data in 1 pcpu_init_value assumes that all sources are rounded up to 8 bytes, and invokes copy_map_value_long to make a data copy, However, the assumption doesn't stand since there are some cases where the source may not be rounded up to 8 bytes, e.g., CGROUP_STORAGE, skb->data. the verifier verifies exactly the size that the source claims, not the size rounded up to 8 bytes by kernel, an OOB happens when the source has only 4 bytes while the copy size(4) is rounded up to 8. Fixes: d3bec0138bfb ("bpf: Zero-fill re-used per-cpu map element") Reported-by: Kaiyan Mei Closes: https://lore.kernel.org/all/14e6c70c.6c121.19c0399d948.Coremail.kaiyanm@hust.edu.cn/ Link: https://lore.kernel.org/r/420FEEDDC768A4BE+20260402074236.2187154-1-xulang@uniontech.com Signed-off-by: Lang Xu Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/hashtab.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index e7721f0776c72..469bc48b25127 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -981,7 +981,7 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, for_each_possible_cpu(cpu) { if (cpu == current_cpu) - copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value); + copy_map_value(&htab->map, per_cpu_ptr(pptr, cpu), value); else /* Since elem is preallocated, we cannot touch special fields */ zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu)); } From 5013be175c7ffd8b39efbc3c9c4db5b10b85fea8 Mon Sep 17 00:00:00 2001 From: Taegu Ha Date: Thu, 9 Apr 2026 16:11:15 +0900 Subject: [PATCH 0351/1518] ppp: require CAP_NET_ADMIN in target netns for unattached ioctls [ Upstream commit 2bb6379416fd19f44c3423a00bfd8626259f6067 ] /dev/ppp open is currently authorized against file->f_cred->user_ns, while unattached administrative ioctls operate on current->nsproxy->net_ns. As a result, a local unprivileged user can create a new user namespace with CLONE_NEWUSER, gain CAP_NET_ADMIN only in that new user namespace, and still issue PPPIOCNEWUNIT, PPPIOCATTACH, or PPPIOCATTCHAN against an inherited network namespace. Require CAP_NET_ADMIN in the user namespace that owns the target network namespace before handling unattached PPP administrative ioctls. This preserves normal pppd operation in the network namespace it is actually privileged in, while rejecting the userns-only inherited-netns case. Fixes: 273ec51dd7ce ("net: ppp_generic - introduce net-namespace functionality v2") Signed-off-by: Taegu Ha Link: https://patch.msgid.link/20260409071117.4354-1-hataegu0826@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ppp/ppp_generic.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index f9f0f16c41d10..7ad6c241c3295 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1057,6 +1057,9 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct ppp_net *pn; int __user *p = (int __user *)arg; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ From 65c7f0bf8ca32c40d0fdc1465a249e3fb579e8f3 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Thu, 9 Apr 2026 10:13:31 +0200 Subject: [PATCH 0352/1518] net: ipa: Fix programming of QTIME_TIMESTAMP_CFG [ Upstream commit de08f9585692813bd41ee654fca0487664c4de30 ] The 'val' variable gets overwritten multiple times, discarding previous values. Looking at the git log shows these should be combined with |= instead. Fixes: 9265a4f0f0b4 ("net: ipa: define even more IPA register fields") Link: https://sashiko.dev/#/patchset/20260403-milos-ipa-v1-0-01e9e4e03d3e%40fairphone.com?part=4 Signed-off-by: Luca Weiss Reviewed-by: Konrad Dybcio Link: https://patch.msgid.link/20260409-ipa-fixes-v1-1-a817c30678ac@fairphone.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ipa/ipa_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 25500c5a6928e..30fe12e3582b2 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -361,7 +361,7 @@ static void ipa_qtime_config(struct ipa *ipa) { const struct reg *reg; u32 offset; - u32 val; + u32 val = 0; /* Timer clock divider must be disabled when we change the rate */ reg = ipa_reg(ipa, TIMERS_XO_CLK_DIV_CFG); @@ -374,8 +374,8 @@ static void ipa_qtime_config(struct ipa *ipa) val |= reg_bit(reg, DPL_TIMESTAMP_SEL); } /* Configure tag and NAT Qtime timestamp resolution as well */ - val = reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT); - val = reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT); + val |= reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT); + val |= reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT); iowrite32(val, ipa->reg_virt + reg_offset(reg)); From a3be96c7b1e532e6f4498ec30dab148c95392000 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Thu, 9 Apr 2026 10:13:32 +0200 Subject: [PATCH 0353/1518] net: ipa: Fix decoding EV_PER_EE for IPA v5.0+ [ Upstream commit 1335b903cf2e8aeaca87fd665683384c731ec941 ] Initially 'reg' and 'val' are assigned from HW_PARAM_2. But since IPA v5.0+ takes EV_PER_EE from HW_PARAM_4 (instead of NUM_EV_PER_EE from HW_PARAM_2), we not only need to re-assign 'reg' but also read the register value of that register into 'val' so that reg_decode() works on the correct value. Fixes: f651334e1ef5 ("net: ipa: add HW_PARAM_4 GSI register") Link: https://sashiko.dev/#/patchset/20260403-milos-ipa-v1-0-01e9e4e03d3e%40fairphone.com?part=2 Signed-off-by: Luca Weiss Reviewed-by: Konrad Dybcio Link: https://patch.msgid.link/20260409-ipa-fixes-v1-2-a817c30678ac@fairphone.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ipa/gsi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 4c3227e77898c..624649484d627 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -2044,6 +2044,7 @@ static int gsi_ring_setup(struct gsi *gsi) count = reg_decode(reg, NUM_EV_PER_EE, val); } else { reg = gsi_reg(gsi, HW_PARAM_4); + val = ioread32(gsi->virt + reg_offset(reg)); count = reg_decode(reg, EV_PER_EE, val); } if (!count) { From d7637c455a92d3527ca56902d2632f349fdc98c4 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Thu, 9 Apr 2026 14:34:33 +0200 Subject: [PATCH 0354/1518] dt-bindings: net: dsa: nxp,sja1105: make spi-cpol optional for sja1110 [ Upstream commit 600f01dc4bd0c736b3ffea9f7976136d8bf1b136 ] Currently, the binding requires 'spi-cpha' for SJA1105 and 'spi-cpol' for SJA1110. However, the SJA1110 supports both SPI modes 0 and 2. Mode 2 (cpha=0, cpol=1) is used by the NXP LX2160 Bluebox 3. On the SolidRun i.MX8DXL HummingBoard Telematics, mode 0 is stable, while forcing mode 2 introduces CRC errors especially during bursts. Drop the requirement on spi-cpol for SJA1110. Fixes: af2eab1a8243 ("dt-bindings: net: nxp,sja1105: document spi-cpol/cpha") Signed-off-by: Josua Mayer Acked-by: Conor Dooley Link: https://patch.msgid.link/20260409-imx8dxl-sr-som-v2-1-83ff20629ba0@solid-run.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index e9dd914b0734c..941f9a25bbea0 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -140,8 +140,6 @@ allOf: else: properties: spi-cpha: false - required: - - spi-cpol unevaluatedProperties: false From 15a9928f8a93bb9df38900b3f21b665679fb8eb8 Mon Sep 17 00:00:00 2001 From: Charles Perry Date: Thu, 9 Apr 2026 06:36:54 -0700 Subject: [PATCH 0355/1518] net: phy: fix a return path in get_phy_c45_ids() [ Upstream commit 6f533abe7bbad2eef1e42c639b6bb9dad2b02362 ] The return value of phy_c45_probe_present() is stored in "ret", not "phy_reg", fix this. "phy_reg" always has a positive value if we reach this return path (since it would have returned earlier otherwise), which means that the original goal of the patch of not considering -ENODEV fatal wasn't achieved. Fixes: 17b447539408 ("net: phy: c45 scanning: Don't consider -ENODEV fatal") Signed-off-by: Charles Perry Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Link: https://patch.msgid.link/20260409133654.3203336-1-charles.perry@microchip.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/phy_device.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2353d6eced68d..dea8b94286d15 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -963,8 +963,8 @@ static int get_phy_c45_ids(struct mii_bus *bus, int addr, /* returning -ENODEV doesn't stop bus * scanning */ - return (phy_reg == -EIO || - phy_reg == -ENODEV) ? -ENODEV : -EIO; + return (ret == -EIO || + ret == -ENODEV) ? -ENODEV : -EIO; if (!ret) continue; From ef6d5a0688113b21135c8f271318bb2ecc929ab5 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 9 Apr 2026 23:28:51 +0300 Subject: [PATCH 0356/1518] net/mlx5e: Fix features not applied during netdev registration [ Upstream commit 9994ad4df82d64e57135c0f0906897685f5a9e87 ] mlx5e_fix_features() returns early when the netdevice is not present. This is correct during profile transitions where priv is cleared, but it also incorrectly blocks feature fixups during register_netdev(), when the device is also not yet present. It is not trivial to distinguish between both cases as we cannot use priv to carry state, and in both cases reg_state == NETREG_REGISTERED. Force a netdev features update after register_netdev() completes, where the device is present and fix_features() can actually work. This is not a pretty solution, as it results in an additional features update call (register_netdevice() already calls __netdev_update_features() internally), but it is the simplest, cleanest, and most robust way I found to fix this issue after multiple attempts. This fixes an issue on systems where CQE compression is enabled by default, RXHASH remains enabled after registration despite the two features being mutually exclusive. Fixes: ab4b01bfdaa6 ("net/mlx5e: Verify dev is present for fix features ndo") Signed-off-by: Gal Pressman Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260409202852.158059-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cb993ad2d9ad9..a696fb88dbef9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6740,6 +6740,14 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_resume; } + /* mlx5e_fix_features() returns early when the device is not present + * to avoid dereferencing cleared priv during profile changes. + * This also causes it to be a no-op during register_netdev(), where + * the device is not yet present. + * Trigger an additional features update that will actually work. + */ + mlx5e_update_features(netdev); + mlx5e_dcbnl_init_app(priv); mlx5_core_uplink_netdev_set(mdev, netdev); mlx5e_params_print_info(mdev, &priv->channels.params); From afdc8516213ee047f5162bdcd7f80ddc9ebae7ac Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 9 Apr 2026 23:28:52 +0300 Subject: [PATCH 0357/1518] net/mlx5e: IPsec, fix ASO poll timeout with read_poll_timeout_atomic() [ Upstream commit edccdd1eb94712da97a6ce71123ec27890add754 ] The do-while poll loop uses jiffies for its timeout: expires = jiffies + msecs_to_jiffies(10); jiffies is sampled at an arbitrary point within the current tick, so the first partial tick contributes anywhere from a full tick down to nearly zero real time. For small msecs_to_jiffies() results this is significant, the effective poll window can be much shorter than the requested 10ms, and in the worst case the loop exits after a single iteration (e.g., when HZ=100), well before the device has delivered the CQE. Replace the loop with read_poll_timeout_atomic(), which counts elapsed time via udelay() accounting rather than jiffies, guaranteeing the full poll window regardless of HZ. Additionally, read_poll_timeout_atomic() executes the poll operation one more time after the timeout has expired, giving the CQE a final chance to be detected. The old do-while loop could exit without a final poll if the timeout expired during the udelay() between iterations. Fixes: 76e463f6508b ("net/mlx5e: Overcome slow response for first IPsec ASO WQE") Signed-off-by: Gal Pressman Reviewed-by: Jianbo Liu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260409202852.158059-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../mellanox/mlx5/core/en_accel/ipsec_offload.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index e0611fa827971..9e9e18f5dbc9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2017, Mellanox Technologies inc. All rights reserved. */ +#include + #include "mlx5_core.h" #include "en.h" #include "ipsec.h" @@ -592,7 +594,6 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5_wqe_aso_ctrl_seg *ctrl; struct mlx5e_hw_objs *res; struct mlx5_aso_wqe *wqe; - unsigned long expires; u8 ds_cnt; int ret; @@ -614,13 +615,8 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, mlx5e_ipsec_aso_copy(ctrl, data); mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl); - expires = jiffies + msecs_to_jiffies(10); - do { - ret = mlx5_aso_poll_cq(aso->aso, false); - if (ret) - /* We are in atomic context */ - udelay(10); - } while (ret && time_is_after_jiffies(expires)); + read_poll_timeout_atomic(mlx5_aso_poll_cq, ret, !ret, 10, + 10 * USEC_PER_MSEC, false, aso->aso, false); if (!ret) memcpy(sa_entry->ctx, aso->ctx, MLX5_ST_SZ_BYTES(ipsec_aso)); spin_unlock_bh(&aso->lock); From 8042240412de3222d27b31e89d29336961cad9e4 Mon Sep 17 00:00:00 2001 From: Sun Jian Date: Wed, 8 Apr 2026 11:46:22 +0800 Subject: [PATCH 0358/1518] bpf: reject short IPv4/IPv6 inputs in bpf_prog_test_run_skb [ Upstream commit 12bec2bd4b76d81c5d3996bd14ec1b7f4d983747 ] bpf_prog_test_run_skb() calls eth_type_trans() first and then uses skb->protocol to initialize sk family and address fields for the test run. For IPv4 and IPv6 packets, it may access ip_hdr(skb) or ipv6_hdr(skb) even when the provided test input only contains an Ethernet header. Reject the input earlier if the Ethernet frame carries IPv4/IPv6 EtherType but the L3 header is too short. Fold the IPv4/IPv6 header length checks into the existing protocol switch and return -EINVAL before accessing the network headers. Fixes: fa5cb548ced6 ("bpf: Setup socket family and addresses in bpf_prog_test_run_skb") Reported-by: syzbot+619b9ef527f510a57cfc@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=619b9ef527f510a57cfc Signed-off-by: Sun Jian Link: https://lore.kernel.org/r/20260408034623.180320-2-sun.jian.kdev@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- net/bpf/test_run.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 65d7f8d51823e..963fee5d01e24 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1057,19 +1057,23 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, switch (skb->protocol) { case htons(ETH_P_IP): - sk->sk_family = AF_INET; - if (sizeof(struct iphdr) <= skb_headlen(skb)) { - sk->sk_rcv_saddr = ip_hdr(skb)->saddr; - sk->sk_daddr = ip_hdr(skb)->daddr; + if (skb_headlen(skb) < sizeof(struct iphdr)) { + ret = -EINVAL; + goto out; } + sk->sk_family = AF_INET; + sk->sk_rcv_saddr = ip_hdr(skb)->saddr; + sk->sk_daddr = ip_hdr(skb)->daddr; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - sk->sk_family = AF_INET6; - if (sizeof(struct ipv6hdr) <= skb_headlen(skb)) { - sk->sk_v6_rcv_saddr = ipv6_hdr(skb)->saddr; - sk->sk_v6_daddr = ipv6_hdr(skb)->daddr; + if (skb_headlen(skb) < sizeof(struct ipv6hdr)) { + ret = -EINVAL; + goto out; } + sk->sk_family = AF_INET6; + sk->sk_v6_rcv_saddr = ipv6_hdr(skb)->saddr; + sk->sk_v6_daddr = ipv6_hdr(skb)->daddr; break; #endif default: From 4ae187c7915d8b7de2cc56ba7732c046c82d198a Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 16 Mar 2026 14:34:13 -0400 Subject: [PATCH 0359/1518] Bluetooth: L2CAP: Fix printing wrong information if SDU length exceeds MTU [ Upstream commit 15bf35a660eb82a49f8397fc3d3acada8dae13db ] The code was printing skb->len and sdu_len in the places where it should be sdu_len and chan->imtu respectively to match the if conditions. Link: https://lore.kernel.org/linux-bluetooth/20260315132013.75ab40c5@kernel.org/T/#m1418f9c82eeff8510c1beaa21cf53af20db96c06 Fixes: e1d9a6688986 ("Bluetooth: LE L2CAP: Disconnect if received packet's SDU exceeds IMTU") Signed-off-by: Luiz Augusto von Dentz Reviewed-by: Paul Menzel Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 29e23f20dc438..7664723a34d0a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6733,7 +6733,7 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) if (sdu_len > chan->imtu) { BT_ERR("Too big LE L2CAP SDU length: len %u > %u", - skb->len, sdu_len); + sdu_len, chan->imtu); l2cap_send_disconn_req(chan, ECONNRESET); err = -EMSGSIZE; goto failed; From 3daa5818e473ed60eb69d8b5c71b651909d28c5a Mon Sep 17 00:00:00 2001 From: Jonathan Rissanen Date: Fri, 27 Mar 2026 11:47:20 +0100 Subject: [PATCH 0360/1518] Bluetooth: hci_ldisc: Clear HCI_UART_PROTO_INIT on error [ Upstream commit 68d39ea5e0adc9ecaea1ce8abd842ec972eb8718 ] When hci_register_dev() fails in hci_uart_register_dev() HCI_UART_PROTO_INIT is not cleared before calling hu->proto->close(hu) and setting hu->hdev to NULL. This means incoming UART data will reach the protocol-specific recv handler in hci_uart_tty_receive() after resources are freed. Clear HCI_UART_PROTO_INIT with a write lock before calling hu->proto->close() and setting hu->hdev to NULL. The write lock ensures all active readers have completed and no new reader can enter the protocol recv path before resources are freed. This allows the protocol-specific recv functions to remove the "HCI_UART_REGISTERED" guard without risking a null pointer dereference if hci_register_dev() fails. Fixes: 5df5dafc171b ("Bluetooth: hci_uart: Fix another race during initialization") Signed-off-by: Jonathan Rissanen Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_ldisc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 2b28515de92c4..5455990ab211e 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -692,6 +692,9 @@ static int hci_uart_register_dev(struct hci_uart *hu) if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); + percpu_down_write(&hu->proto_lock); + clear_bit(HCI_UART_PROTO_INIT, &hu->flags); + percpu_up_write(&hu->proto_lock); hu->proto->close(hu); hu->hdev = NULL; hci_free_dev(hdev); From 385b2d0468a0871fc716c549fa3b0c257c7dbcb3 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Sun, 29 Mar 2026 16:42:59 +0300 Subject: [PATCH 0361/1518] Bluetooth: fix locking in hci_conn_request_evt() with HCI_PROTO_DEFER [ Upstream commit 5c7209a341ff2ac338b2b0375c34a307b37c9ac2 ] When protocol sets HCI_PROTO_DEFER, hci_conn_request_evt() calls hci_connect_cfm(conn) without hdev->lock. Generally hci_connect_cfm() assumes it is held, and if conn is deleted concurrently -> UAF. Only SCO and ISO set HCI_PROTO_DEFER and only for defer setup listen, and HCI_EV_CONN_REQUEST is not generated for ISO. In the non-deferred listening socket code paths, hci_connect_cfm(conn) is called with hdev->lock held. Fix by holding the lock. Fixes: 70c464256310 ("Bluetooth: Refactor connection request handling") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/hci_event.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 6f77ab2629d65..b6b52b81b7b9c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3309,8 +3309,6 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, memcpy(conn->dev_class, ev->dev_class, 3); - hci_dev_unlock(hdev); - if (ev->link_type == ACL_LINK || (!(flags & HCI_PROTO_DEFER) && !lmp_esco_capable(hdev))) { struct hci_cp_accept_conn_req cp; @@ -3344,7 +3342,6 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, hci_connect_cfm(conn, 0); } - return; unlock: hci_dev_unlock(hdev); } From dc89961b76f12aff47124c1df4bdb32a080f4d0c Mon Sep 17 00:00:00 2001 From: Dudu Lu Date: Sun, 5 Apr 2026 23:47:41 +0800 Subject: [PATCH 0362/1518] Bluetooth: l2cap: Add missing chan lock in l2cap_ecred_reconf_rsp [ Upstream commit 42776497cdbc9a665b384a6dcb85f0d4bd927eab ] l2cap_ecred_reconf_rsp() calls l2cap_chan_del() without holding l2cap_chan_lock(). Every other l2cap_chan_del() caller in the file acquires the lock first. A remote BLE device can send a crafted L2CAP ECRED reconfiguration response to corrupt the channel list while another thread is iterating it. Add l2cap_chan_hold() and l2cap_chan_lock() before l2cap_chan_del(), and l2cap_chan_unlock() and l2cap_chan_put() after, matching the pattern used in l2cap_ecred_conn_rsp() and l2cap_conn_del(). Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode") Signed-off-by: Dudu Lu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 7664723a34d0a..bcb13ce531099 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5473,7 +5473,13 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn, if (chan->ident != cmd->ident) continue; + l2cap_chan_hold(chan); + l2cap_chan_lock(chan); + l2cap_chan_del(chan, ECONNRESET); + + l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } return 0; From b28b3bd9c42fd49169bda697d5e33570f4dbe9a9 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Tue, 7 Apr 2026 17:13:45 +0200 Subject: [PATCH 0363/1518] Bluetooth: SCO: check for codecs->num_codecs == 1 before assigning to sco_pi(sk)->codec [ Upstream commit 4e10a9ebbf081c16517cdd9366ac618bf38d7d0c ] copy_struct_from_sockptr() fill 'buffer' in sco_sock_setsockopt() with zeros, so there's no real problem. But it actually looks strange to do this, without checking all of codecs->codecs[0] really comes from userspace: sco_pi(sk)->codec = codecs->codecs[0]; As only optlen < sizeof(struct bt_codecs) is checked and codecs->num_codecs is not checked against != 1, but only <= 1, and the space for the additional struct bt_codec is not checked. Note I don't understand bluetooth and I didn't do any runtime tests with this! I just found it when debugging a problem in copy_struct_from_sockptr(). I just added this to check the size is as expected: BUILD_BUG_ON(struct_size(codecs, codecs, 0) != 1); BUILD_BUG_ON(struct_size(codecs, codecs, 1) != 8); And made sure it still compiles using this: make CF=-D__CHECK_ENDIAN__ W=1ce C=1 net/bluetooth/sco.o Fixes: 3e643e4efa1e ("Bluetooth: Improve setsockopt() handling of malformed user input") Cc: Michal Luczaj Cc: Luiz Augusto von Dentz Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Cc: David Wei Cc: linux-bluetooth@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Stefan Metzmacher Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/sco.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1a38577135d44..9404fdb10ea63 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1045,7 +1045,8 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, codecs = (void *)buffer; - if (codecs->num_codecs > 1) { + if (codecs->num_codecs != 1 || + optlen < struct_size(codecs, codecs, codecs->num_codecs)) { hci_dev_put(hdev); err = -EINVAL; break; From 1218bfe2ad6fb2803733766ae1d0cbdf7ff38a29 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 10 Apr 2026 19:10:20 +0200 Subject: [PATCH 0364/1518] net: phy: qcom: at803x: Use the correct bit to disable extended next page [ Upstream commit e7a62edd34b1b4bc5f979988efc2f81c075733fd ] As noted in the blamed commit, the AR8035 and other PHYs from this family advertise the Extended Next Page support by default, which may be understood by some partners as this PHY being multi-gig capable. The fix is to disable XNP advertising, which is done by setting bit 12 of the Auto-Negotiation Advertisement Register (MII_ADVERTISE). The blamed commit incorrectly uses MDIO_AN_CTRL1_XNP, which is bit 13 as per 802.3 : 45.2.7.1 AN control register (Register 7.0) BIT 12 in MII_ADVERTISE is wrapped by ADVERTISE_RESV, used by some drivers such as the aquantia one. 802.3 Clause 28 defines bit 12 as Extended Next Page ability, at least in recent versions of the standard. Let's add a define for it and use it in the at803x driver. Fixes: 3c51fa5d2afe ("net: phy: ar803x: disable extended next page bit") Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260410171021.1277138-1-maxime.chevallier@bootlin.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/qcom/at803x.c | 2 +- include/uapi/linux/mii.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 338acd11a9b65..023c1fe0cd14b 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -524,7 +524,7 @@ static int at803x_config_init(struct phy_device *phydev) * behaviour but we still need to accommodate it. XNP is only needed * for 10Gbps support, so disable XNP. */ - return phy_modify(phydev, MII_ADVERTISE, MDIO_AN_CTRL1_XNP, 0); + return phy_modify(phydev, MII_ADVERTISE, ADVERTISE_XNP, 0); } static void at803x_link_change_notify(struct phy_device *phydev) diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index 39f7c44baf535..61d6edad4b94a 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -82,7 +82,8 @@ #define ADVERTISE_100BASE4 0x0200 /* Try for 100mbps 4k packets */ #define ADVERTISE_PAUSE_CAP 0x0400 /* Try for pause */ #define ADVERTISE_PAUSE_ASYM 0x0800 /* Try for asymetric pause */ -#define ADVERTISE_RESV 0x1000 /* Unused... */ +#define ADVERTISE_XNP 0x1000 /* Extended Next Page */ +#define ADVERTISE_RESV ADVERTISE_XNP /* Used to be reserved */ #define ADVERTISE_RFAULT 0x2000 /* Say we can detect faults */ #define ADVERTISE_LPACK 0x4000 /* Ack link partners response */ #define ADVERTISE_NPAGE 0x8000 /* Next page bit */ From 81cfd603c0bde31e91de98b0a5fd766c94554382 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 10 Apr 2026 11:59:36 -0400 Subject: [PATCH 0365/1518] udp: Force compute_score to always inline [ Upstream commit b80a95ccf1604a882bb153c45ccb4056e44c8edb ] Back in 2024 I reported a 7-12% regression on an iperf3 UDP loopback thoughput test that we traced to the extra overhead of calling compute_score on two places, introduced by commit f0ea27e7bfe1 ("udp: re-score reuseport groups when connected sockets are present"). At the time, I pointed out the overhead was caused by the multiple calls, associated with cpu-specific mitigations, and merged commit 50aee97d1511 ("udp: Avoid call to compute_score on multiple sites") to jump back explicitly, to force the rescore call in a single place. Recently though, we got another regression report against a newer distro version, which a team colleague traced back to the same root-cause. Turns out that once we updated to gcc-13, the compiler got smart enough to unroll the loop, undoing my previous mitigation. Let's bite the bullet and __always_inline compute_score on both ipv4 and ipv6 to prevent gcc from de-optimizing it again in the future. These functions are only called in two places each, udpX_lib_lookup1 and udpX_lib_lookup2, so the extra size shouldn't be a problem and it is hot enough to be very visible in profilings. In fact, with gcc13, forcing the inline will prevent gcc from unrolling the fix from commit 50aee97d1511, so we don't end up increasing udpX_lib_lookup2 at all. I haven't recollected the results myself, as I don't have access to the machine at the moment. But the same colleague reported 4.67% inprovement with this patch in the loopback benchmark, solving the regression report within noise margins. Eric Dumazet reported no size change to vmlinux when built with clang. I report the same also with gcc-13: scripts/bloat-o-meter vmlinux vmlinux-inline add/remove: 0/2 grow/shrink: 4/0 up/down: 616/-416 (200) Function old new delta udp6_lib_lookup2 762 949 +187 __udp6_lib_lookup 810 975 +165 udp4_lib_lookup2 757 906 +149 __udp4_lib_lookup 871 986 +115 __pfx_compute_score 32 - -32 compute_score 384 - -384 Total: Before=35011784, After=35011984, chg +0.00% Fixes: 50aee97d1511 ("udp: Avoid call to compute_score on multiple sites") Reviewed-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: Gabriel Krisman Bertazi Link: https://patch.msgid.link/20260410155936.654915-1-krisman@suse.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/udp.c | 12 ++++++------ net/ipv6/udp.c | 13 +++++++------ 2 files changed, 13 insertions(+), 12 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index de0deded74f0a..a55642a42e82f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -365,10 +365,10 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static int compute_score(struct sock *sk, const struct net *net, - __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum, - int dif, int sdif) +static __always_inline int +compute_score(struct sock *sk, const struct net *net, + __be32 saddr, __be16 sport, __be32 daddr, + unsigned short hnum, int dif, int sdif) { int score; struct inet_sock *inet; @@ -508,8 +508,8 @@ static struct sock *udp4_lib_lookup2(const struct net *net, continue; /* compute_score is too long of a function to be - * inlined, and calling it again here yields - * measurable overhead for some + * inlined twice here, and calling it uninlined + * here yields measurable overhead for some * workloads. Work around it by jumping * backwards to rescore 'result'. */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 813a2ba75824d..d47b4f5ac8705 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -127,10 +127,11 @@ void udp_v6_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash, new_hash4); } -static int compute_score(struct sock *sk, const struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, unsigned short hnum, - int dif, int sdif) +static __always_inline int +compute_score(struct sock *sk, const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned short hnum, + int dif, int sdif) { int bound_dev_if, score; struct inet_sock *inet; @@ -260,8 +261,8 @@ static struct sock *udp6_lib_lookup2(const struct net *net, continue; /* compute_score is too long of a function to be - * inlined, and calling it again here yields - * measurable overhead for some + * inlined twice here, and calling it uninlined + * here yields measurable overhead for some * workloads. Work around it by jumping * backwards to rescore 'result'. */ From c5a1cb8ff82b06458b458f813c5190bdf4b4634c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 10 Apr 2026 23:53:27 +0000 Subject: [PATCH 0366/1518] tcp: Don't set treq->req_usec_ts in cookie_tcp_reqsk_init(). [ Upstream commit c058bbf05b1197c33df7204842665bd8bc70b3a8 ] Commit de5626b95e13 ("tcp: Factorise cookie-independent fields initialisation in cookie_v[46]_check().") miscategorised tcp_rsk(req)->req_usec_ts init to cookie_tcp_reqsk_init(), which is used by both BPF/non-BPF SYN cookie reqsk. Rather, it should have been moved to cookie_tcp_reqsk_alloc() by commit 8e7bab6b9652 ("tcp: Factorise cookie-dependent fields initialisation in cookie_v[46]_check()") so that only non-BPF SYN cookie sets tcp_rsk(req)->req_usec_ts to false. Let's move the initialisation to cookie_tcp_reqsk_alloc() to respect bpf_tcp_req_attrs.usec_ts_ok. Fixes: e472f88891ab ("bpf: tcp: Support arbitrary SYN Cookie.") Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260410235328.1773449-1-kuniyu@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/syncookies.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index fc3affd9c8014..b5f0a65c67864 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -286,7 +286,6 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = ntohl(th->ack_seq) - 1; treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; - treq->req_usec_ts = false; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -349,6 +348,7 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, ireq->wscale_ok = tcp_opt->wscale_ok; ireq->ecn_ok = !!(tcp_opt->rcv_tsecr & TS_OPT_ECN); + treq->req_usec_ts = false; treq->ts_off = tsoff; return req; From 6a7139084973b4854d589fc30a355c4a8428fcfd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 12 Apr 2026 14:13:51 -0400 Subject: [PATCH 0367/1518] sctp: fix missing encap_port propagation for GSO fragments [ Upstream commit bf6f95ae3b8b2638c0e1d6d802d50983ce5d0f45 ] encap_port in SCTP_INPUT_CB(skb) is used by sctp_vtag_verify() for SCTP-over-UDP processing. In the GSO case, it is only set on the head skb, while fragment skbs leave it 0. This results in fragment skbs seeing encap_port == 0, breaking SCTP-over-UDP connections. Fix it by propagating encap_port from the head skb cb when initializing fragment skbs in sctp_inq_pop(). Fixes: 046c052b475e ("sctp: enable udp tunneling socks") Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Link: https://patch.msgid.link/ea65ed61b3598d8b4940f0170b9aa1762307e6c3.1776017631.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/inqueue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index f5a7d5a387555..a024c08432471 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -201,6 +201,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) cb->chunk = head_cb->chunk; cb->af = head_cb->af; + cb->encap_port = head_cb->encap_port; } } From 7bad93e99737e4a5c0c14ac50c05152cf4e28022 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Sat, 11 Apr 2026 08:55:19 +0800 Subject: [PATCH 0368/1518] net, bpf: fix null-ptr-deref in xdp_master_redirect() for down master [ Upstream commit 1921f91298d1388a0bb9db8f83800c998b649cb3 ] syzkaller reported a kernel panic in bond_rr_gen_slave_id() reached via xdp_master_redirect(). Full decoded trace: https://syzkaller.appspot.com/bug?extid=80e046b8da2820b6ba73 bond_rr_gen_slave_id() dereferences bond->rr_tx_counter, a per-CPU counter that bonding only allocates in bond_open() when the mode is round-robin. If the bond device was never brought up, rr_tx_counter stays NULL. The XDP redirect path can still reach that code on a bond that was never opened: bpf_master_redirect_enabled_key is a global static key, so as soon as any bond device has native XDP attached, the XDP_TX -> xdp_master_redirect() interception is enabled for every slave system-wide. The path xdp_master_redirect() -> bond_xdp_get_xmit_slave() -> bond_xdp_xmit_roundrobin_slave_get() -> bond_rr_gen_slave_id() then runs against a bond that has no rr_tx_counter and crashes. Fix this in the generic xdp_master_redirect() by refusing to call into the master's ->ndo_xdp_get_xmit_slave() when the master device is not up. IFF_UP is only set after ->ndo_open() has successfully returned, so this reliably excludes masters whose XDP state has not been fully initialized. Drop the frame with XDP_ABORTED so the exception is visible via trace_xdp_exception() rather than silently falling through. This is not specific to bonding: any current or future master that defers XDP state allocation to ->ndo_open() is protected. Fixes: 879af96ffd72 ("net, core: Add support for XDP redirection to slave device") Reported-by: syzbot+80e046b8da2820b6ba73@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/698f84c6.a70a0220.2c38d7.00cc.GAE@google.com/T/ Suggested-by: Daniel Borkmann Acked-by: Daniel Borkmann Signed-off-by: Jiayuan Chen Link: https://patch.msgid.link/20260411005524.201200-2-jiayuan.chen@linux.dev Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index 3d4bf4d2a1a4b..7fc01474c3781 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4385,6 +4385,8 @@ u32 xdp_master_redirect(struct xdp_buff *xdp) struct net_device *master, *slave; master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); + if (unlikely(!(master->flags & IFF_UP))) + return XDP_ABORTED; slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); if (slave && slave != xdp->rxq->dev) { /* The target device is different from the receiving device, so From f98084d9786441eb358f702d5aa773db99f383d5 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 12 Apr 2026 10:43:26 +0200 Subject: [PATCH 0369/1518] net: airoha: Add missing PPE configurations in airoha_ppe_hw_init() [ Upstream commit b9d8b856689d2b968495d79fe653d87fcb8ad98c ] Add the following PPE configuration in airoha_ppe_hw_init routine: - 6RD hw offloading is currently not supported by Netfilter flowtable. Disable explicitly PPE 6RD offloading in order to prevent PPE to learn 6RD flows and eventually interrupt the traffic. - Add missing PPE bind rate configuration for L3 and L2 traffic. PPE bind rate configuration specifies the pps threshold to move a PPE entry state from UNBIND to BIND. Without this configuration this value is random. - Set ageing thresholds to the values used in the vendor SDK in order to improve connection stability under load and avoid packet loss caused by fast aging. Fixes: 00a7678310fe3 ("net: airoha: Introduce flowtable offload support") Signed-off-by: Lorenzo Bianconi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260412-airoha_ppe_hw_init-missing-bits-v1-1-06ac670819e3@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_ppe.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 4ed244557065d..81a7056e3510a 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -83,13 +83,13 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) airoha_fe_rmw(eth, REG_PPE_BND_AGE0(i), PPE_BIND_AGE0_DELTA_NON_L4 | PPE_BIND_AGE0_DELTA_UDP, - FIELD_PREP(PPE_BIND_AGE0_DELTA_NON_L4, 1) | - FIELD_PREP(PPE_BIND_AGE0_DELTA_UDP, 12)); + FIELD_PREP(PPE_BIND_AGE0_DELTA_NON_L4, 60) | + FIELD_PREP(PPE_BIND_AGE0_DELTA_UDP, 60)); airoha_fe_rmw(eth, REG_PPE_BND_AGE1(i), PPE_BIND_AGE1_DELTA_TCP_FIN | PPE_BIND_AGE1_DELTA_TCP, FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP_FIN, 1) | - FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP, 7)); + FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP, 60)); airoha_fe_rmw(eth, REG_PPE_TB_HASH_CFG(i), PPE_SRAM_TABLE_EN_MASK | @@ -111,7 +111,15 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) | FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0)); + airoha_fe_rmw(eth, REG_PPE_BIND_RATE(i), + PPE_BIND_RATE_L2B_BIND_MASK | + PPE_BIND_RATE_BIND_MASK, + FIELD_PREP(PPE_BIND_RATE_L2B_BIND_MASK, 0x1e) | + FIELD_PREP(PPE_BIND_RATE_BIND_MASK, 0x1e)); + airoha_fe_wr(eth, REG_PPE_HASH_SEED(i), PPE_HASH_SEED); + airoha_fe_clear(eth, REG_PPE_PPE_FLOW_CFG(i), + PPE_FLOW_CFG_IP6_6RD_MASK); for (p = 0; p < ARRAY_SIZE(eth->ports); p++) airoha_fe_rmw(eth, REG_PPE_MTU(i, p), From 60a90d853fcae19c111ac95d84081e1a3b19c91a Mon Sep 17 00:00:00 2001 From: Yuwen Chen Date: Wed, 28 Jan 2026 10:03:10 +0800 Subject: [PATCH 0370/1518] selftests/futex: Fix incorrect result reporting of futex_requeue test item [ Upstream commit d317e2ef9dcf673c9f37cda784284af7c6812757 ] When using the TEST_HARNESS_MAIN macro definition to declare the main function, it is required to use the EXPECT*() and ASSERT*() macros in conjunction and not ksft_test_result_*(). Otherwise, even if a test item fails, the test will still return a success result because ksft_test_result_*() does not affect the test harness state. Convert the code to use EXPECT/ASSERT() variants, which ensures that the overall test result is fail if one of the EXPECT()s fails. [ tglx: Massaged change log to explain _why_ ksft_test_result*() is the wrong choice ] Fixes: f341a20f6d7e ("selftests/futex: Refactor futex_requeue with kselftest_harness.h") Signed-off-by: Yuwen Chen Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/tencent_51851B741CC4B5EC9C22AFF70BA82BB60805@qq.com Signed-off-by: Sasha Levin --- .../futex/functional/futex_requeue.c | 49 +++---------------- 1 file changed, 8 insertions(+), 41 deletions(-) diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c index 69e2555b60399..d6be3fbd436a4 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue.c +++ b/tools/testing/selftests/futex/functional/futex_requeue.c @@ -34,34 +34,18 @@ TEST(requeue_single) volatile futex_t _f1 = 0; volatile futex_t f2 = 0; pthread_t waiter[10]; - int res; f1 = &_f1; /* * Requeue a waiter from f1 to f2, and wake f2. */ - if (pthread_create(&waiter[0], NULL, waiterfn, NULL)) - ksft_exit_fail_msg("pthread_create failed\n"); + ASSERT_EQ(0, pthread_create(&waiter[0], NULL, waiterfn, NULL)); usleep(WAKE_WAIT_US); - ksft_print_dbg_msg("Requeuing 1 futex from f1 to f2\n"); - res = futex_cmp_requeue(f1, 0, &f2, 0, 1, 0); - if (res != 1) - ksft_test_result_fail("futex_requeue simple returned: %d %s\n", - res ? errno : res, - res ? strerror(errno) : ""); - - ksft_print_dbg_msg("Waking 1 futex at f2\n"); - res = futex_wake(&f2, 1, 0); - if (res != 1) { - ksft_test_result_fail("futex_requeue simple returned: %d %s\n", - res ? errno : res, - res ? strerror(errno) : ""); - } else { - ksft_test_result_pass("futex_requeue simple succeeds\n"); - } + EXPECT_EQ(1, futex_cmp_requeue(f1, 0, &f2, 0, 1, 0)); + EXPECT_EQ(1, futex_wake(&f2, 1, 0)); } TEST(requeue_multiple) @@ -69,7 +53,7 @@ TEST(requeue_multiple) volatile futex_t _f1 = 0; volatile futex_t f2 = 0; pthread_t waiter[10]; - int res, i; + int i; f1 = &_f1; @@ -77,30 +61,13 @@ TEST(requeue_multiple) * Create 10 waiters at f1. At futex_requeue, wake 3 and requeue 7. * At futex_wake, wake INT_MAX (should be exactly 7). */ - for (i = 0; i < 10; i++) { - if (pthread_create(&waiter[i], NULL, waiterfn, NULL)) - ksft_exit_fail_msg("pthread_create failed\n"); - } + for (i = 0; i < 10; i++) + ASSERT_EQ(0, pthread_create(&waiter[i], NULL, waiterfn, NULL)); usleep(WAKE_WAIT_US); - ksft_print_dbg_msg("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n"); - res = futex_cmp_requeue(f1, 0, &f2, 3, 7, 0); - if (res != 10) { - ksft_test_result_fail("futex_requeue many returned: %d %s\n", - res ? errno : res, - res ? strerror(errno) : ""); - } - - ksft_print_dbg_msg("Waking INT_MAX futexes at f2\n"); - res = futex_wake(&f2, INT_MAX, 0); - if (res != 7) { - ksft_test_result_fail("futex_requeue many returned: %d %s\n", - res ? errno : res, - res ? strerror(errno) : ""); - } else { - ksft_test_result_pass("futex_requeue many succeeds\n"); - } + EXPECT_EQ(10, futex_cmp_requeue(f1, 0, &f2, 3, 7, 0)); + EXPECT_EQ(7, futex_wake(&f2, INT_MAX, 0)); } TEST_HARNESS_MAIN From fe1f80f8f6e8611ac6349b9d464e8750443390cf Mon Sep 17 00:00:00 2001 From: Alexander Konyukhov Date: Tue, 3 Feb 2026 16:48:46 +0300 Subject: [PATCH 0371/1518] drm/komeda: fix integer overflow in AFBC framebuffer size check [ Upstream commit 779ec12c85c9e4547519e3903a371a3b26a289de ] The AFBC framebuffer size validation calculates the minimum required buffer size by adding the AFBC payload size to the framebuffer offset. This addition is performed without checking for integer overflow. If the addition oveflows, the size check may incorrectly succed and allow userspace to provide an undersized drm_gem_object, potentially leading to out-of-bounds memory access. Add usage of check_add_overflow() to safely compute the minimum required size and reject the framebuffer if an overflow is detected. This makes the AFBC size validation more robust against malformed. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 65ad2392dd6d ("drm/komeda: Added AFBC support for komeda driver") Signed-off-by: Alexander Konyukhov Acked-by: Liviu Dudau Signed-off-by: Liviu Dudau Link: https://lore.kernel.org/r/20260203134907.1587067-1-Alexander.Konyukhov@kaspersky.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c b/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c index 901f938aefe08..e4b7e2a89d044 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c @@ -4,6 +4,8 @@ * Author: James.Qian.Wang * */ +#include + #include #include #include @@ -92,7 +94,9 @@ komeda_fb_afbc_size_check(struct komeda_fb *kfb, struct drm_file *file, kfb->afbc_size = kfb->offset_payload + n_blocks * ALIGN(bpp * AFBC_SUPERBLK_PIXELS / 8, AFBC_SUPERBLK_ALIGNMENT); - min_size = kfb->afbc_size + fb->offsets[0]; + if (check_add_overflow(kfb->afbc_size, fb->offsets[0], &min_size)) { + goto check_failed; + } if (min_size > obj->size) { DRM_DEBUG_KMS("afbc size check failed, obj_size: 0x%zx. min_size 0x%llx.\n", obj->size, min_size); From 1f7687123d38f9494f7c2e41c80b957d618e9ed3 Mon Sep 17 00:00:00 2001 From: Val Packett Date: Wed, 10 Dec 2025 12:39:23 -0300 Subject: [PATCH 0372/1518] drm/virtio: Allow importing prime buffers when 3D is enabled [ Upstream commit df4dc947c46bb9f80038f52c6e38cb2d40c10e50 ] This functionality was added for using a KMS-only virtgpu with a physical (or SR-IOV) headless GPU in passthrough, but it should not be restricted to KMS-only mode. It can be used with cross-domain to pass guest memfds to the host compositor with zero copies (using udmabuf on both sides). Drop the check for the absence of virgl_3d to allow for more use cases. Fixes: ca77f27a2665 ("drm/virtio: Import prime buffers from other devices as guest blobs") Signed-off-by: Val Packett Reviewed-by: Dmitry Osipenko Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/20251210154755.1119861-2-val@invisiblethingslab.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/virtio/virtgpu_prime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index ce49282198cbf..2fedd5d3bd62c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -312,7 +312,7 @@ struct drm_gem_object *virtgpu_gem_prime_import(struct drm_device *dev, } } - if (!vgdev->has_resource_blob || vgdev->has_virgl_3d) + if (!vgdev->has_resource_blob) return drm_gem_prime_import(dev, buf); bo = kzalloc(sizeof(*bo), GFP_KERNEL); From e14de2cb819ffd210bb78943e3e0082e93f29dc7 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 19 Feb 2026 04:53:52 +0000 Subject: [PATCH 0373/1518] ASoC: soc-compress: use function to clear symmetric params [ Upstream commit 07c774dd64ba0c605dbf844132122e3edbdbea93 ] Current soc-compress.c clears symmetric_rate, but it clears rate only, not clear other symmetric_channels/sample_bits. static int soc_compr_clean(...) { ... if (!snd_soc_dai_active(cpu_dai)) => cpu_dai->symmetric_rate = 0; if (!snd_soc_dai_active(codec_dai)) => codec_dai->symmetric_rate = 0; ... }; This feature was added when v3.7 kernel [1], and there was only symmetric_rate, no symmetric_channels/sample_bits in that timing. symmetric_channels/sample_bits were added in v3.14 [2], but I guess it didn't notice that soc-compress.c is updating symmetric_xxx. We are clearing symmetry_xxx by soc_pcm_set_dai_params(), but is soc-pcm.c local function. Makes it global function and clear symmetry_xxx by it. [1] commit 1245b7005de02 ("ASoC: add compress stream support") [2] commit 3635bf09a89cf ("ASoC: soc-pcm: add symmetry for channels and sample bits") Fixes: 3635bf09a89c ("ASoC: soc-pcm: add symmetry for channels and sample bits") Cc: Nicolin Chen Signed-off-by: Kuninori Morimoto Link: https://patch.msgid.link/87ms15e3kv.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- include/sound/soc.h | 3 +++ sound/soc/soc-compress.c | 4 ++-- sound/soc/soc-pcm.c | 4 ++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/include/sound/soc.h b/include/sound/soc.h index a9c058b06ab42..33968935d00a9 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1414,6 +1414,9 @@ struct snd_soc_dai *snd_soc_find_dai( struct snd_soc_dai *snd_soc_find_dai_with_mutex( const struct snd_soc_dai_link_component *dlc); +void soc_pcm_set_dai_params(struct snd_soc_dai *dai, + struct snd_pcm_hw_params *params); + #include static inline diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 7b81dffc6a935..b8402802ae784 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -69,10 +69,10 @@ static int soc_compr_clean(struct snd_compr_stream *cstream, int rollback) snd_soc_dai_digital_mute(codec_dai, 1, stream); if (!snd_soc_dai_active(cpu_dai)) - cpu_dai->symmetric_rate = 0; + soc_pcm_set_dai_params(cpu_dai, NULL); if (!snd_soc_dai_active(codec_dai)) - codec_dai->symmetric_rate = 0; + soc_pcm_set_dai_params(codec_dai, NULL); snd_soc_link_compr_shutdown(cstream, rollback); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 2c21fd528afd0..99299364c9ba3 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -423,8 +423,8 @@ void dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir, int event) snd_soc_dapm_stream_event(fe, dir, event); } -static void soc_pcm_set_dai_params(struct snd_soc_dai *dai, - struct snd_pcm_hw_params *params) +void soc_pcm_set_dai_params(struct snd_soc_dai *dai, + struct snd_pcm_hw_params *params) { if (params) { dai->symmetric_rate = params_rate(params); From 511c093d9ef4b7002ed1be6d1f0a5732b4335bd6 Mon Sep 17 00:00:00 2001 From: George Abraham P Date: Fri, 9 Jan 2026 10:59:23 +0530 Subject: [PATCH 0374/1518] PCI/TPH: Allow TPH enable for RCiEPs [ Upstream commit d3e996a596967a62c8a13a279221513461f6ab97 ] Previously, pcie_enable_tph() only enabled TLP Processing Hints (TPH) if both the Endpoint and its Root Port advertised TPH support. Root Complex Integrated Endpoints (RCiEPs) are directly integrated into a Root Complex and do not have an associated Root Port, so pcie_enable_tph() never enabled TPH for RCiEPs. PCIe r7.0 doesn't seem to include a way to learn whether a Root Complex supports TPH, but sec 2.2.7.1.1 says Functions that lack TPH support should ignore TPH, and maybe the same is true for Root Complexes: A Function that does not support the TPH Completer or Routing capability and receives a transaction with the TH bit [which indicates the presence of TPH in the TLP header] Set is required to ignore the TH bit and handle the Request in the same way as Requests of the same transaction type without the TH bit Set. Allow drivers to enable TPH for any RCiEP with a TPH Requester Capability. Fixes: f69767a1ada3 ("PCI: Add TLP Processing Hints (TPH) support") Signed-off-by: George Abraham P [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20260109052923.1170070-1-george.abraham.p@intel.com Signed-off-by: Sasha Levin --- drivers/pci/tph.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c index cc64f93709a4f..c61456d24f61b 100644 --- a/drivers/pci/tph.c +++ b/drivers/pci/tph.c @@ -397,10 +397,13 @@ int pcie_enable_tph(struct pci_dev *pdev, int mode) else pdev->tph_req_type = PCI_TPH_REQ_TPH_ONLY; - rp_req_type = get_rp_completer_type(pdev); + /* Check if the device is behind a Root Port */ + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_RC_END) { + rp_req_type = get_rp_completer_type(pdev); - /* Final req_type is the smallest value of two */ - pdev->tph_req_type = min(pdev->tph_req_type, rp_req_type); + /* Final req_type is the smallest value of two */ + pdev->tph_req_type = min(pdev->tph_req_type, rp_req_type); + } if (pdev->tph_req_type == PCI_TPH_REQ_DISABLE) return -EINVAL; From b13984f0212f2ead9963de18de7f15516df7590a Mon Sep 17 00:00:00 2001 From: Koichiro Den Date: Tue, 17 Feb 2026 15:38:55 +0900 Subject: [PATCH 0375/1518] PCI: endpoint: pci-epf-test: Don't free doorbell IRQ unless requested [ Upstream commit e81fa70179aac6ac3a6636565d5d35968dca3900 ] pci_epf_test_doorbell_cleanup() unconditionally calls free_irq() for the doorbell virq, which can trigger "Trying to free already-free IRQ" warnings when the IRQ was never requested or when request_threaded_irq() failed. Move free_irq() out of pci_epf_test_doorbell_cleanup() and invoke it only after a successful request, so that free_irq() is not called for an unrequested IRQ. Fixes: eff0c286aa91 ("PCI: endpoint: pci-epf-test: Add doorbell test support") Signed-off-by: Koichiro Den Signed-off-by: Manivannan Sadhasivam Reviewed-by: Frank Li Reviewed-by: Niklas Cassel Link: https://patch.msgid.link/20260217063856.3759713-3-den@valinux.co.jp Signed-off-by: Sasha Levin --- drivers/pci/endpoint/functions/pci-epf-test.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index b05e8db575c35..9bc6d283eae25 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -704,7 +704,6 @@ static void pci_epf_test_doorbell_cleanup(struct pci_epf_test *epf_test) struct pci_epf_test_reg *reg = epf_test->reg[epf_test->test_reg_bar]; struct pci_epf *epf = epf_test->epf; - free_irq(epf->db_msg[0].virq, epf_test); reg->doorbell_bar = cpu_to_le32(NO_BAR); pci_epf_free_doorbell(epf); @@ -748,7 +747,7 @@ static void pci_epf_test_enable_doorbell(struct pci_epf_test *epf_test, &epf_test->db_bar.phys_addr, &offset); if (ret) - goto err_doorbell_cleanup; + goto err_free_irq; reg->doorbell_offset = cpu_to_le32(offset); @@ -758,12 +757,14 @@ static void pci_epf_test_enable_doorbell(struct pci_epf_test *epf_test, ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, &epf_test->db_bar); if (ret) - goto err_doorbell_cleanup; + goto err_free_irq; status |= STATUS_DOORBELL_ENABLE_SUCCESS; reg->status = cpu_to_le32(status); return; +err_free_irq: + free_irq(epf->db_msg[0].virq, epf_test); err_doorbell_cleanup: pci_epf_test_doorbell_cleanup(epf_test); set_status_err: @@ -783,6 +784,7 @@ static void pci_epf_test_disable_doorbell(struct pci_epf_test *epf_test, if (bar < BAR_0) goto set_status_err; + free_irq(epf->db_msg[0].virq, epf_test); pci_epf_test_doorbell_cleanup(epf_test); /* From 175717cfc06cab79f84cd037d66dda1b8564cd9e Mon Sep 17 00:00:00 2001 From: Koichiro Den Date: Tue, 17 Feb 2026 15:38:56 +0900 Subject: [PATCH 0376/1518] PCI: endpoint: pci-ep-msi: Fix error unwind and prevent double alloc [ Upstream commit 1cba96c0a795124c3229293ed7b5b5765e66f259 ] pci_epf_alloc_doorbell() stores the allocated doorbell message array in epf->db_msg/epf->num_db before requesting MSI vectors. If MSI allocation fails, the array is freed but the EPF state may still point to freed memory. Clear epf->db_msg and epf->num_db on the MSI allocation failure path so that later cleanup cannot double-free the array and callers can retry allocation. Also return -EBUSY when doorbells have already been allocated to prevent leaking or overwriting an existing allocation. Fixes: 1c3b002c6bf6 ("PCI: endpoint: Add RC-to-EP doorbell support using platform MSI controller") Signed-off-by: Koichiro Den Signed-off-by: Manivannan Sadhasivam Reviewed-by: Frank Li Reviewed-by: Niklas Cassel Link: https://patch.msgid.link/20260217063856.3759713-4-den@valinux.co.jp Signed-off-by: Sasha Levin --- drivers/pci/endpoint/pci-ep-msi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/pci/endpoint/pci-ep-msi.c b/drivers/pci/endpoint/pci-ep-msi.c index 1b58357b905fa..ad8a81d6ad773 100644 --- a/drivers/pci/endpoint/pci-ep-msi.c +++ b/drivers/pci/endpoint/pci-ep-msi.c @@ -50,6 +50,9 @@ int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 num_db) return -EINVAL; } + if (epf->db_msg) + return -EBUSY; + domain = of_msi_map_get_device_domain(epc->dev.parent, 0, DOMAIN_BUS_PLATFORM_MSI); if (!domain) { @@ -79,6 +82,8 @@ int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 num_db) if (ret) { dev_err(dev, "Failed to allocate MSI\n"); kfree(msg); + epf->db_msg = NULL; + epf->num_db = 0; return ret; } From 47038159c559824f4dbfb5b0d87b9b3416663372 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Mon, 16 Feb 2026 19:48:01 -0600 Subject: [PATCH 0377/1518] drm/sun4i: backend: fix error pointer dereference [ Upstream commit 06277983eca4a31d3c2114fa33d99a6e82484b11 ] The function drm_atomic_get_plane_state() can return an error pointer and is not checked for it. Add error pointer check. Detected by Smatch: drivers/gpu/drm/sun4i/sun4i_backend.c:496 sun4i_backend_atomic_check() error: 'plane_state' dereferencing possible ERR_PTR() Fixes: 96180dde23b79 ("drm/sun4i: backend: Add a custom atomic_check for the frontend") Signed-off-by: Ethan Tidmore Reviewed-by: Chen-Yu Tsai Link: https://patch.msgid.link/20260217014801.60760-1-ethantidmore06@gmail.com Signed-off-by: Chen-Yu Tsai Signed-off-by: Sasha Levin --- drivers/gpu/drm/sun4i/sun4i_backend.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 2dded3b828df0..0484cc27c97ae 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -490,6 +490,9 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine, drm_for_each_plane_mask(plane, drm, crtc_state->plane_mask) { struct drm_plane_state *plane_state = drm_atomic_get_plane_state(state, plane); + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + struct sun4i_layer_state *layer_state = state_to_sun4i_layer_state(plane_state); struct drm_framebuffer *fb = plane_state->fb; From 36a0dcd0077b879e14c0a473d24a4d393000281d Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Sat, 24 Jan 2026 23:42:45 +0800 Subject: [PATCH 0378/1518] PCI: imx6: Fix device node reference leak in imx_pcie_probe() [ Upstream commit 3b55079d6387805ede687e234d84669aeb0f7e98 ] In imx_pcie_probe(), of_parse_phandle() returns the device node pointer with increased refcount. The pointer reference must be dropped by the caller when it's no longer needed. However, imx_pcie_probe() doesn't drop the reference, causing reference leak. Fix this by using the __free(device_node) cleanup handler to drop the reference when the function goes out of scope. Fixes: 1df82ec46600 ("PCI: imx: Add workaround for e10728, IMX7d PCIe PLL failure") Signed-off-by: Felix Gu [mani: commit log] Signed-off-by: Manivannan Sadhasivam Reviewed-by: Frank Li Acked-by: Richard Zhu Link: https://patch.msgid.link/20260124-pci_imx6-v2-1-acb8d5187683@gmail.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pci-imx6.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 3984c16dbec39..9083658a4287f 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -1619,7 +1619,6 @@ static int imx_pcie_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct dw_pcie *pci; struct imx_pcie *imx_pcie; - struct device_node *np; struct device_node *node = dev->of_node; int ret, domain; u16 val; @@ -1646,7 +1645,8 @@ static int imx_pcie_probe(struct platform_device *pdev) pci->pp.ops = &imx_pcie_host_dw_pme_ops; /* Find the PHY if one is defined, only imx7d uses it */ - np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0); + struct device_node *np __free(device_node) = + of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0); if (np) { struct resource res; From 1f2e41bd668f8f55871555d28763802aaf22143e Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 25 Feb 2026 14:01:16 +0000 Subject: [PATCH 0379/1518] ASoC: SDCA: Update counting of SU/GE DAPM routes [ Upstream commit 1fb720d33eecdb9a90ee340b3000ba378d49f5ca ] Device Layer Selector Unit's are controlled by a Group Entity control rather than by the host directly. For the purposes of the ASoC class driver the number of input routes to the SU is controlled by the number of options within the Group Entity Selected Mode Control. ie. One valid DAPM route for each valid route defined in the Group Entity. Currently the code assumes that a Device Layer SU will have a number of routes equal to the number of potential sources for the SU. ie. it counts the routes using the SU, but then creates the routes using the GE. However, this isn't actually true, it is perfectly allowed for the GE to only define options for some of the potential sources of the SU.o In such a case the number of routes return will not match those created, leading to either an overflow of the routes array or undefined routes to be past to the ASoC core, both of which generally lead to the sound card failing to probe. Update the handling for the counting of routes to count the connected routes on the GE itself and then ignore the source routes on the SU. This makes it match the logic generating the routes and ensuring that both remain in sync. Fixes: 2c8b3a8e6aa8 ("ASoC: SDCA: Create DAPM widgets and routes from DisCo") Reviewed-by: Pierre-Louis Bossart Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20260225140118.402695-3-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sdca/sdca_asoc.c | 41 +++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/sound/soc/sdca/sdca_asoc.c b/sound/soc/sdca/sdca_asoc.c index 197a592ec2f16..523ea9a2c5f42 100644 --- a/sound/soc/sdca/sdca_asoc.c +++ b/sound/soc/sdca/sdca_asoc.c @@ -51,6 +51,25 @@ static bool readonly_control(struct sdca_control *control) return control->has_fixed || control->mode == SDCA_ACCESS_MODE_RO; } +static int ge_count_routes(struct sdca_entity *entity) +{ + int count = 0; + int i, j; + + for (i = 0; i < entity->ge.num_modes; i++) { + struct sdca_ge_mode *mode = &entity->ge.modes[i]; + + for (j = 0; j < mode->num_controls; j++) { + struct sdca_ge_control *affected = &mode->controls[j]; + + if (affected->sel != SDCA_CTL_SU_SELECTOR || affected->val) + count++; + } + } + + return count; +} + /** * sdca_asoc_count_component - count the various component parts * @dev: Pointer to the device against which allocations will be done. @@ -74,6 +93,7 @@ int sdca_asoc_count_component(struct device *dev, struct sdca_function_data *fun int *num_widgets, int *num_routes, int *num_controls, int *num_dais) { + struct sdca_control *control; int i, j; *num_widgets = function->num_entities - 1; @@ -83,6 +103,7 @@ int sdca_asoc_count_component(struct device *dev, struct sdca_function_data *fun for (i = 0; i < function->num_entities - 1; i++) { struct sdca_entity *entity = &function->entities[i]; + bool skip_primary_routes = false; /* Add supply/DAI widget connections */ switch (entity->type) { @@ -96,6 +117,17 @@ int sdca_asoc_count_component(struct device *dev, struct sdca_function_data *fun case SDCA_ENTITY_TYPE_PDE: *num_routes += entity->pde.num_managed; break; + case SDCA_ENTITY_TYPE_GE: + *num_routes += ge_count_routes(entity); + skip_primary_routes = true; + break; + case SDCA_ENTITY_TYPE_SU: + control = sdca_selector_find_control(dev, entity, SDCA_CTL_SU_SELECTOR); + if (!control) + return -EINVAL; + + skip_primary_routes = (control->layers == SDCA_ACCESS_LAYER_DEVICE); + break; default: break; } @@ -104,7 +136,8 @@ int sdca_asoc_count_component(struct device *dev, struct sdca_function_data *fun (*num_routes)++; /* Add primary entity connections from DisCo */ - *num_routes += entity->num_sources; + if (!skip_primary_routes) + *num_routes += entity->num_sources; for (j = 0; j < entity->num_controls; j++) { if (exported_control(entity, &entity->controls[j])) @@ -451,7 +484,6 @@ static int entity_parse_su_device(struct device *dev, struct snd_soc_dapm_route **route) { struct sdca_control_range *range; - int num_routes = 0; int i, j; if (!entity->group) { @@ -487,11 +519,6 @@ static int entity_parse_su_device(struct device *dev, return -EINVAL; } - if (++num_routes > entity->num_sources) { - dev_err(dev, "%s: too many input routes\n", entity->label); - return -EINVAL; - } - term = sdca_range_search(range, SDCA_SELECTED_MODE_INDEX, mode->val, SDCA_SELECTED_MODE_TERM_TYPE); if (!term) { From 7ed07c9ce5252f841bc38077389b428b16ab0f56 Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Sun, 8 Feb 2026 11:35:53 +0100 Subject: [PATCH 0380/1518] crypto: inside-secure/eip93 - fix register definition [ Upstream commit b7abbc8c7acaeb60c114b038f1fa91bbedb3d16a ] Checked the register definitions with the documentation[1]. Turns out that the PKTE_INBUF_CNT register has a bad offset. It's used in Direct Host Mode (DHM). The driver uses Autonomous Ring Mode (ARM), so it causes no harm. 1. ADSP-SC58x/ADSP-2158x SHARC+ Processor Hardware Reference Fixes: 9739f5f93b78 ("crypto: eip93 - Add Inside Secure SafeXcel EIP-93 crypto engine support") Signed-off-by: Aleksander Jan Bajkowski Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/inside-secure/eip93/eip93-regs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/inside-secure/eip93/eip93-regs.h b/drivers/crypto/inside-secure/eip93/eip93-regs.h index 0490b8d151311..116b3fbb6ad79 100644 --- a/drivers/crypto/inside-secure/eip93/eip93-regs.h +++ b/drivers/crypto/inside-secure/eip93/eip93-regs.h @@ -109,7 +109,7 @@ #define EIP93_REG_PE_BUF_THRESH 0x10c #define EIP93_PE_OUTBUF_THRESH GENMASK(23, 16) #define EIP93_PE_INBUF_THRESH GENMASK(7, 0) -#define EIP93_REG_PE_INBUF_COUNT 0x100 +#define EIP93_REG_PE_INBUF_COUNT 0x110 #define EIP93_REG_PE_OUTBUF_COUNT 0x114 #define EIP93_REG_PE_BUF_RW_PNTR 0x118 /* BUF_PNTR */ From 17584bdc724780f4ddc8689f776c420ebd0dc480 Mon Sep 17 00:00:00 2001 From: Sander Vanheule Date: Fri, 20 Feb 2026 16:26:33 +0100 Subject: [PATCH 0381/1518] ASoC: sti: Return errors from regmap_field_alloc() [ Upstream commit 272aabef50bc3fe58edd26de000f4cdd41bdbe60 ] When regmap_field_alloc() fails, it can return an error. Specifically, it will return PTR_ERR(-ENOMEM) when the allocation returns a NULL pointer. The code then uses these allocations with a simple NULL check: if (player->clk_sel) { // May dereference invalid pointer (-ENOMEM) err = regmap_field_write(player->clk_sel, ...); } Ensure initialization fails by forwarding the errors from regmap_field_alloc(), thus avoiding the use of the invalid pointers. Fixes: 76c2145ded6b ("ASoC: sti: Add CPU DAI driver for playback") Signed-off-by: Sander Vanheule Link: https://patch.msgid.link/20260220152634.480766-2-sander@svanheule.net Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sti/uniperif_player.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c index 6d1ce030963c6..f1b7e76f97b58 100644 --- a/sound/soc/sti/uniperif_player.c +++ b/sound/soc/sti/uniperif_player.c @@ -1029,7 +1029,12 @@ static int uni_player_parse_dt_audio_glue(struct platform_device *pdev, } player->clk_sel = regmap_field_alloc(regmap, regfield[0]); + if (IS_ERR(player->clk_sel)) + return PTR_ERR(player->clk_sel); + player->valid_sel = regmap_field_alloc(regmap, regfield[1]); + if (IS_ERR(player->valid_sel)) + return PTR_ERR(player->valid_sel); return 0; } From a3f3c332882c98ae7553af372191116d1384ca52 Mon Sep 17 00:00:00 2001 From: Sander Vanheule Date: Fri, 20 Feb 2026 16:26:34 +0100 Subject: [PATCH 0382/1518] ASoC: sti: use managed regmap_field allocations [ Upstream commit 1696fad8b259a2d46e51cd6e17e4bcdbe02279fa ] The regmap_field objects allocated at player init are never freed and may leak resources if the driver is removed. Switch to devm_regmap_field_alloc() to automatically limit the lifetime of the allocations the lifetime of the device. Fixes: 76c2145ded6b ("ASoC: sti: Add CPU DAI driver for playback") Signed-off-by: Sander Vanheule Link: https://patch.msgid.link/20260220152634.480766-3-sander@svanheule.net Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sti/uniperif_player.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c index f1b7e76f97b58..45d35b887e4eb 100644 --- a/sound/soc/sti/uniperif_player.c +++ b/sound/soc/sti/uniperif_player.c @@ -1028,11 +1028,11 @@ static int uni_player_parse_dt_audio_glue(struct platform_device *pdev, return PTR_ERR(regmap); } - player->clk_sel = regmap_field_alloc(regmap, regfield[0]); + player->clk_sel = devm_regmap_field_alloc(&pdev->dev, regmap, regfield[0]); if (IS_ERR(player->clk_sel)) return PTR_ERR(player->clk_sel); - player->valid_sel = regmap_field_alloc(regmap, regfield[1]); + player->valid_sel = devm_regmap_field_alloc(&pdev->dev, regmap, regfield[1]); if (IS_ERR(player->valid_sel)) return PTR_ERR(player->valid_sel); From 25dcc1989c194ba2b5fb6d03cbb9b83814ac0d15 Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:05 +0800 Subject: [PATCH 0383/1518] dm cache: fix null-deref with concurrent writes in passthrough mode [ Upstream commit 7d1f98d668ee34c1d15bdc0420fdd062f24a27c0 ] In passthrough mode, when dm-cache starts to invalidate a cache entry and bio prison cell lock fails due to concurrent write to the same cached block, mg->cell remains NULL. The error path in invalidate_complete() attempts to unlock and free the cell unconditionally, causing a NULL pointer dereference: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 0 UID: 0 PID: 134 Comm: fio Not tainted 6.19.0-rc7 #3 PREEMPT RIP: 0010:dm_cell_unlock_v2+0x3f/0x210 Call Trace: invalidate_complete+0xef/0x430 map_bio+0x130f/0x1a10 cache_map+0x320/0x6b0 __map_bio+0x458/0x510 dm_submit_bio+0x40e/0x16d0 __submit_bio+0x419/0x870 Reproduce steps: 1. Create a cache device dmsetup create cmeta --table "0 8192 linear /dev/sdc 0" dmsetup create cdata --table "0 131072 linear /dev/sdc 8192" dmsetup create corig --table "0 262144 linear /dev/sdc 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0" 2. Promote the first data block into cache fio --filename=/dev/mapper/cache --name=populate --rw=write --bs=4k \ --direct=1 --size=64k 3. Reload the cache into passthrough mode dmsetup suspend cache dmsetup reload cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" dmsetup resume cache 4. Write to the first cached block concurrently fio --filename=/dev/mapper/cache --name test --rw=randwrite --bs=4k \ --randrepeat=0 --direct=1 --numjobs=2 --size 64k Fix by checking if mg->cell is valid before attempting to unlock it. Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-target.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 7bad7cc87d370..1296965cf94cf 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1462,8 +1462,10 @@ static void invalidate_complete(struct dm_cache_migration *mg, bool success) struct cache *cache = mg->cache; bio_list_init(&bios); - if (dm_cell_unlock_v2(cache->prison, mg->cell, &bios)) - free_prison_cell(cache, mg->cell); + if (mg->cell) { + if (dm_cell_unlock_v2(cache->prison, mg->cell, &bios)) + free_prison_cell(cache, mg->cell); + } if (!success && mg->overwrite_bio) bio_io_error(mg->overwrite_bio); From 788ac6c94d04d966f903a91c64767013514945ff Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:06 +0800 Subject: [PATCH 0384/1518] dm cache: fix write path cache coherency in passthrough mode [ Upstream commit 0c5eef0aad508231d8e43ff8392692925e131b68 ] In passthrough mode, dm-cache defers write bio submission until cache invalidation completes to maintain existing coherency, requiring the target map function to return DM_MAPIO_SUBMITTED. The current map_bio() returns DM_MAPIO_REMAPPED, violating the required ordering constraint. Reproduce steps: 1. Create a cache device dmsetup create cmeta --table "0 8192 linear /dev/sdc 0" dmsetup create cdata --table "0 131072 linear /dev/sdc 8192" dmsetup create corig --table "0 262144 linear /dev/sdc 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0" 2. Promote the first data block into the cache fio --filename=/dev/mapper/cache --name=populate --rw=write --bs=4k \ --direct=1 --size=64k 3. Reload the cache into passthrough mode dmsetup suspend cache dmsetup reload cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" dmsetup resume cache 4. Write to the first data block, and check io ordering using ftrace echo 1 > /sys/kernel/debug/tracing/events/block/block_bio_queue/enable echo 1 > /sys/kernel/debug/tracing/events/block/block_bio_complete/enable echo 1 > /sys/kernel/debug/tracing/events/block/block_rq_complete/enable fio --filename=/dev/mapper/cache --name=test --rw=write --bs=64k \ --direct=1 --size 64k 5. ftrace logs show that write operations to the cache origin (252:2) and metadata operations (252:0) are unsynchronized: the origin write occurs before metadata commit. fio-146 [000] ..... 420.139562: block_bio_queue: 252,3 WS 0 + 128 [fio] fio-146 [000] ..... 420.149395: block_bio_queue: 252,2 WS 0 + 128 [fio] fio-146 [000] ..... 420.149763: block_bio_queue: 8,32 WS 262144 + 128 [fio] fio-146 [000] dNh1. 420.151446: block_rq_complete: 8,32 WS () 262144 + 128 be,0,4 [0] fio-146 [000] dNh1. 420.152731: block_bio_complete: 252,2 WS 0 + 128 [0] fio-146 [000] dNh1. 420.154229: block_bio_complete: 252,3 WS 0 + 128 [0] kworker/0:0-9 [000] ..... 420.160530: block_bio_queue: 252,0 W 408 + 8 [kworker/0:0] kworker/0:0-9 [000] ..... 420.161641: block_bio_queue: 8,32 W 408 + 8 [kworker/0:0] kworker/0:0-9 [000] ..... 420.162533: block_bio_queue: 252,0 W 416 + 8 [kworker/0:0] kworker/0:0-9 [000] ..... 420.162821: block_bio_queue: 8,32 W 416 + 8 [kworker/0:0] Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-target.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 1296965cf94cf..69fa2f6479318 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1703,6 +1703,7 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, bio_drop_shared_lock(cache, bio); atomic_inc(&cache->stats.demotion); invalidate_start(cache, cblock, block, bio); + return DM_MAPIO_SUBMITTED; } else remap_to_origin_clear_discard(cache, bio, block); } else { From b8ace9e96983abb20ccf39edce8a60f1bb0b83d8 Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:07 +0800 Subject: [PATCH 0385/1518] dm cache: fix write hang in passthrough mode [ Upstream commit 4ca8b8bd952df7c3ccdc68af9bd3419d0839a04b ] The invalidate_remove() function has incomplete logic for handling write hit bios after cache invalidation. It sets up the remapping for the overwrite_bio but then drops it immediately without submission, causing write operations to hang. Fix by adding a new invalidate_committed() continuation that submits the remapped writes to the cache origin after metadata commit completes, while using the overwrite_endio hook to ensure proper completion sequencing. This maintains existing coherency. Also improve error handling in invalidate_complete() to preserve the original error status instead of using bio_io_error() unconditionally. Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-target.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 69fa2f6479318..b191ea1361b40 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1467,8 +1467,14 @@ static void invalidate_complete(struct dm_cache_migration *mg, bool success) free_prison_cell(cache, mg->cell); } - if (!success && mg->overwrite_bio) - bio_io_error(mg->overwrite_bio); + if (mg->overwrite_bio) { + // Set generic error if the bio hasn't been issued yet, + // e.g., invalidation or metadata commit failed before bio + // submission. Otherwise preserve the bio's own error status. + if (!success && !mg->overwrite_bio->bi_status) + mg->overwrite_bio->bi_status = BLK_STS_IOERR; + bio_endio(mg->overwrite_bio); + } free_migration(mg); defer_bios(cache, &bios); @@ -1508,6 +1514,22 @@ static int invalidate_cblock(struct cache *cache, dm_cblock_t cblock) return r; } +static void invalidate_committed(struct work_struct *ws) +{ + struct dm_cache_migration *mg = ws_to_mg(ws); + struct cache *cache = mg->cache; + struct bio *bio = mg->overwrite_bio; + struct per_bio_data *pb = get_per_bio_data(bio); + + if (mg->k.input) + invalidate_complete(mg, false); + + init_continuation(&mg->k, invalidate_completed); + remap_to_origin_clear_discard(cache, bio, mg->invalidate_oblock); + dm_hook_bio(&pb->hook_info, bio, overwrite_endio, mg); + dm_submit_bio_remap(bio, NULL); +} + static void invalidate_remove(struct work_struct *ws) { int r; @@ -1520,10 +1542,8 @@ static void invalidate_remove(struct work_struct *ws) return; } - init_continuation(&mg->k, invalidate_completed); + init_continuation(&mg->k, invalidate_committed); continue_after_commit(&cache->committer, &mg->k); - remap_to_origin_clear_discard(cache, mg->overwrite_bio, mg->invalidate_oblock); - mg->overwrite_bio = NULL; schedule_commit(&cache->committer); } From c348ae47d8e65f06429fa41adce9ad986b696766 Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:08 +0800 Subject: [PATCH 0386/1518] dm cache policy smq: fix missing locks in invalidating cache blocks [ Upstream commit 2d1f7b65f5deedd2e6b09fdc6ea27f8375f24b45 ] In passthrough mode, the policy invalidate_mapping operation is called simultaneously from multiple workers, thus it should be protected by a lock. Otherwise, we might end up with data races on the allocated blocks counter, or even use-after-free issues with internal data structures when doing concurrent writes. Note that the existing FIXME in smq_invalidate_mapping() doesn't affect passthrough mode since migration tasks don't exist there, but would need attention if supporting fast device shrinking via suspend/resume without target reloading. Reproduce steps: 1. Create a cache device consisting of 1024 cache entries dmsetup create cmeta --table "0 8192 linear /dev/sdc 0" dmsetup create cdata --table "0 131072 linear /dev/sdc 8192" dmsetup create corig --table "0 262144 linear /dev/sdc 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0" 2. Populate the cache, and record the number of cached blocks fio --name=populate --filename=/dev/mapper/cache --rw=randwrite --bs=4k \ --size=64m --direct=1 nr_cached=$(dmsetup status cache | awk '{split($7, a, "/"); print a[1]}') 3. Reload the cache into passthrough mode dmsetup suspend cache dmsetup reload cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" dmsetup resume cache 4. Write to the passthrough cache. By setting multiple jobs with I/O size equal to the cache block size, cache blocks are invalidated concurrently from different workers. fio --filename=/dev/mapper/cache --name=test --rw=randwrite --bs=64k \ --direct=1 --numjobs=2 --randrepeat=0 --size=64m 5. Check if demoted matches cached block count. These numbers should match but may differ due to the data race. nr_demoted=$(dmsetup status cache | awk '{print $12}') echo "$nr_cached, $nr_demoted" Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-policy-smq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index 7e1e8cc0e33a3..76a35cce85028 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1589,14 +1589,18 @@ static int smq_invalidate_mapping(struct dm_cache_policy *p, dm_cblock_t cblock) { struct smq_policy *mq = to_smq_policy(p); struct entry *e = get_entry(&mq->cache_alloc, from_cblock(cblock)); + unsigned long flags; if (!e->allocated) return -ENODATA; + spin_lock_irqsave(&mq->lock, flags); // FIXME: what if this block has pending background work? del_queue(mq, e); h_remove(&mq->table, e); free_entry(&mq->cache_alloc, e); + spin_unlock_irqrestore(&mq->lock, flags); + return 0; } From cb8b250b427782b1ec16dd5b2201dcf139ee9512 Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:09 +0800 Subject: [PATCH 0387/1518] dm cache: fix concurrent write failure in passthrough mode [ Upstream commit e4f66341779d0cf4c83c74793753a84094286d9e ] When bio prison cell lock acquisition fails due to concurrent writes to the same block in passthrough mode, dm-cache incorrectly returns an I/O error instead of properly handling the concurrency. This can occur in both process and workqueue contexts when invalidate_lock() is called for exclusive access to a data block. Fix this by deferring the write bios to ensure proper block device behavior. Reproduce steps: 1. Create a cache device dmsetup create cmeta --table "0 8192 linear /dev/sdc 0" dmsetup create cdata --table "0 131072 linear /dev/sdc 8192" dmsetup create corig --table "0 262144 linear /dev/sdc 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0" 2. Promote the first data block into cache fio --filename=/dev/mapper/cache --name=populate --rw=write --bs=4k \ --direct=1 --size=64k 3. Reload the cache into passthrough mode dmsetup suspend cache dmsetup reload cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" dmsetup resume cache 4. Write to the first cached block concurrently. Sometimes one of the processes will receive I/O errors. fio --filename=/dev/mapper/cache --name test --rw=randwrite --bs=4k \ --randrepeat=0 --direct=1 --numjobs=2 --size 64k fio-3.41 fio: io_u error on file /dev/mapper/cache: Input/output error: write offset=4096, buflen=4096 fio: pid=106, err=5/file:io_u.c:2008, func=io_u error, error=Input/output error test: (groupid=0, jobs=1): err= 0: pid=105 test: (groupid=0, jobs=1): err= 5 (file:io_u.c:2008, func=io_u error, error=Input/output error): pid=106 Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-target.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index b191ea1361b40..e8709950dc49d 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1561,6 +1561,15 @@ static int invalidate_lock(struct dm_cache_migration *mg) READ_WRITE_LOCK_LEVEL, prealloc, &mg->cell); if (r < 0) { free_prison_cell(cache, prealloc); + + /* Defer the bio for retrying the cell lock */ + if (mg->overwrite_bio) { + struct bio *bio = mg->overwrite_bio; + + mg->overwrite_bio = NULL; + defer_bio(cache, bio); + } + invalidate_complete(mg, false); return r; } From 21c503d60a257e54ca3ac58e2721bd24501d5bde Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:10 +0800 Subject: [PATCH 0388/1518] dm cache: fix dirty mapping checking in passthrough mode switching [ Upstream commit 322586745bd1a0e5f3559fd1635fdeb4dbd1d6b8 ] As mentioned in commit 9b1cc9f251af ("dm cache: share cache-metadata object across inactive and active DM tables"), dm-cache assumed table reload occurs after suspension, while LVM's table preload breaks this assumption. The dirty mapping check for passthrough mode was designed around this assumption and is performed during table creation, causing the check to fail with preload while metadata updates are ongoing. This risks loading dirty mappings into passthrough mode, resulting in data loss. Reproduce steps: 1. Create a writeback cache with zero migration_threshold to produce dirty mappings dmsetup create cmeta --table "0 8192 linear /dev/sdc 0" dmsetup create cdata --table "0 131072 linear /dev/sdc 8192" dmsetup create corig --table "0 262144 linear /dev/sdc 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writeback smq \ 2 migration_threshold 0" 2. Preload a table in passthrough mode dmsetup reload cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" 3. Write to the first cache block to make it dirty fio --filename=/dev/mapper/cache --name=populate --rw=write --bs=4k \ --direct=1 --size=64k 4. Resume the inactive table. Now it's possible to load the dirty block into passthrough mode. dmsetup resume cache Fix by moving the checks to the preresume phase to support table preloading. Also remove the unused function dm_cache_metadata_all_clean. Fixes: 2ee57d587357 ("dm cache: add passthrough mode") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-metadata.c | 11 ----------- drivers/md/dm-cache-metadata.h | 5 ----- drivers/md/dm-cache-target.c | 25 ++++++++----------------- 3 files changed, 8 insertions(+), 33 deletions(-) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index a9a1ab284076a..cf491c8508a42 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1714,17 +1714,6 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy * return r; } -int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result) -{ - int r; - - READ_LOCK(cmd); - r = blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result); - READ_UNLOCK(cmd); - - return r; -} - void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd) { WRITE_LOCK_VOID(cmd); diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h index 5f77890207fed..2f107e7c67d0a 100644 --- a/drivers/md/dm-cache-metadata.h +++ b/drivers/md/dm-cache-metadata.h @@ -135,11 +135,6 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd, */ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p); -/* - * Query method. Are all the blocks in the cache clean? - */ -int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result); - int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result); int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd); void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index e8709950dc49d..9c64fe56ecb6c 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2506,23 +2506,8 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - if (passthrough_mode(cache)) { - bool all_clean; - - r = dm_cache_metadata_all_clean(cache->cmd, &all_clean); - if (r) { - *error = "dm_cache_metadata_all_clean() failed"; - goto bad; - } - - if (!all_clean) { - *error = "Cannot enter passthrough mode unless all blocks are clean"; - r = -EINVAL; - goto bad; - } - + if (passthrough_mode(cache)) policy_allow_migrations(cache->policy, false); - } spin_lock_init(&cache->lock); bio_list_init(&cache->deferred_bios); @@ -2849,6 +2834,12 @@ static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock, struct cache *cache = context; if (dirty) { + if (passthrough_mode(cache)) { + DMERR("%s: cannot enter passthrough mode unless all blocks are clean", + cache_device_name(cache)); + return -EBUSY; + } + set_bit(from_cblock(cblock), cache->dirty_bitset); atomic_inc(&cache->nr_dirty); } else @@ -3082,7 +3073,7 @@ static int cache_preresume(struct dm_target *ti) load_filtered_mapping, cache); if (r) { DMERR("%s: could not load cache mappings", cache_device_name(cache)); - if (r != -EFBIG) + if (r != -EFBIG && r != -EBUSY) metadata_operation_failed(cache, "dm_cache_load_mappings", r); return r; } From 7f3e53990ad3bf3a09107d368bfbf956c70fe058 Mon Sep 17 00:00:00 2001 From: Benjamin Marzinski Date: Thu, 12 Feb 2026 13:05:41 -0500 Subject: [PATCH 0389/1518] dm-mpath: don't stop probing paths at presuspend [ Upstream commit 51d81e14fe6788dc6463064c7517480f2acd2724 ] Commit 5c977f102315 ("dm-mpath: Don't grab work_mutex while probing paths"), added code to make multipath quit probing paths early, if it was trying to suspend. This isn't necessary. It was just an optimization to try to keep path probing from delaying a suspend. However it causes problems with the intended user of this code, qemu. The path probing code was added because failed ioctls to multipath devices don't cause paths to fail in cases where a regular IO failure would. If an ioctl to a path failed because the path was down, and the multipath device had passed presuspend, the M_MPATH_PROBE_PATHS ioctl would exit early, without probing the path. The caller would then retry the original ioctl, hoping to use a different path. But if there was only one path in the pathgroup, it would pick the same non-working path again, even if there were working paths in other pathgroups. ioctls to a suspended dm device will return -EAGAIN, notifying the caller that the device is suspended, but ioctls to a device that is just preparing to suspend won't (and in general, shouldn't). This means that the caller (qemu in this case) would get into a tight loop where it would issue an ioctl that failed, skip probing the paths because the device had already passed presuspend, and start over issuing the ioctl again. This would continue until the multipath device finally fully suspended, or the caller gave up and failed the ioctl. multipath's path probing code could return -EAGAIN in this case, and the caller could delay a bit before retrying, but the whole purpose of skipping the probe after presuspend was to speed things up, and that would just slow them down. Instead, remove the is_suspending flag, and check dm_suspended() instead to decide whether to exit the probing code early. This means that when the probing code exits early, future ioctls will also be delayed, because the device is fully suspended. Fixes: 5c977f102315 ("dm-mpath: Don't grab work_mutex while probing paths") Signed-off-by: Benjamin Marzinski Reviewed-by: Martin Wilck Reviewed-by: Hanna Czenczek Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-mpath.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 00df5be165759..3a25ec2993dc2 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -102,7 +102,6 @@ struct multipath { struct bio_list queued_bios; struct timer_list nopath_timer; /* Timeout for queue_if_no_path */ - bool is_suspending; }; /* @@ -1748,9 +1747,6 @@ static void multipath_presuspend(struct dm_target *ti) { struct multipath *m = ti->private; - spin_lock_irq(&m->lock); - m->is_suspending = true; - spin_unlock_irq(&m->lock); /* FIXME: bio-based shouldn't need to always disable queue_if_no_path */ if (m->queue_mode == DM_TYPE_BIO_BASED || !dm_noflush_suspending(m->ti)) queue_if_no_path(m, false, true, __func__); @@ -1773,7 +1769,6 @@ static void multipath_resume(struct dm_target *ti) struct multipath *m = ti->private; spin_lock_irq(&m->lock); - m->is_suspending = false; if (test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) { set_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags); clear_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags); @@ -2100,7 +2095,7 @@ static int probe_active_paths(struct multipath *m) if (m->current_pg == m->last_probed_pg) goto skip_probe; } - if (!m->current_pg || m->is_suspending || + if (!m->current_pg || dm_suspended(m->ti) || test_bit(MPATHF_QUEUE_IO, &m->flags)) goto skip_probe; set_bit(MPATHF_DELAY_PG_SWITCH, &m->flags); @@ -2109,7 +2104,7 @@ static int probe_active_paths(struct multipath *m) list_for_each_entry(pgpath, &pg->pgpaths, list) { if (pg != READ_ONCE(m->current_pg) || - READ_ONCE(m->is_suspending)) + dm_suspended(m->ti)) goto out; if (!pgpath->is_active) continue; From b7ed10f2d8b538e0a81ca840f826fd4b8774f126 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 5 Mar 2026 20:47:03 +0100 Subject: [PATCH 0390/1518] platform/chrome: chromeos_tbmc: Drop wakeup source on remove [ Upstream commit 5d441a4bc93642ed6f41da87327a39946b4e1455 ] The wakeup source added by device_init_wakeup() in chromeos_tbmc_add() needs to be dropped during driver removal, so add a .remove() callback to the driver for this purpose. Fixes: 0144c00ed86b ("platform/chrome: chromeos_tbmc: Report wake events") Signed-off-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/6151957.MhkbZ0Pkbq@rafael.j.wysocki Signed-off-by: Tzung-Bi Shih Signed-off-by: Sasha Levin --- drivers/platform/chrome/chromeos_tbmc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/platform/chrome/chromeos_tbmc.c b/drivers/platform/chrome/chromeos_tbmc.c index d1cf8f3463ce3..e248567c0a182 100644 --- a/drivers/platform/chrome/chromeos_tbmc.c +++ b/drivers/platform/chrome/chromeos_tbmc.c @@ -95,6 +95,11 @@ static int chromeos_tbmc_add(struct acpi_device *adev) return 0; } +static void chromeos_tbmc_remove(struct acpi_device *adev) +{ + device_init_wakeup(&adev->dev, false); +} + static const struct acpi_device_id chromeos_tbmc_acpi_device_ids[] = { { ACPI_DRV_NAME, 0 }, { } @@ -110,6 +115,7 @@ static struct acpi_driver chromeos_tbmc_driver = { .ids = chromeos_tbmc_acpi_device_ids, .ops = { .add = chromeos_tbmc_add, + .remove = chromeos_tbmc_remove, .notify = chromeos_tbmc_notify, }, .drv.pm = &chromeos_tbmc_pm_ops, From a763a53d648def463e08b418f3d3609403b4f6ce Mon Sep 17 00:00:00 2001 From: Aksh Garg Date: Tue, 24 Feb 2026 14:08:16 +0530 Subject: [PATCH 0391/1518] PCI: dwc: ep: Fix MSI-X Table Size configuration in dw_pcie_ep_set_msix() [ Upstream commit 271d0b1f058ae9815e75233d04b23e3558c3e4f4 ] In dw_pcie_ep_set_msix(), while updating the MSI-X Table Size value for individual functions, Message Control register is read from the passed function number register space using dw_pcie_ep_readw_dbi(), but always written back to the Function 0's register space using dw_pcie_writew_dbi(). This causes incorrect MSI-X configuration for the rest of the functions, other than Function 0. Fix this by using dw_pcie_ep_writew_dbi() to write to the correct function's register space, matching the read operation. Fixes: 70fa02ca1446 ("PCI: dwc: Add dw_pcie_ep_{read,write}_dbi[2] helpers") Signed-off-by: Aksh Garg [mani: commit log] Signed-off-by: Manivannan Sadhasivam Reviewed-by: Niklas Cassel Link: https://patch.msgid.link/20260224083817.916782-2-a-garg7@ti.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-designware-ep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index e2e18beb2951d..7350a703c4d19 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -538,7 +538,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, val = dw_pcie_ep_readw_dbi(ep, func_no, reg); val &= ~PCI_MSIX_FLAGS_QSIZE; val |= nr_irqs - 1; /* encoded as N-1 */ - dw_pcie_writew_dbi(pci, reg, val); + dw_pcie_ep_writew_dbi(ep, func_no, reg, val); reg = ep_func->msix_cap + PCI_MSIX_TABLE; val = offset | bir; From 104a6e53484e565f06b29e32aa32415f1facc80a Mon Sep 17 00:00:00 2001 From: Richard Zhu Date: Wed, 15 Oct 2025 11:04:25 +0800 Subject: [PATCH 0392/1518] PCI: dwc: Invoke post_init in dw_pcie_resume_noirq() [ Upstream commit c577ce2881f9c76892de5ffc1a122e3ef427ecee ] In some SoCs like i.MX95, CLKREQ# is pulled low by the controller driver before link up. After link up, if the 'supports-clkreq' property is specified in DT, the driver will release CLKREQ# so that it can go high and the endpoint can pull it low whenever required i.e., during exit from L1 Substates. Hence, at the end of dw_pcie_resume_noirq(), invoke the '.post_init()' callback if exists to perform the above mentioned action. Signed-off-by: Richard Zhu [mani: reworded description] Signed-off-by: Manivannan Sadhasivam Reviewed-by: Frank Li Link: https://patch.msgid.link/20251015030428.2980427-9-hongxing.zhu@nxp.com Stable-dep-of: edb5ca3262e2 ("PCI: dwc: Perform cleanup in the error path of dw_pcie_resume_noirq()") Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-designware-host.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 894bf23529df5..3fbece96faaad 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -1236,6 +1236,9 @@ int dw_pcie_resume_noirq(struct dw_pcie *pci) if (ret) return ret; + if (pci->pp.ops->post_init) + pci->pp.ops->post_init(&pci->pp); + return ret; } EXPORT_SYMBOL_GPL(dw_pcie_resume_noirq); From a3c61bd4e9438a7928bf111c33c2a41cb7d3bce3 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 26 Feb 2026 19:09:51 +0530 Subject: [PATCH 0393/1518] PCI: dwc: Perform cleanup in the error path of dw_pcie_resume_noirq() [ Upstream commit edb5ca3262e2255cf938a5948709d3472d4871ad ] If the dw_pcie_resume_noirq() API fails, it just returns the errno without doing cleanup in the error path, leading to resource leak. So perform cleanup in the error path. Fixes: 4774faf854f5 ("PCI: dwc: Implement generic suspend/resume functionality") Reported-by: Senchuan Zhang Closes: https://lore.kernel.org/linux-pci/78296255.3869.19c8eb694d6.Coremail.zhangsenchuan@eswincomputing.com Signed-off-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://patch.msgid.link/20260226133951.296743-1-mani@kernel.org Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-designware-host.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 3fbece96faaad..48e4a887bb1bb 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -1230,15 +1230,24 @@ int dw_pcie_resume_noirq(struct dw_pcie *pci) ret = dw_pcie_start_link(pci); if (ret) - return ret; + goto err_deinit; ret = dw_pcie_wait_for_link(pci); - if (ret) - return ret; + if (ret == -ETIMEDOUT) + goto err_stop_link; if (pci->pp.ops->post_init) pci->pp.ops->post_init(&pci->pp); + return 0; + +err_stop_link: + dw_pcie_stop_link(pci); + +err_deinit: + if (pci->pp.ops->deinit) + pci->pp.ops->deinit(&pci->pp); + return ret; } EXPORT_SYMBOL_GPL(dw_pcie_resume_noirq); From 322a3b70368d49e39591fe9fc6c07d262128b05f Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Wed, 4 Mar 2026 19:56:28 +0800 Subject: [PATCH 0394/1518] dm cache metadata: fix memory leak on metadata abort retry [ Upstream commit 044ca491d4086dc5bf233e9fcb71db52df32f633 ] When failing to acquire the root_lock in dm_cache_metadata_abort because the block_manager is read-only, the temporary block_manager created outside the root_lock is not properly released, causing a memory leak. Reproduce steps: This can be reproduced by reloading a new table while the metadata is read-only. While the second call to dm_cache_metadata_abort is caused by lack of support for table preload in dm-cache, mentioned in commit 9b1cc9f251af ("dm cache: share cache-metadata object across inactive and active DM tables"), it exposes the memory leak in dm_cache_metadata_abort when the function is called multiple times. Specifically, dm-cache fails to sync the new cache object's mode during preresume, creating the reproducer condition. This issue could also occur through concurrent metadata_operation_failed calls due to races in cache mode updates, but the table preload scenario below provides a reliable reproducer. 1. Create a cache device with some faulty trailing metadata blocks dmsetup create cmeta < unreferenced object 0xffff8880080c2010 (size 16): comm "dmsetup", pid 132, jiffies 4294982580 hex dump (first 16 bytes): 00 38 b9 07 80 88 ff ff 6a 6b 6b 6b 6b 6b 6b a5 ... backtrace (crc 3118f31c): kmemleak_alloc+0x28/0x40 __kmalloc_cache_noprof+0x3d9/0x510 dm_block_manager_create+0x51/0x140 dm_cache_metadata_abort+0x85/0x320 metadata_operation_failed+0x103/0x1e0 cache_preresume+0xacd/0xe70 dm_table_resume_targets+0xd3/0x320 __dm_resume+0x1b/0xf0 dm_resume+0x127/0x170 Fixes: 352b837a5541 ("dm cache: Fix ABBA deadlock between shrink_slab and dm_cache_metadata_abort") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-metadata.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index cf491c8508a42..db77ba58f64ac 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1023,6 +1023,12 @@ static bool cmd_write_lock(struct dm_cache_metadata *cmd) return; \ } while (0) +#define WRITE_LOCK_OR_GOTO(cmd, label) \ + do { \ + if (!cmd_write_lock((cmd))) \ + goto label; \ + } while (0) + #define WRITE_UNLOCK(cmd) \ up_write(&(cmd)->root_lock) @@ -1780,11 +1786,8 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, CACHE_MAX_CONCURRENT_LOCKS); - WRITE_LOCK(cmd); - if (cmd->fail_io) { - WRITE_UNLOCK(cmd); - goto out; - } + /* cmd_write_lock() already checks fail_io with cmd->root_lock held */ + WRITE_LOCK_OR_GOTO(cmd, out); __destroy_persistent_data_objects(cmd, false); old_bm = cmd->bm; From b455903eed4558982be0811f5b7f44f6bbc4ff57 Mon Sep 17 00:00:00 2001 From: Junrui Luo Date: Thu, 5 Mar 2026 20:05:48 +0800 Subject: [PATCH 0395/1518] dm log: fix out-of-bounds write due to region_count overflow [ Upstream commit c20e36b7631d83e7535877f08af8b0af72c44b1a ] The local variable region_count in create_log_context() is declared as unsigned int (32-bit), but dm_sector_div_up() returns sector_t (64-bit). When a device-mapper target has a sufficiently large ti->len with a small region_size, the division result can exceed UINT_MAX. The truncated value is then used to calculate bitset_size, causing clean_bits, sync_bits, and recovering_bits to be allocated far smaller than needed for the actual number of regions. Subsequent log operations (log_set_bit, log_clear_bit, log_test_bit) use region indices derived from the full untruncated region space, causing out-of-bounds writes to kernel heap memory allocated by vmalloc. This can be reproduced by creating a mirror target whose region_count overflows 32 bits: dmsetup create bigzero --table '0 8589934594 zero' dmsetup create mymirror --table '0 8589934594 mirror \ core 2 2 nosync 2 /dev/mapper/bigzero 0 \ /dev/mapper/bigzero 0' The status output confirms the truncation (sync_count=1 instead of 4294967297, because 0x100000001 was truncated to 1): $ dmsetup status mymirror 0 8589934594 mirror 2 254:1 254:1 1/4294967297 ... This leads to a kernel crash in core_in_sync: BUG: scheduling while atomic: (udev-worker)/9150/0x00000000 RIP: 0010:core_in_sync+0x14/0x30 [dm_log] CR2: 0000000000000008 Fixing recursive fault but reboot is needed! Fix by widening the local region_count to sector_t and adding an explicit overflow check before the value is assigned to lc->region_count. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Yuhao Jiang Signed-off-by: Junrui Luo Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-log.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index bced5a783ee33..4a1369b8f44a0 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -373,7 +373,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti, struct log_c *lc; uint32_t region_size; - unsigned int region_count; + sector_t region_count; size_t bitset_size, buf_size; int r; char dummy; @@ -401,6 +401,10 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti, } region_count = dm_sector_div_up(ti->len, region_size); + if (region_count > UINT_MAX) { + DMWARN("region count exceeds limit of %u", UINT_MAX); + return -EINVAL; + } lc = kmalloc(sizeof(*lc), GFP_KERNEL); if (!lc) { From 3149c4f7f26fe2b1373e630758844111969730d5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 6 Mar 2026 14:10:32 -0800 Subject: [PATCH 0396/1518] iopoll: fix function parameter names in read_poll_timeout_atomic() [ Upstream commit 878004e2852bc22ce0687c5597d6fe3909fb59f3 ] Correct the function parameter names to avoid kernel-doc warnings and to emphasize this function is atomic (non-sleeping). Warning: include/linux/iopoll.h:169 function parameter 'sleep_us' not described in 'read_poll_timeout_atomic' Warning: ../include/linux/iopoll.h:169 function parameter 'sleep_before_read' not described in 'read_poll_timeout_atomic' Fixes: 9df8043a546d ("iopoll: Generalize read_poll_timeout() into poll_timeout_us()") Signed-off-by: Randy Dunlap Reviewed-by: Jani Nikula Link: https://patch.msgid.link/20260306221033.2357305-1-rdunlap@infradead.org Signed-off-by: Jani Nikula Signed-off-by: Sasha Levin --- include/linux/iopoll.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index bdd2e0652bc30..53edd69acb9bd 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -159,7 +159,7 @@ * * This macro does not rely on timekeeping. Hence it is safe to call even when * timekeeping is suspended, at the expense of an underestimation of wall clock - * time, which is rather minimal with a non-zero delay_us. + * time, which is rather minimal with a non-zero @delay_us. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. @@ -167,9 +167,9 @@ * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. */ -#define read_poll_timeout_atomic(op, val, cond, sleep_us, timeout_us, \ - sleep_before_read, args...) \ - poll_timeout_us_atomic((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read) +#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ + delay_before_read, args...) \ + poll_timeout_us_atomic((val) = op(args), cond, delay_us, timeout_us, delay_before_read) /** * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs From cf2ac2cac8b319f89b3a3851ca0c5ffb6a549575 Mon Sep 17 00:00:00 2001 From: Jayesh Choudhary Date: Tue, 9 Dec 2025 17:33:27 +0530 Subject: [PATCH 0397/1518] drm/bridge: cadence: cdns-mhdp8546-core: Set the mhdp connector earlier in atomic_enable() [ Upstream commit 43d6508ddbf9fb974fbc359a033154f78c9d4c8b ] In case if we get errors in cdns_mhdp_link_up() or cdns_mhdp_reg_read() in atomic_enable, we will go to cdns_mhdp_modeset_retry_fn() and will hit NULL pointer while trying to access the mutex. We need the connector to be set before that. Unlike in legacy cases with flag !DRM_BRIDGE_ATTACH_NO_CONNECTOR, we do not have connector initialised in bridge_attach(), so add the mhdp->connector_ptr in device structure to handle both cases with DRM_BRIDGE_ATTACH_NO_CONNECTOR and !DRM_BRIDGE_ATTACH_NO_CONNECTOR, set it in atomic_enable() earlier to avoid possible NULL pointer dereference in recovery paths like modeset_retry_fn() with the DRM_BRIDGE_ATTACH_NO_CONNECTOR flag set. Fixes: c932ced6b585 ("drm/tidss: Update encoder/bridge chain connect model") Signed-off-by: Jayesh Choudhary Signed-off-by: Harikrishna Shenoy Reviewed-by: Luca Ceresoli Reviewed-by: Tomi Valkeinen Link: https://patch.msgid.link/20251209120332.3559893-2-h-shenoy@ti.com Signed-off-by: Luca Ceresoli Signed-off-by: Sasha Levin --- .../drm/bridge/cadence/cdns-mhdp8546-core.c | 29 ++++++++++--------- .../drm/bridge/cadence/cdns-mhdp8546-core.h | 1 + .../drm/bridge/cadence/cdns-mhdp8546-hdcp.c | 18 +++++++++--- 3 files changed, 30 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index 38726ae1bf150..ef2d0ea606f78 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -740,7 +740,7 @@ static void cdns_mhdp_fw_cb(const struct firmware *fw, void *context) bridge_attached = mhdp->bridge_attached; spin_unlock(&mhdp->start_lock); if (bridge_attached) { - if (mhdp->connector.dev) + if (mhdp->connector_ptr) drm_kms_helper_hotplug_event(mhdp->bridge.dev); else drm_bridge_hpd_notify(&mhdp->bridge, cdns_mhdp_detect(mhdp)); @@ -1636,6 +1636,7 @@ static int cdns_mhdp_connector_init(struct cdns_mhdp_device *mhdp) return ret; } + mhdp->connector_ptr = conn; drm_connector_helper_add(conn, &cdns_mhdp_conn_helper_funcs); ret = drm_display_info_set_bus_formats(&conn->display_info, @@ -1915,17 +1916,25 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); struct cdns_mhdp_bridge_state *mhdp_state; struct drm_crtc_state *crtc_state; - struct drm_connector *connector; struct drm_connector_state *conn_state; struct drm_bridge_state *new_state; const struct drm_display_mode *mode; u32 resp; - int ret; + int ret = 0; dev_dbg(mhdp->dev, "bridge enable\n"); mutex_lock(&mhdp->link_mutex); + mhdp->connector_ptr = drm_atomic_get_new_connector_for_encoder(state, + bridge->encoder); + if (WARN_ON(!mhdp->connector_ptr)) + goto out; + + conn_state = drm_atomic_get_new_connector_state(state, mhdp->connector_ptr); + if (WARN_ON(!conn_state)) + goto out; + if (mhdp->plugged && !mhdp->link_up) { ret = cdns_mhdp_link_up(mhdp); if (ret < 0) @@ -1945,15 +1954,6 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, cdns_mhdp_reg_write(mhdp, CDNS_DPTX_CAR, resp | CDNS_VIF_CLK_EN | CDNS_VIF_CLK_RSTN); - connector = drm_atomic_get_new_connector_for_encoder(state, - bridge->encoder); - if (WARN_ON(!connector)) - goto out; - - conn_state = drm_atomic_get_new_connector_state(state, connector); - if (WARN_ON(!conn_state)) - goto out; - if (mhdp->hdcp_supported && mhdp->hw_state == MHDP_HW_READY && conn_state->content_protection == @@ -2030,6 +2030,7 @@ static void cdns_mhdp_atomic_disable(struct drm_bridge *bridge, if (mhdp->info && mhdp->info->ops && mhdp->info->ops->disable) mhdp->info->ops->disable(mhdp); + mhdp->connector_ptr = NULL; mutex_unlock(&mhdp->link_mutex); } @@ -2296,7 +2297,7 @@ static void cdns_mhdp_modeset_retry_fn(struct work_struct *work) mhdp = container_of(work, typeof(*mhdp), modeset_retry_work); - conn = &mhdp->connector; + conn = mhdp->connector_ptr; /* Grab the locks before changing connector property */ mutex_lock(&conn->dev->mode_config.mutex); @@ -2373,7 +2374,7 @@ static void cdns_mhdp_hpd_work(struct work_struct *work) int ret; ret = cdns_mhdp_update_link_status(mhdp); - if (mhdp->connector.dev) { + if (mhdp->connector_ptr) { if (ret < 0) schedule_work(&mhdp->modeset_retry_work); else diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h index bad2fc0c73066..a76775c768956 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h @@ -376,6 +376,7 @@ struct cdns_mhdp_device { struct mutex link_mutex; struct drm_connector connector; + struct drm_connector *connector_ptr; struct drm_bridge bridge; struct cdns_mhdp_link link; diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c index 42248f179b69d..21a7d2fb266e4 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c @@ -394,7 +394,7 @@ static int _cdns_mhdp_hdcp_disable(struct cdns_mhdp_device *mhdp) int ret; dev_dbg(mhdp->dev, "[%s:%d] HDCP is being disabled...\n", - mhdp->connector.name, mhdp->connector.base.id); + mhdp->connector_ptr->name, mhdp->connector_ptr->base.id); ret = cdns_mhdp_hdcp_set_config(mhdp, 0, false); @@ -436,6 +436,10 @@ static int cdns_mhdp_hdcp_check_link(struct cdns_mhdp_device *mhdp) int ret = 0; mutex_lock(&mhdp->hdcp.mutex); + + if (!mhdp->connector_ptr) + goto out; + if (mhdp->hdcp.value == DRM_MODE_CONTENT_PROTECTION_UNDESIRED) goto out; @@ -445,7 +449,7 @@ static int cdns_mhdp_hdcp_check_link(struct cdns_mhdp_device *mhdp) dev_err(mhdp->dev, "[%s:%d] HDCP link failed, retrying authentication\n", - mhdp->connector.name, mhdp->connector.base.id); + mhdp->connector_ptr->name, mhdp->connector_ptr->base.id); ret = _cdns_mhdp_hdcp_disable(mhdp); if (ret) { @@ -487,13 +491,19 @@ static void cdns_mhdp_hdcp_prop_work(struct work_struct *work) struct cdns_mhdp_device *mhdp = container_of(hdcp, struct cdns_mhdp_device, hdcp); - struct drm_device *dev = mhdp->connector.dev; + struct drm_device *dev = NULL; struct drm_connector_state *state; + if (mhdp->connector_ptr) + dev = mhdp->connector_ptr->dev; + + if (!dev) + return; + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); mutex_lock(&mhdp->hdcp.mutex); if (mhdp->hdcp.value != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { - state = mhdp->connector.state; + state = mhdp->connector_ptr->state; state->content_protection = mhdp->hdcp.value; } mutex_unlock(&mhdp->hdcp.mutex); From 1a9bef10f894b088cb488517bdfcd539ffa00098 Mon Sep 17 00:00:00 2001 From: Jayesh Choudhary Date: Tue, 9 Dec 2025 17:33:28 +0530 Subject: [PATCH 0398/1518] drm/bridge: cadence: cdns-mhdp8546-core: Add mode_valid hook to drm_bridge_funcs [ Upstream commit 6dbff34016052b099558b76632e4983e2df13fed ] Add cdns_mhdp_bridge_mode_valid() to check if specific mode is valid for this bridge or not. In the legacy usecase with !DRM_BRIDGE_ATTACH_NO_CONNECTOR we were using the hook from drm_connector_helper_funcs but with DRM_BRIDGE_ATTACH_NO_CONNECTOR we need to have mode_valid() in drm_bridge_funcs. Without this patch, when using DRM_BRIDGE_ATTACH_NO_CONNECTOR flag, the cdns_mhdp_bandwidth_ok() function would not be called during mode validation, potentially allowing modes that exceed the bridge's bandwidth capabilities to be incorrectly marked as valid. Fixes: c932ced6b585 ("drm/tidss: Update encoder/bridge chain connect model") Reviewed-by: Tomi Valkeinen Signed-off-by: Jayesh Choudhary Signed-off-by: Harikrishna Shenoy Reviewed-by: Luca Ceresoli Link: https://patch.msgid.link/20251209120332.3559893-3-h-shenoy@ti.com Signed-off-by: Luca Ceresoli Signed-off-by: Sasha Levin --- .../drm/bridge/cadence/cdns-mhdp8546-core.c | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index ef2d0ea606f78..2fb8acd363b14 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -2162,6 +2162,25 @@ static const struct drm_edid *cdns_mhdp_bridge_edid_read(struct drm_bridge *brid return cdns_mhdp_edid_read(mhdp, connector); } +static enum drm_mode_status +cdns_mhdp_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); + + mutex_lock(&mhdp->link_mutex); + + if (!cdns_mhdp_bandwidth_ok(mhdp, mode, mhdp->link.num_lanes, + mhdp->link.rate)) { + mutex_unlock(&mhdp->link_mutex); + return MODE_CLOCK_HIGH; + } + + mutex_unlock(&mhdp->link_mutex); + return MODE_OK; +} + static const struct drm_bridge_funcs cdns_mhdp_bridge_funcs = { .atomic_enable = cdns_mhdp_atomic_enable, .atomic_disable = cdns_mhdp_atomic_disable, @@ -2176,6 +2195,7 @@ static const struct drm_bridge_funcs cdns_mhdp_bridge_funcs = { .edid_read = cdns_mhdp_bridge_edid_read, .hpd_enable = cdns_mhdp_bridge_hpd_enable, .hpd_disable = cdns_mhdp_bridge_hpd_disable, + .mode_valid = cdns_mhdp_bridge_mode_valid, }; static bool cdns_mhdp_detect_hpd(struct cdns_mhdp_device *mhdp, bool *hpd_pulse) From d7b0489d995596d7a51854bbbfa1af5561b2ef21 Mon Sep 17 00:00:00 2001 From: Harikrishna Shenoy Date: Tue, 9 Dec 2025 17:33:29 +0530 Subject: [PATCH 0399/1518] drm/bridge: cadence: cdns-mhdp8546-core: Handle HDCP state in bridge atomic check [ Upstream commit 4a8edd658489ec2a3d7e20482fa9e8d366153d8d ] Now that we have DRM_BRIDGE_ATTACH_NO_CONNECTOR framework, handle the HDCP state change in bridge atomic check as well to enable correct functioning for HDCP in both DRM_BRIDGE_ATTACH_NO_CONNECTOR and !DRM_BRIDGE_ATTACH_NO_CONNECTOR case. Without this patch, when using DRM_BRIDGE_ATTACH_NO_CONNECTOR flag, HDCP state changes would not be properly handled during atomic commits, potentially leading to HDCP authentication failures or incorrect protection status for content requiring HDCP encryption. Fixes: 6a3608eae6d33 ("drm: bridge: cdns-mhdp8546: Enable HDCP") Signed-off-by: Harikrishna Shenoy Reviewed-by: Luca Ceresoli Reviewed-by: Tomi Valkeinen Link: https://patch.msgid.link/20251209120332.3559893-4-h-shenoy@ti.com Signed-off-by: Luca Ceresoli Signed-off-by: Sasha Levin --- .../drm/bridge/cadence/cdns-mhdp8546-core.c | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index 2fb8acd363b14..7ee19b7cc92fc 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -2123,6 +2123,10 @@ static int cdns_mhdp_atomic_check(struct drm_bridge *bridge, { struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge); const struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct drm_connector_state *old_state, *new_state; + struct drm_atomic_state *state = crtc_state->state; + struct drm_connector *conn = mhdp->connector_ptr; + u64 old_cp, new_cp; mutex_lock(&mhdp->link_mutex); @@ -2142,6 +2146,25 @@ static int cdns_mhdp_atomic_check(struct drm_bridge *bridge, if (mhdp->info) bridge_state->input_bus_cfg.flags = *mhdp->info->input_bus_flags; + if (conn && mhdp->hdcp_supported) { + old_state = drm_atomic_get_old_connector_state(state, conn); + new_state = drm_atomic_get_new_connector_state(state, conn); + old_cp = old_state->content_protection; + new_cp = new_state->content_protection; + + if (old_state->hdcp_content_type != new_state->hdcp_content_type && + new_cp != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { + new_state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; + crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc); + crtc_state->mode_changed = true; + } + + if (!new_state->crtc) { + if (old_cp == DRM_MODE_CONTENT_PROTECTION_ENABLED) + new_state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; + } + } + mutex_unlock(&mhdp->link_mutex); return 0; } From c1c2871f33360830b7086634bdb3c136274d1e7d Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Wed, 4 Mar 2026 20:47:20 +0800 Subject: [PATCH 0400/1518] spi: nxp-fspi: Use reinit_completion() for repeated operations [ Upstream commit 68c8c93fdb0de7e528dc3dfb1d17eb0f652259b8 ] The driver currently calls init_completion() during every spi_mem_op. Tchnically it may work, but it's not the recommended pattern. According to the kernel documentation: Calling init_completion() on the same completion object twice is most likely a bug as it re-initializes the queue to an empty queue and enqueued tasks could get "lost" - use reinit_completion() in that case, but be aware of other races. So moves the initial initialization to probe function and uses reinit_completion() for subsequent operations. Fixes: a5356aef6a90 ("spi: spi-mem: Add driver for NXP FlexSPI controller") Signed-off-by: Felix Gu Reviewed-by: Haibo Chen Link: https://patch.msgid.link/20260304-spi-nxp-v2-2-cd7d7726a27e@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-nxp-fspi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 50a7e4916a600..95ccb1f7dfafa 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -996,7 +996,7 @@ static int nxp_fspi_do_op(struct nxp_fspi *f, const struct spi_mem_op *op) reg = reg | FSPI_IPRXFCR_CLR; fspi_writel(f, reg, base + FSPI_IPRXFCR); - init_completion(&f->c); + reinit_completion(&f->c); fspi_writel(f, op->addr.val, base + FSPI_IPCR0); /* @@ -1365,6 +1365,7 @@ static int nxp_fspi_probe(struct platform_device *pdev) if (ret < 0) return dev_err_probe(dev, ret, "Failed to disable clock"); + init_completion(&f->c); ret = devm_request_irq(dev, irq, nxp_fspi_irq_handler, 0, pdev->name, f); if (ret) From 1de12fc4b943e19f849cb929b5d540d4fea05732 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Wed, 4 Mar 2026 20:47:21 +0800 Subject: [PATCH 0401/1518] spi: fsl-qspi: Use reinit_completion() for repeated operations [ Upstream commit 981b080a79724738882b0af1c5bb7ade30d94f24 ] The driver currently calls init_completion() during every spi_mem_op. Tchnically it may work, but it's not the recommended pattern. According to the kernel documentation: Calling init_completion() on the same completion object twice is most likely a bug as it re-initializes the queue to an empty queue and enqueued tasks could get "lost" - use reinit_completion() in that case, but be aware of other races. So moves the initial initialization to probe function and uses reinit_completion() for subsequent operations. Fixes: 84d043185dbe ("spi: Add a driver for the Freescale/NXP QuadSPI controller") Signed-off-by: Felix Gu Reviewed-by: Haibo Chen Link: https://patch.msgid.link/20260304-spi-nxp-v2-3-cd7d7726a27e@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-fsl-qspi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c index c887abb028d77..3904d64ed4334 100644 --- a/drivers/spi/spi-fsl-qspi.c +++ b/drivers/spi/spi-fsl-qspi.c @@ -607,7 +607,7 @@ static int fsl_qspi_do_op(struct fsl_qspi *q, const struct spi_mem_op *op) void __iomem *base = q->iobase; int err = 0; - init_completion(&q->c); + reinit_completion(&q->c); /* * Always start the sequence at the same index since we update @@ -928,6 +928,7 @@ static int fsl_qspi_probe(struct platform_device *pdev) if (ret < 0) return ret; + init_completion(&q->c); ret = devm_request_irq(dev, ret, fsl_qspi_irq_handler, 0, pdev->name, q); if (ret) { From 9b614ddf3185976df3791782c793b4fad3cf0de2 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Thu, 26 Feb 2026 15:37:34 +0200 Subject: [PATCH 0402/1518] media: i2c: og01a1b: Fix V4L2 subdevice data initialization on probe [ Upstream commit 535b7f106991c7d8f0e5b8e1769bfb8b1ce9d3d6 ] It's necessary to finalize the camera sensor subdevice initialization on driver probe and clean V4L2 subdevice data up on error paths and driver removal. The change fixes a previously reported by v4l2-compliance issue of the failed VIDIOC_(UN)SUBSCRIBE_EVENT/DQEVENT test: fail: v4l2-test-controls.cpp(1104): subscribe event for control 'User Controls' failed Fixes: 472377febf84 ("media: Add a driver for the og01a1b camera sensor") Signed-off-by: Vladimir Zapolskiy Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/og01a1b.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/media/i2c/og01a1b.c b/drivers/media/i2c/og01a1b.c index c7184de6251ae..7b892b26203c0 100644 --- a/drivers/media/i2c/og01a1b.c +++ b/drivers/media/i2c/og01a1b.c @@ -1042,6 +1042,7 @@ static void og01a1b_remove(struct i2c_client *client) struct og01a1b *og01a1b = to_og01a1b(sd); v4l2_async_unregister_subdev(sd); + v4l2_subdev_cleanup(&og01a1b->sd); media_entity_cleanup(&sd->entity); v4l2_ctrl_handler_free(sd->ctrl_handler); pm_runtime_disable(og01a1b->dev); @@ -1153,11 +1154,18 @@ static int og01a1b_probe(struct i2c_client *client) goto probe_error_v4l2_ctrl_handler_free; } + ret = v4l2_subdev_init_finalize(&og01a1b->sd); + if (ret < 0) { + dev_err_probe(og01a1b->dev, ret, + "failed to finalize subdevice init\n"); + goto probe_error_media_entity_cleanup; + } + ret = v4l2_async_register_subdev_sensor(&og01a1b->sd); if (ret < 0) { dev_err(og01a1b->dev, "failed to register V4L2 subdev: %d", ret); - goto probe_error_media_entity_cleanup; + goto probe_error_v4l2_subdev_cleanup; } /* Enable runtime PM and turn off the device */ @@ -1167,6 +1175,9 @@ static int og01a1b_probe(struct i2c_client *client) return 0; +probe_error_v4l2_subdev_cleanup: + v4l2_subdev_cleanup(&og01a1b->sd); + probe_error_media_entity_cleanup: media_entity_cleanup(&og01a1b->sd.entity); From 75849e13e428ec5680cef65a2dcef21099f96acd Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Mon, 9 Mar 2026 15:17:00 +0530 Subject: [PATCH 0403/1518] drm/amd/pm: Fix xgmi max speed reporting [ Upstream commit da16822ce5c32b5aca848eaea521936d4410d48c ] Fix XGMI max bitrate/width reporting on SMUv13.0.12 SOCs. The data format got changed when moved to static table from dynamic metrics table. Fixes: 1bec2f270766 ("drm/amd/pm: Fetch SMUv13.0.12 xgmi max speed/width") Signed-off-by: Lijo Lazar Reviewed-by: Asad Kamal Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c index cb3fea9e8cf31..72d56cfd9d287 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c @@ -248,8 +248,9 @@ static void smu_v13_0_12_init_xgmi_data(struct smu_context *smu, int ret; if (smu_table->tables[SMU_TABLE_SMU_METRICS].version >= 0x13) { - max_width = (uint8_t)static_metrics->MaxXgmiWidth; - max_speed = (uint16_t)static_metrics->MaxXgmiBitrate; + max_width = (uint8_t)SMUQ10_ROUND(static_metrics->MaxXgmiWidth); + max_speed = + (uint16_t)SMUQ10_ROUND(static_metrics->MaxXgmiBitrate); ret = 0; } else { MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; From cb54064705ad60c3eb043693189a167344108643 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 13 Mar 2026 05:17:55 +0000 Subject: [PATCH 0404/1518] selftests/sched_ext: Add missing error check for exit__load() [ Upstream commit 1d02346fec8d13b05e54296ddc6ae29b7e1067df ] exit__load(skel) was called without checking its return value. Every other test in the suite wraps the load call with SCX_FAIL_IF(). Add the missing check to be consistent with the rest of the test suite. Fixes: a5db7817af78 ("sched_ext: Add selftests") Signed-off-by: David Carlier Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- tools/testing/selftests/sched_ext/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index ee25824b1cbe6..b987611789d16 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -33,7 +33,7 @@ static enum scx_test_status run(void *ctx) skel = exit__open(); SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; - exit__load(skel); + SCX_FAIL_IF(exit__load(skel), "Failed to load skel"); link = bpf_map__attach_struct_ops(skel->maps.exit_ops); if (!link) { SCX_ERR("Failed to attach scheduler"); From 555eb897a4558a725ab70f8657e8e3679ca55413 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Fri, 6 Mar 2026 08:30:33 -0300 Subject: [PATCH 0405/1518] drm/v3d: Handle error from drm_sched_entity_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8cf1bec37b27846ad3169744c9f1a89a06dcb3fa ] drm_sched_entity_init() can fail but its return value is currently being ignored in v3d_open(). Check the return value and properly unwind on failure by destroying any already-initialized scheduler entities. Fixes: 57692c94dcbe ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+") Reviewed-by: Iago Toral Quiroga Link: https://patch.msgid.link/20260306-v3d-reset-locking-improv-v3-1-49864fe00692@igalia.com Signed-off-by: Maíra Canal Signed-off-by: Sasha Levin --- drivers/gpu/drm/v3d/v3d_drv.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index f4da7a94e4016..7bbb2256ce7dc 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -130,7 +130,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file) struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv; struct drm_gpu_scheduler *sched; - int i; + int i, ret; v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL); if (!v3d_priv) @@ -140,9 +140,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file) for (i = 0; i < V3D_MAX_QUEUES; i++) { sched = &v3d->queue[i].sched; - drm_sched_entity_init(&v3d_priv->sched_entity[i], - DRM_SCHED_PRIORITY_NORMAL, &sched, - 1, NULL); + ret = drm_sched_entity_init(&v3d_priv->sched_entity[i], + DRM_SCHED_PRIORITY_NORMAL, &sched, + 1, NULL); + if (ret) + goto err_sched; memset(&v3d_priv->stats[i], 0, sizeof(v3d_priv->stats[i])); seqcount_init(&v3d_priv->stats[i].lock); @@ -152,6 +154,12 @@ v3d_open(struct drm_device *dev, struct drm_file *file) file->driver_priv = v3d_priv; return 0; + +err_sched: + for (i--; i >= 0; i--) + drm_sched_entity_destroy(&v3d_priv->sched_entity[i]); + kfree(v3d_priv); + return ret; } static void From 4ad705f5e88969e34db9d5baa4811c175a42011d Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Thu, 26 Feb 2026 10:38:36 -0600 Subject: [PATCH 0406/1518] drm/sun4i: Fix resource leaks [ Upstream commit 127367ad2e0f4870de60c6d719ae82ecf68d674c ] Three clocks are not being released in devm_regmap_init_mmio() error path. Add proper goto and set ret to the error code. Fixes: 8270249fbeaf0 ("drm/sun4i: backend: Create regmap after access is possible") Signed-off-by: Ethan Tidmore Reviewed-by: Jernej Skrabec Link: https://patch.msgid.link/20260226163836.10335-1-ethantidmore06@gmail.com Signed-off-by: Chen-Yu Tsai Signed-off-by: Sasha Levin --- drivers/gpu/drm/sun4i/sun4i_backend.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 0484cc27c97ae..1518126e9fe32 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -880,7 +880,8 @@ static int sun4i_backend_bind(struct device *dev, struct device *master, &sun4i_backend_regmap_config); if (IS_ERR(backend->engine.regs)) { dev_err(dev, "Couldn't create the backend regmap\n"); - return PTR_ERR(backend->engine.regs); + ret = PTR_ERR(backend->engine.regs); + goto err_disable_ram_clk; } list_add_tail(&backend->engine.list, &drv->engine_list); From b6263eb2b188255735d1ef6b96a95abe7d8ce324 Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Fri, 6 Mar 2026 23:17:40 +0100 Subject: [PATCH 0407/1518] crypto: inside-secure/eip93 - register hash before authenc algorithms [ Upstream commit 5377032914b29b4643adece0ff1dfc67e36700f4 ] Register hash before hmac and authenc algorithms. This will ensure selftests pass at startup. Previously, selftests failed on the crypto_alloc_ahash() function since the associated algorithm was not yet registered. Fixes following error: ... [ 18.375811] alg: self-tests for authenc(hmac(sha1),cbc(aes)) using authenc(hmac(sha1-eip93),cbc(aes-eip93)) failed (rc=-2) [ 18.382140] alg: self-tests for authenc(hmac(sha224),rfc3686(ctr(aes))) using authenc(hmac(sha224-eip93),rfc3686(ctr(aes-eip93))) failed (rc=-2) [ 18.395029] alg: aead: authenc(hmac(sha256-eip93),cbc(des-eip93)) setkey failed on test vector 0; expected_error=0, actual_error=-2, flags=0x1 [ 18.409734] alg: aead: authenc(hmac(md5-eip93),cbc(des3_ede-eip93)) setkey failed on test vector 0; expected_error=0, actual_error=-2, flags=0x1 ... Fixes: 9739f5f93b78 ("crypto: eip93 - Add Inside Secure SafeXcel EIP-93 crypto engine support") Signed-off-by: Aleksander Jan Bajkowski Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/inside-secure/eip93/eip93-main.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/crypto/inside-secure/eip93/eip93-main.c b/drivers/crypto/inside-secure/eip93/eip93-main.c index b7fd9795062d4..76858bb4fcc22 100644 --- a/drivers/crypto/inside-secure/eip93/eip93-main.c +++ b/drivers/crypto/inside-secure/eip93/eip93-main.c @@ -36,6 +36,14 @@ static struct eip93_alg_template *eip93_algs[] = { &eip93_alg_cbc_aes, &eip93_alg_ctr_aes, &eip93_alg_rfc3686_aes, + &eip93_alg_md5, + &eip93_alg_sha1, + &eip93_alg_sha224, + &eip93_alg_sha256, + &eip93_alg_hmac_md5, + &eip93_alg_hmac_sha1, + &eip93_alg_hmac_sha224, + &eip93_alg_hmac_sha256, &eip93_alg_authenc_hmac_md5_cbc_des, &eip93_alg_authenc_hmac_sha1_cbc_des, &eip93_alg_authenc_hmac_sha224_cbc_des, @@ -52,14 +60,6 @@ static struct eip93_alg_template *eip93_algs[] = { &eip93_alg_authenc_hmac_sha1_rfc3686_aes, &eip93_alg_authenc_hmac_sha224_rfc3686_aes, &eip93_alg_authenc_hmac_sha256_rfc3686_aes, - &eip93_alg_md5, - &eip93_alg_sha1, - &eip93_alg_sha224, - &eip93_alg_sha256, - &eip93_alg_hmac_md5, - &eip93_alg_hmac_sha1, - &eip93_alg_hmac_sha224, - &eip93_alg_hmac_sha256, }; inline void eip93_irq_disable(struct eip93_device *eip93, u32 mask) From 3f917d9bff68600f77561900f3145bd4706dc840 Mon Sep 17 00:00:00 2001 From: Fangyu Yu Date: Thu, 22 Jan 2026 22:32:24 +0800 Subject: [PATCH 0408/1518] iommu/riscv: Add IOTINVAL after updating DDT/PDT entries [ Upstream commit f5c262b544975e067ea265fc7403aefbbea8563e ] Add riscv_iommu_iodir_iotinval() to perform required TLB and context cache invalidations after updating DDT or PDT entries, as mandated by the RISC-V IOMMU specification (Section 6.3.1 and 6.3.2). Fixes: 488ffbf18171 ("iommu/riscv: Paging domain support") Signed-off-by: Fangyu Yu Reviewed-by: Andrew Jones Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/riscv/iommu.c | 70 +++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index ebb22979075df..c183818015813 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -996,7 +996,67 @@ static void riscv_iommu_iotlb_inval(struct riscv_iommu_domain *domain, } #define RISCV_IOMMU_FSC_BARE 0 +/* + * This function sends IOTINVAL commands as required by the RISC-V + * IOMMU specification (Section 6.3.1 and 6.3.2 in 1.0 spec version) + * after modifying DDT or PDT entries + */ +static void riscv_iommu_iodir_iotinval(struct riscv_iommu_device *iommu, + bool inval_pdt, unsigned long iohgatp, + struct riscv_iommu_dc *dc, + struct riscv_iommu_pc *pc) +{ + struct riscv_iommu_command cmd; + + riscv_iommu_cmd_inval_vma(&cmd); + if (FIELD_GET(RISCV_IOMMU_DC_IOHGATP_MODE, iohgatp) == + RISCV_IOMMU_DC_IOHGATP_MODE_BARE) { + if (inval_pdt) { + /* + * IOTINVAL.VMA with GV=AV=0, and PSCV=1, and + * PSCID=PC.PSCID + */ + riscv_iommu_cmd_inval_set_pscid(&cmd, + FIELD_GET(RISCV_IOMMU_PC_TA_PSCID, pc->ta)); + } else { + if (!FIELD_GET(RISCV_IOMMU_DC_TC_PDTV, dc->tc) && + FIELD_GET(RISCV_IOMMU_DC_FSC_MODE, dc->fsc) != + RISCV_IOMMU_DC_FSC_MODE_BARE) { + /* + * DC.tc.PDTV == 0 && DC.fsc.MODE != Bare + * IOTINVAL.VMA with GV=AV=0, and PSCV=1, and + * PSCID=DC.ta.PSCID + */ + riscv_iommu_cmd_inval_set_pscid(&cmd, + FIELD_GET(RISCV_IOMMU_DC_TA_PSCID, dc->ta)); + } + /* else: IOTINVAL.VMA with GV=AV=PSCV=0 */ + } + } else { + riscv_iommu_cmd_inval_set_gscid(&cmd, + FIELD_GET(RISCV_IOMMU_DC_IOHGATP_GSCID, iohgatp)); + + if (inval_pdt) { + /* + * IOTINVAL.VMA with GV=1, AV=0, and PSCV=1, and + * GSCID=DC.iohgatp.GSCID, PSCID=PC.PSCID + */ + riscv_iommu_cmd_inval_set_pscid(&cmd, + FIELD_GET(RISCV_IOMMU_PC_TA_PSCID, pc->ta)); + } + /* + * else: IOTINVAL.VMA with GV=1,AV=PSCV=0,and + * GSCID=DC.iohgatp.GSCID + * + * IOTINVAL.GVMA with GV=1,AV=0,and + * GSCID=DC.iohgatp.GSCID + * TODO: For now, the Second-Stage feature have not yet been merged, + * also issue IOTINVAL.GVMA once second-stage support is merged. + */ + } + riscv_iommu_cmd_send(iommu, &cmd); +} /* * Update IODIR for the device. * @@ -1031,6 +1091,11 @@ static void riscv_iommu_iodir_update(struct riscv_iommu_device *iommu, riscv_iommu_cmd_iodir_inval_ddt(&cmd); riscv_iommu_cmd_iodir_set_did(&cmd, fwspec->ids[i]); riscv_iommu_cmd_send(iommu, &cmd); + /* + * For now, the SVA and PASID features have not yet been merged, the + * default configuration is inval_pdt=false and pc=NULL. + */ + riscv_iommu_iodir_iotinval(iommu, false, dc->iohgatp, dc, NULL); sync_required = true; } @@ -1056,6 +1121,11 @@ static void riscv_iommu_iodir_update(struct riscv_iommu_device *iommu, riscv_iommu_cmd_iodir_inval_ddt(&cmd); riscv_iommu_cmd_iodir_set_did(&cmd, fwspec->ids[i]); riscv_iommu_cmd_send(iommu, &cmd); + /* + * For now, the SVA and PASID features have not yet been merged, the + * default configuration is inval_pdt=false and pc=NULL. + */ + riscv_iommu_iodir_iotinval(iommu, false, dc->iohgatp, dc, NULL); } riscv_iommu_cmd_sync(iommu, RISCV_IOMMU_IOTINVAL_TIMEOUT); From 380698b43f072c424d5d8151e5636fd925557c4d Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 27 Feb 2026 11:25:40 -0400 Subject: [PATCH 0409/1518] iommu/riscv: Add missing GENERIC_MSI_IRQ [ Upstream commit c70d20b25ca30d68b377b9363a2adca6eb2538e3 ] The commit below added MSI related calls to the driver that depends on GENERIC_MSI_IRQ. It is possible to build RISC-V without this selected. This is also necessary to make the driver COMPILE_TEST. Fixes: d5f88acdd6ff ("iommu/riscv: Add support for platform msi") Tested-by: Vincent Chen Tested-by: Tomasz Jeznach Signed-off-by: Jason Gunthorpe Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/riscv/Kconfig b/drivers/iommu/riscv/Kconfig index c071816f59a67..fb8e217edc3d3 100644 --- a/drivers/iommu/riscv/Kconfig +++ b/drivers/iommu/riscv/Kconfig @@ -4,6 +4,7 @@ config RISCV_IOMMU bool "RISC-V IOMMU Support" depends on RISCV && 64BIT + depends on GENERIC_MSI_IRQ default y select IOMMU_API help From 0d3b392b0f2cffa408cc8cf7798a53c114326a7f Mon Sep 17 00:00:00 2001 From: Fangyu Yu Date: Fri, 27 Feb 2026 19:26:40 +0800 Subject: [PATCH 0410/1518] iommu/riscv: Stop polling when CQCSR reports an error [ Upstream commit b2e5684558edf3e9bbe18d0e0043854994eab1be ] The cmdq wait loop busy-polls the consumer index until it advances or the software timeout expires. If the IOMMU has already signaled a command queue failure in CQCSR, continuing to poll for progress is pointless. Make riscv_iommu_queue_wait() also terminate the poll when any of these CQCSR error bits are observed. This helps the caller return earlier in failure cases and avoids spinning until the full timeout interval when the hardware has already reported an error. On single-core systems in particular, the current busy-wait can delay servicing the command-timeout interrupt until the software timeout expires (90s by default). Fixes: 856c0cfe5c5f ("iommu/riscv: Command and fault queue support") Signed-off-by: Fangyu Yu Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/riscv/iommu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index c183818015813..1e8007a153c32 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -368,6 +368,8 @@ static int riscv_iommu_queue_wait(struct riscv_iommu_queue *queue, unsigned int timeout_us) { unsigned int cons = atomic_read(&queue->head); + unsigned int flags = RISCV_IOMMU_CQCSR_CQMF | RISCV_IOMMU_CQCSR_CMD_TO | + RISCV_IOMMU_CQCSR_CMD_ILL; /* Already processed by the consumer */ if ((int)(cons - index) > 0) @@ -375,6 +377,7 @@ static int riscv_iommu_queue_wait(struct riscv_iommu_queue *queue, /* Monitor consumer index */ return readx_poll_timeout(riscv_iommu_queue_cons, queue, cons, + (riscv_iommu_readl(queue->iommu, queue->qcr) & flags) || (int)(cons - index) > 0, 0, timeout_us); } From c695257f6b8d5bf8f303430bf8de3efaf37055dd Mon Sep 17 00:00:00 2001 From: Srinivasan Shanmugam Date: Thu, 12 Mar 2026 19:29:54 +0530 Subject: [PATCH 0411/1518] drm/amdgpu: Add default case in DVI mode validation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e6020a55b8e364d15eac27f9c788e13114eec6b7 ] amdgpu_connector_dvi_mode_valid() assigns max_digital_pixel_clock_khz based on connector_object_id using a switch statement that lacks a default case. In practice this code path should never be hit because the existing cases already cover all digital connector types that this function is used for. This is also legacy display code which is not used for new hardware. Add a default case returning MODE_BAD to make the switch exhaustive and silence the static analyzer smatch error. The new branch is effectively defensive and should never be reached during normal operation. Fixes: 585b2f685c56 ("drm/amdgpu: Respect max pixel clock for HDMI and DVI-D (v2)") Cc: Dan Carpenter Cc: Timur Kristóf Cc: Alex Deucher Cc: Christian König Signed-off-by: Srinivasan Shanmugam Acked-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 47e9bfba06424..46b04e2203eba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -1244,6 +1244,8 @@ static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector case CONNECTOR_OBJECT_ID_HDMI_TYPE_B: max_digital_pixel_clock_khz = max_dvi_single_link_pixel_clock * 2; break; + default: + return MODE_BAD; } /* When the display EDID claims that it's an HDMI display, From 57a1079af3ee3dd91fd1c04ac9a9ee198de58f56 Mon Sep 17 00:00:00 2001 From: Guillaume Gonnet Date: Tue, 17 Mar 2026 22:32:28 +0100 Subject: [PATCH 0412/1518] dm init: ensure device probing has finished in dm-mod.waitfor= [ Upstream commit 99a2312f69805f4ba92d98a757625e0300a747ab ] The early_lookup_bdev() function returns successfully when the disk device is present but not necessarily its partitions. In this situation, dm_early_create() fails as the partition block device does not exist yet. In my case, this phenomenon occurs quite often because the device is an SD card with slow reading times, on which kernel takes time to enumerate available partitions. Fortunately, the underlying device is back to "probing" state while enumerating partitions. Waiting for all probing to end is enough to fix this issue. That's also the reason why this problem never occurs with rootwait= parameter: the while loop inside wait_for_root() explicitly waits for probing to be done and then the function calls async_synchronize_full(). These lines were omitted in 035641b, even though the commit says it's based on the rootwait logic... Anyway, calling wait_for_device_probe() after our while loop does the job (it both waits for probing and calls async_synchronize_full). Fixes: 035641b01e72 ("dm init: add dm-mod.waitfor to wait for asynchronously probed block devices") Signed-off-by: Guillaume Gonnet Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index b37bbe7625003..423269cbdd2bb 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -303,8 +303,10 @@ static int __init dm_init_init(void) } } - if (waitfor[0]) + if (waitfor[0]) { + wait_for_device_probe(); DMINFO("all devices available"); + } list_for_each_entry(dev, &devices, list) { if (dm_early_create(&dev->dmi, dev->table, From 4a894ba48fa5123032a766a45fb075086720dc2b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 20 Mar 2026 15:36:46 +0100 Subject: [PATCH 0413/1518] fbdev: matroxfb: Mark variable with __maybe_unused to avoid W=1 build break [ Upstream commit caf6144053b4e1c815aa56afb54745a176f999df ] Clang is not happy about set but unused variable: drivers/video/fbdev/matrox/g450_pll.c:412:18: error: variable 'mnp' set but not used 412 | unsigned int mnp; | ^ 1 error generated. Since the commit 7b987887f97b ("video: fbdev: matroxfb: remove dead code and set but not used variable") the 'mnp' became unused, but eliminating that code might have side-effects. The question here is what should we do with 'mnp'? The easiest way out is just mark it with __maybe_unused which will shut the compiler up and won't change any possible IO flow. So does this change. A dive into the history of the driver: The problem was revealed when the #if 0 guarded code along with unused pixel_vco variable was removed. That code was introduced in the original commit 213d22146d1f ("[PATCH] (1/3) matroxfb for 2.5.3"). And then guarded in the commit 705e41f82988 ("matroxfb DVI updates: Handle DVI output on G450/G550. Powerdown unused portions of G450/G550 DAC. Split G450/G550 DAC from older DAC1064 handling. Modify PLL setting when both CRTCs use same pixel clocks."). NOTE: The two commits mentioned above pre-date Git era and available in history.git repository for archaeological purposes. Even without that guard the modern compilers may see that the pixel_vco wasn't ever used and seems a leftover after some debug or review made 25 years ago. The g450_mnp2vco() doesn't have any IO and as Jason said doesn't seem to have any side effects either than some unneeded CPU processing during runtime. I agree that's unlikely that timeout (or heating up the CPU) has any effect on the HW (GPU/display) functionality. Fixes: 7b987887f97b ("video: fbdev: matroxfb: remove dead code and set but not used variable") Signed-off-by: Andy Shevchenko Reviewed-by: Jason Yan Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/matrox/g450_pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/matrox/g450_pll.c b/drivers/video/fbdev/matrox/g450_pll.c index e2c1478aa47f9..6a08f78cd1acb 100644 --- a/drivers/video/fbdev/matrox/g450_pll.c +++ b/drivers/video/fbdev/matrox/g450_pll.c @@ -409,7 +409,7 @@ static int __g450_setclk(struct matrox_fb_info *minfo, unsigned int fout, case M_VIDEO_PLL: { u_int8_t tmp; - unsigned int mnp; + unsigned int mnp __maybe_unused; unsigned long flags; matroxfb_DAC_lock_irqsave(flags); From 9458a6513fe7b78a98075257e9a5c29936cbf82f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 10 Mar 2026 18:28:29 +0900 Subject: [PATCH 0414/1518] crypto: tegra - Disable softirqs before finalizing request [ Upstream commit 2aeec9af775fb53aa086419b953302c6f4ad4984 ] Softirqs must be disabled when calling the finalization fucntion on a request. Reported-by: Guangwu Zhang Fixes: 0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver") Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/tegra/tegra-se-aes.c | 9 +++++++++ drivers/crypto/tegra/tegra-se-hash.c | 3 +++ 2 files changed, 12 insertions(+) diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c index 9210cceb4b7b2..30c78afe3dea6 100644 --- a/drivers/crypto/tegra/tegra-se-aes.c +++ b/drivers/crypto/tegra/tegra-se-aes.c @@ -4,6 +4,7 @@ * Crypto driver to handle block cipher algorithms using NVIDIA Security Engine. */ +#include #include #include #include @@ -333,7 +334,9 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq) tegra_key_invalidate_reserved(ctx->se, key2_id, ctx->alg); out_finalize: + local_bh_disable(); crypto_finalize_skcipher_request(se->engine, req, ret); + local_bh_enable(); return 0; } @@ -1262,7 +1265,9 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq) tegra_key_invalidate_reserved(ctx->se, rctx->key_id, ctx->alg); out_finalize: + local_bh_disable(); crypto_finalize_aead_request(ctx->se->engine, req, ret); + local_bh_enable(); return 0; } @@ -1348,7 +1353,9 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq) tegra_key_invalidate_reserved(ctx->se, rctx->key_id, ctx->alg); out_finalize: + local_bh_disable(); crypto_finalize_aead_request(ctx->se->engine, req, ret); + local_bh_enable(); return 0; } @@ -1746,7 +1753,9 @@ static int tegra_cmac_do_one_req(struct crypto_engine *engine, void *areq) if (tegra_key_is_reserved(rctx->key_id)) tegra_key_invalidate_reserved(ctx->se, rctx->key_id, ctx->alg); + local_bh_disable(); crypto_finalize_hash_request(se->engine, req, ret); + local_bh_enable(); return 0; } diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c index 06bb5bf0fa335..23d549801612e 100644 --- a/drivers/crypto/tegra/tegra-se-hash.c +++ b/drivers/crypto/tegra/tegra-se-hash.c @@ -4,6 +4,7 @@ * Crypto driver to handle HASH algorithms using NVIDIA Security Engine. */ +#include #include #include #include @@ -546,7 +547,9 @@ static int tegra_sha_do_one_req(struct crypto_engine *engine, void *areq) } out: + local_bh_disable(); crypto_finalize_hash_request(se->engine, req, ret); + local_bh_enable(); return 0; } From f4b747f0755eed7215c1be8bf7b891d519a73e83 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Mon, 26 Jan 2026 18:47:03 +0100 Subject: [PATCH 0415/1518] crypto: atmel - Use unregister_{aeads,ahashes,skciphers} [ Upstream commit 2ffc1ef4e826f0c3274f9ff5eb42bc70a5571afd ] Replace multiple for loops with calls to crypto_unregister_aeads(), crypto_unregister_ahashes(), and crypto_unregister_skciphers(). Remove the definition of atmel_tdes_unregister_algs() because it is equivalent to calling crypto_unregister_skciphers() directly, and the function parameter 'struct atmel_tdes_dev *' is unused anyway. Signed-off-by: Thorsten Blum Signed-off-by: Herbert Xu Stable-dep-of: 57a13941c0bb ("crypto: atmel-aes - guard unregister on error in atmel_aes_register_algs") Signed-off-by: Sasha Levin --- drivers/crypto/atmel-aes.c | 17 ++++++----------- drivers/crypto/atmel-sha.c | 27 ++++++++++----------------- drivers/crypto/atmel-tdes.c | 25 ++++++------------------- 3 files changed, 22 insertions(+), 47 deletions(-) diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 5a6d64be81858..9b0cb97055dc5 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -2201,12 +2201,10 @@ static irqreturn_t atmel_aes_irq(int irq, void *dev_id) static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd) { - int i; - #if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) if (dd->caps.has_authenc) - for (i = 0; i < ARRAY_SIZE(aes_authenc_algs); i++) - crypto_unregister_aead(&aes_authenc_algs[i]); + crypto_unregister_aeads(aes_authenc_algs, + ARRAY_SIZE(aes_authenc_algs)); #endif if (dd->caps.has_xts) @@ -2215,8 +2213,7 @@ static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd) if (dd->caps.has_gcm) crypto_unregister_aead(&aes_gcm_alg); - for (i = 0; i < ARRAY_SIZE(aes_algs); i++) - crypto_unregister_skcipher(&aes_algs[i]); + crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs)); } static void atmel_aes_crypto_alg_init(struct crypto_alg *alg) @@ -2229,7 +2226,7 @@ static void atmel_aes_crypto_alg_init(struct crypto_alg *alg) static int atmel_aes_register_algs(struct atmel_aes_dev *dd) { - int err, i, j; + int err, i; for (i = 0; i < ARRAY_SIZE(aes_algs); i++) { atmel_aes_crypto_alg_init(&aes_algs[i].base); @@ -2272,8 +2269,7 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd) #if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) /* i = ARRAY_SIZE(aes_authenc_algs); */ err_aes_authenc_alg: - for (j = 0; j < i; j++) - crypto_unregister_aead(&aes_authenc_algs[j]); + crypto_unregister_aeads(aes_authenc_algs, i); crypto_unregister_skcipher(&aes_xts_alg); #endif err_aes_xts_alg: @@ -2281,8 +2277,7 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd) err_aes_gcm_alg: i = ARRAY_SIZE(aes_algs); err_aes_algs: - for (j = 0; j < i; j++) - crypto_unregister_skcipher(&aes_algs[j]); + crypto_unregister_skciphers(aes_algs, i); return err; } diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 3d7573c7bd1ca..b02a71061708c 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -2418,27 +2418,23 @@ EXPORT_SYMBOL_GPL(atmel_sha_authenc_abort); static void atmel_sha_unregister_algs(struct atmel_sha_dev *dd) { - int i; - if (dd->caps.has_hmac) - for (i = 0; i < ARRAY_SIZE(sha_hmac_algs); i++) - crypto_unregister_ahash(&sha_hmac_algs[i]); + crypto_unregister_ahashes(sha_hmac_algs, + ARRAY_SIZE(sha_hmac_algs)); - for (i = 0; i < ARRAY_SIZE(sha_1_256_algs); i++) - crypto_unregister_ahash(&sha_1_256_algs[i]); + crypto_unregister_ahashes(sha_1_256_algs, ARRAY_SIZE(sha_1_256_algs)); if (dd->caps.has_sha224) crypto_unregister_ahash(&sha_224_alg); - if (dd->caps.has_sha_384_512) { - for (i = 0; i < ARRAY_SIZE(sha_384_512_algs); i++) - crypto_unregister_ahash(&sha_384_512_algs[i]); - } + if (dd->caps.has_sha_384_512) + crypto_unregister_ahashes(sha_384_512_algs, + ARRAY_SIZE(sha_384_512_algs)); } static int atmel_sha_register_algs(struct atmel_sha_dev *dd) { - int err, i, j; + int err, i; for (i = 0; i < ARRAY_SIZE(sha_1_256_algs); i++) { atmel_sha_alg_init(&sha_1_256_algs[i]); @@ -2480,18 +2476,15 @@ static int atmel_sha_register_algs(struct atmel_sha_dev *dd) /*i = ARRAY_SIZE(sha_hmac_algs);*/ err_sha_hmac_algs: - for (j = 0; j < i; j++) - crypto_unregister_ahash(&sha_hmac_algs[j]); + crypto_unregister_ahashes(sha_hmac_algs, i); i = ARRAY_SIZE(sha_384_512_algs); err_sha_384_512_algs: - for (j = 0; j < i; j++) - crypto_unregister_ahash(&sha_384_512_algs[j]); + crypto_unregister_ahashes(sha_384_512_algs, i); crypto_unregister_ahash(&sha_224_alg); err_sha_224_algs: i = ARRAY_SIZE(sha_1_256_algs); err_sha_1_256_algs: - for (j = 0; j < i; j++) - crypto_unregister_ahash(&sha_1_256_algs[j]); + crypto_unregister_ahashes(sha_1_256_algs, i); return err; } diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index d3bd8b72c2c95..643e507f9c020 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -897,38 +897,25 @@ static irqreturn_t atmel_tdes_irq(int irq, void *dev_id) return IRQ_NONE; } -static void atmel_tdes_unregister_algs(struct atmel_tdes_dev *dd) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(tdes_algs); i++) - crypto_unregister_skcipher(&tdes_algs[i]); -} - static int atmel_tdes_register_algs(struct atmel_tdes_dev *dd) { - int err, i, j; + int err, i; for (i = 0; i < ARRAY_SIZE(tdes_algs); i++) { atmel_tdes_skcipher_alg_init(&tdes_algs[i]); err = crypto_register_skcipher(&tdes_algs[i]); - if (err) - goto err_tdes_algs; + if (err) { + crypto_unregister_skciphers(tdes_algs, i); + return err; + } } return 0; - -err_tdes_algs: - for (j = 0; j < i; j++) - crypto_unregister_skcipher(&tdes_algs[j]); - - return err; } static void atmel_tdes_get_cap(struct atmel_tdes_dev *dd) { - dd->caps.has_dma = 0; /* keep only major version number */ @@ -1061,7 +1048,7 @@ static void atmel_tdes_remove(struct platform_device *pdev) list_del(&tdes_dd->list); spin_unlock(&atmel_tdes.lock); - atmel_tdes_unregister_algs(tdes_dd); + crypto_unregister_skciphers(tdes_algs, ARRAY_SIZE(tdes_algs)); tasklet_kill(&tdes_dd->done_task); tasklet_kill(&tdes_dd->queue_task); From 3ffcd6c5dca983572d3ee0f9f371b5a431817672 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Wed, 11 Mar 2026 12:39:28 +0100 Subject: [PATCH 0416/1518] crypto: atmel-aes - guard unregister on error in atmel_aes_register_algs [ Upstream commit 57a13941c0bb06ae24e3b34672d7b6f2172b253f ] Ensure the device supports XTS and GCM with 'has_xts' and 'has_gcm' before unregistering algorithms when XTS or authenc registration fails, which would trigger a WARN in crypto_unregister_alg(). Currently, with the capabilities defined in atmel_aes_get_cap(), this bug cannot happen because all devices that support XTS and authenc also support GCM, but the error handling should still be correct regardless of hardware capabilities. Fixes: d52db5188a87 ("crypto: atmel-aes - add support to the XTS mode") Signed-off-by: Thorsten Blum Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/atmel-aes.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 9b0cb97055dc5..b393689400b4c 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -2270,10 +2270,12 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd) /* i = ARRAY_SIZE(aes_authenc_algs); */ err_aes_authenc_alg: crypto_unregister_aeads(aes_authenc_algs, i); - crypto_unregister_skcipher(&aes_xts_alg); + if (dd->caps.has_xts) + crypto_unregister_skcipher(&aes_xts_alg); #endif err_aes_xts_alg: - crypto_unregister_aead(&aes_gcm_alg); + if (dd->caps.has_gcm) + crypto_unregister_aead(&aes_gcm_alg); err_aes_gcm_alg: i = ARRAY_SIZE(aes_algs); err_aes_algs: From 8e26246dc1049fc0a49b34829f2a83c69ebefa8d Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Thu, 26 Feb 2026 16:07:03 +0800 Subject: [PATCH 0417/1518] padata: Remove cpu online check from cpu add and removal [ Upstream commit 73117ea6470dca787f70f33c001f9faf437a1c0b ] During the CPU offline process, the dying CPU is cleared from the cpu_online_mask in takedown_cpu(). After this step, various CPUHP_*_DEAD callbacks are executed to perform cleanup jobs for the dead CPU, so this cpu online check in padata_cpu_dead() is unnecessary. Similarly, when executing padata_cpu_online() during the CPUHP_AP_ONLINE_DYN phase, the CPU has already been set in the cpu_online_mask, the action even occurs earlier than the CPUHP_AP_ONLINE_IDLE stage. Remove this unnecessary cpu online check in __padata_add_cpu() and __padata_remove_cpu(). Signed-off-by: Chuyi Zhou Acked-by: Daniel Jordan Signed-off-by: Herbert Xu Stable-dep-of: c8c4a2972f83 ("padata: Put CPU offline callback in ONLINE section to allow failure") Signed-off-by: Sasha Levin --- kernel/padata.c | 26 ++++++++------------------ 1 file changed, 8 insertions(+), 18 deletions(-) diff --git a/kernel/padata.c b/kernel/padata.c index f4def028c48c0..f53263d7c9d42 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -736,32 +736,22 @@ EXPORT_SYMBOL(padata_set_cpumask); static int __padata_add_cpu(struct padata_instance *pinst, int cpu) { - int err = 0; - - if (cpumask_test_cpu(cpu, cpu_online_mask)) { - err = padata_replace(pinst); + int err = padata_replace(pinst); - if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) && - padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) - __padata_start(pinst); - } + if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) && + padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) + __padata_start(pinst); return err; } static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) { - int err = 0; - - if (!cpumask_test_cpu(cpu, cpu_online_mask)) { - if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) || - !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) - __padata_stop(pinst); - - err = padata_replace(pinst); - } + if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) || + !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) + __padata_stop(pinst); - return err; + return padata_replace(pinst); } static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu) From 5a9f29a3e076b637d2234093e57989cf755ded5b Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Fri, 13 Mar 2026 11:24:33 -0400 Subject: [PATCH 0418/1518] padata: Put CPU offline callback in ONLINE section to allow failure [ Upstream commit c8c4a2972f83c8b68ff03b43cecdb898939ff851 ] syzbot reported the following warning: DEAD callback error for CPU1 WARNING: kernel/cpu.c:1463 at _cpu_down+0x759/0x1020 kernel/cpu.c:1463, CPU#0: syz.0.1960/14614 at commit 4ae12d8bd9a8 ("Merge tag 'kbuild-fixes-7.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kbuild/linux") which tglx traced to padata_cpu_dead() given it's the only sub-CPUHP_TEARDOWN_CPU callback that returns an error. Failure isn't allowed in hotplug states before CPUHP_TEARDOWN_CPU so move the CPU offline callback to the ONLINE section where failure is possible. Fixes: 894c9ef9780c ("padata: validate cpumask without removed CPU during offline") Reported-by: syzbot+123e1b70473ce213f3af@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/69af0a05.050a0220.310d8.002f.GAE@google.com/ Debugged-by: Thomas Gleixner Signed-off-by: Daniel Jordan Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- include/linux/cpuhotplug.h | 1 - include/linux/padata.h | 8 +-- kernel/padata.c | 120 +++++++++++++++++++------------------ 3 files changed, 65 insertions(+), 64 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 62cd7b35a29c9..22ba327ec2278 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -92,7 +92,6 @@ enum cpuhp_state { CPUHP_NET_DEV_DEAD, CPUHP_IOMMU_IOVA_DEAD, CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, - CPUHP_PADATA_DEAD, CPUHP_AP_DTPM_CPU_DEAD, CPUHP_RANDOM_PREPARE, CPUHP_WORKQUEUE_PREP, diff --git a/include/linux/padata.h b/include/linux/padata.h index 765f2778e264a..b6232bea6edf5 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -149,23 +149,23 @@ struct padata_mt_job { /** * struct padata_instance - The overall control structure. * - * @cpu_online_node: Linkage for CPU online callback. - * @cpu_dead_node: Linkage for CPU offline callback. + * @cpuhp_node: Linkage for CPU hotplug callbacks. * @parallel_wq: The workqueue used for parallel work. * @serial_wq: The workqueue used for serial work. * @pslist: List of padata_shell objects attached to this instance. * @cpumask: User supplied cpumasks for parallel and serial works. + * @validate_cpumask: Internal cpumask used to validate @cpumask during hotplug. * @kobj: padata instance kernel object. * @lock: padata instance lock. * @flags: padata flags. */ struct padata_instance { - struct hlist_node cpu_online_node; - struct hlist_node cpu_dead_node; + struct hlist_node cpuhp_node; struct workqueue_struct *parallel_wq; struct workqueue_struct *serial_wq; struct list_head pslist; struct padata_cpumask cpumask; + cpumask_var_t validate_cpumask; struct kobject kobj; struct mutex lock; u8 flags; diff --git a/kernel/padata.c b/kernel/padata.c index f53263d7c9d42..938c926711876 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -539,7 +539,8 @@ static void padata_init_reorder_list(struct parallel_data *pd) } /* Allocate and initialize the internal cpumask dependend resources. */ -static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) +static struct parallel_data *padata_alloc_pd(struct padata_shell *ps, + int offlining_cpu) { struct padata_instance *pinst = ps->pinst; struct parallel_data *pd; @@ -565,6 +566,10 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask); cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask); + if (offlining_cpu >= 0) { + __cpumask_clear_cpu(offlining_cpu, pd->cpumask.pcpu); + __cpumask_clear_cpu(offlining_cpu, pd->cpumask.cbcpu); + } padata_init_reorder_list(pd); padata_init_squeues(pd); @@ -611,11 +616,11 @@ static void __padata_stop(struct padata_instance *pinst) } /* Replace the internal control structure with a new one. */ -static int padata_replace_one(struct padata_shell *ps) +static int padata_replace_one(struct padata_shell *ps, int offlining_cpu) { struct parallel_data *pd_new; - pd_new = padata_alloc_pd(ps); + pd_new = padata_alloc_pd(ps, offlining_cpu); if (!pd_new) return -ENOMEM; @@ -625,7 +630,7 @@ static int padata_replace_one(struct padata_shell *ps) return 0; } -static int padata_replace(struct padata_instance *pinst) +static int padata_replace(struct padata_instance *pinst, int offlining_cpu) { struct padata_shell *ps; int err = 0; @@ -633,7 +638,7 @@ static int padata_replace(struct padata_instance *pinst) pinst->flags |= PADATA_RESET; list_for_each_entry(ps, &pinst->pslist, list) { - err = padata_replace_one(ps); + err = padata_replace_one(ps, offlining_cpu); if (err) break; } @@ -650,9 +655,21 @@ static int padata_replace(struct padata_instance *pinst) /* If cpumask contains no active cpu, we mark the instance as invalid. */ static bool padata_validate_cpumask(struct padata_instance *pinst, - const struct cpumask *cpumask) + const struct cpumask *cpumask, + int offlining_cpu) { - if (!cpumask_intersects(cpumask, cpu_online_mask)) { + cpumask_copy(pinst->validate_cpumask, cpu_online_mask); + + /* + * @offlining_cpu is still in cpu_online_mask, so remove it here for + * validation. Using a sub-CPUHP_TEARDOWN_CPU hotplug state where + * @offlining_cpu wouldn't be in the online mask doesn't work because + * padata_cpu_offline() can fail but such a state doesn't allow failure. + */ + if (offlining_cpu >= 0) + __cpumask_clear_cpu(offlining_cpu, pinst->validate_cpumask); + + if (!cpumask_intersects(cpumask, pinst->validate_cpumask)) { pinst->flags |= PADATA_INVALID; return false; } @@ -668,13 +685,13 @@ static int __padata_set_cpumasks(struct padata_instance *pinst, int valid; int err; - valid = padata_validate_cpumask(pinst, pcpumask); + valid = padata_validate_cpumask(pinst, pcpumask, -1); if (!valid) { __padata_stop(pinst); goto out_replace; } - valid = padata_validate_cpumask(pinst, cbcpumask); + valid = padata_validate_cpumask(pinst, cbcpumask, -1); if (!valid) __padata_stop(pinst); @@ -682,7 +699,7 @@ static int __padata_set_cpumasks(struct padata_instance *pinst, cpumask_copy(pinst->cpumask.pcpu, pcpumask); cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); - err = padata_setup_cpumasks(pinst) ?: padata_replace(pinst); + err = padata_setup_cpumasks(pinst) ?: padata_replace(pinst, -1); if (valid) __padata_start(pinst); @@ -734,26 +751,6 @@ EXPORT_SYMBOL(padata_set_cpumask); #ifdef CONFIG_HOTPLUG_CPU -static int __padata_add_cpu(struct padata_instance *pinst, int cpu) -{ - int err = padata_replace(pinst); - - if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) && - padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) - __padata_start(pinst); - - return err; -} - -static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) -{ - if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) || - !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) - __padata_stop(pinst); - - return padata_replace(pinst); -} - static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu) { return cpumask_test_cpu(cpu, pinst->cpumask.pcpu) || @@ -765,27 +762,39 @@ static int padata_cpu_online(unsigned int cpu, struct hlist_node *node) struct padata_instance *pinst; int ret; - pinst = hlist_entry_safe(node, struct padata_instance, cpu_online_node); + pinst = hlist_entry_safe(node, struct padata_instance, cpuhp_node); if (!pinst_has_cpu(pinst, cpu)) return 0; mutex_lock(&pinst->lock); - ret = __padata_add_cpu(pinst, cpu); + + ret = padata_replace(pinst, -1); + + if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu, -1) && + padata_validate_cpumask(pinst, pinst->cpumask.cbcpu, -1)) + __padata_start(pinst); + mutex_unlock(&pinst->lock); return ret; } -static int padata_cpu_dead(unsigned int cpu, struct hlist_node *node) +static int padata_cpu_offline(unsigned int cpu, struct hlist_node *node) { struct padata_instance *pinst; int ret; - pinst = hlist_entry_safe(node, struct padata_instance, cpu_dead_node); + pinst = hlist_entry_safe(node, struct padata_instance, cpuhp_node); if (!pinst_has_cpu(pinst, cpu)) return 0; mutex_lock(&pinst->lock); - ret = __padata_remove_cpu(pinst, cpu); + + if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu, cpu) || + !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu, cpu)) + __padata_stop(pinst); + + ret = padata_replace(pinst, cpu); + mutex_unlock(&pinst->lock); return ret; } @@ -796,15 +805,14 @@ static enum cpuhp_state hp_online; static void __padata_free(struct padata_instance *pinst) { #ifdef CONFIG_HOTPLUG_CPU - cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD, - &pinst->cpu_dead_node); - cpuhp_state_remove_instance_nocalls(hp_online, &pinst->cpu_online_node); + cpuhp_state_remove_instance_nocalls(hp_online, &pinst->cpuhp_node); #endif WARN_ON(!list_empty(&pinst->pslist)); free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); + free_cpumask_var(pinst->validate_cpumask); destroy_workqueue(pinst->serial_wq); destroy_workqueue(pinst->parallel_wq); kfree(pinst); @@ -965,10 +973,10 @@ struct padata_instance *padata_alloc(const char *name) if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL)) goto err_free_serial_wq; - if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) { - free_cpumask_var(pinst->cpumask.pcpu); - goto err_free_serial_wq; - } + if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) + goto err_free_p_mask; + if (!alloc_cpumask_var(&pinst->validate_cpumask, GFP_KERNEL)) + goto err_free_cb_mask; INIT_LIST_HEAD(&pinst->pslist); @@ -976,7 +984,7 @@ struct padata_instance *padata_alloc(const char *name) cpumask_copy(pinst->cpumask.cbcpu, cpu_possible_mask); if (padata_setup_cpumasks(pinst)) - goto err_free_masks; + goto err_free_v_mask; __padata_start(pinst); @@ -985,18 +993,19 @@ struct padata_instance *padata_alloc(const char *name) #ifdef CONFIG_HOTPLUG_CPU cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, - &pinst->cpu_online_node); - cpuhp_state_add_instance_nocalls_cpuslocked(CPUHP_PADATA_DEAD, - &pinst->cpu_dead_node); + &pinst->cpuhp_node); #endif cpus_read_unlock(); return pinst; -err_free_masks: - free_cpumask_var(pinst->cpumask.pcpu); +err_free_v_mask: + free_cpumask_var(pinst->validate_cpumask); +err_free_cb_mask: free_cpumask_var(pinst->cpumask.cbcpu); +err_free_p_mask: + free_cpumask_var(pinst->cpumask.pcpu); err_free_serial_wq: destroy_workqueue(pinst->serial_wq); err_put_cpus: @@ -1039,7 +1048,7 @@ struct padata_shell *padata_alloc_shell(struct padata_instance *pinst) ps->pinst = pinst; cpus_read_lock(); - pd = padata_alloc_pd(ps); + pd = padata_alloc_pd(ps, -1); cpus_read_unlock(); if (!pd) @@ -1088,32 +1097,25 @@ void __init padata_init(void) int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online", - padata_cpu_online, NULL); + padata_cpu_online, padata_cpu_offline); if (ret < 0) goto err; hp_online = ret; - - ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead", - NULL, padata_cpu_dead); - if (ret < 0) - goto remove_online_state; #endif possible_cpus = num_possible_cpus(); padata_works = kmalloc_array(possible_cpus, sizeof(struct padata_work), GFP_KERNEL); if (!padata_works) - goto remove_dead_state; + goto remove_online_state; for (i = 0; i < possible_cpus; ++i) list_add(&padata_works[i].pw_list, &padata_free_works); return; -remove_dead_state: -#ifdef CONFIG_HOTPLUG_CPU - cpuhp_remove_multi_state(CPUHP_PADATA_DEAD); remove_online_state: +#ifdef CONFIG_HOTPLUG_CPU cpuhp_remove_multi_state(hp_online); err: #endif From db201e6fab1e8d2552b65ed78442bc5844650e38 Mon Sep 17 00:00:00 2001 From: Koichiro Den Date: Fri, 6 Mar 2026 00:10:50 +0900 Subject: [PATCH 0419/1518] PCI: dwc: rcar-gen4: Change EPC BAR alignment to 4K as per the documentation [ Upstream commit 13f55a7ca773c731a1e645934c1ae48577f48785 ] R-Car S4 Series (R8A779F[4-7]*) EP controller uses a 4K minimum iATU region size (CX_ATU_MIN_REGION_SIZE = 4K) as per R19UH0161EJ0130 Rev.1.30. Also, the controller itself can only be configured in the range 4 KB to 64 KB, so the current 1 MB alignment requirement is incorrect. Hence, change the alignment to the min size 4K as per the documentation. This also fixes needless unusability of BAR4 on this platform when the target address is fixed, such as for doorbell targets. Fixes: e311b3834dfa ("PCI: rcar-gen4: Add endpoint mode support") Signed-off-by: Koichiro Den [mani: commit log] Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Reviewed-by: Niklas Cassel Link: https://patch.msgid.link/20260305151050.1834007-1-den@valinux.co.jp Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-rcar-gen4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c index 80778917d2ddd..7e171526b1ded 100644 --- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c +++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c @@ -425,7 +425,7 @@ static const struct pci_epc_features rcar_gen4_pcie_epc_features = { .bar[BAR_3] = { .type = BAR_RESERVED, }, .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256 }, .bar[BAR_5] = { .type = BAR_RESERVED, }, - .align = SZ_1M, + .align = SZ_4K, }; static const struct pci_epc_features* From 0cd9d5878b3cc810869aaa92b74337c3edd36eaf Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 19 Feb 2026 18:18:28 -0500 Subject: [PATCH 0420/1518] drm/amdgpu/gfx10: look at the right prop for gfx queue priority MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 355d96cdec5c61fd83f7eb54f1a28e38809645d6 ] Look at hqd_queue_priority rather than hqd_pipe_priority. In practice, it didn't matter as both were always set for kernel queues, but that will change in the future. Fixes: b07d1d73b09e ("drm/amd/amdgpu: Enable high priority gfx queue") Reviewed-by：Jesse Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 003bcece715eb..234753a10361f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6751,7 +6751,7 @@ static void gfx_v10_0_gfx_mqd_set_priority(struct amdgpu_device *adev, /* set up default queue priority level * 0x0 = low priority, 0x1 = high priority */ - if (prop->hqd_pipe_priority == AMDGPU_GFX_PIPE_PRIO_HIGH) + if (prop->hqd_queue_priority == AMDGPU_GFX_QUEUE_PRIORITY_MAXIMUM) priority = 1; tmp = RREG32_SOC15(GC, 0, mmCP_GFX_HQD_QUEUE_PRIORITY); From eae672a7ec8a9ba4e06b8d94e88cb2361bc5e21c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 19 Feb 2026 18:20:27 -0500 Subject: [PATCH 0421/1518] drm/amdgpu/gfx11: look at the right prop for gfx queue priority MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f9a4e81bcbd04e6f967d851f9fe69d8bb3cc08b3 ] Look at hqd_queue_priority rather than hqd_pipe_priority. In practice, it didn't matter as both were always set for kernel queues, but that will change in the future. Fixes: 2e216b1e6ba2 ("drm/amdgpu/gfx11: handle priority setup for gfx pipe1") Reviewed-by：Jesse Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index feb56b6b31c9c..cf23b5da6dbbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4080,7 +4080,7 @@ static void gfx_v11_0_gfx_mqd_set_priority(struct amdgpu_device *adev, /* set up default queue priority level * 0x0 = low priority, 0x1 = high priority */ - if (prop->hqd_pipe_priority == AMDGPU_GFX_PIPE_PRIO_HIGH) + if (prop->hqd_queue_priority == AMDGPU_GFX_QUEUE_PRIORITY_MAXIMUM) priority = 1; tmp = regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT; From 3d0ef0567d21c635b9496b138e55343d95e72e10 Mon Sep 17 00:00:00 2001 From: Pei Xiao Date: Thu, 19 Mar 2026 11:06:41 +0800 Subject: [PATCH 0422/1518] spi: hisi-kunpeng: prevent infinite while() loop in hisi_spi_flush_fifo [ Upstream commit 9f61daf2c2debe9f5cf4e1a4471e56a89a6fe45a ] The hisi_spi_flush_fifo()'s inner while loop that lacks any timeout mechanism. Maybe the hardware never becomes empty, the loop will spin forever, causing the CPU to hang. Fix this by adding a inner_limit based on loops_per_jiffy. The inner loop now exits after approximately one jiffy if the FIFO remains non-empty, logs a ratelimited warning, and breaks out of the outer loop. Additionally, add a cpu_relax() inside the busy loop to improve power efficiency. Fixes: c770d8631e18 ("spi: Add HiSilicon SPI Controller Driver for Kunpeng SoCs") Signed-off-by: Pei Xiao Link: https://patch.msgid.link/d834ce28172886bfaeb9c8ca00cfd9bf1c65d5a1.1773889292.git.xiaopei01@kylinos.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-hisi-kunpeng.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index 80a1a15de0bc3..a38dcae6271ff 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -196,8 +196,18 @@ static void hisi_spi_flush_fifo(struct hisi_spi *hs) unsigned long limit = loops_per_jiffy << 1; do { - while (hisi_spi_rx_not_empty(hs)) + unsigned long inner_limit = loops_per_jiffy; + + while (hisi_spi_rx_not_empty(hs) && --inner_limit) { readl(hs->regs + HISI_SPI_DOUT); + cpu_relax(); + } + + if (!inner_limit) { + dev_warn_ratelimited(hs->dev, "RX FIFO flush timeout\n"); + break; + } + } while (hisi_spi_busy(hs) && limit--); } From 3a8d94405fd5d53b51ad48ee6078aec123cd83cd Mon Sep 17 00:00:00 2001 From: Alexandru Dadu Date: Mon, 23 Mar 2026 20:31:29 +0200 Subject: [PATCH 0423/1518] drm/imagination: Switch reset_reason fields from enum to u32 [ Upstream commit d2f83a6cd598bf413f1acf34153bd1d71023fbab ] Update the reset_reason fwif structure fields from enum to u32 to remove any ambiguity from the interface (enum is not a fixed size thus is unfit for the purpose of the data type). Fixes: a26f067feac1f ("drm/imagination: Add FWIF headers") Signed-off-by: Alexandru Dadu Reviewed-by: Matt Coster Link: https://patch.msgid.link/20260323-b4-firmware-context-reset-notification-handling-v3-2-1a66049a9a65@imgtec.com Signed-off-by: Matt Coster Signed-off-by: Sasha Levin --- drivers/gpu/drm/imagination/pvr_rogue_fwif.h | 8 ++++++-- drivers/gpu/drm/imagination/pvr_rogue_fwif_shared.h | 6 +++++- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/imagination/pvr_rogue_fwif.h b/drivers/gpu/drm/imagination/pvr_rogue_fwif.h index 172886be4c820..5d590c4c25663 100644 --- a/drivers/gpu/drm/imagination/pvr_rogue_fwif.h +++ b/drivers/gpu/drm/imagination/pvr_rogue_fwif.h @@ -1347,8 +1347,12 @@ struct rogue_fwif_fwccb_cmd_freelists_reconstruction_data { struct rogue_fwif_fwccb_cmd_context_reset_data { /* Context affected by the reset */ u32 server_common_context_id; - /* Reason for reset */ - enum rogue_context_reset_reason reset_reason; + /* + * Reason for reset + * The valid values for reset_reason are the ones from + * enum rogue_context_reset_reason + */ + u32 reset_reason; /* Data Master affected by the reset */ u32 dm; /* Job ref running at the time of reset */ diff --git a/drivers/gpu/drm/imagination/pvr_rogue_fwif_shared.h b/drivers/gpu/drm/imagination/pvr_rogue_fwif_shared.h index 6c09c15bf9bd8..f95acd5a1f8e8 100644 --- a/drivers/gpu/drm/imagination/pvr_rogue_fwif_shared.h +++ b/drivers/gpu/drm/imagination/pvr_rogue_fwif_shared.h @@ -249,7 +249,11 @@ enum rogue_context_reset_reason { }; struct rogue_context_reset_reason_data { - enum rogue_context_reset_reason reset_reason; + /* + * The valid values for reset_reason are the ones from + * enum rogue_context_reset_reason + */ + u32 reset_reason; u32 reset_ext_job_ref; }; From 86c8d5cdadd9d56d336a8bd38d44d95f752cc084 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Thu, 12 Mar 2026 17:36:34 -0700 Subject: [PATCH 0424/1518] iommu/tegra241-cmdqv: Set supports_cmd op in tegra241_vcmdq_hw_init() [ Upstream commit 803e41f36d227022ab9bbe780c82283fd4713b2e ] vintf->hyp_own is finalized in tegra241_vintf_hw_init(). On the other hand, tegra241_vcmdq_alloc_smmu_cmdq() is called via an init_structures callback, which is earlier than tegra241_vintf_hw_init(). This results in the supports_cmd op always being set to the guest function, although this doesn't break any functionality nor have some noticeable perf impact since non-invalidation commands are not issued in the perf sensitive context. Fix this by moving supports_cmd to tegra241_vcmdq_hw_init(). After this change, - For a guest kernel, this will be a status quo - For a host kernel, non-invalidation commands will be issued to VCMDQ(s) Fixes: a9d40285bdef ("iommu/tegra241-cmdqv: Limit CMDs for VCMDQs of a guest owned VINTF") Reported-by: Eric Auger Reported-by: Shameer Kolothum Closes: https://lore.kernel.org/qemu-devel/CH3PR12MB754836BEE54E39B30C7210C0AB44A@CH3PR12MB7548.namprd12.prod.outlook.com/ Signed-off-by: Nicolin Chen Reviewed-by: Eric Auger Tested-by: Shameer Kolothum Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 04cc7a9036e43..17591d8eb64b8 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -481,6 +481,10 @@ static int tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) /* Reset VCMDQ */ tegra241_vcmdq_hw_deinit(vcmdq); + /* vintf->hyp_own is a HW state finalized in tegra241_vintf_hw_init() */ + if (!vcmdq->vintf->hyp_own) + vcmdq->cmdq.supports_cmd = tegra241_guest_vcmdq_supports_cmd; + /* Configure and enable VCMDQ */ writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); @@ -641,9 +645,6 @@ static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq) q->q_base = q->base_dma & VCMDQ_ADDR; q->q_base |= FIELD_PREP(VCMDQ_LOG2SIZE, q->llq.max_n_shift); - if (!vcmdq->vintf->hyp_own) - cmdq->supports_cmd = tegra241_guest_vcmdq_supports_cmd; - return arm_smmu_cmdq_init(smmu, cmdq); } From 3441e4b70cf9b43bde900e349f64ab175f4cad91 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Thu, 12 Mar 2026 17:36:35 -0700 Subject: [PATCH 0425/1518] iommu/tegra241-cmdqv: Update uAPI to clarify HYP_OWN requirement [ Upstream commit 9dcef98dbee35b8ae784df04c041efffdd42a69c ] >From hardware implementation perspective, a guest tegra241-cmdqv hardware is different than the host hardware: - Host HW is backed by a VINTF (HYP_OWN=1) - Guest HW is backed by a VINTF (HYP_OWN=0) The kernel driver has an implementation requirement of the HYP_OWN bit in the VM. So, VMM must follow that to allow the same copy of Linux to work. Add this requirement to the uAPI, which is currently missing. Fixes: 4dc0d12474f9 ("iommu/tegra241-cmdqv: Add user-space use support") Signed-off-by: Nicolin Chen Reviewed-by: Eric Auger Reviewed-by: Jason Gunthorpe Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- include/uapi/linux/iommufd.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index c218c89e0e2eb..bdd20666d1eb1 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -1003,6 +1003,11 @@ struct iommu_fault_alloc { enum iommu_viommu_type { IOMMU_VIOMMU_TYPE_DEFAULT = 0, IOMMU_VIOMMU_TYPE_ARM_SMMUV3 = 1, + /* + * TEGRA241_CMDQV requirements (otherwise, VCMDQs will not work) + * - Kernel will allocate a VINTF (HYP_OWN=0) to back this VIOMMU. So, + * VMM must wire the HYP_OWN bit to 0 in guest VINTF_CONFIG register + */ IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV = 2, }; From c7d586c6348dfc14d0254528cc63efd5951393d8 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 28 Feb 2026 19:20:37 +0200 Subject: [PATCH 0426/1518] drm/msm: add missing MODULE_DEVICE_ID definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b21e85400ce763f2c6ad913e03fea5cadc323c13 ] The drm/msm module bundles several drivers, each of them having a separate OF match table, however only MDSS (subsystem), KMS devices and GPU have corresponding MODULE_DEVICE_ID tables. Add MODULE_DEVICE_ID to the display-related driver and to all other drivers in this module, simplifying userspace job. Fixes: 060530f1ea67 ("drm/msm: use componentised device support") Reported-by: Loïc Minier Patchwork: https://patchwork.freedesktop.org/patch/707960/ Link: https://lore.kernel.org/r/20260228-msm-device-id-v2-1-24b085919444@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dp/dp_display.c | 1 + drivers/gpu/drm/msm/dsi/dsi.c | 1 + drivers/gpu/drm/msm/dsi/phy/dsi_phy.c | 1 + drivers/gpu/drm/msm/hdmi/hdmi.c | 1 + drivers/gpu/drm/msm/hdmi/hdmi_phy.c | 1 + 5 files changed, 5 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index f247aad553975..c79e624c11758 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -201,6 +201,7 @@ static const struct of_device_id msm_dp_dt_match[] = { { .compatible = "qcom,x1e80100-dp", .data = &msm_dp_desc_x1e80100 }, {} }; +MODULE_DEVICE_TABLE(of, msm_dp_dt_match); static struct msm_dp_display_private *dev_get_dp_display_private(struct device *dev) { diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index d8bb40ef820e2..3c9f01ed62713 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -198,6 +198,7 @@ static const struct of_device_id dt_match[] = { { .compatible = "qcom,dsi-ctrl-6g-qcm2290" }, {} }; +MODULE_DEVICE_TABLE(of, dt_match); static const struct dev_pm_ops dsi_pm_ops = { SET_RUNTIME_PM_OPS(msm_dsi_runtime_suspend, msm_dsi_runtime_resume, NULL) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 4ea681130dbaf..5d627df687700 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -580,6 +580,7 @@ static const struct of_device_id dsi_phy_dt_match[] = { #endif {} }; +MODULE_DEVICE_TABLE(of, dsi_phy_dt_match); /* * Currently, we only support one SoC for each PHY type. When we have multiple diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 5afac09c0d334..d5ef5089c9e9c 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -441,6 +441,7 @@ static const struct of_device_id msm_hdmi_dt_match[] = { { .compatible = "qcom,hdmi-tx-8660", .data = &hdmi_tx_8960_config }, {} }; +MODULE_DEVICE_TABLE(of, msm_hdmi_dt_match); static struct platform_driver msm_hdmi_driver = { .probe = msm_hdmi_dev_probe, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c index 667573f1db7c6..f726555bb6810 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c @@ -204,6 +204,7 @@ static const struct of_device_id msm_hdmi_phy_dt_match[] = { .data = &msm_hdmi_phy_8998_cfg }, {} }; +MODULE_DEVICE_TABLE(of, msm_hdmi_phy_dt_match); static struct platform_driver msm_hdmi_phy_platform_driver = { .probe = msm_hdmi_phy_probe, From 0f7dd5839cfabaf9c007fb718ec66e907a473c93 Mon Sep 17 00:00:00 2001 From: Yuanjie Yang Date: Mon, 9 Mar 2026 14:37:20 +0800 Subject: [PATCH 0427/1518] drm/msm/dpu: fix mismatch between power and frequency [ Upstream commit bc1dccc518cc5ab5140fba06c27e7188e0ed342b ] During DPU runtime suspend, calling dev_pm_opp_set_rate(dev, 0) drops the MMCX rail to MIN_SVS while the core clock frequency remains at its original (highest) rate. When runtime resume re-enables the clock, this may result in a mismatch between the rail voltage and the clock rate. For example, in the DPU bind path, the sequence could be: cpu0: dev_sync_state -> rpmhpd_sync_state cpu1: dpu_kms_hw_init timeline 0 ------------------------------------------------> t After rpmhpd_sync_state, the voltage performance is no longer guaranteed to stay at the highest level. During dpu_kms_hw_init, calling dev_pm_opp_set_rate(dev, 0) drops the voltage, causing the MMCX rail to fall to MIN_SVS while the core clock is still at its maximum frequency. When the power is re-enabled, only the clock is enabled, leading to a situation where the MMCX rail is at MIN_SVS but the core clock is at its highest rate. In this state, the rail cannot sustain the clock rate, which may cause instability or system crash. Remove the call to dev_pm_opp_set_rate(dev, 0) from dpu_runtime_suspend to ensure the correct vote is restored when DPU resumes. Fixes: b0530eb11913 ("drm/msm/dpu: Use OPP API to set clk/perf state") Signed-off-by: Yuanjie Yang Reviewed-by: Konrad Dybcio Patchwork: https://patchwork.freedesktop.org/patch/710077/ Link: https://lore.kernel.org/r/20260309063720.13572-1-yuanjie.yang@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 4e5a8ecd31f75..bc1a016471411 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1461,8 +1461,6 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev) struct msm_drm_private *priv = platform_get_drvdata(pdev); struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); - /* Drop the performance state vote */ - dev_pm_opp_set_rate(dev, 0); clk_bulk_disable_unprepare(dpu_kms->num_clocks, dpu_kms->clocks); for (i = 0; i < dpu_kms->num_paths; i++) From acde37cb798d257db5debf1f2fe4ef524e962dda Mon Sep 17 00:00:00 2001 From: Pengyu Luo Date: Mon, 9 Mar 2026 18:02:53 +0800 Subject: [PATCH 0428/1518] drm/msm/dsi: add the missing parameter description [ Upstream commit 958adefc4c0fddee3b12269da5dd7cb49bac953f ] Add a description for is_bonded_dsi in dsi_adjust_pclk_for_compression to match the existing kernel-doc comment. Fixes: e4eb11b34d6c ("drm/msm/dsi: fix pclk rate calculation for bonded dsi") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202603080314.XeqyRZ7A-lkp@intel.com/ Signed-off-by: Pengyu Luo Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/710112/ Link: https://lore.kernel.org/r/20260309100254.877801-1-mitltlatltl@gmail.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dsi/dsi_host.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index db6da99375a18..6cb634590e7a7 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -569,6 +569,7 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host) * dsi_adjust_pclk_for_compression() - Adjust the pclk rate for compression case * @mode: The selected mode for the DSI output * @dsc: DRM DSC configuration for this DSI output + * @is_bonded_dsi: True if two DSI controllers are bonded * * Adjust the pclk rate by calculating a new hdisplay proportional to * the compression ratio such that: From 94e021272c455c9c710743256b5fe8fe9457f176 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 17 Mar 2026 17:30:05 +0200 Subject: [PATCH 0429/1518] drm/msm/dpu: don't try using 2 LMs if only one DSC is available [ Upstream commit b9699dd862760e642807a2bc226e4d127e35dcb7 ] Current topology code will try using 2 LMs with just one DSC, which breaks cases like SC7280 / Fairphone5. Forbid using 2 LMs split in such a case. Fixes: 1ce69c265a53 ("drm/msm/dpu: move resource allocation to CRTC") Reported-by: Luca Weiss Closes: https://lore.kernel.org/r/DH1IKLU0YZYU.2SW4WYO7H3H4R@fairphone.com/ Tested-by: Luca Weiss # qcm6490-fairphone-fp5 Patchwork: https://patchwork.freedesktop.org/patch/712386/ Link: https://lore.kernel.org/r/20260317-fix-3d-dsc-v1-1-88b54f62f659@oss.qualcomm.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 2f8156051d9b0..6f5d90b7ba7d4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1354,7 +1354,8 @@ static struct msm_display_topology dpu_crtc_get_topology( topology.num_lm = 2; else if (topology.num_dsc == 2) topology.num_lm = 2; - else if (dpu_kms->catalog->caps->has_3d_merge) + else if (dpu_kms->catalog->caps->has_3d_merge && + topology.num_dsc == 0) topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; else topology.num_lm = 1; From e82ef4ef320c56d2a12443eb796253427a5b67cb Mon Sep 17 00:00:00 2001 From: Pengyu Luo Date: Sat, 7 Mar 2026 19:12:48 +0800 Subject: [PATCH 0430/1518] drm/msm/dsi: fix bits_per_pclk [ Upstream commit 2d51cfb77daa30b10bc68c403f8ace35783d2922 ] mipi_dsi_pixel_format_to_bpp return dst bpp not src bpp, dst bpp may not be the uncompressed data size. use src bpc * 3 to get src bpp, this aligns with pclk rate calculation. Fixes: ac47870fd795 ("drm/msm/dsi: fix hdisplay calculation when programming dsi registers") Signed-off-by: Pengyu Luo Patchwork: https://patchwork.freedesktop.org/patch/709916/ Link: https://lore.kernel.org/r/20260307111250.105772-1-mitltlatltl@gmail.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dsi/dsi_host.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 6cb634590e7a7..3efcc3f6c381c 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1048,7 +1048,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) */ h_total -= hdisplay; if (wide_bus_enabled) - bits_per_pclk = mipi_dsi_pixel_format_to_bpp(msm_host->format); + bits_per_pclk = dsc->bits_per_component * 3; else bits_per_pclk = 24; From a303f8863c9766d0f3fadd5874286fee6992644d Mon Sep 17 00:00:00 2001 From: Pengyu Luo Date: Sat, 7 Mar 2026 19:12:49 +0800 Subject: [PATCH 0431/1518] drm/msm/dsi: fix hdisplay calculation for CMD mode panel [ Upstream commit 82159db4371f5cef56444ebd0b8f96e2a6d709ff ] Commit ac47870fd795 ("drm/msm/dsi: fix hdisplay calculation when programming dsi registers") incorrecly broke hdisplay calculation for CMD mode by specifying incorrect number of bytes per transfer, fix it. Fixes: ac47870fd795 ("drm/msm/dsi: fix hdisplay calculation when programming dsi registers") Signed-off-by: Pengyu Luo Patchwork: https://patchwork.freedesktop.org/patch/709917/ Link: https://lore.kernel.org/r/20260307111250.105772-2-mitltlatltl@gmail.com [DB: fixed commit message] Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dsi/dsi_host.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 3efcc3f6c381c..1c0841a1c1013 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1034,8 +1034,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) /* * DPU sends 3 bytes per pclk cycle to DSI. If widebus is * enabled, MDP always sends out 48-bit compressed data per - * pclk and on average, DSI consumes an amount of compressed - * data equivalent to the uncompressed pixel depth per pclk. + * pclk and on average, for video mode, DSI consumes only an + * amount of compressed data equivalent to the uncompressed + * pixel depth per pclk. * * Calculate the number of pclks needed to transmit one line of * the compressed data. @@ -1047,10 +1048,14 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) * unused anyway. */ h_total -= hdisplay; - if (wide_bus_enabled) - bits_per_pclk = dsc->bits_per_component * 3; - else + if (wide_bus_enabled) { + if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) + bits_per_pclk = dsc->bits_per_component * 3; + else + bits_per_pclk = 48; + } else { bits_per_pclk = 24; + } hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc) * 8, bits_per_pclk); From 9c47a36ceaf043e07c872597069826916e20e3ef Mon Sep 17 00:00:00 2001 From: Alexander Koskovich Date: Tue, 24 Mar 2026 11:48:27 +0000 Subject: [PATCH 0432/1518] drm/msm/dsi: rename MSM8998 DSI version from V2_2_0 to V2_0_0 [ Upstream commit 913a709dea0eff9c7b2e9470f8c8594b9a0114ab ] The MSM8998 DSI controller is v2.0.0 as stated in commit 7b8c9e203039 ("drm/msm/dsi: Add support for MSM8998 DSI controller"). The value was always correct just the name was wrong. Rename and reorder to maintain version sorting. Fixes: 7b8c9e203039 ("drm/msm/dsi: Add support for MSM8998 DSI controller") Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Signed-off-by: Alexander Koskovich Patchwork: https://patchwork.freedesktop.org/patch/713717/ Link: https://lore.kernel.org/r/20260324-dsi-rgb101010-support-v5-3-ff6afc904115@pm.me Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dsi/dsi_cfg.c | 4 ++-- drivers/gpu/drm/msm/dsi/dsi_cfg.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index fed8e9b67011c..cdcf0cab7aaa2 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -306,10 +306,10 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = { &msm8996_dsi_cfg, &msm_dsi_6g_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_2, &msm8976_dsi_cfg, &msm_dsi_6g_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_0_0, + &msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_1_0, &sdm660_dsi_cfg, &msm_dsi_6g_v2_host_ops}, - {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_0, - &msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_3_0, diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index 38f303f2ed04c..4d760ffd8b4a8 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -19,8 +19,8 @@ #define MSM_DSI_6G_VER_MINOR_V1_3_1 0x10030001 #define MSM_DSI_6G_VER_MINOR_V1_4_1 0x10040001 #define MSM_DSI_6G_VER_MINOR_V1_4_2 0x10040002 +#define MSM_DSI_6G_VER_MINOR_V2_0_0 0x20000000 #define MSM_DSI_6G_VER_MINOR_V2_1_0 0x20010000 -#define MSM_DSI_6G_VER_MINOR_V2_2_0 0x20000000 #define MSM_DSI_6G_VER_MINOR_V2_2_1 0x20020001 #define MSM_DSI_6G_VER_MINOR_V2_3_0 0x20030000 #define MSM_DSI_6G_VER_MINOR_V2_3_1 0x20030001 From 131e01ba249f28f90e8ec1db1c7187f33868381d Mon Sep 17 00:00:00 2001 From: Alexey Charkov Date: Wed, 18 Mar 2026 18:50:25 +0400 Subject: [PATCH 0433/1518] ASoC: rockchip: rockchip_sai: Set slot width for non-TDM mode [ Upstream commit 8a6391ec669366cbe7bde92b468c561e8b309fd6 ] Currently the slot width in non-TDM mode is always kept at the POR value of 32 bits, regardless of the sample width, which doesn't work well for some codecs such as NAU8822. Set the slot width according to the sample width in non-TDM mode, which is what other CPU DAI drivers do. Tested on the following RK3576 configurations: - SAI2 + NAU8822 (codec as the clock master), custom board - SAI1 + ES8388 (codec as the clock master), RK3576 EVB1 - SAI2 + RT5616 (SAI as the clock master), FriendlyElec NanoPi M5 NAU8822 didn't work prior to this patch but works after the patch. Other two configurations work both before and after the patch. Fixes: cc78d1eaabad ("ASoC: rockchip: add Serial Audio Interface (SAI) driver") Signed-off-by: Alexey Charkov Tested-by: Nicolas Frattaroli Link: https://patch.msgid.link/20260318-sai-slot-width-v1-1-1f68186f71e3@flipper.net Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/rockchip/rockchip_sai.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/rockchip/rockchip_sai.c b/sound/soc/rockchip/rockchip_sai.c index 6695349ee561e..b38c2cb81f807 100644 --- a/sound/soc/rockchip/rockchip_sai.c +++ b/sound/soc/rockchip/rockchip_sai.c @@ -628,6 +628,10 @@ static int rockchip_sai_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(sai->regmap, reg, SAI_XCR_VDW_MASK | SAI_XCR_CSR_MASK, val); + if (!sai->is_tdm) + regmap_update_bits(sai->regmap, reg, SAI_XCR_SBW_MASK, + SAI_XCR_SBW(params_physical_width(params))); + regmap_read(sai->regmap, reg, &val); slot_width = SAI_XCR_SBW_V(val); From 31b2d7be7540cec5c5fc7dbb1dbeaa61d5c6b739 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 23 Mar 2026 03:21:49 +0200 Subject: [PATCH 0434/1518] drm/panel: sharp-ls043t1le01: make use of prepare_prev_first [ Upstream commit c222177d7c7e1b2e0433d9e47ec2da7015345d50 ] The DSI link must be powered up to let panel driver to talk to the panel during prepare() callback execution. Set the prepare_prev_first flag to guarantee this. Fixes: 9e15123eca79 ("drm/msm/dsi: Stop unconditionally powering up DSI hosts at modeset") Signed-off-by: Dmitry Baryshkov Reviewed-by: Douglas Anderson Signed-off-by: Neil Armstrong Link: https://patch.msgid.link/20260323-panel-fix-v1-1-9f12b09161e8@oss.qualcomm.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c index 36abfa2e65e96..dd1eaba23ad3c 100644 --- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c +++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c @@ -201,6 +201,7 @@ static int sharp_nt_panel_add(struct sharp_nt_panel *sharp_nt) drm_panel_init(&sharp_nt->base, &sharp_nt->dsi->dev, &sharp_nt_panel_funcs, DRM_MODE_CONNECTOR_DSI); + sharp_nt->base.prepare_prev_first = true; ret = drm_panel_of_backlight(&sharp_nt->base); if (ret) From cd3938c12bdac9f23a9d1fcdb1176504c47e39bc Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Tue, 17 Feb 2026 16:25:26 +0200 Subject: [PATCH 0435/1518] drm/panel: simple: Correct G190EAN01 prepare timing [ Upstream commit f1080f82570b797598c1ba7e9c800ae9e94aafc6 ] The prepare timing specified by the G190EAN01 datasheet should be between 30 and 50 ms. Considering it might take some time for the LVDS encoder to enable the signal, we should only wait the min. required time in the panel driver and not the max. allowed time. Fixes: 2f7b832fc992 ("drm/panel: simple: Add support for AUO G190EAN01 panel") Signed-off-by: Sebastian Reichel Signed-off-by: Ian Ray Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patch.msgid.link/20260217142528.68613-1-ian.ray@gehealthcare.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-simple.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 271f933991937..ef1c4b9299ee4 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1295,7 +1295,7 @@ static const struct panel_desc auo_g190ean01 = { .height = 301, }, .delay = { - .prepare = 50, + .prepare = 30, .enable = 200, .disable = 110, .unprepare = 1000, From f176c47683bf6365e2f6d580d557fae49169a703 Mon Sep 17 00:00:00 2001 From: Krishna Chaitanya Chundru Date: Sat, 14 Mar 2026 07:26:34 +0530 Subject: [PATCH 0436/1518] PCI: qcom: Advertise Hotplug Slot Capability with no Command Completion support [ Upstream commit 33a76fc3c3e61386524479b99f35423bd3d9a895 ] Qcom PCIe Root Ports advertise hotplug capability in hardware, but do not support hotplug command completion. As a result, the hotplug commands issued by the pciehp driver never gets completion notification, leading to repeated timeout warnings and multi-second delays during boot and suspend/resume. Commit a54db86ddc153 ("PCI: qcom: Do not advertise hotplug capability for IPs v2.7.0 and v1.9.0") mistakenly assumed that the Root Ports doesn't support Hotplug due to timeouts and disabled the Hotplug functionality altogether. But the Root Ports does support reporting Hotplug events like DL_Up/Down events. So to fix the command completion timeout issues, just set the No Command Completed Support (NCCS) bit and enable Hotplug in Slot Capability field back. Fixes: a54db86ddc153 ("PCI: qcom: Do not advertise hotplug capability for IPs v2.7.0 and v1.9.0") Signed-off-by: Krishna Chaitanya Chundru [mani: renamed function, commit log and added comment] Signed-off-by: Manivannan Sadhasivam Tested-by: Konrad Dybcio # Hamoa CRD, tunneled link Reviewed-by: Konrad Dybcio Link: https://patch.msgid.link/20260314-hotplug-v1-1-96ac87d93867@oss.qualcomm.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-qcom.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 789cc0e3c10da..43555ad9e5dcf 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -341,15 +341,20 @@ static void qcom_pcie_clear_aspm_l0s(struct dw_pcie *pci) dw_pcie_dbi_ro_wr_dis(pci); } -static void qcom_pcie_clear_hpc(struct dw_pcie *pci) +static void qcom_pcie_set_slot_nccs(struct dw_pcie *pci) { u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); u32 val; dw_pcie_dbi_ro_wr_en(pci); + /* + * Qcom PCIe Root Ports do not support generating command completion + * notifications for the Hot-Plug commands. So set the NCCS field to + * avoid waiting for the completions. + */ val = readl(pci->dbi_base + offset + PCI_EXP_SLTCAP); - val &= ~PCI_EXP_SLTCAP_HPC; + val |= PCI_EXP_SLTCAP_NCCS; writel(val, pci->dbi_base + offset + PCI_EXP_SLTCAP); dw_pcie_dbi_ro_wr_dis(pci); @@ -549,7 +554,7 @@ static int qcom_pcie_post_init_2_1_0(struct qcom_pcie *pcie) writel(CFG_BRIDGE_SB_INIT, pci->dbi_base + AXI_MSTR_RESP_COMP_CTRL1); - qcom_pcie_clear_hpc(pcie->pci); + qcom_pcie_set_slot_nccs(pcie->pci); return 0; } @@ -629,7 +634,7 @@ static int qcom_pcie_post_init_1_0_0(struct qcom_pcie *pcie) writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT); } - qcom_pcie_clear_hpc(pcie->pci); + qcom_pcie_set_slot_nccs(pcie->pci); return 0; } @@ -722,7 +727,7 @@ static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie) val |= EN; writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); - qcom_pcie_clear_hpc(pcie->pci); + qcom_pcie_set_slot_nccs(pcie->pci); return 0; } @@ -1028,7 +1033,7 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) writel(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN, pcie->parf + PARF_NO_SNOOP_OVERRIDE); - qcom_pcie_clear_hpc(pcie->pci); + qcom_pcie_set_slot_nccs(pcie->pci); return 0; } From 34678c9788887b65d48ca10530581ca7440402e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 19 Dec 2025 19:40:21 +0200 Subject: [PATCH 0437/1518] PCI: Use res_to_dev_res() in reassign_resources_sorted() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4bee4fc0f4ee1086e498f9d197352237a0232598 ] reassign_resources_sorted() contains a search loop for a particular resource in the head list. res_to_dev_res() already implements the same search so use it instead. Drop unused found_match and dev_res variables. Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20251219174036.16738-9-ilpo.jarvinen@linux.intel.com Stable-dep-of: 1ee4716a5a28 ("PCI: Fix premature removal from realloc_head list during resource assignment") Signed-off-by: Sasha Levin --- drivers/pci/setup-bus.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index c2d640164f697..3ea6f3e726a8c 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -417,7 +417,6 @@ static void reassign_resources_sorted(struct list_head *realloc_head, struct list_head *head) { struct pci_dev_resource *add_res, *tmp; - struct pci_dev_resource *dev_res; struct pci_dev *dev; struct resource *res; const char *res_name; @@ -425,8 +424,6 @@ static void reassign_resources_sorted(struct list_head *realloc_head, int idx; list_for_each_entry_safe(add_res, tmp, realloc_head, list) { - bool found_match = false; - res = add_res->res; dev = add_res->dev; idx = pci_resource_num(dev, res); @@ -440,13 +437,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head, goto out; /* Skip this resource if not found in head list */ - list_for_each_entry(dev_res, head, list) { - if (dev_res->res == res) { - found_match = true; - break; - } - } - if (!found_match) /* Just skip */ + if (!res_to_dev_res(head, res)) continue; res_name = pci_resource_name(dev, idx); From 2d18cf09f2b07e116b53532fe20dc7020b01525b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 13 Mar 2026 10:45:50 +0200 Subject: [PATCH 0438/1518] PCI: Fix premature removal from realloc_head list during resource assignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1ee4716a5a28eaef81ae1f280d983258bee49623 ] reassign_resources_sorted() checks for two things: a) Resource assignment failures for mandatory resources by checking if the resource remains unassigned, which are known to always repeat, and does not attempt to assign them again. b) That resource is not among the ones being processed/assigned at this stage, leading to skip processing such resources in reassign_resources_sorted() as well (resource assignment progresses one PCI hierarchy level at a time). The problem here is that a) is checked before b), but b) also implies the resource is not being assigned yet, making also a) true. As a) only skips resource assignment but still removes the resource from realloc_head, the later stages that would need to process the information in realloc_head cannot obtain the optional size information anymore. This leads to considering only non-optional part for bridge windows deeper in the PCI hierarchy. This problem has been observed during rescan (add_size is not considered while attempting assignment for 0000:e2:00.0 indicating the corresponding entry was removed from realloc_head while processing resource assignments for 0000:e1): pci_bus 0000:e1: scanning bus ... pci 0000:e3:01.0: bridge window [mem 0x800000000-0x1000ffffff 64bit pref] to [bus e4] add_size 60c000000 add_align 800000000 pci 0000:e3:01.0: bridge window [mem 0x00100000-0x000fffff] to [bus e4] add_size 200000 add_align 200000 pci 0000:e3:02.0: disabling bridge window [mem 0x00000000-0x000fffff 64bit pref] to [bus e5] (unused) pci 0000:e2:00.0: bridge window [mem 0x800000000-0x1000ffffff 64bit pref] to [bus e3-e5] add_size 60c000000 add_align 800000000 pci 0000:e2:00.0: bridge window [mem 0x00100000-0x001fffff] to [bus e3-e5] add_size 200000 add_align 200000 pcieport 0000:e1:02.0: bridge window [io size 0x2000]: can't assign; no space pcieport 0000:e1:02.0: bridge window [io size 0x2000]: failed to assign pcieport 0000:e1:02.0: bridge window [io 0x1000-0x2fff]: resource restored pcieport 0000:e1:02.0: bridge window [io 0x1000-0x2fff]: resource restored pcieport 0000:e1:02.0: bridge window [io size 0x2000]: can't assign; no space pcieport 0000:e1:02.0: bridge window [io size 0x2000]: failed to assign pci 0000:e2:00.0: bridge window [mem 0x28f000000000-0x28f800ffffff 64bit pref]: assigned Fixes: 96336ec70264 ("PCI: Perform reset_resource() and build fail list in sync") Reported-by: Peter Nisbet Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Tested-by: Peter Nisbet Link: https://patch.msgid.link/20260313084551.1934-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin --- drivers/pci/setup-bus.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 3ea6f3e726a8c..29ad8d8718974 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -428,6 +428,10 @@ static void reassign_resources_sorted(struct list_head *realloc_head, dev = add_res->dev; idx = pci_resource_num(dev, res); + /* Skip this resource if not found in head list */ + if (!res_to_dev_res(head, res)) + continue; + /* * Skip resource that failed the earlier assignment and is * not optional as it would just fail again. @@ -436,10 +440,6 @@ static void reassign_resources_sorted(struct list_head *realloc_head, !pci_resource_is_optional(dev, idx)) goto out; - /* Skip this resource if not found in head list */ - if (!res_to_dev_res(head, res)) - continue; - res_name = pci_resource_name(dev, idx); add_size = add_res->add_size; align = add_res->min_align; From b375c3c7209cc59e40e97998aa9bc768369cca0e Mon Sep 17 00:00:00 2001 From: Wenkai Lin Date: Sat, 21 Mar 2026 15:00:38 +0800 Subject: [PATCH 0439/1518] crypto: hisilicon/sec2 - prevent req used-after-free for sec [ Upstream commit 67b53a660e6bf0da2fa8d8872e897a14d8059eaf ] During packet transmission, if the system is under heavy load, the hardware might complete processing the packet and free the request memory (req) before the transmission function finishes. If the software subsequently accesses this req, a use-after-free error will occur. The qp_ctx memory exists throughout the packet sending process, so replace the req with the qp_ctx. Fixes: f0ae287c5045 ("crypto: hisilicon/sec2 - implement full backlog mode for sec") Signed-off-by: Wenkai Lin Signed-off-by: Chenghai Huang Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/hisilicon/sec2/sec_crypto.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index c462b58d30343..2d0b248c59ebd 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -230,7 +230,7 @@ static int qp_send_message(struct sec_req *req) spin_unlock_bh(&qp_ctx->req_lock); - atomic64_inc(&req->ctx->sec->debug.dfx.send_cnt); + atomic64_inc(&qp_ctx->ctx->sec->debug.dfx.send_cnt); return -EINPROGRESS; } From ccd4c3e5c9078249d9448519fe8cf042821005a8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Tue, 24 Mar 2026 18:56:33 +0200 Subject: [PATCH 0440/1518] PCI: Fix alignment calculation for resource size larger than align MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8cb081667377709f4924ab6b3a88a0d7a761fe91 ] The commit bc75c8e50711 ("PCI: Rewrite bridge window head alignment function") did not use if (r_size <= align) check from pbus_size_mem() for the new head alignment bookkeeping structure (aligns2[]). In some configurations, this can result in producing a gap into the bridge window which the resource larger than its alignment cannot fill. The old alignment calculation algorithm was removed by the subsequent commit 3958bf16e2fe ("PCI: Stop over-estimating bridge window size") which renamed the aligns2[] array leaving only aligns[] array. Add the if (r_size <= align) check back to avoid this problem. Fixes: bc75c8e50711 ("PCI: Rewrite bridge window head alignment function") Reported-by: Guenter Roeck Closes: https://lore.kernel.org/all/b05a6f14-979d-42c9-924c-d8408cb12ae7@roeck-us.net/ Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Tested-by: Xifer Link: https://patch.msgid.link/20260324165633.4583-11-ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin --- drivers/pci/setup-bus.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 29ad8d8718974..522e25d725bad 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1342,7 +1342,14 @@ static void pbus_size_mem(struct pci_bus *bus, unsigned long type, } size += max(r_size, align); - aligns[order] += align; + /* + * If resource's size is larger than its alignment, + * some configurations result in an unwanted gap in + * the head space that the larger resource cannot + * fill. + */ + if (r_size <= align) + aligns[order] += align; if (order > max_order) max_order = order; From e3fae61f4799d7cc84a815c5d60a67431ec273cd Mon Sep 17 00:00:00 2001 From: Yaxing Guo Date: Fri, 30 Jan 2026 14:54:20 +0800 Subject: [PATCH 0441/1518] iommu/riscv: Skip IRQ count check when using MSI interrupts [ Upstream commit 7217cee35aadbb07e12673bcf1dcf729e1b2f6c9 ] In RISC-V IOMMU platform devices that use MSI interrupts (indicated by the presence of 'msi-parent' in the device tree), there are no wired interrupt lines, so calling platform_get_irq_count() returns 0 or -ENXIO, causing the driver to fail during probe. However, MSI interrupts are allocated dynamically via the MSI subsystem and do not appear in the device tree 'interrupts' property. Therefore, the driver should not require a non-zero IRQ count when 'msi-parent' is present. This patch fixes the bug where probe fails when using MSI interrupts (which do not have an 'interrupts' property in the device tree).. Fixes: ("iommu/riscv: Add support for platform msi") Signed-off-by: Yaxing Guo Reviewed-by: Andrew Jones Signed-off-by: Joerg Roedel Stable-dep-of: 553a127cb665 ("iommu/riscv: Fix signedness bug") Signed-off-by: Sasha Levin --- drivers/iommu/riscv/iommu-platform.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/riscv/iommu-platform.c b/drivers/iommu/riscv/iommu-platform.c index 83a28c83f9914..8f15b06e84997 100644 --- a/drivers/iommu/riscv/iommu-platform.c +++ b/drivers/iommu/riscv/iommu-platform.c @@ -68,12 +68,7 @@ static int riscv_iommu_platform_probe(struct platform_device *pdev) iommu->caps = riscv_iommu_readq(iommu, RISCV_IOMMU_REG_CAPABILITIES); iommu->fctl = riscv_iommu_readl(iommu, RISCV_IOMMU_REG_FCTL); - iommu->irqs_count = platform_irq_count(pdev); - if (iommu->irqs_count <= 0) - return dev_err_probe(dev, -ENODEV, - "no IRQ resources provided\n"); - if (iommu->irqs_count > RISCV_IOMMU_INTR_COUNT) - iommu->irqs_count = RISCV_IOMMU_INTR_COUNT; + iommu->irqs_count = RISCV_IOMMU_INTR_COUNT; igs = FIELD_GET(RISCV_IOMMU_CAPABILITIES_IGS, iommu->caps); switch (igs) { @@ -120,6 +115,13 @@ static int riscv_iommu_platform_probe(struct platform_device *pdev) fallthrough; case RISCV_IOMMU_CAPABILITIES_IGS_WSI: + iommu->irqs_count = platform_irq_count(pdev); + if (iommu->irqs_count <= 0) + return dev_err_probe(dev, -ENODEV, + "no IRQ resources provided\n"); + if (iommu->irqs_count > RISCV_IOMMU_INTR_COUNT) + iommu->irqs_count = RISCV_IOMMU_INTR_COUNT; + for (vec = 0; vec < iommu->irqs_count; vec++) iommu->irqs[vec] = platform_get_irq(pdev, vec); From 3c349995e51edfa3d1d12cf341b5ae3bb98119d7 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Thu, 19 Mar 2026 13:26:44 -0500 Subject: [PATCH 0442/1518] iommu/riscv: Fix signedness bug [ Upstream commit 553a127cb66523089bc10eb54640205495f4bb5b ] The function platform_irq_count() returns negative error codes and iommu->irqs_count is an unsigned integer, so the check (iommu->irqs_count <= 0) is always impossible. Make the return value of platform_irq_count() be assigned to ret, check for error, and then assign iommu->irqs_count to ret. Detected by Smatch: drivers/iommu/riscv/iommu-platform.c:119 riscv_iommu_platform_probe() warn: 'iommu->irqs_count' unsigned <= 0 Signed-off-by: Ethan Tidmore Fixes: 5c0ebbd3c6c6 ("iommu/riscv: Add RISC-V IOMMU platform device driver") Reviewed-by: Andrew Jones Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/riscv/iommu-platform.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/riscv/iommu-platform.c b/drivers/iommu/riscv/iommu-platform.c index 8f15b06e84997..399ba8fe1b3e5 100644 --- a/drivers/iommu/riscv/iommu-platform.c +++ b/drivers/iommu/riscv/iommu-platform.c @@ -115,10 +115,13 @@ static int riscv_iommu_platform_probe(struct platform_device *pdev) fallthrough; case RISCV_IOMMU_CAPABILITIES_IGS_WSI: - iommu->irqs_count = platform_irq_count(pdev); - if (iommu->irqs_count <= 0) + ret = platform_irq_count(pdev); + if (ret <= 0) return dev_err_probe(dev, -ENODEV, "no IRQ resources provided\n"); + + iommu->irqs_count = ret; + if (iommu->irqs_count > RISCV_IOMMU_INTR_COUNT) iommu->irqs_count = RISCV_IOMMU_INTR_COUNT; From edfa91bb652e2d03ccc8caa3b17af01ddce23538 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Wed, 25 Mar 2026 02:24:04 -0300 Subject: [PATCH 0443/1518] ALSA: core: Validate compress device numbers without dynamic minors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 796e119e9b14763be905ad0d023c71a14bc2e931 ] Without CONFIG_SND_DYNAMIC_MINORS, ALSA reserves only two fixed minors for compress devices on each card: comprD0 and comprD1. snd_find_free_minor() currently computes the compress minor as type + dev without validating dev first, so device numbers greater than 1 spill into the HWDEP minor range instead of failing registration. ASoC passes rtd->id to snd_compress_new(), so this can happen on real non-dynamic-minor builds. Add a dedicated fixed-minor check for SNDRV_DEVICE_TYPE_COMPRESS in snd_find_free_minor() and reject out-of-range device numbers with -EINVAL before constructing the minor. Also remove the stale TODO in compress_offload.c that still claims multiple compress nodes are missing. Fixes: 3eafc959b32f ("ALSA: core: add support for compressed devices") Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260325-alsa-compress-static-minors-v1-1-0628573bee1c@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/core/compress_offload.c | 7 ------- sound/core/sound.c | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index da514fef45bca..2181442e3a1da 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -41,13 +41,6 @@ #define COMPR_CODEC_CAPS_OVERFLOW #endif -/* TODO: - * - add substream support for multiple devices in case of - * SND_DYNAMIC_MINORS is not used - * - Multiple node representation - * driver should be able to register multiple nodes - */ - struct snd_compr_file { unsigned long caps; struct snd_compr_stream stream; diff --git a/sound/core/sound.c b/sound/core/sound.c index 6531a67f13b3e..7980b60f4ba0b 100644 --- a/sound/core/sound.c +++ b/sound/core/sound.c @@ -216,9 +216,16 @@ static int snd_find_free_minor(int type, struct snd_card *card, int dev) case SNDRV_DEVICE_TYPE_RAWMIDI: case SNDRV_DEVICE_TYPE_PCM_PLAYBACK: case SNDRV_DEVICE_TYPE_PCM_CAPTURE: + if (snd_BUG_ON(!card)) + return -EINVAL; + minor = SNDRV_MINOR(card->number, type + dev); + break; case SNDRV_DEVICE_TYPE_COMPRESS: if (snd_BUG_ON(!card)) return -EINVAL; + if (dev < 0 || + dev >= SNDRV_MINOR_HWDEP - SNDRV_MINOR_COMPRESS) + return -EINVAL; minor = SNDRV_MINOR(card->number, type + dev); break; default: From 67e582c86ab17b40f97e17fd5c06ac0cb6e693a8 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Mon, 30 Mar 2026 12:50:27 +0530 Subject: [PATCH 0444/1518] ASoC: amd: acp: update dmic_num logic for acp pdm dmic [ Upstream commit 5902e1f3c501375797dcd7ca21b58e2c9abbe317 ] Currently there is no mechanism to read dmic_num in mach_params structure. In this scenario mach_params->dmic_num check always returns 0 which fails to add component string for dmic. Update the condition check with acp pdm dmic quirk check and pass the dmic_num as 1. Fixes: 2981d9b0789c ("ASoC: amd: acp: add soundwire machine driver for legacy stack") Signed-off-by: Vijendar Mukunda Link: https://patch.msgid.link/20260330072431.3512358-2-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/amd/acp/acp-sdw-legacy-mach.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c index 2b2910b1856d5..798c73d7e26de 100644 --- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c +++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c @@ -520,11 +520,11 @@ static int mc_probe(struct platform_device *pdev) " cfg-amp:%d", amp_num); if (!card->components) return -ENOMEM; - if (mach->mach_params.dmic_num) { + if (soc_sdw_quirk & ASOC_SDW_ACP_DMIC) { card->components = devm_kasprintf(card->dev, GFP_KERNEL, "%s mic:dmic cfg-mics:%d", card->components, - mach->mach_params.dmic_num); + 1); if (!card->components) return -ENOMEM; } From 21e8dd9906bff50b97ca7c3c782496678635ddce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:02:58 +0200 Subject: [PATCH 0445/1518] drm/amd/pm/ci: Use highest MCLK on CI when MCLK DPM is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 894f0d34d66cb47fe718fe2ae5c18729d22c5218 ] When MCLK DPM is disabled for any reason, populate the MCLK table with the highest MCLK DPM level, so that the ASIC can use the highest possible memory clock to get good performance even when MCLK DPM is disabled. Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 0cb7eaaba3844..71b1dad34926e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -1322,6 +1322,14 @@ static int ci_populate_all_memory_levels(struct pp_hwmgr *hwmgr) return result; } + if (data->mclk_dpm_key_disabled && dpm_table->mclk_table.count) { + /* Populate the table with the highest MCLK level when MCLK DPM is disabled */ + for (i = 0; i < dpm_table->mclk_table.count - 1; i++) { + levels[i] = levels[dpm_table->mclk_table.count - 1]; + levels[i].DisplayWatermark = PPSMC_DISPLAY_WATERMARK_HIGH; + } + } + smu_data->smc_state_table.MemoryLevel[0].EnabledForActivity = 1; dev_id = adev->pdev->device; From c829b4633041f3eb59b197a6e38baf6f94541dd8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:02:59 +0200 Subject: [PATCH 0446/1518] drm/amd/pm/ci: Disable MCLK DPM on problematic CI ASICs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9851f29cb06c09f7dad3867d8b0feec3fc71b6c8 ] There are two known cases where MCLK DPM can causes issues: Radeon R9 M380 found in iMac computers from 2015. The SMU in this GPU just hangs as soon as we send it the PPSMC_MSG_MCLKDPM_Enable command, even when MCLK switching is disabled, and even when we only populate one MCLK DPM level. Apply workaround to all devices with the same subsystem ID. Radeon R7 260X due to old memory controller microcode. We only flash the MC ucode when it isn't set up by the VBIOS, therefore there is no way to make sure that it has the correct ucode version. I verified that this patch fixes the SMU hang on the R9 M380 which would previously fail to boot. This also fixes the UVD initialization error on that GPU which happened because the SMU couldn't ungate the UVD after it hung. Fixes: 86457c3b21cb ("drm/amd/powerplay: Add support for CI asics to hwmgr") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c index 2b5ac21fee399..1d6e30269d567 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c @@ -104,6 +104,21 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr) PP_GFXOFF_MASK); hwmgr->pp_table_version = PP_TABLE_V0; hwmgr->od_enabled = false; + switch (hwmgr->chip_id) { + case CHIP_BONAIRE: + /* R9 M380 in iMac 2015: SMU hangs when enabling MCLK DPM + * R7 260X cards with old MC ucode: MCLK DPM is unstable + */ + if (adev->pdev->subsystem_vendor == 0x106B || + adev->pdev->device == 0x6658) { + dev_info(adev->dev, "disabling MCLK DPM on quirky ASIC"); + adev->pm.pp_feature &= ~PP_MCLK_DPM_MASK; + hwmgr->feature_mask &= ~PP_MCLK_DPM_MASK; + } + break; + default: + break; + } smu7_init_function_pointers(hwmgr); break; case AMDGPU_FAMILY_CZ: From 432fdc0141b53793702e862884cd04bff9b409c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:03:00 +0200 Subject: [PATCH 0447/1518] drm/amd/pm/smu7: Fix SMU7 voltage dependency on display clock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0138610c14130425be53423b35336561829965e0 ] The DCE (display controller engine) requires a minimum voltage in order to function correctly, depending on which clock level it currently uses. Add a new table that contains display clock frequency levels and the corresponding required voltages. The clock frequency levels are taken from DC (and the old radeon driver's voltage dependency table for CI in cases where its values were lower). The voltage levels are taken from the following function: phm_initializa_dynamic_state_adjustment_rule_settings(). Furthermore, in case of CI, call smu7_patch_vddc() on the new table to account for leakage voltage (like in radeon). Use the display clock value from amd_pp_display_configuration to look up the voltage level needed by the DCE. Send the voltage to the SMU via the PPSMC_MSG_VddC_Request command. The previous implementation of this feature was non-functional because it relied on a "dal_power_level" field which was never assigned; and it was not at all implemented for CI ASICs. I verified this on a Radeon R9 M380 which previously booted to a black screen with DC enabled (default since Linux 6.19), but now works correctly. Fixes: 599a7e9fe1b6 ("drm/amd/powerplay: implement smu7 hwmgr to manager asics with smu ip version 7.") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 88 ++++++++++++++++++- drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h | 1 + 2 files changed, 86 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 9b28c07282699..07d946c38ec04 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2802,6 +2802,10 @@ static int smu7_patch_dependency_tables_with_leakage(struct pp_hwmgr *hwmgr) if (tmp) return -EINVAL; + tmp = smu7_patch_vddc(hwmgr, hwmgr->dyn_state.vddc_dependency_on_display_clock); + if (tmp) + return -EINVAL; + tmp = smu7_patch_vce_vddc(hwmgr, hwmgr->dyn_state.vce_clock_voltage_dependency_table); if (tmp) return -EINVAL; @@ -2885,6 +2889,8 @@ static int smu7_hwmgr_backend_fini(struct pp_hwmgr *hwmgr) { kfree(hwmgr->dyn_state.vddc_dep_on_dal_pwrl); hwmgr->dyn_state.vddc_dep_on_dal_pwrl = NULL; + kfree(hwmgr->dyn_state.vddc_dependency_on_display_clock); + hwmgr->dyn_state.vddc_dependency_on_display_clock = NULL; kfree(hwmgr->backend); hwmgr->backend = NULL; @@ -2955,6 +2961,51 @@ static int smu7_update_edc_leakage_table(struct pp_hwmgr *hwmgr) return ret; } +static int smu7_init_voltage_dependency_on_display_clock_table(struct pp_hwmgr *hwmgr) +{ + struct phm_clock_voltage_dependency_table *table; + + if (!amdgpu_device_ip_get_ip_block(hwmgr->adev, AMD_IP_BLOCK_TYPE_DCE)) + return 0; + + table = kzalloc(struct_size(table, entries, 4), GFP_KERNEL); + if (!table) + return -ENOMEM; + + if (hwmgr->chip_id >= CHIP_POLARIS10) { + table->entries[0].clk = 38918; + table->entries[1].clk = 45900; + table->entries[2].clk = 66700; + table->entries[3].clk = 113200; + + table->entries[0].v = 700; + table->entries[1].v = 740; + table->entries[2].v = 800; + table->entries[3].v = 900; + } else { + if (hwmgr->chip_family == AMDGPU_FAMILY_CZ) { + table->entries[0].clk = 35200; + table->entries[1].clk = 35200; + table->entries[2].clk = 46700; + table->entries[3].clk = 64300; + } else { + table->entries[0].clk = 0; + table->entries[1].clk = 35200; + table->entries[2].clk = 54000; + table->entries[3].clk = 62500; + } + + table->entries[0].v = 0; + table->entries[1].v = 720; + table->entries[2].v = 810; + table->entries[3].v = 900; + } + + table->count = 4; + hwmgr->dyn_state.vddc_dependency_on_display_clock = table; + return 0; +} + static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { struct amdgpu_device *adev = hwmgr->adev; @@ -2983,6 +3034,10 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) smu7_get_elb_voltages(hwmgr); } + result = smu7_init_voltage_dependency_on_display_clock_table(hwmgr); + if (result) + goto fail; + if (hwmgr->pp_table_version == PP_TABLE_V1) { smu7_complete_dependency_tables(hwmgr); smu7_set_private_data_based_on_pptable_v1(hwmgr); @@ -3079,13 +3134,40 @@ static int smu7_force_dpm_highest(struct pp_hwmgr *hwmgr) return 0; } +static uint32_t smu7_lookup_vddc_from_dispclk(struct pp_hwmgr *hwmgr) +{ + const struct amd_pp_display_configuration *cfg = hwmgr->display_config; + const struct phm_clock_voltage_dependency_table *vddc_dep_on_dispclk = + hwmgr->dyn_state.vddc_dependency_on_display_clock; + uint32_t i; + + if (!vddc_dep_on_dispclk || !vddc_dep_on_dispclk->count || + !cfg || !cfg->num_display || !cfg->display_clk) + return 0; + + /* Start from 1 because ClocksStateUltraLow should not be used according to DC. */ + for (i = 1; i < vddc_dep_on_dispclk->count; ++i) + if (vddc_dep_on_dispclk->entries[i].clk >= cfg->display_clk) + return vddc_dep_on_dispclk->entries[i].v; + + return vddc_dep_on_dispclk->entries[vddc_dep_on_dispclk->count - 1].v; +} + +static void smu7_apply_minimum_dce_voltage_request(struct pp_hwmgr *hwmgr) +{ + uint32_t req_vddc = smu7_lookup_vddc_from_dispclk(hwmgr); + + smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_VddC_Request, + req_vddc * VOLTAGE_SCALE, + NULL); +} + static int smu7_upload_dpm_level_enable_mask(struct pp_hwmgr *hwmgr) { struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); - if (hwmgr->pp_table_version == PP_TABLE_V1) - phm_apply_dal_min_voltage_request(hwmgr); -/* TO DO for v0 iceland and Ci*/ + smu7_apply_minimum_dce_voltage_request(hwmgr); if (!data->sclk_dpm_key_disabled) { if (data->dpm_level_enable_mask.sclk_dpm_enable_mask) diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index c661185753b42..2f49c95342a14 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -631,6 +631,7 @@ struct phm_dynamic_state_info { struct phm_clock_voltage_dependency_table *vddci_dependency_on_mclk; struct phm_clock_voltage_dependency_table *vddc_dependency_on_mclk; struct phm_clock_voltage_dependency_table *mvdd_dependency_on_mclk; + struct phm_clock_voltage_dependency_table *vddc_dependency_on_display_clock; struct phm_clock_voltage_dependency_table *vddc_dep_on_dal_pwrl; struct phm_clock_array *valid_sclk_values; struct phm_clock_array *valid_mclk_values; From 9d92707b43f74648bb163ed4536bf34de65cc86c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:03:02 +0200 Subject: [PATCH 0448/1518] drm/amd/pm/ci: Fix powertune defaults for Hawaii 0x67B0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d784759c07924280f3c313f205fc48eb62d7cb71 ] There is no AMD GPU with the ID 0x66B0, this looks like a typo. It should be 0x67B0 which is actually part of the PCI ID list, and should use the Hawaii XT powertune defaults according to the old radeon driver. Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 71b1dad34926e..1d99b4f9bc03e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -245,7 +245,7 @@ static void ci_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr) smu_data->power_tune_defaults = &defaults_hawaii_pro; break; case 0x67B8: - case 0x66B0: + case 0x67B0: smu_data->power_tune_defaults = &defaults_hawaii_xt; break; case 0x6640: From 1de9639b50dbc574815924651bd9eee6c04eeccf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:03:03 +0200 Subject: [PATCH 0449/1518] drm/amd/pm/ci: Clear EnabledForActivity field for memory levels MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5facfd4c4c67e8500116ffec0d9da35d92b9c787 ] Follow what radeon did and what amdgpu does for other GPUs with SMU7. Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 1d99b4f9bc03e..1494143132eb5 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -1217,7 +1217,7 @@ static int ci_populate_single_memory_level( } memory_level->EnabledForThrottle = 1; - memory_level->EnabledForActivity = 1; + memory_level->EnabledForActivity = 0; memory_level->UpH = data->current_profile_setting.mclk_up_hyst; memory_level->DownH = data->current_profile_setting.mclk_down_hyst; memory_level->VoltageDownH = 0; From c140492d0bbe014c5b3962e0c1b68d314a37122f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:03:04 +0200 Subject: [PATCH 0450/1518] drm/amd/pm/ci: Fill DW8 fields from SMC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit baf28ec5795c077406d6f52b8ad39e614153bce6 ] In ci_populate_dw8() we currently just read a value from the SMU and then throw it away. Instead of throwing away the value, we should use it to fill other fields in DW8 (like radeon). Otherwise the value of the other fiels is just cleared when we copy this data to the SMU later. Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 1494143132eb5..aea3ad523cc03 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -543,12 +543,11 @@ static int ci_populate_dw8(struct pp_hwmgr *hwmgr, uint32_t fuse_table_offset) { struct ci_smumgr *smu_data = (struct ci_smumgr *)(hwmgr->smu_backend); const struct ci_pt_defaults *defaults = smu_data->power_tune_defaults; - uint32_t temp; if (ci_read_smc_sram_dword(hwmgr, fuse_table_offset + offsetof(SMU7_Discrete_PmFuses, TdcWaterfallCtl), - (uint32_t *)&temp, SMC_RAM_END)) + (uint32_t *)&smu_data->power_tune_table.TdcWaterfallCtl, SMC_RAM_END)) PP_ASSERT_WITH_CODE(false, "Attempt to read PmFuses.DW6 (SviLoadLineEn) from SMC Failed!", return -EINVAL); From 2381d4c5cc1efa2dc9db3d7b7789c15d59d0ce00 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:03:05 +0200 Subject: [PATCH 0451/1518] drm/amd/pm/smu7: Add SCLK cap for quirky Hawaii board MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4724bc5b8d78c34b993594f9406135408ccb312a ] On a specific Radeon R9 390X board, the GPU can "randomly" hang while gaming. Initially I thought this was a RADV bug and tried to work around this in Mesa: commit 8ea08747b86b ("radv: Mitigate GPU hang on Hawaii in Dota 2 and RotTR") However, I got some feedback from other users who are reporting that the above mitigation causes a significant performance regression for them, and they didn't experience the hang on their GPU in the first place. After some further investigation, it turns out that the problem is that the highest SCLK DPM level on this board isn't stable. Lowering SCLK to 1040 MHz (from 1070 MHz) works around the issue, and has a negligible impact on performance compared to the Mesa patch. (Note that increasing the voltage can also work around it, but we felt that lowering the SCLK is the safer option.) To solve the above issue, add an "sclk_cap" field to smu7_hwmgr and set this field for the affected board. The capped SCLK value correctly appears on the sysfs interface and shows up in GUI tools such as LACT. Fixes: 9f4b35411cfe ("drm/amd/powerplay: add CI asics support to smumgr (v3)") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 30 ++++++++++++++++--- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h | 1 + 2 files changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 07d946c38ec04..6529a91a613b6 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -787,7 +787,7 @@ static int smu7_setup_dpm_tables_v0(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.vddc_dependency_on_mclk; struct phm_cac_leakage_table *std_voltage_table = hwmgr->dyn_state.cac_leakage_table; - uint32_t i; + uint32_t i, clk; PP_ASSERT_WITH_CODE(allowed_vdd_sclk_table != NULL, "SCLK dependency table is missing. This table is mandatory", return -EINVAL); @@ -804,10 +804,12 @@ static int smu7_setup_dpm_tables_v0(struct pp_hwmgr *hwmgr) data->dpm_table.sclk_table.count = 0; for (i = 0; i < allowed_vdd_sclk_table->count; i++) { + clk = min(allowed_vdd_sclk_table->entries[i].clk, data->sclk_cap); + if (i == 0 || data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count-1].value != - allowed_vdd_sclk_table->entries[i].clk) { + clk) { data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].value = - allowed_vdd_sclk_table->entries[i].clk; + clk; data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].enabled = (i == 0) ? 1 : 0; data->dpm_table.sclk_table.count++; } @@ -3006,6 +3008,25 @@ static int smu7_init_voltage_dependency_on_display_clock_table(struct pp_hwmgr * return 0; } +static void smu7_set_sclk_cap(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = hwmgr->adev; + struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); + + data->sclk_cap = 0xffffffff; + + if (hwmgr->od_enabled) + return; + + /* R9 390X board: last sclk dpm level is unstable, use lower sclk */ + if (adev->pdev->device == 0x67B0 && + adev->pdev->subsystem_vendor == 0x1043) + data->sclk_cap = 104000; /* 1040 MHz */ + + if (data->sclk_cap != 0xffffffff) + dev_info(adev->dev, "sclk cap: %u kHz on quirky ASIC\n", data->sclk_cap * 10); +} + static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { struct amdgpu_device *adev = hwmgr->adev; @@ -3017,6 +3038,7 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) return -ENOMEM; hwmgr->backend = data; + smu7_set_sclk_cap(hwmgr); smu7_patch_voltage_workaround(hwmgr); smu7_init_dpm_defaults(hwmgr); @@ -3903,7 +3925,7 @@ static int smu7_get_pp_table_entry_callback_func_v0(struct pp_hwmgr *hwmgr, /* Performance levels are arranged from low to high. */ performance_level->memory_clock = memory_clock; - performance_level->engine_clock = engine_clock; + performance_level->engine_clock = min(engine_clock, data->sclk_cap); pcie_gen_from_bios = visland_clk_info->ucPCIEGen; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h index d9e8b386bd4d3..66adabeab6a3a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.h @@ -234,6 +234,7 @@ struct smu7_hwmgr { uint32_t pcie_gen_cap; uint32_t pcie_lane_cap; uint32_t pcie_spc_cap; + uint32_t sclk_cap; struct smu7_leakage_voltage vddc_leakage; struct smu7_leakage_voltage vddci_leakage; struct smu7_leakage_voltage vddcgfx_leakage; From 0a84e210daec23132035a944d430d562ffcc8097 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sun, 29 Mar 2026 18:03:06 +0200 Subject: [PATCH 0452/1518] drm/amdgpu/uvd4.2: Don't initialize UVD 4.2 when DPM is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8b3e8fa6d7bdab292447a43f70532db437d5d4f5 ] UVD 4.2 doesn't work at all when DPM is disabled because the SMU is responsible for ungating it. So, Linux fails to boot with CIK GPUs when using the amdgpu.dpm=0 parameter. Fix this by returning -ENOENT from uvd_v4_2_early_init() when amdgpu_dpm isn't enabled. Note: amdgpu.dpm=0 is often suggested as a workaround for issues and is useful for debugging. Fixes: a2e73f56fa62 ("drm/amdgpu: Add support for CIK parts") Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index 4b96fd5837720..d7302938e6662 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -93,6 +93,11 @@ static void uvd_v4_2_ring_set_wptr(struct amdgpu_ring *ring) static int uvd_v4_2_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + + /* UVD doesn't work without DPM, it needs DPM to ungate it. */ + if (!amdgpu_dpm) + return -ENOENT; + adev->uvd.num_uvd_inst = 1; uvd_v4_2_set_ring_funcs(adev); From 06fed91296f8c451fbac3067687c8c450d8ceb99 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Wed, 18 Mar 2026 10:04:49 -0700 Subject: [PATCH 0453/1518] PCI/DPC: Log AER error info for DPC/EDR uncorrectable errors [ Upstream commit 97970e7c694356e3386a10e3b936d61eafd06bce ] aer_print_error() skips printing if ratelimit_print[i] is not set. In the native AER path, ratelimit_print is initialized by add_error_device() during source device discovery, and is set to 1 for fatal errors to bypass rate limiting since fatal errors should always be logged. The DPC/EDR path uses the DPC-capable port as the error source and reads its AER uncorrectable error status registers directly in dpc_get_aer_uncorrect_severity(). Since it does not go through add_error_device(), ratelimit_print[0] is left uninitialized and zero. As a result, aer_print_error() silently drops all AER error messages for DPC/EDR triggered events. Set ratelimit_print[0] to 1 to bypass rate limiting and always print AER logs for uncorrectable errors detected by the DPC port. Fixes: a57f2bfb4a58 ("PCI/AER: Ratelimit correctable and non-fatal error logging") Co-developed-by: Goudar Manjunath Ramanagouda Signed-off-by: Goudar Manjunath Ramanagouda Signed-off-by: Kuppuswamy Sathyanarayanan [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20260318170449.2733581-1-sathyanarayanan.kuppuswamy@linux.intel.com Signed-off-by: Sasha Levin --- drivers/pci/pcie/dpc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index fc18349614d7c..7605ddd9f0ba8 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -256,6 +256,7 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev, info->dev[0] = dev; info->error_dev_num = 1; + info->ratelimit_print[0] = 1; return 1; } From f329dccceb764e063e6c60c1f7877e27e2b0cf2b Mon Sep 17 00:00:00 2001 From: Billy Tsai Date: Mon, 9 Mar 2026 10:33:24 +0800 Subject: [PATCH 0454/1518] hwmon: (aspeed-g6-pwm-tach): remove redundant driver remove callback [ Upstream commit 46fef8583daa1bf78fda7eaa523c64d4440322ac ] Drops the remove callback as it only asserts reset and the probe already registers a devres action (devm_add_action_or_reset()) to call aspeed_pwm_tach_reset_assert(). Fixes: 7e1449cd15d1 ("hwmon: (aspeed-g6-pwm-tacho): Support for ASPEED g6 PWM/Fan tach") Signed-off-by: Billy Tsai Link: https://lore.kernel.org/r/20260309-pwm_fixes-v2-1-ca9768e70470@aspeedtech.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/aspeed-g6-pwm-tach.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/hwmon/aspeed-g6-pwm-tach.c b/drivers/hwmon/aspeed-g6-pwm-tach.c index 4174b129d1fce..d1f7f43974824 100644 --- a/drivers/hwmon/aspeed-g6-pwm-tach.c +++ b/drivers/hwmon/aspeed-g6-pwm-tach.c @@ -517,13 +517,6 @@ static int aspeed_pwm_tach_probe(struct platform_device *pdev) return 0; } -static void aspeed_pwm_tach_remove(struct platform_device *pdev) -{ - struct aspeed_pwm_tach_data *priv = platform_get_drvdata(pdev); - - reset_control_assert(priv->reset); -} - static const struct of_device_id aspeed_pwm_tach_match[] = { { .compatible = "aspeed,ast2600-pwm-tach", @@ -534,7 +527,6 @@ MODULE_DEVICE_TABLE(of, aspeed_pwm_tach_match); static struct platform_driver aspeed_pwm_tach_driver = { .probe = aspeed_pwm_tach_probe, - .remove = aspeed_pwm_tach_remove, .driver = { .name = "aspeed-g6-pwm-tach", .of_match_table = aspeed_pwm_tach_match, From c87f914822c26ae00484fdba11e7ef68df5c82d7 Mon Sep 17 00:00:00 2001 From: Lei Huang Date: Tue, 31 Mar 2026 15:54:05 +0800 Subject: [PATCH 0455/1518] ALSA: hda/realtek: fix code style (ERROR: else should follow close brace '}') [ Upstream commit d1888bf848ade6a9e71c7ba516fd215aa1bd8d65 ] Fix checkpatch code style errors: ERROR: else should follow close brace '}' #2300: FILE: sound/hda/codecs/realtek/alc269.c:2300: + } + else Fixes: 31278997add6 ("ALSA: hda/realtek - Add headset quirk for Dell DT") Signed-off-by: Lei Huang Link: https://patch.msgid.link/20260331075405.78148-1-huanglei814@163.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/realtek/alc269.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 844c4650230cd..a2ecbe1412632 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -2237,9 +2237,9 @@ static void alc_fixup_headset_mode_alc255_no_hp_mic(struct hda_codec *codec, struct alc_spec *spec = codec->spec; spec->parse_flags |= HDA_PINCFG_HEADSET_MIC; alc255_set_default_jack_type(codec); - } - else + } else { alc_fixup_headset_mode(codec, fix, action); + } } static void alc288_update_headset_jack_cb(struct hda_codec *codec, From d0b28251ca4488a7c87a38b59983bc604a392339 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Tue, 24 Mar 2026 12:38:30 -0500 Subject: [PATCH 0456/1518] ASoC: SOF: Intel: hda: Place check before dereference [ Upstream commit 6cbc8360f51a3df2ea16a786b262b9fe44d4c68c ] The struct hext_stream is dereferenced before it is checked for NULL. Although it can never be NULL due to a check prior to hda_dsp_iccmax_stream_hw_params() being called, this change clears any confusion regarding hext_stream possibly being NULL. Check hext_stream for NULL and then assign its members. Detected by Smatch: sound/soc/sof/intel/hda-stream.c:488 hda_dsp_iccmax_stream_hw_params() warn: variable dereferenced before check 'hext_stream' (see line 486) Fixes: aca961f196e5d ("ASoC: SOF: Intel: hda: Add helper function to program ICCMAX stream") Signed-off-by: Ethan Tidmore Link: https://patch.msgid.link/20260324173830.17563-1-ethantidmore06@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/intel/hda-stream.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index 9c3b3a9aaf83c..56faafb3dd0e5 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -445,16 +445,20 @@ int hda_dsp_iccmax_stream_hw_params(struct snd_sof_dev *sdev, struct hdac_ext_st struct snd_dma_buffer *dmab, struct snd_pcm_hw_params *params) { - struct hdac_stream *hstream = &hext_stream->hstream; - int sd_offset = SOF_STREAM_SD_OFFSET(hstream); + struct hdac_stream *hstream; + int sd_offset; int ret; - u32 mask = 0x1 << hstream->index; + u32 mask; if (!hext_stream) { dev_err(sdev->dev, "error: no stream available\n"); return -ENODEV; } + hstream = &hext_stream->hstream; + sd_offset = SOF_STREAM_SD_OFFSET(hstream); + mask = 0x1 << hstream->index; + if (!dmab) { dev_err(sdev->dev, "error: no dma buffer allocated!\n"); return -ENODEV; From 30b8a3f88c5935f37fa4f1a0d8cdf86e584217c8 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 16 Mar 2026 11:44:42 -0700 Subject: [PATCH 0457/1518] drm/msm/vma: Avoid lock in VM_BIND fence signaling path [ Upstream commit 8a7023b035355ef5bfa096bd323256fa8abbbc6a ] Use msm_gem_unpin_active(), similar to what is used in the GEM_SUBMIT path. This avoids needing to hold the obj lock, and the end result is the same. (As with GEM_SUBMIT, we know the fence isn't signaled yet.) Reported-by: Akhil P Oommen Fixes: 2e6a8a1fe2b2 ("drm/msm: Add VM_BIND ioctl") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/712230/ Message-ID: <20260316184442.673558-1-robin.clark@oss.qualcomm.com> Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_gem.c | 3 +++ drivers/gpu/drm/msm/msm_gem_vma.c | 9 ++++++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 9f7fbe577abb1..8636a7f031d24 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -533,8 +533,11 @@ void msm_gem_unpin_locked(struct drm_gem_object *obj) */ void msm_gem_unpin_active(struct drm_gem_object *obj) { + struct msm_drm_private *priv = obj->dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); + GEM_WARN_ON(!mutex_is_locked(&priv->lru.lock)); + msm_obj->pin_count--; GEM_WARN_ON(msm_obj->pin_count < 0); update_lru_active(obj); diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 89a95977f41ef..44bcc2b291e47 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -680,6 +680,7 @@ static struct dma_fence * msm_vma_job_run(struct drm_sched_job *_job) { struct msm_vm_bind_job *job = to_msm_vm_bind_job(_job); + struct msm_drm_private *priv = job->vm->drm->dev_private; struct msm_gem_vm *vm = to_msm_vm(job->vm); struct drm_gem_object *obj; int ret = vm->unusable ? -EINVAL : 0; @@ -722,12 +723,14 @@ msm_vma_job_run(struct drm_sched_job *_job) if (ret) msm_gem_vm_unusable(job->vm); + mutex_lock(&priv->lru.lock); + job_foreach_bo (obj, job) { - msm_gem_lock(obj); - msm_gem_unpin_locked(obj); - msm_gem_unlock(obj); + msm_gem_unpin_active(obj); } + mutex_unlock(&priv->lru.lock); + /* VM_BIND ops are synchronous, so no fence to wait on: */ return NULL; } From 8cf18974284fbfd43fe32fdacec59fabbcca9003 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 25 Mar 2026 11:59:26 -0700 Subject: [PATCH 0458/1518] drm/msm: Reject fb creation from _NO_SHARE objs [ Upstream commit cf50ccdb765b3a6f1cd8e75642b0439fea0263a5 ] It would be an error to map these into kms->vm. So reject this as early as possible, when creating an fb. Fixes: b58e12a66e47 ("drm/msm: Add _NO_SHARE flag") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/714264/ Message-ID: <20260325185926.1265661-1-robin.clark@oss.qualcomm.com> Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_fb.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index 1eff615ff9bff..ce1725990a48d 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -219,7 +219,12 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, + mode_cmd->offsets[i]; if (bos[i]->size < min_size) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "plane %d too small", i); + goto fail; + } + + if (to_msm_bo(bos[i])->flags & MSM_BO_NO_SHARE) { + ret = UERR(EINVAL, dev, "Cannot map _NO_SHARE to kms vm"); goto fail; } From 206f812ef140727b75697111391ae320fd8aa652 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 24 Mar 2026 15:05:18 -0700 Subject: [PATCH 0459/1518] drm/msm: Fix VM_BIND UNMAP locking [ Upstream commit 85042c2cd970a6b0e686329387096fe19989ae62 ] Wrong argument meant that the objs involved in UNMAP ops were not always getting locked. Since _NO_SHARE objs share a common resv with the VM (which is always locked) this would only show up with non-_NO_SHARE BOs. Reported-by: Victoria Brekenfeld Fixes: 2e6a8a1fe2b2 ("drm/msm: Add VM_BIND ioctl") Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/94 Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/713898/ Message-ID: <20260324220519.1221471-2-robin.clark@oss.qualcomm.com> Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_gem_vma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 44bcc2b291e47..9016ef978be5e 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -1232,7 +1232,7 @@ vm_bind_job_lock_objects(struct msm_vm_bind_job *job, struct drm_exec *exec) case MSM_VM_BIND_OP_UNMAP: ret = drm_gpuvm_sm_unmap_exec_lock(job->vm, exec, op->iova, - op->obj_offset); + op->range); break; case MSM_VM_BIND_OP_MAP: case MSM_VM_BIND_OP_MAP_NULL: { From 6a83ea4da004f0a6ed448261c31277486773bd62 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 25 Mar 2026 11:40:42 -0700 Subject: [PATCH 0460/1518] drm/msm/a6xx: Fix HLSQ register dumping [ Upstream commit c289a6db9ba6cb974f0317da142e4f665d589566 ] Fix the bitfield offset of HLSQ_READ_SEL state-type bitfield. Otherwise we are always reading TP state when we wanted SP or HLSQ state. Reported-by: Connor Abbott Suggested-by: Connor Abbott Fixes: 1707add81551 ("drm/msm/a6xx: Add a6xx gpu state") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/714236/ Message-ID: <20260325184043.1259312-1-robin.clark@oss.qualcomm.com> Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 9cec333e23e15..def021ba19299 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1013,7 +1013,7 @@ static void a6xx_get_crashdumper_hlsq_registers(struct msm_gpu *gpu, u64 out = dumper->iova + A6XX_CD_DATA_OFFSET; int i, regcount = 0; - in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL, regs->val1); + in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL, (regs->val1 & 0xff) << 8); for (i = 0; i < regs->count; i += 2) { u32 count = RANGE(regs->registers, i); From 279fde87aa70bdce2409a7586b66dfc87e693183 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 25 Mar 2026 11:41:05 -0700 Subject: [PATCH 0461/1518] drm/msm/shrinker: Fix can_block() logic [ Upstream commit df0f439e3926817cf577ca6272aad68468ff7624 ] The intention here was to allow blocking if DIRECT_RECLAIM or if called from kswapd and KSWAPD_RECLAIM is set. Reported by Claude code review: https://lore.gitlab.freedesktop.org/drm-ai-reviews/review-patch9-20260309151119.290217-10-boris.brezillon@collabora.com/ on a panthor patch which had copied similar logic. Reported-by: Boris Brezillon Fixes: 7860d720a84c ("drm/msm: Fix build break with recent mm tree") Signed-off-by: Rob Clark Reviewed-by: Boris Brezillon Patchwork: https://patchwork.freedesktop.org/patch/714238/ Message-ID: <20260325184106.1259528-1-robin.clark@oss.qualcomm.com> Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_gem_shrinker.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 1039e3c0a47bf..31fa51a44f86e 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -26,9 +26,8 @@ static bool can_swap(void) static bool can_block(struct shrink_control *sc) { - if (!(sc->gfp_mask & __GFP_DIRECT_RECLAIM)) - return false; - return current_is_kswapd() || (sc->gfp_mask & __GFP_RECLAIM); + return (sc->gfp_mask & __GFP_DIRECT_RECLAIM) || + (current_is_kswapd() && (sc->gfp_mask & __GFP_KSWAPD_RECLAIM)); } static unsigned long From 4180d90a40545b0d5992acab6a2ef564af32c27c Mon Sep 17 00:00:00 2001 From: Connor Abbott Date: Wed, 25 Mar 2026 16:58:37 -0400 Subject: [PATCH 0462/1518] drm/msm/a6xx: Fix dumping A650+ debugbus blocks [ Upstream commit cc83f71c9be0715fe93b963ffa9767d5d84354ed ] These should be appended after the existing debugbus blocks, instead of replacing them. Fixes: 1e05bba5e2b8 ("drm/msm/a6xx: Update a6xx gpu coredump") Signed-off-by: Connor Abbott Patchwork: https://patchwork.freedesktop.org/patch/714270/ Message-ID: <20260325-drm-msm-a650-debugbus-v1-1-dfbf358890a7@gmail.com> Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index def021ba19299..918d2e504adec 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -361,7 +361,7 @@ static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, sizeof(*a6xx_state->debugbus)); if (a6xx_state->debugbus) { - int i; + int i, j; for (i = 0; i < ARRAY_SIZE(a6xx_debugbus_blocks); i++) a6xx_get_debugbus_block(gpu, @@ -369,8 +369,6 @@ static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, &a6xx_debugbus_blocks[i], &a6xx_state->debugbus[i]); - a6xx_state->nr_debugbus = ARRAY_SIZE(a6xx_debugbus_blocks); - /* * GBIF has same debugbus as of other GPU blocks, fall back to * default path if GPU uses GBIF, also GBIF uses exactly same @@ -381,17 +379,19 @@ static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, &a6xx_gbif_debugbus_block, &a6xx_state->debugbus[i]); - a6xx_state->nr_debugbus += 1; + i++; } if (adreno_is_a650_family(to_adreno_gpu(gpu))) { - for (i = 0; i < ARRAY_SIZE(a650_debugbus_blocks); i++) + for (j = 0; j < ARRAY_SIZE(a650_debugbus_blocks); i++, j++) a6xx_get_debugbus_block(gpu, a6xx_state, - &a650_debugbus_blocks[i], + &a650_debugbus_blocks[j], &a6xx_state->debugbus[i]); } + + a6xx_state->nr_debugbus = i; } } From 70f694e0bb878bf526ed9ab85660f398cf39a278 Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Fri, 27 Mar 2026 05:43:50 +0530 Subject: [PATCH 0463/1518] drm/msm/a6xx: Use barriers while updating HFI Q headers [ Upstream commit dc78b35d5ec09d1b0b8a937e6e640d2c5a030915 ] To avoid harmful compiler optimizations and IO reordering in the HW, use barriers and READ/WRITE_ONCE helpers as necessary while accessing the HFI queue index variables. Fixes: 4b565ca5a2cb ("drm/msm: Add A6XX device support") Signed-off-by: Akhil P Oommen Patchwork: https://patchwork.freedesktop.org/patch/714653/ Message-ID: <20260327-a8xx-gpu-batch2-v2-1-2b53c38d2101@oss.qualcomm.com> Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 550de6ad68eff..ef1365afd767b 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -33,7 +33,7 @@ static int a6xx_hfi_queue_read(struct a6xx_gmu *gmu, struct a6xx_hfi_queue_header *header = queue->header; u32 i, hdr, index = header->read_index; - if (header->read_index == header->write_index) { + if (header->read_index == READ_ONCE(header->write_index)) { header->rx_request = 1; return 0; } @@ -61,7 +61,10 @@ static int a6xx_hfi_queue_read(struct a6xx_gmu *gmu, if (!gmu->legacy) index = ALIGN(index, 4) % header->size; - header->read_index = index; + /* Ensure all memory operations are complete before updating the read index */ + dma_mb(); + + WRITE_ONCE(header->read_index, index); return HFI_HEADER_SIZE(hdr); } @@ -73,7 +76,7 @@ static int a6xx_hfi_queue_write(struct a6xx_gmu *gmu, spin_lock(&queue->lock); - space = CIRC_SPACE(header->write_index, header->read_index, + space = CIRC_SPACE(header->write_index, READ_ONCE(header->read_index), header->size); if (space < dwords) { header->dropped++; @@ -94,7 +97,10 @@ static int a6xx_hfi_queue_write(struct a6xx_gmu *gmu, queue->data[index] = 0xfafafafa; } - header->write_index = index; + /* Ensure all memory operations are complete before updating the write index */ + dma_mb(); + + WRITE_ONCE(header->write_index, index); spin_unlock(&queue->lock); gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 0x01); From 9232d70f98cdf1a5d96dd2f1fbed465da6b9a0b9 Mon Sep 17 00:00:00 2001 From: wangdicheng Date: Wed, 1 Apr 2026 16:26:25 +0800 Subject: [PATCH 0464/1518] ALSA: hda/cmedia: Remove duplicate pin configuration parsing [ Upstream commit 579e7b820de5dd5124585413bb5e9c278d255436 ] The cmedia_probe() function calls snd_hda_parse_pin_defcfg() and snd_hda_gen_parse_auto_config() twice unnecessarily. Remove The duplicate code. Fixes: 0f1e8306dcbe ("ALSA: hda/cmedia: Rewrite to new probe method") Signed-off-by: wangdicheng Link: https://patch.msgid.link/20260401082625.157868-1-wangdich9700@163.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/cmedia.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/sound/hda/codecs/cmedia.c b/sound/hda/codecs/cmedia.c index 15e5a1118a6e8..a156bea7ca446 100644 --- a/sound/hda/codecs/cmedia.c +++ b/sound/hda/codecs/cmedia.c @@ -39,13 +39,6 @@ static int cmedia_probe(struct hda_codec *codec, const struct hda_device_id *id) spec->out_vol_mask = (1ULL << 0x10); } - err = snd_hda_parse_pin_defcfg(codec, cfg, NULL, 0); - if (err < 0) - goto error; - err = snd_hda_gen_parse_auto_config(codec, cfg); - if (err < 0) - goto error; - err = snd_hda_parse_pin_defcfg(codec, cfg, NULL, 0); if (err < 0) goto error; From 2d9cb1f588ceeda5960cca983267ab743e69abe3 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Fri, 16 Jan 2026 20:27:47 +0800 Subject: [PATCH 0465/1518] pmdomain: ti: omap_prm: Fix a reference leak on device node [ Upstream commit 44c28e1c52764fef6dd1c1ada3a248728812e67f ] When calling of_parse_phandle_with_args(), the caller is responsible to call of_node_put() to release the reference of device node. In omap_prm_domain_attach_dev, it does not release the reference. Fixes: 58cbff023bfa ("soc: ti: omap-prm: Add basic power domain support") Signed-off-by: Felix Gu Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/pmdomain/ti/omap_prm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pmdomain/ti/omap_prm.c b/drivers/pmdomain/ti/omap_prm.c index 5142f064bf5cd..64a187f79a1a7 100644 --- a/drivers/pmdomain/ti/omap_prm.c +++ b/drivers/pmdomain/ti/omap_prm.c @@ -655,6 +655,7 @@ static int omap_prm_domain_attach_dev(struct generic_pm_domain *domain, if (pd_args.args_count != 0) dev_warn(dev, "%s: unusupported #power-domain-cells: %i\n", prmd->pd.name, pd_args.args_count); + of_node_put(pd_args.np); genpd_data = dev_gpd_data(dev); genpd_data->data = NULL; From 2ba2e8ce483cfb524a650cf8aa684d271c315fb9 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Wed, 21 Jan 2026 22:17:17 +0800 Subject: [PATCH 0466/1518] pmdomain: imx: scu-pd: Fix device_node reference leak during ->probe() [ Upstream commit c8e9b6a55702be6c6d034e973d519c52c3848415 ] When calling of_parse_phandle_with_args(), the caller is responsible to call of_node_put() to release the reference of device node. In imx_sc_pd_get_console_rsrc(), it does not release the reference. Fixes: 893cfb99734f ("firmware: imx: scu-pd: do not power off console domain") Signed-off-by: Felix Gu Reviewed-by: Peng Fan Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/pmdomain/imx/scu-pd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pmdomain/imx/scu-pd.c b/drivers/pmdomain/imx/scu-pd.c index 01d465d88f60d..3ec33667a308c 100644 --- a/drivers/pmdomain/imx/scu-pd.c +++ b/drivers/pmdomain/imx/scu-pd.c @@ -326,6 +326,7 @@ static void imx_sc_pd_get_console_rsrc(void) return; imx_con_rsrc = specs.args[0]; + of_node_put(specs.np); } static int imx_sc_get_pd_power(struct device *dev, u32 rsrc) From 507cc9ab1e8ca1268db95002a3faf0d40900345a Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sun, 1 Feb 2026 12:48:59 +0200 Subject: [PATCH 0467/1518] PM: domains: De-constify fields in struct dev_pm_domain_attach_data [ Upstream commit 1877d3f258cbb57d64e275754fb9b18b089ce72d ] It doesn't really make sense to keep u32 fields to be marked as const. Having the const fields prevents their modification in the driver. Instead the whole struct can be defined as const, if it is constant. Fixes: 161e16a5e50a ("PM: domains: Add helper functions to attach/detach multiple PM domains") Signed-off-by: Dmitry Baryshkov Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- include/linux/pm_domain.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index f67a2cb7d7814..5ed1753a7cb47 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -49,8 +49,8 @@ struct dev_pm_domain_attach_data { const char * const *pd_names; - const u32 num_pd_names; - const u32 pd_flags; + u32 num_pd_names; + u32 pd_flags; }; struct dev_pm_domain_list { From 1140626eb6f57cd79ba08834da27754f2c50934b Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 25 Mar 2026 07:35:44 +0200 Subject: [PATCH 0468/1518] drm/msm/dpu: drop INTF_0 on MSM8953 [ Upstream commit 7090420420d5a7d7c88b21d16962f2a230be3ef3 ] There is no INTF_0 on MSM8953. Currently catalog lists dummy INTF_NONE entry for it. Drop it from the catalog. Fixes: 7a6109ce1c2c ("drm/msm/dpu: Add support for MSM8953") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Patchwork: https://patchwork.freedesktop.org/patch/713990/ Link: https://lore.kernel.org/r/20260325-drop-8953-intf-v1-1-d80e214a1a75@oss.qualcomm.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h index b44d02b48418f..2162ff917b0f8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h @@ -121,13 +121,6 @@ static const struct dpu_dspp_cfg msm8953_dspp[] = { static const struct dpu_intf_cfg msm8953_intf[] = { { - .name = "intf_0", .id = INTF_0, - .base = 0x6a000, .len = 0x268, - .type = INTF_NONE, - .prog_fetch_lines_worst_case = 14, - .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), - .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x268, .type = INTF_DSI, From 2a6a72a0beab24594e9b1483b8ca116ab1ecf197 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:16 +0800 Subject: [PATCH 0469/1518] ASoC: fsl_micfil: Add access property for "VAD Detected" [ Upstream commit c7661bfc7422443df394c01e069ae4e5c3a7f04c ] Add access property SNDRV_CTL_ELEM_ACCESS_READ for control "VAD Detected", which doesn't support put operation, otherwise there will be issue with mixer-test. Fixes: 29dbfeecab85 ("ASoC: fsl_micfil: Add Hardware Voice Activity Detector support") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-2-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_micfil.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index cac26ba0aa4b0..ddc56f77f1455 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -424,7 +424,13 @@ static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { SOC_SINGLE("HWVAD ZCD Adjustment", REG_MICFIL_VAD0_ZCD, 8, 15, 0), SOC_SINGLE("HWVAD ZCD And Behavior Switch", REG_MICFIL_VAD0_ZCD, 4, 1, 0), - SOC_SINGLE_BOOL_EXT("VAD Detected", 0, hwvad_detected, NULL), + { + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, + .access = SNDRV_CTL_ELEM_ACCESS_READ | SNDRV_CTL_ELEM_ACCESS_VOLATILE, + .name = "VAD Detected", + .info = snd_soc_info_bool_ext, + .get = hwvad_detected, + }, }; static int fsl_micfil_use_verid(struct device *dev) From 891c51e19d3a0ca4241cec598ac7efda6dacfafd Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:17 +0800 Subject: [PATCH 0470/1518] ASoC: fsl_micfil: Fix event generation in hwvad_put_enable() [ Upstream commit 59b9061824f2179fe133e2636203548eaba3e528 ] ALSA controls should return 1 if the value in the control changed but the control put operation hwvad_put_enable() only returns 0 or a negative error code, causing ALSA to not generate any change events. Add a suitable check in the function before updating the vad_enabled variable. Fixes: 29dbfeecab85 ("ASoC: fsl_micfil: Add Hardware Voice Activity Detector support") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-3-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_micfil.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index ddc56f77f1455..668e6dbe5a712 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -306,10 +306,15 @@ static int hwvad_put_enable(struct snd_kcontrol *kcontrol, unsigned int *item = ucontrol->value.enumerated.item; struct fsl_micfil *micfil = snd_soc_component_get_drvdata(comp); int val = snd_soc_enum_item_to_val(e, item[0]); + bool change = false; + if (val < 0 || val > 1) + return -EINVAL; + + change = (micfil->vad_enabled != val); micfil->vad_enabled = val; - return 0; + return change; } static int hwvad_get_enable(struct snd_kcontrol *kcontrol, From 79acc3ea6fb690b219c55f6dcf700a8dce4e7583 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:18 +0800 Subject: [PATCH 0471/1518] ASoC: fsl_micfil: Fix event generation in hwvad_put_init_mode() [ Upstream commit 7e226209906906421f0d952d7304e48fdb0adabc ] ALSA controls should return 1 if the value in the control changed but the control put operation hwvad_put_init_mode() only returns 0 or a negative error code, causing ALSA to not generate any change events. Add a suitable check in the function before updating the vad_init_mode variable. Fixes: 29dbfeecab85 ("ASoC: fsl_micfil: Add Hardware Voice Activity Detector support") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-4-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_micfil.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 668e6dbe5a712..36eefb7f0eb2f 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -336,13 +336,18 @@ static int hwvad_put_init_mode(struct snd_kcontrol *kcontrol, unsigned int *item = ucontrol->value.enumerated.item; struct fsl_micfil *micfil = snd_soc_component_get_drvdata(comp); int val = snd_soc_enum_item_to_val(e, item[0]); + bool change = false; + + if (val < MICFIL_HWVAD_ENVELOPE_MODE || val > MICFIL_HWVAD_ENERGY_MODE) + return -EINVAL; /* 0 - Envelope-based Mode * 1 - Energy-based Mode */ + change = (micfil->vad_init_mode != val); micfil->vad_init_mode = val; - return 0; + return change; } static int hwvad_get_init_mode(struct snd_kcontrol *kcontrol, From fe6e720bf2a065694e50775ca4e9c831433528ea Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:20 +0800 Subject: [PATCH 0472/1518] ASoC: fsl_micfil: Fix event generation in micfil_put_dc_remover_state() [ Upstream commit 7d2bd35100de370dc326b250e8f6b66bee06a2f3 ] ALSA controls should return 1 if the value in the control changed but the control put operation micfil_put_dc_remover_state() only returns 0 or a negative error code, causing ALSA to not generate any change events. return the value of snd_soc_component_update_bits() directly, as it has the capability of return check status of changed or not. Also enable pm runtime before calling the function snd_soc_component_update_bits() to make the regmap cache data align with the value in hardware. Fixes: 29dbfeecab85 ("ASoC: fsl_micfil: Add Hardware Voice Activity Detector support") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-6-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_micfil.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 36eefb7f0eb2f..980c6e1d9b1ce 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -272,6 +272,10 @@ static int micfil_put_dc_remover_state(struct snd_kcontrol *kcontrol, if (val < 0 || val > 3) return -EINVAL; + ret = pm_runtime_resume_and_get(comp->dev); + if (ret) + return ret; + micfil->dc_remover = val; /* Calculate total value for all channels */ @@ -281,10 +285,10 @@ static int micfil_put_dc_remover_state(struct snd_kcontrol *kcontrol, /* Update DC Remover mode for all channels */ ret = snd_soc_component_update_bits(comp, REG_MICFIL_DC_CTRL, MICFIL_DC_CTRL_CONFIG, reg_val); - if (ret < 0) - return ret; - return 0; + pm_runtime_put_autosuspend(comp->dev); + + return ret; } static int micfil_get_dc_remover_state(struct snd_kcontrol *kcontrol, From 4095fa1c8ed98463a33184effcb44df149ef0e66 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:21 +0800 Subject: [PATCH 0473/1518] ASoC: fsl_micfil: Fix event generation in micfil_quality_set() [ Upstream commit e5785093b1b45af7ee57d18619b2854a8aed073a ] ALSA controls should return 1 if the value in the control changed but the control put operation micfil_quality_set() only returns 0 or a negative error code, causing ALSA to not generate any change events. Add a suitable check in the function before updating the quality variable. Also enable pm runtime before calling the function micfil_set_quality() to make the regmap cache data align with the value in hardware. Fixes: bea1d61d5892 ("ASoC: fsl_micfil: rework quality setting") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-7-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_micfil.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 980c6e1d9b1ce..09deb880bd37d 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -210,10 +210,34 @@ static int micfil_quality_set(struct snd_kcontrol *kcontrol, { struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct fsl_micfil *micfil = snd_soc_component_get_drvdata(cmpnt); + int val = ucontrol->value.integer.value[0]; + bool change = false; + int old_val; + int ret; + + if (val < QUALITY_HIGH || val > QUALITY_VLOW2) + return -EINVAL; + + if (micfil->quality != val) { + ret = pm_runtime_resume_and_get(cmpnt->dev); + if (ret) + return ret; + + old_val = micfil->quality; + micfil->quality = val; + ret = micfil_set_quality(micfil); - micfil->quality = ucontrol->value.integer.value[0]; + pm_runtime_put_autosuspend(cmpnt->dev); - return micfil_set_quality(micfil); + if (ret) { + micfil->quality = old_val; + return ret; + } + + change = true; + } + + return change; } static const char * const micfil_hwvad_enable[] = { From 4ab351b4b785afccef524ea6a518f2c59459417a Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:22 +0800 Subject: [PATCH 0474/1518] ASoC: fsl_xcvr: Fix event generation in fsl_xcvr_arc_mode_put() [ Upstream commit 1b61c8103c9317a9c37fe544c2d83cee1c281149 ] ALSA controls should return 1 if the value in the control changed but the control put operation fsl_xcvr_arc_mode_put() only returns 0 or a negative error code, causing ALSA to not generate any change events. Add a suitable check in the function before updating the arc_mode variable. Fixes: 28564486866f ("ASoC: fsl_xcvr: Add XCVR ASoC CPU DAI driver") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-8-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_xcvr.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index a268fb81a2f86..008e45009c83f 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -115,10 +115,17 @@ static int fsl_xcvr_arc_mode_put(struct snd_kcontrol *kcontrol, struct fsl_xcvr *xcvr = snd_soc_dai_get_drvdata(dai); struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int *item = ucontrol->value.enumerated.item; + int val = snd_soc_enum_item_to_val(e, item[0]); + int ret; - xcvr->arc_mode = snd_soc_enum_item_to_val(e, item[0]); + if (val < 0 || val > 1) + return -EINVAL; - return 0; + ret = (xcvr->arc_mode != val); + + xcvr->arc_mode = val; + + return ret; } static int fsl_xcvr_arc_mode_get(struct snd_kcontrol *kcontrol, From 15ff6da3e9bd21acf9538d8a5dbd81f97c9c7329 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:23 +0800 Subject: [PATCH 0475/1518] ASoC: fsl_xcvr: Fix event generation in fsl_xcvr_mode_put() [ Upstream commit 64a496ba976324615b845d60739dfcdae3d57434 ] ALSA controls should return 1 if the value in the control changed but the control put operation fsl_xcvr_mode_put() only returns 0 or a negative error code, causing ALSA to not generate any change events. Add a suitable check in the function before updating the mode variable. Fixes: 28564486866f ("ASoC: fsl_xcvr: Add XCVR ASoC CPU DAI driver") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-9-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_xcvr.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index 008e45009c83f..d7a823384c08a 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -225,10 +225,17 @@ static int fsl_xcvr_mode_put(struct snd_kcontrol *kcontrol, struct fsl_xcvr *xcvr = snd_soc_dai_get_drvdata(dai); struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int *item = ucontrol->value.enumerated.item; + int val = snd_soc_enum_item_to_val(e, item[0]); struct snd_soc_card *card = dai->component->card; struct snd_soc_pcm_runtime *rtd; + int ret; + + if (val < FSL_XCVR_MODE_SPDIF || val > FSL_XCVR_MODE_EARC) + return -EINVAL; - xcvr->mode = snd_soc_enum_item_to_val(e, item[0]); + ret = (xcvr->mode != val); + + xcvr->mode = val; fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, (xcvr->mode == FSL_XCVR_MODE_ARC)); @@ -238,7 +245,7 @@ static int fsl_xcvr_mode_put(struct snd_kcontrol *kcontrol, rtd = snd_soc_get_pcm_runtime(card, card->dai_link); rtd->pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream_count = (xcvr->mode == FSL_XCVR_MODE_SPDIF ? 1 : 0); - return 0; + return ret; } static int fsl_xcvr_mode_get(struct snd_kcontrol *kcontrol, From cbf3693ddf5aa87e53963518108e404715f13baa Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:24 +0800 Subject: [PATCH 0476/1518] ASoC: fsl_easrc: Check the variable range in fsl_easrc_iec958_put_bits() [ Upstream commit 00541b86fb578d4949cfdd6aff1f82d43fcf07af ] Add check of input value's range in fsl_easrc_iec958_put_bits(), otherwise the wrong value may be written from user space. Fixes: 955ac624058f ("ASoC: fsl_easrc: Add EASRC ASoC CPU DAI drivers") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-10-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_easrc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c index 8e52e43a8ba85..8647df027c3fd 100644 --- a/sound/soc/fsl/fsl_easrc.c +++ b/sound/soc/fsl/fsl_easrc.c @@ -54,6 +54,9 @@ static int fsl_easrc_iec958_put_bits(struct snd_kcontrol *kcontrol, unsigned int regval = ucontrol->value.integer.value[0]; int ret; + if (regval < EASRC_WIDTH_16_BIT || regval > EASRC_WIDTH_24_BIT) + return -EINVAL; + ret = (easrc_priv->bps_iec958[mc->regbase] != regval); easrc_priv->bps_iec958[mc->regbase] = regval; From 9f8304abcd7e7c56e98bba47f618e92d436ac2e6 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:25 +0800 Subject: [PATCH 0477/1518] ASoC: fsl_easrc: Fix value type in fsl_easrc_iec958_get_bits() [ Upstream commit aa21fe4a81458cf469c2615b08cbde5997dde25a ] The value type of controls "Context 0 IEC958 Bits Per Sample" should be integer, not enumerated, the issue is found by the mixer-test. Fixes: 955ac624058f ("ASoC: fsl_easrc: Add EASRC ASoC CPU DAI drivers") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-11-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_easrc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c index 8647df027c3fd..725c7b65fe6b8 100644 --- a/sound/soc/fsl/fsl_easrc.c +++ b/sound/soc/fsl/fsl_easrc.c @@ -73,7 +73,7 @@ static int fsl_easrc_iec958_get_bits(struct snd_kcontrol *kcontrol, struct soc_mreg_control *mc = (struct soc_mreg_control *)kcontrol->private_value; - ucontrol->value.enumerated.item[0] = easrc_priv->bps_iec958[mc->regbase]; + ucontrol->value.integer.value[0] = easrc_priv->bps_iec958[mc->regbase]; return 0; } From 715d7b1e1af8096fa4eae5eb046b684b7ae4350e Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Wed, 1 Apr 2026 17:42:26 +0800 Subject: [PATCH 0478/1518] ASoC: fsl_easrc: Change the type for iec958 channel status controls [ Upstream commit 47f28a5bd154a95d5aa563dde02a801bd32ddb81 ] Use the type SNDRV_CTL_ELEM_TYPE_IEC958 for iec958 channel status controls, the original type will cause mixer-test to iterate all 32bit values, which costs a lot of time. And using IEC958 type can reduce the control numbers. Also enable pm runtime before updating registers to make the regmap cache data align with the value in hardware. Fixes: 955ac624058f ("ASoC: fsl_easrc: Add EASRC ASoC CPU DAI drivers") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260401094226.2900532-12-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_easrc.c | 118 +++++++++++++++++++++++++++----------- 1 file changed, 84 insertions(+), 34 deletions(-) diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c index 725c7b65fe6b8..59cdf18731a0a 100644 --- a/sound/soc/fsl/fsl_easrc.c +++ b/sound/soc/fsl/fsl_easrc.c @@ -78,17 +78,47 @@ static int fsl_easrc_iec958_get_bits(struct snd_kcontrol *kcontrol, return 0; } +static int fsl_easrc_iec958_info(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo) +{ + uinfo->type = SNDRV_CTL_ELEM_TYPE_IEC958; + uinfo->count = 1; + return 0; +} + static int fsl_easrc_get_reg(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); struct soc_mreg_control *mc = (struct soc_mreg_control *)kcontrol->private_value; - unsigned int regval; + struct fsl_asrc *easrc = snd_soc_component_get_drvdata(component); + unsigned int *regval = (unsigned int *)ucontrol->value.iec958.status; + int ret; + + ret = regmap_read(easrc->regmap, REG_EASRC_CS0(mc->regbase), ®val[0]); + if (ret) + return ret; + + ret = regmap_read(easrc->regmap, REG_EASRC_CS1(mc->regbase), ®val[1]); + if (ret) + return ret; + + ret = regmap_read(easrc->regmap, REG_EASRC_CS2(mc->regbase), ®val[2]); + if (ret) + return ret; - regval = snd_soc_component_read(component, mc->regbase); + ret = regmap_read(easrc->regmap, REG_EASRC_CS3(mc->regbase), ®val[3]); + if (ret) + return ret; + + ret = regmap_read(easrc->regmap, REG_EASRC_CS4(mc->regbase), ®val[4]); + if (ret) + return ret; - ucontrol->value.integer.value[0] = regval; + ret = regmap_read(easrc->regmap, REG_EASRC_CS5(mc->regbase), ®val[5]); + if (ret) + return ret; return 0; } @@ -100,22 +130,62 @@ static int fsl_easrc_set_reg(struct snd_kcontrol *kcontrol, struct soc_mreg_control *mc = (struct soc_mreg_control *)kcontrol->private_value; struct fsl_asrc *easrc = snd_soc_component_get_drvdata(component); - unsigned int regval = ucontrol->value.integer.value[0]; - bool changed; + unsigned int *regval = (unsigned int *)ucontrol->value.iec958.status; + bool changed, changed_all = false; int ret; - ret = regmap_update_bits_check(easrc->regmap, mc->regbase, - GENMASK(31, 0), regval, &changed); - if (ret != 0) + ret = pm_runtime_resume_and_get(component->dev); + if (ret) return ret; - return changed; + ret = regmap_update_bits_check(easrc->regmap, REG_EASRC_CS0(mc->regbase), + GENMASK(31, 0), regval[0], &changed); + if (ret != 0) + goto err; + changed_all |= changed; + + ret = regmap_update_bits_check(easrc->regmap, REG_EASRC_CS1(mc->regbase), + GENMASK(31, 0), regval[1], &changed); + if (ret != 0) + goto err; + changed_all |= changed; + + ret = regmap_update_bits_check(easrc->regmap, REG_EASRC_CS2(mc->regbase), + GENMASK(31, 0), regval[2], &changed); + if (ret != 0) + goto err; + changed_all |= changed; + + ret = regmap_update_bits_check(easrc->regmap, REG_EASRC_CS3(mc->regbase), + GENMASK(31, 0), regval[3], &changed); + if (ret != 0) + goto err; + changed_all |= changed; + + ret = regmap_update_bits_check(easrc->regmap, REG_EASRC_CS4(mc->regbase), + GENMASK(31, 0), regval[4], &changed); + if (ret != 0) + goto err; + changed_all |= changed; + + ret = regmap_update_bits_check(easrc->regmap, REG_EASRC_CS5(mc->regbase), + GENMASK(31, 0), regval[5], &changed); + if (ret != 0) + goto err; + changed_all |= changed; +err: + pm_runtime_put_autosuspend(component->dev); + + if (ret != 0) + return ret; + else + return changed_all; } #define SOC_SINGLE_REG_RW(xname, xreg) \ { .iface = SNDRV_CTL_ELEM_IFACE_PCM, .name = (xname), \ .access = SNDRV_CTL_ELEM_ACCESS_READWRITE, \ - .info = snd_soc_info_xr_sx, .get = fsl_easrc_get_reg, \ + .info = fsl_easrc_iec958_info, .get = fsl_easrc_get_reg, \ .put = fsl_easrc_set_reg, \ .private_value = (unsigned long)&(struct soc_mreg_control) \ { .regbase = xreg, .regcount = 1, .nbits = 32, \ @@ -146,30 +216,10 @@ static const struct snd_kcontrol_new fsl_easrc_snd_controls[] = { SOC_SINGLE_VAL_RW("Context 2 IEC958 Bits Per Sample", 2), SOC_SINGLE_VAL_RW("Context 3 IEC958 Bits Per Sample", 3), - SOC_SINGLE_REG_RW("Context 0 IEC958 CS0", REG_EASRC_CS0(0)), - SOC_SINGLE_REG_RW("Context 1 IEC958 CS0", REG_EASRC_CS0(1)), - SOC_SINGLE_REG_RW("Context 2 IEC958 CS0", REG_EASRC_CS0(2)), - SOC_SINGLE_REG_RW("Context 3 IEC958 CS0", REG_EASRC_CS0(3)), - SOC_SINGLE_REG_RW("Context 0 IEC958 CS1", REG_EASRC_CS1(0)), - SOC_SINGLE_REG_RW("Context 1 IEC958 CS1", REG_EASRC_CS1(1)), - SOC_SINGLE_REG_RW("Context 2 IEC958 CS1", REG_EASRC_CS1(2)), - SOC_SINGLE_REG_RW("Context 3 IEC958 CS1", REG_EASRC_CS1(3)), - SOC_SINGLE_REG_RW("Context 0 IEC958 CS2", REG_EASRC_CS2(0)), - SOC_SINGLE_REG_RW("Context 1 IEC958 CS2", REG_EASRC_CS2(1)), - SOC_SINGLE_REG_RW("Context 2 IEC958 CS2", REG_EASRC_CS2(2)), - SOC_SINGLE_REG_RW("Context 3 IEC958 CS2", REG_EASRC_CS2(3)), - SOC_SINGLE_REG_RW("Context 0 IEC958 CS3", REG_EASRC_CS3(0)), - SOC_SINGLE_REG_RW("Context 1 IEC958 CS3", REG_EASRC_CS3(1)), - SOC_SINGLE_REG_RW("Context 2 IEC958 CS3", REG_EASRC_CS3(2)), - SOC_SINGLE_REG_RW("Context 3 IEC958 CS3", REG_EASRC_CS3(3)), - SOC_SINGLE_REG_RW("Context 0 IEC958 CS4", REG_EASRC_CS4(0)), - SOC_SINGLE_REG_RW("Context 1 IEC958 CS4", REG_EASRC_CS4(1)), - SOC_SINGLE_REG_RW("Context 2 IEC958 CS4", REG_EASRC_CS4(2)), - SOC_SINGLE_REG_RW("Context 3 IEC958 CS4", REG_EASRC_CS4(3)), - SOC_SINGLE_REG_RW("Context 0 IEC958 CS5", REG_EASRC_CS5(0)), - SOC_SINGLE_REG_RW("Context 1 IEC958 CS5", REG_EASRC_CS5(1)), - SOC_SINGLE_REG_RW("Context 2 IEC958 CS5", REG_EASRC_CS5(2)), - SOC_SINGLE_REG_RW("Context 3 IEC958 CS5", REG_EASRC_CS5(3)), + SOC_SINGLE_REG_RW("Context 0 IEC958 CS", 0), + SOC_SINGLE_REG_RW("Context 1 IEC958 CS", 1), + SOC_SINGLE_REG_RW("Context 2 IEC958 CS", 2), + SOC_SINGLE_REG_RW("Context 3 IEC958 CS", 3), }; /* From 20b3c566e2702e5d4d0545be8a97029a2eebcc0e Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Wed, 1 Apr 2026 08:00:17 +0000 Subject: [PATCH 0479/1518] iommu/amd: Fix clone_alias() to use the original device's devid [ Upstream commit faad224fe0f0857a04ff2eb3c90f0de57f47d0f3 ] Currently clone_alias() assumes first argument (pdev) is always the original device pointer. This function is called by pci_for_each_dma_alias() which based on topology decides to send original or alias device details in first argument. This meant that the source devid used to look up and copy the DTE may be incorrect, leading to wrong or stale DTE entries being propagated to alias device. Fix this by passing the original pdev as the opaque data argument to both the direct clone_alias() call and pci_for_each_dma_alias(). Inside clone_alias(), retrieve the original device from data and compute devid from it. Fixes: 3332364e4ebc ("iommu/amd: Support multiple PCI DMA aliases in device table") Signed-off-by: Vasant Hegde Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd/iommu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 4beef73139611..5afd1621d715e 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -381,11 +381,12 @@ struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid) return NULL; } -static int clone_alias(struct pci_dev *pdev, u16 alias, void *data) +static int clone_alias(struct pci_dev *pdev_origin, u16 alias, void *data) { struct dev_table_entry new; struct amd_iommu *iommu; struct iommu_dev_data *dev_data, *alias_data; + struct pci_dev *pdev = data; u16 devid = pci_dev_id(pdev); int ret = 0; @@ -432,9 +433,9 @@ static void clone_aliases(struct amd_iommu *iommu, struct device *dev) * part of the PCI DMA aliases if it's bus differs * from the original device. */ - clone_alias(pdev, iommu->pci_seg->alias_table[pci_dev_id(pdev)], NULL); + clone_alias(pdev, iommu->pci_seg->alias_table[pci_dev_id(pdev)], pdev); - pci_for_each_dma_alias(pdev, clone_alias, NULL); + pci_for_each_dma_alias(pdev, clone_alias, pdev); } static void setup_aliases(struct amd_iommu *iommu, struct device *dev) From 9f0632b0d4246675fa221aa1a3bffadf9c6bd9ac Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 27 Mar 2026 12:22:10 -0300 Subject: [PATCH 0480/1518] iommu/riscv: Remove overflows on the invalidation path [ Upstream commit 40a13b49957937427bc23e78eb50679df4396a47 ] Since RISC-V supports a sign extended page table it should support a gather->end of ULONG_MAX, but if this happens it will infinite loop because of the overflow. Also avoid overflow computing the length by moving the +1 to the other side of the < Fixes: 488ffbf18171 ("iommu/riscv: Paging domain support") Signed-off-by: Jason Gunthorpe Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/riscv/iommu.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index 1e8007a153c32..de286563bd44e 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -931,8 +931,6 @@ static void riscv_iommu_iotlb_inval(struct riscv_iommu_domain *domain, struct riscv_iommu_bond *bond; struct riscv_iommu_device *iommu, *prev; struct riscv_iommu_command cmd; - unsigned long len = end - start + 1; - unsigned long iova; /* * For each IOMMU linked with this protection domain (via bonds->dev), @@ -975,11 +973,14 @@ static void riscv_iommu_iotlb_inval(struct riscv_iommu_domain *domain, riscv_iommu_cmd_inval_vma(&cmd); riscv_iommu_cmd_inval_set_pscid(&cmd, domain->pscid); - if (len && len < RISCV_IOMMU_IOTLB_INVAL_LIMIT) { - for (iova = start; iova < end; iova += PAGE_SIZE) { + if (end - start < RISCV_IOMMU_IOTLB_INVAL_LIMIT - 1) { + unsigned long iova = start; + + do { riscv_iommu_cmd_inval_set_addr(&cmd, iova); riscv_iommu_cmd_send(iommu, &cmd); - } + } while (!check_add_overflow(iova, PAGE_SIZE, &iova) && + iova < end); } else { riscv_iommu_cmd_send(iommu, &cmd); } From a1a24d4b8c9682f9b7a9138f636ff004c721aef1 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 2 Apr 2026 08:11:08 +0000 Subject: [PATCH 0481/1518] ASoC: qcom: qdsp6: topology: check widget type before accessing data [ Upstream commit d5bfdd28e0cdd45043ae6e0ac168a451d59283dc ] Check widget type before accessing the private data, as this could a virtual widget which is no associated with a dsp graph, container and module. Accessing witout check could lead to incorrect memory access. Fixes: 36ad9bf1d93d ("ASoC: qdsp6: audioreach: add topology support") Signed-off-by: Srinivas Kandagatla Link: https://patch.msgid.link/20260402081118.348071-4-srinivas.kandagatla@oss.qualcomm.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/qcom/qdsp6/topology.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/sound/soc/qcom/qdsp6/topology.c b/sound/soc/qcom/qdsp6/topology.c index f61285e7dcf20..f8d3bb83e3b0d 100644 --- a/sound/soc/qcom/qdsp6/topology.c +++ b/sound/soc/qcom/qdsp6/topology.c @@ -952,9 +952,6 @@ static int audioreach_widget_unload(struct snd_soc_component *scomp, struct audioreach_container *cont; struct audioreach_module *mod; - mod = dobj->private; - cont = mod->container; - if (w->id == snd_soc_dapm_mixer) { /* virtual widget */ struct snd_ar_control *scontrol = dobj->private; @@ -963,6 +960,11 @@ static int audioreach_widget_unload(struct snd_soc_component *scomp, kfree(scontrol); return 0; } + mod = dobj->private; + if (!mod) + return 0; + + cont = mod->container; mutex_lock(&apm->lock); idr_remove(&apm->modules_idr, mod->instance_id); From 44faf7ea013c28f9231a64744c155b0126f89a2c Mon Sep 17 00:00:00 2001 From: Hans Zhang <18255117159@163.com> Date: Wed, 1 Apr 2026 10:30:48 +0800 Subject: [PATCH 0482/1518] PCI: dwc: Fix type mismatch for kstrtou32_from_user() return value [ Upstream commit 445588a3b18bb0702d746cb61f7a443639027651 ] kstrtou32_from_user() returns int, but the return value was stored in a u32 variable 'val', risking sign loss. Use a dedicated int variable to correctly handle the return code. Fixes: 4fbfa17f9a07 ("PCI: dwc: Add debugfs based Silicon Debug support for DWC") Signed-off-by: Hans Zhang <18255117159@163.com> Signed-off-by: Manivannan Sadhasivam Link: https://patch.msgid.link/20260401023048.4182452-1-18255117159@163.com Signed-off-by: Sasha Levin --- .../controller/dwc/pcie-designware-debugfs.c | 21 +++++++++++-------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-debugfs.c b/drivers/pci/controller/dwc/pcie-designware-debugfs.c index df98fee69892b..afcc08efe2531 100644 --- a/drivers/pci/controller/dwc/pcie-designware-debugfs.c +++ b/drivers/pci/controller/dwc/pcie-designware-debugfs.c @@ -208,10 +208,11 @@ static ssize_t lane_detect_write(struct file *file, const char __user *buf, struct dw_pcie *pci = file->private_data; struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; u32 lane, val; + int ret; - val = kstrtou32_from_user(buf, count, 0, &lane); - if (val) - return val; + ret = kstrtou32_from_user(buf, count, 0, &lane); + if (ret) + return ret; val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); val &= ~(LANE_SELECT); @@ -347,10 +348,11 @@ static ssize_t counter_enable_write(struct file *file, const char __user *buf, struct dw_pcie *pci = pdata->pci; struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; u32 val, enable; + int ret; - val = kstrtou32_from_user(buf, count, 0, &enable); - if (val) - return val; + ret = kstrtou32_from_user(buf, count, 0, &enable); + if (ret) + return ret; mutex_lock(&rinfo->reg_event_lock); set_event_number(pdata, pci, rinfo); @@ -408,10 +410,11 @@ static ssize_t counter_lane_write(struct file *file, const char __user *buf, struct dw_pcie *pci = pdata->pci; struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; u32 val, lane; + int ret; - val = kstrtou32_from_user(buf, count, 0, &lane); - if (val) - return val; + ret = kstrtou32_from_user(buf, count, 0, &lane); + if (ret) + return ret; mutex_lock(&rinfo->reg_event_lock); set_event_number(pdata, pci, rinfo); From 6aef8e6fdf4d3dae5ea87b3af78a0c88d78f0c2f Mon Sep 17 00:00:00 2001 From: Ahsan Atta Date: Tue, 24 Mar 2026 11:11:12 +0000 Subject: [PATCH 0483/1518] crypto: qat - disable 4xxx AE cluster when lead engine is fused off [ Upstream commit b260d53561dd69b29505222ec44cf386ac2c2ca6 ] The get_ae_mask() function only disables individual engines based on the fuse register, but engines are organized in clusters of 4. If the lead engine of a cluster is fused off, the entire cluster must be disabled. Replace the single bitmask inversion with explicit test_bit() checks on the lead engine of each group, disabling the full ADF_AE_GROUP when the lead bit is set. Signed-off-by: Ahsan Atta Reviewed-by: Giovanni Cabiddu Fixes: 8c8268166e834 ("crypto: qat - add qat_4xxx driver") Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- .../crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c index 740f68a36ac51..900f19b90b2dc 100644 --- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c +++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c @@ -100,9 +100,19 @@ static struct adf_hw_device_class adf_4xxx_class = { static u32 get_ae_mask(struct adf_hw_device_data *self) { - u32 me_disable = self->fuses[ADF_FUSECTL4]; + unsigned long fuses = self->fuses[ADF_FUSECTL4]; + u32 mask = ADF_4XXX_ACCELENGINES_MASK; - return ~me_disable & ADF_4XXX_ACCELENGINES_MASK; + if (test_bit(0, &fuses)) + mask &= ~ADF_AE_GROUP_0; + + if (test_bit(4, &fuses)) + mask &= ~ADF_AE_GROUP_1; + + if (test_bit(8, &fuses)) + mask &= ~ADF_AE_GROUP_2; + + return mask; } static u32 get_accel_cap(struct adf_accel_dev *accel_dev) From 06b30beb9104390137e31ec9694b5aad01dd406f Mon Sep 17 00:00:00 2001 From: Ahsan Atta Date: Tue, 24 Mar 2026 11:12:34 +0000 Subject: [PATCH 0484/1518] crypto: qat - disable 420xx AE cluster when lead engine is fused off [ Upstream commit f216e0f2d1787e662bb6662c9c522185aa3b855a ] The get_ae_mask() function only disables individual engines based on the fuse register, but engines are organized in clusters of 4. If the lead engine of a cluster is fused off, the entire cluster must be disabled. Replace the single bitmask inversion with explicit test_bit() checks on the lead engine of each group, disabling the full ADF_AE_GROUP when the lead bit is set. Signed-off-by: Ahsan Atta Reviewed-by: Giovanni Cabiddu Fixes: fcf60f4bcf54 ("crypto: qat - add support for 420xx devices") Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- .../intel/qat/qat_420xx/adf_420xx_hw_data.c | 20 +++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c index 53fa91d577ed0..cb52aaa323a7e 100644 --- a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c +++ b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c @@ -96,9 +96,25 @@ static struct adf_hw_device_class adf_420xx_class = { static u32 get_ae_mask(struct adf_hw_device_data *self) { - u32 me_disable = self->fuses[ADF_FUSECTL4]; + unsigned long fuses = self->fuses[ADF_FUSECTL4]; + u32 mask = ADF_420XX_ACCELENGINES_MASK; - return ~me_disable & ADF_420XX_ACCELENGINES_MASK; + if (test_bit(0, &fuses)) + mask &= ~ADF_AE_GROUP_0; + + if (test_bit(4, &fuses)) + mask &= ~ADF_AE_GROUP_1; + + if (test_bit(8, &fuses)) + mask &= ~ADF_AE_GROUP_2; + + if (test_bit(12, &fuses)) + mask &= ~ADF_AE_GROUP_3; + + if (test_bit(16, &fuses)) + mask &= ~ADF_AE_GROUP_4; + + return mask; } static u32 uof_get_num_objs(struct adf_accel_dev *accel_dev) From 684bd5404f9c3605b8e10be7c7affe88fd198121 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Tue, 24 Mar 2026 17:59:40 +0000 Subject: [PATCH 0485/1518] crypto: qat - fix compression instance leak [ Upstream commit 795c24c677c7a1c12f5768daf22a874a2890662f ] qat_comp_alg_init_tfm() acquires a compression instance via qat_compression_get_instance_node() before calling qat_comp_build_ctx() to initialize the compression context. If qat_comp_build_ctx() fails, the function returns an error without releasing the compression instance, causing a resource leak. When qat_comp_build_ctx() fails, release the compression instance with qat_compression_put_instance() and clear the context to avoid leaving a stale reference to the released instance. The issue was introduced when build_deflate_ctx() (which always returned void) was replaced by qat_comp_build_ctx() (which can return an error) without adding error handling for the failure path. Fixes: cd0e7160f80f ("crypto: qat - refactor compression template logic") Signed-off-by: Giovanni Cabiddu Reviewed-by: Laurent M Coquerel Reviewed-by: Ahsan Atta Reviewed-by: Wojciech Drewek Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/intel/qat/qat_common/qat_comp_algs.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c index 8b123472b71cc..4273a0ecb6c80 100644 --- a/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c +++ b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c @@ -133,7 +133,7 @@ static int qat_comp_alg_init_tfm(struct crypto_acomp *acomp_tfm) struct crypto_tfm *tfm = crypto_acomp_tfm(acomp_tfm); struct qat_compression_ctx *ctx = crypto_tfm_ctx(tfm); struct qat_compression_instance *inst; - int node; + int node, ret; if (tfm->node == NUMA_NO_NODE) node = numa_node_id(); @@ -146,7 +146,13 @@ static int qat_comp_alg_init_tfm(struct crypto_acomp *acomp_tfm) return -EINVAL; ctx->inst = inst; - return qat_comp_build_ctx(inst->accel_dev, ctx->comp_ctx, QAT_DEFLATE); + ret = qat_comp_build_ctx(inst->accel_dev, ctx->comp_ctx, QAT_DEFLATE); + if (ret) { + qat_compression_put_instance(inst); + memset(ctx, 0, sizeof(*ctx)); + } + + return ret; } static void qat_comp_alg_exit_tfm(struct crypto_acomp *acomp_tfm) From 52906bb0f636c4279a263ea19a76deb824d47e39 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Tue, 24 Mar 2026 18:17:23 +0000 Subject: [PATCH 0486/1518] crypto: qat - fix type mismatch in RAS sysfs show functions [ Upstream commit ec23d75c4b77ae42af0777ea59599b1d4f611371 ] ADF_RAS_ERR_CTR_READ() expands to atomic_read(), which returns int. The local variable 'counter' was declared as 'unsigned long', causing a type mismatch on the assignment. The format specifier '%ld' was consequently wrong in two ways: wrong length modifier and wrong signedness. Use int to match the return type of atomic_read() and update the format specifier to '%d' accordingly. Fixes: 532d7f6bc458 ("crypto: qat - add error counters") Signed-off-by: Giovanni Cabiddu Reviewed-by: Ahsan Atta Reviewed-by: Andy Shevchenko Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- .../intel/qat/qat_common/adf_sysfs_ras_counters.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c index e97c67c87b3cf..6abb57bfd3285 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c +++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs_ras_counters.c @@ -13,14 +13,14 @@ static ssize_t errors_correctable_show(struct device *dev, char *buf) { struct adf_accel_dev *accel_dev; - unsigned long counter; + int counter; accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); if (!accel_dev) return -EINVAL; counter = ADF_RAS_ERR_CTR_READ(accel_dev->ras_errors, ADF_RAS_CORR); - return scnprintf(buf, PAGE_SIZE, "%ld\n", counter); + return scnprintf(buf, PAGE_SIZE, "%d\n", counter); } static ssize_t errors_nonfatal_show(struct device *dev, @@ -28,14 +28,14 @@ static ssize_t errors_nonfatal_show(struct device *dev, char *buf) { struct adf_accel_dev *accel_dev; - unsigned long counter; + int counter; accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); if (!accel_dev) return -EINVAL; counter = ADF_RAS_ERR_CTR_READ(accel_dev->ras_errors, ADF_RAS_UNCORR); - return scnprintf(buf, PAGE_SIZE, "%ld\n", counter); + return scnprintf(buf, PAGE_SIZE, "%d\n", counter); } static ssize_t errors_fatal_show(struct device *dev, @@ -43,14 +43,14 @@ static ssize_t errors_fatal_show(struct device *dev, char *buf) { struct adf_accel_dev *accel_dev; - unsigned long counter; + int counter; accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); if (!accel_dev) return -EINVAL; counter = ADF_RAS_ERR_CTR_READ(accel_dev->ras_errors, ADF_RAS_FATAL); - return scnprintf(buf, PAGE_SIZE, "%ld\n", counter); + return scnprintf(buf, PAGE_SIZE, "%d\n", counter); } static ssize_t reset_error_counters_store(struct device *dev, From 8d77cf260535e0b2b7692212a8df2c03629a56ca Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Tue, 24 Mar 2026 18:29:05 +0000 Subject: [PATCH 0487/1518] crypto: iaa - fix per-node CPU counter reset in rebalance_wq_table() [ Upstream commit 590fa5d69c27cfaecd2e8287aec78f902417c877 ] The cpu counter used to compute the IAA device index is reset to zero at the start of each NUMA node iteration. This causes CPUs on every node to map starting from IAA index 0 instead of continuing from the previous node's last index. On multi-node systems, this results in all nodes mapping their CPUs to the same initial set of IAA devices, leaving higher-indexed devices unused. Move the cpu counter initialization before the for_each_node_with_cpus() loop so that the IAA index computation accumulates correctly across all nodes. Fixes: 714ca27e9bf4 ("crypto: iaa - Optimize rebalance_wq_table()") Signed-off-by: Giovanni Cabiddu Acked-by: Vinicius Costa Gomes Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/intel/iaa/iaa_crypto_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c index da9b2bc515194..78218f3a3cd06 100644 --- a/drivers/crypto/intel/iaa/iaa_crypto_main.c +++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c @@ -911,8 +911,8 @@ static void rebalance_wq_table(void) return; } + cpu = 0; for_each_node_with_cpus(node) { - cpu = 0; node_cpus = cpumask_of_node(node); for_each_cpu(node_cpu, node_cpus) { From 254091c91767ee282fb75bde980134ab6e3626cc Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Sat, 28 Mar 2026 22:29:46 +0000 Subject: [PATCH 0488/1518] crypto: qat - use swab32 macro [ Upstream commit 35ecb77ae0749a2f1b04872c9978d9d7ddbbeb79 ] Replace __builtin_bswap32() with swab32 in icp_qat_hw_20_comp.h to fix the following build errors on architectures without native byte-swap support: alpha-linux-ld: drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.o: in function `adf_gen4_build_decomp_block': drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h:141:(.text+0xeec): undefined reference to `__bswapsi2' alpha-linux-ld: drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h:141:(.text+0xef8): undefined reference to `__bswapsi2' alpha-linux-ld: drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.o: in function `adf_gen4_build_comp_block': drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h:57:(.text+0xf64): undefined reference to `__bswapsi2' alpha-linux-ld: drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h:57:(.text+0xf7c): undefined reference to `__bswapsi2' Fixes: 5b14b2b307e4 ("crypto: qat - enable deflate for QAT GEN4") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202603290259.Ig9kDOmI-lkp@intel.com/ Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- .../crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h b/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h index 7ea8962272f2f..d28732225c9e0 100644 --- a/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h +++ b/drivers/crypto/intel/qat/qat_common/icp_qat_hw_20_comp.h @@ -3,6 +3,8 @@ #ifndef _ICP_QAT_HW_20_COMP_H_ #define _ICP_QAT_HW_20_COMP_H_ +#include + #include "icp_qat_hw_20_comp_defs.h" #include "icp_qat_fw.h" @@ -54,7 +56,7 @@ ICP_QAT_FW_COMP_20_BUILD_CONFIG_LOWER(struct icp_qat_hw_comp_20_config_csr_lower QAT_FIELD_SET(val32, csr.abd, ICP_QAT_HW_COMP_20_CONFIG_CSR_ABD_BITPOS, ICP_QAT_HW_COMP_20_CONFIG_CSR_ABD_MASK); - return __builtin_bswap32(val32); + return swab32(val32); } struct icp_qat_hw_comp_20_config_csr_upper { @@ -106,7 +108,7 @@ ICP_QAT_FW_COMP_20_BUILD_CONFIG_UPPER(struct icp_qat_hw_comp_20_config_csr_upper ICP_QAT_HW_COMP_20_CONFIG_CSR_NICE_PARAM_BITPOS, ICP_QAT_HW_COMP_20_CONFIG_CSR_NICE_PARAM_MASK); - return __builtin_bswap32(val32); + return swab32(val32); } struct icp_qat_hw_decomp_20_config_csr_lower { @@ -138,7 +140,7 @@ ICP_QAT_FW_DECOMP_20_BUILD_CONFIG_LOWER(struct icp_qat_hw_decomp_20_config_csr_l ICP_QAT_HW_DECOMP_20_CONFIG_CSR_LZ4_BLOCK_CHECKSUM_PRESENT_BITPOS, ICP_QAT_HW_DECOMP_20_CONFIG_CSR_LZ4_BLOCK_CHECKSUM_PRESENT_MASK); - return __builtin_bswap32(val32); + return swab32(val32); } struct icp_qat_hw_decomp_20_config_csr_upper { @@ -158,7 +160,7 @@ ICP_QAT_FW_DECOMP_20_BUILD_CONFIG_UPPER(struct icp_qat_hw_decomp_20_config_csr_u ICP_QAT_HW_DECOMP_20_CONFIG_CSR_MINI_CAM_CONTROL_BITPOS, ICP_QAT_HW_DECOMP_20_CONFIG_CSR_MINI_CAM_CONTROL_MASK); - return __builtin_bswap32(val32); + return swab32(val32); } #endif From 134c61925e9e9ee0f4fdbab5c3984d5bb024f5f5 Mon Sep 17 00:00:00 2001 From: Denis Rastyogin Date: Fri, 27 Mar 2026 13:33:11 +0300 Subject: [PATCH 0489/1518] ASoC: rsnd: Fix potential out-of-bounds access of component_dais[] [ Upstream commit f9e437cddf6cf9e603bdaefe148c1f4792aaf39c ] component_dais[RSND_MAX_COMPONENT] is initially zero-initialized and later populated in rsnd_dai_of_node(). However, the existing boundary check: if (i >= RSND_MAX_COMPONENT) does not guarantee that the last valid element remains zero. As a result, the loop can rely on component_dais[RSND_MAX_COMPONENT] being zero, which may lead to an out-of-bounds access. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 547b02f74e4a ("ASoC: rsnd: enable multi Component support for Audio Graph Card/Card2") Signed-off-by: Denis Rastyogin Acked-by: Kuninori Morimoto Link: https://patch.msgid.link/20260327103311.459239-1-gerben@altlinux.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/renesas/rcar/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/renesas/rcar/core.c b/sound/soc/renesas/rcar/core.c index 69fb19964a71d..2dc078358612d 100644 --- a/sound/soc/renesas/rcar/core.c +++ b/sound/soc/renesas/rcar/core.c @@ -1974,7 +1974,7 @@ static int rsnd_probe(struct platform_device *pdev) * asoc register */ ci = 0; - for (i = 0; priv->component_dais[i] > 0; i++) { + for (i = 0; i < RSND_MAX_COMPONENT && priv->component_dais[i] > 0; i++) { int nr = priv->component_dais[i]; ret = devm_snd_soc_register_component(dev, &rsnd_soc_component, From db805e9399c8cdfa19f57aababb4f22d01dc64c1 Mon Sep 17 00:00:00 2001 From: Gerd Bayer Date: Mon, 30 Mar 2026 15:09:45 +0200 Subject: [PATCH 0490/1518] PCI: Enable AtomicOps only if Root Port supports them [ Upstream commit 1ae8c4ce157037e266184064a182af9ef9af278b ] When inspecting the config space of a Connect-X physical function in an s390 system after it was initialized by the mlx5_core device driver, we found the function to be enabled to request AtomicOps despite the Root Port lacking support for completing them: 00:00.1 Ethernet controller: Mellanox Technologies MT2894 Family [ConnectX-6 Lx] Subsystem: Mellanox Technologies Device 0002 DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis- AtomicOpsCtl: ReqEn+ On s390 and many virtualized guests, the Endpoint is visible but the Root Port is not. In this case, pci_enable_atomic_ops_to_root() previously enabled AtomicOps in the Endpoint even though it can't tell whether the Root Port supports them as a completer. Change pci_enable_atomic_ops_to_root() to fail if there's no Root Port or the Root Port doesn't support AtomicOps. Fixes: 430a23689dea ("PCI: Add pci_enable_atomic_ops_to_root()") Reported-by: Alexander Schmidt Signed-off-by: Gerd Bayer [bhelgaas: commit log, check RP first to simplify flow] Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20260330-fix_pciatops-v7-2-f601818417e8@linux.ibm.com Signed-off-by: Sasha Levin --- drivers/pci/pci.c | 41 ++++++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 21 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a62ed5560c68f..0b6a23405f167 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3818,8 +3818,7 @@ int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) */ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask) { - struct pci_bus *bus = dev->bus; - struct pci_dev *bridge; + struct pci_dev *root, *bridge; u32 cap, ctl2; /* @@ -3849,35 +3848,35 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask) return -EINVAL; } - while (bus->parent) { - bridge = bus->self; + root = pcie_find_root_port(dev); + if (!root) + return -EINVAL; - pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &cap); + pcie_capability_read_dword(root, PCI_EXP_DEVCAP2, &cap); + if ((cap & cap_mask) != cap_mask) + return -EINVAL; + bridge = pci_upstream_bridge(dev); + while (bridge != root) { switch (pci_pcie_type(bridge)) { - /* Ensure switch ports support AtomicOp routing */ case PCI_EXP_TYPE_UPSTREAM: - case PCI_EXP_TYPE_DOWNSTREAM: - if (!(cap & PCI_EXP_DEVCAP2_ATOMIC_ROUTE)) - return -EINVAL; - break; - - /* Ensure root port supports all the sizes we care about */ - case PCI_EXP_TYPE_ROOT_PORT: - if ((cap & cap_mask) != cap_mask) - return -EINVAL; - break; - } - - /* Ensure upstream ports don't block AtomicOps on egress */ - if (pci_pcie_type(bridge) == PCI_EXP_TYPE_UPSTREAM) { + /* Upstream ports must not block AtomicOps on egress */ pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2, &ctl2); if (ctl2 & PCI_EXP_DEVCTL2_ATOMIC_EGRESS_BLOCK) return -EINVAL; + fallthrough; + + /* All switch ports need to route AtomicOps */ + case PCI_EXP_TYPE_DOWNSTREAM: + pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, + &cap); + if (!(cap & PCI_EXP_DEVCAP2_ATOMIC_ROUTE)) + return -EINVAL; + break; } - bus = bus->parent; + bridge = pci_upstream_bridge(bridge); } pcie_capability_set_word(dev, PCI_EXP_DEVCTL2, From 0a2d60edc3e57c9512e239ebdfd12204d3368560 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 24 Mar 2026 17:35:41 +0800 Subject: [PATCH 0491/1518] PCI: mediatek-gen3: Prevent leaking IRQ domains when IRQ not found [ Upstream commit 5573c44cb3fd01a9f62d569ae9ac870ef5f0e0ba ] In mtk_pcie_setup_irq(), the IRQ domains are allocated before the controller's IRQ is fetched. If the latter fails, the function directly returns an error, without cleaning up the allocated domains. Hence, reverse the order so that the IRQ domains are allocated after the controller's IRQ is found. This was flagged by Sashiko during a review of "[PATCH v6 0/7] PCI: mediatek-gen3: add power control support". Fixes: 814cceebba9b ("PCI: mediatek-gen3: Add INTx support") Signed-off-by: Chen-Yu Tsai Signed-off-by: Manivannan Sadhasivam Link: https://sashiko.dev/#/patchset/20260324052002.4072430-1-wenst%40chromium.org Link: https://patch.msgid.link/20260324093542.18523-1-wenst@chromium.org Signed-off-by: Sasha Levin --- drivers/pci/controller/pcie-mediatek-gen3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c index 75ddb8bee168f..e45c43ccc84c2 100644 --- a/drivers/pci/controller/pcie-mediatek-gen3.c +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -851,14 +851,14 @@ static int mtk_pcie_setup_irq(struct mtk_gen3_pcie *pcie) struct platform_device *pdev = to_platform_device(dev); int err; - err = mtk_pcie_init_irq_domains(pcie); - if (err) - return err; - pcie->irq = platform_get_irq(pdev, 0); if (pcie->irq < 0) return pcie->irq; + err = mtk_pcie_init_irq_domains(pcie); + if (err) + return err; + irq_set_chained_handler_and_data(pcie->irq, mtk_pcie_irq_handler, pcie); return 0; From e6b0e1f74d355a207dee4cc76ad91178bd4457f0 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Thu, 16 Oct 2025 11:13:20 -0400 Subject: [PATCH 0492/1518] gpu: nova-core: register: use field type for Into implementation [ Upstream commit 3f674dc4ef1b3783f9d8dae33b46bf50eaac7c79 ] The getter method of a field works with the field type, but its setter expects the type of the register. This leads to an asymmetry in the From/Into implementations required for a field with a dedicated type. For instance, a field declared as pub struct ControlReg(u32) { 3:0 mode as u8 ?=> Mode; ... } currently requires the following implementations: impl TryFrom for Mode { ... } impl From for u32 { ... } Change this so the `From` now needs to be implemented for `u8`, i.e. the primitive type of the field. This is more consistent, and will become a requirement once we start using the TryFrom/Into derive macros to implement these automatically. Reported-by: Edwin Peer Closes: https://lore.kernel.org/rust-for-linux/F3853912-2C1C-4F9B-89B0-3168689F35B3@nvidia.com/ Reviewed-by: Joel Fernandes Signed-off-by: Joel Fernandes Signed-off-by: Alexandre Courbot Message-ID: <20251016151323.1201196-2-joelagnelf@nvidia.com> Stable-dep-of: de0aca13509b ("gpu: nova-core: bitfield: fix broken Default implementation") Signed-off-by: Sasha Levin --- drivers/gpu/nova-core/falcon.rs | 38 ++++++++++++++++++++-------- drivers/gpu/nova-core/regs/macros.rs | 10 ++++---- 2 files changed, 32 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/nova-core/falcon.rs b/drivers/gpu/nova-core/falcon.rs index 37e6298195e49..3f505b8706011 100644 --- a/drivers/gpu/nova-core/falcon.rs +++ b/drivers/gpu/nova-core/falcon.rs @@ -22,11 +22,11 @@ mod hal; pub(crate) mod sec2; // TODO[FPRI]: Replace with `ToPrimitive`. -macro_rules! impl_from_enum_to_u32 { +macro_rules! impl_from_enum_to_u8 { ($enum_type:ty) => { - impl From<$enum_type> for u32 { + impl From<$enum_type> for u8 { fn from(value: $enum_type) -> Self { - value as u32 + value as u8 } } }; @@ -46,7 +46,7 @@ pub(crate) enum FalconCoreRev { Rev6 = 6, Rev7 = 7, } -impl_from_enum_to_u32!(FalconCoreRev); +impl_from_enum_to_u8!(FalconCoreRev); // TODO[FPRI]: replace with `FromPrimitive`. impl TryFrom for FalconCoreRev { @@ -81,7 +81,7 @@ pub(crate) enum FalconCoreRevSubversion { Subversion2 = 2, Subversion3 = 3, } -impl_from_enum_to_u32!(FalconCoreRevSubversion); +impl_from_enum_to_u8!(FalconCoreRevSubversion); // TODO[FPRI]: replace with `FromPrimitive`. impl TryFrom for FalconCoreRevSubversion { @@ -125,7 +125,7 @@ pub(crate) enum FalconSecurityModel { /// Also known as High-Secure, Privilege Level 3 or PL3. Heavy = 3, } -impl_from_enum_to_u32!(FalconSecurityModel); +impl_from_enum_to_u8!(FalconSecurityModel); // TODO[FPRI]: replace with `FromPrimitive`. impl TryFrom for FalconSecurityModel { @@ -157,7 +157,7 @@ pub(crate) enum FalconModSelAlgo { #[default] Rsa3k = 1, } -impl_from_enum_to_u32!(FalconModSelAlgo); +impl_from_enum_to_u8!(FalconModSelAlgo); // TODO[FPRI]: replace with `FromPrimitive`. impl TryFrom for FalconModSelAlgo { @@ -179,7 +179,7 @@ pub(crate) enum DmaTrfCmdSize { #[default] Size256B = 0x6, } -impl_from_enum_to_u32!(DmaTrfCmdSize); +impl_from_enum_to_u8!(DmaTrfCmdSize); // TODO[FPRI]: replace with `FromPrimitive`. impl TryFrom for DmaTrfCmdSize { @@ -202,7 +202,6 @@ pub(crate) enum PeregrineCoreSelect { /// RISC-V core is active. Riscv = 1, } -impl_from_enum_to_u32!(PeregrineCoreSelect); impl From for PeregrineCoreSelect { fn from(value: bool) -> Self { @@ -213,6 +212,15 @@ impl From for PeregrineCoreSelect { } } +impl From for bool { + fn from(value: PeregrineCoreSelect) -> Self { + match value { + PeregrineCoreSelect::Falcon => false, + PeregrineCoreSelect::Riscv => true, + } + } +} + /// Different types of memory present in a falcon core. #[derive(Debug, Clone, Copy, PartialEq, Eq)] pub(crate) enum FalconMem { @@ -236,7 +244,7 @@ pub(crate) enum FalconFbifTarget { /// Non-coherent system memory (System DRAM). NoncoherentSysmem = 2, } -impl_from_enum_to_u32!(FalconFbifTarget); +impl_from_enum_to_u8!(FalconFbifTarget); // TODO[FPRI]: replace with `FromPrimitive`. impl TryFrom for FalconFbifTarget { @@ -263,7 +271,6 @@ pub(crate) enum FalconFbifMemType { /// Physical memory addresses. Physical = 1, } -impl_from_enum_to_u32!(FalconFbifMemType); /// Conversion from a single-bit register field. impl From for FalconFbifMemType { @@ -275,6 +282,15 @@ impl From for FalconFbifMemType { } } +impl From for bool { + fn from(value: FalconFbifMemType) -> Self { + match value { + FalconFbifMemType::Virtual => false, + FalconFbifMemType::Physical => true, + } + } +} + /// Type used to represent the `PFALCON` registers address base for a given falcon engine. pub(crate) struct PFalconBase(()); diff --git a/drivers/gpu/nova-core/regs/macros.rs b/drivers/gpu/nova-core/regs/macros.rs index 8058e1696df97..1c54a4533822e 100644 --- a/drivers/gpu/nova-core/regs/macros.rs +++ b/drivers/gpu/nova-core/regs/macros.rs @@ -482,7 +482,7 @@ macro_rules! register { register!( @leaf_accessor $name $hi:$lo $field { |f| <$into_type>::from(if f != 0 { true } else { false }) } - $into_type => $into_type $(, $comment)?; + bool $into_type => $into_type $(, $comment)?; ); }; @@ -499,7 +499,7 @@ macro_rules! register { $(, $comment:literal)?; ) => { register!(@leaf_accessor $name $hi:$lo $field - { |f| <$try_into_type>::try_from(f as $type) } $try_into_type => + { |f| <$try_into_type>::try_from(f as $type) } $type $try_into_type => ::core::result::Result< $try_into_type, <$try_into_type as ::core::convert::TryFrom<$type>>::Error @@ -513,7 +513,7 @@ macro_rules! register { $(, $comment:literal)?; ) => { register!(@leaf_accessor $name $hi:$lo $field - { |f| <$into_type>::from(f as $type) } $into_type => $into_type $(, $comment)?;); + { |f| <$into_type>::from(f as $type) } $type $into_type => $into_type $(, $comment)?;); }; // Shortcut for non-boolean fields defined without the `=>` or `?=>` syntax. @@ -527,7 +527,7 @@ macro_rules! register { // Generates the accessor methods for a single field. ( @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident - { $process:expr } $to_type:ty => $res_type:ty $(, $comment:literal)?; + { $process:expr } $prim_type:tt $to_type:ty => $res_type:ty $(, $comment:literal)?; ) => { ::kernel::macros::paste!( const [<$field:upper _RANGE>]: ::core::ops::RangeInclusive = $lo..=$hi; @@ -559,7 +559,7 @@ macro_rules! register { pub(crate) fn [](mut self, value: $to_type) -> Self { const MASK: u32 = $name::[<$field:upper _MASK>]; const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; - let value = (u32::from(value) << SHIFT) & MASK; + let value = (u32::from($prim_type::from(value)) << SHIFT) & MASK; self.0 = (self.0 & !MASK) | value; self From af46044d16714911d0e2c45f4d5697f89221a6f8 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 16 Oct 2025 11:13:21 -0400 Subject: [PATCH 0493/1518] gpu: nova-core: bitfield: Move bitfield-specific code from register! into new macro [ Upstream commit 71ea85be25b4f54a53ec03d5deaed52f5ee65da8 ] Move the bitfield-specific code from the register macro into a new macro called bitfield. This will be used to define structs with bitfields, similar to C language. Reviewed-by: Elle Rhumsaa Reviewed-by: Alexandre Courbot Reviewed-by: Edwin Peer Signed-off-by: Joel Fernandes Signed-off-by: Alexandre Courbot Message-ID: <20251016151323.1201196-3-joelagnelf@nvidia.com> Stable-dep-of: de0aca13509b ("gpu: nova-core: bitfield: fix broken Default implementation") Signed-off-by: Sasha Levin --- drivers/gpu/nova-core/bitfield.rs | 319 +++++++++++++++++++++++++++ drivers/gpu/nova-core/nova_core.rs | 3 + drivers/gpu/nova-core/regs/macros.rs | 259 +--------------------- 3 files changed, 332 insertions(+), 249 deletions(-) create mode 100644 drivers/gpu/nova-core/bitfield.rs diff --git a/drivers/gpu/nova-core/bitfield.rs b/drivers/gpu/nova-core/bitfield.rs new file mode 100644 index 0000000000000..fb60800898c55 --- /dev/null +++ b/drivers/gpu/nova-core/bitfield.rs @@ -0,0 +1,319 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Bitfield library for Rust structures +//! +//! Support for defining bitfields in Rust structures. Also used by the [`register!`] macro. + +/// Defines a struct with accessors to access bits within an inner unsigned integer. +/// +/// # Syntax +/// +/// ```rust +/// use nova_core::bitfield; +/// +/// #[derive(Debug, Clone, Copy, Default)] +/// enum Mode { +/// #[default] +/// Low = 0, +/// High = 1, +/// Auto = 2, +/// } +/// +/// impl TryFrom for Mode { +/// type Error = u8; +/// fn try_from(value: u8) -> Result { +/// match value { +/// 0 => Ok(Mode::Low), +/// 1 => Ok(Mode::High), +/// 2 => Ok(Mode::Auto), +/// _ => Err(value), +/// } +/// } +/// } +/// +/// impl From for u8 { +/// fn from(mode: Mode) -> u8 { +/// mode as u8 +/// } +/// } +/// +/// #[derive(Debug, Clone, Copy, Default)] +/// enum State { +/// #[default] +/// Inactive = 0, +/// Active = 1, +/// } +/// +/// impl From for State { +/// fn from(value: bool) -> Self { +/// if value { State::Active } else { State::Inactive } +/// } +/// } +/// +/// impl From for bool { +/// fn from(state: State) -> bool { +/// match state { +/// State::Inactive => false, +/// State::Active => true, +/// } +/// } +/// } +/// +/// bitfield! { +/// struct ControlReg { +/// 7:7 state as bool => State; +/// 3:0 mode as u8 ?=> Mode; +/// } +/// } +/// ``` +/// +/// This generates a struct with: +/// - Field accessors: `mode()`, `state()`, etc. +/// - Field setters: `set_mode()`, `set_state()`, etc. (supports chaining with builder pattern). +/// - Debug and Default implementations. +/// +/// Fields are defined as follows: +/// +/// - `as ` simply returns the field value casted to , typically `u32`, `u16`, `u8` or +/// `bool`. Note that `bool` fields must have a range of 1 bit. +/// - `as => ` calls ``'s `From::<>` implementation and returns +/// the result. +/// - `as ?=> ` calls ``'s `TryFrom::<>` implementation +/// and returns the result. This is useful with fields for which not all values are valid. +macro_rules! bitfield { + // Main entry point - defines the bitfield struct with fields + (struct $name:ident $(, $comment:literal)? { $($fields:tt)* }) => { + bitfield!(@core $name $(, $comment)? { $($fields)* }); + }; + + // All rules below are helpers. + + // Defines the wrapper `$name` type, as well as its relevant implementations (`Debug`, + // `Default`, `BitOr`, and conversion to the value type) and field accessor methods. + (@core $name:ident $(, $comment:literal)? { $($fields:tt)* }) => { + $( + #[doc=$comment] + )? + #[repr(transparent)] + #[derive(Clone, Copy)] + pub(crate) struct $name(u32); + + impl ::core::ops::BitOr for $name { + type Output = Self; + + fn bitor(self, rhs: Self) -> Self::Output { + Self(self.0 | rhs.0) + } + } + + impl ::core::convert::From<$name> for u32 { + fn from(val: $name) -> u32 { + val.0 + } + } + + bitfield!(@fields_dispatcher $name { $($fields)* }); + }; + + // Captures the fields and passes them to all the implementers that require field information. + // + // Used to simplify the matching rules for implementers, so they don't need to match the entire + // complex fields rule even though they only make use of part of it. + (@fields_dispatcher $name:ident { + $($hi:tt:$lo:tt $field:ident as $type:tt + $(?=> $try_into_type:ty)? + $(=> $into_type:ty)? + $(, $comment:literal)? + ; + )* + } + ) => { + bitfield!(@field_accessors $name { + $( + $hi:$lo $field as $type + $(?=> $try_into_type)? + $(=> $into_type)? + $(, $comment)? + ; + )* + }); + bitfield!(@debug $name { $($field;)* }); + bitfield!(@default $name { $($field;)* }); + }; + + // Defines all the field getter/setter methods for `$name`. + ( + @field_accessors $name:ident { + $($hi:tt:$lo:tt $field:ident as $type:tt + $(?=> $try_into_type:ty)? + $(=> $into_type:ty)? + $(, $comment:literal)? + ; + )* + } + ) => { + $( + bitfield!(@check_field_bounds $hi:$lo $field as $type); + )* + + #[allow(dead_code)] + impl $name { + $( + bitfield!(@field_accessor $name $hi:$lo $field as $type + $(?=> $try_into_type)? + $(=> $into_type)? + $(, $comment)? + ; + ); + )* + } + }; + + // Boolean fields must have `$hi == $lo`. + (@check_field_bounds $hi:tt:$lo:tt $field:ident as bool) => { + #[allow(clippy::eq_op)] + const _: () = { + ::kernel::build_assert!( + $hi == $lo, + concat!("boolean field `", stringify!($field), "` covers more than one bit") + ); + }; + }; + + // Non-boolean fields must have `$hi >= $lo`. + (@check_field_bounds $hi:tt:$lo:tt $field:ident as $type:tt) => { + #[allow(clippy::eq_op)] + const _: () = { + ::kernel::build_assert!( + $hi >= $lo, + concat!("field `", stringify!($field), "`'s MSB is smaller than its LSB") + ); + }; + }; + + // Catches fields defined as `bool` and convert them into a boolean value. + ( + @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as bool => $into_type:ty + $(, $comment:literal)?; + ) => { + bitfield!( + @leaf_accessor $name $hi:$lo $field + { |f| <$into_type>::from(if f != 0 { true } else { false }) } + bool $into_type => $into_type $(, $comment)?; + ); + }; + + // Shortcut for fields defined as `bool` without the `=>` syntax. + ( + @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as bool $(, $comment:literal)?; + ) => { + bitfield!(@field_accessor $name $hi:$lo $field as bool => bool $(, $comment)?;); + }; + + // Catches the `?=>` syntax for non-boolean fields. + ( + @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt ?=> $try_into_type:ty + $(, $comment:literal)?; + ) => { + bitfield!(@leaf_accessor $name $hi:$lo $field + { |f| <$try_into_type>::try_from(f as $type) } $type $try_into_type => + ::core::result::Result< + $try_into_type, + <$try_into_type as ::core::convert::TryFrom<$type>>::Error + > + $(, $comment)?;); + }; + + // Catches the `=>` syntax for non-boolean fields. + ( + @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt => $into_type:ty + $(, $comment:literal)?; + ) => { + bitfield!(@leaf_accessor $name $hi:$lo $field + { |f| <$into_type>::from(f as $type) } $type $into_type => $into_type $(, $comment)?;); + }; + + // Shortcut for non-boolean fields defined without the `=>` or `?=>` syntax. + ( + @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt + $(, $comment:literal)?; + ) => { + bitfield!(@field_accessor $name $hi:$lo $field as $type => $type $(, $comment)?;); + }; + + // Generates the accessor methods for a single field. + ( + @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident + { $process:expr } $prim_type:tt $to_type:ty => $res_type:ty $(, $comment:literal)?; + ) => { + ::kernel::macros::paste!( + const [<$field:upper _RANGE>]: ::core::ops::RangeInclusive = $lo..=$hi; + const [<$field:upper _MASK>]: u32 = ((((1 << $hi) - 1) << 1) + 1) - ((1 << $lo) - 1); + const [<$field:upper _SHIFT>]: u32 = Self::[<$field:upper _MASK>].trailing_zeros(); + ); + + $( + #[doc="Returns the value of this field:"] + #[doc=$comment] + )? + #[inline(always)] + pub(crate) fn $field(self) -> $res_type { + ::kernel::macros::paste!( + const MASK: u32 = $name::[<$field:upper _MASK>]; + const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; + ); + let field = ((self.0 & MASK) >> SHIFT); + + $process(field) + } + + ::kernel::macros::paste!( + $( + #[doc="Sets the value of this field:"] + #[doc=$comment] + )? + #[inline(always)] + pub(crate) fn [](mut self, value: $to_type) -> Self { + const MASK: u32 = $name::[<$field:upper _MASK>]; + const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; + let value = (u32::from($prim_type::from(value)) << SHIFT) & MASK; + self.0 = (self.0 & !MASK) | value; + + self + } + ); + }; + + // Generates the `Debug` implementation for `$name`. + (@debug $name:ident { $($field:ident;)* }) => { + impl ::kernel::fmt::Debug for $name { + fn fmt(&self, f: &mut ::kernel::fmt::Formatter<'_>) -> ::kernel::fmt::Result { + f.debug_struct(stringify!($name)) + .field("", &::kernel::prelude::fmt!("{:#x}", &self.0)) + $( + .field(stringify!($field), &self.$field()) + )* + .finish() + } + } + }; + + // Generates the `Default` implementation for `$name`. + (@default $name:ident { $($field:ident;)* }) => { + /// Returns a value for the bitfield where all fields are set to their default value. + impl ::core::default::Default for $name { + fn default() -> Self { + #[allow(unused_mut)] + let mut value = Self(Default::default()); + + ::kernel::macros::paste!( + $( + value.[](Default::default()); + )* + ); + + value + } + } + }; +} diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs index fffcaee2249fe..112277c7921eb 100644 --- a/drivers/gpu/nova-core/nova_core.rs +++ b/drivers/gpu/nova-core/nova_core.rs @@ -2,6 +2,9 @@ //! Nova Core GPU Driver +#[macro_use] +mod bitfield; + mod dma; mod driver; mod falcon; diff --git a/drivers/gpu/nova-core/regs/macros.rs b/drivers/gpu/nova-core/regs/macros.rs index 1c54a4533822e..945d15a2c529d 100644 --- a/drivers/gpu/nova-core/regs/macros.rs +++ b/drivers/gpu/nova-core/regs/macros.rs @@ -8,7 +8,8 @@ //! //! The `register!` macro in this module provides an intuitive and readable syntax for defining a //! dedicated type for each register. Each such type comes with its own field accessors that can -//! return an error if a field's value is invalid. +//! return an error if a field's value is invalid. Please look at the [`bitfield`] macro for the +//! complete syntax of fields definitions. /// Trait providing a base address to be added to the offset of a relative register to obtain /// its actual offset. @@ -54,15 +55,6 @@ pub(crate) trait RegisterBase { /// BOOT_0::alter(&bar, |r| r.set_major_revision(3).set_minor_revision(10)); /// ``` /// -/// Fields are defined as follows: -/// -/// - `as ` simply returns the field value casted to , typically `u32`, `u16`, `u8` or -/// `bool`. Note that `bool` fields must have a range of 1 bit. -/// - `as => ` calls ``'s `From::<>` implementation and returns -/// the result. -/// - `as ?=> ` calls ``'s `TryFrom::<>` implementation -/// and returns the result. This is useful with fields for which not all values are valid. -/// /// The documentation strings are optional. If present, they will be added to the type's /// definition, or the field getter and setter methods they are attached to. /// @@ -284,25 +276,25 @@ pub(crate) trait RegisterBase { macro_rules! register { // Creates a register at a fixed offset of the MMIO space. ($name:ident @ $offset:literal $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_fixed $name @ $offset); }; // Creates an alias register of fixed offset register `alias` with its own fields. ($name:ident => $alias:ident $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_fixed $name @ $alias::OFFSET); }; // Creates a register at a relative offset from a base address provider. ($name:ident @ $base:ty [ $offset:literal ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_relative $name @ $base [ $offset ]); }; // Creates an alias register of relative offset register `alias` with its own fields. ($name:ident => $base:ty [ $alias:ident ] $(, $comment:literal)? { $($fields:tt)* }) => { - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_relative $name @ $base [ $alias::OFFSET ]); }; @@ -313,7 +305,7 @@ macro_rules! register { } ) => { static_assert!(::core::mem::size_of::() <= $stride); - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_array $name @ $offset [ $size ; $stride ]); }; @@ -334,7 +326,7 @@ macro_rules! register { $(, $comment:literal)? { $($fields:tt)* } ) => { static_assert!(::core::mem::size_of::() <= $stride); - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_relative_array $name @ $base [ $offset [ $size ; $stride ] ]); }; @@ -356,7 +348,7 @@ macro_rules! register { } ) => { static_assert!($idx < $alias::SIZE); - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_relative $name @ $base [ $alias::OFFSET + $idx * $alias::STRIDE ] ); }; @@ -365,241 +357,10 @@ macro_rules! register { // to avoid it being interpreted in place of the relative register array alias rule. ($name:ident => $alias:ident [ $idx:expr ] $(, $comment:literal)? { $($fields:tt)* }) => { static_assert!($idx < $alias::SIZE); - register!(@core $name $(, $comment)? { $($fields)* } ); + bitfield!(struct $name $(, $comment)? { $($fields)* } ); register!(@io_fixed $name @ $alias::OFFSET + $idx * $alias::STRIDE ); }; - // All rules below are helpers. - - // Defines the wrapper `$name` type, as well as its relevant implementations (`Debug`, - // `Default`, `BitOr`, and conversion to the value type) and field accessor methods. - (@core $name:ident $(, $comment:literal)? { $($fields:tt)* }) => { - $( - #[doc=$comment] - )? - #[repr(transparent)] - #[derive(Clone, Copy)] - pub(crate) struct $name(u32); - - impl ::core::ops::BitOr for $name { - type Output = Self; - - fn bitor(self, rhs: Self) -> Self::Output { - Self(self.0 | rhs.0) - } - } - - impl ::core::convert::From<$name> for u32 { - fn from(reg: $name) -> u32 { - reg.0 - } - } - - register!(@fields_dispatcher $name { $($fields)* }); - }; - - // Captures the fields and passes them to all the implementers that require field information. - // - // Used to simplify the matching rules for implementers, so they don't need to match the entire - // complex fields rule even though they only make use of part of it. - (@fields_dispatcher $name:ident { - $($hi:tt:$lo:tt $field:ident as $type:tt - $(?=> $try_into_type:ty)? - $(=> $into_type:ty)? - $(, $comment:literal)? - ; - )* - } - ) => { - register!(@field_accessors $name { - $( - $hi:$lo $field as $type - $(?=> $try_into_type)? - $(=> $into_type)? - $(, $comment)? - ; - )* - }); - register!(@debug $name { $($field;)* }); - register!(@default $name { $($field;)* }); - }; - - // Defines all the field getter/methods methods for `$name`. - ( - @field_accessors $name:ident { - $($hi:tt:$lo:tt $field:ident as $type:tt - $(?=> $try_into_type:ty)? - $(=> $into_type:ty)? - $(, $comment:literal)? - ; - )* - } - ) => { - $( - register!(@check_field_bounds $hi:$lo $field as $type); - )* - - #[allow(dead_code)] - impl $name { - $( - register!(@field_accessor $name $hi:$lo $field as $type - $(?=> $try_into_type)? - $(=> $into_type)? - $(, $comment)? - ; - ); - )* - } - }; - - // Boolean fields must have `$hi == $lo`. - (@check_field_bounds $hi:tt:$lo:tt $field:ident as bool) => { - #[allow(clippy::eq_op)] - const _: () = { - ::kernel::build_assert!( - $hi == $lo, - concat!("boolean field `", stringify!($field), "` covers more than one bit") - ); - }; - }; - - // Non-boolean fields must have `$hi >= $lo`. - (@check_field_bounds $hi:tt:$lo:tt $field:ident as $type:tt) => { - #[allow(clippy::eq_op)] - const _: () = { - ::kernel::build_assert!( - $hi >= $lo, - concat!("field `", stringify!($field), "`'s MSB is smaller than its LSB") - ); - }; - }; - - // Catches fields defined as `bool` and convert them into a boolean value. - ( - @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as bool => $into_type:ty - $(, $comment:literal)?; - ) => { - register!( - @leaf_accessor $name $hi:$lo $field - { |f| <$into_type>::from(if f != 0 { true } else { false }) } - bool $into_type => $into_type $(, $comment)?; - ); - }; - - // Shortcut for fields defined as `bool` without the `=>` syntax. - ( - @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as bool $(, $comment:literal)?; - ) => { - register!(@field_accessor $name $hi:$lo $field as bool => bool $(, $comment)?;); - }; - - // Catches the `?=>` syntax for non-boolean fields. - ( - @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt ?=> $try_into_type:ty - $(, $comment:literal)?; - ) => { - register!(@leaf_accessor $name $hi:$lo $field - { |f| <$try_into_type>::try_from(f as $type) } $type $try_into_type => - ::core::result::Result< - $try_into_type, - <$try_into_type as ::core::convert::TryFrom<$type>>::Error - > - $(, $comment)?;); - }; - - // Catches the `=>` syntax for non-boolean fields. - ( - @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt => $into_type:ty - $(, $comment:literal)?; - ) => { - register!(@leaf_accessor $name $hi:$lo $field - { |f| <$into_type>::from(f as $type) } $type $into_type => $into_type $(, $comment)?;); - }; - - // Shortcut for non-boolean fields defined without the `=>` or `?=>` syntax. - ( - @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt - $(, $comment:literal)?; - ) => { - register!(@field_accessor $name $hi:$lo $field as $type => $type $(, $comment)?;); - }; - - // Generates the accessor methods for a single field. - ( - @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident - { $process:expr } $prim_type:tt $to_type:ty => $res_type:ty $(, $comment:literal)?; - ) => { - ::kernel::macros::paste!( - const [<$field:upper _RANGE>]: ::core::ops::RangeInclusive = $lo..=$hi; - const [<$field:upper _MASK>]: u32 = ((((1 << $hi) - 1) << 1) + 1) - ((1 << $lo) - 1); - const [<$field:upper _SHIFT>]: u32 = Self::[<$field:upper _MASK>].trailing_zeros(); - ); - - $( - #[doc="Returns the value of this field:"] - #[doc=$comment] - )? - #[inline(always)] - pub(crate) fn $field(self) -> $res_type { - ::kernel::macros::paste!( - const MASK: u32 = $name::[<$field:upper _MASK>]; - const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; - ); - let field = ((self.0 & MASK) >> SHIFT); - - $process(field) - } - - ::kernel::macros::paste!( - $( - #[doc="Sets the value of this field:"] - #[doc=$comment] - )? - #[inline(always)] - pub(crate) fn [](mut self, value: $to_type) -> Self { - const MASK: u32 = $name::[<$field:upper _MASK>]; - const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; - let value = (u32::from($prim_type::from(value)) << SHIFT) & MASK; - self.0 = (self.0 & !MASK) | value; - - self - } - ); - }; - - // Generates the `Debug` implementation for `$name`. - (@debug $name:ident { $($field:ident;)* }) => { - impl ::kernel::fmt::Debug for $name { - fn fmt(&self, f: &mut ::kernel::fmt::Formatter<'_>) -> ::kernel::fmt::Result { - f.debug_struct(stringify!($name)) - .field("", &::kernel::prelude::fmt!("{:#x}", &self.0)) - $( - .field(stringify!($field), &self.$field()) - )* - .finish() - } - } - }; - - // Generates the `Default` implementation for `$name`. - (@default $name:ident { $($field:ident;)* }) => { - /// Returns a value for the register where all fields are set to their default value. - impl ::core::default::Default for $name { - fn default() -> Self { - #[allow(unused_mut)] - let mut value = Self(Default::default()); - - ::kernel::macros::paste!( - $( - value.[](Default::default()); - )* - ); - - value - } - } - }; - // Generates the IO accessors for a fixed offset register. (@io_fixed $name:ident @ $offset:expr) => { #[allow(dead_code)] From fa123b901eb6ff7d8992ee49af1526a22ffdc955 Mon Sep 17 00:00:00 2001 From: Eliot Courtney Date: Wed, 1 Apr 2026 10:42:28 +0900 Subject: [PATCH 0494/1518] gpu: nova-core: bitfield: fix broken Default implementation [ Upstream commit de0aca13509bf47a2d49bc7a26d56079c758c95f ] The current implementation does not actually set the default values for the fields in the bitfield. Fixes: 3fa145bef533 ("gpu: nova-core: register: generate correct `Default` implementation") Signed-off-by: Eliot Courtney Link: https://patch.msgid.link/20260401-fix-bitfield-v2-1-2fa68c98114a@nvidia.com Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/gpu/nova-core/bitfield.rs | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/nova-core/bitfield.rs b/drivers/gpu/nova-core/bitfield.rs index fb60800898c55..1d4931c251bf4 100644 --- a/drivers/gpu/nova-core/bitfield.rs +++ b/drivers/gpu/nova-core/bitfield.rs @@ -303,12 +303,11 @@ macro_rules! bitfield { /// Returns a value for the bitfield where all fields are set to their default value. impl ::core::default::Default for $name { fn default() -> Self { - #[allow(unused_mut)] - let mut value = Self(Default::default()); + let value = Self(Default::default()); ::kernel::macros::paste!( $( - value.[](Default::default()); + let value = value.[](Default::default()); )* ); From 43106160a00b42f10d989e36010db57fd5493eae Mon Sep 17 00:00:00 2001 From: AnishMulay Date: Wed, 18 Feb 2026 11:39:41 -0500 Subject: [PATCH 0495/1518] selftests/mm: skip migration tests if NUMA is unavailable [ Upstream commit 54218f10dfbe88c8e41c744fd45a756cde60b8c4 ] Currently, the migration test asserts that numa_available() returns 0. On systems where NUMA is not available (returning -1), such as certain ARM64 configurations or single-node systems, this assertion fails and crashes the test. Update the test to check the return value of numa_available(). If it is less than 0, skip the test gracefully instead of failing. This aligns the behavior with other MM selftests (like rmap) that skip when NUMA support is missing. Link: https://lkml.kernel.org/r/20260218163941.13499-1-anishm7030@gmail.com Fixes: 0c2d08728470 ("mm: add selftests for migration entries") Signed-off-by: AnishMulay Reviewed-by: SeongJae Park Reviewed-by: Dev Jain Reviewed-by: Anshuman Khandual Tested-by: Sayali Patil Acked-by: David Hildenbrand (Arm) Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- tools/testing/selftests/mm/migration.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index ea945eebec2f6..aa556c708d6bc 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -36,7 +36,8 @@ FIXTURE_SETUP(migration) { int n; - ASSERT_EQ(numa_available(), 0); + if (numa_available() < 0) + SKIP(return, "NUMA not available"); self->nthreads = numa_num_task_cpus() - 1; self->n1 = -1; self->n2 = -1; From fc1ca4f0d6be0939bac2db6f7a1fa681c8775eeb Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Sat, 1 Nov 2025 10:23:17 -0400 Subject: [PATCH 0496/1518] kho: make debugfs interface optional [ Upstream commit 03d3963464a43654703938a66503cd686c5fc54e ] Patch series "liveupdate: Rework KHO for in-kernel users", v9. This series refactors the KHO framework to better support in-kernel users like the upcoming LUO. The current design, which relies on a notifier chain and debugfs for control, is too restrictive for direct programmatic use. The core of this rework is the removal of the notifier chain in favor of a direct registration API. This decouples clients from the shutdown-time finalization sequence, allowing them to manage their preserved state more flexibly and at any time. In support of this new model, this series also: - Makes the debugfs interface optional. - Introduces APIs to unpreserve memory and fixes a bug in the abort path where client state was being incorrectly discarded. Note that this is an interim step, as a more comprehensive fix is planned as part of the stateless KHO work [1]. - Moves all KHO code into a new kernel/liveupdate/ directory to consolidate live update components. This patch (of 9): Currently, KHO is controlled via debugfs interface, but once LUO is introduced, it can control KHO, and the debug interface becomes optional. Add a separate config CONFIG_KEXEC_HANDOVER_DEBUGFS that enables the debugfs interface, and allows to inspect the tree. Move all debugfs related code to a new file to keep the .c files clear of ifdefs. Link: https://lkml.kernel.org/r/20251101142325.1326536-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20251101142325.1326536-2-pasha.tatashin@soleen.com Link: https://lore.kernel.org/all/20251020100306.2709352-1-jasonmiu@google.com [1] Co-developed-by: Mike Rapoport (Microsoft) Signed-off-by: Mike Rapoport (Microsoft) Signed-off-by: Pasha Tatashin Reviewed-by: Pratyush Yadav Cc: Alexander Graf Cc: Christian Brauner Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Masahiro Yamada Cc: Miguel Ojeda Cc: Randy Dunlap Cc: Tejun Heo Cc: Changyuan Lyu Cc: Jason Gunthorpe Cc: Simon Horman Cc: Zhu Yanjun Signed-off-by: Andrew Morton Stable-dep-of: 019fc3687237 ("kho: fix KASAN support for restored vmalloc regions") Signed-off-by: Sasha Levin --- MAINTAINERS | 2 +- kernel/Kconfig.kexec | 12 +- kernel/Makefile | 1 + kernel/kexec_handover.c | 269 +++++--------------------- kernel/kexec_handover_debugfs.c | 216 +++++++++++++++++++++ kernel/kexec_handover_internal.h | 35 ++++ tools/testing/selftests/kho/vmtest.sh | 1 + 7 files changed, 314 insertions(+), 222 deletions(-) create mode 100644 kernel/kexec_handover_debugfs.c diff --git a/MAINTAINERS b/MAINTAINERS index e8f06145fb54c..554e881b05bea 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13798,7 +13798,7 @@ S: Maintained F: Documentation/admin-guide/mm/kho.rst F: Documentation/core-api/kho/* F: include/linux/kexec_handover.h -F: kernel/kexec_handover.c +F: kernel/kexec_handover* F: lib/test_kho.c F: tools/testing/selftests/kho/ diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 54e5810726176..cc6743137946f 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -100,7 +100,6 @@ config KEXEC_HANDOVER depends on !DEFERRED_STRUCT_PAGE_INIT select MEMBLOCK_KHO_SCRATCH select KEXEC_FILE - select DEBUG_FS select LIBFDT select CMA help @@ -118,6 +117,17 @@ config KEXEC_HANDOVER_DEBUG scenarios and the extra code might be adding overhead it is only optionally enabled. +config KEXEC_HANDOVER_DEBUGFS + bool "kexec handover debugfs interface" + default KEXEC_HANDOVER + depends on KEXEC_HANDOVER + select DEBUG_FS + help + Allow to control kexec handover device tree via debugfs + interface, i.e. finalize the state or aborting the finalization. + Also, enables inspecting the KHO fdt trees with the debugfs binary + blobs. + config CRASH_DUMP bool "kernel crash dumps" default ARCH_DEFAULT_CRASH_DUMP diff --git a/kernel/Makefile b/kernel/Makefile index 9fe722305c9be..2cf7909a74e56 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o +obj-$(CONFIG_KEXEC_HANDOVER_DEBUGFS) += kexec_handover_debugfs.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup/ diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 2da4bd994322f..c13b99f7c9891 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -30,6 +29,7 @@ */ #include "../mm/internal.h" #include "kexec_internal.h" +#include "kexec_handover_internal.h" #define KHO_FDT_COMPATIBLE "kho-v1" #define PROP_PRESERVED_MEMORY_MAP "preserved-memory-map" @@ -105,8 +105,6 @@ struct khoser_mem_chunk; struct kho_serialization { struct page *fdt; - struct list_head fdt_list; - struct dentry *sub_fdt_dir; struct kho_mem_track track; /* First chunk of serialized preserved memory map */ struct khoser_mem_chunk *preserved_mem_map; @@ -114,20 +112,16 @@ struct kho_serialization { struct kho_out { struct blocking_notifier_head chain_head; - - struct dentry *dir; - struct mutex lock; /* protects KHO FDT finalization */ - struct kho_serialization ser; bool finalized; + struct kho_debugfs dbg; }; static struct kho_out kho_out = { .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head), .lock = __MUTEX_INITIALIZER(kho_out.lock), .ser = { - .fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list), .track = { .orders = XARRAY_INIT(kho_out.ser.track.orders, 0), }, @@ -678,37 +672,6 @@ static void __init kho_reserve_scratch(void) kho_enable = false; } -struct fdt_debugfs { - struct list_head list; - struct debugfs_blob_wrapper wrapper; - struct dentry *file; -}; - -static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir, - const char *name, const void *fdt) -{ - struct fdt_debugfs *f; - struct dentry *file; - - f = kmalloc(sizeof(*f), GFP_KERNEL); - if (!f) - return -ENOMEM; - - f->wrapper.data = (void *)fdt; - f->wrapper.size = fdt_totalsize(fdt); - - file = debugfs_create_blob(name, 0400, dir, &f->wrapper); - if (IS_ERR(file)) { - kfree(f); - return PTR_ERR(file); - } - - f->file = file; - list_add(&f->list, list); - - return 0; -} - /** * kho_add_subtree - record the physical address of a sub FDT in KHO root tree. * @ser: serialization control object passed by KHO notifiers. @@ -720,7 +683,8 @@ static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir, * by KHO for the new kernel to retrieve it after kexec. * * A debugfs blob entry is also created at - * ``/sys/kernel/debug/kho/out/sub_fdts/@name``. + * ``/sys/kernel/debug/kho/out/sub_fdts/@name`` when kernel is configured with + * CONFIG_KEXEC_HANDOVER_DEBUGFS * * Return: 0 on success, error code on failure */ @@ -737,7 +701,7 @@ int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt) if (err) return err; - return kho_debugfs_fdt_add(&ser->fdt_list, ser->sub_fdt_dir, name, fdt); + return kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false); } EXPORT_SYMBOL_GPL(kho_add_subtree); @@ -1069,30 +1033,7 @@ void *kho_restore_vmalloc(const struct kho_vmalloc *preservation) } EXPORT_SYMBOL_GPL(kho_restore_vmalloc); -/* Handling for debug/kho/out */ - -static struct dentry *debugfs_root; - -static int kho_out_update_debugfs_fdt(void) -{ - int err = 0; - struct fdt_debugfs *ff, *tmp; - - if (kho_out.finalized) { - err = kho_debugfs_fdt_add(&kho_out.ser.fdt_list, kho_out.dir, - "fdt", page_to_virt(kho_out.ser.fdt)); - } else { - list_for_each_entry_safe(ff, tmp, &kho_out.ser.fdt_list, list) { - debugfs_remove(ff->file); - list_del(&ff->list); - kfree(ff); - } - } - - return err; -} - -static int kho_abort(void) +static int __kho_abort(void) { int err; unsigned long order; @@ -1125,7 +1066,28 @@ static int kho_abort(void) return err; } -static int kho_finalize(void) +int kho_abort(void) +{ + int ret = 0; + + if (!kho_enable) + return -EOPNOTSUPP; + + guard(mutex)(&kho_out.lock); + if (!kho_out.finalized) + return -ENOENT; + + ret = __kho_abort(); + if (ret) + return ret; + + kho_out.finalized = false; + kho_debugfs_cleanup(&kho_out.dbg); + + return 0; +} + +static int __kho_finalize(void) { int err = 0; u64 *preserved_mem_map; @@ -1168,118 +1130,46 @@ static int kho_finalize(void) abort: if (err) { pr_err("Failed to convert KHO state tree: %d\n", err); - kho_abort(); + __kho_abort(); } return err; } -static int kho_out_finalize_get(void *data, u64 *val) -{ - mutex_lock(&kho_out.lock); - *val = kho_out.finalized; - mutex_unlock(&kho_out.lock); - - return 0; -} - -static int kho_out_finalize_set(void *data, u64 _val) +int kho_finalize(void) { - int ret = 0; - bool val = !!_val; - - mutex_lock(&kho_out.lock); + int ret; - if (val == kho_out.finalized) { - if (kho_out.finalized) - ret = -EEXIST; - else - ret = -ENOENT; - goto unlock; - } + if (!kho_enable) + return -EOPNOTSUPP; - if (val) - ret = kho_finalize(); - else - ret = kho_abort(); + guard(mutex)(&kho_out.lock); + if (kho_out.finalized) + return -EEXIST; + ret = __kho_finalize(); if (ret) - goto unlock; - - kho_out.finalized = val; - ret = kho_out_update_debugfs_fdt(); - -unlock: - mutex_unlock(&kho_out.lock); - return ret; -} - -DEFINE_DEBUGFS_ATTRIBUTE(fops_kho_out_finalize, kho_out_finalize_get, - kho_out_finalize_set, "%llu\n"); - -static int scratch_phys_show(struct seq_file *m, void *v) -{ - for (int i = 0; i < kho_scratch_cnt; i++) - seq_printf(m, "0x%llx\n", kho_scratch[i].addr); - - return 0; -} -DEFINE_SHOW_ATTRIBUTE(scratch_phys); + return ret; -static int scratch_len_show(struct seq_file *m, void *v) -{ - for (int i = 0; i < kho_scratch_cnt; i++) - seq_printf(m, "0x%llx\n", kho_scratch[i].size); + kho_out.finalized = true; - return 0; + return kho_debugfs_fdt_add(&kho_out.dbg, "fdt", + page_to_virt(kho_out.ser.fdt), true); } -DEFINE_SHOW_ATTRIBUTE(scratch_len); -static __init int kho_out_debugfs_init(void) +bool kho_finalized(void) { - struct dentry *dir, *f, *sub_fdt_dir; - - dir = debugfs_create_dir("out", debugfs_root); - if (IS_ERR(dir)) - return -ENOMEM; - - sub_fdt_dir = debugfs_create_dir("sub_fdts", dir); - if (IS_ERR(sub_fdt_dir)) - goto err_rmdir; - - f = debugfs_create_file("scratch_phys", 0400, dir, NULL, - &scratch_phys_fops); - if (IS_ERR(f)) - goto err_rmdir; - - f = debugfs_create_file("scratch_len", 0400, dir, NULL, - &scratch_len_fops); - if (IS_ERR(f)) - goto err_rmdir; - - f = debugfs_create_file("finalize", 0600, dir, NULL, - &fops_kho_out_finalize); - if (IS_ERR(f)) - goto err_rmdir; - - kho_out.dir = dir; - kho_out.ser.sub_fdt_dir = sub_fdt_dir; - return 0; - -err_rmdir: - debugfs_remove_recursive(dir); - return -ENOENT; + guard(mutex)(&kho_out.lock); + return kho_out.finalized; } struct kho_in { - struct dentry *dir; phys_addr_t fdt_phys; phys_addr_t scratch_phys; - struct list_head fdt_list; + struct kho_debugfs dbg; }; static struct kho_in kho_in = { - .fdt_list = LIST_HEAD_INIT(kho_in.fdt_list), }; static const void *kho_get_fdt(void) @@ -1343,56 +1233,6 @@ int kho_retrieve_subtree(const char *name, phys_addr_t *phys) } EXPORT_SYMBOL_GPL(kho_retrieve_subtree); -/* Handling for debugfs/kho/in */ - -static __init int kho_in_debugfs_init(const void *fdt) -{ - struct dentry *sub_fdt_dir; - int err, child; - - kho_in.dir = debugfs_create_dir("in", debugfs_root); - if (IS_ERR(kho_in.dir)) - return PTR_ERR(kho_in.dir); - - sub_fdt_dir = debugfs_create_dir("sub_fdts", kho_in.dir); - if (IS_ERR(sub_fdt_dir)) { - err = PTR_ERR(sub_fdt_dir); - goto err_rmdir; - } - - err = kho_debugfs_fdt_add(&kho_in.fdt_list, kho_in.dir, "fdt", fdt); - if (err) - goto err_rmdir; - - fdt_for_each_subnode(child, fdt, 0) { - int len = 0; - const char *name = fdt_get_name(fdt, child, NULL); - const u64 *fdt_phys; - - fdt_phys = fdt_getprop(fdt, child, "fdt", &len); - if (!fdt_phys) - continue; - if (len != sizeof(*fdt_phys)) { - pr_warn("node `%s`'s prop `fdt` has invalid length: %d\n", - name, len); - continue; - } - err = kho_debugfs_fdt_add(&kho_in.fdt_list, sub_fdt_dir, name, - phys_to_virt(*fdt_phys)); - if (err) { - pr_warn("failed to add fdt `%s` to debugfs: %d\n", name, - err); - continue; - } - } - - return 0; - -err_rmdir: - debugfs_remove_recursive(kho_in.dir); - return err; -} - static __init int kho_init(void) { int err = 0; @@ -1407,27 +1247,16 @@ static __init int kho_init(void) goto err_free_scratch; } - debugfs_root = debugfs_create_dir("kho", NULL); - if (IS_ERR(debugfs_root)) { - err = -ENOENT; + err = kho_debugfs_init(); + if (err) goto err_free_fdt; - } - err = kho_out_debugfs_init(); + err = kho_out_debugfs_init(&kho_out.dbg); if (err) goto err_free_fdt; if (fdt) { - err = kho_in_debugfs_init(fdt); - /* - * Failure to create /sys/kernel/debug/kho/in does not prevent - * reviving state from KHO and setting up KHO for the next - * kexec. - */ - if (err) - pr_err("failed exposing handover FDT in debugfs: %d\n", - err); - + kho_in_debugfs_init(&kho_in.dbg, fdt); return 0; } diff --git a/kernel/kexec_handover_debugfs.c b/kernel/kexec_handover_debugfs.c new file mode 100644 index 0000000000000..a91b279f1b232 --- /dev/null +++ b/kernel/kexec_handover_debugfs.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_handover_debugfs.c - kexec handover debugfs interfaces + * Copyright (C) 2023 Alexander Graf + * Copyright (C) 2025 Microsoft Corporation, Mike Rapoport + * Copyright (C) 2025 Google LLC, Changyuan Lyu + * Copyright (C) 2025 Google LLC, Pasha Tatashin + */ + +#define pr_fmt(fmt) "KHO: " fmt + +#include +#include +#include +#include +#include "kexec_handover_internal.h" + +static struct dentry *debugfs_root; + +struct fdt_debugfs { + struct list_head list; + struct debugfs_blob_wrapper wrapper; + struct dentry *file; +}; + +static int __kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir, + const char *name, const void *fdt) +{ + struct fdt_debugfs *f; + struct dentry *file; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return -ENOMEM; + + f->wrapper.data = (void *)fdt; + f->wrapper.size = fdt_totalsize(fdt); + + file = debugfs_create_blob(name, 0400, dir, &f->wrapper); + if (IS_ERR(file)) { + kfree(f); + return PTR_ERR(file); + } + + f->file = file; + list_add(&f->list, list); + + return 0; +} + +int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name, + const void *fdt, bool root) +{ + struct dentry *dir; + + if (root) + dir = dbg->dir; + else + dir = dbg->sub_fdt_dir; + + return __kho_debugfs_fdt_add(&dbg->fdt_list, dir, name, fdt); +} + +void kho_debugfs_cleanup(struct kho_debugfs *dbg) +{ + struct fdt_debugfs *ff, *tmp; + + list_for_each_entry_safe(ff, tmp, &dbg->fdt_list, list) { + debugfs_remove(ff->file); + list_del(&ff->list); + kfree(ff); + } +} + +static int kho_out_finalize_get(void *data, u64 *val) +{ + *val = kho_finalized(); + + return 0; +} + +static int kho_out_finalize_set(void *data, u64 val) +{ + if (val) + return kho_finalize(); + else + return kho_abort(); +} + +DEFINE_DEBUGFS_ATTRIBUTE(kho_out_finalize_fops, kho_out_finalize_get, + kho_out_finalize_set, "%llu\n"); + +static int scratch_phys_show(struct seq_file *m, void *v) +{ + for (int i = 0; i < kho_scratch_cnt; i++) + seq_printf(m, "0x%llx\n", kho_scratch[i].addr); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(scratch_phys); + +static int scratch_len_show(struct seq_file *m, void *v) +{ + for (int i = 0; i < kho_scratch_cnt; i++) + seq_printf(m, "0x%llx\n", kho_scratch[i].size); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(scratch_len); + +__init void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt) +{ + struct dentry *dir, *sub_fdt_dir; + int err, child; + + INIT_LIST_HEAD(&dbg->fdt_list); + + dir = debugfs_create_dir("in", debugfs_root); + if (IS_ERR(dir)) { + err = PTR_ERR(dir); + goto err_out; + } + + sub_fdt_dir = debugfs_create_dir("sub_fdts", dir); + if (IS_ERR(sub_fdt_dir)) { + err = PTR_ERR(sub_fdt_dir); + goto err_rmdir; + } + + err = __kho_debugfs_fdt_add(&dbg->fdt_list, dir, "fdt", fdt); + if (err) + goto err_rmdir; + + fdt_for_each_subnode(child, fdt, 0) { + int len = 0; + const char *name = fdt_get_name(fdt, child, NULL); + const u64 *fdt_phys; + + fdt_phys = fdt_getprop(fdt, child, "fdt", &len); + if (!fdt_phys) + continue; + if (len != sizeof(*fdt_phys)) { + pr_warn("node %s prop fdt has invalid length: %d\n", + name, len); + continue; + } + err = __kho_debugfs_fdt_add(&dbg->fdt_list, sub_fdt_dir, name, + phys_to_virt(*fdt_phys)); + if (err) { + pr_warn("failed to add fdt %s to debugfs: %d\n", name, + err); + continue; + } + } + + dbg->dir = dir; + dbg->sub_fdt_dir = sub_fdt_dir; + + return; +err_rmdir: + debugfs_remove_recursive(dir); +err_out: + /* + * Failure to create /sys/kernel/debug/kho/in does not prevent + * reviving state from KHO and setting up KHO for the next + * kexec. + */ + if (err) + pr_err("failed exposing handover FDT in debugfs: %d\n", err); +} + +__init int kho_out_debugfs_init(struct kho_debugfs *dbg) +{ + struct dentry *dir, *f, *sub_fdt_dir; + + INIT_LIST_HEAD(&dbg->fdt_list); + + dir = debugfs_create_dir("out", debugfs_root); + if (IS_ERR(dir)) + return -ENOMEM; + + sub_fdt_dir = debugfs_create_dir("sub_fdts", dir); + if (IS_ERR(sub_fdt_dir)) + goto err_rmdir; + + f = debugfs_create_file("scratch_phys", 0400, dir, NULL, + &scratch_phys_fops); + if (IS_ERR(f)) + goto err_rmdir; + + f = debugfs_create_file("scratch_len", 0400, dir, NULL, + &scratch_len_fops); + if (IS_ERR(f)) + goto err_rmdir; + + f = debugfs_create_file("finalize", 0600, dir, NULL, + &kho_out_finalize_fops); + if (IS_ERR(f)) + goto err_rmdir; + + dbg->dir = dir; + dbg->sub_fdt_dir = sub_fdt_dir; + return 0; + +err_rmdir: + debugfs_remove_recursive(dir); + return -ENOENT; +} + +__init int kho_debugfs_init(void) +{ + debugfs_root = debugfs_create_dir("kho", NULL); + if (IS_ERR(debugfs_root)) + return -ENOENT; + return 0; +} diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h index 3c3c7148ceed4..217b8b25a5422 100644 --- a/kernel/kexec_handover_internal.h +++ b/kernel/kexec_handover_internal.h @@ -3,11 +3,46 @@ #define LINUX_KEXEC_HANDOVER_INTERNAL_H #include +#include #include +#ifdef CONFIG_KEXEC_HANDOVER_DEBUGFS +#include + +struct kho_debugfs { + struct dentry *dir; + struct dentry *sub_fdt_dir; + struct list_head fdt_list; +}; + +#else +struct kho_debugfs {}; +#endif + extern struct kho_scratch *kho_scratch; extern unsigned int kho_scratch_cnt; +bool kho_finalized(void); +int kho_finalize(void); +int kho_abort(void); + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUGFS +int kho_debugfs_init(void); +void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt); +int kho_out_debugfs_init(struct kho_debugfs *dbg); +int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name, + const void *fdt, bool root); +void kho_debugfs_cleanup(struct kho_debugfs *dbg); +#else +static inline int kho_debugfs_init(void) { return 0; } +static inline void kho_in_debugfs_init(struct kho_debugfs *dbg, + const void *fdt) { } +static inline int kho_out_debugfs_init(struct kho_debugfs *dbg) { return 0; } +static inline int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name, + const void *fdt, bool root) { return 0; } +static inline void kho_debugfs_cleanup(struct kho_debugfs *dbg) {} +#endif /* CONFIG_KEXEC_HANDOVER_DEBUGFS */ + #ifdef CONFIG_KEXEC_HANDOVER_DEBUG bool kho_scratch_overlap(phys_addr_t phys, size_t size); #else diff --git a/tools/testing/selftests/kho/vmtest.sh b/tools/testing/selftests/kho/vmtest.sh index 3f6c171668467..49fdac8e8b159 100755 --- a/tools/testing/selftests/kho/vmtest.sh +++ b/tools/testing/selftests/kho/vmtest.sh @@ -59,6 +59,7 @@ function build_kernel() { tee "$kconfig" > "$kho_config" < Date: Mon, 2 Mar 2026 13:10:15 -0700 Subject: [PATCH 0497/1518] Documentation: fix a hugetlbfs reservation statement [ Upstream commit 7a197d346a44384a1a858a98ef03766840e561d4 ] Documentation/mm/hugetlbfs_reserv.rst has if (resv_needed <= (resv_huge_pages - free_huge_pages)) resv_huge_pages += resv_needed; which describes this code in gather_surplus_pages() needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } which means if there are enough free hugepages to account for the new reservation, simply update the global reservation count without further action. But the description is backwards, it should be if (resv_needed <= (free_huge_pages - resv_huge_pages)) instead. Link: https://lkml.kernel.org/r/20260302201015.1824798-1-jane.chu@oracle.com Fixes: 70bc0dc578b3 ("Documentation: vm, add hugetlbfs reservation overview") Signed-off-by: Jane Chu Cc: David Hildenbrand Cc: Hillf Danton Cc: Jonathan Corbet Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Oscar Salvador Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- Documentation/mm/hugetlbfs_reserv.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/mm/hugetlbfs_reserv.rst b/Documentation/mm/hugetlbfs_reserv.rst index 4914fbf07966c..a49115db18c76 100644 --- a/Documentation/mm/hugetlbfs_reserv.rst +++ b/Documentation/mm/hugetlbfs_reserv.rst @@ -155,7 +155,7 @@ are enough free huge pages to accommodate the reservation. If there are, the global reservation count resv_huge_pages is adjusted something like the following:: - if (resv_needed <= (resv_huge_pages - free_huge_pages)) + if (resv_needed <= (free_huge_pages - resv_huge_pages) resv_huge_pages += resv_needed; Note that the global lock hugetlb_lock is held when checking and adjusting From 2fdb6c1e743d2d442b19a1bc702a38d5a0c3c7f2 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 11 Mar 2026 16:05:26 -0400 Subject: [PATCH 0498/1518] selftest: memcg: skip memcg_sock test if address family not supported MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2d028f3e4bbbfd448928a8d3d2814b0b04c214f4 ] The test_memcg_sock test in memcontrol.c sets up an IPv6 socket and send data over it to consume memory and verify that memory.stat.sock and memory.current values are close. On systems where IPv6 isn't enabled or not configured to support SOCK_STREAM, the test_memcg_sock test always fails. When the socket() call fails, there is no way we can test the memory consumption and verify the above claim. I believe it is better to just skip the test in this case instead of reporting a test failure hinting that there may be something wrong with the memcg code. Link: https://lkml.kernel.org/r/20260311200526.885899-1-longman@redhat.com Fixes: 5f8f019380b8 ("selftests: cgroup/memcontrol: add basic test for socket accounting") Signed-off-by: Waiman Long Acked-by: Michal Koutný Acked-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Michal Koutný Cc: Mike Rapoport Cc: Muchun Song Cc: Roman Gushchin Cc: Shuah Khan Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- tools/testing/selftests/cgroup/test_memcontrol.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index a680f773f2d54..1f64db1afa212 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -1278,8 +1278,11 @@ static int tcp_server(const char *cgroup, void *arg) saddr.sin6_port = htons(srv_args->port); sk = socket(AF_INET6, SOCK_STREAM, 0); - if (sk < 0) + if (sk < 0) { + /* Pass back errno to the ctl_fd */ + write(ctl_fd, &errno, sizeof(errno)); return ret; + } if (setsockopt(sk, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0) goto cleanup; @@ -1409,6 +1412,12 @@ static int test_memcg_sock(const char *root) goto cleanup; close(args.ctl[0]); + /* Skip if address family not supported by protocol */ + if (err == EAFNOSUPPORT) { + ret = KSFT_SKIP; + goto cleanup; + } + if (!err) break; if (err != EADDRINUSE) From 12d76d99e8453dd261c2343111b4fc852c01245c Mon Sep 17 00:00:00 2001 From: Panagiotis Petrakopoulos Date: Mon, 6 Apr 2026 01:25:48 +0300 Subject: [PATCH 0499/1518] ALSA: scarlett2: Add missing sentinel initializer field [ Upstream commit 2428cd6e8b6fa80c36db4652702ca0acd2ce3f08 ] A "-Wmissing-field-initializers" warning was emitted when compiling the module using the W=2 option. There is a sentinel initializer field missing in the end of scarlett2_devices[]. Tested using a Scarlett Solo 4th gen. Fixes: d98cc489029d ("ALSA: scarlett2: Move USB IDs out from device_info struct") Signed-off-by: Panagiotis Petrakopoulos Link: https://patch.msgid.link/20260405222548.8903-1-npetrakopoulos2003@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/mixer_scarlett2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index 48d77030a63d8..a75a4610663e9 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -2262,7 +2262,7 @@ static const struct scarlett2_device_entry scarlett2_devices[] = { { USB_ID(0x1235, 0x820c), &clarett_8pre_info, "Clarett+" }, /* End of list */ - { 0, NULL }, + { 0, NULL, NULL }, }; /* get the starting port index number for a given port type/direction */ From 989ccfcc920e71d065a736f54b77ec5501126874 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Wed, 25 Mar 2026 17:05:11 -0300 Subject: [PATCH 0500/1518] ASoC: SOF: compress: return the configured codec from get_params MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2c4fdd055f92a2fc8602dcd88bcea08c374b7e8b ] The SOF compressed offload path accepts codec parameters in sof_compr_set_params() and forwards them to firmware as extended data in the SOF IPC stream params message. However, sof_compr_get_params() still returns success without filling the snd_codec structure. Since the compress core allocates that structure zeroed and copies it back to userspace on success, SNDRV_COMPRESS_GET_PARAMS returns an all-zero codec description even after the stream has been configured successfully. The stale TODO in this callback conflates get_params() with capability discovery. Supported codec enumeration belongs in get_caps() and get_codec_caps(). get_params() should report the current codec settings. Cache the codec accepted by sof_compr_set_params() in the per-stream SOF compress state and return it from sof_compr_get_params(). Fixes: 6324cf901e14 ("ASoC: SOF: compr: Add compress ops implementation") Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260325-sof-compr-get-params-v1-1-0758815f13c7@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/compress.c | 8 +++++--- sound/soc/sof/sof-priv.h | 2 ++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/sound/soc/sof/compress.c b/sound/soc/sof/compress.c index 593b8c7474846..31455ebb0f5bb 100644 --- a/sound/soc/sof/compress.c +++ b/sound/soc/sof/compress.c @@ -247,6 +247,7 @@ static int sof_compr_set_params(struct snd_soc_component *component, sstream->sampling_rate = params->codec.sample_rate; sstream->channels = params->codec.ch_out; sstream->sample_container_bytes = pcm->params.sample_container_bytes; + sstream->codec_params = params->codec; spcm->prepared[cstream->direction] = true; @@ -259,9 +260,10 @@ static int sof_compr_set_params(struct snd_soc_component *component, static int sof_compr_get_params(struct snd_soc_component *component, struct snd_compr_stream *cstream, struct snd_codec *params) { - /* TODO: we don't query the supported codecs for now, if the - * application asks for an unsupported codec the set_params() will fail. - */ + struct sof_compr_stream *sstream = cstream->runtime->private_data; + + *params = sstream->codec_params; + return 0; } diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h index 0f624d8cde201..985284a7b4ec9 100644 --- a/sound/soc/sof/sof-priv.h +++ b/sound/soc/sof/sof-priv.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -111,6 +112,7 @@ struct sof_compr_stream { u32 sampling_rate; u16 channels; u16 sample_container_bytes; + struct snd_codec codec_params; size_t posn_offset; }; From 19ad2384ce5e6e2d967cdff4b766be21be5d36c0 Mon Sep 17 00:00:00 2001 From: Richard Cheng Date: Thu, 2 Apr 2026 17:38:50 +0800 Subject: [PATCH 0501/1518] PCI/NPEM: Set LED_HW_PLUGGABLE for hotplug-capable ports [ Upstream commit 16d021c878dca22532c984668c9e8cf4722d6a49 ] NPEM registers LED classdevs on PCI endpoint that may be behind hotplug-capable ports. During hot-removal, led_classdev_unregister() calls led_set_brightness(LED_OFF) which leads to a PCI config read to a disconnected device, which fails and returns -ENODEV (topology details in msgid.link below): leds 0003:01:00.0:enclosure:ok: Setting an LED's brightness failed (-19) The LED core already suppresses this for devices with LED_HW_PLUGGABLE set, but NPEM never sets it. Add the flag since NPEM LEDs are on hot-pluggable hardware by nature. Fixes: 4e893545ef87 ("PCI/NPEM: Add Native PCIe Enclosure Management support") Signed-off-by: Richard Cheng Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Wunner Acked-by: Kai-Heng Feng Link: https://patch.msgid.link/20260402093850.23075-1-icheng@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/npem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/npem.c b/drivers/pci/npem.c index 97507e0df769b..b5d012edebf35 100644 --- a/drivers/pci/npem.c +++ b/drivers/pci/npem.c @@ -504,7 +504,7 @@ static int pci_npem_set_led_classdev(struct npem *npem, struct npem_led *nled) led->brightness_get = brightness_get; led->max_brightness = 1; led->default_trigger = "none"; - led->flags = 0; + led->flags = LED_HW_PLUGGABLE; ret = led_classdev_register(&npem->dev->dev, led); if (ret) From feac3db37d14adc2565bf4e46dfc98cf292d0624 Mon Sep 17 00:00:00 2001 From: songxiebing Date: Wed, 8 Apr 2026 16:33:11 +0800 Subject: [PATCH 0502/1518] ALSA: usb-audio: qcom: Fix incorrect type in enable_audio_stream [ Upstream commit 292286b2d229fb732421429b027d38ac3f969383 ] Fix sparse warning: sound/usb/qcom/qc_audio_offload.c:943:27: sparse: incorrect type in argument 2 expected unsigned int val but got snd_pcm_format_t. Explicitly cast pcm_format to unsigned int for snd_mask_leave(). Fixes: 326bbc348298 ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202604062109.Oxi8JjWW-lkp@intel.com/ Signed-off-by: songxiebing Link: https://patch.msgid.link/20260408083311.774173-1-songxiebing@kylinos.cn Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/qcom/qc_audio_offload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 542eae3a57d9d..fc25e709ed4b2 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -948,7 +948,7 @@ static int enable_audio_stream(struct snd_usb_substream *subs, _snd_pcm_hw_params_any(¶ms); m = hw_param_mask(¶ms, SNDRV_PCM_HW_PARAM_FORMAT); - snd_mask_leave(m, pcm_format); + snd_mask_leave(m, (__force unsigned int)pcm_format); i = hw_param_interval(¶ms, SNDRV_PCM_HW_PARAM_CHANNELS); snd_interval_setinteger(i); From f38e0c5f377a58bdbfd4818b13e2574765558118 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:42 +0530 Subject: [PATCH 0503/1518] PCI: tegra194: Fix polling delay for L2 state [ Upstream commit adaffed907f14f954096555665ad6af2ae724d83 ] As per PCIe r7.0, sec 5.3.3.2.1, after sending PME_Turn_Off message, Root Port should wait for 1-10 msec for PME_TO_Ack message. Currently, driver is polling for 10 msec with 1 usec delay which is aggressive. Use existing macro PCIE_PME_TO_L2_TIMEOUT_US to poll for 10 msec with 1 msec delay. Since this function is used in non-atomic context only, use non-atomic poll function. Fixes: 56e15a238d92 ("PCI: tegra: Add Tegra194 PCIe support") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Link: https://patch.msgid.link/20260324190755.1094879-2-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 3934757baa30c..d2d3139e81d36 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -198,8 +198,6 @@ #define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK GENMASK(11, 8) #define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT 8 -#define PME_ACK_TIMEOUT 10000 - #define LTSSM_TIMEOUT 50000 /* 50ms */ #define GEN3_GEN4_EQ_PRESET_INIT 5 @@ -1582,9 +1580,10 @@ static int tegra_pcie_try_link_l2(struct tegra_pcie_dw *pcie) val |= APPL_PM_XMT_TURNOFF_STATE; appl_writel(pcie, val, APPL_RADM_STATUS); - return readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, val, - val & APPL_DEBUG_PM_LINKST_IN_L2_LAT, - 1, PME_ACK_TIMEOUT); + return readl_poll_timeout(pcie->appl_base + APPL_DEBUG, val, + val & APPL_DEBUG_PM_LINKST_IN_L2_LAT, + PCIE_PME_TO_L2_TIMEOUT_US/10, + PCIE_PME_TO_L2_TIMEOUT_US); } static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) From 8626b64c37c9c1000b378056fab8848c3ced0b96 Mon Sep 17 00:00:00 2001 From: Manikanta Maddireddy Date: Wed, 25 Mar 2026 00:37:43 +0530 Subject: [PATCH 0504/1518] PCI: tegra194: Increase LTSSM poll time on surprise link down [ Upstream commit 74dd8efe4d6cead433162147333af989a568aac7 ] On surprise link down, LTSSM state transits from L0 -> Recovery.RcvrLock -> Recovery.RcvrSpeed -> Gen1 Recovery.RcvrLock -> Detect. Recovery.RcvrLock and Recovery.RcvrSpeed transit times are 24 ms and 48 ms respectively, so the total time from L0 to Detect is ~96 ms. Increase the poll timeout to 120 ms to account for this. While at it, add LTSSM state defines for Detect-related states and use them in the poll condition. Use readl_poll_timeout() instead of readl_poll_timeout_atomic() in tegra_pcie_dw_pme_turnoff() since that path runs in non-atomic context. Fixes: 56e15a238d92 ("PCI: tegra: Add Tegra194 PCIe support") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Link: https://patch.msgid.link/20260324190755.1094879-3-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 36 +++++++++++++--------- 1 file changed, 21 insertions(+), 15 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index d2d3139e81d36..d2fefd5c8b08f 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -137,7 +137,11 @@ #define APPL_DEBUG_PM_LINKST_IN_L0 0x11 #define APPL_DEBUG_LTSSM_STATE_MASK GENMASK(8, 3) #define APPL_DEBUG_LTSSM_STATE_SHIFT 3 -#define LTSSM_STATE_PRE_DETECT 5 +#define LTSSM_STATE_DETECT_QUIET 0x00 +#define LTSSM_STATE_DETECT_ACT 0x08 +#define LTSSM_STATE_PRE_DETECT_QUIET 0x28 +#define LTSSM_STATE_DETECT_WAIT 0x30 +#define LTSSM_STATE_L2_IDLE 0xa8 #define APPL_RADM_STATUS 0xE4 #define APPL_PM_XMT_TURNOFF_STATE BIT(0) @@ -198,7 +202,8 @@ #define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK GENMASK(11, 8) #define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT 8 -#define LTSSM_TIMEOUT 50000 /* 50ms */ +#define LTSSM_DELAY_US 10000 /* 10 ms */ +#define LTSSM_TIMEOUT_US 120000 /* 120 ms */ #define GEN3_GEN4_EQ_PRESET_INIT 5 @@ -1626,15 +1631,14 @@ static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) data &= ~APPL_CTRL_LTSSM_EN; writel(data, pcie->appl_base + APPL_CTRL); - err = readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, - data, - ((data & - APPL_DEBUG_LTSSM_STATE_MASK) >> - APPL_DEBUG_LTSSM_STATE_SHIFT) == - LTSSM_STATE_PRE_DETECT, - 1, LTSSM_TIMEOUT); + err = readl_poll_timeout(pcie->appl_base + APPL_DEBUG, data, + ((data & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_QUIET) || + ((data & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_ACT) || + ((data & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_PRE_DETECT_QUIET) || + ((data & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_WAIT), + LTSSM_DELAY_US, LTSSM_TIMEOUT_US); if (err) - dev_info(pcie->dev, "Link didn't go to detect state\n"); + dev_info(pcie->dev, "LTSSM state: 0x%x detect timeout: %d\n", data, err); } /* * DBI registers may not be accessible after this as PLL-E would be @@ -1714,12 +1718,14 @@ static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) appl_writel(pcie, val, APPL_CTRL); ret = readl_poll_timeout(pcie->appl_base + APPL_DEBUG, val, - ((val & APPL_DEBUG_LTSSM_STATE_MASK) >> - APPL_DEBUG_LTSSM_STATE_SHIFT) == - LTSSM_STATE_PRE_DETECT, - 1, LTSSM_TIMEOUT); + ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_QUIET) || + ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_ACT) || + ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_PRE_DETECT_QUIET) || + ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_WAIT) || + ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_L2_IDLE), + LTSSM_DELAY_US, LTSSM_TIMEOUT_US); if (ret) - dev_err(pcie->dev, "Failed to go Detect state: %d\n", ret); + dev_info(pcie->dev, "LTSSM state: 0x%x detect timeout: %d\n", val, ret); reset_control_assert(pcie->core_rst); From fb08535d374c4bd3c539fc6fb8cb038180424a7f Mon Sep 17 00:00:00 2001 From: Manikanta Maddireddy Date: Wed, 25 Mar 2026 00:37:44 +0530 Subject: [PATCH 0505/1518] PCI: tegra194: Disable LTSSM after transition to Detect on surprise link down [ Upstream commit 9fa0c242f8d7acf1b124d4462d18f4023573ac1c ] After the link reaches a Detect-related LTSSM state, disable LTSSM so it does not keep toggling between Polling and Detect. Do this by polling for the Detect state first, then clearing APPL_CTRL_LTSSM_EN in both tegra_pcie_dw_pme_turnoff() and pex_ep_event_pex_rst_assert(). Fixes: 56e15a238d92 ("PCI: tegra: Add Tegra194 PCIe support") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Link: https://patch.msgid.link/20260324190755.1094879-4-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 29 ++++++++++++---------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index d2fefd5c8b08f..b3a1161f49daf 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1623,14 +1623,6 @@ static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) data &= ~APPL_PINMUX_PEX_RST; appl_writel(pcie, data, APPL_PINMUX); - /* - * Some cards do not go to detect state even after de-asserting - * PERST#. So, de-assert LTSSM to bring link to detect state. - */ - data = readl(pcie->appl_base + APPL_CTRL); - data &= ~APPL_CTRL_LTSSM_EN; - writel(data, pcie->appl_base + APPL_CTRL); - err = readl_poll_timeout(pcie->appl_base + APPL_DEBUG, data, ((data & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_QUIET) || ((data & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_ACT) || @@ -1639,6 +1631,14 @@ static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) LTSSM_DELAY_US, LTSSM_TIMEOUT_US); if (err) dev_info(pcie->dev, "LTSSM state: 0x%x detect timeout: %d\n", data, err); + + /* + * Deassert LTSSM state to stop the state toggling between + * Polling and Detect. + */ + data = readl(pcie->appl_base + APPL_CTRL); + data &= ~APPL_CTRL_LTSSM_EN; + writel(data, pcie->appl_base + APPL_CTRL); } /* * DBI registers may not be accessible after this as PLL-E would be @@ -1712,11 +1712,6 @@ static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) if (pcie->ep_state == EP_STATE_DISABLED) return; - /* Disable LTSSM */ - val = appl_readl(pcie, APPL_CTRL); - val &= ~APPL_CTRL_LTSSM_EN; - appl_writel(pcie, val, APPL_CTRL); - ret = readl_poll_timeout(pcie->appl_base + APPL_DEBUG, val, ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_QUIET) || ((val & APPL_DEBUG_LTSSM_STATE_MASK) == LTSSM_STATE_DETECT_ACT) || @@ -1727,6 +1722,14 @@ static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) if (ret) dev_info(pcie->dev, "LTSSM state: 0x%x detect timeout: %d\n", val, ret); + /* + * Deassert LTSSM state to stop the state toggling between + * Polling and Detect. + */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + reset_control_assert(pcie->core_rst); tegra_pcie_disable_phy(pcie); From 871d9a6bf21b6e5e3d5a85aaa6216ff8abf8ff08 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:45 +0530 Subject: [PATCH 0506/1518] PCI: tegra194: Don't force the device into the D0 state before L2 [ Upstream commit 71d9f67701e1affc82d18ca88ae798c5361beddf ] As per PCIe CEM r6.0, sec 2.3, the PCIe Endpoint device should be in D3cold to assert WAKE# pin. The previous workaround that forced downstream devices to D0 before taking the link to L2 cited PCIe r4.0, sec 5.2, "Link State Power Management"; however, that spec does not explicitly require putting the device into D0 and only indicates that power removal may be initiated without transitioning to D3hot. Remove the D0 workaround so that Endpoint devices can use wake functionality (WAKE# from D3). With some Endpoints the link may not enter L2 when they remain in D3, but the Root Port continues with the usual flow after PME timeout, so there is no functional issue. Fixes: 56e15a238d92 ("PCI: tegra: Add Tegra194 PCIe support") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Vidya Sagar Reviewed-by: Jon Hunter Link: https://patch.msgid.link/20260324190755.1094879-5-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 41 ---------------------- 1 file changed, 41 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index b3a1161f49daf..112fd5ea5a0ab 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1287,44 +1287,6 @@ static int tegra_pcie_bpmp_set_pll_state(struct tegra_pcie_dw *pcie, return 0; } -static void tegra_pcie_downstream_dev_to_D0(struct tegra_pcie_dw *pcie) -{ - struct dw_pcie_rp *pp = &pcie->pci.pp; - struct pci_bus *child, *root_port_bus = NULL; - struct pci_dev *pdev; - - /* - * link doesn't go into L2 state with some of the endpoints with Tegra - * if they are not in D0 state. So, need to make sure that immediate - * downstream devices are in D0 state before sending PME_TurnOff to put - * link into L2 state. - * This is as per PCI Express Base r4.0 v1.0 September 27-2017, - * 5.2 Link State Power Management (Page #428). - */ - - list_for_each_entry(child, &pp->bridge->bus->children, node) { - if (child->parent == pp->bridge->bus) { - root_port_bus = child; - break; - } - } - - if (!root_port_bus) { - dev_err(pcie->dev, "Failed to find downstream bus of Root Port\n"); - return; - } - - /* Bring downstream devices to D0 if they are not already in */ - list_for_each_entry(pdev, &root_port_bus->devices, bus_list) { - if (PCI_SLOT(pdev->devfn) == 0) { - if (pci_set_power_state(pdev, PCI_D0)) - dev_err(pcie->dev, - "Failed to transition %s to D0 state\n", - dev_name(&pdev->dev)); - } - } -} - static int tegra_pcie_get_slot_regulators(struct tegra_pcie_dw *pcie) { pcie->slot_ctl_3v3 = devm_regulator_get_optional(pcie->dev, "vpcie3v3"); @@ -1654,7 +1616,6 @@ static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) static void tegra_pcie_deinit_controller(struct tegra_pcie_dw *pcie) { - tegra_pcie_downstream_dev_to_D0(pcie); dw_pcie_host_deinit(&pcie->pci.pp); tegra_pcie_dw_pme_turnoff(pcie); tegra_pcie_unconfig_controller(pcie); @@ -2370,7 +2331,6 @@ static int tegra_pcie_dw_suspend_noirq(struct device *dev) if (!pcie->link_state) return 0; - tegra_pcie_downstream_dev_to_D0(pcie); tegra_pcie_dw_pme_turnoff(pcie); tegra_pcie_unconfig_controller(pcie); @@ -2444,7 +2404,6 @@ static void tegra_pcie_dw_shutdown(struct platform_device *pdev) return; debugfs_remove_recursive(pcie->debugfs); - tegra_pcie_downstream_dev_to_D0(pcie); disable_irq(pcie->pci.pp.irq); if (IS_ENABLED(CONFIG_PCI_MSI)) From 89b7185833db4ea4d82f6e70088497da74a5dc95 Mon Sep 17 00:00:00 2001 From: Manikanta Maddireddy Date: Wed, 25 Mar 2026 00:37:46 +0530 Subject: [PATCH 0507/1518] PCI: tegra194: Disable PERST# IRQ only in Endpoint mode [ Upstream commit 40658a31b6e134169c648041efc84944c4c71dcd ] The PERST# GPIO interrupt is only registered when the controller is operating in Endpoint mode. In Root Port mode, the PERST# GPIO is configured as an output to control downstream devices, and no interrupt is registered for it. Currently, tegra_pcie_dw_stop_link() unconditionally calls disable_irq() on pex_rst_irq, which causes issues in Root Port mode where this IRQ is not registered. Fix this by only disabling the PERST# IRQ when operating in Endpoint mode, where the interrupt is actually registered and used to detect PERST# assertion/deassertion from the host. Fixes: c57247f940e8 ("PCI: tegra: Add support for PCIe endpoint mode in Tegra194") Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-6-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 112fd5ea5a0ab..68920c6263a41 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1054,7 +1054,8 @@ static void tegra_pcie_dw_stop_link(struct dw_pcie *pci) { struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); - disable_irq(pcie->pex_rst_irq); + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) + disable_irq(pcie->pex_rst_irq); } static const struct dw_pcie_ops tegra_dw_pcie_ops = { From f4556f70f00a0f0aa9403d34fae5af81b8ac6b4b Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:47 +0530 Subject: [PATCH 0508/1518] PCI: tegra194: Use devm_gpiod_get_optional() to parse "nvidia,refclk-select" [ Upstream commit f62bc7917de1374dce86a852ffba8baf9cb7a56a ] The GPIO DT property "nvidia,refclk-select", to select the PCIe reference clock is optional. Use devm_gpiod_get_optional() to get it. Fixes: c57247f940e8 ("PCI: tegra: Add support for PCIe endpoint mode in Tegra194") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-7-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 68920c6263a41..2557217f9df16 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1196,9 +1196,9 @@ static int tegra_pcie_dw_parse_dt(struct tegra_pcie_dw *pcie) return err; } - pcie->pex_refclk_sel_gpiod = devm_gpiod_get(pcie->dev, - "nvidia,refclk-select", - GPIOD_OUT_HIGH); + pcie->pex_refclk_sel_gpiod = devm_gpiod_get_optional(pcie->dev, + "nvidia,refclk-select", + GPIOD_OUT_HIGH); if (IS_ERR(pcie->pex_refclk_sel_gpiod)) { int err = PTR_ERR(pcie->pex_refclk_sel_gpiod); const char *level = KERN_ERR; From e463beb1e13092aa04be36ea3d7314c418a207d2 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:48 +0530 Subject: [PATCH 0509/1518] PCI: tegra194: Disable direct speed change for Endpoint mode [ Upstream commit 976f6763f57970388bcd7118931f33f447916927 ] Pre-silicon simulation showed the controller operating in Endpoint mode initiating link speed change after completing Secondary Bus Reset. Ideally, the Root Port or the Switch Downstream Port should initiate the link speed change post SBR, not the Endpoint. So, as per the hardware team recommendation, disable direct speed change for the Endpoint mode to prevent it from initiating speed change after the physical layer link is up at Gen1, leaving speed change ownership with the host. Fixes: c57247f940e8 ("PCI: tegra: Add support for PCIe endpoint mode in Tegra194") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy [mani: commit log] Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-8-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 2557217f9df16..698012f2a9465 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1834,6 +1834,10 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) reset_control_deassert(pcie->core_rst); + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val &= ~PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + if (pcie->update_fc_fixup) { val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF); val |= 0x1 << CFG_TIMER_CTRL_ACK_NAK_SHIFT; From 849068f0129cc64043f2b3350dc5b77eb1459135 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:49 +0530 Subject: [PATCH 0510/1518] PCI: tegra194: Set LTR message request before PCIe link up in Endpoint mode [ Upstream commit b256493bf8cacf0e524bf4c10b5c4901d0c6cefe ] LTR message should be sent as soon as the Root Port enables LTR in the Endpoint mode. So set snoop and no-snoop LTR timing and LTR message request before the PCIe link comes up, so that the LTR message is sent upstream as soon as LTR is enabled. Without programming these values, the Endpoint would send latencies of 0 to the host, which will be inaccurate. Fixes: c57247f940e8 ("PCI: tegra: Add support for PCIe endpoint mode in Tegra194") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy [mani: commit log] Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Reviewed-by: Jon Hunter Tested-by: Jon Hunter Link: https://patch.msgid.link/20260324190755.1094879-9-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 698012f2a9465..7d3ea4309e9bb 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -487,15 +487,6 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) if (val & PCI_COMMAND_MASTER) { ktime_t timeout; - /* 110us for both snoop and no-snoop */ - val = FIELD_PREP(PCI_LTR_VALUE_MASK, 110) | - FIELD_PREP(PCI_LTR_SCALE_MASK, 2) | - LTR_MSG_REQ | - FIELD_PREP(PCI_LTR_NOSNOOP_VALUE, 110) | - FIELD_PREP(PCI_LTR_NOSNOOP_SCALE, 2) | - LTR_NOSNOOP_MSG_REQ; - appl_writel(pcie, val, APPL_LTR_MSG_1); - /* Send LTR upstream */ val = appl_readl(pcie, APPL_LTR_MSG_2); val |= APPL_LTR_MSG_2_LTR_MSG_REQ_STATE; @@ -1832,6 +1823,15 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) val |= APPL_INTR_EN_L1_0_0_RDLH_LINK_UP_INT_EN; appl_writel(pcie, val, APPL_INTR_EN_L1_0_0); + /* 110us for both snoop and no-snoop */ + val = FIELD_PREP(PCI_LTR_VALUE_MASK, 110) | + FIELD_PREP(PCI_LTR_SCALE_MASK, 2) | + LTR_MSG_REQ | + FIELD_PREP(PCI_LTR_NOSNOOP_VALUE, 110) | + FIELD_PREP(PCI_LTR_NOSNOOP_SCALE, 2) | + LTR_NOSNOOP_MSG_REQ; + appl_writel(pcie, val, APPL_LTR_MSG_1); + reset_control_deassert(pcie->core_rst); val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); From e697ea9ecdebc06cef89dbf6f0f667028528ddb1 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:50 +0530 Subject: [PATCH 0511/1518] PCI: tegra194: Allow system suspend when the Endpoint link is not up [ Upstream commit c76f8eae7d4695b1176c4ea5eb93c17e16a20272 ] Host software initiates the L2 sequence. PCIe link is kept in L2 state during suspend. If Endpoint mode is enabled and the link is up, the software cannot proceed with suspend. However, when the PCIe Endpoint driver is probed, but the PCIe link is not up, Tegra can go into suspend state. So, allow system to suspend in this case. Fixes: de2bbf2b71bb ("PCI: tegra194: Don't allow suspend when Tegra PCIe is in EP mode") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-10-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 31 +++++++++++++++++----- 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 7d3ea4309e9bb..f4784945c04bb 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -2304,16 +2304,28 @@ static void tegra_pcie_dw_remove(struct platform_device *pdev) gpiod_set_value(pcie->pex_refclk_sel_gpiod, 0); } -static int tegra_pcie_dw_suspend_late(struct device *dev) +static int tegra_pcie_dw_suspend(struct device *dev) { struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); - u32 val; if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { - dev_err(dev, "Failed to Suspend as Tegra PCIe is in EP mode\n"); - return -EPERM; + if (pcie->ep_state == EP_STATE_ENABLED) { + dev_err(dev, "Tegra PCIe is in EP mode, suspend not allowed\n"); + return -EPERM; + } + + disable_irq(pcie->pex_rst_irq); + return 0; } + return 0; +} + +static int tegra_pcie_dw_suspend_late(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + u32 val; + if (!pcie->link_state) return 0; @@ -2333,6 +2345,9 @@ static int tegra_pcie_dw_suspend_noirq(struct device *dev) { struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) + return 0; + if (!pcie->link_state) return 0; @@ -2347,6 +2362,9 @@ static int tegra_pcie_dw_resume_noirq(struct device *dev) struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); int ret; + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) + return 0; + if (!pcie->link_state) return 0; @@ -2379,8 +2397,8 @@ static int tegra_pcie_dw_resume_early(struct device *dev) u32 val; if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { - dev_err(dev, "Suspend is not supported in EP mode"); - return -ENOTSUPP; + enable_irq(pcie->pex_rst_irq); + return 0; } if (!pcie->link_state) @@ -2485,6 +2503,7 @@ static const struct of_device_id tegra_pcie_dw_of_match[] = { }; static const struct dev_pm_ops tegra_pcie_dw_pm_ops = { + .suspend = tegra_pcie_dw_suspend, .suspend_late = tegra_pcie_dw_suspend_late, .suspend_noirq = tegra_pcie_dw_suspend_noirq, .resume_noirq = tegra_pcie_dw_resume_noirq, From 1e877168b0e7b43a626a961b55876cec26d5fa2d Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:51 +0530 Subject: [PATCH 0512/1518] PCI: tegra194: Free up Endpoint resources during remove() [ Upstream commit 8870f02f7868209eb9bdc5dc53540a6262cf9227 ] Free up the resources during remove() that were acquired by the DesignWare driver for the Endpoint mode during probe(). Fixes: bb617cbd8151 ("PCI: tegra194: Clean up the exit path for Endpoint mode") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-11-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index f4784945c04bb..eb6fecf2e6f42 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -2285,6 +2285,7 @@ static int tegra_pcie_dw_probe(struct platform_device *pdev) static void tegra_pcie_dw_remove(struct platform_device *pdev) { struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev); + struct dw_pcie_ep *ep = &pcie->pci.ep; if (pcie->of_data->mode == DW_PCIE_RC_TYPE) { if (!pcie->link_state) @@ -2296,6 +2297,7 @@ static void tegra_pcie_dw_remove(struct platform_device *pdev) } else { disable_irq(pcie->pex_rst_irq); pex_ep_event_pex_rst_assert(pcie); + dw_pcie_ep_deinit(ep); } pm_runtime_disable(pcie->dev); From 5cb649c27024521b7bf1e94702b00d1af5844906 Mon Sep 17 00:00:00 2001 From: Manikanta Maddireddy Date: Wed, 25 Mar 2026 00:37:52 +0530 Subject: [PATCH 0513/1518] PCI: tegra194: Use DWC IP core version [ Upstream commit ea60ca067f0f098043610c96a915d162113c1aac ] Tegra194 PCIe driver used custom version numbers to detect Tegra194 and Tegra234 IPs. With version detect logic added, version check results in mismatch warnings: tegra194-pcie 14100000.pcie: Versions don't match (0000562a != 3536322a) Use HW version numbers which match to PORT_LOGIC.PCIE_VERSION_OFF in Tegra194 driver to avoid these kernel warnings. Fixes: a54e19073718 ("PCI: tegra194: Add Tegra234 PCIe support") Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-12-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-designware.h | 2 ++ drivers/pci/controller/dwc/pcie-tegra194.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index d32ee1fa3cf85..aa27211b68dd1 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -34,8 +34,10 @@ #define DW_PCIE_VER_470A 0x3437302a #define DW_PCIE_VER_480A 0x3438302a #define DW_PCIE_VER_490A 0x3439302a +#define DW_PCIE_VER_500A 0x3530302a #define DW_PCIE_VER_520A 0x3532302a #define DW_PCIE_VER_540A 0x3534302a +#define DW_PCIE_VER_562A 0x3536322a #define __dw_pcie_ver_cmp(_pci, _ver, _op) \ ((_pci)->version _op DW_PCIE_VER_ ## _ver) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index eb6fecf2e6f42..f740e0afafa94 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -35,8 +35,8 @@ #include #include "../../pci.h" -#define TEGRA194_DWC_IP_VER 0x490A -#define TEGRA234_DWC_IP_VER 0x562A +#define TEGRA194_DWC_IP_VER DW_PCIE_VER_500A +#define TEGRA234_DWC_IP_VER DW_PCIE_VER_562A #define APPL_PINMUX 0x0 #define APPL_PINMUX_PEX_RST BIT(0) From 9daf2a8d9cc140b2ade231428622ad34e6f5f93e Mon Sep 17 00:00:00 2001 From: Manikanta Maddireddy Date: Wed, 25 Mar 2026 00:37:53 +0530 Subject: [PATCH 0514/1518] PCI: dwc: Apply ECRC workaround to DesignWare 5.00a as well [ Upstream commit 40805f32dceadebb7381d911003100bec7b8cd51 ] The ECRC (TLP digest) workaround was originally added for DesignWare version 4.90a. Tegra234 SoC has 5.00a DWC HW version, which has the same ATU TD override behaviour, so apply the workaround for 5.00a too. Fixes: a54e19073718 ("PCI: tegra194: Add Tegra234 PCIe support") Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-13-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-designware.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 345365ea97c74..2c1dd6ffa27db 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -486,13 +486,13 @@ static inline void dw_pcie_writel_atu_ob(struct dw_pcie *pci, u32 index, u32 reg static inline u32 dw_pcie_enable_ecrc(u32 val) { /* - * DesignWare core version 4.90A has a design issue where the 'TD' - * bit in the Control register-1 of the ATU outbound region acts - * like an override for the ECRC setting, i.e., the presence of TLP - * Digest (ECRC) in the outgoing TLPs is solely determined by this - * bit. This is contrary to the PCIe spec which says that the - * enablement of the ECRC is solely determined by the AER - * registers. + * DWC versions 0x3530302a and 0x3536322a have a design issue where + * the 'TD' bit in the Control register-1 of the ATU outbound + * region acts like an override for the ECRC setting, i.e., the + * presence of TLP Digest (ECRC) in the outgoing TLPs is solely + * determined by this bit. This is contrary to the PCIe spec which + * says that the enablement of the ECRC is solely determined by the + * AER registers. * * Because of this, even when the ECRC is enabled through AER * registers, the transactions going through ATU won't have TLP @@ -559,7 +559,7 @@ int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, if (upper_32_bits(limit_addr) > upper_32_bits(parent_bus_addr) && dw_pcie_ver_is_ge(pci, 460A)) val |= PCIE_ATU_INCREASE_REGION_SIZE; - if (dw_pcie_ver_is(pci, 490A)) + if (dw_pcie_ver_is(pci, 490A) || dw_pcie_ver_is(pci, 500A)) val = dw_pcie_enable_ecrc(val); dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL1, val); From 2914977cb75e48e760ab6925154a6ad7a34ca9fa Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 18 Nov 2025 15:42:16 -0600 Subject: [PATCH 0515/1518] PCI: tegra194: Remove unnecessary L1SS disable code [ Upstream commit 07c99eac0bc2c1fe962e56d8b5dc5b1152d421bf ] The DWC core clears the L1 Substates Supported bits unless the driver sets the "dw_pcie.l1ss_support" flag. The tegra194 init_host_aspm() sets "dw_pcie.l1ss_support" if the platform has the "supports-clkreq" DT property. If "supports-clkreq" is absent, "dw_pcie.l1ss_support" is not set, and the DWC core will clear the L1 Substates Supported bits. The tegra194 code to clear the L1 Substates Supported bits is unnecessary, so remove it. Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20251118214312.2598220-3-helgaas@kernel.org Stable-dep-of: f59df1d9e6bd ("PCI: tegra194: Disable L1.2 capability of Tegra234 EP") Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 45 +++------------------- 1 file changed, 5 insertions(+), 40 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index f740e0afafa94..257965ada3bd0 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -263,7 +263,6 @@ struct tegra_pcie_dw { u32 msi_ctrl_int; u32 num_lanes; u32 cid; - u32 cfg_link_cap_l1sub; u32 ras_des_cap; u32 pcie_cap_base; u32 aspm_cmrt; @@ -478,8 +477,7 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) return IRQ_HANDLED; /* If EP doesn't advertise L1SS, just return */ - val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub); - if (!(val & (PCI_L1SS_CAP_ASPM_L1_1 | PCI_L1SS_CAP_ASPM_L1_2))) + if (!pci->l1ss_support) return IRQ_HANDLED; /* Check if BME is set to '1' */ @@ -602,24 +600,6 @@ static struct pci_ops tegra_pci_ops = { }; #if defined(CONFIG_PCIEASPM) -static void disable_aspm_l11(struct tegra_pcie_dw *pcie) -{ - u32 val; - - val = dw_pcie_readl_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub); - val &= ~PCI_L1SS_CAP_ASPM_L1_1; - dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val); -} - -static void disable_aspm_l12(struct tegra_pcie_dw *pcie) -{ - u32 val; - - val = dw_pcie_readl_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub); - val &= ~PCI_L1SS_CAP_ASPM_L1_2; - dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val); -} - static inline u32 event_counter_prog(struct tegra_pcie_dw *pcie, u32 event) { u32 val; @@ -676,10 +656,9 @@ static int aspm_state_cnt(struct seq_file *s, void *data) static void init_host_aspm(struct tegra_pcie_dw *pcie) { struct dw_pcie *pci = &pcie->pci; - u32 val; + u32 l1ss, val; - val = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS); - pcie->cfg_link_cap_l1sub = val + PCI_L1SS_CAP; + l1ss = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS); pcie->ras_des_cap = dw_pcie_find_ext_capability(&pcie->pci, PCI_EXT_CAP_ID_VNDR); @@ -691,11 +670,11 @@ static void init_host_aspm(struct tegra_pcie_dw *pcie) PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); /* Program T_cmrt and T_pwr_on values */ - val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub); + val = dw_pcie_readl_dbi(pci, l1ss + PCI_L1SS_CAP); val &= ~(PCI_L1SS_CAP_CM_RESTORE_TIME | PCI_L1SS_CAP_P_PWR_ON_VALUE); val |= (pcie->aspm_cmrt << 8); val |= (pcie->aspm_pwr_on_t << 19); - dw_pcie_writel_dbi(pci, pcie->cfg_link_cap_l1sub, val); + dw_pcie_writel_dbi(pci, l1ss + PCI_L1SS_CAP, val); if (pcie->supports_clkreq) pci->l1ss_support = true; @@ -723,8 +702,6 @@ static void init_debugfs(struct tegra_pcie_dw *pcie) aspm_state_cnt); } #else -static inline void disable_aspm_l12(struct tegra_pcie_dw *pcie) { return; } -static inline void disable_aspm_l11(struct tegra_pcie_dw *pcie) { return; } static inline void init_host_aspm(struct tegra_pcie_dw *pcie) { return; } static inline void init_debugfs(struct tegra_pcie_dw *pcie) { return; } #endif @@ -928,12 +905,6 @@ static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) init_host_aspm(pcie); - /* Disable ASPM-L1SS advertisement if there is no CLKREQ routing */ - if (!pcie->supports_clkreq) { - disable_aspm_l11(pcie); - disable_aspm_l12(pcie); - } - if (!pcie->of_data->has_l1ss_exit_fix) { val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; @@ -1848,12 +1819,6 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) init_host_aspm(pcie); - /* Disable ASPM-L1SS advertisement if there is no CLKREQ routing */ - if (!pcie->supports_clkreq) { - disable_aspm_l11(pcie); - disable_aspm_l12(pcie); - } - if (!pcie->of_data->has_l1ss_exit_fix) { val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; From 4e7a00aeb09172521ce651d5f0e0dd2a0775c22f Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Wed, 25 Mar 2026 00:37:54 +0530 Subject: [PATCH 0516/1518] PCI: tegra194: Disable L1.2 capability of Tegra234 EP [ Upstream commit f59df1d9e6bdb6bd7ef65fb5d200900ac40c20ba ] When Tegra234 is operating in the Endpoint mode with L1.2 enabled, PCIe link goes down during L1.2 exit. This is because Tegra234 powers up UPHY PLL immediately without making sure that the REFCLK is stable. This causes UPHY PLL to fail to lock to the correct frequency and leads to link going down. There is no hardware fix for this, hence do not advertise the L1.2 capability in the Endpoint mode. Fixes: a54e19073718 ("PCI: tegra194: Add Tegra234 PCIe support") Signed-off-by: Vidya Sagar Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-14-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 257965ada3bd0..c37be61f2b90a 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -234,6 +234,7 @@ struct tegra_pcie_dw_of_data { bool has_sbr_reset_fix; bool has_l1ss_exit_fix; bool has_ltr_req_fix; + bool disable_l1_2; u32 cdm_chk_int_en_bit; u32 gen4_preset_vec; u8 n_fts[2]; @@ -679,6 +680,23 @@ static void init_host_aspm(struct tegra_pcie_dw *pcie) if (pcie->supports_clkreq) pci->l1ss_support = true; + /* + * Disable L1.2 capability advertisement for Tegra234 Endpoint mode. + * Tegra234 has a hardware bug where during L1.2 exit, the UPHY PLL is + * powered up immediately without waiting for REFCLK to stabilize. This + * causes the PLL to fail to lock to the correct frequency, resulting in + * PCIe link loss. Since there is no hardware fix available, we prevent + * the Endpoint from advertising L1.2 support by clearing the L1.2 bits + * in the L1 PM Substates Capabilities register. This ensures the host + * will not attempt to enter L1.2 state with this Endpoint. + */ + if (pcie->of_data->disable_l1_2 && + pcie->of_data->mode == DW_PCIE_EP_TYPE) { + val = dw_pcie_readl_dbi(pci, l1ss + PCI_L1SS_CAP); + val &= ~(PCI_L1SS_CAP_PCIPM_L1_2 | PCI_L1SS_CAP_ASPM_L1_2); + dw_pcie_writel_dbi(pci, l1ss + PCI_L1SS_CAP, val); + } + /* Program L0s and L1 entrance latencies */ val = dw_pcie_readl_dbi(pci, PCIE_PORT_AFR); val &= ~PORT_AFR_L0S_ENTRANCE_LAT_MASK; @@ -2443,6 +2461,7 @@ static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_ep_of_data = { .mode = DW_PCIE_EP_TYPE, .has_l1ss_exit_fix = true, .has_ltr_req_fix = true, + .disable_l1_2 = true, .cdm_chk_int_en_bit = BIT(18), /* Gen4 - 6, 8 and 9 presets enabled */ .gen4_preset_vec = 0x340, From b059a41bdd5b202b2b9d7708403fb43c69689e53 Mon Sep 17 00:00:00 2001 From: Manikanta Maddireddy Date: Wed, 25 Mar 2026 00:37:55 +0530 Subject: [PATCH 0517/1518] PCI: tegra194: Fix CBB timeout caused by DBI access before core power-on [ Upstream commit 34b3eef48d980cd37b876e128bbf314f69fb5d70 ] When PERST# is deasserted twice (assert -> deassert -> assert -> deassert), a CBB (Control Backbone) timeout occurs at DBI register offset 0x8bc (PCIE_MISC_CONTROL_1_OFF). This happens because pci_epc_deinit_notify() and dw_pcie_ep_cleanup() are called before reset_control_deassert() powers on the controller core. The call chain that causes the timeout: pex_ep_event_pex_rst_deassert() pci_epc_deinit_notify() pci_epf_test_epc_deinit() pci_epf_test_clear_bar() pci_epc_clear_bar() dw_pcie_ep_clear_bar() __dw_pcie_ep_reset_bar() dw_pcie_dbi_ro_wr_en() <- Accesses 0x8bc DBI register reset_control_deassert(pcie->core_rst) <- Core powered on HERE The DBI registers, including PCIE_MISC_CONTROL_1_OFF (0x8bc), are only accessible after the controller core is powered on via reset_control_deassert(pcie->core_rst). Accessing them before this point results in a CBB timeout because the hardware is not yet operational. Fix this by moving pci_epc_deinit_notify() and dw_pcie_ep_cleanup() to after reset_control_deassert(pcie->core_rst), ensuring the controller is fully powered on before any DBI register accesses occur. Fixes: 40e2125381dc ("PCI: tegra194: Move controller cleanups to pex_ep_event_pex_rst_deassert()") Signed-off-by: Manikanta Maddireddy Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Jon Hunter Reviewed-by: Jon Hunter Reviewed-by: Vidya Sagar Link: https://patch.msgid.link/20260324190755.1094879-15-mmaddireddy@nvidia.com Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index c37be61f2b90a..fdbf440fb3819 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1750,10 +1750,6 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) goto fail_phy; } - /* Perform cleanup that requires refclk */ - pci_epc_deinit_notify(pcie->pci.ep.epc); - dw_pcie_ep_cleanup(&pcie->pci.ep); - /* Clear any stale interrupt statuses */ appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); @@ -1823,6 +1819,10 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) reset_control_deassert(pcie->core_rst); + /* Perform cleanup that requires refclk and core reset deasserted */ + pci_epc_deinit_notify(pcie->pci.ep.epc); + dw_pcie_ep_cleanup(&pcie->pci.ep); + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); val &= ~PORT_LOGIC_SPEED_CHANGE; dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); From e0b049bd7b279d7b6ad22a637cddced93198a51b Mon Sep 17 00:00:00 2001 From: Pei Xiao Date: Tue, 7 Apr 2026 15:26:59 +0800 Subject: [PATCH 0518/1518] spi: mtk-snfi: unregister ECC engine on probe failure and remove() callback [ Upstream commit ab00febad191d7a4400aa1c3468279fb508258d4 ] mtk_snand_probe() registers the on-host NAND ECC engine, but teardown was missing from both probe unwind and remove-time cleanup. Add a devm cleanup action after successful registration so nand_ecc_unregister_on_host_hw_engine() runs automatically on probe failures and during device removal. Fixes: 764f1b748164 ("spi: add driver for MTK SPI NAND Flash Interface") Signed-off-by: Pei Xiao Link: https://patch.msgid.link/20263f885f1a9c9d559f95275298cd6de4b11ed5.1775546401.git.xiaopei01@kylinos.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-mtk-snfi.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/spi/spi-mtk-snfi.c b/drivers/spi/spi-mtk-snfi.c index ae38c244e2581..a026b0e61994b 100644 --- a/drivers/spi/spi-mtk-snfi.c +++ b/drivers/spi/spi-mtk-snfi.c @@ -1303,6 +1303,13 @@ static const struct spi_controller_mem_caps mtk_snand_mem_caps = { .ecc = true, }; +static void mtk_unregister_ecc_engine(void *data) +{ + struct nand_ecc_engine *eng = data; + + nand_ecc_unregister_on_host_hw_engine(eng); +} + static irqreturn_t mtk_snand_irq(int irq, void *id) { struct mtk_snand *snf = id; @@ -1443,6 +1450,13 @@ static int mtk_snand_probe(struct platform_device *pdev) goto release_ecc; } + ret = devm_add_action_or_reset(&pdev->dev, mtk_unregister_ecc_engine, + &ms->ecc_eng); + if (ret) { + dev_err_probe(&pdev->dev, ret, "failed to add ECC unregister action\n"); + goto release_ecc; + } + ctlr->num_chipselect = 1; ctlr->mem_ops = &mtk_snand_mem_ops; ctlr->mem_caps = &mtk_snand_mem_caps; From 9a0f6c0485544311ff7151d6881912f31012afb9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Fri, 10 Apr 2026 00:54:32 -0300 Subject: [PATCH 0519/1518] ALSA: sc6000: Keep the programmed board state in card-private data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit fb79bf127ac2577b4876132da6dba768018aad4c ] The driver may auto-select IRQ and DMA resources at probe time, but sc6000_init_board() still derives the SC-6000 soft configuration from the module parameter arrays. When irq=auto or dma=auto is used, the codec is created with the selected resources while the board is programmed with the unresolved values. Store the mapped ports and generated SC-6000 board configuration in card-private data, build that configuration from the live probe results instead of the raw module parameters, and keep the probe-time board programming in a shared helper. This fixes the resource-programming mismatch and leaves the driver with a stable board-state block that can be reused by suspend/resume. Fixes: c282866101bf ("ALSA: sc6000: add support for SC-6600 and SC-7000") Signed-off-by: Cássio Gabriel Signed-off-by: Takashi Iwai Link: https://patch.msgid.link/20260410-alsa-sc6000-pm-v1-1-4d9e95493d26@gmail.com Signed-off-by: Sasha Levin --- sound/isa/sc6000.c | 152 +++++++++++++++++++++++++++------------------ 1 file changed, 92 insertions(+), 60 deletions(-) diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c index 6d618cc2ba457..9949e06403f61 100644 --- a/sound/isa/sc6000.c +++ b/sound/isa/sc6000.c @@ -100,6 +100,15 @@ MODULE_PARM_DESC(joystick, "Enable gameport."); #define PFX "sc6000: " #define DRV_NAME "SC-6000" +struct snd_sc6000 { + char __iomem *vport; + char __iomem *vmss_port; + u8 mss_config; + u8 config; + u8 hw_cfg[2]; + bool old_dsp; +}; + /* hardware dependent functions */ /* @@ -267,7 +276,7 @@ static int sc6000_dsp_reset(char __iomem *vport) /* detection and initialization */ static int sc6000_hw_cfg_write(struct device *devptr, - char __iomem *vport, const int *cfg) + char __iomem *vport, const u8 *cfg) { if (sc6000_write(devptr, vport, COMMAND_6C) < 0) { dev_warn(devptr, "CMD 0x%x: failed!\n", COMMAND_6C); @@ -353,8 +362,7 @@ static int sc6000_init_mss(struct device *devptr, return 0; } -static void sc6000_hw_cfg_encode(struct device *devptr, - char __iomem *vport, int *cfg, +static void sc6000_hw_cfg_encode(struct device *devptr, u8 *cfg, long xport, long xmpu, long xmss_port, int joystick) { @@ -376,27 +384,83 @@ static void sc6000_hw_cfg_encode(struct device *devptr, dev_dbg(devptr, "hw cfg %x, %x\n", cfg[0], cfg[1]); } -static int sc6000_init_board(struct device *devptr, - char __iomem *vport, - char __iomem *vmss_port, int dev) +static void sc6000_prepare_board(struct device *devptr, + struct snd_sc6000 *sc6000, + unsigned int dev, int xirq, int xdma) +{ + sc6000->mss_config = sc6000_irq_to_softcfg(xirq) | + sc6000_dma_to_softcfg(xdma); + sc6000->config = sc6000->mss_config | + sc6000_mpu_irq_to_softcfg(mpu_irq[dev]); + sc6000_hw_cfg_encode(devptr, sc6000->hw_cfg, port[dev], mpu_port[dev], + mss_port[dev], joystick[dev]); +} + +static void sc6000_detect_old_dsp(struct device *devptr, + struct snd_sc6000 *sc6000) +{ + sc6000_write(devptr, sc6000->vport, COMMAND_5C); + sc6000->old_dsp = sc6000_read(sc6000->vport) < 0; +} + +static int sc6000_program_board(struct device *devptr, + struct snd_sc6000 *sc6000) +{ + int err; + + if (!sc6000->old_dsp) { + if (sc6000_hw_cfg_write(devptr, sc6000->vport, + sc6000->hw_cfg) < 0) { + dev_err(devptr, "sc6000_hw_cfg_write: failed!\n"); + return -EIO; + } + } + + err = sc6000_setup_board(devptr, sc6000->vport, sc6000->config); + if (err < 0) { + dev_err(devptr, "sc6000_setup_board: failed!\n"); + return -ENODEV; + } + + sc6000_dsp_reset(sc6000->vport); + + if (!sc6000->old_dsp) { + sc6000_write(devptr, sc6000->vport, COMMAND_60); + sc6000_write(devptr, sc6000->vport, 0x02); + sc6000_dsp_reset(sc6000->vport); + } + + err = sc6000_setup_board(devptr, sc6000->vport, sc6000->config); + if (err < 0) { + dev_err(devptr, "sc6000_setup_board: failed!\n"); + return -ENODEV; + } + + err = sc6000_init_mss(devptr, sc6000->vport, sc6000->config, + sc6000->vmss_port, sc6000->mss_config); + if (err < 0) { + dev_err(devptr, "Cannot initialize Microsoft Sound System mode.\n"); + return -ENODEV; + } + + return 0; +} + +static int sc6000_init_board(struct device *devptr, struct snd_sc6000 *sc6000) { char answer[15]; char version[2]; - int mss_config = sc6000_irq_to_softcfg(irq[dev]) | - sc6000_dma_to_softcfg(dma[dev]); - int config = mss_config | - sc6000_mpu_irq_to_softcfg(mpu_irq[dev]); int err; - int old = 0; - err = sc6000_dsp_reset(vport); + err = sc6000_dsp_reset(sc6000->vport); if (err < 0) { dev_err(devptr, "sc6000_dsp_reset: failed!\n"); return err; } memset(answer, 0, sizeof(answer)); - err = sc6000_dsp_get_answer(devptr, vport, GET_DSP_COPYRIGHT, answer, 15); + err = sc6000_dsp_get_answer(devptr, sc6000->vport, GET_DSP_COPYRIGHT, + answer, 15); if (err <= 0) { dev_err(devptr, "sc6000_dsp_copyright: failed!\n"); return -ENODEV; @@ -408,54 +472,17 @@ static int sc6000_init_board(struct device *devptr, if (strncmp("SC-6000", answer, 7)) dev_warn(devptr, "Warning: non SC-6000 audio card!\n"); - if (sc6000_dsp_get_answer(devptr, vport, GET_DSP_VERSION, version, 2) < 2) { + if (sc6000_dsp_get_answer(devptr, sc6000->vport, + GET_DSP_VERSION, version, 2) < 2) { dev_err(devptr, "sc6000_dsp_version: failed!\n"); return -ENODEV; } dev_info(devptr, "Detected model: %s, DSP version %d.%d\n", answer, version[0], version[1]); - /* set configuration */ - sc6000_write(devptr, vport, COMMAND_5C); - if (sc6000_read(vport) < 0) - old = 1; - - if (!old) { - int cfg[2]; - sc6000_hw_cfg_encode(devptr, - vport, &cfg[0], port[dev], mpu_port[dev], - mss_port[dev], joystick[dev]); - if (sc6000_hw_cfg_write(devptr, vport, cfg) < 0) { - dev_err(devptr, "sc6000_hw_cfg_write: failed!\n"); - return -EIO; - } - } - err = sc6000_setup_board(devptr, vport, config); - if (err < 0) { - dev_err(devptr, "sc6000_setup_board: failed!\n"); - return -ENODEV; - } - - sc6000_dsp_reset(vport); - - if (!old) { - sc6000_write(devptr, vport, COMMAND_60); - sc6000_write(devptr, vport, 0x02); - sc6000_dsp_reset(vport); - } + sc6000_detect_old_dsp(devptr, sc6000); - err = sc6000_setup_board(devptr, vport, config); - if (err < 0) { - dev_err(devptr, "sc6000_setup_board: failed!\n"); - return -ENODEV; - } - err = sc6000_init_mss(devptr, vport, config, vmss_port, mss_config); - if (err < 0) { - dev_err(devptr, "Cannot initialize Microsoft Sound System mode.\n"); - return -ENODEV; - } - - return 0; + return sc6000_program_board(devptr, sc6000); } static int snd_sc6000_mixer(struct snd_wss *chip) @@ -538,10 +565,10 @@ static int snd_sc6000_match(struct device *devptr, unsigned int dev) static void snd_sc6000_free(struct snd_card *card) { - char __iomem *vport = (char __force __iomem *)card->private_data; + struct snd_sc6000 *sc6000 = card->private_data; - if (vport) - sc6000_setup_board(card->dev, vport, 0); + if (sc6000->vport) + sc6000_setup_board(card->dev, sc6000->vport, 0); } static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) @@ -552,15 +579,17 @@ static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) int xirq = irq[dev]; int xdma = dma[dev]; struct snd_card *card; + struct snd_sc6000 *sc6000; struct snd_wss *chip; struct snd_opl3 *opl3; char __iomem *vport; char __iomem *vmss_port; err = snd_devm_card_new(devptr, index[dev], id[dev], THIS_MODULE, - 0, &card); + sizeof(*sc6000), &card); if (err < 0) return err; + sc6000 = card->private_data; if (xirq == SNDRV_AUTO_IRQ) { xirq = snd_legacy_find_free_irq(possible_irqs); @@ -587,7 +616,7 @@ static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) dev_err(devptr, "I/O port cannot be iomapped.\n"); return -EBUSY; } - card->private_data = (void __force *)vport; + sc6000->vport = vport; /* to make it marked as used */ if (!devm_request_region(devptr, mss_port[dev], 4, DRV_NAME)) { @@ -600,12 +629,15 @@ static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) dev_err(devptr, "MSS port I/O cannot be iomapped.\n"); return -EBUSY; } + sc6000->vmss_port = vmss_port; dev_dbg(devptr, "Initializing BASE[0x%lx] IRQ[%d] DMA[%d] MIRQ[%d]\n", port[dev], xirq, xdma, mpu_irq[dev] == SNDRV_AUTO_IRQ ? 0 : mpu_irq[dev]); - err = sc6000_init_board(devptr, vport, vmss_port, dev); + sc6000_prepare_board(devptr, sc6000, dev, xirq, xdma); + + err = sc6000_init_board(devptr, sc6000); if (err < 0) return err; card->private_free = snd_sc6000_free; From 9769c143015cba7fbb3225940ff183d121ad234e Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Fri, 10 Apr 2026 21:08:01 +0800 Subject: [PATCH 0520/1518] dm cache: fix missing return in invalidate_committed's error path [ Upstream commit 8c0ee19db81f0fa1ff25fd75b22b17c0cc2acde3 ] In passthrough mode, dm-cache defers write submission until after metadata commit completes via the invalidate_committed() continuation. On commit error, invalidate_committed() calls invalidate_complete() to end the bio and free the migration struct, after which it should return immediately. The patch 4ca8b8bd952d ("dm cache: fix write hang in passthrough mode") omitted this early return, causing execution to fall through into the success path on error. This results in use-after-free on the migration struct in the subsequent calls. Fix by adding the missing return after the invalidate_complete() call. Fixes: 4ca8b8bd952d ("dm cache: fix write hang in passthrough mode") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/dm-devel/adjMq6T5RRjv_uxM@stanley.mountain/ Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka Signed-off-by: Sasha Levin --- drivers/md/dm-cache-target.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 9c64fe56ecb6c..bb0b484d4d687 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1521,8 +1521,10 @@ static void invalidate_committed(struct work_struct *ws) struct bio *bio = mg->overwrite_bio; struct per_bio_data *pb = get_per_bio_data(bio); - if (mg->k.input) + if (mg->k.input) { invalidate_complete(mg, false); + return; + } init_continuation(&mg->k, invalidate_completed); remap_to_origin_clear_discard(cache, bio, mg->invalidate_oblock); From b60a90bf7cde00d166ecf54971b7a859ca291504 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Apr 2026 07:54:06 -1000 Subject: [PATCH 0521/1518] sched_ext: Track @p's rq lock across set_cpus_allowed_scx -> ops.set_cpumask [ Upstream commit 9fb457074f6d118b30458624223abef985725a88 ] The SCX_CALL_OP_TASK call site passes rq=NULL incorrectly, leaving scx_locked_rq() unset. Pass task_rq(p) instead so update_locked_rq() reflects reality. v2: Add Fixes: tag (Andrea Righi). Fixes: 18853ba782be ("sched_ext: Track currently locked rq") Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi Signed-off-by: Sasha Levin --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 177bbf31116d0..17905ad77598c 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2606,7 +2606,7 @@ static void set_cpus_allowed_scx(struct task_struct *p, * designation pointless. Cast it away when calling the operation. */ if (SCX_HAS_OP(sch, set_cpumask)) - SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_cpumask, NULL, + SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_cpumask, task_rq(p), p, (struct cpumask *)p->cpus_ptr); } From 3ab9ab2dc18829d8c4bb65a677ae4ef7beb5c728 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Apr 2026 07:54:06 -1000 Subject: [PATCH 0522/1518] sched_ext: Fix ops.cgroup_move() invocation kf_mask and rq tracking [ Upstream commit b470e37c1fad72731be6f437e233cb6b16618f41 ] sched_move_task() invokes ops.cgroup_move() inside task_rq_lock(tsk), so @p's rq lock is held. The SCX_CALL_OP_TASK invocation mislabels this: - kf_mask = SCX_KF_UNLOCKED (== 0), claiming no lock is held. - rq = NULL, so update_locked_rq() doesn't run and scx_locked_rq() returns NULL. Switch to SCX_KF_REST and pass task_rq(p), matching ops.set_cpumask() from set_cpus_allowed_scx(). Three effects: - scx_bpf_task_cgroup() becomes callable (was rejected by scx_kf_allowed(__SCX_KF_RQ_LOCKED)). Safe; rq lock is held. - scx_bpf_dsq_move() is now rejected (was allowed via the unlocked branch). Calling it while holding an unrelated task's rq lock is risky; rejection is correct. - scx_bpf_select_cpu_*() previously took the unlocked branch in select_cpu_from_kfunc() and called task_rq_lock(p, &rf), which would deadlock against the already-held pi_lock. Now it takes the locked-rq branch and is rejected with -EPERM via the existing kf_allowed(SCX_KF_SELECT_CPU | SCX_KF_ENQUEUE) check. Latent deadlock fix. No in-tree scheduler is known to call any of these from ops.cgroup_move(). v2: Add Fixes: tag (Andrea Righi). Fixes: 18853ba782be ("sched_ext: Track currently locked rq") Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi Signed-off-by: Sasha Levin --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 17905ad77598c..32bb89559716e 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3225,7 +3225,7 @@ void scx_cgroup_move_task(struct task_struct *p) */ if (SCX_HAS_OP(sch, cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) - SCX_CALL_OP_TASK(sch, SCX_KF_UNLOCKED, cgroup_move, NULL, + SCX_CALL_OP_TASK(sch, SCX_KF_REST, cgroup_move, task_rq(p), p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); p->scx.cgrp_moving_from = NULL; From ff734dbd9e2432601a6dcd167cfb0bf8a36d1880 Mon Sep 17 00:00:00 2001 From: Haixin Xu Date: Mon, 30 Mar 2026 15:23:46 +0800 Subject: [PATCH 0523/1518] crypto: jitterentropy - replace long-held spinlock with mutex [ Upstream commit 01d798e9feb30212952d4e992801ba6bd6a82351 ] jent_kcapi_random() serializes the shared jitterentropy state, but it currently holds a spinlock across the jent_read_entropy() call. That path performs expensive jitter collection and SHA3 conditioning, so parallel readers can trigger stalls as contending waiters spin for the same lock. To prevent non-preemptible lock hold, replace rng->jent_lock with a mutex so contended readers sleep instead of spinning on a shared lock held across expensive entropy generation. Fixes: bb5530e40824 ("crypto: jitterentropy - add jitterentropy RNG") Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Yuan Tan Suggested-by: Xin Liu Signed-off-by: Haixin Xu Reviewed-by: Stephan Mueller Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/jitterentropy-kcapi.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c index a53de7affe8d1..e9cd2b27d1e3c 100644 --- a/crypto/jitterentropy-kcapi.c +++ b/crypto/jitterentropy-kcapi.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -193,7 +194,7 @@ int jent_read_random_block(void *hash_state, char *dst, unsigned int dst_len) ***************************************************************************/ struct jitterentropy { - spinlock_t jent_lock; + struct mutex jent_lock; struct rand_data *entropy_collector; struct crypto_shash *tfm; struct shash_desc *sdesc; @@ -203,7 +204,7 @@ static void jent_kcapi_cleanup(struct crypto_tfm *tfm) { struct jitterentropy *rng = crypto_tfm_ctx(tfm); - spin_lock(&rng->jent_lock); + mutex_lock(&rng->jent_lock); if (rng->sdesc) { shash_desc_zero(rng->sdesc); @@ -218,7 +219,7 @@ static void jent_kcapi_cleanup(struct crypto_tfm *tfm) if (rng->entropy_collector) jent_entropy_collector_free(rng->entropy_collector); rng->entropy_collector = NULL; - spin_unlock(&rng->jent_lock); + mutex_unlock(&rng->jent_lock); } static int jent_kcapi_init(struct crypto_tfm *tfm) @@ -228,7 +229,7 @@ static int jent_kcapi_init(struct crypto_tfm *tfm) struct shash_desc *sdesc; int size, ret = 0; - spin_lock_init(&rng->jent_lock); + mutex_init(&rng->jent_lock); /* * Use SHA3-256 as conditioner. We allocate only the generic @@ -265,7 +266,6 @@ static int jent_kcapi_init(struct crypto_tfm *tfm) goto err; } - spin_lock_init(&rng->jent_lock); return 0; err: @@ -280,7 +280,7 @@ static int jent_kcapi_random(struct crypto_rng *tfm, struct jitterentropy *rng = crypto_rng_ctx(tfm); int ret = 0; - spin_lock(&rng->jent_lock); + mutex_lock(&rng->jent_lock); ret = jent_read_entropy(rng->entropy_collector, rdata, dlen); @@ -306,7 +306,7 @@ static int jent_kcapi_random(struct crypto_rng *tfm, ret = -EINVAL; } - spin_unlock(&rng->jent_lock); + mutex_unlock(&rng->jent_lock); return ret; } From 4573698801107087b583dc9554161b90209f5626 Mon Sep 17 00:00:00 2001 From: "Geoffrey D. Bennett" Date: Tue, 14 Apr 2026 03:03:00 +0930 Subject: [PATCH 0524/1518] ALSA: usb-audio: Exclude Scarlett 18i20 1st Gen from SKIP_IFACE_SETUP [ Upstream commit a47306a74c31557b1e5cab54642950bbb20294cb ] Same issue as the other 1st Gen Scarletts: QUIRK_FLAG_SKIP_IFACE_SETUP causes distorted audio on the Scarlett 18i20 1st Gen (1235:800c). Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP") Reported-by: tucktuckg00se [https://github.com/geoffreybennett/linux-fcp/issues/54] Signed-off-by: Geoffrey D. Bennett Link: https://patch.msgid.link/ad0ozNnkcFrcjVQz@m.b4.vu Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index a2c039a1b3cd6..f21e708675422 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2426,6 +2426,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_VALIDATE_RATES), DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */ DEVICE_FLG(0x1235, 0x800a, 0), /* Focusrite Scarlett 2i4 1st Gen */ + DEVICE_FLG(0x1235, 0x800c, 0), /* Focusrite Scarlett 18i20 1st Gen */ DEVICE_FLG(0x1235, 0x8016, 0), /* Focusrite Scarlett 2i2 1st Gen */ DEVICE_FLG(0x1235, 0x801c, 0), /* Focusrite Scarlett Solo 1st Gen */ VENDOR_FLG(0x1235, /* Focusrite Novation */ From ac25916e75ca2c68274b642b44e84cf8ae654afe Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Tue, 14 Apr 2026 15:44:04 +0800 Subject: [PATCH 0525/1518] ALSA: hda/realtek - fixed speaker no sound update [ Upstream commit 46c862f5419e0a86b60b9f9558d247f6084c99f9 ] Fixed speaker has pop noise on Lenovo Thinkpad X11 Carbon Gen 12. Fixes: 630fbc6e870e ("ALSA: hda/realtek - fixed speaker no sound") Reported-and-tested-by: Jeremy Bethmont Closes: https://lore.kernel.org/CAC88DfsHrhyhy0Pn1O-z9egBvMYu=6NYgcvcC6KCgwh_-Ldkxg@mail.gmail.com Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/realtek/alc269.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index a2ecbe1412632..e14caa040fc92 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3615,22 +3615,11 @@ static void alc287_alc1318_playback_pcm_hook(struct hda_pcm_stream *hinfo, struct snd_pcm_substream *substream, int action) { - static const struct coef_fw dis_coefs[] = { - WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), - WRITE_COEF(0x28, 0x0004), WRITE_COEF(0x29, 0xb023), - }; /* Disable AMP silence detection */ - static const struct coef_fw en_coefs[] = { - WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), - WRITE_COEF(0x28, 0x0084), WRITE_COEF(0x29, 0xb023), - }; /* Enable AMP silence detection */ - switch (action) { case HDA_GEN_PCM_ACT_OPEN: - alc_process_coef_fw(codec, dis_coefs); alc_write_coefex_idx(codec, 0x5a, 0x00, 0x954f); /* write gpio3 to high */ break; case HDA_GEN_PCM_ACT_CLOSE: - alc_process_coef_fw(codec, en_coefs); alc_write_coefex_idx(codec, 0x5a, 0x00, 0x554f); /* write gpio3 as default value */ break; } @@ -3653,10 +3642,15 @@ static void alc287_fixup_lenovo_thinkpad_with_alc1318(struct hda_codec *codec, WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC301), WRITE_COEF(0x28, 0x0001), WRITE_COEF(0x29, 0xb023), }; + static const struct coef_fw dis_coefs[] = { + WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), + WRITE_COEF(0x28, 0x0004), WRITE_COEF(0x29, 0xb023), + }; /* Disable AMP silence detection */ if (action != HDA_FIXUP_ACT_PRE_PROBE) return; alc_update_coef_idx(codec, 0x10, 1<<11, 1<<11); + alc_process_coef_fw(codec, dis_coefs); alc_process_coef_fw(codec, coefs); spec->power_hook = alc287_s4_power_gpio3_default; spec->gen.pcm_playback_hook = alc287_alc1318_playback_pcm_hook; From 0d19bce169328388039ea26184b063c2678ec503 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 23 Feb 2026 12:04:05 +0100 Subject: [PATCH 0526/1518] gfs2: Call unlock_new_inode before d_instantiate [ Upstream commit 2ff7cf7e0640ff071ebc5c7e3dc2df024a7c91e6 ] As Neil Brown describes in detail in the link referenced below, new inodes must be unlocked before they can be instantiated. An even better fix is to use d_instantiate_new(), which combines d_instantiate() and unlock_new_inode(). Fixes: 3d36e57ff768 ("gfs2: gfs2_create_inode rework") Reported-by: syzbot+0ea5108a1f5fb4fcc2d8@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-fsdevel/177153754005.8396.8777398743501764194@noble.neil.brown.name/ Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/inode.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 03dd54fb7e8c8..12e5792190650 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -892,7 +892,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, goto fail_gunlock4; mark_inode_dirty(inode); - d_instantiate(dentry, inode); + d_instantiate_new(dentry, inode); /* After instantiate, errors should result in evict which will destroy * both inode and iopen glocks properly. */ if (file) { @@ -904,7 +904,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(&gh); gfs2_glock_put(io_gl); gfs2_qa_put(dip); - unlock_new_inode(inode); return error; fail_gunlock4: From 27c95204b51820bcc1ad1dab3e12abd4b42ef2b1 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Mon, 16 Feb 2026 16:06:24 +0100 Subject: [PATCH 0527/1518] fanotify: avoid/silence premature LSM capability checks [ Upstream commit 0d5ee3373426395478c355f3e93ba4b1118a04e9 ] Make sure calling capable()/ns_capable() actually leads to access denied when false is returned, because these functions emit an audit record when a Linux Security Module denies the capability, which makes it difficult to avoid allowing/silencing unnecessary permissions in security policies (namely with SELinux). Where the return value just used to set a flag, use the non-auditing ns_capable_noaudit() instead. Fixes: 7cea2a3c505e ("fanotify: support limited functionality for unprivileged users") Signed-off-by: Ondrej Mosnacek Reviewed-by: Paul Moore Reviewed-by: Amir Goldstein Link: https://patch.msgid.link/20260216150625.793013-2-omosnace@redhat.com Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/notify/fanotify/fanotify_user.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 1dadda82cae51..1c05c11e3cb25 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1611,17 +1611,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); - if (!capable(CAP_SYS_ADMIN)) { - /* - * An unprivileged user can setup an fanotify group with - * limited functionality - an unprivileged group is limited to - * notification events with file handles or mount ids and it - * cannot use unlimited queue/marks. - */ - if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || - !(flags & (FANOTIFY_FID_BITS | FAN_REPORT_MNT))) - return -EPERM; + /* + * An unprivileged user can setup an fanotify group with limited + * functionality - an unprivileged group is limited to notification + * events with file handles or mount ids and it cannot use unlimited + * queue/marks. + */ + if (((flags & FANOTIFY_ADMIN_INIT_FLAGS) || + !(flags & (FANOTIFY_FID_BITS | FAN_REPORT_MNT))) && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) { /* * Setting the internal flag FANOTIFY_UNPRIV on the group * prevents setting mount/filesystem marks on this group and @@ -2006,8 +2007,8 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, * A user is allowed to setup sb/mount/mntns marks only if it is * capable in the user ns where the group was created. */ - if (!ns_capable(group->user_ns, CAP_SYS_ADMIN) && - mark_type != FAN_MARK_INODE) + if (mark_type != FAN_MARK_INODE && + !ns_capable(group->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* From 14dee7a3441fa66b4b37dea99b5b5f261fad3722 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Mon, 16 Feb 2026 16:06:25 +0100 Subject: [PATCH 0528/1518] fanotify: call fanotify_events_supported() before path_permission() and security_path_notify() [ Upstream commit 66052a768d4726a31e939b5ac902f2b0b452c8d5 ] The latter trigger LSM (e.g. SELinux) checks, which will log a denial when permission is denied, so it's better to do them after validity checks to avoid logging a denial when the operation would fail anyway. Fixes: 0b3b094ac9a7 ("fanotify: Disallow permission events for proc filesystem") Signed-off-by: Ondrej Mosnacek Reviewed-by: Amir Goldstein Reviewed-by: Paul Moore Link: https://patch.msgid.link/20260216150625.793013-3-omosnace@redhat.com Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/notify/fanotify/fanotify_user.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 1c05c11e3cb25..5c30f4d8c7c16 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1210,6 +1210,7 @@ static int fanotify_find_path(int dfd, const char __user *filename, *path = fd_file(f)->f_path; path_get(path); + ret = 0; } else { unsigned int lookup_flags = 0; @@ -1219,22 +1220,7 @@ static int fanotify_find_path(int dfd, const char __user *filename, lookup_flags |= LOOKUP_DIRECTORY; ret = user_path_at(dfd, filename, lookup_flags, path); - if (ret) - goto out; } - - /* you can only watch an inode if you have read permissions on it */ - ret = path_permission(path, MAY_READ); - if (ret) { - path_put(path); - goto out; - } - - ret = security_path_notify(path, mask, obj_type); - if (ret) - path_put(path); - -out: return ret; } @@ -2074,6 +2060,15 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, goto path_put_and_out; } + /* you can only watch an inode if you have read permissions on it */ + ret = path_permission(&path, MAY_READ); + if (ret) + goto path_put_and_out; + + ret = security_path_notify(&path, mask, obj_type); + if (ret) + goto path_put_and_out; + if (fid_mode) { ret = fanotify_test_fsid(path.dentry, flags, &__fsid); if (ret) From f68e24b9697af129756e25309b3c969a0038ca8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= Date: Sat, 7 Mar 2026 19:07:56 -0300 Subject: [PATCH 0529/1518] ktest: Avoid undef warning when WARNINGS_FILE is unset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 057854f8a595160656fe77ed7bf0d2403724b915 ] check_buildlog() probes $warnings_file with -f even when WARNINGS_FILE is not configured. Perl warns about the uninitialized value and adds noise to the test log, which can hide the output we actually care about. Check that WARNINGS_FILE is defined before testing whether the file exists. Cc: John Hawley Cc: Andrea Righi Cc: Marcos Paulo de Souza Cc: Matthieu Baerts Cc: Fernando Fernandez Mancera Cc: Pedro Falcato Link: https://patch.msgid.link/20260307-ktest-fixes-v1-1-565d412f4925@suse.com Fixes: 4283b169abfb ("ktest: Add make_warnings_file and process full warnings") Signed-off-by: Ricardo B. Marlière Signed-off-by: Steven Rostedt Signed-off-by: Sasha Levin --- tools/testing/ktest/ktest.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 88de775097fef..28643812184bc 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -2508,7 +2508,7 @@ sub check_buildlog { my $save_no_reboot = $no_reboot; $no_reboot = 1; - if (-f $warnings_file) { + if (defined($warnings_file) && -f $warnings_file) { open(IN, $warnings_file) or dodie "Error opening $warnings_file"; From 9b798ad996922e28341a0aa87ecbc50f964d7e2c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= Date: Sat, 7 Mar 2026 19:07:59 -0300 Subject: [PATCH 0530/1518] ktest: Honor empty per-test option overrides MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a2de57a3c8192dcd67cccaff6c341b93748d799b ] A per-test override can clear an inherited default option by assigning an empty value, but __set_test_option() still used option_defined() to decide whether a per-test key existed. That turned an empty per-test assignment back into "fall back to the default", so tests still could not clear inherited settings. For example: DEFAULTS (...) LOG_FILE = /tmp/ktest-empty-override.log CLEAR_LOG = 1 ADD_CONFIG = /tmp/.config TEST_START TEST_TYPE = build BUILD_TYPE = nobuild ADD_CONFIG = This would run the test with ADD_CONFIG[1] = /tmp/.config Fix by checking whether the per-test key exists before falling back. If it does exist but is empty, treat it as unset for that test and stop the fallback chain there. Cc: John Hawley Cc: Andrea Righi Cc: Marcos Paulo de Souza Cc: Matthieu Baerts Cc: Fernando Fernandez Mancera Cc: Pedro Falcato Link: https://patch.msgid.link/20260307-ktest-fixes-v1-4-565d412f4925@suse.com Fixes: 22c37a9ac49d ("ktest: Allow tests to undefine default options") Signed-off-by: Ricardo B. Marlière Signed-off-by: Steven Rostedt Signed-off-by: Sasha Levin --- tools/testing/ktest/ktest.pl | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 28643812184bc..924e17df56f74 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -4183,7 +4183,8 @@ sub __set_test_option { my $option = "$name\[$i\]"; - if (option_defined($option)) { + if (exists($opt{$option})) { + return undef if (!option_defined($option)); return $opt{$option}; } @@ -4191,7 +4192,8 @@ sub __set_test_option { if ($i >= $test && $i < $test + $repeat_tests{$test}) { $option = "$name\[$test\]"; - if (option_defined($option)) { + if (exists($opt{$option})) { + return undef if (!option_defined($option)); return $opt{$option}; } } From 0a7a4ab3be8e34200f28861b95ddb74b279681ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20B=2E=20Marli=C3=A8re?= Date: Sat, 7 Mar 2026 19:08:03 -0300 Subject: [PATCH 0531/1518] ktest: Run POST_KTEST hooks on failure and cancellation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit bc6e165a452da909cef0efbc286e6695624db372 ] PRE_KTEST can be useful for setting up the environment and POST_KTEST to tear it down, however POST_KTEST only runs on the normal end-of-run path. It is skipped when ktest exits through dodie() or cancel_test(). Final cleanup hooks are skipped. Factor the final hook execution into run_post_ktest(), call it from the normal exit path and from the early exit paths, and guard it so the hook runs at most once. Cc: John Hawley Cc: Andrea Righi Cc: Marcos Paulo de Souza Cc: Matthieu Baerts Cc: Fernando Fernandez Mancera Cc: Pedro Falcato Link: https://patch.msgid.link/20260307-ktest-fixes-v1-8-565d412f4925@suse.com Fixes: 921ed4c7208e ("ktest: Add PRE/POST_KTEST and TEST options") Signed-off-by: Ricardo B. Marlière Signed-off-by: Steven Rostedt Signed-off-by: Sasha Levin --- tools/testing/ktest/ktest.pl | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 924e17df56f74..17bdce9cafac2 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -100,6 +100,7 @@ my $build_type; my $build_options; my $final_post_ktest; +my $post_ktest_done = 0; my $pre_ktest; my $post_ktest; my $pre_test; @@ -1575,6 +1576,24 @@ () return $name; } +sub run_post_ktest { + my $cmd; + + return if ($post_ktest_done); + + if (defined($final_post_ktest)) { + $cmd = $final_post_ktest; + } elsif (defined($post_ktest)) { + $cmd = $post_ktest; + } else { + return; + } + + my $cp_post_ktest = eval_kernel_version($cmd); + run_command $cp_post_ktest; + $post_ktest_done = 1; +} + sub dodie { # avoid recursion return if ($in_die); @@ -1634,6 +1653,7 @@ sub dodie { if (defined($post_test)) { run_command $post_test; } + run_post_ktest; die @_, "\n"; } @@ -4300,6 +4320,7 @@ sub cancel_test { send_email("KTEST: Your [$name] test was cancelled", "Your test started at $script_start_time was cancelled: sig int"); } + run_post_ktest; die "\nCaught Sig Int, test interrupted: $!\n" } @@ -4661,11 +4682,7 @@ sub die_usage { success $i; } -if (defined($final_post_ktest)) { - - my $cp_final_post_ktest = eval_kernel_version $final_post_ktest; - run_command $cp_final_post_ktest; -} +run_post_ktest; if ($opt{"POWEROFF_ON_SUCCESS"}) { halt; From dac3f0a68ec25169ed6d6bbe566835697f836268 Mon Sep 17 00:00:00 2001 From: Ivan Pravdin Date: Mon, 3 Nov 2025 11:19:06 -0500 Subject: [PATCH 0532/1518] rtla: Fix -C/--cgroup interface [ Upstream commit 7b71f3a6986c93defbb72bb6c143e04122720cb1 ] Currently, user can only specify cgroup to the tracer's thread the following ways: `-C[cgroup]` `-C[=cgroup]` `--cgroup[=cgroup]` If user tries to specify cgroup as `-C [cgroup]` or `--cgroup [cgroup]`, the parser silently fails and rtla's cgroup is used for the tracer threads. To make interface more user-friendly, allow user to specify cgroup in the aforementioned way, i.e. `-C [cgroup]` and `--cgroup [cgroup]`. Refactor identical logic between -t/--trace and -C/--cgroup into a common function. Change documentation to reflect this user interface change. Fixes: a957cbc02531 ("rtla: Add -C cgroup support") Signed-off-by: Ivan Pravdin Reviewed-by: Tomas Glozar Link: https://lore.kernel.org/r/16132f1565cf5142b5fbd179975be370b529ced7.1762186418.git.ipravdin.official@gmail.com [ use capital letter in subject, as required by tracing subsystem ] Signed-off-by: Tomas Glozar Stable-dep-of: 5b6dc659ad79 ("rtla/utils: Fix resource leak in set_comm_sched_attr()") Signed-off-by: Sasha Levin --- Documentation/tools/rtla/common_options.txt | 2 +- tools/tracing/rtla/src/osnoise_hist.c | 26 ++++++--------------- tools/tracing/rtla/src/osnoise_top.c | 26 ++++++--------------- tools/tracing/rtla/src/timerlat_hist.c | 26 ++++++--------------- tools/tracing/rtla/src/timerlat_top.c | 26 ++++++--------------- tools/tracing/rtla/src/utils.c | 26 +++++++++++++++++++++ tools/tracing/rtla/src/utils.h | 1 + 7 files changed, 56 insertions(+), 77 deletions(-) diff --git a/Documentation/tools/rtla/common_options.txt b/Documentation/tools/rtla/common_options.txt index 77ef35d3f8317..edc8e850f5d01 100644 --- a/Documentation/tools/rtla/common_options.txt +++ b/Documentation/tools/rtla/common_options.txt @@ -42,7 +42,7 @@ - *f:prio* - use SCHED_FIFO with *prio*; - *d:runtime[us|ms|s]:period[us|ms|s]* - use SCHED_DEADLINE with *runtime* and *period* in nanoseconds. -**-C**, **--cgroup**\[*=cgroup*] +**-C**, **--cgroup** \[*cgroup*] Set a *cgroup* to the tracer's threads. If the **-C** option is passed without arguments, the tracer's thread will inherit **rtla**'s *cgroup*. Otherwise, the threads will be placed on the *cgroup* passed to the option. diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index d22feb4d6cc9d..ae8426f40f8f4 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -428,9 +428,9 @@ static void osnoise_hist_usage(char *usage) static const char * const msg[] = { "", " usage: rtla osnoise hist [-h] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\", - " [-T us] [-t[file]] [-e sys[:event]] [--filter ] [--trigger ] \\", + " [-T us] [-t [file]] [-e sys[:event]] [--filter ] [--trigger ] \\", " [-c cpu-list] [-H cpu-list] [-P priority] [-b N] [-E N] [--no-header] [--no-summary] \\", - " [--no-index] [--with-zeros] [-C[=cgroup_name]] [--warm-up]", + " [--no-index] [--with-zeros] [-C [cgroup_name]] [--warm-up]", "", " -h/--help: print this menu", " -a/--auto: set automatic trace mode, stopping the session if argument in us sample is hit", @@ -441,10 +441,10 @@ static void osnoise_hist_usage(char *usage) " -T/--threshold us: the minimum delta to be considered a noise", " -c/--cpus cpu-list: list of cpus to run osnoise threads", " -H/--house-keeping cpus: run rtla control threads only on the given cpus", - " -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", + " -C/--cgroup [cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", " -d/--duration time[s|m|h|d]: duration of the session", " -D/--debug: print debug info", - " -t/--trace[file]: save the stopped trace to [file|osnoise_trace.txt]", + " -t/--trace [file]: save the stopped trace to [file|osnoise_trace.txt]", " -e/--event : enable the in the trace instance, multiple -e are allowed", " --filter : enable a trace event filter to the previous -e event", " --trigger : enable a trace event trigger to the previous -e event", @@ -575,13 +575,7 @@ static struct common_params break; case 'C': params->common.cgroup = 1; - if (!optarg) { - /* will inherit this cgroup */ - params->common.cgroup_name = NULL; - } else if (*optarg == '=') { - /* skip the = */ - params->common.cgroup_name = ++optarg; - } + params->common.cgroup_name = parse_optional_arg(argc, argv); break; case 'D': config_debug = 1; @@ -647,14 +641,8 @@ static struct common_params params->threshold = get_llong_from_str(optarg); break; case 't': - if (optarg) { - if (optarg[0] == '=') - trace_output = &optarg[1]; - else - trace_output = &optarg[0]; - } else if (optind < argc && argv[optind][0] != '0') - trace_output = argv[optind]; - else + trace_output = parse_optional_arg(argc, argv); + if (!trace_output) trace_output = "osnoise_trace.txt"; break; case '0': /* no header */ diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index a8d31030c4122..6ae7cdb3bdc0d 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -263,8 +263,8 @@ static void osnoise_top_usage(struct osnoise_params *params, char *usage) static const char * const msg[] = { " [-h] [-q] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\", - " [-T us] [-t[file]] [-e sys[:event]] [--filter ] [--trigger ] \\", - " [-c cpu-list] [-H cpu-list] [-P priority] [-C[=cgroup_name]] [--warm-up s]", + " [-T us] [-t [file]] [-e sys[:event]] [--filter ] [--trigger ] \\", + " [-c cpu-list] [-H cpu-list] [-P priority] [-C [cgroup_name]] [--warm-up s]", "", " -h/--help: print this menu", " -a/--auto: set automatic trace mode, stopping the session if argument in us sample is hit", @@ -275,10 +275,10 @@ static void osnoise_top_usage(struct osnoise_params *params, char *usage) " -T/--threshold us: the minimum delta to be considered a noise", " -c/--cpus cpu-list: list of cpus to run osnoise threads", " -H/--house-keeping cpus: run rtla control threads only on the given cpus", - " -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", + " -C/--cgroup [cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", " -d/--duration time[s|m|h|d]: duration of the session", " -D/--debug: print debug info", - " -t/--trace[file]: save the stopped trace to [file|osnoise_trace.txt]", + " -t/--trace [file]: save the stopped trace to [file|osnoise_trace.txt]", " -e/--event : enable the in the trace instance, multiple -e are allowed", " --filter : enable a trace event filter to the previous -e event", " --trigger : enable a trace event trigger to the previous -e event", @@ -409,13 +409,7 @@ struct common_params *osnoise_top_parse_args(int argc, char **argv) break; case 'C': params->common.cgroup = 1; - if (!optarg) { - /* will inherit this cgroup */ - params->common.cgroup_name = NULL; - } else if (*optarg == '=') { - /* skip the = */ - params->common.cgroup_name = ++optarg; - } + params->common.cgroup_name = parse_optional_arg(argc, argv); break; case 'D': config_debug = 1; @@ -475,14 +469,8 @@ struct common_params *osnoise_top_parse_args(int argc, char **argv) params->common.stop_total_us = get_llong_from_str(optarg); break; case 't': - if (optarg) { - if (optarg[0] == '=') - trace_output = &optarg[1]; - else - trace_output = &optarg[0]; - } else if (optind < argc && argv[optind][0] != '-') - trace_output = argv[optind]; - else + trace_output = parse_optional_arg(argc, argv); + if (!trace_output) trace_output = "osnoise_trace.txt"; break; case 'T': diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 3d56df3d5fa0d..311c4f18ce4c6 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -717,9 +717,9 @@ static void timerlat_hist_usage(char *usage) char *msg[] = { "", " usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-a us] [-p us] [-i us] [-T us] [-s us] \\", - " [-t[file]] [-e sys[:event]] [--filter ] [--trigger ] [-c cpu-list] [-H cpu-list]\\", + " [-t [file]] [-e sys[:event]] [--filter ] [--trigger ] [-c cpu-list] [-H cpu-list]\\", " [-P priority] [-E N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\", - " [--no-index] [--with-zeros] [--dma-latency us] [-C[=cgroup_name]] [--no-aa] [--dump-task] [-u|-k]", + " [--no-index] [--with-zeros] [--dma-latency us] [-C [cgroup_name]] [--no-aa] [--dump-task] [-u|-k]", " [--warm-up s] [--deepest-idle-state n]", "", " -h/--help: print this menu", @@ -730,11 +730,11 @@ static void timerlat_hist_usage(char *usage) " -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us", " -c/--cpus cpus: run the tracer only on the given cpus", " -H/--house-keeping cpus: run rtla control threads only on the given cpus", - " -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", + " -C/--cgroup [cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", " -d/--duration time[m|h|d]: duration of the session in seconds", " --dump-tasks: prints the task running on all CPUs if stop conditions are met (depends on !--no-aa)", " -D/--debug: print debug info", - " -t/--trace[file]: save the stopped trace to [file|timerlat_trace.txt]", + " -t/--trace [file]: save the stopped trace to [file|timerlat_trace.txt]", " -e/--event : enable the in the trace instance, multiple -e are allowed", " --filter : enable a trace event filter to the previous -e event", " --trigger : enable a trace event trigger to the previous -e event", @@ -890,13 +890,7 @@ static struct common_params break; case 'C': params->common.cgroup = 1; - if (!optarg) { - /* will inherit this cgroup */ - params->common.cgroup_name = NULL; - } else if (*optarg == '=') { - /* skip the = */ - params->common.cgroup_name = ++optarg; - } + params->common.cgroup_name = parse_optional_arg(argc, argv); break; case 'b': params->common.hist.bucket_size = get_llong_from_str(optarg); @@ -969,14 +963,8 @@ static struct common_params params->common.stop_total_us = get_llong_from_str(optarg); break; case 't': - if (optarg) { - if (optarg[0] == '=') - trace_output = &optarg[1]; - else - trace_output = &optarg[0]; - } else if (optind < argc && argv[optind][0] != '-') - trace_output = argv[optind]; - else + trace_output = parse_optional_arg(argc, argv); + if (!trace_output) trace_output = "timerlat_trace.txt"; break; case 'u': diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 6cc9a3607c665..3a3b11b5beaaa 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -483,8 +483,8 @@ static void timerlat_top_usage(char *usage) static const char *const msg[] = { "", " usage: rtla timerlat [top] [-h] [-q] [-a us] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] \\", - " [[-t[file]] [-e sys[:event]] [--filter ] [--trigger ] [-c cpu-list] [-H cpu-list]\\", - " [-P priority] [--dma-latency us] [--aa-only us] [-C[=cgroup_name]] [-u|-k] [--warm-up s] [--deepest-idle-state n]", + " [[-t [file]] [-e sys[:event]] [--filter ] [--trigger ] [-c cpu-list] [-H cpu-list]\\", + " [-P priority] [--dma-latency us] [--aa-only us] [-C [cgroup_name]] [-u|-k] [--warm-up s] [--deepest-idle-state n]", "", " -h/--help: print this menu", " -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit", @@ -495,11 +495,11 @@ static void timerlat_top_usage(char *usage) " -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us", " -c/--cpus cpus: run the tracer only on the given cpus", " -H/--house-keeping cpus: run rtla control threads only on the given cpus", - " -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", + " -C/--cgroup [cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited", " -d/--duration time[s|m|h|d]: duration of the session", " -D/--debug: print debug info", " --dump-tasks: prints the task running on all CPUs if stop conditions are met (depends on !--no-aa)", - " -t/--trace[file]: save the stopped trace to [file|timerlat_trace.txt]", + " -t/--trace [file]: save the stopped trace to [file|timerlat_trace.txt]", " -e/--event : enable the in the trace instance, multiple -e are allowed", " --filter : enable a trace event filter to the previous -e event", " --trigger : enable a trace event trigger to the previous -e event", @@ -654,13 +654,7 @@ static struct common_params break; case 'C': params->common.cgroup = 1; - if (!optarg) { - /* will inherit this cgroup */ - params->common.cgroup_name = NULL; - } else if (*optarg == '=') { - /* skip the = */ - params->common.cgroup_name = ++optarg; - } + params->common.cgroup_name = optarg; break; case 'D': config_debug = 1; @@ -723,14 +717,8 @@ static struct common_params params->common.stop_total_us = get_llong_from_str(optarg); break; case 't': - if (optarg) { - if (optarg[0] == '=') - trace_output = &optarg[1]; - else - trace_output = &optarg[0]; - } else if (optind < argc && argv[optind][0] != '-') - trace_output = argv[optind]; - else + trace_output = parse_optional_arg(argc, argv); + if (!trace_output) trace_output = "timerlat_trace.txt"; break; case 'u': diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index d6ab15dcb4907..bd5f34b446480 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -959,3 +959,29 @@ int auto_house_keeping(cpu_set_t *monitored_cpus) return 1; } + +/** + * parse_optional_arg - Parse optional argument value + * + * Parse optional argument value, which can be in the form of: + * -sarg, -s/--long=arg, -s/--long arg + * + * Returns arg value if found, NULL otherwise. + */ +char *parse_optional_arg(int argc, char **argv) +{ + if (optarg) { + if (optarg[0] == '=') { + /* skip the = */ + return &optarg[1]; + } else { + return optarg; + } + /* parse argument of form -s [arg] and --long [arg]*/ + } else if (optind < argc && argv[optind][0] != '-') { + /* consume optind */ + return argv[optind++]; + } else { + return NULL; + } +} diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index a2a6f89f342d0..d8d83abf0f0d0 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -24,6 +24,7 @@ long parse_seconds_duration(char *val); void get_duration(time_t start_time, char *output, int output_size); int parse_cpu_list(char *cpu_list, char **monitored_cpus); +char *parse_optional_arg(int argc, char **argv); long long get_llong_from_str(char *start); static inline void From 6a815bb366c9b5d4546c3fa4da0474edd40e7803 Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Tue, 6 Jan 2026 08:49:40 -0300 Subject: [PATCH 0533/1518] rtla: Replace atoi() with a robust strtoi() [ Upstream commit 7e9dfccf8f11c26208211457c4597a466135b56a ] The atoi() function does not perform error checking, which can lead to undefined behavior when parsing invalid or out-of-range strings. This can cause issues when parsing user-provided numerical inputs, such as signal numbers, PIDs, or CPU lists. To address this, introduce a new strtoi() helper function that safely converts a string to an integer. This function validates the input and checks for overflows, returning a negative value on failure. Replace all calls to atoi() with the new strtoi() function and add proper error handling to make the parsing more robust and prevent potential issues. Signed-off-by: Wander Lairson Costa Link: https://lore.kernel.org/r/20260106133655.249887-5-wander@redhat.com Signed-off-by: Tomas Glozar Stable-dep-of: 5b6dc659ad79 ("rtla/utils: Fix resource leak in set_comm_sched_attr()") Signed-off-by: Sasha Levin --- tools/tracing/rtla/src/actions.c | 7 +++--- tools/tracing/rtla/src/utils.c | 40 ++++++++++++++++++++++++++++---- tools/tracing/rtla/src/utils.h | 2 ++ 3 files changed, 41 insertions(+), 8 deletions(-) diff --git a/tools/tracing/rtla/src/actions.c b/tools/tracing/rtla/src/actions.c index 15986505b4376..4274fa0894b04 100644 --- a/tools/tracing/rtla/src/actions.c +++ b/tools/tracing/rtla/src/actions.c @@ -181,12 +181,13 @@ actions_parse(struct actions *self, const char *trigger, const char *tracefn) /* Takes two arguments, num (signal) and pid */ while (token != NULL) { if (strlen(token) > 4 && strncmp(token, "num=", 4) == 0) { - signal = atoi(token + 4); + if (strtoi(token + 4, &signal)) + return -1; } else if (strlen(token) > 4 && strncmp(token, "pid=", 4) == 0) { if (strncmp(token + 4, "parent", 7) == 0) pid = -1; - else - pid = atoi(token + 4); + else if (strtoi(token + 4, &pid)) + return -1; } else { /* Invalid argument */ return -1; diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index bd5f34b446480..6b7717fcd142b 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "utils.h" @@ -112,16 +113,18 @@ int parse_cpu_set(char *cpu_list, cpu_set_t *set) nr_cpus = sysconf(_SC_NPROCESSORS_CONF); for (p = cpu_list; *p; ) { - cpu = atoi(p); - if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus) + if (strtoi(p, &cpu)) + goto err; + if (cpu < 0 || cpu >= nr_cpus) goto err; while (isdigit(*p)) p++; if (*p == '-') { p++; - end_cpu = atoi(p); - if (end_cpu < cpu || (!end_cpu && *p != '0') || end_cpu >= nr_cpus) + if (strtoi(p, &end_cpu)) + goto err; + if (end_cpu < cpu || end_cpu >= nr_cpus) goto err; while (isdigit(*p)) p++; @@ -322,6 +325,7 @@ int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr) struct dirent *proc_entry; DIR *procfs; int retval; + int pid; if (strlen(comm_prefix) >= MAX_PATH) { err_msg("Command prefix is too long: %d < strlen(%s)\n", @@ -341,8 +345,12 @@ int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr) if (!retval) continue; + if (strtoi(proc_entry->d_name, &pid)) { + err_msg("'%s' is not a valid pid", proc_entry->d_name); + goto out_err; + } /* procfs_is_workload_pid confirmed it is a pid */ - retval = __set_sched_attr(atoi(proc_entry->d_name), attr); + retval = __set_sched_attr(pid, attr); if (retval) { err_msg("Error setting sched attributes for pid:%s\n", proc_entry->d_name); goto out_err; @@ -985,3 +993,25 @@ char *parse_optional_arg(int argc, char **argv) return NULL; } } + +/* + * strtoi - convert string to integer with error checking + * + * Returns 0 on success, -1 if conversion fails or result is out of int range. + */ +int strtoi(const char *s, int *res) +{ + char *end_ptr; + long lres; + + if (!*s) + return -1; + + errno = 0; + lres = strtol(s, &end_ptr, 0); + if (errno || *end_ptr || lres > INT_MAX || lres < INT_MIN) + return -1; + + *res = (int) lres; + return 0; +} diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index d8d83abf0f0d0..f11d27927223c 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -3,6 +3,7 @@ #include #include #include +#include /* * '18446744073709551615\0' @@ -81,6 +82,7 @@ static inline int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int stat static inline int have_libcpupower_support(void) { return 0; } #endif /* HAVE_LIBCPUPOWER_SUPPORT */ int auto_house_keeping(cpu_set_t *monitored_cpus); +__attribute__((__warn_unused_result__)) int strtoi(const char *s, int *res); #define ns_to_usf(x) (((double)x/1000)) #define ns_to_per(total, part) ((part * 100) / (double)total) From 2c57d6c0afcd5dc08adf4a10858a04e814b8ec67 Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Mon, 9 Mar 2026 16:46:30 -0300 Subject: [PATCH 0534/1518] rtla/utils: Fix resource leak in set_comm_sched_attr() [ Upstream commit 5b6dc659ad792c72b3ff1be8039ae2945e030928 ] The set_comm_sched_attr() function opens the /proc directory via opendir() but fails to call closedir() on its successful exit path. If the function iterates through all processes without error, it returns 0 directly, leaking the DIR stream pointer. Fix this by refactoring the function to use a single exit path. A retval variable is introduced to track the success or failure status. All exit points now jump to a unified out label that calls closedir() before the function returns, ensuring the resource is always freed. Fixes: dada03db9bb19 ("rtla: Remove procps-ng dependency") Signed-off-by: Wander Lairson Costa Link: https://lore.kernel.org/r/20260309195040.1019085-18-wander@redhat.com Signed-off-by: Tomas Glozar Signed-off-by: Sasha Levin --- tools/tracing/rtla/src/utils.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index 6b7717fcd142b..bf20077cca742 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -347,22 +347,23 @@ int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr) if (strtoi(proc_entry->d_name, &pid)) { err_msg("'%s' is not a valid pid", proc_entry->d_name); - goto out_err; + retval = 1; + goto out; } /* procfs_is_workload_pid confirmed it is a pid */ retval = __set_sched_attr(pid, attr); if (retval) { err_msg("Error setting sched attributes for pid:%s\n", proc_entry->d_name); - goto out_err; + goto out; } debug_msg("Set sched attributes for pid:%s\n", proc_entry->d_name); } - return 0; -out_err: + retval = 0; +out: closedir(procfs); - return 1; + return retval; } #define INVALID_VAL (~0L) From d05d4a6ee877bed2600189c63f7f8de597ec9e88 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 6 Mar 2026 18:05:48 +0100 Subject: [PATCH 0535/1518] gfs2: less aggressive low-memory log flushing [ Upstream commit 7288185ce87ec70133b7bc3b694b0f74bf46a0ee ] It turns out that for some workloads, the fix in commit b74cd55aa9a9d ("gfs2: low-memory forced flush fixes") causes the number of forced log flushes to increase to a degree that the overall filesystem performance drops significantly. Address that by forcing a log flush only when gfs2_writepages cannot make any progress rather than when it cannot make "enough" progress. Fixes: b74cd55aa9a9d ("gfs2: low-memory forced flush fixes") Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/aops.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 47d74afd63ac9..eafe0488b10d4 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -159,6 +159,7 @@ static int gfs2_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); + long initial_nr_to_write = wbc->nr_to_write; struct iomap_writepage_ctx wpc = { .inode = mapping->host, .wbc = wbc, @@ -167,13 +168,13 @@ static int gfs2_writepages(struct address_space *mapping, int ret; /* - * Even if we didn't write enough pages here, we might still be holding + * Even if we didn't write any pages here, we might still be holding * dirty pages in the ail. We forcibly flush the ail because we don't * want balance_dirty_pages() to loop indefinitely trying to write out * pages held in the ail that it can't find. */ ret = iomap_writepages(&wpc); - if (ret == 0 && wbc->nr_to_write > 0) + if (ret == 0 && wbc->nr_to_write == initial_nr_to_write) set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags); return ret; } From fdd424d7c35633ac577fd87d1b043d1b8a6cd350 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 27 Feb 2026 14:22:16 +0100 Subject: [PATCH 0536/1518] quota: Fix race of dquot_scan_active() with quota deactivation [ Upstream commit e93ab401da4b2e2c1b8ef2424de2f238d51c8b2d ] dquot_scan_active() can race with quota deactivation in quota_release_workfn() like: CPU0 (quota_release_workfn) CPU1 (dquot_scan_active) ============================== ============================== spin_lock(&dq_list_lock); list_replace_init( &releasing_dquots, &rls_head); /* dquot X on rls_head, dq_count == 0, DQ_ACTIVE_B still set */ spin_unlock(&dq_list_lock); synchronize_srcu(&dquot_srcu); spin_lock(&dq_list_lock); list_for_each_entry(dquot, &inuse_list, dq_inuse) { /* finds dquot X */ dquot_active(X) -> true atomic_inc(&X->dq_count); } spin_unlock(&dq_list_lock); spin_lock(&dq_list_lock); dquot = list_first_entry(&rls_head); WARN_ON_ONCE(atomic_read(&dquot->dq_count)); The problem is not only a cosmetic one as under memory pressure the caller of dquot_scan_active() can end up working on freed dquot. Fix the problem by making sure the dquot is removed from releasing list when we acquire a reference to it. Fixes: 869b6ea1609f ("quota: Fix slow quotaoff") Reported-by: Sam Sun Link: https://lore.kernel.org/all/CAEkJfYPTt3uP1vAYnQ5V2ZWn5O9PLhhGi5HbOcAzyP9vbXyjeg@mail.gmail.com Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/quota/dquot.c | 38 ++++++++++++++++++++++++++++++-------- include/linux/quotaops.h | 9 +-------- 2 files changed, 31 insertions(+), 16 deletions(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6c4a6ee1fa2b6..45a46dc4de4ef 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -363,6 +363,31 @@ static inline int dquot_active(struct dquot *dquot) return test_bit(DQ_ACTIVE_B, &dquot->dq_flags); } +static struct dquot *__dqgrab(struct dquot *dquot) +{ + lockdep_assert_held(&dq_list_lock); + if (!atomic_read(&dquot->dq_count)) + remove_free_dquot(dquot); + atomic_inc(&dquot->dq_count); + return dquot; +} + +/* + * Get reference to dquot when we got pointer to it by some other means. The + * dquot has to be active and the caller has to make sure it cannot get + * deactivated under our hands. + */ +struct dquot *dqgrab(struct dquot *dquot) +{ + spin_lock(&dq_list_lock); + WARN_ON_ONCE(!dquot_active(dquot)); + dquot = __dqgrab(dquot); + spin_unlock(&dq_list_lock); + + return dquot; +} +EXPORT_SYMBOL_GPL(dqgrab); + static inline int dquot_dirty(struct dquot *dquot) { return test_bit(DQ_MOD_B, &dquot->dq_flags); @@ -641,15 +666,14 @@ int dquot_scan_active(struct super_block *sb, continue; if (dquot->dq_sb != sb) continue; - /* Now we have active dquot so we can just increase use count */ - atomic_inc(&dquot->dq_count); + __dqgrab(dquot); spin_unlock(&dq_list_lock); dqput(old_dquot); old_dquot = dquot; /* * ->release_dquot() can be racing with us. Our reference - * protects us from new calls to it so just wait for any - * outstanding call and recheck the DQ_ACTIVE_B after that. + * protects us from dquot_release() proceeding so just wait for + * any outstanding call and recheck the DQ_ACTIVE_B after that. */ wait_on_dquot(dquot); if (dquot_active(dquot)) { @@ -717,7 +741,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ - dqgrab(dquot); + __dqgrab(dquot); spin_unlock(&dq_list_lock); err = dquot_write_dquot(dquot); if (err && !ret) @@ -963,9 +987,7 @@ struct dquot *dqget(struct super_block *sb, struct kqid qid) spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); } else { - if (!atomic_read(&dquot->dq_count)) - remove_free_dquot(dquot); - atomic_inc(&dquot->dq_count); + __dqgrab(dquot); spin_unlock(&dq_list_lock); dqstats_inc(DQST_CACHE_HITS); dqstats_inc(DQST_LOOKUPS); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index c334f82ed385a..f9c0f9d7c9d93 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -44,14 +44,7 @@ int dquot_initialize(struct inode *inode); bool dquot_initialize_needed(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); -static inline struct dquot *dqgrab(struct dquot *dquot) -{ - /* Make sure someone else has active reference to dquot */ - WARN_ON_ONCE(!atomic_read(&dquot->dq_count)); - WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); - atomic_inc(&dquot->dq_count); - return dquot; -} +struct dquot *dqgrab(struct dquot *dquot); static inline bool dquot_is_busy(struct dquot *dquot) { From 3f90bfd31f163b2ed6088afe087e45c6338a3737 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Mar 2026 17:55:08 +0100 Subject: [PATCH 0537/1518] vfio: unhide vdev->debug_root [ Upstream commit 555aa178f8d22261d71da74df6267e6e6e97f95a ] When debugfs is disabled, the hisilicon driver now fails to build: drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c: In function 'hisi_acc_vfio_debug_init': drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c:1671:62: error: 'struct vfio_device' has no member named 'debug_root' 1671 | vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root); | ^~ The driver otherwise relies on dead-code elimination, but this reference fails. The single struct member is not going to make much of a difference for memory consumption, so just keep this visible unconditionally. Signed-off-by: Arnd Bergmann Fixes: b398f91779b8 ("hisi_acc_vfio_pci: register debugfs for hisilicon migration driver") Link: https://lore.kernel.org/r/20260327165521.3779707-1-arnd@kernel.org Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- include/linux/vfio.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/vfio.h b/include/linux/vfio.h index eb563f538dee5..18fc36aadc326 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -71,13 +71,11 @@ struct vfio_device { u8 iommufd_attached:1; #endif u8 cdev_opened:1; -#ifdef CONFIG_DEBUG_FS /* * debug_root is a static property of the vfio_device * which must be set prior to registering the vfio_device. */ struct dentry *debug_root; -#endif }; /** From 49d9be0722da3a4a893ba905720cba1921834ec3 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 31 Mar 2026 06:13:42 +0200 Subject: [PATCH 0538/1518] gfs2: add some missing log locking [ Upstream commit fe2c8d051150b90b3ccb85f89e3b1d636cb88ec8 ] Function gfs2_logd() calls the log flushing functions gfs2_ail1_start(), gfs2_ail1_wait(), and gfs2_ail1_empty() without holding sdp->sd_log_flush_lock, but these functions require exclusion against concurrent transactions. To fix that, add a non-locking __gfs2_log_flush() function. Then, in gfs2_logd(), take sdp->sd_log_flush_lock before calling the above mentioned log flushing functions and __gfs2_log_flush(). Fixes: 5e4c7632aae1c ("gfs2: Issue revokes more intelligently") Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/log.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 115c4ac457e90..592f69602e5aa 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1027,14 +1027,15 @@ static void trans_drain(struct gfs2_trans *tr) } /** - * gfs2_log_flush - flush incore transaction(s) + * __gfs2_log_flush - flush incore transaction(s) * @sdp: The filesystem * @gl: The glock structure to flush. If NULL, flush the whole incore log * @flags: The log header flags: GFS2_LOG_HEAD_FLUSH_* and debug flags * */ -void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) +static void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, + u32 flags) { struct gfs2_trans *tr = NULL; unsigned int reserved_blocks = 0, used_blocks = 0; @@ -1042,7 +1043,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) unsigned int first_log_head; unsigned int reserved_revokes = 0; - down_write(&sdp->sd_log_flush_lock); trace_gfs2_log_flush(sdp, 1, flags); repeat: @@ -1154,7 +1154,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_assert_withdraw_delayed(sdp, used_blocks < reserved_blocks); gfs2_log_release(sdp, reserved_blocks - used_blocks); } - up_write(&sdp->sd_log_flush_lock); gfs2_trans_free(sdp, tr); if (gfs2_withdrawing(sdp)) gfs2_withdraw(sdp); @@ -1177,6 +1176,13 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) goto out_end; } +void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) +{ + down_write(&sdp->sd_log_flush_lock); + __gfs2_log_flush(sdp, gl, flags); + up_write(&sdp->sd_log_flush_lock); +} + /** * gfs2_merge_trans - Merge a new transaction into a cached transaction * @sdp: the filesystem @@ -1319,19 +1325,25 @@ int gfs2_logd(void *data) } if (gfs2_jrnl_flush_reqd(sdp) || t == 0) { + down_write(&sdp->sd_log_flush_lock); gfs2_ail1_empty(sdp, 0); - gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | - GFS2_LFC_LOGD_JFLUSH_REQD); + __gfs2_log_flush(sdp, NULL, + GFS2_LOG_HEAD_FLUSH_NORMAL | + GFS2_LFC_LOGD_JFLUSH_REQD); + up_write(&sdp->sd_log_flush_lock); } if (test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) || gfs2_ail_flush_reqd(sdp)) { clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags); + down_write(&sdp->sd_log_flush_lock); gfs2_ail1_start(sdp); gfs2_ail1_wait(sdp); gfs2_ail1_empty(sdp, 0); - gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | - GFS2_LFC_LOGD_AIL_FLUSH_REQD); + __gfs2_log_flush(sdp, NULL, + GFS2_LOG_HEAD_FLUSH_NORMAL | + GFS2_LFC_LOGD_AIL_FLUSH_REQD); + up_write(&sdp->sd_log_flush_lock); } t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; From d8ffae016c4a78693fe1283335d0b6833a9c1366 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 7 Apr 2026 12:14:30 +0200 Subject: [PATCH 0539/1518] gfs2: prevent NULL pointer dereference during unmount [ Upstream commit 74b4dbb946060a3233604d91859a9abd3708141d ] When flushing out outstanding glock work during an unmount, gfs2_log_flush() can be called when sdp->sd_jdesc has already been deallocated and sdp->sd_jdesc is NULL. Commit 35264909e9d1 ("gfs2: Fix NULL pointer dereference in gfs2_log_flush") added a check for that to gfs2_log_flush() itself, but it missed the sdp->sd_jdesc dereference in gfs2_log_release(). Fix that. Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202604071139.HNJiCaAi-lkp@intel.com/ Fixes: 35264909e9d1 ("gfs2: Fix NULL pointer dereference in gfs2_log_flush") Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/log.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 592f69602e5aa..ecc5c59b87008 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -471,8 +471,9 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) { atomic_add(blks, &sdp->sd_log_blks_free); trace_gfs2_log_blocks(sdp, blks); - gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= - sdp->sd_jdesc->jd_blocks); + gfs2_assert_withdraw(sdp, !sdp->sd_jdesc || + atomic_read(&sdp->sd_log_blks_free) <= + sdp->sd_jdesc->jd_blocks); if (atomic_read(&sdp->sd_log_blks_needed)) wake_up(&sdp->sd_log_waitq); } From e0e6b14995fd6fa2c0df8c712d76ab32f0694c31 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Fri, 10 Apr 2026 17:46:37 +0200 Subject: [PATCH 0540/1518] efi/capsule-loader: fix incorrect sizeof in phys array reallocation [ Upstream commit 48a428215782321b56956974f23593e40ce84b7a ] The krealloc() call for cap_info->phys in __efi_capsule_setup_info() uses sizeof(phys_addr_t *) instead of sizeof(phys_addr_t), which might be causing an undersized allocation. The allocation is also inconsistent with the initial array allocation in efi_capsule_open() that allocates one entry with sizeof(phys_addr_t), and the efi_capsule_write() function that stores phys_addr_t values (not pointers) via page_to_phys(). On 64-bit systems where sizeof(phys_addr_t) == sizeof(phys_addr_t *), this goes unnoticed. On 32-bit systems with PAE where phys_addr_t is 64-bit but pointers are 32-bit, this allocates half the required space, which might lead to a heap buffer overflow when storing physical addresses. This is similar to the bug fixed in commit fccfa646ef36 ("efi/capsule-loader: fix incorrect allocation size") which fixed the same issue at the initial allocation site. Fixes: f24c4d478013 ("efi/capsule-loader: Reinstate virtual capsule mapping") Assisted-by: Claude:claude-sonnet-4-5 Signed-off-by: Thomas Huth Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- drivers/firmware/efi/capsule-loader.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 0c17bdd388e12..bbddeb6a09552 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -67,7 +67,7 @@ int __efi_capsule_setup_info(struct capsule_info *cap_info) cap_info->pages = temp_page; temp_page = krealloc(cap_info->phys, - pages_needed * sizeof(phys_addr_t *), + pages_needed * sizeof(phys_addr_t), GFP_KERNEL | __GFP_ZERO); if (!temp_page) return -ENOMEM; From 7164b3953cefd540e7ebca828c793bc6869cfbc4 Mon Sep 17 00:00:00 2001 From: Joshua Klinesmith Date: Mon, 6 Apr 2026 22:31:12 -0400 Subject: [PATCH 0541/1518] ksmbd: fix use-after-free from async crypto on Qualcomm crypto engine [ Upstream commit 3e298897f41c61450c2e7a4f457e8b2485eb35b3 ] ksmbd_crypt_message() sets a NULL completion callback on AEAD requests and does not handle the -EINPROGRESS return code from async hardware crypto engines like the Qualcomm Crypto Engine (QCE). When QCE returns -EINPROGRESS, ksmbd treats it as an error and immediately frees the request while the hardware DMA operation is still in flight. The DMA completion callback then dereferences freed memory, causing a NULL pointer crash: pc : qce_skcipher_done+0x24/0x174 lr : vchan_complete+0x230/0x27c ... el1h_64_irq+0x68/0x6c ksmbd_free_work_struct+0x20/0x118 [ksmbd] ksmbd_exit_file_cache+0x694/0xa4c [ksmbd] Use the standard crypto_wait_req() pattern with crypto_req_done() as the completion callback, matching the approach used by the SMB client in fs/smb/client/smb2ops.c. This properly handles both synchronous engines (immediate return) and async engines (-EINPROGRESS followed by callback notification). Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Link: https://github.com/openwrt/openwrt/issues/21822 Signed-off-by: Joshua Klinesmith Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/auth.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index c37b86a83cac8..b63f32c692bab 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1076,6 +1076,7 @@ int ksmbd_crypt_message(struct ksmbd_work *work, struct kvec *iov, struct smb2_transform_hdr *tr_hdr = smb2_get_msg(iov[0].iov_base); unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int rc; + DECLARE_CRYPTO_WAIT(wait); struct scatterlist *sg; u8 sign[SMB2_SIGNATURE_SIZE] = {}; u8 key[SMB3_ENC_DEC_KEY_SIZE]; @@ -1162,12 +1163,12 @@ int ksmbd_crypt_message(struct ksmbd_work *work, struct kvec *iov, aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); - aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | + CRYPTO_TFM_REQ_MAY_SLEEP, + crypto_req_done, &wait); - if (enc) - rc = crypto_aead_encrypt(req); - else - rc = crypto_aead_decrypt(req); + rc = crypto_wait_req(enc ? crypto_aead_encrypt(req) : + crypto_aead_decrypt(req), &wait); if (rc) goto free_iv; From e2b1e633257e7236a304eaf9d03b785a0586ed78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Fri, 2 May 2025 12:43:22 -0400 Subject: [PATCH 0542/1518] arm64: dts: mediatek: mt8365: Describe infracfg-nao as a pure syscon MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0651c24658360706c30588cec0a12c05edb03e9a ] The infracfg-nao register space at 0x1020e000 has different registers than the infracfg space at 0x10001000, and most importantly, doesn't contain any clock controls. Therefore it shouldn't use the same compatible used for the mt8365 infracfg clocks driver: mediatek,mt8365-infracfg. Since it currently does, probe errors are reported in the kernel logs: [ 0.245959] Failed to register clk ifr_pmic_tmr: -EEXIST [ 0.245998] clk-mt8365 1020e000.infracfg: probe with driver clk-mt8365 failed with error -17 This register space is used only as a syscon for bus control by the power domain controller, so in order to properly describe it and fix the errors, set its compatible to a distinct compatible used exclusively as a syscon, drop the clock-cells, and while at it rename the node to 'syscon' following the naming convention. Fixes: 6ff945376556 ("arm64: dts: mediatek: Initial mt8365-evk support") Signed-off-by: Nícolas F. R. A. Prado Reviewed-by: David Lechner Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt8365.dtsi | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt8365.dtsi b/arch/arm64/boot/dts/mediatek/mt8365.dtsi index e6d2b3221a3b7..49ad4dee9c4cf 100644 --- a/arch/arm64/boot/dts/mediatek/mt8365.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8365.dtsi @@ -495,10 +495,9 @@ #iommu-cells = <1>; }; - infracfg_nao: infracfg@1020e000 { - compatible = "mediatek,mt8365-infracfg", "syscon"; + infracfg_nao: syscon@1020e000 { + compatible = "mediatek,mt8365-infracfg-nao", "syscon"; reg = <0 0x1020e000 0 0x1000>; - #clock-cells = <1>; }; rng: rng@1020f000 { From 6dd527eb8b70672f44dbba7ef2985e132dda20ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 24 Feb 2026 09:25:41 +0100 Subject: [PATCH 0543/1518] ARM: dts: mediatek: mt7623: fix efuse fallback compatible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5978ff33cc6f0988388a2830dc5cd2ea4e81f36a ] Fix following validation error: arch/arm/boot/dts/mediatek/mt7623a-rfb-emmc.dtb: efuse@10206000: compatible: 'oneOf' conditional failed, one must be fixed: ['mediatek,mt7623-efuse', 'mediatek,mt8173-efuse'] is too long 'mediatek,mt8173-efuse' was expected 'mediatek,efuse' was expected from schema $id: http://devicetree.org/schemas/nvmem/mediatek,efuse.yaml# arch/arm/boot/dts/mediatek/mt7623a-rfb-emmc.dtb: efuse@10206000: Unevaluated properties are not allowed ('compatible' was unexpected) from schema $id: http://devicetree.org/schemas/nvmem/mediatek,efuse.yaml# Fixes: 43c7a91b4b3a ("arm: dts: mt7623: add efuse nodes to the mt7623.dtsi file") Signed-off-by: Rafał Miłecki Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm/boot/dts/mediatek/mt7623.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/mediatek/mt7623.dtsi b/arch/arm/boot/dts/mediatek/mt7623.dtsi index fd7a89cc337d6..a60b1d6879ffe 100644 --- a/arch/arm/boot/dts/mediatek/mt7623.dtsi +++ b/arch/arm/boot/dts/mediatek/mt7623.dtsi @@ -328,7 +328,7 @@ efuse: efuse@10206000 { compatible = "mediatek,mt7623-efuse", - "mediatek,mt8173-efuse"; + "mediatek,efuse"; reg = <0 0x10206000 0 0x1000>; #address-cells = <1>; #size-cells = <1>; From 1793249c067a4b28e1aba0ad0e4d73aa9f9e165a Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Mon, 26 Jan 2026 15:50:42 +0900 Subject: [PATCH 0544/1518] memory: tegra124-emc: Fix dll_change check [ Upstream commit 9597ab9a8296ab337e6820f8a717ff621078b632 ] The code checking whether the specified memory timing enables DLL in the EMRS register was reversed. DLL is enabled if bit A0 is low. Fix the check. Fixes: 73a7f0a90641 ("memory: tegra: Add EMC (external memory controller) driver") Signed-off-by: Mikko Perttunen Link: https://patch.msgid.link/20260126-fix-emc-dllchange-v1-1-47ad3bb63262@nvidia.com Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/memory/tegra/tegra124-emc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/memory/tegra/tegra124-emc.c b/drivers/memory/tegra/tegra124-emc.c index 03f1daa2d132a..71d20b5916d89 100644 --- a/drivers/memory/tegra/tegra124-emc.c +++ b/drivers/memory/tegra/tegra124-emc.c @@ -608,7 +608,7 @@ static int tegra_emc_prepare_timing_change(struct tegra_emc *emc, if ((last->emc_mode_1 & 0x1) == (timing->emc_mode_1 & 0x1)) dll_change = DLL_CHANGE_NONE; - else if (timing->emc_mode_1 & 0x1) + else if (!(timing->emc_mode_1 & 0x1)) dll_change = DLL_CHANGE_ON; else dll_change = DLL_CHANGE_OFF; From 86b77735cb4c47df862bc9ac6bb8b3fd6e69b118 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Mon, 26 Jan 2026 15:50:43 +0900 Subject: [PATCH 0545/1518] memory: tegra30-emc: Fix dll_change check [ Upstream commit 0a93f2355cf4922ad2399dbef5ea1049fef116d4 ] The code checking whether the specified memory timing enables DLL in the EMRS register was reversed. DLL is enabled if bit A0 is low. Fix the check. Fixes: e34212c75a68 ("memory: tegra: Introduce Tegra30 EMC driver") Signed-off-by: Mikko Perttunen Link: https://patch.msgid.link/20260126-fix-emc-dllchange-v1-2-47ad3bb63262@nvidia.com Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/memory/tegra/tegra30-emc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/memory/tegra/tegra30-emc.c b/drivers/memory/tegra/tegra30-emc.c index 921dce1b8bc63..4981b7fa0f780 100644 --- a/drivers/memory/tegra/tegra30-emc.c +++ b/drivers/memory/tegra/tegra30-emc.c @@ -554,14 +554,14 @@ static int emc_prepare_timing_change(struct tegra_emc *emc, unsigned long rate) emc->emc_cfg = readl_relaxed(emc->regs + EMC_CFG); emc_dbg = readl_relaxed(emc->regs + EMC_DBG); - if (emc->dll_on == !!(timing->emc_mode_1 & 0x1)) + if (emc->dll_on == !(timing->emc_mode_1 & 0x1)) dll_change = DLL_CHANGE_NONE; - else if (timing->emc_mode_1 & 0x1) + else if (!(timing->emc_mode_1 & 0x1)) dll_change = DLL_CHANGE_ON; else dll_change = DLL_CHANGE_OFF; - emc->dll_on = !!(timing->emc_mode_1 & 0x1); + emc->dll_on = !(timing->emc_mode_1 & 0x1); if (timing->data[80] && !readl_relaxed(emc->regs + EMC_ZCAL_INTERVAL)) emc->zcal_long = true; From a028d9919f46c3a9490062167a82347126a88485 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Mon, 19 Jan 2026 11:34:09 +0100 Subject: [PATCH 0546/1518] arm64: dts: imx8-apalis: Fix LEDs name collision [ Upstream commit 92ab53b9bb2a72581c32073755077af916eb9aee ] Ixora boards have multiple instances of status leds, to avoid a name collision add the function-enumerator property. This fixes the following Linux kernel warnings: leds-gpio leds: Led green:status renamed to green:status_1 due to name collision leds-gpio leds: Led red:status renamed to red:status_1 due to name collision Fixes: c083131c9021 ("arm64: dts: freescale: add apalis imx8 aka quadmax carrier board support") Signed-off-by: Francesco Dolcini Reviewed-by: Frank Li Reviewed-by: Daniel Baluta Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.1.dtsi | 4 ++++ arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.1.dtsi index 3d8731504ce15..1e8b6e61e33d4 100644 --- a/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.1.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.1.dtsi @@ -21,6 +21,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <1>; gpios = <&lsio_gpio5 27 GPIO_ACTIVE_HIGH>; }; @@ -29,6 +30,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <1>; gpios = <&lsio_gpio5 29 GPIO_ACTIVE_HIGH>; }; @@ -37,6 +39,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <2>; gpios = <&lsio_gpio5 20 GPIO_ACTIVE_HIGH>; }; @@ -45,6 +48,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <2>; gpios = <&lsio_gpio5 21 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi index 106e802a68ba5..70dcb66f8fda4 100644 --- a/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-apalis-ixora-v1.2.dtsi @@ -21,6 +21,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <1>; gpios = <&lsio_gpio5 27 GPIO_ACTIVE_HIGH>; }; @@ -29,6 +30,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <1>; gpios = <&lsio_gpio5 29 GPIO_ACTIVE_HIGH>; }; @@ -37,6 +39,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <2>; gpios = <&lsio_gpio5 20 GPIO_ACTIVE_HIGH>; }; @@ -45,6 +48,7 @@ color = ; default-state = "off"; function = LED_FUNCTION_STATUS; + function-enumerator = <2>; gpios = <&lsio_gpio5 21 GPIO_ACTIVE_HIGH>; }; }; From e483129ae51315f12222f034ca40fd9b0780bb0f Mon Sep 17 00:00:00 2001 From: Luke Wang Date: Tue, 3 Feb 2026 19:23:10 +0800 Subject: [PATCH 0547/1518] arm64: dts: imx91-11x11-evk: change usdhc tuning step for eMMC and SD [ Upstream commit 5ab0c76df2403137a6d0fb27a55e03cedf47f44c ] During system resume, the following errors occurred: [ 430.638625] mmc1: error -84 writing Cache Enable bit [ 430.643618] mmc1: error -84 doing runtime resume For eMMC and SD, there are two tuning pass windows and the gap between those two windows may only have one cell. If tuning step > 1, the gap may just be skipped and host assumes those two windows as a continuous windows. This will cause a wrong delay cell near the gap to be selected. Set the tuning step to 1 to avoid selecting the wrong delay cell. For SDIO, the gap is sufficiently large, so the default tuning step does not cause this issue. Fixes: 6772c4cffd87 ("arm64: dts: freescale: add i.MX91 11x11 EVK basic support") Signed-off-by: Luke Wang Reviewed-by: Frank Li Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx91-11x11-evk.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx91-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx91-11x11-evk.dts index aca78768dbd4b..4164d9e4e0fd2 100644 --- a/arch/arm64/boot/dts/freescale/imx91-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx91-11x11-evk.dts @@ -415,6 +415,7 @@ pinctrl-1 = <&pinctrl_usdhc1_100mhz>; pinctrl-2 = <&pinctrl_usdhc1_200mhz>; pinctrl-names = "default", "state_100mhz", "state_200mhz"; + fsl,tuning-step = <1>; status = "okay"; }; @@ -429,6 +430,7 @@ pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_gpio_sleep>; pinctrl-names = "default", "state_100mhz", "state_200mhz", "sleep"; vmmc-supply = <®_usdhc2_vmmc>; + fsl,tuning-step = <1>; status = "okay"; }; From 8e7ff76becce01927774e784b6aa0ed7e14ff4de Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 10 Feb 2026 09:03:02 +0100 Subject: [PATCH 0548/1518] arm64: dts: rockchip: Make Jaguar PCIe-refclk pin use pull-up config [ Upstream commit f45d4356feeba1c8dac3414b688f59292ddfc9f9 ] The hardware PU/PD config of the pin after reset is to pull-up and on Jaguar this will also keep the device in reset until the driver actually enables the pin. So restore this boot pull-up config of the pin on Jaguar instead of setting it to pull-none. Suggested-by: Quentin Schulz Fixes: 0ec7e1096332 ("arm64: dts: rockchip: add PCIe3 support on rk3588-jaguar") Signed-off-by: Heiko Stuebner Reviewed-by: Shawn Lin Reviewed-by: Quentin Schulz Link: https://patch.msgid.link/20260210080303.680403-5-heiko@sntech.de Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts index 176925d0a1a80..557158093b586 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts @@ -585,7 +585,7 @@ pcie30x4 { pcie30x4_clkreqn_m0: pcie30x4-clkreqn-m0 { - rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>; + rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_up>; }; pcie30x4_perstn_m0: pcie30x4-perstn-m0 { From 982b56bf7c7d2baf6e4875e06102e17b6927ba8f Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Thu, 5 Feb 2026 15:34:53 +0800 Subject: [PATCH 0549/1518] arm64: dts: imx8mp-evk: Enable pull select bit for PCIe regulator GPIO (M.2 W_DISABLE1) [ Upstream commit d1e7eab6033f9885a02c4b4e8f09e34d8e9d21ab ] The current pin configuration for MX8MP_IOMUXC_SD1_DATA4__GPIO2_IO06 sets the weak pull-up but does not enable the pull select field. Bit 8 in the IOMUX register must be set in order for the weak pull-up to actually take effect. Update the pinctrl setting from 0x40 to 0x140 to enable both the pull select and the weak pull-up, ensuring the line behaves as expected. Fixes: d50650500064 ("arm64: dts: imx8mp-evk: Add PCIe support") Signed-off-by: Sherry Sun Reviewed-by: Frank Li Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-evk.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index 3730792daf501..d957d6cc20f7f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -995,7 +995,7 @@ pinctrl_pcie0_reg: pcie0reggrp { fsl,pins = < - MX8MP_IOMUXC_SD1_DATA4__GPIO2_IO06 0x40 + MX8MP_IOMUXC_SD1_DATA4__GPIO2_IO06 0x140 >; }; From 643af7b854596c9f02799cd8b93927d8f154ec67 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 13 Feb 2026 10:36:36 -0800 Subject: [PATCH 0550/1518] iommufd: vfio compatibility extension check for noiommu mode [ Upstream commit 7147ec874ea08c322d779d8eba28946e294ed1f3 ] VFIO_CHECK_EXTENSION should return false for TYPE1_IOMMU variants when in NO-IOMMU mode and IOMMUFD compat container is set. This change makes the behavior match VFIO_CONTAINER in noiommu mode. It also prevents userspace from incorrectly attempting to use TYPE1 IOMMU operations in a no-iommu context. Fixes: d624d6652a65 ("iommufd: vfio container FD ioctl compatibility") Link: https://patch.msgid.link/r/20260213183636.3340-1-jacob.pan@linux.microsoft.com Signed-off-by: Jacob Pan Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/iommu/iommufd/vfio_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c index a258ee2f4579f..acb48cdd3b005 100644 --- a/drivers/iommu/iommufd/vfio_compat.c +++ b/drivers/iommu/iommufd/vfio_compat.c @@ -283,7 +283,7 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, case VFIO_TYPE1_IOMMU: case VFIO_TYPE1v2_IOMMU: case VFIO_UNMAP_ALL: - return 1; + return !ictx->no_iommu_mode; case VFIO_NOIOMMU_IOMMU: return IS_ENABLED(CONFIG_VFIO_NOIOMMU); From 4e3f607c3b99a537f65247725d51b5a2c960d221 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 29 Dec 2025 15:28:07 +0100 Subject: [PATCH 0551/1518] arm64: dts: qcom: sm6125-ginkgo: Fix missing msm-id subtype [ Upstream commit 2c3b8260d1a0d9a388f2d30e3bbe50d93edfa2aa ] qcom,msm-id property must consist of two numbers, where the second number is the subtype, as reported by dtbs_check: sm6125-xiaomi-ginkgo.dtb: / (xiaomi,ginkgo): qcom,msm-id:0: [394] is too short Xiaomi vendor DTS for Trinket IDP and QRD boards uses value of 0x10000, so put it here as well. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20251229142806.241088-2-krzysztof.kozlowski@oss.qualcomm.com Signed-off-by: Bjorn Andersson Stable-dep-of: 535e5741bc9a ("arm64: dts: qcom: sm6125-xiaomi-ginkgo: Remove board-id") Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts index 68a237215bd1f..6b68e391cf3ea 100644 --- a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts +++ b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts @@ -19,7 +19,7 @@ chassis-type = "handset"; /* required for bootloader to select correct board */ - qcom,msm-id = ; + qcom,msm-id = ; qcom,board-id = <22 0>; chosen { From 6256ef55fe90c2351c281955d4a97df54ac56a08 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Mon, 26 Jan 2026 17:34:51 +0100 Subject: [PATCH 0552/1518] arm64: dts: qcom: sm6125-xiaomi-ginkgo: Remove board-id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 535e5741bc9acef5ea2561aa300f28370599e7e2 ] Remove board-id it is not necessary for the bootloader. Fixes: 9b1a6c925c88 ("arm64: dts: qcom: sm6125: Initial support for xiaomi-ginkgo") Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Signed-off-by: Barnabás Czémán Link: https://lore.kernel.org/r/20260126-xiaomi-willow-v3-1-aad7b106c311@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts index 6b68e391cf3ea..bf03226a6f854 100644 --- a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts +++ b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts @@ -18,9 +18,7 @@ compatible = "xiaomi,ginkgo", "qcom,sm6125"; chassis-type = "handset"; - /* required for bootloader to select correct board */ qcom,msm-id = ; - qcom,board-id = <22 0>; chosen { #address-cells = <2>; From e849632c0988e9f162357449256a92f14978acd1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Mon, 26 Jan 2026 17:34:52 +0100 Subject: [PATCH 0553/1518] arm64: dts: qcom: sm6125-xiaomi-ginkgo: Correct reserved memory ranges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 242801cc24e865cb525ef7d826ce6ebeffcad606 ] The device was crashing on high memory load because the reserved memory ranges was wrongly defined. Correct the ranges for avoid the crashes. Change the ramoops memory range to match with the values from the recovery to be able to get the results from the device. Fixes: 9b1a6c925c88 ("arm64: dts: qcom: sm6125: Initial support for xiaomi-ginkgo") Reviewed-by: Konrad Dybcio Signed-off-by: Barnabás Czémán Link: https://lore.kernel.org/r/20260126-xiaomi-willow-v3-2-aad7b106c311@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- .../boot/dts/qcom/sm6125-xiaomi-ginkgo.dts | 41 +++++++++++++------ 1 file changed, 29 insertions(+), 12 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts index bf03226a6f854..d5e5abdb3b2ff 100644 --- a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts +++ b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts @@ -13,6 +13,12 @@ #include "sm6125.dtsi" #include "pm6125.dtsi" +/delete-node/ &adsp_pil_mem; +/delete-node/ &cont_splash_mem; +/delete-node/ &gpu_mem; +/delete-node/ &ipa_fw_mem; +/delete-node/ &ipa_gsi_mem; + / { model = "Xiaomi Redmi Note 8"; compatible = "xiaomi,ginkgo", "qcom,sm6125"; @@ -36,28 +42,39 @@ }; reserved-memory { - debug_mem: debug@ffb00000 { - reg = <0x0 0xffb00000 0x0 0xc0000>; + adsp_pil_mem: adsp_pil_mem@55300000 { + reg = <0x0 0x55300000 0x0 0x2200000>; no-map; }; - last_log_mem: lastlog@ffbc0000 { - reg = <0x0 0xffbc0000 0x0 0x80000>; + ipa_fw_mem: ipa_fw_mem@57500000 { + reg = <0x0 0x57500000 0x0 0x10000>; no-map; }; - pstore_mem: ramoops@ffc00000 { - compatible = "ramoops"; - reg = <0x0 0xffc40000 0x0 0xc0000>; - record-size = <0x1000>; - console-size = <0x40000>; - pmsg-size = <0x20000>; + ipa_gsi_mem: ipa_gsi_mem@57510000 { + reg = <0x0 0x57510000 0x0 0x5000>; + no-map; }; - cmdline_mem: memory@ffd00000 { - reg = <0x0 0xffd40000 0x0 0x1000>; + gpu_mem: gpu_mem@57515000 { + reg = <0x0 0x57515000 0x0 0x2000>; no-map; }; + + framebuffer@5c000000 { + reg = <0x0 0x5c000000 0x0 (2340 * 1080 * 4)>; + no-map; + }; + + /* Matching with recovery values to be able to get the results. */ + ramoops@61600000 { + compatible = "ramoops"; + reg = <0x0 0x61600000 0x0 0x400000>; + record-size = <0x80000>; + pmsg-size = <0x200000>; + console-size = <0x100000>; + }; }; extcon_usb: extcon-usb { From 449023f22c11b2816a2655a590aae9b0bf144313 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Mon, 26 Jan 2026 17:34:54 +0100 Subject: [PATCH 0554/1518] arm64: dts: qcom: sm6125-xiaomi-ginkgo: Remove extcon MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 79664600fd3ed3972ad9321e13d1f80267730447 ] GPIO pin 102 is related to DisplayPort what is not supported by this device and it is also disabled at downstream, remove the unnecessary extcon-usb node. Fixes: 9b1a6c925c88 ("arm64: dts: qcom: sm6125: Initial support for xiaomi-ginkgo") Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Signed-off-by: Barnabás Czémán Link: https://lore.kernel.org/r/20260126-xiaomi-willow-v3-4-aad7b106c311@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts | 9 --------- 1 file changed, 9 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts index d5e5abdb3b2ff..418cfe67a2da8 100644 --- a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts +++ b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts @@ -77,11 +77,6 @@ }; }; - extcon_usb: extcon-usb { - compatible = "linux,extcon-usb-gpio"; - id-gpios = <&tlmm 102 GPIO_ACTIVE_HIGH>; - }; - gpio-keys { compatible = "gpio-keys"; @@ -304,7 +299,3 @@ &usb3 { status = "okay"; }; - -&usb3_dwc3 { - extcon = <&extcon_usb>; -}; From c4620dad9f1b56830b36c24618aedd11e6510fbb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Mon, 26 Jan 2026 17:34:55 +0100 Subject: [PATCH 0555/1518] arm64: dts: qcom: sm6125-xiaomi-ginkgo: Fix reserved gpio ranges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e8669e010991154bedadd1cd67700544e0362e99 ] The device was crashing on boot because the reserved gpio ranges was wrongly defined. Correct the ranges for avoid pinctrl crashing. Fixes: 9b1a6c925c88 ("arm64: dts: qcom: sm6125: Initial support for xiaomi-ginkgo") Tested-by: Biswapriyo Nath Reviewed-by: Konrad Dybcio Signed-off-by: Barnabás Czémán Link: https://lore.kernel.org/r/20260126-xiaomi-willow-v3-5-aad7b106c311@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts index 418cfe67a2da8..c3edeee3af3ef 100644 --- a/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts +++ b/arch/arm64/boot/dts/qcom/sm6125-xiaomi-ginkgo.dts @@ -293,7 +293,7 @@ }; &tlmm { - gpio-reserved-ranges = <22 2>, <28 6>; + gpio-reserved-ranges = <0 4>, <30 4>; }; &usb3 { From a2475c0a2bbbea5a554b1a36a73111c42047396a Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jan 2026 10:45:03 +0100 Subject: [PATCH 0556/1518] arm64: dts: qcom: talos: Add missing clock-names to GCC [ Upstream commit c653607929bb4e0d8b80573bdb523adab5b975c2 ] The binding for this clock controller requires that clock-names are present. They're not really used by the kernel driver, but they're marked as required, so someone might have assumed it's done on purpose (where in reality we try to stay away from that since index-based references are faster, take up less space and are already widely used) and referenced it in drivers for another OS. Hence, do the least painful thing and add the missing entries. Fixes: 8e266654a2fe ("arm64: dts: qcom: add QCS615 platform") Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Taniya Das Link: https://lore.kernel.org/r/20260126-topic-talos_dt_warn-v1-1-c452afc647ad@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6150.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm6150.dtsi b/arch/arm64/boot/dts/qcom/sm6150.dtsi index 363b9f436cd0a..a066ad5ffde57 100644 --- a/arch/arm64/boot/dts/qcom/sm6150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6150.dtsi @@ -522,6 +522,9 @@ clocks = <&rpmhcc RPMH_CXO_CLK>, <&rpmhcc RPMH_CXO_CLK_A>, <&sleep_clk>; + clock-names = "bi_tcxo", + "bi_tcxo_ao", + "sleep_clk"; #clock-cells = <1>; #reset-cells = <1>; From 1a94d799de9e6ed533d3da3ebcbe48b236196a00 Mon Sep 17 00:00:00 2001 From: Akari Tsuyukusa Date: Thu, 12 Mar 2026 13:15:28 +0900 Subject: [PATCH 0557/1518] arm64: dts: mediatek: mt6795: Fix gpio-ranges pin count [ Upstream commit c4c4823c8a5baa10b8100b01f49d7c3f4a871689 ] The gpio-ranges in the MT6795 pinctrl node were incorrectly defined, therefore, GPIO196 cannot be used. Correct the range count to match the driver. Fixes: b888886a4536 ("arm64: dts: mediatek: mt6795: Add pinctrl controller node") Signed-off-by: Akari Tsuyukusa Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt6795.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt6795.dtsi b/arch/arm64/boot/dts/mediatek/mt6795.dtsi index 58833e5135c8e..9757e37a65d4e 100644 --- a/arch/arm64/boot/dts/mediatek/mt6795.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt6795.dtsi @@ -372,7 +372,7 @@ ; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pio 0 0 196>; + gpio-ranges = <&pio 0 0 197>; interrupt-controller; #interrupt-cells = <2>; }; From 1cda0e4ef9c47b46a450571f407735e24abf152b Mon Sep 17 00:00:00 2001 From: Akari Tsuyukusa Date: Thu, 12 Mar 2026 13:15:29 +0900 Subject: [PATCH 0558/1518] arm64: dts: mediatek: mt7981b: Fix gpio-ranges pin count [ Upstream commit b62a927f4a46a7f58d88ba3d5fb6e88e1a4b4603 ] The gpio-ranges in the MT7981B pinctrl node were incorrectly defined, therefore, pin 56 cannot be used. Correct the range count to match the driver. Fixes: 62b24c7fdf0a ("arm64: dts: mediatek: mt7981: add pinctrl") Signed-off-by: Akari Tsuyukusa Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt7981b.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt7981b.dtsi b/arch/arm64/boot/dts/mediatek/mt7981b.dtsi index 277c11247c132..88d7c3da3e49b 100644 --- a/arch/arm64/boot/dts/mediatek/mt7981b.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7981b.dtsi @@ -225,7 +225,7 @@ interrupt-controller; interrupts = ; interrupt-parent = <&gic>; - gpio-ranges = <&pio 0 0 56>; + gpio-ranges = <&pio 0 0 57>; gpio-controller; #gpio-cells = <2>; #interrupt-cells = <2>; From d02f10e74fe22abaeb823e1b29c8b059d838ba8a Mon Sep 17 00:00:00 2001 From: Akari Tsuyukusa Date: Thu, 12 Mar 2026 13:15:30 +0900 Subject: [PATCH 0559/1518] arm64: dts: mediatek: mt7986a: Fix gpio-ranges pin count [ Upstream commit 820ed0c1a13c5fafb36232538d793f99a0986ef3 ] The gpio-ranges in the MT7986A pinctrl node were incorrectly defined, therefore, pin 100 cannot be used. Correct the range count to match the driver. Fixes: c3a064a32ed9 ("arm64: dts: mediatek: add pinctrl support for mt7986a") Signed-off-by: Akari Tsuyukusa Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt7986a.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index a8972330a7b89..6786e5b590e85 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -187,7 +187,7 @@ "iocfg_lb", "iocfg_tr", "iocfg_tl", "eint"; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pio 0 0 100>; + gpio-ranges = <&pio 0 0 101>; interrupt-controller; interrupts = ; interrupt-parent = <&gic>; From a5f56ff8573ffdc9cdac21822c139533ae3c1e0e Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Thu, 12 Mar 2026 17:40:42 +0100 Subject: [PATCH 0560/1518] iommufd/selftest: Fix page leaks in mock_viommu_{init,destroy} [ Upstream commit 09c091fddb0b93297ea659ab48ee64f54ebeeaa2 ] mock_viommu_init() allocates two pages using __get_free_pages(..., 1), but its error path and mock_viommu_destroy() only release the first page using free_page(), leaking the second page. Use free_pages() with the matching order instead to avoid any page leaks. Fixes: 80478a2b450e ("iommufd/selftest: Add coverage for the new mmap interface") Link: https://patch.msgid.link/r/20260312164040.457293-3-thorsten.blum@linux.dev Signed-off-by: Thorsten Blum Reviewed-by: Nicolin Chen Reviewed-by: Pranjal Shrivastava Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/iommu/iommufd/selftest.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index dc0947aaac625..8fd27f65d6237 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -699,7 +699,7 @@ static void mock_viommu_destroy(struct iommufd_viommu *viommu) if (mock_viommu->mmap_offset) iommufd_viommu_destroy_mmap(&mock_viommu->core, mock_viommu->mmap_offset); - free_page((unsigned long)mock_viommu->page); + free_pages((unsigned long)mock_viommu->page, 1); mutex_destroy(&mock_viommu->queue_mutex); /* iommufd core frees mock_viommu and viommu */ @@ -933,7 +933,7 @@ static int mock_viommu_init(struct iommufd_viommu *viommu, iommufd_viommu_destroy_mmap(&mock_viommu->core, mock_viommu->mmap_offset); err_free_page: - free_page((unsigned long)mock_viommu->page); + free_pages((unsigned long)mock_viommu->page, 1); return rc; } From 7e6420179e217308780ce6a8b11f161911fb135b Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Fri, 20 Feb 2026 11:36:16 +0100 Subject: [PATCH 0561/1518] arm64: dts: imx8mp-kontron: Fix touch reset configuration on DL devices [ Upstream commit 058c53476dde9937877e93d964a283bbb5e1e4c7 ] The reset signal needs a pullup, but there is no hardware pullup. As a workaround, enable the internal pullup to fix the touchscreen. As this deviates from the default generic GPIO settings in the OSM devicetree, add a new node for the touch pinctrl and redefine the generic gpio1 pinctrl. Fixes: 946ab10e3f40f ("arm64: dts: Add support for Kontron OSM-S i.MX8MP SoM and BL carrier board") Signed-off-by: Frieder Schrempf Reviewed-by: Frank Li Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- .../boot/dts/freescale/imx8mp-kontron-dl.dtso | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-kontron-dl.dtso b/arch/arm64/boot/dts/freescale/imx8mp-kontron-dl.dtso index a3cba41d2b531..7131e9a499ae1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-kontron-dl.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mp-kontron-dl.dtso @@ -77,6 +77,8 @@ touchscreen@5d { compatible = "goodix,gt928"; reg = <0x5d>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_touch>; interrupt-parent = <&gpio1>; interrupts = <6 8>; irq-gpios = <&gpio1 6 0>; @@ -98,6 +100,16 @@ status = "okay"; }; +/* redefine to remove touch controller GPIOs */ +&pinctrl_gpio1 { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO00__GPIO1_IO00 0x19 /* GPIO_A_0 */ + MX8MP_IOMUXC_GPIO1_IO01__GPIO1_IO01 0x19 /* GPIO_A_1 */ + MX8MP_IOMUXC_GPIO1_IO05__GPIO1_IO05 0x19 /* GPIO_A_2 */ + MX8MP_IOMUXC_GPIO1_IO08__GPIO1_IO08 0x19 /* GPIO_A_5 */ + >; +}; + &pwm1 { status = "okay"; }; @@ -108,4 +120,11 @@ MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28 0x19 >; }; + + pinctrl_touch: touchgrp { + fsl,pins = < + MX8MP_IOMUXC_GPIO1_IO06__GPIO1_IO06 0x19 + MX8MP_IOMUXC_GPIO1_IO07__GPIO1_IO07 0x150 + >; + }; }; From 6c5178dd60366274a5ac180a3ffaba5aca2cd307 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Fri, 20 Feb 2026 11:36:17 +0100 Subject: [PATCH 0562/1518] arm64: dts: imx8mp-kontron: Drop vmmc-supply to fix SD card on SMARC eval carrier [ Upstream commit d2ce84eecf081056b1d18d7524de52f849281ba7 ] The SMARC evaluation carrier provides an SD card power switch that complies with the OSM standard definition. The OSM base devicetree already describes this correctly. Stop overriding the vmmc-supply in the board devicetree and rely on the definition from the OSM base DTS instead to fix the power supply configuration for the SD card. Fixes: 6fe1ced5ccab7 ("arm64: dts: Add support for Kontron i.MX8MP SMARC module and eval carrier") Signed-off-by: Frieder Schrempf Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- .../boot/dts/freescale/imx8mp-kontron-smarc-eval-carrier.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-kontron-smarc-eval-carrier.dts b/arch/arm64/boot/dts/freescale/imx8mp-kontron-smarc-eval-carrier.dts index 2173a36ff6917..74d620dd06b7b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-kontron-smarc-eval-carrier.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-kontron-smarc-eval-carrier.dts @@ -249,6 +249,5 @@ }; &usdhc2 { - vmmc-supply = <®_vdd_3v3>; status = "okay"; }; From 1ab2769df3deb91a7b0b222bfcae2a1c530bd65b Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Thu, 26 Feb 2026 18:36:32 +0200 Subject: [PATCH 0563/1518] arm64: dts: imx8mp-hummingboard-pulse: fix mini-hdmi dsi port reference [ Upstream commit 1d1d14d4253e6f373c247e67f3716768910be81e ] imx8mp.dtsi includes a default port@1 node with an empty placeholder endpoint intended for linking to a dsi bridge or panel. HummingBoard Pulse mini-hdmi dtsi described a new endpoint node with a different label attached. This duplicate label causes confusion and is suspected to also cause errors during dsi_attach. Remove the duplicate node and link to the one defined in soc dtsi. Further remove the unnecessary attach-bridge property. Fixes: 2a222aa2bee9 ("arm64: dts: add description for solidrun imx8mp hummingboard variants") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- .../imx8mp-hummingboard-pulse-mini-hdmi.dtsi | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-hummingboard-pulse-mini-hdmi.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-hummingboard-pulse-mini-hdmi.dtsi index 46916ddc05335..0e5f4607c7c1b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-hummingboard-pulse-mini-hdmi.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-hummingboard-pulse-mini-hdmi.dtsi @@ -41,7 +41,7 @@ reg = <0>; adv7535_from_dsim: endpoint { - remote-endpoint = <&dsim_to_adv7535>; + remote-endpoint = <&mipi_dsi_out>; }; }; @@ -71,11 +71,8 @@ &mipi_dsi { samsung,esc-clock-frequency = <10000000>; status = "okay"; +}; - port@1 { - dsim_to_adv7535: endpoint { - remote-endpoint = <&adv7535_from_dsim>; - attach-bridge; - }; - }; +&mipi_dsi_out { + remote-endpoint = <&adv7535_from_dsim>; }; From 151c29b6952ccd7f267b4b181b52168b736aa66e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Fri, 16 Jan 2026 08:07:37 +0100 Subject: [PATCH 0564/1518] arm64: dts: qcom: msm8953-xiaomi-vince: correct wled ovp value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9e87f0eaadccc3fecdf3c3c0334e05694804b5f5 ] PMI8950 doesn't actually support setting an OVP threshold value of 29.6 V. The closest allowed value is 29.5 V. Set that instead. Fixes: aa17e707e04a ("arm64: dts: qcom: msm8953: Add device tree for Xiaomi Redmi 5 Plus") Reviewed-by: Konrad Dybcio Signed-off-by: Barnabás Czémán Link: https://lore.kernel.org/r/20260116-pmi8950-wled-v3-5-e6c93de84079@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts index d46325e799176..c2a290bf493c1 100644 --- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts +++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts @@ -169,7 +169,7 @@ &pmi8950_wled { qcom,current-limit-microamp = <20000>; - qcom,ovp-millivolt = <29600>; + qcom,ovp-millivolt = <29500>; qcom,num-strings = <2>; qcom,external-pfet; qcom,cabc; From 2fda9b3776e04903929fa37d918050df5f13e5a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Fri, 16 Jan 2026 08:07:39 +0100 Subject: [PATCH 0565/1518] arm64: dts: qcom: msm8953-xiaomi-daisy: fix backlight MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7131f6d909a6546329b71f2bacfdc60cb3e6020e ] The backlight on this device is connected via 3 strings. Currently, the DT claims only two are present, which results in visible stripes on the display (since every third backlight string remains unconfigured). Fix the number of strings to avoid that. Fixes: 38d779c26395 ("arm64: dts: qcom: msm8953: Add device tree for Xiaomi Mi A2 Lite") Signed-off-by: Barnabás Czémán Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260116-pmi8950-wled-v3-7-e6c93de84079@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8953-xiaomi-daisy.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-daisy.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-daisy.dts index ddd7af6167942..59f873a06e4dd 100644 --- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-daisy.dts +++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-daisy.dts @@ -157,7 +157,7 @@ &pmi8950_wled { qcom,current-limit-microamp = <20000>; - qcom,num-strings = <2>; + qcom,num-strings = <3>; status = "okay"; }; From 31d145a54f169317fd08b0b60107e73113544d74 Mon Sep 17 00:00:00 2001 From: Ming Wang Date: Fri, 6 Feb 2026 17:04:53 +0800 Subject: [PATCH 0566/1518] arm64: dts: rockchip: Fix Bluetooth stability on LCKFB TaiShan Pi [ Upstream commit 861a9593e10bb6ab2a492b315c8a2a3aad70ac00 ] The AP6212 WiFi/BT module on the LCKFB TaiShan Pi (RK3566) is prone to communication timeouts and reset failures (error -110) when operating at 3 Mbps. This patch stabilizes the Bluetooth interface by: 1. Updating the compatible string to 'brcm,bcm43430a1-bt' to better reflect the actual chip revision used in the AP6212 module. 2. Lowering the maximum UART baud rate from 3,000,000 to 1,500,000 bps. Tests show that 1.5 Mbps is the reliable upper limit for this board's UART configuration, eliminating the initialization timeouts. Fixes: 251e5ade9ba4 ("arm64: dts: rockchip: add dts for LCKFB Taishan Pi RK3566") Signed-off-by: Ming Wang Link: https://patch.msgid.link/20260206090453.1041919-1-wming126@126.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3566-lckfb-tspi.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lckfb-tspi.dts b/arch/arm64/boot/dts/rockchip/rk3566-lckfb-tspi.dts index ed65d31204446..18a560a6e2a4a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-lckfb-tspi.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-lckfb-tspi.dts @@ -635,10 +635,10 @@ status = "okay"; bluetooth: bluetooth { - compatible = "brcm,bcm43438-bt"; + compatible = "brcm,bcm43430a1-bt"; clocks = <&rk809 1>; clock-names = "lpo"; - max-speed = <3000000>; + max-speed = <1500000>; pinctrl-names = "default"; pinctrl-0 = <&bt_host_wake_l &bt_wake_l &bt_enable_h>; shutdown-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>; From 6db6534abfe13d1192e9b507adecbda98f43136b Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 26 Jan 2026 12:32:04 +0000 Subject: [PATCH 0567/1518] Revert "arm64: dts: rockchip: add SPDIF audio to Beelink A1" [ Upstream commit 03978cb18059ecd27e3d955508b18cf2a1196142 ] This reverts commit bdc4d388c6452498ab62ef2564589f40e0c8c262. While Beelink A1 mostly follows the high-end RK3328 reference design, it does not in fact have the S/PDIF connector, only HDMI and a 3.5mm jack for the analog audio/TV codecs - the tiny form factor literally doesn't have room to fit more! Cc: Christian Hewitt Cc: Alex Bee Fixes: bdc4d388c645 ("arm64: dts: rockchip: add SPDIF audio to Beelink A1") Signed-off-by: Robin Murphy Link: https://patch.msgid.link/0af77a02c2b0806d4ca72066392a5453fcc89a8f.1767111968.git.robin.murphy@arm.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3328-a1.dts | 23 ---------------------- 1 file changed, 23 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts index 30bdb38f0727a..e810ed146451c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-a1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-a1.dts @@ -58,24 +58,6 @@ gpios = <&gpio2 RK_PA2 GPIO_ACTIVE_LOW>; linux,rc-map-name = "rc-beelink-gs1"; }; - - spdif_dit: spdif-dit { - compatible = "linux,spdif-dit"; - #sound-dai-cells = <0>; - }; - - spdif_sound: spdif-sound { - compatible = "simple-audio-card"; - simple-audio-card,name = "SPDIF"; - - simple-audio-card,cpu { - sound-dai = <&spdif>; - }; - - simple-audio-card,codec { - sound-dai = <&spdif_dit>; - }; - }; }; &analog_sound { @@ -343,11 +325,6 @@ status = "okay"; }; -&spdif { - pinctrl-0 = <&spdifm0_tx>; - status = "okay"; -}; - &tsadc { rockchip,hw-tshut-mode = <0>; rockchip,hw-tshut-polarity = <0>; From fd16a9e05b48056661c824a9c6963d5d46bd28d9 Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Tue, 10 Mar 2026 08:46:48 -0500 Subject: [PATCH 0568/1518] arm64: dts: rockchip: Correct Fan Supply for Gameforce Ace [ Upstream commit c7079215b7dbf88b84a95ff13982bf3dab3cfbe1 ] Correct the regulator providing power to the PWM controlled fan. Without this fix the fan only runs when the audio path is playing audio (because the speaker amplifier and PWM fan share the same regulator). Fixes: 4e946c447a04 ("arm64: dts: rockchip: Add GameForce Ace") Signed-off-by: Chris Morgan Link: https://patch.msgid.link/20260310134648.550006-1-macroalpha82@gmail.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts b/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts index f5894672fcbd3..ef8805219ea16 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts @@ -304,7 +304,7 @@ compatible = "pwm-fan"; #cooling-cells = <2>; cooling-levels = <0 120 150 180 210 240 255>; - fan-supply = <&vcc5v0_sys>; + fan-supply = <&vcc5v0_spk>; interrupt-parent = <&gpio4>; interrupts = ; pulses-per-revolution = <4>; From 99eb1df4acd43eaa64b53500b6785eb05be08109 Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Tue, 10 Mar 2026 08:49:19 -0500 Subject: [PATCH 0569/1518] arm64: dts: rockchip: Correct Joystick Axes on Gameforce Ace [ Upstream commit c337c1b561c1c3016d30776d7dc2032ea4979334 ] The Gameforce Ace's joystick axes were set incorrectly initially, getting the X/Y and RX/RY axes backwards. Additionally, correct the RY axis so that it is inverted. All axes tested with evtest and outputting correct values. Fixes: 4e946c447a04 ("arm64: dts: rockchip: Add GameForce Ace") Reported-by: sydarn Signed-off-by: Chris Morgan Link: https://patch.msgid.link/20260310134919.550023-1-macroalpha82@gmail.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts b/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts index ef8805219ea16..afac54ba58318 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts @@ -60,8 +60,8 @@ reg = <0>; abs-flat = <40>; abs-fuzz = <30>; - abs-range = <0 4095>; - linux,code = ; + abs-range = <4095 0>; + linux,code = ; }; axis@1 { @@ -69,7 +69,7 @@ abs-flat = <40>; abs-fuzz = <30>; abs-range = <0 4095>; - linux,code = ; + linux,code = ; }; axis@2 { @@ -77,7 +77,7 @@ abs-flat = <40>; abs-fuzz = <30>; abs-range = <0 4095>; - linux,code = ; + linux,code = ; }; axis@3 { @@ -85,7 +85,7 @@ abs-flat = <40>; abs-fuzz = <30>; abs-range = <0 4095>; - linux,code = ; + linux,code = ; }; }; From 702ee8e9821b45206d9d79ab3913476b75651afd Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 23 Mar 2026 03:20:57 +0200 Subject: [PATCH 0570/1518] soc: qcom: ocmem: make the core clock optional [ Upstream commit e8a61c51417c679d1a599fb36695e9d3b8d95514 ] OCMEM's core clock (aka RPM bus 2 clock) is being handled internally by the interconnect driver. Corresponding clock has been dropped from the SMD RPM clock driver. The users of the ocmem will vote on the ocmemnoc interconnect paths, making sure that ocmem is on. Make the clock optional, keeping it for compatibility with older DT. Fixes: d6edc31f3a68 ("clk: qcom: smd-rpm: Separate out interconnect bus clocks") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260323-ocmem-v1-1-ad9bcae44763@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/ocmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index 71130a2f62e9e..7bcd0c71d7f64 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -308,7 +308,7 @@ static int ocmem_dev_probe(struct platform_device *pdev) ocmem->dev = dev; ocmem->config = device_get_match_data(dev); - ocmem->core_clk = devm_clk_get(dev, "core"); + ocmem->core_clk = devm_clk_get_optional(dev, "core"); if (IS_ERR(ocmem->core_clk)) return dev_err_probe(dev, PTR_ERR(ocmem->core_clk), "Unable to get core clock\n"); From c10e14863b626abafa3dee6ddece297b54e8b84f Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 23 Mar 2026 03:20:58 +0200 Subject: [PATCH 0571/1518] soc: qcom: ocmem: register reasons for probe deferrals [ Upstream commit 9dfd69cd89cd6afa4723be9098979abeef3bb8c6 ] Instead of printing messages to the dmesg, let the message be recorded as a reason for the OCMEM client deferral. Fixes: 88c1e9404f1d ("soc: qcom: add OCMEM driver") Signed-off-by: Dmitry Baryshkov Reviewed-by: Brian Masney Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260323-ocmem-v1-2-ad9bcae44763@oss.qualcomm.com [bjorn: s/ERR_PTR(dev_err_probe)/dev_err_ptr_probe/ Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/ocmem.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index 7bcd0c71d7f64..ed77fdc76c9b2 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -196,10 +196,10 @@ struct ocmem *of_get_ocmem(struct device *dev) } pdev = of_find_device_by_node(devnode->parent); - if (!pdev) { - dev_err(dev, "Cannot find device node %s\n", devnode->name); - return ERR_PTR(-EPROBE_DEFER); - } + if (!pdev) + return dev_err_ptr_probe(dev, -EPROBE_DEFER, + "Cannot find device node %s\n", + devnode->name); ocmem = platform_get_drvdata(pdev); put_device(&pdev->dev); From 2fea83507b4cea111f620b0f243a9956dad77682 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 23 Mar 2026 03:20:59 +0200 Subject: [PATCH 0572/1518] soc: qcom: ocmem: return -EPROBE_DEFER is ocmem is not available [ Upstream commit 91b59009c7d48b58dbc50fecb27f2ad20749a05a ] If OCMEM is declared in DT, it is expected that it is present and handled by the driver. The GPU driver will ignore -ENODEV error, which typically means that OCMEM isn't defined in DT. Let ocmem return -EPROBE_DEFER if it supposed to be used, but it is not probed (yet). Fixes: 88c1e9404f1d ("soc: qcom: add OCMEM driver") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260323-ocmem-v1-3-ad9bcae44763@oss.qualcomm.com [bjorn: s/ERR_PTR(dev_err_probe)/dev_err_ptr_probe/ Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/ocmem.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index ed77fdc76c9b2..37ea6b86aebcb 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -203,10 +203,9 @@ struct ocmem *of_get_ocmem(struct device *dev) ocmem = platform_get_drvdata(pdev); put_device(&pdev->dev); - if (!ocmem) { - dev_err(dev, "Cannot get ocmem\n"); - return ERR_PTR(-ENODEV); - } + if (!ocmem) + return dev_err_ptr_probe(dev, -EPROBE_DEFER, "Cannot get ocmem\n"); + return ocmem; } EXPORT_SYMBOL_GPL(of_get_ocmem); From 835d16955dd75e5d742f3f4e8e8145ac455cbd5a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=B0=A2=E8=87=B4=E9=82=A6=20=28XIE=20Zhibang=29?= Date: Thu, 19 Mar 2026 13:55:00 +0000 Subject: [PATCH 0573/1518] arm64: dts: rockchip: Fix RK3562 EVB2 model name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ede6a05606892bab4f6d785ffcfc124150c2eb32 ] The model name should be "Rockchip RK3562 EVB2 V10 Board". Fixes: ceb6ef1ea900 ("arm64: dts: rockchip: Add RK3562 evb2 devicetree") Signed-off-by: 谢致邦 (XIE Zhibang) Link: https://patch.msgid.link/tencent_78E7E3F6991FB4403D5ADC9E6A6BC3BF8307@qq.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3562-evb2-v10.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3562-evb2-v10.dts b/arch/arm64/boot/dts/rockchip/rk3562-evb2-v10.dts index 6a84db154a7d5..387062eea5208 100644 --- a/arch/arm64/boot/dts/rockchip/rk3562-evb2-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3562-evb2-v10.dts @@ -13,7 +13,7 @@ #include "rk3562.dtsi" / { - model = "Rockchip RK3562 EVB V20 Board"; + model = "Rockchip RK3562 EVB2 V10 Board"; compatible = "rockchip,rk3562-evb2-v10", "rockchip,rk3562"; chosen: chosen { From 8bfa413a1bd8b05101151b14614abbab94529250 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Thu, 12 Mar 2026 09:11:53 +0800 Subject: [PATCH 0574/1518] arm64: dts: rockchip: Add mphy reset to ufshc node [ Upstream commit 792c42da47fa199f90492784e3c57280acd57f22 ] The mphy reset signal is used to reset the physical adapter. Resetting other components while leaving the mphy unreset may occasionally prevent the UFS controller from successfully linking up with the device. This addresses an intermittent hardware bug where the UFS link fails to establish under specific timing conditions with certain chips. While difficult to reproduce initially, this issue was consistently observed in downstream testing and requires explicit mphy reset control for full stability. Fixes: c75e5e010fef ("scsi: arm64: dts: rockchip: Add UFS support for RK3576 SoC") Signed-off-by: Shawn Lin Link: https://patch.msgid.link/1773277913-29580-1-git-send-email-shawn.lin@rock-chips.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3576.dtsi | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index 70e67d4dccb8a..5d69a81aecc64 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -1829,8 +1829,9 @@ pinctrl-0 = <&ufs_refclk &ufs_rstgpio>; pinctrl-names = "default"; resets = <&cru SRST_A_UFS_BIU>, <&cru SRST_A_UFS_SYS>, - <&cru SRST_A_UFS>, <&cru SRST_P_UFS_GRF>; - reset-names = "biu", "sys", "ufs", "grf"; + <&cru SRST_A_UFS>, <&cru SRST_P_UFS_GRF>, + <&cru SRST_MPHY_INIT>; + reset-names = "biu", "sys", "ufs", "grf", "mphy"; reset-gpios = <&gpio4 RK_PD0 GPIO_ACTIVE_LOW>; status = "disabled"; }; From 8344cd62b825cb656699a89a0c826faff4b7ed39 Mon Sep 17 00:00:00 2001 From: Gatien Chevallier Date: Thu, 29 Jan 2026 13:56:17 +0100 Subject: [PATCH 0575/1518] bus: rifsc: fix RIF configuration check for peripherals [ Upstream commit d5ce3b4e951bc41a6ce877c8500bb4fe42146669 ] Peripheral holding CID0 cannot be accessed, remove this completely incorrect check. While there, fix and simplify the semaphore checking that should be performed when the CID filtering is enabled. Fixes: a18208457253 ("bus: rifsc: introduce RIFSC firewall controller driver") Signed-off-by: Gatien Chevallier Link: https://lore.kernel.org/r/20260129-fix_cid_check_rifsc-v1-1-ef280ccf764d@foss.st.com Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- drivers/bus/stm32_rifsc.c | 52 ++++++++++++++------------------------- 1 file changed, 18 insertions(+), 34 deletions(-) diff --git a/drivers/bus/stm32_rifsc.c b/drivers/bus/stm32_rifsc.c index 4cf1b60014b77..59872134c3224 100644 --- a/drivers/bus/stm32_rifsc.c +++ b/drivers/bus/stm32_rifsc.c @@ -126,34 +126,6 @@ static int stm32_rifsc_grant_access(struct stm32_firewall_controller *ctrl, u32 sec_reg_value = readl(rifsc_controller->mmio + RIFSC_RISC_SECCFGR0 + 0x4 * reg_id); cid_reg_value = readl(rifsc_controller->mmio + RIFSC_RISC_PER0_CIDCFGR + 0x8 * firewall_id); - /* First check conditions for semaphore mode, which doesn't take into account static CID. */ - if ((cid_reg_value & CIDCFGR_SEMEN) && (cid_reg_value & CIDCFGR_CFEN)) { - if (cid_reg_value & BIT(RIF_CID1 + SEMWL_SHIFT)) { - /* Static CID is irrelevant if semaphore mode */ - goto skip_cid_check; - } else { - dev_dbg(rifsc_controller->dev, - "Invalid bus semaphore configuration: index %d\n", firewall_id); - return -EACCES; - } - } - - /* - * Skip CID check if CID filtering isn't enabled or filtering is enabled on CID0, which - * corresponds to whatever CID. - */ - if (!(cid_reg_value & CIDCFGR_CFEN) || - FIELD_GET(RIFSC_RISC_SCID_MASK, cid_reg_value) == RIF_CID0) - goto skip_cid_check; - - /* Coherency check with the CID configuration */ - if (FIELD_GET(RIFSC_RISC_SCID_MASK, cid_reg_value) != RIF_CID1) { - dev_dbg(rifsc_controller->dev, "Invalid CID configuration for peripheral: %d\n", - firewall_id); - return -EACCES; - } - -skip_cid_check: /* Check security configuration */ if (sec_reg_value & BIT(reg_offset)) { dev_dbg(rifsc_controller->dev, @@ -161,19 +133,31 @@ static int stm32_rifsc_grant_access(struct stm32_firewall_controller *ctrl, u32 return -EACCES; } - /* - * If the peripheral is in semaphore mode, take the semaphore so that - * the CID1 has the ownership. - */ - if ((cid_reg_value & CIDCFGR_SEMEN) && (cid_reg_value & CIDCFGR_CFEN)) { + /* Skip CID check if CID filtering isn't enabled */ + if (!(cid_reg_value & CIDCFGR_CFEN)) + goto skip_cid_check; + + /* First check conditions for semaphore mode, which doesn't take into account static CID. */ + if (cid_reg_value & CIDCFGR_SEMEN) { + if (!(cid_reg_value & BIT(RIF_CID1 + SEMWL_SHIFT))) { + dev_dbg(rifsc_controller->dev, + "Invalid bus semaphore configuration: index %d\n", firewall_id); + return -EACCES; + } + rc = stm32_rif_acquire_semaphore(rifsc_controller, firewall_id); if (rc) { - dev_err(rifsc_controller->dev, + dev_dbg(rifsc_controller->dev, "Couldn't acquire semaphore for peripheral: %d\n", firewall_id); return rc; } + } else if (FIELD_GET(RIFSC_RISC_SCID_MASK, cid_reg_value) != RIF_CID1) { + dev_dbg(rifsc_controller->dev, "Invalid CID configuration for peripheral: %d\n", + firewall_id); + return -EACCES; } +skip_cid_check: return 0; } From c0040375fec7fbb6860c0b050c650fa8bc68e1cf Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 13 Mar 2026 17:27:08 +0200 Subject: [PATCH 0576/1518] arm64: dts: qcom: hamoa: correct Iris corners for the MXC rail [ Upstream commit baac8b5e43f42b632b912a6a837d94fd5bca48f2 ] The corners of the MVS0 / MVS0C clocks on the MMCX rail don't always match the PLL corners on the MXC rail. Correct the performance corners for the MXC rail following the PLL documentation. Fixes: 9065340ac04d ("arm64: dts: qcom: x1e80100: Add IRIS video codec") Signed-off-by: Dmitry Baryshkov Reviewed-by: Dikshita Agarwal Link: https://lore.kernel.org/r/20260313-iris-fix-corners-v1-1-32a393c25dda@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/x1e80100.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index efe8d5e7079fe..66c31c1799421 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -5297,19 +5297,19 @@ opp-366000000 { opp-hz = /bits/ 64 <366000000>; - required-opps = <&rpmhpd_opp_svs_l1>, + required-opps = <&rpmhpd_opp_svs>, <&rpmhpd_opp_svs_l1>; }; opp-444000000 { opp-hz = /bits/ 64 <444000000>; - required-opps = <&rpmhpd_opp_nom>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_nom>; }; opp-481000000 { opp-hz = /bits/ 64 <481000000>; - required-opps = <&rpmhpd_opp_turbo>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_turbo>; }; }; From e589b6c38265c3bf8edcfc5854bb42ef251dd8a3 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 13 Mar 2026 17:27:09 +0200 Subject: [PATCH 0577/1518] arm64: dts: qcom: lemans: correct Iris corners for the MXC rail [ Upstream commit 85a6cf5ef8cf6e6de948fbba56101fa05049417f ] The corners of the MVS0 / MVS0C clocks on the MMCX rail don't always match the PLL corners on the MXC rail. Correct the performance corners for the MXC rail following the PLL documentation. Fixes: 7bc95052c64f ("arm64: dts: qcom: sa8775p: add support for video node") Signed-off-by: Dmitry Baryshkov Reviewed-by: Dikshita Agarwal Link: https://lore.kernel.org/r/20260313-iris-fix-corners-v1-2-32a393c25dda@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/lemans.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/lemans.dtsi b/arch/arm64/boot/dts/qcom/lemans.dtsi index 530dc1e832b70..ef20ea941aa91 100644 --- a/arch/arm64/boot/dts/qcom/lemans.dtsi +++ b/arch/arm64/boot/dts/qcom/lemans.dtsi @@ -4363,19 +4363,19 @@ opp-444000000 { opp-hz = /bits/ 64 <444000000>; - required-opps = <&rpmhpd_opp_nom>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_nom>; }; opp-533000000 { opp-hz = /bits/ 64 <533000000>; - required-opps = <&rpmhpd_opp_turbo>, + required-opps = <&rpmhpd_opp_nom>, <&rpmhpd_opp_turbo>; }; opp-560000000 { opp-hz = /bits/ 64 <560000000>; - required-opps = <&rpmhpd_opp_turbo_l1>, + required-opps = <&rpmhpd_opp_nom>, <&rpmhpd_opp_turbo_l1>; }; }; From 14ec98366e303ffb998ff552d6bfb22672becd65 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 13 Mar 2026 17:27:10 +0200 Subject: [PATCH 0578/1518] arm64: dts: qcom: monaco: correct Iris corners for the MXC rail [ Upstream commit bba8d9ba7df8f6592552377049fc84958fd0575a ] The corners of the MVS0 / MVS0C clocks on the MMCX rail don't always match the PLL corners on the MXC rail. Correct the performance corners for the MXC rail following the PLL documentation. Fixes: bf6ec39c3f36 ("arm64: dts: qcom: qcs8300: add video node") Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260313-iris-fix-corners-v1-3-32a393c25dda@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/qcs8300.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/qcs8300.dtsi b/arch/arm64/boot/dts/qcom/qcs8300.dtsi index 7a4c3e872d8ee..8580884a16e98 100644 --- a/arch/arm64/boot/dts/qcom/qcs8300.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs8300.dtsi @@ -4743,19 +4743,19 @@ opp-444000000 { opp-hz = /bits/ 64 <444000000>; - required-opps = <&rpmhpd_opp_nom>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_nom>; }; opp-533000000 { opp-hz = /bits/ 64 <533000000>; - required-opps = <&rpmhpd_opp_turbo>, + required-opps = <&rpmhpd_opp_nom>, <&rpmhpd_opp_turbo>; }; opp-560000000 { opp-hz = /bits/ 64 <560000000>; - required-opps = <&rpmhpd_opp_turbo_l1>, + required-opps = <&rpmhpd_opp_nom>, <&rpmhpd_opp_turbo_l1>; }; }; From 16771dd53aa9365349ec1cdb9ff657e58348a082 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 13 Mar 2026 17:27:11 +0200 Subject: [PATCH 0579/1518] arm64: dts: qcom: sm8550: correct Iris corners for the MXC rail [ Upstream commit ff8edb5bc8bdf8bdf4573d8dc062b09cc1e6bc76 ] The corners of the MVS0 / MVS0C clocks on the MMCX rail don't always match the PLL corners on the MXC rail. Correct the performance corners for the MXC rail following the PLL documentation. Fixes: 41661853ae8e ("arm64: dts: qcom: sm8550: add iris DT node") Signed-off-by: Dmitry Baryshkov Reviewed-by: Dikshita Agarwal Link: https://lore.kernel.org/r/20260313-iris-fix-corners-v1-4-32a393c25dda@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8550.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index e294dc9c68c9a..63e17c3014061 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -3284,19 +3284,19 @@ opp-366000000 { opp-hz = /bits/ 64 <366000000>; - required-opps = <&rpmhpd_opp_svs_l1>, + required-opps = <&rpmhpd_opp_svs>, <&rpmhpd_opp_svs_l1>; }; opp-444000000 { opp-hz = /bits/ 64 <444000000>; - required-opps = <&rpmhpd_opp_nom>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_nom>; }; opp-533333334 { opp-hz = /bits/ 64 <533333334>; - required-opps = <&rpmhpd_opp_turbo>, + required-opps = <&rpmhpd_opp_nom>, <&rpmhpd_opp_turbo>; }; }; From 3bb7be86f4c0b54d1d0d135d7baa61f6f03b7407 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 13 Mar 2026 17:27:12 +0200 Subject: [PATCH 0580/1518] arm64: dts: qcom: sm8650: correct Iris corners for the MXC rail [ Upstream commit 7c302a2a6c1a4644e798ecfc4e72ddc4acec653f ] The corners of the MVS0 / MVS0C clocks on the MMCX rail don't always match the PLL corners on the MXC rail. Correct the performance corners for the MXC rail following the PLL documentation. Fixes: 56cf5ad39a55 ("arm64: dts: qcom: sm8650: add iris DT node") Signed-off-by: Dmitry Baryshkov Reviewed-by: Dikshita Agarwal Link: https://lore.kernel.org/r/20260313-iris-fix-corners-v1-5-32a393c25dda@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8650.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index d22a26a416ccc..4e34c686265d6 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -5201,13 +5201,13 @@ opp-300000000 { opp-hz = /bits/ 64 <300000000>; - required-opps = <&rpmhpd_opp_low_svs>, + required-opps = <&rpmhpd_opp_svs>, <&rpmhpd_opp_low_svs>; }; opp-380000000 { opp-hz = /bits/ 64 <380000000>; - required-opps = <&rpmhpd_opp_svs>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_svs>; }; @@ -5219,13 +5219,13 @@ opp-480000000 { opp-hz = /bits/ 64 <480000000>; - required-opps = <&rpmhpd_opp_nom>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_nom>; }; opp-533333334 { opp-hz = /bits/ 64 <533333334>; - required-opps = <&rpmhpd_opp_turbo>, + required-opps = <&rpmhpd_opp_svs_l1>, <&rpmhpd_opp_turbo>; }; }; From 1de0b109aaa7ed3e6e461fc36f26ca1fa82d1f03 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 17 Mar 2026 15:41:16 +0100 Subject: [PATCH 0581/1518] arm64: dts: qcom: sm8450: Fix GIC_ITS range length [ Upstream commit 14044fa192c50265bc1f636108371044bbdcf7b7 ] Currently, the GITS_SGIR register is cut off. Fix it up. Fixes: fc8b0b9b630d ("arm64: dts: qcom: sm8450 add ITS device tree node") Signed-off-by: Konrad Dybcio Reviewed-by: Neil Armstrong Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20260317-topic-its_range_fixup-v1-3-49be8076adb1@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8450.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 23420e6924728..68f5e7bca7cde 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -5079,7 +5079,7 @@ gic_its: msi-controller@17140000 { compatible = "arm,gic-v3-its"; - reg = <0x0 0x17140000 0x0 0x20000>; + reg = <0x0 0x17140000 0x0 0x40000>; msi-controller; #msi-cells = <1>; }; From 6670dc96864b4b671d0ae8dd3e3f3f70c5bd7947 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 17 Mar 2026 15:41:17 +0100 Subject: [PATCH 0582/1518] arm64: dts: qcom: sm8550: Fix GIC_ITS range length [ Upstream commit 357c559e386705609b6b9dc0544c420e3f91f3a0 ] Currently, the GITS_SGIR register is cut off. Fix it up. Fixes: ffc50b2d3828 ("arm64: dts: qcom: Add base SM8550 dtsi") Signed-off-by: Konrad Dybcio Reviewed-by: Neil Armstrong Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20260317-topic-its_range_fixup-v1-4-49be8076adb1@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8550.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 63e17c3014061..c9a781273e842 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -5094,7 +5094,7 @@ gic_its: msi-controller@17140000 { compatible = "arm,gic-v3-its"; - reg = <0 0x17140000 0 0x20000>; + reg = <0 0x17140000 0 0x40000>; msi-controller; #msi-cells = <1>; }; From 000d5533f451238788f8dca100c9971adc07592b Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 17 Mar 2026 15:41:18 +0100 Subject: [PATCH 0583/1518] arm64: dts: qcom: sm8650: Fix GIC_ITS range length [ Upstream commit 6c8e2ca1263d0da5976418ed285eaec430e8d87f ] Currently, the GITS_SGIR register is cut off. Fix it up. Fixes: d2350377997f ("arm64: dts: qcom: add initial SM8650 dtsi") Signed-off-by: Konrad Dybcio Reviewed-by: Neil Armstrong Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20260317-topic-its_range_fixup-v1-5-49be8076adb1@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8650.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 4e34c686265d6..0faaf54e597ea 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -6885,7 +6885,7 @@ gic_its: msi-controller@17140000 { compatible = "arm,gic-v3-its"; - reg = <0 0x17140000 0 0x20000>; + reg = <0 0x17140000 0 0x40000>; msi-controller; #msi-cells = <1>; From c1b5e85c88fbf8786803a1458719baac0036a1db Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 17 Mar 2026 15:41:19 +0100 Subject: [PATCH 0584/1518] arm64: dts: qcom: sm8750: Fix GIC_ITS range length [ Upstream commit c2f1f8874fda674af1efaa9a90efbdea8b6834ff ] Currently, the GITS_SGIR register is cut off. Fix it up. Fixes: 068c3d3c83be ("arm64: dts: qcom: Add base SM8750 dtsi") Signed-off-by: Konrad Dybcio Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20260317-topic-its_range_fixup-v1-6-49be8076adb1@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8750.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8750.dtsi b/arch/arm64/boot/dts/qcom/sm8750.dtsi index 33963fee1f699..3e1d1133792bb 100644 --- a/arch/arm64/boot/dts/qcom/sm8750.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8750.dtsi @@ -3299,7 +3299,7 @@ gic_its: msi-controller@16040000 { compatible = "arm,gic-v3-its"; - reg = <0x0 0x16040000 0x0 0x20000>; + reg = <0x0 0x16040000 0x0 0x40000>; msi-controller; #msi-cells = <1>; From cd2894362390e44b397a8ce7565c3989ea5a1729 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 14 Mar 2026 04:37:10 +0200 Subject: [PATCH 0585/1518] arm64: dts: qcom: sm8550: Fix xo clock supply of platform SD host controller [ Upstream commit 30ac651c69bddbc83cab6d52fc5d2e03bed83282 ] The expected frequency of SD host controller core supply clock is 19.2MHz, while RPMH_CXO_CLK clock frequency on SM8650 platform is 38.4MHz. Apparently the overclocked supply clock could be good enough on some boards and even with the most of SD cards, however some low-end UHS-I SD cards in SDR104 mode of the host controller produce I/O errors in runtime, fortunately this problem is gone, if the "xo" clock frequency matches the expected 19.2MHz clock rate. Fixes: ffc50b2d3828 ("arm64: dts: qcom: Add base SM8550 dtsi") Signed-off-by: Vladimir Zapolskiy Reviewed-by: Konrad Dybcio Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20260314023715.357512-2-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8550.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index c9a781273e842..002ed12f942c0 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -3175,7 +3175,7 @@ clocks = <&gcc GCC_SDCC2_AHB_CLK>, <&gcc GCC_SDCC2_APPS_CLK>, - <&rpmhcc RPMH_CXO_CLK>; + <&bi_tcxo_div2>; clock-names = "iface", "core", "xo"; iommus = <&apps_smmu 0x540 0>; qcom,dll-config = <0x0007642c>; From 168ec540bdfd844c8758ebc1c9ba6e53ca99fc12 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 14 Mar 2026 04:37:11 +0200 Subject: [PATCH 0586/1518] arm64: dts: qcom: sm8650: Fix xo clock supply of SD host controller [ Upstream commit 390903efaa057c44fd80e7d9839419c50092018e ] The expected frequency of SD host controller core supply clock is 19.2MHz, while RPMH_CXO_CLK clock frequency on SM8650 platform is 38.4MHz. Apparently the overclocked supply clock could be good enough on some boards and even with the most of SD cards, however some low-end UHS-I SD cards in SDR104 mode of the host controller produce I/O errors in runtime, fortunately this problem is gone, if the "xo" clock frequency matches the expected 19.2MHz clock rate. Fixes: 10e024671295 ("arm64: dts: qcom: sm8650: add interconnect dependent device nodes") Signed-off-by: Vladimir Zapolskiy Reviewed-by: Konrad Dybcio Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20260314023715.357512-3-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8650.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 0faaf54e597ea..d157cbc493d92 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -4922,7 +4922,7 @@ clocks = <&gcc GCC_SDCC2_AHB_CLK>, <&gcc GCC_SDCC2_APPS_CLK>, - <&rpmhcc RPMH_CXO_CLK>; + <&bi_tcxo_div2>; clock-names = "iface", "core", "xo"; From 6360bcaf572712cf50398b8ca61ad8cacf234390 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 14 Mar 2026 04:37:12 +0200 Subject: [PATCH 0587/1518] arm64: dts: qcom: hamoa: Fix xo clock supply of platform SD host controller [ Upstream commit d094f79960e1da20c1380083c95945371baa3668 ] The expected frequency of SD host controller core supply clock is 19.2MHz, while RPMH_CXO_CLK clock frequency on SM8650 platform is 38.4MHz. Apparently the overclocked supply clock could be good enough on some boards and even with the most of SD cards, however some low-end UHS-I SD cards in SDR104 mode of the host controller produce I/O errors in runtime, fortunately this problem is gone, if the "xo" clock frequency matches the expected 19.2MHz clock rate. Fixes: ffb21c1e19b1 ("arm64: dts: qcom: x1e80100: Describe the SDHC controllers") Reported-by: Neil Armstrong Signed-off-by: Vladimir Zapolskiy Reviewed-by: Konrad Dybcio Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20260314023715.357512-4-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/x1e80100.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 66c31c1799421..ee9c12600f95a 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -4579,7 +4579,7 @@ clocks = <&gcc GCC_SDCC2_AHB_CLK>, <&gcc GCC_SDCC2_APPS_CLK>, - <&rpmhcc RPMH_CXO_CLK>; + <&bi_tcxo_div2>; clock-names = "iface", "core", "xo"; iommus = <&apps_smmu 0x520 0>; qcom,dll-config = <0x0007642c>; @@ -4632,7 +4632,7 @@ clocks = <&gcc GCC_SDCC4_AHB_CLK>, <&gcc GCC_SDCC4_APPS_CLK>, - <&rpmhcc RPMH_CXO_CLK>; + <&bi_tcxo_div2>; clock-names = "iface", "core", "xo"; iommus = <&apps_smmu 0x160 0>; qcom,dll-config = <0x0007642c>; From 2ea7bfce00245cb55378031b5fe2a149f83ddfb7 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 14 Mar 2026 04:37:13 +0200 Subject: [PATCH 0588/1518] arm64: dts: qcom: sm8450: Enable UHS-I SDR50 and SDR104 SD card modes [ Upstream commit db0c5ef1abda6effdc5c85d6688fb6af2b351ae5 ] The reported problem of some non-working UHS-I speed modes on SM8450 originates in commit 0a631a36f724 ("arm64: dts: qcom: Add device tree for Sony Xperia 1 IV"), and then it was spread to all SM8450 powered platforms by commit 9d561dc4e5cc ("arm64: dts: qcom: sm8450: disable SDHCI SDR104/SDR50 on all boards"). The tests show that the rootcause of the problem was related to an overclocking of SD cards, and it's fixed later on by commit a27ac3806b0a ("clk: qcom: gcc-sm8450: Use floor ops for SDCC RCGs"). Since then both SDR50 and SDR104 speed modes are working fine on SM8450, tested on SM8450-HDK: SDR50 speed mode: mmc0: new UHS-I speed SDR50 SDHC card at address 0001 mmcblk0: mmc0:0001 00000 14.6 GiB mmcblk0: p1 % dd if=/dev/mmcblk0p1 of=/dev/null bs=1M count=1024 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 24.6254 s, 43.6 MB/s SDR104 speed mode: mmc0: new UHS-I speed SDR104 SDHC card at address 59b4 mmcblk0: mmc0:59b4 USDU1 28.3 GiB mmcblk0: p1 % dd if=/dev/mmcblk0p1 of=/dev/null bs=1M count=1024 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 12.3266 s, 87.1 MB/s Remove the restrictions on SD card speed modes from the SM8450 platform dtsi file and enable UHS-I speed modes. Fixes: 9d561dc4e5cc ("arm64: dts: qcom: sm8450: disable SDHCI SDR104/SDR50 on all boards") Reviewed-by: Neil Armstrong Reviewed-by: Konrad Dybcio Signed-off-by: Vladimir Zapolskiy Link: https://lore.kernel.org/r/20260314023715.357512-5-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8450.dtsi | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 68f5e7bca7cde..6c00390010f1f 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -5404,9 +5404,6 @@ bus-width = <4>; dma-coherent; - /* Forbid SDR104/SDR50 - broken hw! */ - sdhci-caps-mask = <0x3 0x0>; - status = "disabled"; sdhc2_opp_table: opp-table { From 3578d41b7ef0609f76a7db84bb71b0b1ab6f7836 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 14 Mar 2026 04:37:14 +0200 Subject: [PATCH 0589/1518] arm64: dts: qcom: sm8550: Enable UHS-I SDR50 and SDR104 SD card modes [ Upstream commit 66b0f024fba0728ddce6916dce173bb1bdd4eab0 ] The restriction on UHS-I speed modes was added to all SM8550 platforms by copying it from SM8450 dtsi file, and due to the overclocking of SD cards it was an actually reproducible problem. Since the latter issue has been fixed, UHS-I speed modes are working fine on SM8550 boards, below is the test performed on SM8550-HDK: SDR50 speed mode: mmc0: new UHS-I speed SDR50 SDHC card at address 0001 mmcblk0: mmc0:0001 00000 14.6 GiB mmcblk0: p1 % dd if=/dev/mmcblk0p1 of=/dev/null bs=1M count=1024 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 23.5468 s, 45.6 MB/s SDR104 speed mode: mmc0: new UHS-I speed SDR104 SDHC card at address 59b4 mmcblk0: mmc0:59b4 USDU1 28.3 GiB mmcblk0: p1 % dd if=/dev/mmcblk0p1 of=/dev/null bs=1M count=1024 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 11.9819 s, 89.6 MB/s Unset the UHS-I speed mode restrictions from the SM8550 platform dtsi file, there is no indication that the SDHC controller is broken. Fixes: ffc50b2d3828 ("arm64: dts: qcom: Add base SM8550 dtsi") Reviewed-by: Neil Armstrong Signed-off-by: Vladimir Zapolskiy Link: https://lore.kernel.org/r/20260314023715.357512-6-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8550.dtsi | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 002ed12f942c0..118a626dfcff5 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -3191,9 +3191,6 @@ bus-width = <4>; dma-coherent; - /* Forbid SDR104/SDR50 - broken hw! */ - sdhci-caps-mask = <0x3 0>; - status = "disabled"; sdhc2_opp_table: opp-table { From 1327f28e4775375365966d683541f53d7d0226ee Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 14 Mar 2026 04:37:15 +0200 Subject: [PATCH 0590/1518] arm64: dts: qcom: sm8650: Enable UHS-I SDR50 and SDR104 SD card modes [ Upstream commit 93f823e7d48232e62fb8fb74481696609c90244a ] The restriction on UHS-I speed modes was added to all SM8650 platforms by copying it from SM8450 and SM8550 dtsi files, and it was an actually reproducible problem due to the overclocking of SD cards. Since the latter issue has been fixed in the SM8650 GCC driver, UHS-I speed modes are working fine on SM8650 boards, below is the test performed on SM8650-HDK: SDR50 speed mode: mmc0: new UHS-I speed SDR50 SDHC card at address 0001 mmcblk0: mmc0:0001 00000 14.6 GiB mmcblk0: p1 % dd if=/dev/mmcblk0p1 of=/dev/null bs=1M count=1024 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 24.8086 s, 43.3 MB/s SDR104 speed mode: mmc0: new UHS-I speed SDR104 SDHC card at address 59b4 mmcblk0: mmc0:59b4 USDU1 28.3 GiB mmcblk0: p1 % dd if=/dev/mmcblk0p1 of=/dev/null bs=1M count=1024 1024+0 records in 1024+0 records out 1073741824 bytes (1.1 GB, 1.0 GiB) copied, 12.9448 s, 82.9 MB/s Unset the UHS-I speed mode restrictions from the SM8550 platform dtsi file, there is no indication that the SDHC controller is broken. Fixes: 10e024671295 ("arm64: dts: qcom: sm8650: add interconnect dependent device nodes") Reviewed-by: Neil Armstrong Reviewed-by: Konrad Dybcio Signed-off-by: Vladimir Zapolskiy Link: https://lore.kernel.org/r/20260314023715.357512-7-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8650.dtsi | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index d157cbc493d92..069b7f1267a0e 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -4941,9 +4941,6 @@ bus-width = <4>; - /* Forbid SDR104/SDR50 - broken hw! */ - sdhci-caps-mask = <0x3 0>; - qcom,dll-config = <0x0007642c>; qcom,ddr-config = <0x80040868>; From 7f8365e8ff829bc963846ac09f3f85439d42284f Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Thu, 19 Mar 2026 09:55:00 +0100 Subject: [PATCH 0591/1518] arm64: dts: qcom: sm7225-fairphone-fp4: Fix conflicting bias pinctrl [ Upstream commit be7c1badb0b934cfe88427b1d4ec3eb9f52ba587 ] The pinctrl nodes from sm6350.dtsi already contain a bias-* property, so that needs to be deleted, otherwise the dtb will contain two conflicting bias-* properties. Reported-by: Conor Dooley Closes: https://lore.kernel.org/r/20260310-maritime-silly-05e7b7e03aa6@spud/ Fixes: c4ef464b24c5 ("arm64: dts: qcom: sm7225-fairphone-fp4: Add Bluetooth") Signed-off-by: Luca Weiss Reviewed-by: Konrad Dybcio Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20260319-fp4-uart1-fix-v1-1-f6b3fedef583@fairphone.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts b/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts index 4afbab570ca15..8cbe068645ea9 100644 --- a/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts +++ b/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts @@ -953,12 +953,14 @@ * the Bluetooth module drives the pin in either * direction or leaves the pin fully unpowered. */ + /delete-property/ bias-disable; bias-bus-hold; }; &qup_uart1_rts { /* We'll drive RTS, so no pull */ drive-strength = <2>; + /delete-property/ bias-pull-down; bias-disable; }; @@ -969,12 +971,14 @@ * in tri-state (module powered off or not driving the * signal yet). */ + /delete-property/ bias-disable; bias-pull-up; }; &qup_uart1_tx { /* We'll drive TX, so no pull */ drive-strength = <2>; + /delete-property/ bias-pull-up; bias-disable; }; From bf30d3790340248d876dc430c6c94fc30472292b Mon Sep 17 00:00:00 2001 From: David Heidelberg Date: Fri, 20 Mar 2026 18:33:11 +0100 Subject: [PATCH 0592/1518] arm64: dts: qcom: sdm845-xiaomi-beryllium: Mark l1a regulator as powered during boot [ Upstream commit 3b0dd81eea6b7a239fce456ce4545af76f1a9715 ] The regulator must be on, since it provides the display subsystem and therefore the bootloader had turned it on before Linux booted. Fixes: 77809cf74a8c ("arm64: dts: qcom: Add support for Xiaomi Poco F1 (Beryllium)") Signed-off-by: David Heidelberg Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260320-beryllium-booton-v2-1-931d1be21eae@ixit.cz Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi index 7480c8d7ac5b7..dbd5f08b5cdd3 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium-common.dtsi @@ -148,6 +148,7 @@ regulator-min-microvolt = <880000>; regulator-max-microvolt = <880000>; regulator-initial-mode = ; + regulator-boot-on; }; vreg_l5a_0p8: ldo5 { From 8caadf4fef50be0f93a1a4ceb798d2af3961822b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20Cz=C3=A9m=C3=A1n?= Date: Sun, 15 Mar 2026 17:26:19 +0100 Subject: [PATCH 0593/1518] arm64: dts: qcom: msm8917-xiaomi-riva: Fix board-id for all bootloader MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a49cd243503c528ea99e31a7853cf438ccc9032d ] Redmi 5A comes with multiple bootloader versions where the expected board-id is different. Change the board-id to unified form what works on both bootloader version. Fixes: 26633b582056 ("arm64: dts: qcom: Add Xiaomi Redmi 5A") Reviewed-by: Konrad Dybcio Signed-off-by: Barnabás Czémán Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260315-riva-common-v3-1-897f130786ed@mainlining.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts b/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts index 9db503e218886..1bfb16f90ddd5 100644 --- a/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts +++ b/arch/arm64/boot/dts/qcom/msm8917-xiaomi-riva.dts @@ -18,7 +18,7 @@ chassis-type = "handset"; qcom,msm-id = ; - qcom,board-id = <0x1000b 2>, <0x2000b 2>; + qcom,board-id = <0x1000b 1>, <0x1000b 2>; pwm_backlight: backlight { compatible = "pwm-backlight"; From 5f852e9baea0b1f85a312cad84ff4c96fea6d4d6 Mon Sep 17 00:00:00 2001 From: Judith Mendez Date: Mon, 23 Feb 2026 17:37:29 -0600 Subject: [PATCH 0594/1518] arm64: dts: ti: k3-am62p5-sk: Disable MMC1 internal pulls on data pins [ Upstream commit 6d4441be969bea89bb9702781f5dfb3a8f2a02a4 ] AM62P SK has external 10K pullups on MMC1 DAT1-DAT3 pins [0]. Disable internal pullups on DAT1-DAT3 so that each line has a single pullup source: - with both pullups enabled, the effective parallel resistance on DAT1-3 (~8.33K) drops below the 10K minimum pullup requirement for data lines (per SD Physical Layer Specification) - removing internal pullups makes DAT1-3 match DAT0 10K external pullup so its consistent and within spec - both internal and external pullups enabled equals unnecessary power consumption [0] https://www.ti.com/lit/zip/SPRR487 Fixes: c00504ea42c0 ("arm64: dts: ti: k3-am62p5-sk: Updates for SK EVM") Signed-off-by: Judith Mendez Reviewed-by: Moteen Shah Link: https://patch.msgid.link/20260223233731.2690472-2-jm@ti.com Signed-off-by: Vignesh Raghavendra Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/ti/k3-am62p5-sk.dts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts index a064a632680ec..f5054912ad910 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts @@ -271,9 +271,9 @@ AM62PX_IOPAD(0x023c, PIN_INPUT, 0) /* (H20) MMC1_CMD */ AM62PX_IOPAD(0x0234, PIN_OUTPUT, 0) /* (J24) MMC1_CLK */ AM62PX_IOPAD(0x0230, PIN_INPUT, 0) /* (H21) MMC1_DAT0 */ - AM62PX_IOPAD(0x022c, PIN_INPUT_PULLUP, 0) /* (H23) MMC1_DAT1 */ - AM62PX_IOPAD(0x0228, PIN_INPUT_PULLUP, 0) /* (H22) MMC1_DAT2 */ - AM62PX_IOPAD(0x0224, PIN_INPUT_PULLUP, 0) /* (H25) MMC1_DAT3 */ + AM62PX_IOPAD(0x022c, PIN_INPUT, 0) /* (H23) MMC1_DAT1 */ + AM62PX_IOPAD(0x0228, PIN_INPUT, 0) /* (H22) MMC1_DAT2 */ + AM62PX_IOPAD(0x0224, PIN_INPUT, 0) /* (H25) MMC1_DAT3 */ AM62PX_IOPAD(0x0240, PIN_INPUT, 0) /* (D23) MMC1_SDCD */ >; bootph-all; From 45669e3578aca4e59b1f0ab4637b812a5518632a Mon Sep 17 00:00:00 2001 From: Judith Mendez Date: Mon, 23 Feb 2026 17:37:31 -0600 Subject: [PATCH 0595/1518] arm64: dts: ti: k3-am62-lp-sk: Enable internal pulls for MMC0 data pins [ Upstream commit ee2a9d9c9e6c9643fb7e45febcaedfbc038e483a ] AM62 LP SK board does not have external pullups on MMC0 DAT1-DAT7 pins [0]. Enable internal pullups on DAT1-DAT7 considering: - without a host-side pullup, these lines rely solely on the eMMC device's internal pullup (R_int, 10-150K per JEDEC), which may exceed the recommended 50K max for 1.8V VCCQ - JEDEC JESD84-B51 Table 200 requires host-side pullups (R_DAT, 10K-100K) on all data lines to prevent bus floating [0] https://www.ti.com/lit/zip/SPRR471 Fixes: a0b8da04153e ("arm64: dts: ti: k3-am62*: Move eMMC pinmux to top level board file") Signed-off-by: Judith Mendez Reviewed-by: Moteen Shah Link: https://patch.msgid.link/20260223233731.2690472-4-jm@ti.com Signed-off-by: Vignesh Raghavendra Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts b/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts index ecfba05fe5c27..5ed757c19db60 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts @@ -88,13 +88,13 @@ AM62X_IOPAD(0x220, PIN_INPUT, 0) /* (V3) MMC0_CMD */ AM62X_IOPAD(0x218, PIN_INPUT, 0) /* (Y1) MMC0_CLK */ AM62X_IOPAD(0x214, PIN_INPUT, 0) /* (V2) MMC0_DAT0 */ - AM62X_IOPAD(0x210, PIN_INPUT, 0) /* (V1) MMC0_DAT1 */ - AM62X_IOPAD(0x20c, PIN_INPUT, 0) /* (W2) MMC0_DAT2 */ - AM62X_IOPAD(0x208, PIN_INPUT, 0) /* (W1) MMC0_DAT3 */ - AM62X_IOPAD(0x204, PIN_INPUT, 0) /* (Y2) MMC0_DAT4 */ - AM62X_IOPAD(0x200, PIN_INPUT, 0) /* (W3) MMC0_DAT5 */ - AM62X_IOPAD(0x1fc, PIN_INPUT, 0) /* (W4) MMC0_DAT6 */ - AM62X_IOPAD(0x1f8, PIN_INPUT, 0) /* (V4) MMC0_DAT7 */ + AM62X_IOPAD(0x210, PIN_INPUT_PULLUP, 0) /* (V1) MMC0_DAT1 */ + AM62X_IOPAD(0x20c, PIN_INPUT_PULLUP, 0) /* (W2) MMC0_DAT2 */ + AM62X_IOPAD(0x208, PIN_INPUT_PULLUP, 0) /* (W1) MMC0_DAT3 */ + AM62X_IOPAD(0x204, PIN_INPUT_PULLUP, 0) /* (Y2) MMC0_DAT4 */ + AM62X_IOPAD(0x200, PIN_INPUT_PULLUP, 0) /* (W3) MMC0_DAT5 */ + AM62X_IOPAD(0x1fc, PIN_INPUT_PULLUP, 0) /* (W4) MMC0_DAT6 */ + AM62X_IOPAD(0x1f8, PIN_INPUT_PULLUP, 0) /* (V4) MMC0_DAT7 */ >; }; From 4675ae61aa6364bd8802bd6ed42220fd4e1e5197 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Tue, 24 Mar 2026 10:36:57 +0100 Subject: [PATCH 0596/1518] arm64: dts: ti: k3-am62-verdin: Fix SPI_1 GPIO CS pinctrl label [ Upstream commit 944dffaec1ef0f21c203728de77b5618ed70df6e ] Fix SPI_1_CS GPIO pinmux label, this is spi1_cs, not qspi1_io4. There are no user of this label yet, therefore this change does not create any compatibility issue. Fixes: fcb335934c51 ("arm64: dts: ti: verdin-am62: Improve spi1 chip-select pinctrl") Signed-off-by: Francesco Dolcini Link: https://patch.msgid.link/20260324093705.26730-3-francesco@dolcini.it Signed-off-by: Vignesh Raghavendra Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi index 796f2cedf5d62..059ec492a973e 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi @@ -278,7 +278,7 @@ }; /* Verdin SPI_1 CS as GPIO */ - pinctrl_qspi1_io4_gpio: main-gpio0-7-default-pins { + pinctrl_spi1_cs_gpio: main-gpio0-7-default-pins { pinctrl-single,pins = < AM62X_IOPAD(0x001c, PIN_INPUT, 7) /* (J23) OSPI0_D4.GPIO0_7 */ /* SODIMM 202 */ >; From 85163323ab36824da95f07b5203c8d2c3a7e757b Mon Sep 17 00:00:00 2001 From: Nora Schiffer Date: Mon, 2 Mar 2026 09:45:48 +0100 Subject: [PATCH 0597/1518] arm64: dts: freescale: imx8mp-tqma8mpql-mba8mp-ras314: fix UART1 RTS/CTS muxing [ Upstream commit b8d785a9f360abcd6a6f8f10a2adf222f8494d66 ] UART1 operates in DCE mode, but the RTS/CTS pins were incorrectly configured using the DTE pinmux setting. Correct the pinmux to match DCE mode. Switching the RTS and CTS signals is fine for this board, as UART1 is routed to a pin header. Existing functionality is unaffected, as RTS/CTS could never have worked with the incorrect pinmux. Fixes: ddabb3ce3f90 ("arm64: dts: freescale: add TQMa8MPQL on MBa8MP-RAS314") Signed-off-by: Nora Schiffer Reviewed-by: Alexander Stein Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- .../boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts index a122f2ed5f531..06c865c3a8cf8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts @@ -833,8 +833,8 @@ pinctrl_uart1: uart1grp { fsl,pins = , , - , - ; + , + ; }; pinctrl_uart1_gpio: uart1gpiogrp { From 7fedcbedec65ee5d9157403c0fceeba508c49f77 Mon Sep 17 00:00:00 2001 From: Annette Kobou Date: Mon, 9 Mar 2026 09:57:43 +0100 Subject: [PATCH 0598/1518] arm64: dts: imx8mp-kontron: Fix boot order for PMIC and RTC [ Upstream commit 130d90114c5255a7a729158da8fd8298a02017f1 ] The PMIC provides a level-shifter for the I2C lines to the RTC. As the level shifter needs to be enabled before the RTC can be accessed, make sure that the PMIC driver is probed first. As the PMIC also provides the supply voltage for the RTC through the 3.3V regulator, simply express this in the DT to create the required dependency. Avoid sporadic boot hangs that occurred when the RTC was accessed before the level-shifter was enabled. Fixes: 946ab10e3f40f ("arm64: dts: Add support for Kontron OSM-S i.MX8MP SoM and BL carrier board") Signed-off-by: Annette Kobou Signed-off-by: Frieder Schrempf Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi index b97bfeb1c30f8..bc1a261bb000e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi @@ -330,6 +330,12 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rtc>; interrupts-extended = <&gpio3 24 IRQ_TYPE_LEVEL_LOW>; + /* + * While specifying the vdd-supply is normally not strictly necessary, + * here it also makes sure that the PMIC driver enables the level- + * shifter for the RTC before the RTC is probed. + */ + vdd-supply = <®_vdd_3v3>; }; }; From 5f2ca479f0f30930bbec35dc6280a431d5499e68 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Tue, 17 Mar 2026 13:37:38 +0800 Subject: [PATCH 0599/1518] arm64: dts: imx8dxl-evk: Use audio-graph-card2 for wm8960-2 and wm8960-3 [ Upstream commit e8341b0245736619f8d6a2cc311c9e8ad8e82390 ] The sound card wm8960-2 and wm8960-3 only support capture mode for the reason of connection on the EVK board. But fsl-asoc-card don't support capture_only setting, the sound card creation will fail. fsl-sai 59060000.sai: Missing dma channel for stream: 0 fsl-sai 59060000.sai: ASoC error (-22): at snd_soc_pcm_component_new() on 59060000.sai fsl-sai 59070000.sai: Missing dma channel for stream: 0 fsl-sai 59070000.sai: ASoC error (-22): at snd_soc_pcm_component_new() on 59070000.sai so switch to use audio-graph-card2 which supports 'capture_only' property for wm8960-2 and wm8960-3 cards. Fixes: b41c45eb990a ("arm64: dts: imx8dxl-evk: add audio nodes") Signed-off-by: Shengjiu Wang Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8dxl-evk.dts | 114 ++++++++++++++---- 1 file changed, 90 insertions(+), 24 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts index 25a77cac6f0b5..b75ab1e010f0c 100644 --- a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts @@ -259,33 +259,37 @@ }; sound-wm8960-2 { - compatible = "fsl,imx-audio-wm8960"; - model = "wm8960-audio-2"; - audio-cpu = <&sai2>; - audio-codec = <&wm8960_2>; - audio-routing = "Headphone Jack", "HP_L", - "Headphone Jack", "HP_R", - "Ext Spk", "SPK_LP", - "Ext Spk", "SPK_LN", - "Ext Spk", "SPK_RP", - "Ext Spk", "SPK_RN", - "LINPUT1", "Mic Jack", - "Mic Jack", "MICB"; + compatible = "audio-graph-card2"; + label = "wm8960-audio-2"; + links = <&sai2_port2>; + routing = "Headphones", "HP_L", + "Headphones", "HP_R", + "Ext Spk", "SPK_LP", + "Ext Spk", "SPK_LN", + "Ext Spk", "SPK_RP", + "Ext Spk", "SPK_RN", + "LINPUT1", "Mic Jack", + "Mic Jack", "MICB"; + widgets = "Headphone", "Headphones", + "Speaker", "Ext Spk", + "Microphone", "Mic Jack"; }; sound-wm8960-3 { - compatible = "fsl,imx-audio-wm8960"; - model = "wm8960-audio-3"; - audio-cpu = <&sai3>; - audio-codec = <&wm8960_3>; - audio-routing = "Headphone Jack", "HP_L", - "Headphone Jack", "HP_R", - "Ext Spk", "SPK_LP", - "Ext Spk", "SPK_LN", - "Ext Spk", "SPK_RP", - "Ext Spk", "SPK_RN", - "LINPUT1", "Mic Jack", - "Mic Jack", "MICB"; + compatible = "audio-graph-card2"; + label = "wm8960-audio-3"; + links = <&sai3_port2>; + routing = "Headphones", "HP_L", + "Headphones", "HP_R", + "Ext Spk", "SPK_LP", + "Ext Spk", "SPK_LN", + "Ext Spk", "SPK_RP", + "Ext Spk", "SPK_RN", + "LINPUT1", "Mic Jack", + "Mic Jack", "MICB"; + widgets = "Headphone", "Headphones", + "Speaker", "Ext Spk", + "Microphone", "Mic Jack"; }; }; @@ -481,6 +485,16 @@ DCVDD-supply = <®_audio_1v8>; SPKVDD1-supply = <®_audio_5v>; SPKVDD2-supply = <®_audio_5v>; + + port { + capture-only; + + wm8960_2_ep: endpoint { + bitclock-master; + frame-master; + remote-endpoint = <&sai2_endpoint2>; + }; + }; }; }; @@ -510,6 +524,16 @@ DCVDD-supply = <®_audio_1v8>; SPKVDD1-supply = <®_audio_5v>; SPKVDD2-supply = <®_audio_5v>; + + port { + capture-only; + + wm8960_3_ep: endpoint { + bitclock-master; + frame-master; + remote-endpoint = <&sai3_endpoint2>; + }; + }; }; }; @@ -695,6 +719,27 @@ pinctrl-0 = <&pinctrl_sai2>; fsl,sai-asynchronous; status = "okay"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + sai2_port1: port@1 { + reg = <1>; + endpoint { /* not used */ }; + }; + + sai2_port2: port@2 { + reg = <2>; + capture-only; + + sai2_endpoint2: endpoint { + dai-format = "i2s"; + remote-endpoint = <&wm8960_2_ep>; + system-clock-direction-out; + }; + }; + }; }; &sai3 { @@ -707,6 +752,27 @@ pinctrl-0 = <&pinctrl_sai3>; fsl,sai-asynchronous; status = "okay"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + sai3_port1: port@1 { + reg = <1>; + endpoint { /* not used */ }; + }; + + sai3_port2: port@2 { + reg = <2>; + capture-only; + + sai3_endpoint2: endpoint { + dai-format = "i2s"; + remote-endpoint = <&wm8960_3_ep>; + system-clock-direction-out; + }; + }; + }; }; &thermal_zones { From 69f4d9ce27d89615561d46aab8d7f121f68413b7 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:40:56 +0100 Subject: [PATCH 0600/1518] arm64: dts: lx2160a: change i2c0 (iic1) pinmux mask to one bit [ Upstream commit 7a3cc49ad1fc8d063abb7f5de8f1b981b99d2978 ] LX2160A pinmux is done in groups by various length bitfields within configuration registers. The first i2c bus (called IIC1 in reference manual) is configured through field IIC1_PMUX in register RCWSR14 bit 10 which is described in the reference manual as a single bit, unlike the other i2c buses. Change the bitmask for the pinmux nodes from 0x7 to 0x1 to ensure only single bit is modified. Further change the zero in the same line to hexadecimal format for consistency. Align with documentation by avoiding writes to reserved bits. No functional change, as writing the extra two reserved bits is not known to cause issues. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index bc1d34f1cd545..79a22f53afc50 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1790,11 +1790,11 @@ }; i2c0_scl: i2c0-scl-pins { - pinctrl-single,bits = <0x8 0 (0x7 << 10)>; + pinctrl-single,bits = <0x8 0x0 (0x1 << 10)>; }; i2c0_scl_gpio: i2c0-scl-gpio-pins { - pinctrl-single,bits = <0x8 (0x1 << 10) (0x7 << 10)>; + pinctrl-single,bits = <0x8 (0x1 << 10) (0x1 << 10)>; }; }; From b165c477175b528d1dc472bf02e79bfcf19a503e Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:40:57 +0100 Subject: [PATCH 0601/1518] arm64: dts: lx2160a: remove duplicate pinmux nodes [ Upstream commit 325ca511ca3dda936207ce737e0afe837d45a674 ] LX2160A pinmux is done in groups by various length bitfields within configuration registers. The pinmux nodes i2c7-scl-pins and i2c7-scl-gpio-pins are duplicates of i2c6-scl-gpio and i2c6-scl-gpio-pins, writing to the same register and bits. These two i2c buses i2c6/i2c7 (IIC7/IIC8) are configured together in register RCWSR13 bits 3-0. Drop the duplicate node name and change references to the i2c6 node. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 79a22f53afc50..6d21982e057b3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -862,8 +862,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c7_scl>; - pinctrl-1 = <&i2c7_scl_gpio>; + pinctrl-0 = <&i2c6_scl>; + pinctrl-1 = <&i2c6_scl_gpio>; scl-gpios = <&gpio1 18 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -1781,14 +1781,6 @@ pinctrl-single,bits = <0x4 0x1 0x7>; }; - i2c7_scl: i2c7-scl-pins { - pinctrl-single,bits = <0x4 0x2 0x7>; - }; - - i2c7_scl_gpio: i2c7-scl-gpio-pins { - pinctrl-single,bits = <0x4 0x1 0x7>; - }; - i2c0_scl: i2c0-scl-pins { pinctrl-single,bits = <0x8 0x0 (0x1 << 10)>; }; From ce85b22e556aff1f487196f219e9fa0b02b0ac70 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:40:58 +0100 Subject: [PATCH 0602/1518] arm64: dts: lx2160a: rename pinmux nodes for readability [ Upstream commit 456eb494746afd56d3a9dc30271300136e55b96e ] LX2160A pinmux is done in groups by various length bitfields within configuration registers. Each group of pins is named in the reference manual after a primary function using soc-specific naming, e.g. IIC1 (for i2c0). Hardware block numbering starts from zero in device-tree but one in the reference manual. Rename the already defined pinmux nodes originally added for changing i2c pins between i2c and gpio functions reflecting the reference manual name (IIC) in the node name, and the device-tree name (i2c, gpio) in the label. Specifically, drop the "_scl" suffix from the I2C labels because the nodes actually configure both SDA and SCL pins together. Instead add "_pins" suffix to avoid conflicts with I2C controller labels. For GPIO functions, include the specific controller and pin numbers in the label to clarify they are generic GPIOs and help spot mistakes. No functional change intended. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- .../arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 64 +++++++++---------- 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 6d21982e057b3..59417e00ac93d 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -750,8 +750,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c0_scl>; - pinctrl-1 = <&i2c0_scl_gpio>; + pinctrl-0 = <&i2c0_pins>; + pinctrl-1 = <&gpio0_3_2_pins>; scl-gpios = <&gpio0 3 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -766,8 +766,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c1_scl>; - pinctrl-1 = <&i2c1_scl_gpio>; + pinctrl-0 = <&i2c1_pins>; + pinctrl-1 = <&gpio0_31_30_pins>; scl-gpios = <&gpio0 31 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -782,8 +782,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c2_scl>; - pinctrl-1 = <&i2c2_scl_gpio>; + pinctrl-0 = <&i2c2_pins>; + pinctrl-1 = <&gpio0_29_28_pins>; scl-gpios = <&gpio0 29 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -798,8 +798,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c3_scl>; - pinctrl-1 = <&i2c3_scl_gpio>; + pinctrl-0 = <&i2c3_pins>; + pinctrl-1 = <&gpio0_27_26_pins>; scl-gpios = <&gpio0 27 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -814,8 +814,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c4_scl>; - pinctrl-1 = <&i2c4_scl_gpio>; + pinctrl-0 = <&i2c4_pins>; + pinctrl-1 = <&gpio0_25_24_pins>; scl-gpios = <&gpio0 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -830,8 +830,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c5_scl>; - pinctrl-1 = <&i2c5_scl_gpio>; + pinctrl-0 = <&i2c5_pins>; + pinctrl-1 = <&gpio0_23_22_pins>; scl-gpios = <&gpio0 23 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -846,8 +846,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c6_scl>; - pinctrl-1 = <&i2c6_scl_gpio>; + pinctrl-0 = <&i2c6_i2c7_pins>; + pinctrl-1 = <&gpio1_18_15_pins>; scl-gpios = <&gpio1 16 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -862,8 +862,8 @@ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(16)>; pinctrl-names = "default", "gpio"; - pinctrl-0 = <&i2c6_scl>; - pinctrl-1 = <&i2c6_scl_gpio>; + pinctrl-0 = <&i2c6_i2c7_pins>; + pinctrl-1 = <&gpio1_18_15_pins>; scl-gpios = <&gpio1 18 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -1709,11 +1709,11 @@ pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0x7>; - i2c1_scl: i2c1-scl-pins { + i2c1_pins: iic2-i2c-pins { pinctrl-single,bits = <0x0 0 0x7>; }; - i2c1_scl_gpio: i2c1-scl-gpio-pins { + gpio0_31_30_pins: iic2-gpio-pins { pinctrl-single,bits = <0x0 0x1 0x7>; }; @@ -1721,35 +1721,35 @@ pinctrl-single,bits = <0x0 0x6 0x7>; }; - i2c2_scl: i2c2-scl-pins { + i2c2_pins: iic3-i2c-pins { pinctrl-single,bits = <0x0 0 (0x7 << 3)>; }; - i2c2_scl_gpio: i2c2-scl-gpio-pins { + gpio0_29_28_pins: iic3-gpio-pins { pinctrl-single,bits = <0x0 (0x1 << 3) (0x7 << 3)>; }; - i2c3_scl: i2c3-scl-pins { + i2c3_pins: iic4-i2c-pins { pinctrl-single,bits = <0x0 0 (0x7 << 6)>; }; - i2c3_scl_gpio: i2c3-scl-gpio-pins { + gpio0_27_26_pins: iic4-gpio-pins { pinctrl-single,bits = <0x0 (0x1 << 6) (0x7 << 6)>; }; - i2c4_scl: i2c4-scl-pins { + i2c4_pins: iic5-i2c-pins { pinctrl-single,bits = <0x0 0 (0x7 << 9)>; }; - i2c4_scl_gpio: i2c4-scl-gpio-pins { + gpio0_25_24_pins: iic5-gpio-pins { pinctrl-single,bits = <0x0 (0x1 << 9) (0x7 << 9)>; }; - i2c5_scl: i2c5-scl-pins { + i2c5_pins: iic6-i2c-pins { pinctrl-single,bits = <0x0 0 (0x7 << 12)>; }; - i2c5_scl_gpio: i2c5-scl-gpio-pins { + gpio0_23_22_pins: iic6-gpio-pins { pinctrl-single,bits = <0x0 (0x1 << 12) (0x7 << 12)>; }; @@ -1773,19 +1773,19 @@ pinctrl-single,bits = <0x0 (0x1 << 27) (0x7 << 27)>; }; - i2c6_scl: i2c6-scl-pins { - pinctrl-single,bits = <0x4 0x2 0x7>; + gpio1_18_15_pins: iic8-iic7-gpio-pins { + pinctrl-single,bits = <0x4 0x1 0x7>; }; - i2c6_scl_gpio: i2c6-scl-gpio-pins { - pinctrl-single,bits = <0x4 0x1 0x7>; + i2c6_i2c7_pins: iic8-iic7-i2c-pins { + pinctrl-single,bits = <0x4 0x2 0x7>; }; - i2c0_scl: i2c0-scl-pins { + i2c0_pins: iic1-i2c-pins { pinctrl-single,bits = <0x8 0x0 (0x1 << 10)>; }; - i2c0_scl_gpio: i2c0-scl-gpio-pins { + gpio0_3_2_pins: iic1-gpio-pins { pinctrl-single,bits = <0x8 (0x1 << 10) (0x1 << 10)>; }; }; From e77a86d883b5e4ee784191bcc406991d10a692eb Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:40:59 +0100 Subject: [PATCH 0603/1518] arm64: dts: lx2160a: add sda gpio references for i2c bus recovery [ Upstream commit 89ea0dbd701f89805499d26bd90657468c789545 ] LX2160A pinmux is done in groups by various length bitfields within configuration registers. In particular i2c sda/scl pins are always configured together. Therefore bus recovery may control both sda and scl. When pinmux nodes and bus recovery was enabled originally for LX2160, only the scl-gpios were added to the i2c controller nodes. Add references to sda-gpios for each i2c controller. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 59417e00ac93d..e7790a94e888f 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -753,6 +753,7 @@ pinctrl-0 = <&i2c0_pins>; pinctrl-1 = <&gpio0_3_2_pins>; scl-gpios = <&gpio0 3 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 2 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -769,6 +770,7 @@ pinctrl-0 = <&i2c1_pins>; pinctrl-1 = <&gpio0_31_30_pins>; scl-gpios = <&gpio0 31 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 30 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -785,6 +787,7 @@ pinctrl-0 = <&i2c2_pins>; pinctrl-1 = <&gpio0_29_28_pins>; scl-gpios = <&gpio0 29 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 28 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -801,6 +804,7 @@ pinctrl-0 = <&i2c3_pins>; pinctrl-1 = <&gpio0_27_26_pins>; scl-gpios = <&gpio0 27 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 26 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -817,6 +821,7 @@ pinctrl-0 = <&i2c4_pins>; pinctrl-1 = <&gpio0_25_24_pins>; scl-gpios = <&gpio0 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -833,6 +838,7 @@ pinctrl-0 = <&i2c5_pins>; pinctrl-1 = <&gpio0_23_22_pins>; scl-gpios = <&gpio0 23 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio0 22 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -849,6 +855,7 @@ pinctrl-0 = <&i2c6_i2c7_pins>; pinctrl-1 = <&gpio1_18_15_pins>; scl-gpios = <&gpio1 16 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio1 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; @@ -865,6 +872,7 @@ pinctrl-0 = <&i2c6_i2c7_pins>; pinctrl-1 = <&gpio1_18_15_pins>; scl-gpios = <&gpio1 18 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio1 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; status = "disabled"; }; From 857dbf1f51feffbb819b7f61b696c76e5fb0ed93 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:41:00 +0100 Subject: [PATCH 0604/1518] arm64: dts: lx2160a: change zeros to hexadecimal in pinmux nodes [ Upstream commit 03241620d2b9915c9e3463dbc56e9eb95ad43c08 ] Replace some stray zeros from decimal to hexadecimal format within pinmux nodes. No functional change intended. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index e7790a94e888f..536f4bfad9a67 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1718,7 +1718,7 @@ pinctrl-single,function-mask = <0x7>; i2c1_pins: iic2-i2c-pins { - pinctrl-single,bits = <0x0 0 0x7>; + pinctrl-single,bits = <0x0 0x0 0x7>; }; gpio0_31_30_pins: iic2-gpio-pins { @@ -1730,7 +1730,7 @@ }; i2c2_pins: iic3-i2c-pins { - pinctrl-single,bits = <0x0 0 (0x7 << 3)>; + pinctrl-single,bits = <0x0 0x0 (0x7 << 3)>; }; gpio0_29_28_pins: iic3-gpio-pins { @@ -1738,7 +1738,7 @@ }; i2c3_pins: iic4-i2c-pins { - pinctrl-single,bits = <0x0 0 (0x7 << 6)>; + pinctrl-single,bits = <0x0 0x0 (0x7 << 6)>; }; gpio0_27_26_pins: iic4-gpio-pins { @@ -1746,7 +1746,7 @@ }; i2c4_pins: iic5-i2c-pins { - pinctrl-single,bits = <0x0 0 (0x7 << 9)>; + pinctrl-single,bits = <0x0 0x0 (0x7 << 9)>; }; gpio0_25_24_pins: iic5-gpio-pins { @@ -1754,7 +1754,7 @@ }; i2c5_pins: iic6-i2c-pins { - pinctrl-single,bits = <0x0 0 (0x7 << 12)>; + pinctrl-single,bits = <0x0 0x0 (0x7 << 12)>; }; gpio0_23_22_pins: iic6-gpio-pins { From 3341ca45d2808018bc5f1d0d3abfad12ee38de68 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Tue, 24 Mar 2026 13:41:01 +0100 Subject: [PATCH 0605/1518] arm64: dts: lx2160a: complete pinmux for rcwsr12 configuration word [ Upstream commit 284ad7064aaa1badde022785cd925af29c696b21 ] Commit 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") introduced pinmux nodes for lx2160 i2c interfaces, allowing runtime change between i2c and gpio functions implementing bus recovery. However, the dynamic configuration area (overwrite MUX) used by the pinctrl-single driver initially reads as zero and does not reflect the actual hardware state set by the Reset Configuration Word (RCW) at power-on. Because multiple groups of pins are configured from a single 32-bit register, the first write from the pinctrl driver unintentionally clears all other bits to zero. Add description for all bits of RCWSR12 register, allowing boards to explicitly define and restore their intended hardware state. This includes i2c, gpio, flextimer, spi, can and sdhc functions. Other configuration words, i.e. RCWSR13 & RCWSR14 may be added in the future for boards setting non-zero values there. Fixes: 8a1365c7bbc1 ("arm64: dts: lx2160a: add pinmux and i2c gpio to support bus recovery") Signed-off-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- .../arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 75 +++++++++++++++++++ 1 file changed, 75 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 536f4bfad9a67..f7fb0a0562ec7 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1717,6 +1717,7 @@ pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0x7>; + /* RCWSR12 */ i2c1_pins: iic2-i2c-pins { pinctrl-single,bits = <0x0 0x0 0x7>; }; @@ -1725,6 +1726,10 @@ pinctrl-single,bits = <0x0 0x1 0x7>; }; + ftm0_ch10_pins: iic2-ftm-pins { + pinctrl-single,bits = <0x0 0x2 0x7>; + }; + esdhc0_cd_wp_pins: iic2-sdhc-pins { pinctrl-single,bits = <0x0 0x6 0x7>; }; @@ -1737,6 +1742,14 @@ pinctrl-single,bits = <0x0 (0x1 << 3) (0x7 << 3)>; }; + can0_pins: iic3-can-pins { + pinctrl-single,bits = <0x0 (0x2 << 3) (0x7 << 3)>; + }; + + event65_pins: iic3-event-pins { + pinctrl-single,bits = <0x0 (0x6 << 3) (0x7 << 3)>; + }; + i2c3_pins: iic4-i2c-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 6)>; }; @@ -1745,6 +1758,14 @@ pinctrl-single,bits = <0x0 (0x1 << 6) (0x7 << 6)>; }; + can1_pins: iic4-can-pins { + pinctrl-single,bits = <0x0 (0x2 << 6) (0x7 << 6)>; + }; + + event87_pins: iic4-event-pins { + pinctrl-single,bits = <0x0 (0x6 << 6) (0x7 << 6)>; + }; + i2c4_pins: iic5-i2c-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 9)>; }; @@ -1753,6 +1774,14 @@ pinctrl-single,bits = <0x0 (0x1 << 9) (0x7 << 9)>; }; + esdhc0_clksync_pins: iic5-sdhc-clk-pins { + pinctrl-single,bits = <0x0 (0x2 << 9) (0x7 << 9)>; + }; + + dspi2_miso_mosi_pins: iic5-spi3-pins { + pinctrl-single,bits = <0x3 (0x2 << 9) (0x7 << 9)>; + }; + i2c5_pins: iic6-i2c-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 12)>; }; @@ -1761,26 +1790,71 @@ pinctrl-single,bits = <0x0 (0x1 << 12) (0x7 << 12)>; }; + esdhc1_clksync_pins: iic6-sdhc-clk-pins { + pinctrl-single,bits = <0x0 (0x2 << 12) (0x7 << 12)>; + }; + fspi_data74_pins: xspi1-data74-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 15)>; }; + gpio1_31_28_pins: xspi1-data74-gpio-pins { + pinctrl-single,bits = <0x0 0x1 (0x7 << 15)>; + }; + fspi_data30_pins: xspi1-data30-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 18)>; }; + gpio1_27_24_pins: xspi1-data30-gpio-pins { + pinctrl-single,bits = <0x0 0x1 (0x7 << 18)>; + }; + fspi_dqs_sck_cs10_pins: xspi1-base-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 21)>; }; + gpio1_23_20_pins: xspi1-base-gpio-pins { + pinctrl-single,bits = <0x0 0x1 (0x7 << 21)>; + }; + esdhc0_cmd_data30_clk_vsel_pins: sdhc1-base-sdhc-vsel-pins { pinctrl-single,bits = <0x0 0x0 (0x7 << 24)>; }; + gpio0_21_15_pins: sdhc1-base-gpio-pins { + pinctrl-single,bits = <0x0 (0x1 << 24) (0x7 << 24)>; + }; + + dspi0_pins: sdhc1-base-spi1-pins { + pinctrl-single,bits = <0x0 (0x2 << 24) (0x7 << 24)>; + }; + + esdhc0_cmd_data30_clk_dspi2_cs0_pins: sdhc1-base-sdhc-spi3-pins { + pinctrl-single,bits = <0x0 (0x3 << 24) (0x7 << 24)>; + }; + + esdhc0_cmd_data30_clk_data4_pins: sdhc1-base-sdhc-data4-pins { + pinctrl-single,bits = <0x0 (0x4 << 24) (0x7 << 24)>; + }; + + esdhc0_dir_pins: sdhc1-dir-pins { + pinctrl-single,bits = <0x0 0x0 (0x7 << 27)>; + }; + gpio0_14_12_pins: sdhc1-dir-gpio-pins { pinctrl-single,bits = <0x0 (0x1 << 27) (0x7 << 27)>; }; + dspi2_cs31_pins: sdhc1-dir-spi3-pins { + pinctrl-single,bits = <0x0 (0x3 << 27) (0x7 << 27)>; + }; + + esdhc0_data75_pins: sdhc1-dir-sdhc-pins { + pinctrl-single,bits = <0x0 (0x4 << 27) (0x7 << 27)>; + }; + + /* RCWSR13 */ gpio1_18_15_pins: iic8-iic7-gpio-pins { pinctrl-single,bits = <0x4 0x1 0x7>; }; @@ -1789,6 +1863,7 @@ pinctrl-single,bits = <0x4 0x2 0x7>; }; + /* RCWSR14 */ i2c0_pins: iic1-i2c-pins { pinctrl-single,bits = <0x8 0x0 (0x1 << 10)>; }; From bf9a33944d7d08597ddb580d910221c44bd76793 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Tue, 24 Mar 2026 19:04:58 +0800 Subject: [PATCH 0606/1518] arm64: dts: imx8qm-mek: switch Type-C connector power-role to dual [ Upstream commit e3d3d19d1c0050789a4813ce836a641a3387d916 ] When attach to PC Type-A port, the USB device controller does not function at all. Because it is configured as source-only and a Type-A port doesn't support PD capability, a data role swap is impossible. Actually, PTN5110THQ is configured for Source role only at POR, but after POR it can operate as a DRP (Dual-Role Power). By switching the power-role to dual, the port can operate as a sink and enter device mode when attach to Type-A port. Since the board design uses EN_SRC to control the 5V VBUS path and EN_SNK to control the 12V VBUS output, to avoid outputting a higher VBUS when in sink role, we set the operation current limit to 0mA so that SW will not control EN_SNK at all. Fixes: b237975b2cd58 ("arm64: dts: imx8qm-mek: add usb 3.0 and related type C nodes") Signed-off-by: Xu Yang Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8qm-mek.dts | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index df99fe88cf4ac..a97883873b564 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -593,9 +593,17 @@ usb_con1: connector { compatible = "usb-c-connector"; label = "USB-C"; - power-role = "source"; + power-role = "dual"; data-role = "dual"; + try-power-role = "sink"; source-pdos = ; + /* + * Set operational current to 0mA as we don't want EN_SNK + * enable 12V VBUS switch when it work as a sink. + */ + sink-pdos = ; + op-sink-microwatt = <0>; + self-powered; ports { #address-cells = <1>; From aabc9baae9a73e65e481219eac4381770f2c6679 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Tue, 24 Mar 2026 19:04:59 +0800 Subject: [PATCH 0607/1518] arm64: dts: imx8qxp-mek: switch Type-C connector power-role to dual [ Upstream commit 825b8c7e1d2918d89eb378b761530d1e51dba82e ] When attach to PC Type-A port, the USB device controller does not function at all. Because it is configured as source-only and a Type-A port doesn't support PD capability, a data role swap is impossible. Actually, PTN5110THQ is configured for Source role only at POR, but after POR it can operate as a DRP (Dual-Role Power). By switching the power-role to dual, the port can operate as a sink and enter device mode when attach to Type-A port. Since the board design uses EN_SRC to control the 5V VBUS path and EN_SNK to control the 12V VBUS output, to avoid outputting a higher VBUS when in sink role, we set the operation current limit to 0mA so that SW will not control EN_SNK at all. Fixes: 2faf4ebcee2e5 ("arm64: dts: freescale: imx8qxp-mek: enable cadence usb3") Signed-off-by: Xu Yang Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8qxp-mek.dts | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts index 7b03374455410..ea78e84341523 100644 --- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts @@ -497,9 +497,17 @@ usb_con1: connector { compatible = "usb-c-connector"; label = "USB-C"; - power-role = "source"; + power-role = "dual"; data-role = "dual"; + try-power-role = "sink"; source-pdos = ; + /* + * Set operational current to 0mA as we don't want EN_SNK + * enable 12V VBUS switch when it work as a sink. + */ + sink-pdos = ; + op-sink-microwatt = <0>; + self-powered; ports { #address-cells = <1>; From 9dc2462a7595f32e970b7c0649d6d7cfd636030d Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Wed, 21 Jan 2026 15:42:03 +0530 Subject: [PATCH 0608/1518] soc/tegra: cbb: Set ERD on resume for err interrupt [ Upstream commit b6ff71c5d1d4ad858ddf6f39394d169c96689596 ] Set the Error Response Disable (ERD) bit to mask SError responses and use interrupt-based error reporting. When the ERD bit is set, inband error responses to the initiator via SError are suppressed, and fabric errors are reported via an interrupt instead. The register is set during boot but the info is lost during system suspend and needs to be set again on resume. Fixes: fc2f151d2314 ("soc/tegra: cbb: Add driver for Tegra234 CBB 2.0") Signed-off-by: Sumit Gupta Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/soc/tegra/cbb/tegra234-cbb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/soc/tegra/cbb/tegra234-cbb.c b/drivers/soc/tegra/cbb/tegra234-cbb.c index a9adbcecd47cc..518733a066588 100644 --- a/drivers/soc/tegra/cbb/tegra234-cbb.c +++ b/drivers/soc/tegra/cbb/tegra234-cbb.c @@ -1586,6 +1586,10 @@ static int __maybe_unused tegra234_cbb_resume_noirq(struct device *dev) { struct tegra234_cbb *cbb = dev_get_drvdata(dev); + /* set ERD bit to mask SError and generate interrupt to report error */ + if (cbb->fabric->off_mask_erd) + tegra234_cbb_mask_serror(cbb); + tegra234_cbb_error_enable(&cbb->base); dev_dbg(dev, "%s resumed\n", cbb->fabric->fab_list[cbb->fabric->fab_id].name); From f46870b451f7583802ed26eec8b93e138840fcd9 Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Wed, 21 Jan 2026 15:42:04 +0530 Subject: [PATCH 0609/1518] soc/tegra: cbb: Fix incorrect ARRAY_SIZE in fabric lookup tables [ Upstream commit 499f7e5ebbdd9ff0c4d532b1c432f8a61ff585b3 ] Fix incorrect ARRAY_SIZE usage in fabric lookup tables which could cause out-of-bounds access during target timeout lookup. Fixes: 25de5c8fe0801 ("soc/tegra: cbb: Improve handling for per SoC fabric data") Signed-off-by: Sumit Gupta Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/soc/tegra/cbb/tegra234-cbb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soc/tegra/cbb/tegra234-cbb.c b/drivers/soc/tegra/cbb/tegra234-cbb.c index 518733a066588..626e0e820329b 100644 --- a/drivers/soc/tegra/cbb/tegra234-cbb.c +++ b/drivers/soc/tegra/cbb/tegra234-cbb.c @@ -881,7 +881,7 @@ static const struct tegra234_fabric_lookup tegra234_cbb_fab_list[] = { ARRAY_SIZE(tegra234_common_target_map) }, [T234_AON_FABRIC_ID] = { "aon-fabric", true, tegra234_aon_target_map, - ARRAY_SIZE(tegra234_bpmp_target_map) }, + ARRAY_SIZE(tegra234_aon_target_map) }, [T234_PSC_FABRIC_ID] = { "psc-fabric" }, [T234_BPMP_FABRIC_ID] = { "bpmp-fabric", true, tegra234_bpmp_target_map, @@ -1160,7 +1160,7 @@ static const struct tegra234_fabric_lookup tegra241_cbb_fab_list[] = { [T234_CBB_FABRIC_ID] = { "cbb-fabric", true, tegra241_cbb_target_map, ARRAY_SIZE(tegra241_cbb_target_map) }, [T234_BPMP_FABRIC_ID] = { "bpmp-fabric", true, - tegra241_bpmp_target_map, ARRAY_SIZE(tegra241_cbb_target_map) }, + tegra241_bpmp_target_map, ARRAY_SIZE(tegra241_bpmp_target_map) }, }; static const struct tegra234_cbb_fabric tegra241_cbb_fabric = { .fab_id = T234_CBB_FABRIC_ID, From c892d0d4fe5ec05d3fdfb1616c3c0e3c12ef5abc Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Wed, 21 Jan 2026 15:42:05 +0530 Subject: [PATCH 0610/1518] soc/tegra: cbb: Fix cross-fabric target timeout lookup [ Upstream commit a5f51b04cbb3ae0f9cb2c4488952b775ebb0ccbf ] When a fabric receives an error interrupt, the error may have occurred on a different fabric. The target timeout lookup was using the wrong base address (cbb->regs) with offsets from a different fabric's target map, causing a kernel page fault. Unable to handle kernel paging request at virtual address ffff80000954cc00 pc : tegra234_cbb_get_tmo_slv+0xc/0x28 Call trace: tegra234_cbb_get_tmo_slv+0xc/0x28 print_err_notifier+0x6c0/0x7d0 tegra234_cbb_isr+0xe4/0x1b4 Add tegra234_cbb_get_fabric() to look up the correct fabric device using fab_id, and use its base address for accessing target timeout registers. Fixes: 25de5c8fe0801 ("soc/tegra: cbb: Improve handling for per SoC fabric data") Signed-off-by: Sumit Gupta Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/soc/tegra/cbb/tegra234-cbb.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/drivers/soc/tegra/cbb/tegra234-cbb.c b/drivers/soc/tegra/cbb/tegra234-cbb.c index 626e0e820329b..7e387fc54c6b1 100644 --- a/drivers/soc/tegra/cbb/tegra234-cbb.c +++ b/drivers/soc/tegra/cbb/tegra234-cbb.c @@ -313,12 +313,37 @@ static void tegra234_cbb_lookup_apbslv(struct seq_file *file, const char *target } } +static struct tegra234_cbb *tegra234_cbb_get_fabric(u8 fab_id) +{ + struct tegra_cbb *entry; + + list_for_each_entry(entry, &cbb_list, node) { + struct tegra234_cbb *priv = to_tegra234_cbb(entry); + + if (priv->fabric->fab_id == fab_id) + return priv; + } + + return NULL; +} + static void tegra234_sw_lookup_target_timeout(struct seq_file *file, struct tegra234_cbb *cbb, u8 target_id, u8 fab_id) { const struct tegra234_target_lookup *map = cbb->fabric->fab_list[fab_id].target_map; + struct tegra234_cbb *target_cbb = NULL; void __iomem *addr; + if (fab_id == cbb->fabric->fab_id) + target_cbb = cbb; + else + target_cbb = tegra234_cbb_get_fabric(fab_id); + + if (!target_cbb) { + dev_err(cbb->base.dev, "could not find fabric for fab_id:%d\n", fab_id); + return; + } + if (target_id >= cbb->fabric->fab_list[fab_id].max_targets) { tegra_cbb_print_err(file, "\t Invalid target_id:%d\n", target_id); return; @@ -341,7 +366,7 @@ static void tegra234_sw_lookup_target_timeout(struct seq_file *file, struct tegr * e) Goto step-a till all bits are set. */ - addr = cbb->regs + map[target_id].offset; + addr = target_cbb->regs + map[target_id].offset; if (strstr(map[target_id].name, "AXI2APB")) { addr += APB_BLOCK_TMO_STATUS_0; From a261fccdb4ac58ec5ba6aa1d92a6cc418fff301f Mon Sep 17 00:00:00 2001 From: Michal Grzedzicki Date: Fri, 13 Feb 2026 11:39:59 -0800 Subject: [PATCH 0611/1518] unshare: fix nsproxy leak in ksys_unshare() on set_cred_ucounts() failure [ Upstream commit a98621a0f187a934c115dcfe79a49520ae892111 ] When set_cred_ucounts() fails in ksys_unshare() new_nsproxy is leaked. Let's call put_nsproxy() if that happens. Link: https://lkml.kernel.org/r/20260213193959.2556730-1-mge@meta.com Fixes: 905ae01c4ae2 ("Add a reference to ucounts for each cred") Signed-off-by: Michal Grzedzicki Reviewed-by: Andrew Morton Cc: Alexey Gladkov (Intel) Cc: Ben Segall Cc: David Hildenbrand Cc: Dietmar Eggemann Cc: Ingo Molnar Cc: Juri Lelli Cc: Kees Cook Cc: "Liam R. Howlett" Cc: Lorenzo Stoakes (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Suren Baghdasaryan Cc: Valentin Schneider Cc: Vincent Guittot Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- kernel/fork.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 34e6b94c22129..3ad76c2cf5af5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -3132,11 +3132,10 @@ int ksys_unshare(unsigned long unshare_flags) new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; - if (new_cred) { err = set_cred_ucounts(new_cred); if (err) - goto bad_unshare_cleanup_cred; + goto bad_unshare_cleanup_nsproxy; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { @@ -3152,8 +3151,10 @@ int ksys_unshare(unsigned long unshare_flags) shm_init_task(current); } - if (new_nsproxy) + if (new_nsproxy) { switch_task_namespaces(current, new_nsproxy); + new_nsproxy = NULL; + } task_lock(current); @@ -3182,13 +3183,15 @@ int ksys_unshare(unsigned long unshare_flags) perf_event_namespaces(current); +bad_unshare_cleanup_nsproxy: + if (new_nsproxy) + put_nsproxy(new_nsproxy); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); - bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); From 3f474c33ebc2e2ca3fcb587d7de4375348f13373 Mon Sep 17 00:00:00 2001 From: Junrui Luo Date: Sat, 7 Mar 2026 15:21:08 +0800 Subject: [PATCH 0612/1518] ocfs2/dlm: validate qr_numregions in dlm_match_regions() [ Upstream commit 7ab3fbb01bc6d79091bc375e5235d360cd9b78be ] Patch series "ocfs2/dlm: fix two bugs in dlm_match_regions()". In dlm_match_regions(), the qr_numregions field from a DLM_QUERY_REGION network message is used to drive loops over the qr_regions buffer without sufficient validation. This series fixes two issues: - Patch 1 adds a bounds check to reject messages where qr_numregions exceeds O2NM_MAX_REGIONS. The o2net layer only validates message byte length; it does not constrain field values, so a crafted message can set qr_numregions up to 255 and trigger out-of-bounds reads past the 1024-byte qr_regions buffer. - Patch 2 fixes an off-by-one in the local-vs-remote comparison loop, which uses '<=' instead of '<', reading one entry past the valid range even when qr_numregions is within bounds. This patch (of 2): The qr_numregions field from a DLM_QUERY_REGION network message is used directly as loop bounds in dlm_match_regions() without checking against O2NM_MAX_REGIONS. Since qr_regions is sized for at most O2NM_MAX_REGIONS (32) entries, a crafted message with qr_numregions > 32 causes out-of-bounds reads past the qr_regions buffer. Add a bounds check for qr_numregions before entering the loops. Link: https://lkml.kernel.org/r/SYBPR01MB7881A334D02ACEE5E0645801AF7BA@SYBPR01MB7881.ausprd01.prod.outlook.com Link: https://lkml.kernel.org/r/SYBPR01MB788166F524AD04E262E174BEAF7BA@SYBPR01MB7881.ausprd01.prod.outlook.com Fixes: ea2034416b54 ("ocfs2/dlm: Add message DLM_QUERY_REGION") Signed-off-by: Junrui Luo Reported-by: Yuhao Jiang Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Jun Piao Cc: Heming Zhao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/dlm/dlmdomain.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 2347a50f079b7..f159785a21116 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -980,6 +980,14 @@ static int dlm_match_regions(struct dlm_ctxt *dlm, goto bail; } + if (qr->qr_numregions > O2NM_MAX_REGIONS) { + mlog(ML_ERROR, "Domain %s: Joining node %d has invalid " + "number of heartbeat regions %u\n", + qr->qr_domain, qr->qr_node, qr->qr_numregions); + status = -EINVAL; + goto bail; + } + r = remote; for (i = 0; i < qr->qr_numregions; ++i) { mlog(0, "Region %.*s\n", O2HB_MAX_REGION_NAME_LEN, r); From 1fb7f356547d9688822315cd2b205ff0bd5429b4 Mon Sep 17 00:00:00 2001 From: Junrui Luo Date: Sat, 7 Mar 2026 15:21:09 +0800 Subject: [PATCH 0613/1518] ocfs2/dlm: fix off-by-one in dlm_match_regions() region comparison [ Upstream commit 01b61e8dda9b0fdb0d4cda43de25f4e390554d7b ] The local-vs-remote region comparison loop uses '<=' instead of '<', causing it to read one entry past the valid range of qr_regions. The other loops in the same function correctly use '<'. Fix the loop condition to use '<' for consistency and correctness. Link: https://lkml.kernel.org/r/SYBPR01MB78813DA26B50EC5E01F00566AF7BA@SYBPR01MB7881.ausprd01.prod.outlook.com Fixes: ea2034416b54 ("ocfs2/dlm: Add message DLM_QUERY_REGION") Signed-off-by: Junrui Luo Reported-by: Yuhao Jiang Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Jun Piao Cc: Heming Zhao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/dlm/dlmdomain.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index f159785a21116..09bee7b86815e 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1002,7 +1002,7 @@ static int dlm_match_regions(struct dlm_ctxt *dlm, for (i = 0; i < localnr; ++i) { foundit = 0; r = remote; - for (j = 0; j <= qr->qr_numregions; ++j) { + for (j = 0; j < qr->qr_numregions; ++j) { if (!memcmp(l, r, O2HB_MAX_REGION_NAME_LEN)) { foundit = 1; break; From 611d9e46bdc6c0d6c005a13643ef185873b6a9fb Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Mon, 30 Mar 2026 02:51:11 -0700 Subject: [PATCH 0614/1518] soc: qcom: llcc: fix v1 SB syndrome register offset [ Upstream commit 24e7625df5ce065393249b78930781be593bc381 ] The llcc_v1_edac_reg_offset table uses 0x2304c for trp_ecc_sb_err_syn0, which is inconsistent with the surrounding TRP ECC registers (0x2034x) and with llcc_v2_1_edac_reg_offset, where trp_ecc_sb_err_syn0 is 0x2034c adjacent to trp_ecc_error_status0/1 at 0x20344/0x20348. Use 0x2034c for llcc v1 so the SB syndrome register follows the expected +0x4 progression from trp_ecc_error_status1. This fixes EDAC reading the wrong register for SB syndrome reporting. Fixes: c13d7d261e36 ("soc: qcom: llcc: Pass LLCC version based register offsets to EDAC driver") Signed-off-by: Alok Tiwari Reviewed-by: Manivannan Sadhasivam Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260330095118.2657362-1-alok.a.tiwari@oracle.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/llcc-qcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 857ead56b37d0..d5ce09d6115f0 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -3394,7 +3394,7 @@ static const struct llcc_slice_config x1e80100_data[] = { static const struct llcc_edac_reg_offset llcc_v1_edac_reg_offset = { .trp_ecc_error_status0 = 0x20344, .trp_ecc_error_status1 = 0x20348, - .trp_ecc_sb_err_syn0 = 0x2304c, + .trp_ecc_sb_err_syn0 = 0x2034c, .trp_ecc_db_err_syn0 = 0x20370, .trp_ecc_error_cntr_clear = 0x20440, .trp_interrupt_0_status = 0x20480, From 9dd9d748c5a09584ba0470f4e88cf635051659ef Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Sun, 29 Mar 2026 12:53:23 -0700 Subject: [PATCH 0615/1518] soc: qcom: aoss: compare against normalized cooling state [ Upstream commit cd3c4670db3ffe997be9548c7a9db3952563cf14 ] qmp_cdev_set_cur_state() normalizes the requested state to a boolean (cdev_state = !!state). The existing early-return check compares qmp_cdev->state == state, which can be wrong if state is non-boolean (any non-zero value). Compare qmp_cdev->state against cdev_state instead, so the check matches the effective state and avoids redundant updates. Signed-off-by: Alok Tiwari Fixes: 05589b30b21a ("soc: qcom: Extend AOSS QMP driver to support resources that are used to wake up the SoC.") Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260329195333.1478090-1-alok.a.tiwari@oracle.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/qcom_aoss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c index a543ab9bee6c4..c255662b8fc3d 100644 --- a/drivers/soc/qcom/qcom_aoss.c +++ b/drivers/soc/qcom/qcom_aoss.c @@ -355,7 +355,7 @@ static int qmp_cdev_set_cur_state(struct thermal_cooling_device *cdev, /* Normalize state */ cdev_state = !!state; - if (qmp_cdev->state == state) + if (qmp_cdev->state == cdev_state) return 0; ret = qmp_send(qmp_cdev->qmp, "{class: volt_flr, event:zero_temp, res:%s, value:%s}", From 42fbb173e855e592e86cf311cbf08570a25167ed Mon Sep 17 00:00:00 2001 From: Alexander Koskovich Date: Sun, 8 Mar 2026 04:26:37 +0000 Subject: [PATCH 0616/1518] arm64: dts: qcom: sm8250: Add missing CPU7 3.09GHz OPP [ Upstream commit b683730e27ba4f91986c4c92f5cb7297f1e01a6d ] This resolves the following error seen on the ASUS ROG Phone 3: cpu cpu7: Voltage update failed freq=3091200 cpu cpu7: failed to update OPP for freq=3091200 Fixes: 8e0e8016cb79 ("arm64: dts: qcom: sm8250: Add CPU opp tables") Signed-off-by: Alexander Koskovich Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260307-sm8250-cpu7-opp-v1-1-435f5f6628a1@pm.me Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8250.dtsi | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 50dd11432bb2e..adf6b49b52c48 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -665,6 +665,11 @@ opp-hz = /bits/ 64 <2841600000>; opp-peak-kBps = <8368000 51609600>; }; + + cpu7_opp21: opp-3091200000 { + opp-hz = /bits/ 64 <3091200000>; + opp-peak-kBps = <8368000 51609600>; + }; }; firmware { From 8f466be889a2959b159513b84beca2d00b90064b Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Fri, 27 Mar 2026 19:15:10 +0200 Subject: [PATCH 0617/1518] ARM: OMAP1: Fix DEBUG_LL and earlyprintk on OMAP16XX [ Upstream commit 7e74b606dd39c46d4378d6f6563f560a00ab8694 ] On OMAP16XX, the UART enable bit shifts are written instead of the actual bits. This breaks the boot when DEBUG_LL and earlyprintk is enabled; the UART gets disabled and some random bits get enabled. Fix that. Fixes: 34c86239b184 ("ARM: OMAP1: clock: Fix early UART rate issues") Signed-off-by: Aaro Koskinen Link: https://patch.msgid.link/aca7HnXZ-aCSJPW7@darkstar.musicnaut.iki.fi Signed-off-by: Kevin Hilman Signed-off-by: Sasha Levin --- arch/arm/mach-omap1/clock_data.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c index c58d200e4816b..5203b047deac8 100644 --- a/arch/arm/mach-omap1/clock_data.c +++ b/arch/arm/mach-omap1/clock_data.c @@ -700,8 +700,8 @@ int __init omap1_clk_init(void) /* Make sure UART clocks are enabled early */ if (cpu_is_omap16xx()) omap_writel(omap_readl(MOD_CONF_CTRL_0) | - CONF_MOD_UART1_CLK_MODE_R | - CONF_MOD_UART3_CLK_MODE_R, MOD_CONF_CTRL_0); + (1 << CONF_MOD_UART1_CLK_MODE_R) | + (1 << CONF_MOD_UART3_CLK_MODE_R), MOD_CONF_CTRL_0); #endif /* USB_REQ_EN will be disabled later if necessary (usb_dc_ck) */ From 9777d7e6fc58795707dba6b9238cdb95b96144e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Mar 2026 07:16:35 +0100 Subject: [PATCH 0618/1518] arm64/xor: fix conflicting attributes for xor_block_template [ Upstream commit 675a0dd596e712404557286d0a883b54ee28e4f4 ] Commit 2c54b423cf85 ("arm64/xor: use EOR3 instructions when available") changes the definition to __ro_after_init instead of const, but failed to update the external declaration in xor.h. This was not found because xor-neon.c doesn't include , and can't easily do that due to current architecture of the XOR code. Link: https://lkml.kernel.org/r/20260327061704.3707577-4-hch@lst.de Fixes: 2c54b423cf85 ("arm64/xor: use EOR3 instructions when available") Signed-off-by: Christoph Hellwig Reviewed-by: Eric Biggers Tested-by: Eric Biggers Cc: Albert Ou Cc: Alexander Gordeev Cc: Alexandre Ghiti Cc: Andreas Larsson Cc: Anton Ivanov Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: "Borislav Petkov (AMD)" Cc: Catalin Marinas Cc: Chris Mason Cc: Christian Borntraeger Cc: Dan Williams Cc: David S. Miller Cc: David Sterba Cc: Heiko Carstens Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Jason A. Donenfeld Cc: Johannes Berg Cc: Li Nan Cc: Madhavan Srinivasan Cc: Magnus Lindholm Cc: Matt Turner Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Richard Henderson Cc: Richard Weinberger Cc: Russell King Cc: Song Liu Cc: Sven Schnelle Cc: Ted Ts'o Cc: Vasily Gorbik Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- arch/arm64/include/asm/xor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h index befcd8a7abc98..7c03207157196 100644 --- a/arch/arm64/include/asm/xor.h +++ b/arch/arm64/include/asm/xor.h @@ -13,7 +13,7 @@ #ifdef CONFIG_KERNEL_MODE_NEON -extern struct xor_block_template const xor_block_inner_neon; +extern struct xor_block_template xor_block_inner_neon __ro_after_init; static void xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, From 3bf5e19c804d0b03f2293a12cac9a3f556c68229 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 3 Dec 2025 15:30:31 -0800 Subject: [PATCH 0619/1518] slab: Introduce kmalloc_obj() and family [ Upstream commit 2932ba8d9c99875b98c951d9d3fd6d651d35df3a ] Introduce type-aware kmalloc-family helpers to replace the common idioms for single object and arrays of objects allocation: ptr = kmalloc(sizeof(*ptr), gfp); ptr = kmalloc(sizeof(struct some_obj_name), gfp); ptr = kzalloc(sizeof(*ptr), gfp); ptr = kmalloc_array(count, sizeof(*ptr), gfp); ptr = kcalloc(count, sizeof(*ptr), gfp); These become, respectively: ptr = kmalloc_obj(*ptr, gfp); ptr = kmalloc_obj(*ptr, gfp); ptr = kzalloc_obj(*ptr, gfp); ptr = kmalloc_objs(*ptr, count, gfp); ptr = kzalloc_objs(*ptr, count, gfp); Beyond the other benefits outlined below, the primary ergonomic benefit is the elimination of needing "sizeof" nor the type name, and the enforcement of assignment types (they do not return "void *", but rather a pointer to the type of the first argument). The type name _can_ be used, though, in the case where an assignment is indirect (e.g. via "return"). This additionally allows[1] variables to be declared via __auto_type: __auto_type ptr = kmalloc_obj(struct foo, gfp); Internal introspection of the allocated type now becomes possible, allowing for future alignment-aware choices to be made by the allocator and future hardening work that can be type sensitive. For example, adding __alignof(*ptr) as an argument to the internal allocators so that appropriate/efficient alignment choices can be made, or being able to correctly choose per-allocation offset randomization within a bucket that does not break alignment requirements. Link: https://lore.kernel.org/all/CAHk-=wiCOTW5UftUrAnvJkr6769D29tF7Of79gUjdQHS_TkF5A@mail.gmail.com/ [1] Acked-by: Vlastimil Babka Link: https://patch.msgid.link/20251203233036.3212363-1-kees@kernel.org Signed-off-by: Kees Cook Stable-dep-of: 0b49c7d0ae69 ("lib: kunit_iov_iter: fix memory leaks") Signed-off-by: Sasha Levin --- Documentation/process/deprecated.rst | 24 ++++++++++++ include/linux/slab.h | 58 ++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+) diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 1f7f3e6c9cda9..91c628fa2d59c 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -372,3 +372,27 @@ The helper must be used:: DECLARE_FLEX_ARRAY(struct type2, two); }; }; + +Open-coded kmalloc assignments for struct objects +------------------------------------------------- +Performing open-coded kmalloc()-family allocation assignments prevents +the kernel (and compiler) from being able to examine the type of the +variable being assigned, which limits any related introspection that +may help with alignment, wrap-around, or additional hardening. The +kmalloc_obj()-family of macros provide this introspection, which can be +used for the common code patterns for single, array, and flexible object +allocations. For example, these open coded assignments:: + + ptr = kmalloc(sizeof(*ptr), gfp); + ptr = kzalloc(sizeof(*ptr), gfp); + ptr = kmalloc_array(count, sizeof(*ptr), gfp); + ptr = kcalloc(count, sizeof(*ptr), gfp); + ptr = kmalloc(sizeof(struct foo, gfp); + +become, respectively:: + + ptr = kmalloc_obj(*ptr, gfp); + ptr = kzalloc_obj(*ptr, gfp); + ptr = kmalloc_objs(*ptr, count, gfp); + ptr = kzalloc_objs(*ptr, count, gfp); + __auto_type ptr = kmalloc_obj(struct foo, gfp); diff --git a/include/linux/slab.h b/include/linux/slab.h index 2482992248dc9..cbb64a2698f5d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -12,6 +12,7 @@ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H +#include #include #include #include @@ -965,6 +966,63 @@ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t f void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); #define kmalloc_nolock(...) alloc_hooks(kmalloc_nolock_noprof(__VA_ARGS__)) +/** + * __alloc_objs - Allocate objects of a given type using + * @KMALLOC: which size-based kmalloc wrapper to allocate with. + * @GFP: GFP flags for the allocation. + * @TYPE: type to allocate space for. + * @COUNT: how many @TYPE objects to allocate. + * + * Returns: Newly allocated pointer to (first) @TYPE of @COUNT-many + * allocated @TYPE objects, or NULL on failure. + */ +#define __alloc_objs(KMALLOC, GFP, TYPE, COUNT) \ +({ \ + const size_t __obj_size = size_mul(sizeof(TYPE), COUNT); \ + (TYPE *)KMALLOC(__obj_size, GFP); \ +}) + +/** + * kmalloc_obj - Allocate a single instance of the given type + * @VAR_OR_TYPE: Variable or type to allocate. + * @GFP: GFP flags for the allocation. + * + * Returns: newly allocated pointer to a @VAR_OR_TYPE on success, or NULL + * on failure. + */ +#define kmalloc_obj(VAR_OR_TYPE, GFP) \ + __alloc_objs(kmalloc, GFP, typeof(VAR_OR_TYPE), 1) + +/** + * kmalloc_objs - Allocate an array of the given type + * @VAR_OR_TYPE: Variable or type to allocate an array of. + * @COUNT: How many elements in the array. + * @GFP: GFP flags for the allocation. + * + * Returns: newly allocated pointer to array of @VAR_OR_TYPE on success, + * or NULL on failure. + */ +#define kmalloc_objs(VAR_OR_TYPE, COUNT, GFP) \ + __alloc_objs(kmalloc, GFP, typeof(VAR_OR_TYPE), COUNT) + +/* All kzalloc aliases for kmalloc_(obj|objs|flex). */ +#define kzalloc_obj(P, GFP) \ + __alloc_objs(kzalloc, GFP, typeof(P), 1) +#define kzalloc_objs(P, COUNT, GFP) \ + __alloc_objs(kzalloc, GFP, typeof(P), COUNT) + +/* All kvmalloc aliases for kmalloc_(obj|objs|flex). */ +#define kvmalloc_obj(P, GFP) \ + __alloc_objs(kvmalloc, GFP, typeof(P), 1) +#define kvmalloc_objs(P, COUNT, GFP) \ + __alloc_objs(kvmalloc, GFP, typeof(P), COUNT) + +/* All kvzalloc aliases for kmalloc_(obj|objs|flex). */ +#define kvzalloc_obj(P, GFP) \ + __alloc_objs(kvzalloc, GFP, typeof(P), 1) +#define kvzalloc_objs(P, COUNT, GFP) \ + __alloc_objs(kvzalloc, GFP, typeof(P), COUNT) + #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) From 6eab9741965b21bba4ad4b460e2ff91487e9b5eb Mon Sep 17 00:00:00 2001 From: "Christian A. Ehrhardt" Date: Thu, 26 Mar 2026 22:49:03 +0100 Subject: [PATCH 0620/1518] lib: kunit_iov_iter: fix memory leaks [ Upstream commit 0b49c7d0ae697fcecd7377cb7dda220f7cd096ff ] Use vfree() instead of vunmap() to free the buffer allocated by iov_kunit_create_buffer() because vunmap() does not honour VM_MAP_PUT_PAGES. In order for this to work the page array itself must not be managed by kunit. Remove the folio_put() when destroying a folioq. This is handled by vfree(), now. Pointed out by sashiko.dev on a previous iteration of this series. Tested by running the kunit test 10000 times in a loop. Link: https://lkml.kernel.org/r/20260326214905.818170-4-lk@c--e.de Fixes: 2d71340ff1d4 ("iov_iter: Kunit tests for copying to/from an iterator") Signed-off-by: Christian A. Ehrhardt Cc: David Howells Cc: David Gow Cc: Kees Cook Cc: Petr Mladek Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- lib/tests/kunit_iov_iter.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/lib/tests/kunit_iov_iter.c b/lib/tests/kunit_iov_iter.c index 48342736d0164..43e63bf4c0956 100644 --- a/lib/tests/kunit_iov_iter.c +++ b/lib/tests/kunit_iov_iter.c @@ -42,7 +42,7 @@ static inline u8 pattern(unsigned long x) static void iov_kunit_unmap(void *data) { - vunmap(data); + vfree(data); } static void *__init iov_kunit_create_buffer(struct kunit *test, @@ -53,17 +53,22 @@ static void *__init iov_kunit_create_buffer(struct kunit *test, unsigned long got; void *buffer; - pages = kunit_kcalloc(test, npages, sizeof(struct page *), GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages); + pages = kzalloc_objs(struct page *, npages, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages); *ppages = pages; got = alloc_pages_bulk(GFP_KERNEL, npages, pages); if (got != npages) { release_pages(pages, got); + kvfree(pages); KUNIT_ASSERT_EQ(test, got, npages); } buffer = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL); + if (buffer == NULL) { + release_pages(pages, got); + kvfree(pages); + } KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buffer); kunit_add_action_or_reset(test, iov_kunit_unmap, buffer); @@ -369,9 +374,6 @@ static void iov_kunit_destroy_folioq(void *data) for (folioq = data; folioq; folioq = next) { next = folioq->next; - for (int i = 0; i < folioq_nr_slots(folioq); i++) - if (folioq_folio(folioq, i)) - folio_put(folioq_folio(folioq, i)); kfree(folioq); } } From 28a547af44323c8da7ffb9427664181e03b373c2 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Wed, 11 Feb 2026 18:12:55 -0500 Subject: [PATCH 0621/1518] ARM: dts: imx27-eukrea: replace interrupts with interrupts-extended [ Upstream commit 0477a6b31e2874e554e3bcfac9883684b8f8ca2d ] The property interrupts use default interrupt controllers. But pass down gpio as phandle. Correct it by use interrupts-extended. Fixes: d8cae888aa2bc ("ARM: dts: Add support for the cpuimx27 board from Eukrea and its baseboard") Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi | 8 ++++---- .../boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi index c7e9235848782..9f0e65526d5f9 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi @@ -106,7 +106,7 @@ compatible = "ns8250"; clocks = <&clk14745600>; fsl,weim-cs-timing = <0x0000d603 0x0d1d0d01 0x00d20000>; - interrupts = <&gpio2 23 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 23 IRQ_TYPE_LEVEL_LOW>; reg = <3 0x200000 0x1000>; reg-shift = <1>; reg-io-width = <1>; @@ -119,7 +119,7 @@ compatible = "ns8250"; clocks = <&clk14745600>; fsl,weim-cs-timing = <0x0000d603 0x0d1d0d01 0x00d20000>; - interrupts = <&gpio2 22 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 22 IRQ_TYPE_LEVEL_LOW>; reg = <3 0x400000 0x1000>; reg-shift = <1>; reg-io-width = <1>; @@ -132,7 +132,7 @@ compatible = "ns8250"; clocks = <&clk14745600>; fsl,weim-cs-timing = <0x0000d603 0x0d1d0d01 0x00d20000>; - interrupts = <&gpio2 27 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 27 IRQ_TYPE_LEVEL_LOW>; reg = <3 0x800000 0x1000>; reg-shift = <1>; reg-io-width = <1>; @@ -145,7 +145,7 @@ compatible = "ns8250"; clocks = <&clk14745600>; fsl,weim-cs-timing = <0x0000d603 0x0d1d0d01 0x00d20000>; - interrupts = <&gpio2 30 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 30 IRQ_TYPE_LEVEL_LOW>; reg = <3 0x1000000 0x1000>; reg-shift = <1>; reg-io-width = <1>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts index d78793601306c..c71f802983304 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts +++ b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts @@ -76,7 +76,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_touch>; reg = <0>; - interrupts = <&gpio4 25 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio4 25 IRQ_TYPE_LEVEL_LOW>; spi-cpol; spi-max-frequency = <1500000>; ti,keep-vref-on; From a3879c708a60a662b0847ddc5fe527a0d7bc40d9 Mon Sep 17 00:00:00 2001 From: Sebastian Ene Date: Thu, 2 Apr 2026 11:39:39 +0000 Subject: [PATCH 0622/1518] firmware: arm_ffa: Use the correct buffer size during RXTX_MAP [ Upstream commit 83210251fd70d5f96bcdc8911e15f7411a6b2463 ] Don't use the discovered buffer size from an FFA_FEATURES call directly since we can run on a system that has the PAGE_SIZE larger than the returned size which makes the alloc_pages_exact for the buffer to be rounded up. Fixes: 61824feae5c0 ("firmware: arm_ffa: Fetch the Rx/Tx buffer size using ffa_features()") Signed-off-by: Sebastian Ene Link: https://patch.msgid.link/20260402113939.930221-1-sebastianene@google.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index f6ceae987acbc..d71a2ef335d1c 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -2074,7 +2074,7 @@ static int __init ffa_init(void) ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), virt_to_phys(drv_info->rx_buffer), - rxtx_bufsz / FFA_PAGE_SIZE); + PAGE_ALIGN(rxtx_bufsz) / FFA_PAGE_SIZE); if (ret) { pr_err("failed to register FFA RxTx buffers\n"); goto free_pages; From a28f56988c8e5bb9375806a5cfb0bf54d662ae3f Mon Sep 17 00:00:00 2001 From: Richard Cheng Date: Thu, 9 Apr 2026 13:19:02 +0800 Subject: [PATCH 0623/1518] fwctl: Fix class init ordering to avoid NULL pointer dereference on device removal [ Upstream commit a55f80233f384dc89ef3425b2e1dd0e6d44bcf29 ] CXL is linked before fwctl in drivers/Makefile. Both use `module_init, so `cxl_pci_driver_init()` runs first. When `cxl_pci_probe()` calls `fwctl_register()` and then `device_add()`, fwctl_class is not yet registered because fwctl_init() hasn't run, causing `class_to_subsys()` to return NULL and skip knode_class initialization. On device removal, `class_to_subsys()` returns non-NULL, and `device_del()` calls `klist_del()` on the uninitialized knode, triggering a NULL pointer dereference. Fixes: 858ce2f56b52 ("cxl: Add FWCTL support to CXL") Link: https://patch.msgid.link/r/20260409051902.40218-1-icheng@nvidia.com Signed-off-by: Richard Cheng Reviewed-by: Kai-Heng Feng Reviewed-by: Dave Jiang Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/fwctl/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/fwctl/main.c b/drivers/fwctl/main.c index bc6378506296c..098c3824ad751 100644 --- a/drivers/fwctl/main.c +++ b/drivers/fwctl/main.c @@ -415,7 +415,7 @@ static void __exit fwctl_exit(void) unregister_chrdev_region(fwctl_dev, FWCTL_MAX_DEVICES); } -module_init(fwctl_init); +subsys_initcall(fwctl_init); module_exit(fwctl_exit); MODULE_DESCRIPTION("fwctl device firmware access framework"); MODULE_LICENSE("GPL"); From 2685df8577a38d83b367c8cf52eda9dc286959ff Mon Sep 17 00:00:00 2001 From: ZhengYuan Huang Date: Fri, 10 Apr 2026 12:03:39 +0800 Subject: [PATCH 0624/1518] ocfs2: fix listxattr handling when the buffer is full [ Upstream commit d12f558e6200b3f47dbef9331ed6d115d2410e59 ] [BUG] If an OCFS2 inode has both inline and block-based xattrs, listxattr() can return a size larger than the caller's buffer when the inline names consume that buffer exactly. kernel BUG at mm/usercopy.c:102! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:usercopy_abort+0xb7/0xd0 mm/usercopy.c:102 Call Trace: __check_heap_object+0xe3/0x120 mm/slub.c:8243 check_heap_object mm/usercopy.c:196 [inline] __check_object_size mm/usercopy.c:250 [inline] __check_object_size+0x5c5/0x780 mm/usercopy.c:215 check_object_size include/linux/ucopysize.h:22 [inline] check_copy_size include/linux/ucopysize.h:59 [inline] copy_to_user include/linux/uaccess.h:219 [inline] listxattr+0xb0/0x170 fs/xattr.c:926 filename_listxattr fs/xattr.c:958 [inline] path_listxattrat+0x137/0x320 fs/xattr.c:988 __do_sys_listxattr fs/xattr.c:1001 [inline] __se_sys_listxattr fs/xattr.c:998 [inline] __x64_sys_listxattr+0x7f/0xd0 fs/xattr.c:998 ... [CAUSE] Commit 936b8834366e ("ocfs2: Refactor xattr list and remove ocfs2_xattr_handler().") replaced the old per-handler list accounting with ocfs2_xattr_list_entry(), but it kept using size == 0 to detect probe mode. That assumption stops being true once ocfs2_listxattr() finishes the inline-xattr pass. If the inline names fill the caller buffer exactly, the block-xattr pass runs with a non-NULL buffer and a remaining size of zero. ocfs2_xattr_list_entry() then skips the bounds check, keeps counting block names, and returns a positive size larger than the supplied buffer. [FIX] Detect probe mode by testing whether the destination buffer pointer is NULL instead of whether the remaining size is zero. That restores the pre-refactor behavior and matches the OCFS2 getxattr helpers. Once the remaining buffer reaches zero while more names are left, the block-xattr pass now returns -ERANGE instead of reporting a size larger than the allocated list buffer. Link: https://lkml.kernel.org/r/20260410040339.3837162-1-gality369@gmail.com Fixes: 936b8834366e ("ocfs2: Refactor xattr list and remove ocfs2_xattr_handler().") Signed-off-by: ZhengYuan Huang Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Jun Piao Cc: Heming Zhao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/xattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 64ba3946f8408..8f7018bad283b 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -907,8 +907,8 @@ static int ocfs2_xattr_list_entry(struct super_block *sb, total_len = prefix_len + name_len + 1; *result += total_len; - /* we are just looking for how big our buffer needs to be */ - if (!size) + /* No buffer means we are only looking for the required size. */ + if (!buffer) return 0; if (*result > size) From 4c2d62ddde8928db12f4608950b67a20e67deab2 Mon Sep 17 00:00:00 2001 From: ZhengYuan Huang Date: Fri, 10 Apr 2026 11:42:20 +0800 Subject: [PATCH 0625/1518] ocfs2: validate bg_bits during freefrag scan [ Upstream commit 8f687eeed3da3012152b0f9473f578869de0cd7b ] [BUG] A crafted filesystem can trigger an out-of-bounds bitmap walk when OCFS2_IOC_INFO is issued with OCFS2_INFO_FL_NON_COHERENT. BUG: KASAN: use-after-free in instrument_atomic_read include/linux/instrumented.h:68 [inline] BUG: KASAN: use-after-free in _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline] BUG: KASAN: use-after-free in test_bit_le include/asm-generic/bitops/le.h:21 [inline] BUG: KASAN: use-after-free in ocfs2_info_freefrag_scan_chain fs/ocfs2/ioctl.c:495 [inline] BUG: KASAN: use-after-free in ocfs2_info_freefrag_scan_bitmap fs/ocfs2/ioctl.c:588 [inline] BUG: KASAN: use-after-free in ocfs2_info_handle_freefrag fs/ocfs2/ioctl.c:662 [inline] BUG: KASAN: use-after-free in ocfs2_info_handle_request+0x1c66/0x3370 fs/ocfs2/ioctl.c:754 Read of size 8 at addr ffff888031bce000 by task syz.0.636/1435 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xbe/0x130 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xd1/0x650 mm/kasan/report.c:482 kasan_report+0xfb/0x140 mm/kasan/report.c:595 check_region_inline mm/kasan/generic.c:186 [inline] kasan_check_range+0x11c/0x200 mm/kasan/generic.c:200 __kasan_check_read+0x11/0x20 mm/kasan/shadow.c:31 instrument_atomic_read include/linux/instrumented.h:68 [inline] _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline] test_bit_le include/asm-generic/bitops/le.h:21 [inline] ocfs2_info_freefrag_scan_chain fs/ocfs2/ioctl.c:495 [inline] ocfs2_info_freefrag_scan_bitmap fs/ocfs2/ioctl.c:588 [inline] ocfs2_info_handle_freefrag fs/ocfs2/ioctl.c:662 [inline] ocfs2_info_handle_request+0x1c66/0x3370 fs/ocfs2/ioctl.c:754 ocfs2_info_handle+0x18d/0x2a0 fs/ocfs2/ioctl.c:828 ocfs2_ioctl+0x632/0x6e0 fs/ocfs2/ioctl.c:913 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 ... [CAUSE] ocfs2_info_freefrag_scan_chain() uses on-disk bg_bits directly as the bitmap scan limit. The coherent path reads group descriptors through ocfs2_read_group_descriptor(), which validates the descriptor before use. The non-coherent path uses ocfs2_read_blocks_sync() instead and skips that validation, so an impossible bg_bits value can drive the bitmap walk past the end of the block. [FIX] Compute the bitmap capacity from the filesystem format with ocfs2_group_bitmap_size(), report descriptors whose bg_bits exceeds that limit, and clamp the scan to the computed capacity. This keeps the freefrag report going while avoiding reads beyond the buffer. Link: https://lkml.kernel.org/r/20260410034220.3825769-1-gality369@gmail.com Fixes: d24a10b9f8ed ("Ocfs2: Add a new code 'OCFS2_INFO_FREEFRAG' for o2info ioctl.") Signed-off-by: ZhengYuan Huang Reviewed-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Jun Piao Cc: Heming Zhao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/ioctl.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index b6864602814c4..b004e7117a5f3 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -441,13 +441,16 @@ static int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb, struct buffer_head *bh = NULL; struct ocfs2_group_desc *bg = NULL; - unsigned int max_bits, num_clusters; + unsigned int max_bits, max_bitmap_bits, num_clusters; unsigned int offset = 0, cluster, chunk; unsigned int chunk_free, last_chunksize = 0; if (!le32_to_cpu(rec->c_free)) goto bail; + max_bitmap_bits = 8 * ocfs2_group_bitmap_size(osb->sb, 0, + osb->s_feature_incompat); + do { if (!bg) blkno = le64_to_cpu(rec->c_blkno); @@ -479,6 +482,19 @@ static int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb, continue; max_bits = le16_to_cpu(bg->bg_bits); + + /* + * Non-coherent scans read raw blocks and do not get the + * bg_bits validation from + * ocfs2_read_group_descriptor(). + */ + if (max_bits > max_bitmap_bits) { + mlog(ML_ERROR, + "Group desc #%llu has %u bits, max bitmap bits %u\n", + (unsigned long long)blkno, max_bits, max_bitmap_bits); + max_bits = max_bitmap_bits; + } + offset = 0; for (chunk = 0; chunk < chunks_in_group; chunk++) { From aed87e866d1a321edb9703563c2faa8fec89835d Mon Sep 17 00:00:00 2001 From: ZhengYuan Huang Date: Fri, 10 Apr 2026 10:02:08 +0800 Subject: [PATCH 0626/1518] ocfs2: validate group add input before caching [ Upstream commit 70b672833f4025341c11b22c7f83778a5cd611bc ] [BUG] OCFS2_IOC_GROUP_ADD can trigger a BUG_ON in ocfs2_set_new_buffer_uptodate(): kernel BUG at fs/ocfs2/uptodate.c:509! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:ocfs2_set_new_buffer_uptodate+0x194/0x1e0 fs/ocfs2/uptodate.c:509 Code: ffffe88f 42b9fe4c 89e64889 dfe8b4df Call Trace: ocfs2_group_add+0x3f1/0x1510 fs/ocfs2/resize.c:507 ocfs2_ioctl+0x309/0x6e0 fs/ocfs2/ioctl.c:887 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7bbfb55a966d [CAUSE] ocfs2_group_add() calls ocfs2_set_new_buffer_uptodate() on a user-controlled group block before ocfs2_verify_group_and_input() validates that block number. That helper is only valid for newly allocated metadata and asserts that the block is not already present in the chosen metadata cache. The code also uses INODE_CACHE(inode) even though the group descriptor belongs to main_bm_inode and later journal accesses use that cache context instead. [FIX] Validate the on-disk group descriptor before caching it, then add it to the metadata cache tracked by INODE_CACHE(main_bm_inode). Keep the validation failure path separate from the later cleanup path so we only remove the buffer from that cache after it has actually been inserted. This keeps the group buffer lifetime consistent across validation, journaling, and cleanup. Link: https://lkml.kernel.org/r/20260410020209.3786348-1-gality369@gmail.com Fixes: 7909f2bf8353 ("[PATCH 2/2] ocfs2: Implement group add for online resize") Signed-off-by: ZhengYuan Huang Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Jun Piao Cc: Heming Zhao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/resize.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index ed7ed15ad9a73..583a411557ab9 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -508,14 +508,14 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) goto out_unlock; } - ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), group_bh); - ret = ocfs2_verify_group_and_input(main_bm_inode, fe, input, group_bh); if (ret) { mlog_errno(ret); goto out_free_group_bh; } + ocfs2_set_new_buffer_uptodate(INODE_CACHE(main_bm_inode), group_bh); + trace_ocfs2_group_add((unsigned long long)input->group, input->chain, input->clusters, input->frees); @@ -523,7 +523,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) if (IS_ERR(handle)) { mlog_errno(PTR_ERR(handle)); ret = -EINVAL; - goto out_free_group_bh; + goto out_remove_cache; } cl_bpc = le16_to_cpu(fe->id2.i_chain.cl_bpc); @@ -577,9 +577,11 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) out_commit: ocfs2_commit_trans(osb, handle); -out_free_group_bh: +out_remove_cache: if (ret < 0) - ocfs2_remove_from_cache(INODE_CACHE(inode), group_bh); + ocfs2_remove_from_cache(INODE_CACHE(main_bm_inode), group_bh); + +out_free_group_bh: brelse(group_bh); out_unlock: From 8cedbb75f70eb7aef4d10ec089407f403ff6a655 Mon Sep 17 00:00:00 2001 From: Khairul Anuar Romli Date: Mon, 2 Feb 2026 14:02:19 +0800 Subject: [PATCH 0627/1518] dmaengine: dw-axi-dmac: Remove unnecessary return statement from void function [ Upstream commit 48278a72fce8a8d30efaedeb206c9c3f05c1eb3f ] checkpatch.pl --strict reports a WARNING in dw-axi-dmac-platform.c: WARNING: void function return statements are not generally useful FILE: drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c According to Linux kernel coding style [Documentation/process/ coding-style.rst], explicit "return;" statements at the end of void functions are redundant and should be omitted. The function will automatically return upon reaching the closing brace, so the extra statement adds unnecessary clutter without functional benefit. This patch removes the superfluous "return;" statement in dw_axi_dma_set_hw_channel() to comply with kernel coding standards and eliminate the checkpatch warning. Fixes: 32286e279385 ("dmaengine: dw-axi-dmac: Remove free slot check algorithm in dw_axi_dma_set_hw_channel") Signed-off-by: Khairul Anuar Romli Link: https://patch.msgid.link/20260202060224.12616-4-karom.9560@gmail.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index b23536645ff7c..b0e689f48bb67 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -592,8 +592,6 @@ static void dw_axi_dma_set_hw_channel(struct axi_dma_chan *chan, bool set) (chan->id * DMA_APB_HS_SEL_BIT_SIZE)); reg_value |= (val << (chan->id * DMA_APB_HS_SEL_BIT_SIZE)); lo_hi_writeq(reg_value, chip->apb_regs + DMAC_APB_HW_HS_SEL_0); - - return; } /* From 03d56c4c3861dcfe741bb82e13750604b0f25867 Mon Sep 17 00:00:00 2001 From: Cole Leavitt Date: Wed, 18 Feb 2026 11:02:10 -0700 Subject: [PATCH 0628/1518] soundwire: bus: demote UNATTACHED state warnings to dev_dbg() [ Upstream commit 2c96956fe764f8224f9ec93b2a9160a578949a7a ] The dev_warn() messages in sdw_handle_slave_status() for UNATTACHED transitions were added in commit d1b328557058 ("soundwire: bus: add dev_warn() messages to track UNATTACHED devices") to debug attachment failures with dynamic debug enabled. These warnings fire during normal operation -- for example when a codec driver triggers a hardware reset after firmware download, causing the device to momentarily go UNATTACHED before re-attaching -- producing misleading noise on every boot. Demote the messages to dev_dbg() so they remain available via dynamic debug for diagnosing real attachment failures without alarming users during expected initialization sequences. Fixes: d1b328557058 ("soundwire: bus: add dev_warn() messages to track UNATTACHED devices") Signed-off-by: Cole Leavitt Reviewed-by: Richard Fitzgerald Link: https://patch.msgid.link/20260218180210.9263-1-cole@unwrap.rs Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/soundwire/bus.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 55c1db8165340..14e1351a3f8ae 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -1899,8 +1899,8 @@ int sdw_handle_slave_status(struct sdw_bus *bus, if (status[i] == SDW_SLAVE_UNATTACHED && slave->status != SDW_SLAVE_UNATTACHED) { - dev_warn(&slave->dev, "Slave %d state check1: UNATTACHED, status was %d\n", - i, slave->status); + dev_dbg(&slave->dev, "Slave %d state check1: UNATTACHED, status was %d\n", + i, slave->status); sdw_modify_slave_status(slave, SDW_SLAVE_UNATTACHED); /* Ensure driver knows that peripheral unattached */ @@ -1951,8 +1951,8 @@ int sdw_handle_slave_status(struct sdw_bus *bus, if (slave->status == SDW_SLAVE_UNATTACHED) break; - dev_warn(&slave->dev, "Slave %d state check2: UNATTACHED, status was %d\n", - i, slave->status); + dev_dbg(&slave->dev, "Slave %d state check2: UNATTACHED, status was %d\n", + i, slave->status); sdw_modify_slave_status(slave, SDW_SLAVE_UNATTACHED); break; From 4cafee50af44bb87b32c98770ec722afc4793fa2 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Mon, 26 Jan 2026 13:40:45 +0800 Subject: [PATCH 0629/1518] soundwire: Intel: test bus.bpt_stream before assigning it [ Upstream commit b2c9f1d5a7eb50bcdda607afef1378e552bbb490 ] We only allow up to 1 bpt stream running on a SoundWire bus. bus.bpt_stream will be assigned when it is opened and will be set to NULL when it is closed. We do check bus->bpt_stream_refcount if the stream type is SDW_STREAM_BPT in sdw_master_rt_alloc(), but at that moment the bpt stream is allocated and set to bus.bpt_stream. It will lead to the original bus.bpt_stream be changed to the new and not used bpt stream. And it will be released and set to NULL when sdw_slave_bpt_stream_add() return error as it supposed to. Then the original stream will try to use the NULL bus.bpt_stream. Fixes: 4c1ce9f37d8a ("soundwire: intel_ace2x: add BPT send_async/wait callbacks") Reported-by: Simon Trimmer Signed-off-by: Bard Liao Reviewed-by: Simon Trimmer Reviewed-by: Ranjani Sridharan Link: https://patch.msgid.link/20260126054045.2504103-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/soundwire/intel_ace2x.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c index 5d08364ad6d14..5b73bbb73be6e 100644 --- a/drivers/soundwire/intel_ace2x.c +++ b/drivers/soundwire/intel_ace2x.c @@ -68,6 +68,11 @@ static int intel_ace2x_bpt_open_stream(struct sdw_intel *sdw, struct sdw_slave * int dir; int i; + if (cdns->bus.bpt_stream) { + dev_err(cdns->dev, "%s: BPT stream already exists\n", __func__); + return -EAGAIN; + } + stream = sdw_alloc_stream("BPT", SDW_STREAM_BPT); if (!stream) return -ENOMEM; From 8995ef2dbebc021e076a78032490cfbb36fb8a17 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Wed, 25 Feb 2026 16:41:38 -0500 Subject: [PATCH 0630/1518] dmaengine: mxs-dma: Fix missing return value from of_dma_controller_register() [ Upstream commit ab2bf6d4c0a0152907b18d25c1b118ea5ea779df ] Propagate the return value of of_dma_controller_register() in probe() instead of ignoring it. Fixes: a580b8c5429a6 ("dmaengine: mxs-dma: add dma support for i.MX23/28") Signed-off-by: Frank Li Link: https://patch.msgid.link/20260225-mxsdma-module-v3-2-8f798b13baa6@nxp.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/mxs-dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c index cfb9962417ef6..53f572b6b6fc6 100644 --- a/drivers/dma/mxs-dma.c +++ b/drivers/dma/mxs-dma.c @@ -824,6 +824,7 @@ static int mxs_dma_probe(struct platform_device *pdev) if (ret) { dev_err(mxs_dma->dma_device.dev, "failed to register controller\n"); + return ret; } dev_info(mxs_dma->dma_device.dev, "initialized\n"); From 1e78af7019762329e7e1ac32ddd3b1a78d56ed2f Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 10 Mar 2026 11:31:33 +0000 Subject: [PATCH 0631/1518] soundwire: cadence: Clear message complete before signaling waiting thread [ Upstream commit cbfea84f820962c3c5394ff06e7e9344c96bf761 ] Clear the CDNS_MCP_INT_RX_WL interrupt before signaling completion. This is to prevent the potential race where: - The main thread is scheduled immediately the completion is signaled, and starts a new message - The RX_WL IRQ for this new message happens before sdw_cdns_irq() has been re-scheduled. - When sdw_cdns_irq() is re-scheduled it clears the new RX_WL interrupt. MAIN THREAD | IRQ THREAD | _cdns_xfer_msg() | { | write data to FIFO | wait_for_completion_timeout() | | <---- RX_WL IRQ | sdw_cdns_irq() | { | signal completion <== RESCHEDULE <== Handle message completion | } | | Start new message | _cdns_xfer_msg() | { | write data to FIFO | wait_for_completion_timeout() | | <---- RX_WL IRQ ==> RESCHEDULE ==> | // New RX_WL IRQ is cleared before | // it has been handled. | clear CDNS_MCP_INTSTAT | return IRQ_HANDLED; | } Before this change, this error message was sometimes seen on kernels that have large amounts of debugging enabled: SCP Msg trf timed out This error indicates that the completion has not been signalled after 500ms. Signed-off-by: Richard Fitzgerald Fixes: 956baa1992f9 ("soundwire: cdns: Add sdw_master_ops and IO transfer support") Reported-by: Norman Bintang Closes: https://issuetracker.google.com/issues/477099834 Reviewed-by: Pierre-Louis Bossart Link: https://patch.msgid.link/20260310113133.1707288-1-rf@opensource.cirrus.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/soundwire/cadence_master.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 21bb491d026b4..d7a0a14ad9626 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -933,6 +933,14 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) cdns_read_response(cdns); + /* + * Clear interrupt before signalling the completion to avoid + * a race between this thread and the main thread starting + * another TX. + */ + cdns_writel(cdns, CDNS_MCP_INTSTAT, CDNS_MCP_INT_RX_WL); + int_status &= ~CDNS_MCP_INT_RX_WL; + if (defer && defer->msg) { cdns_fill_msg_resp(cdns, defer->msg, defer->length, 0); From d09b029f639cddf6336ee3e25d544ac2ddff3499 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 15 Jan 2026 23:25:08 -0500 Subject: [PATCH 0632/1518] tracing: remove size parameter in __trace_puts() [ Upstream commit 86e685ff364394b477cd1c476029480a2a1960c5 ] The __trace_puts() function takes a string pointer and the size of the string itself. All users currently simply pass in the strlen() of the string it is also passing in. There's no reason to pass in the size. Instead have the __trace_puts() function do the strlen() within the function itself. This fixes a header recursion issue where using strlen() in the macro calling __trace_puts() requires adding #include in order to use strlen(). Removing the use of strlen() from the header fixes the recursion issue. Link: https://lore.kernel.org/all/aUN8Hm377C5A0ILX@yury/ Link: https://lkml.kernel.org/r/20260116042510.241009-6-ynorov@nvidia.com Signed-off-by: Steven Rostedt (Google) Signed-off-by: Yury Norov Reviewed-by: Andy Shevchenko Reviewed-by: Joel Fernandes Cc: Aaron Tomlin Cc: Andi Shyti Cc: Christophe Leroy (CS GROUP) Cc: Greg Kroah-Hartman Cc: Jani Nikula Cc: Petr Pavlu Cc: Randy Dunlap Signed-off-by: Andrew Morton Stable-dep-of: 473e470f16f9 ("tracing: move __printf() attribute on __ftrace_vbprintk()") Signed-off-by: Sasha Levin --- include/linux/kernel.h | 4 ++-- kernel/trace/trace.c | 7 +++---- kernel/trace/trace.h | 2 +- 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5b46924fdff52..d5a939b8c3911 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -331,10 +331,10 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); if (__builtin_constant_p(str)) \ __trace_bputs(_THIS_IP_, trace_printk_fmt); \ else \ - __trace_puts(_THIS_IP_, str, strlen(str)); \ + __trace_puts(_THIS_IP_, str); \ }) extern int __trace_bputs(unsigned long ip, const char *str); -extern int __trace_puts(unsigned long ip, const char *str, int size); +extern int __trace_puts(unsigned long ip, const char *str); extern void trace_dump_stack(int skip); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2be9e47d64b08..55c9f51a2fda0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1180,11 +1180,10 @@ EXPORT_SYMBOL_GPL(__trace_array_puts); * __trace_puts - write a constant string into the trace buffer. * @ip: The address of the caller * @str: The constant string to write - * @size: The size of the string. */ -int __trace_puts(unsigned long ip, const char *str, int size) +int __trace_puts(unsigned long ip, const char *str) { - return __trace_array_puts(printk_trace, ip, str, size); + return __trace_array_puts(printk_trace, ip, str, strlen(str)); } EXPORT_SYMBOL_GPL(__trace_puts); @@ -1203,7 +1202,7 @@ int __trace_bputs(unsigned long ip, const char *str) int size = sizeof(struct bputs_entry); if (!printk_binsafe(tr)) - return __trace_puts(ip, str, strlen(str)); + return __trace_puts(ip, str); if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ec372e0f2e716..62d5a5f224c4a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -2099,7 +2099,7 @@ extern void tracing_log_err(struct trace_array *tr, * about performance). The internal_trace_puts() is for such * a purpose. */ -#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) +#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str) #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ From 2be24b87a474336db545a5c9fea57fd0f15183f4 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 15 Jan 2026 23:25:09 -0500 Subject: [PATCH 0633/1518] tracing: move tracing declarations from kernel.h to a dedicated header [ Upstream commit bec261fec6d41318e414c4064f2b67c6db628acd ] Tracing is a half of the kernel.h in terms of LOCs, although it's a self-consistent part. It is intended for quick debugging purposes and isn't used by the normal tracing utilities. Move it to a separate header. If someone needs to just throw a trace_printk() in their driver, they will not have to pull all the heavy tracing machinery. This is a pure move. Link: https://lkml.kernel.org/r/20260116042510.241009-7-ynorov@nvidia.com Signed-off-by: Yury Norov Acked-by: Steven Rostedt Reviewed-by: Andy Shevchenko Reviewed-by: Joel Fernandes Cc: Aaron Tomlin Cc: Andi Shyti Cc: Christophe Leroy (CS GROUP) Cc: Greg Kroah-Hartman Cc: Jani Nikula Cc: Petr Pavlu Cc: Randy Dunlap Signed-off-by: Andrew Morton Stable-dep-of: 473e470f16f9 ("tracing: move __printf() attribute on __ftrace_vbprintk()") Signed-off-by: Sasha Levin --- include/linux/kernel.h | 196 +-------------------------------- include/linux/trace_printk.h | 204 +++++++++++++++++++++++++++++++++++ 2 files changed, 205 insertions(+), 195 deletions(-) create mode 100644 include/linux/trace_printk.h diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d5a939b8c3911..356a6f1db9dac 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include @@ -192,200 +192,6 @@ enum system_states { }; extern enum system_states system_state; -/* - * General tracing related utility functions - trace_printk(), - * tracing_on/tracing_off and tracing_start()/tracing_stop - * - * Use tracing_on/tracing_off when you want to quickly turn on or off - * tracing. It simply enables or disables the recording of the trace events. - * This also corresponds to the user space /sys/kernel/tracing/tracing_on - * file, which gives a means for the kernel and userspace to interact. - * Place a tracing_off() in the kernel where you want tracing to end. - * From user space, examine the trace, and then echo 1 > tracing_on - * to continue tracing. - * - * tracing_stop/tracing_start has slightly more overhead. It is used - * by things like suspend to ram where disabling the recording of the - * trace is not enough, but tracing must actually stop because things - * like calling smp_processor_id() may crash the system. - * - * Most likely, you want to use tracing_on/tracing_off. - */ - -enum ftrace_dump_mode { - DUMP_NONE, - DUMP_ALL, - DUMP_ORIG, - DUMP_PARAM, -}; - -#ifdef CONFIG_TRACING -void tracing_on(void); -void tracing_off(void); -int tracing_is_on(void); -void tracing_snapshot(void); -void tracing_snapshot_alloc(void); - -extern void tracing_start(void); -extern void tracing_stop(void); - -static inline __printf(1, 2) -void ____trace_printk_check_format(const char *fmt, ...) -{ -} -#define __trace_printk_check_format(fmt, args...) \ -do { \ - if (0) \ - ____trace_printk_check_format(fmt, ##args); \ -} while (0) - -/** - * trace_printk - printf formatting in the ftrace buffer - * @fmt: the printf format for printing - * - * Note: __trace_printk is an internal function for trace_printk() and - * the @ip is passed in via the trace_printk() macro. - * - * This function allows a kernel developer to debug fast path sections - * that printk is not appropriate for. By scattering in various - * printk like tracing in the code, a developer can quickly see - * where problems are occurring. - * - * This is intended as a debugging tool for the developer only. - * Please refrain from leaving trace_printks scattered around in - * your code. (Extra memory is used for special buffers that are - * allocated when trace_printk() is used.) - * - * A little optimization trick is done here. If there's only one - * argument, there's no need to scan the string for printf formats. - * The trace_puts() will suffice. But how can we take advantage of - * using trace_puts() when trace_printk() has only one argument? - * By stringifying the args and checking the size we can tell - * whether or not there are args. __stringify((__VA_ARGS__)) will - * turn into "()\0" with a size of 3 when there are no args, anything - * else will be bigger. All we need to do is define a string to this, - * and then take its size and compare to 3. If it's bigger, use - * do_trace_printk() otherwise, optimize it to trace_puts(). Then just - * let gcc optimize the rest. - */ - -#define trace_printk(fmt, ...) \ -do { \ - char _______STR[] = __stringify((__VA_ARGS__)); \ - if (sizeof(_______STR) > 3) \ - do_trace_printk(fmt, ##__VA_ARGS__); \ - else \ - trace_puts(fmt); \ -} while (0) - -#define do_trace_printk(fmt, args...) \ -do { \ - static const char *trace_printk_fmt __used \ - __section("__trace_printk_fmt") = \ - __builtin_constant_p(fmt) ? fmt : NULL; \ - \ - __trace_printk_check_format(fmt, ##args); \ - \ - if (__builtin_constant_p(fmt)) \ - __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \ - else \ - __trace_printk(_THIS_IP_, fmt, ##args); \ -} while (0) - -extern __printf(2, 3) -int __trace_bprintk(unsigned long ip, const char *fmt, ...); - -extern __printf(2, 3) -int __trace_printk(unsigned long ip, const char *fmt, ...); - -/** - * trace_puts - write a string into the ftrace buffer - * @str: the string to record - * - * Note: __trace_bputs is an internal function for trace_puts and - * the @ip is passed in via the trace_puts macro. - * - * This is similar to trace_printk() but is made for those really fast - * paths that a developer wants the least amount of "Heisenbug" effects, - * where the processing of the print format is still too much. - * - * This function allows a kernel developer to debug fast path sections - * that printk is not appropriate for. By scattering in various - * printk like tracing in the code, a developer can quickly see - * where problems are occurring. - * - * This is intended as a debugging tool for the developer only. - * Please refrain from leaving trace_puts scattered around in - * your code. (Extra memory is used for special buffers that are - * allocated when trace_puts() is used.) - * - * Returns: 0 if nothing was written, positive # if string was. - * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) - */ - -#define trace_puts(str) ({ \ - static const char *trace_printk_fmt __used \ - __section("__trace_printk_fmt") = \ - __builtin_constant_p(str) ? str : NULL; \ - \ - if (__builtin_constant_p(str)) \ - __trace_bputs(_THIS_IP_, trace_printk_fmt); \ - else \ - __trace_puts(_THIS_IP_, str); \ -}) -extern int __trace_bputs(unsigned long ip, const char *str); -extern int __trace_puts(unsigned long ip, const char *str); - -extern void trace_dump_stack(int skip); - -/* - * The double __builtin_constant_p is because gcc will give us an error - * if we try to allocate the static variable to fmt if it is not a - * constant. Even with the outer if statement. - */ -#define ftrace_vprintk(fmt, vargs) \ -do { \ - if (__builtin_constant_p(fmt)) { \ - static const char *trace_printk_fmt __used \ - __section("__trace_printk_fmt") = \ - __builtin_constant_p(fmt) ? fmt : NULL; \ - \ - __ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \ - } else \ - __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ -} while (0) - -extern __printf(2, 0) int -__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); - -extern __printf(2, 0) int -__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); - -extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); -#else -static inline void tracing_start(void) { } -static inline void tracing_stop(void) { } -static inline void trace_dump_stack(int skip) { } - -static inline void tracing_on(void) { } -static inline void tracing_off(void) { } -static inline int tracing_is_on(void) { return 0; } -static inline void tracing_snapshot(void) { } -static inline void tracing_snapshot_alloc(void) { } - -static inline __printf(1, 2) -int trace_printk(const char *fmt, ...) -{ - return 0; -} -static __printf(1, 0) inline int -ftrace_vprintk(const char *fmt, va_list ap) -{ - return 0; -} -static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } -#endif /* CONFIG_TRACING */ - /* Rebuild everything on CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_DYNAMIC_FTRACE # define REBUILD_DUE_TO_DYNAMIC_FTRACE diff --git a/include/linux/trace_printk.h b/include/linux/trace_printk.h new file mode 100644 index 0000000000000..bb5874097f24e --- /dev/null +++ b/include/linux/trace_printk.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TRACE_PRINTK_H +#define _LINUX_TRACE_PRINTK_H + +#include +#include +#include +#include + +/* + * General tracing related utility functions - trace_printk(), + * tracing_on/tracing_off and tracing_start()/tracing_stop + * + * Use tracing_on/tracing_off when you want to quickly turn on or off + * tracing. It simply enables or disables the recording of the trace events. + * This also corresponds to the user space /sys/kernel/tracing/tracing_on + * file, which gives a means for the kernel and userspace to interact. + * Place a tracing_off() in the kernel where you want tracing to end. + * From user space, examine the trace, and then echo 1 > tracing_on + * to continue tracing. + * + * tracing_stop/tracing_start has slightly more overhead. It is used + * by things like suspend to ram where disabling the recording of the + * trace is not enough, but tracing must actually stop because things + * like calling smp_processor_id() may crash the system. + * + * Most likely, you want to use tracing_on/tracing_off. + */ + +enum ftrace_dump_mode { + DUMP_NONE, + DUMP_ALL, + DUMP_ORIG, + DUMP_PARAM, +}; + +#ifdef CONFIG_TRACING +void tracing_on(void); +void tracing_off(void); +int tracing_is_on(void); +void tracing_snapshot(void); +void tracing_snapshot_alloc(void); + +extern void tracing_start(void); +extern void tracing_stop(void); + +static inline __printf(1, 2) +void ____trace_printk_check_format(const char *fmt, ...) +{ +} +#define __trace_printk_check_format(fmt, args...) \ +do { \ + if (0) \ + ____trace_printk_check_format(fmt, ##args); \ +} while (0) + +/** + * trace_printk - printf formatting in the ftrace buffer + * @fmt: the printf format for printing + * + * Note: __trace_printk is an internal function for trace_printk() and + * the @ip is passed in via the trace_printk() macro. + * + * This function allows a kernel developer to debug fast path sections + * that printk is not appropriate for. By scattering in various + * printk like tracing in the code, a developer can quickly see + * where problems are occurring. + * + * This is intended as a debugging tool for the developer only. + * Please refrain from leaving trace_printks scattered around in + * your code. (Extra memory is used for special buffers that are + * allocated when trace_printk() is used.) + * + * A little optimization trick is done here. If there's only one + * argument, there's no need to scan the string for printf formats. + * The trace_puts() will suffice. But how can we take advantage of + * using trace_puts() when trace_printk() has only one argument? + * By stringifying the args and checking the size we can tell + * whether or not there are args. __stringify((__VA_ARGS__)) will + * turn into "()\0" with a size of 3 when there are no args, anything + * else will be bigger. All we need to do is define a string to this, + * and then take its size and compare to 3. If it's bigger, use + * do_trace_printk() otherwise, optimize it to trace_puts(). Then just + * let gcc optimize the rest. + */ + +#define trace_printk(fmt, ...) \ +do { \ + char _______STR[] = __stringify((__VA_ARGS__)); \ + if (sizeof(_______STR) > 3) \ + do_trace_printk(fmt, ##__VA_ARGS__); \ + else \ + trace_puts(fmt); \ +} while (0) + +#define do_trace_printk(fmt, args...) \ +do { \ + static const char *trace_printk_fmt __used \ + __section("__trace_printk_fmt") = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ + __trace_printk_check_format(fmt, ##args); \ + \ + if (__builtin_constant_p(fmt)) \ + __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \ + else \ + __trace_printk(_THIS_IP_, fmt, ##args); \ +} while (0) + +extern __printf(2, 3) +int __trace_bprintk(unsigned long ip, const char *fmt, ...); + +extern __printf(2, 3) +int __trace_printk(unsigned long ip, const char *fmt, ...); + +/** + * trace_puts - write a string into the ftrace buffer + * @str: the string to record + * + * Note: __trace_bputs is an internal function for trace_puts and + * the @ip is passed in via the trace_puts macro. + * + * This is similar to trace_printk() but is made for those really fast + * paths that a developer wants the least amount of "Heisenbug" effects, + * where the processing of the print format is still too much. + * + * This function allows a kernel developer to debug fast path sections + * that printk is not appropriate for. By scattering in various + * printk like tracing in the code, a developer can quickly see + * where problems are occurring. + * + * This is intended as a debugging tool for the developer only. + * Please refrain from leaving trace_puts scattered around in + * your code. (Extra memory is used for special buffers that are + * allocated when trace_puts() is used.) + * + * Returns: 0 if nothing was written, positive # if string was. + * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) + */ + +#define trace_puts(str) ({ \ + static const char *trace_printk_fmt __used \ + __section("__trace_printk_fmt") = \ + __builtin_constant_p(str) ? str : NULL; \ + \ + if (__builtin_constant_p(str)) \ + __trace_bputs(_THIS_IP_, trace_printk_fmt); \ + else \ + __trace_puts(_THIS_IP_, str); \ +}) +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str); + +extern void trace_dump_stack(int skip); + +/* + * The double __builtin_constant_p is because gcc will give us an error + * if we try to allocate the static variable to fmt if it is not a + * constant. Even with the outer if statement. + */ +#define ftrace_vprintk(fmt, vargs) \ +do { \ + if (__builtin_constant_p(fmt)) { \ + static const char *trace_printk_fmt __used \ + __section("__trace_printk_fmt") = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ + __ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \ + } else \ + __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ +} while (0) + +extern __printf(2, 0) int +__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); + +extern __printf(2, 0) int +__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); + +extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); +#else +static inline void tracing_start(void) { } +static inline void tracing_stop(void) { } +static inline void trace_dump_stack(int skip) { } + +static inline void tracing_on(void) { } +static inline void tracing_off(void) { } +static inline int tracing_is_on(void) { return 0; } +static inline void tracing_snapshot(void) { } +static inline void tracing_snapshot_alloc(void) { } + +static inline __printf(1, 2) +int trace_printk(const char *fmt, ...) +{ + return 0; +} +static __printf(1, 0) inline int +ftrace_vprintk(const char *fmt, va_list ap) +{ + return 0; +} +static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } +#endif /* CONFIG_TRACING */ + +#endif From d7338f4dde91eab87be2a20ead8387bb5f20f078 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Feb 2026 17:45:29 +0100 Subject: [PATCH 0634/1518] tracing: move __printf() attribute on __ftrace_vbprintk() [ Upstream commit 473e470f16f98569d59adc11c4a318780fb68fe9 ] The sunrpc change to use trace_printk() for debugging caused a new warning for every instance of dprintk() in some configurations, when -Wformat-security is enabled: fs/nfs/getroot.c: In function 'nfs_get_root': fs/nfs/getroot.c:90:17: error: format not a string literal and no format arguments [-Werror=format-security] 90 | nfs_errorf(fc, "NFS: Couldn't getattr on root"); I've been slowly chipping away at those warnings over time with the intention of enabling them by default in the future. While I could not figure out why this only happens for this one instance, I see that the __trace_bprintk() function is always called with a local variable as the format string, rather than a literal. Move the __printf(2,3) annotation on this function from the declaration to the caller. As this is can only be validated for literals, the attribute on the declaration causes the warnings every time, but removing it entirely introduces a new warning on the __ftrace_vbprintk() definition. The format strings still get checked because the underlying literal keeps getting passed into __trace_printk() in the "else" branch, which is not taken but still evaluated for compile-time warnings. Cc: Masami Hiramatsu Cc: Anna Schumaker Cc: Chuck Lever Cc: Simon Horman Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Yury Norov Cc: Randy Dunlap Link: https://patch.msgid.link/20260203164545.3174910-1-arnd@kernel.org Fixes: ec7d8e68ef0e ("sunrpc: add a Kconfig option to redirect dfprintk() output to trace buffer") Acked-by: Jeff Layton Acked-by: Steven Rostedt (Google) Signed-off-by: Arnd Bergmann Acked-by: Andy Shevchenko Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- include/linux/trace_printk.h | 1 - kernel/trace/trace_printk.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/trace_printk.h b/include/linux/trace_printk.h index bb5874097f24e..2670ec7f42629 100644 --- a/include/linux/trace_printk.h +++ b/include/linux/trace_printk.h @@ -107,7 +107,6 @@ do { \ __trace_printk(_THIS_IP_, fmt, ##args); \ } while (0) -extern __printf(2, 3) int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 29f6e95439b67..48c085fcae7aa 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -197,6 +197,7 @@ struct notifier_block module_trace_bprintk_format_nb = { .notifier_call = module_trace_bprintk_format_notify, }; +__printf(2, 3) int __trace_bprintk(unsigned long ip, const char *fmt, ...) { int ret; From 0402c60abe769098d77f3b3bd1e29a97922b614b Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Wed, 1 Apr 2026 19:22:23 +0800 Subject: [PATCH 0635/1518] tracing: Rebuild full_name on each hist_field_name() call [ Upstream commit 5ec1d1e97de134beed3a5b08235a60fc1c51af96 ] hist_field_name() uses a static MAX_FILTER_STR_VAL buffer for fully qualified variable-reference names, but it currently appends into that buffer with strcat() without rebuilding it first. As a result, repeated calls append a new "system.event.field" name onto the previous one, which can eventually run past the end of full_name. Build the name with snprintf() on each call and return NULL if the fully qualified name does not fit in MAX_FILTER_STR_VAL. Link: https://patch.msgid.link/20260401112224.85582-1-pengpeng@iscas.ac.cn Fixes: 067fe038e70f ("tracing: Add variable reference handling to hist triggers") Reviewed-by: Tom Zanussi Tested-by: Tom Zanussi Signed-off-by: Pengpeng Hou Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace_events_hist.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 2a0726e1bc97f..cb9e067138683 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1355,12 +1355,14 @@ static const char *hist_field_name(struct hist_field *field, field->flags & HIST_FIELD_FL_VAR_REF) { if (field->system) { static char full_name[MAX_FILTER_STR_VAL]; + int len; + + len = snprintf(full_name, sizeof(full_name), "%s.%s.%s", + field->system, field->event_name, + field->name); + if (len >= sizeof(full_name)) + return NULL; - strcat(full_name, field->system); - strcat(full_name, "."); - strcat(full_name, field->event_name); - strcat(full_name, "."); - strcat(full_name, field->name); field_name = full_name; } else field_name = field->name; From 514f1eb75ffb3e5068b7084baeb513f0c2d9b2b4 Mon Sep 17 00:00:00 2001 From: Francesco Lavra Date: Wed, 26 Nov 2025 11:46:18 +0100 Subject: [PATCH 0636/1518] hte: tegra194: remove Kconfig dependency on Tegra194 SoC [ Upstream commit 92dfd92f747698352b256cd9ddd7497bb7ebe9c8 ] This driver runs also on other Tegra SoCs (e.g. Tegra234). Replace Kconfig dependency on Tegra194 with more generic dependency on Tegra, and amend the Kconfig help text to reflect the fact that this driver works on SoCs other than Tegra194. Fixes: b003fb5c9df8 ("hte: Add Tegra234 provider") Signed-off-by: Francesco Lavra Acked-by: Dipen Patel Signed-off-by: Dipen Patel Signed-off-by: Sasha Levin --- drivers/hte/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hte/Kconfig b/drivers/hte/Kconfig index 641af722b555d..f57bad67deef0 100644 --- a/drivers/hte/Kconfig +++ b/drivers/hte/Kconfig @@ -16,13 +16,13 @@ if HTE config HTE_TEGRA194 tristate "NVIDIA Tegra194 HTE Support" - depends on (ARCH_TEGRA_194_SOC || COMPILE_TEST) + depends on (ARCH_TEGRA || COMPILE_TEST) depends on GPIOLIB help Enable this option for integrated hardware timestamping engine also known as generic timestamping engine (GTE) support on NVIDIA Tegra194 - systems-on-chip. The driver supports 352 LIC IRQs and 39 AON GPIOs - lines for timestamping in realtime. + and later systems-on-chip. The driver supports 352 LIC IRQs and 39 + AON GPIOs lines for timestamping in realtime. config HTE_TEGRA194_TEST tristate "NVIDIA Tegra194 HTE Test" From 405c94550c684c959466ccfe9665906b9630de94 Mon Sep 17 00:00:00 2001 From: Tim Michals Date: Wed, 4 Feb 2026 12:27:30 -0800 Subject: [PATCH 0637/1518] remoteproc: xlnx: Fix sram property parsing [ Upstream commit d116bccf6f1c199b27c9ebdf07cc3cfe868f919c ] As per sram bindings, "sram" property can be list of phandles. When more than one sram phandles are listed, driver can't parse second phandle's address correctly. Because, phandle index is passed to the API instead of offset of address from reg property which is always 0 as per sram.yaml bindings. Fix it by passing 0 to the API instead of sram phandle index. Fixes: 77fcdf51b8ca ("remoteproc: xlnx: Add sram support") Signed-off-by: Tim Michals Signed-off-by: Tanmay Shah Link: https://lore.kernel.org/r/20260204202730.3729984-1-tanmay.shah@amd.com Signed-off-by: Mathieu Poirier Signed-off-by: Sasha Levin --- drivers/remoteproc/xlnx_r5_remoteproc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/remoteproc/xlnx_r5_remoteproc.c b/drivers/remoteproc/xlnx_r5_remoteproc.c index b30f660a1c553..5ef586fd37bca 100644 --- a/drivers/remoteproc/xlnx_r5_remoteproc.c +++ b/drivers/remoteproc/xlnx_r5_remoteproc.c @@ -1022,7 +1022,7 @@ static int zynqmp_r5_get_sram_banks(struct zynqmp_r5_core *r5_core) } /* Get SRAM device address */ - ret = of_property_read_reg(sram_np, i, &abs_addr, &size); + ret = of_property_read_reg(sram_np, 0, &abs_addr, &size); if (ret) { dev_err(dev, "failed to get reg property\n"); goto fail_sram_get; From 28122fcd7bccfe762f58125430f5765326ccd77e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 17 Feb 2026 14:11:11 +0100 Subject: [PATCH 0638/1518] stop_machine: Fix the documentation for a NULL cpus argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 48f7a50c027dd2abb9e7b8a6ecc8e531d87f2c21 ] A recent refactoring of the kernel-docs for stop machine changed the description of the cpus parameter from "NULL = any online cpu" to "NULL = run on each online CPU". However the callback is only executed on a single CPU, not all of them. The old wording was a bit ambiguous and could have been read both ways. Reword the documentation to be correct again and hopefully also clearer. Fixes: fc6f89dc7078 ("stop_machine: Improve kernel-doc function-header comments") Signed-off-by: Thomas Weißschuh Signed-off-by: Paul E. McKenney Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Sasha Levin --- include/linux/stop_machine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 72820503514cc..01011113d2263 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -99,7 +99,7 @@ static inline void print_stop_info(const char *log_lvl, struct task_struct *task * stop_machine: freeze the machine on all CPUs and run this function * @fn: the function to run * @data: the data ptr to pass to @fn() - * @cpus: the cpus to run @fn() on (NULL = run on each online CPU) + * @cpus: the cpus to run @fn() on (NULL = one unspecified online CPU) * * Description: This causes a thread to be scheduled on every CPU, which * will run with interrupts disabled. Each CPU specified by @cpus will @@ -133,7 +133,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); * stop_machine_cpuslocked: freeze the machine on all CPUs and run this function * @fn: the function to run * @data: the data ptr to pass to @fn() - * @cpus: the cpus to run @fn() on (NULL = run on each online CPU) + * @cpus: the cpus to run @fn() on (NULL = one unspecified online CPU) * * Same as above. Avoids nested calls to cpus_read_lock(). * From 5bfc58588ae02496a7648a1d07660e3b5ebc8bd4 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Mon, 9 Feb 2026 13:14:07 +0800 Subject: [PATCH 0639/1518] remoteproc: imx_rproc: Check return value of regmap_attach_dev() in imx_rproc_mmio_detect_mode() [ Upstream commit a48c6676912fb808d2af1b8344d8656815a3e108 ] Add error checking for regmap_attach_dev() call in imx_rproc_mmio_detect_mode() function to ensure proper error propagation. Return the value of regmap_attach_dev() if it fails to prevent proceeding with an incomplete regmap setup. Suggested-by: Peng Fan Signed-off-by: Chen Ni Fixes: e14168bf3493 ("remoteproc: imx_rproc: Simplify IMX_RPROC_MMIO switch case") Link: https://lore.kernel.org/r/20260209051407.1467660-1-nichen@iscas.ac.cn Signed-off-by: Mathieu Poirier Signed-off-by: Sasha Levin --- drivers/remoteproc/imx_rproc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index 7ef99eac37f1a..8fa81d3779849 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -899,7 +899,11 @@ static int imx_rproc_mmio_detect_mode(struct rproc *rproc) } priv->regmap = regmap; - regmap_attach_dev(dev, regmap, &config); + ret = regmap_attach_dev(dev, regmap, &config); + if (ret) { + dev_err(dev, "regmap attach failed\n"); + return ret; + } if (priv->gpr) { ret = regmap_read(priv->gpr, dcfg->gpr_reg, &val); From 148e4f7ece72022311f70c5638fb15d4f088db61 Mon Sep 17 00:00:00 2001 From: Daniel Hodges Date: Sat, 31 Jan 2026 18:40:15 -0800 Subject: [PATCH 0640/1518] ima: check return value of crypto_shash_final() in boot aggregate [ Upstream commit 870819434c8dfcc3158033b66e7851b81bb17e21 ] The return value of crypto_shash_final() is not checked in ima_calc_boot_aggregate_tfm(). If the hash finalization fails, the function returns success and a corrupted boot aggregate digest could be used for IMA measurements. Capture the return value and propagate any error to the caller. Fixes: 76bb28f6126f ("ima: use new crypto_shash API instead of old crypto_hash") Signed-off-by: Daniel Hodges Reviewed-by: Roberto Sassu Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/ima_crypto.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index 6f5696d999d0d..8ae7821a65c26 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -832,7 +832,7 @@ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, } } if (!rc) - crypto_shash_final(shash, digest); + rc = crypto_shash_final(shash, digest); return rc; } From 59601f0e83d422fd19d6720bc4fd934eeac0c76d Mon Sep 17 00:00:00 2001 From: Denis Benato Date: Sat, 28 Feb 2026 20:10:07 +0100 Subject: [PATCH 0641/1518] HID: asus: make asus_resume adhere to linux kernel coding standards [ Upstream commit 51d33b42b8ae23da92819d28439fdd5636c45186 ] Linux kernel coding standars requires functions opening brackets to be in a newline: move the opening bracket of asus_resume in its own line. Fixes: 546edbd26cff ("HID: hid-asus: reset the backlight brightness level on resume") Signed-off-by: Denis Benato Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-asus.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 5a068f6fd2ce5..b9dfb38b0df4f 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1095,7 +1095,8 @@ static int asus_start_multitouch(struct hid_device *hdev) return 0; } -static int __maybe_unused asus_resume(struct hid_device *hdev) { +static int __maybe_unused asus_resume(struct hid_device *hdev) +{ struct asus_drvdata *drvdata = hid_get_drvdata(hdev); int ret = 0; From fb9364ba4fa66deb1e554cbed4a130502b7ba866 Mon Sep 17 00:00:00 2001 From: Denis Benato Date: Sat, 28 Feb 2026 20:10:09 +0100 Subject: [PATCH 0642/1518] HID: asus: do not abort probe when not necessary [ Upstream commit 7253091766ded0fd81fe8d8be9b8b835495b06e8 ] In order to avoid dereferencing a NULL pointer asus_probe is aborted early and control of some asus devices is transferred over hid-generic after erroring out even when such NULL dereference cannot happen: only early abort when the NULL dereference can happen. Also make the code shorter and more adherent to coding standards removing square brackets enclosing single-line if-else statements. Fixes: d3af6ca9a8c3 ("HID: asus: fix UAF via HID_CLAIMED_INPUT validation") Signed-off-by: Denis Benato Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-asus.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index b9dfb38b0df4f..1746e8ea50ddf 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1223,22 +1223,17 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) * were freed during registration due to no usages being mapped, * leaving drvdata->input pointing to freed memory. */ - if (!drvdata->input || !(hdev->claimed & HID_CLAIMED_INPUT)) { - hid_err(hdev, "Asus input not registered\n"); - ret = -ENOMEM; - goto err_stop_hw; - } - - if (drvdata->tp) { - drvdata->input->name = "Asus TouchPad"; - } else { - drvdata->input->name = "Asus Keyboard"; - } + if (drvdata->input && (hdev->claimed & HID_CLAIMED_INPUT)) { + if (drvdata->tp) + drvdata->input->name = "Asus TouchPad"; + else + drvdata->input->name = "Asus Keyboard"; - if (drvdata->tp) { - ret = asus_start_multitouch(hdev); - if (ret) - goto err_stop_hw; + if (drvdata->tp) { + ret = asus_start_multitouch(hdev); + if (ret) + goto err_stop_hw; + } } return 0; From e4e0bd721b92ba5ba02569b37880df5cf5a6e60f Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Fri, 27 Feb 2026 09:43:36 +0800 Subject: [PATCH 0643/1518] mtd: physmap_of_gemini: Fix disabled pinctrl state check [ Upstream commit b7c0982184b0661f5b1b805f3a56f1bd3757b63e ] The condition for checking the disabled pinctrl state incorrectly checks gf->enabled_state instead of gf->disabled_state. This causes misleading error messages and could lead to incorrect behavior when only one of the pinctrl states is defined. Fix the condition to properly check gf->disabled_state. Fixes: 9d3b5086f6d4 ("mtd: physmap_of_gemini: Handle pin control") Signed-off-by: Chen Ni Reviewed-by: Linus Walleij Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- drivers/mtd/maps/physmap-gemini.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/maps/physmap-gemini.c b/drivers/mtd/maps/physmap-gemini.c index 9d3b4bf84a1ad..1c34b4ef77ea3 100644 --- a/drivers/mtd/maps/physmap-gemini.c +++ b/drivers/mtd/maps/physmap-gemini.c @@ -181,7 +181,7 @@ int of_flash_probe_gemini(struct platform_device *pdev, dev_err(dev, "no enabled pin control state\n"); gf->disabled_state = pinctrl_lookup_state(gf->p, "disabled"); - if (IS_ERR(gf->enabled_state)) { + if (IS_ERR(gf->disabled_state)) { dev_err(dev, "no disabled pin control state\n"); } else { ret = pinctrl_select_state(gf->p, gf->disabled_state); From b6766b171a5c4c33b26ff6fec530cb798db1f75e Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 10 Mar 2026 17:40:39 +0000 Subject: [PATCH 0644/1518] ima_fs: Correctly create securityfs files for unsupported hash algos [ Upstream commit d7bd8cf0b348d3edae7bee33e74a32b21668b181 ] ima_tpm_chip->allocated_banks[i].crypto_id is initialized to HASH_ALGO__LAST if the TPM algorithm is not supported. However there are places relying on the algorithm to be valid because it is accessed by hash_algo_name[]. On 6.12.40 I observe the following read out-of-bounds in hash_algo_name: ================================================================== BUG: KASAN: global-out-of-bounds in create_securityfs_measurement_lists+0x396/0x440 Read of size 8 at addr ffffffff83e18138 by task swapper/0/1 CPU: 4 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.40 #3 Call Trace: dump_stack_lvl+0x61/0x90 print_report+0xc4/0x580 ? kasan_addr_to_slab+0x26/0x80 ? create_securityfs_measurement_lists+0x396/0x440 kasan_report+0xc2/0x100 ? create_securityfs_measurement_lists+0x396/0x440 create_securityfs_measurement_lists+0x396/0x440 ima_fs_init+0xa3/0x300 ima_init+0x7d/0xd0 init_ima+0x28/0x100 do_one_initcall+0xa6/0x3e0 kernel_init_freeable+0x455/0x740 kernel_init+0x24/0x1d0 ret_from_fork+0x38/0x80 ret_from_fork_asm+0x11/0x20 The buggy address belongs to the variable: hash_algo_name+0xb8/0x420 Memory state around the buggy address: ffffffff83e18000: 00 01 f9 f9 f9 f9 f9 f9 00 01 f9 f9 f9 f9 f9 f9 ffffffff83e18080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffff83e18100: 00 00 00 00 00 00 00 f9 f9 f9 f9 f9 00 05 f9 f9 ^ ffffffff83e18180: f9 f9 f9 f9 00 00 00 00 00 00 00 04 f9 f9 f9 f9 ffffffff83e18200: 00 00 00 00 00 00 00 00 04 f9 f9 f9 f9 f9 f9 f9 ================================================================== Seems like the TPM chip supports sha3_256, which isn't yet in tpm_algorithms: tpm tpm0: TPM with unsupported bank algorithm 0x0027 That's TPM_ALG_SHA3_256 == 0x0027 from "Trusted Platform Module 2.0 Library Part 2: Structures", page 51 [1]. See also the related U-Boot algorithms update [2]. Thus solve the problem by creating a file name with "_tpm_alg_" postfix if the crypto algorithm isn't initialized. This is how it looks on the test machine (patch ported to v6.12 release): # ls -1 /sys/kernel/security/ima/ ascii_runtime_measurements ascii_runtime_measurements_tpm_alg_27 ascii_runtime_measurements_sha1 ascii_runtime_measurements_sha256 binary_runtime_measurements binary_runtime_measurements_tpm_alg_27 binary_runtime_measurements_sha1 binary_runtime_measurements_sha256 policy runtime_measurements_count violations [1]: https://trustedcomputinggroup.org/wp-content/uploads/Trusted-Platform-Module-2.0-Library-Part-2-Version-184_pub.pdf [2]: https://lists.denx.de/pipermail/u-boot/2024-July/558835.html Fixes: 9fa8e7625008 ("ima: add crypto agility support for template-hash algorithm") Signed-off-by: Dmitry Safonov Cc: Enrico Bravi Cc: Silvia Sisinni Cc: Roberto Sassu Cc: Mimi Zohar Reviewed-by: Roberto Sassu Tested-by: Roberto Sassu Link: https://github.com/linux-integrity/linux/issues/14 Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/ima_fs.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 87045b09f1206..25970867f594e 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -404,16 +404,24 @@ static int __init create_securityfs_measurement_lists(void) char file_name[NAME_MAX + 1]; struct dentry *dentry; - sprintf(file_name, "ascii_runtime_measurements_%s", - hash_algo_name[algo]); + if (algo == HASH_ALGO__LAST) + sprintf(file_name, "ascii_runtime_measurements_tpm_alg_%x", + ima_tpm_chip->allocated_banks[i].alg_id); + else + sprintf(file_name, "ascii_runtime_measurements_%s", + hash_algo_name[algo]); dentry = securityfs_create_file(file_name, S_IRUSR | S_IRGRP, ima_dir, (void *)(uintptr_t)i, &ima_ascii_measurements_ops); if (IS_ERR(dentry)) return PTR_ERR(dentry); - sprintf(file_name, "binary_runtime_measurements_%s", - hash_algo_name[algo]); + if (algo == HASH_ALGO__LAST) + sprintf(file_name, "binary_runtime_measurements_tpm_alg_%x", + ima_tpm_chip->allocated_banks[i].alg_id); + else + sprintf(file_name, "binary_runtime_measurements_%s", + hash_algo_name[algo]); dentry = securityfs_create_file(file_name, S_IRUSR | S_IRGRP, ima_dir, (void *)(uintptr_t)i, &ima_measurements_ops); From 756afec88e85c9ea400564c16373ce7b875c05c0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 6 Mar 2026 11:26:20 +0100 Subject: [PATCH 0645/1518] dt-bindings: interrupt-controller: arm,gic-v3: Fix EPPI range [ Upstream commit 15cfc8984defc17e5e4de1f58db7b993240fcbda ] According to the "Arm Generic Interrupt Controller (GIC) Architecture Specification, v3 and v4", revision H.b[1], there can be only 64 Extended PPI interrupts. [1] https://developer.arm.com/documentation/ihi0069/hb/ Fixes: 4b049063e0bcbfd3 ("dt-bindings: interrupt-controller: arm,gic-v3: Describe EPPI range support") Signed-off-by: Geert Uytterhoeven Brain-farted-by: Marc Zyngier Acked-by: Marc Zyngier Link: https://patch.msgid.link/3e49a63c6b2b6ee48e3737adee87781f9c136c5f.1772792753.git.geert+renesas@glider.be Signed-off-by: Rob Herring (Arm) Signed-off-by: Sasha Levin --- .../devicetree/bindings/interrupt-controller/arm,gic-v3.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index f3247a47f9eed..71e6016fe3ca0 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -50,7 +50,7 @@ properties: The 2nd cell contains the interrupt number for the interrupt type. SPI interrupts are in the range [0-987]. PPI interrupts are in the range [0-15]. Extended SPI interrupts are in the range [0-1023]. - Extended PPI interrupts are in the range [0-127]. + Extended PPI interrupts are in the range [0-63]. The 3rd cell is the flags, encoded as follows: bits[3:0] trigger type and level flags. From ad41b585f0e4a67480eda8ea4adab34c277bb865 Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Mon, 8 Dec 2025 17:14:14 +0800 Subject: [PATCH 0646/1518] mtd: spi-nor: core: correct the op.dummy.nbytes when check read operations [ Upstream commit 756564a536ecd8c9d33edd89f0647a91a0b03587 ] When check read operation, need to setting the op.dummy.nbytes based on current read operation rather than the nor->read_proto. Fixes: 0e30f47232ab ("mtd: spi-nor: add support for DTR protocol") Signed-off-by: Haibo Chen Reviewed-by: Pratyush Yadav Signed-off-by: Pratyush Yadav (Google) Signed-off-by: Sasha Levin --- drivers/mtd/spi-nor/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 20ea80450f222..19dc13faf9fd9 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -2393,7 +2393,7 @@ static int spi_nor_spimem_check_readop(struct spi_nor *nor, /* convert the dummy cycles to the number of bytes */ op.dummy.nbytes = (read->num_mode_clocks + read->num_wait_states) * op.dummy.buswidth / 8; - if (spi_nor_protocol_is_dtr(nor->read_proto)) + if (spi_nor_protocol_is_dtr(read->proto)) op.dummy.nbytes *= 2; return spi_nor_spimem_check_op(nor, &op); From 6278713f55d42b723abe04c71b89db5e787b3fab Mon Sep 17 00:00:00 2001 From: Takahiro Kuwano Date: Wed, 5 Nov 2025 16:47:58 +0900 Subject: [PATCH 0647/1518] mtd: spi-nor: sfdp: introduce smpt_read_dummy fixup hook [ Upstream commit 653f6def567c81f37302f9591ffd54df3e2a11eb ] SMPT contains config detection info that describes opcode, address, and dummy cycles to read sector map config. The dummy cycles parameter can be SMPT_CMD_READ_DUMMY_IS_VARIABLE and in that case nor->read_dummy (initialized as 0) is used. In Infineon flash chips, Read Any Register command with variable dummy cycle is defined in SMPT. S25Hx/S28Hx flash has 0 dummy cycle by default to read volatile regiters and nor->read_dummy can work. S25FS-S flash has 8 dummy cycles so we need a hook that can fix dummy cycles with actually used value. Inroduce smpt_read_dummy() in struct spi_nor_fixups. It is called when the dummy cycle field in SMPT config detection is 'varialble'. Reviewed-by: Tudor Ambarus Tested-by: Marek Vasut # S25FS512S Signed-off-by: Takahiro Kuwano Signed-off-by: Pratyush Yadav Stable-dep-of: 3620d67b4849 ("mtd: spi-nor: update spi_nor_fixups::post_sfdp() documentation") Signed-off-by: Sasha Levin --- drivers/mtd/spi-nor/core.h | 3 +++ drivers/mtd/spi-nor/sfdp.c | 18 ++++++++++++++++-- 2 files changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index ceff412f7d65a..5ad46d95d09cc 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -409,6 +409,8 @@ struct spi_nor_flash_parameter { * flash parameters when information provided by the flash_info * table is incomplete or wrong. * @post_bfpt: called after the BFPT table has been parsed + * @smpt_read_dummy: called during SMPT table is being parsed. Used to fix the + * number of dummy cycles in read register ops. * @post_sfdp: called after SFDP has been parsed (is also called for SPI NORs * that do not support RDSFDP). Typically used to tweak various * parameters that could not be extracted by other means (i.e. @@ -426,6 +428,7 @@ struct spi_nor_fixups { int (*post_bfpt)(struct spi_nor *nor, const struct sfdp_parameter_header *bfpt_header, const struct sfdp_bfpt *bfpt); + void (*smpt_read_dummy)(const struct spi_nor *nor, u8 *read_dummy); int (*post_sfdp)(struct spi_nor *nor); int (*late_init)(struct spi_nor *nor); }; diff --git a/drivers/mtd/spi-nor/sfdp.c b/drivers/mtd/spi-nor/sfdp.c index 21727f9a4ac69..9a47dcaca06ae 100644 --- a/drivers/mtd/spi-nor/sfdp.c +++ b/drivers/mtd/spi-nor/sfdp.c @@ -699,6 +699,17 @@ static u8 spi_nor_smpt_addr_nbytes(const struct spi_nor *nor, const u32 settings } } +static void spi_nor_smpt_read_dummy_fixups(const struct spi_nor *nor, + u8 *read_dummy) +{ + if (nor->manufacturer && nor->manufacturer->fixups && + nor->manufacturer->fixups->smpt_read_dummy) + nor->manufacturer->fixups->smpt_read_dummy(nor, read_dummy); + + if (nor->info->fixups && nor->info->fixups->smpt_read_dummy) + nor->info->fixups->smpt_read_dummy(nor, read_dummy); +} + /** * spi_nor_smpt_read_dummy() - return the configuration detection command read * latency, in clock cycles. @@ -711,8 +722,11 @@ static u8 spi_nor_smpt_read_dummy(const struct spi_nor *nor, const u32 settings) { u8 read_dummy = SMPT_CMD_READ_DUMMY(settings); - if (read_dummy == SMPT_CMD_READ_DUMMY_IS_VARIABLE) - return nor->read_dummy; + if (read_dummy == SMPT_CMD_READ_DUMMY_IS_VARIABLE) { + read_dummy = nor->read_dummy; + spi_nor_smpt_read_dummy_fixups(nor, &read_dummy); + } + return read_dummy; } From 0173aca3e4b1ff20d1c8ee5bb06066c59b726536 Mon Sep 17 00:00:00 2001 From: Takahiro Kuwano Date: Wed, 5 Nov 2025 16:47:59 +0900 Subject: [PATCH 0648/1518] mtd: spi-nor: sfdp: introduce smpt_map_id fixup hook [ Upstream commit f74de390557bf2bcc5dca4a357b41c0701d3f76e ] Certain chips have inconsistent Sector Map Parameter Table (SMPT) data, which leads to the wrong map ID being identified, causing failures to detect the correct sector map. To fix this, introduce smpt_map_id() into the struct spi_nor_fixups. This function will be called after the initial SMPT-based detection, allowing chip-specific logic to correct the map ID. Infineon S25FS512S needs this fixup as it has inconsistency between map ID definition and configuration register value actually obtained. Co-developed-by: Marek Vasut Signed-off-by: Marek Vasut Reviewed-by: Tudor Ambarus Tested-by: Marek Vasut # S25FS512S Signed-off-by: Takahiro Kuwano Reviewed-by: Tudor Ambarus > Signed-off-by: Pratyush Yadav Stable-dep-of: 3620d67b4849 ("mtd: spi-nor: update spi_nor_fixups::post_sfdp() documentation") Signed-off-by: Sasha Levin --- drivers/mtd/spi-nor/core.h | 3 +++ drivers/mtd/spi-nor/sfdp.c | 12 ++++++++++++ 2 files changed, 15 insertions(+) diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index 5ad46d95d09cc..16b382d4f04f2 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -411,6 +411,8 @@ struct spi_nor_flash_parameter { * @post_bfpt: called after the BFPT table has been parsed * @smpt_read_dummy: called during SMPT table is being parsed. Used to fix the * number of dummy cycles in read register ops. + * @smpt_map_id: called after map ID in SMPT table has been determined for the + * case the map ID is wrong and needs to be fixed. * @post_sfdp: called after SFDP has been parsed (is also called for SPI NORs * that do not support RDSFDP). Typically used to tweak various * parameters that could not be extracted by other means (i.e. @@ -429,6 +431,7 @@ struct spi_nor_fixups { const struct sfdp_parameter_header *bfpt_header, const struct sfdp_bfpt *bfpt); void (*smpt_read_dummy)(const struct spi_nor *nor, u8 *read_dummy); + void (*smpt_map_id)(const struct spi_nor *nor, u8 *map_id); int (*post_sfdp)(struct spi_nor *nor); int (*late_init)(struct spi_nor *nor); }; diff --git a/drivers/mtd/spi-nor/sfdp.c b/drivers/mtd/spi-nor/sfdp.c index 9a47dcaca06ae..a8324c2da0acf 100644 --- a/drivers/mtd/spi-nor/sfdp.c +++ b/drivers/mtd/spi-nor/sfdp.c @@ -730,6 +730,16 @@ static u8 spi_nor_smpt_read_dummy(const struct spi_nor *nor, const u32 settings) return read_dummy; } +static void spi_nor_smpt_map_id_fixups(const struct spi_nor *nor, u8 *map_id) +{ + if (nor->manufacturer && nor->manufacturer->fixups && + nor->manufacturer->fixups->smpt_map_id) + nor->manufacturer->fixups->smpt_map_id(nor, map_id); + + if (nor->info->fixups && nor->info->fixups->smpt_map_id) + nor->info->fixups->smpt_map_id(nor, map_id); +} + /** * spi_nor_get_map_in_use() - get the configuration map in use * @nor: pointer to a 'struct spi_nor' @@ -783,6 +793,8 @@ static const u32 *spi_nor_get_map_in_use(struct spi_nor *nor, const u32 *smpt, map_id = map_id << 1 | !!(*buf & read_data_mask); } + spi_nor_smpt_map_id_fixups(nor, &map_id); + /* * If command descriptors are provided, they always precede map * descriptors in the table. There is no need to start the iteration From 53d7a4e1b04175bedbba3ad7d4d61ad303d51082 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Thu, 18 Dec 2025 10:54:30 +0100 Subject: [PATCH 0649/1518] mtd: spi-nor: update spi_nor_fixups::post_sfdp() documentation [ Upstream commit 3620d67b48493c6252bbc873dc88dde81641d56b ] After commit 5273cc6df984 ("mtd: spi-nor: core: Call spi_nor_post_sfdp_fixups() only when SFDP is defined") spi_nor_post_sfdp_fixups() isn't called anymore if no SFDP is detected. Update the documentation accordingly. Fixes: 5273cc6df984 ("mtd: spi-nor: core: Call spi_nor_post_sfdp_fixups() only when SFDP is defined") Signed-off-by: Jonas Gorski Reviewed-by: Pratyush Yadav Signed-off-by: Pratyush Yadav (Google) Signed-off-by: Sasha Levin --- drivers/mtd/spi-nor/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index 16b382d4f04f2..e838c40a25897 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -413,7 +413,7 @@ struct spi_nor_flash_parameter { * number of dummy cycles in read register ops. * @smpt_map_id: called after map ID in SMPT table has been determined for the * case the map ID is wrong and needs to be fixed. - * @post_sfdp: called after SFDP has been parsed (is also called for SPI NORs + * @post_sfdp: called after SFDP has been parsed (is not called for SPI NORs * that do not support RDSFDP). Typically used to tweak various * parameters that could not be extracted by other means (i.e. * when information provided by the SFDP/flash_info tables are From 5549c3f88dd7bea1792e11baffc7c3c738a7b5f7 Mon Sep 17 00:00:00 2001 From: Shiji Yang Date: Wed, 28 Jan 2026 20:42:56 +0800 Subject: [PATCH 0650/1518] mtd: spi-nor: swp: check SR_TB flag when getting tb_mask [ Upstream commit 94645aa41bf9ecb87c2ce78b1c3405bfb6074a37 ] When the chip does not support top/bottom block protect, the tb_mask must be set to 0, otherwise SR1 bit5 will be unexpectedly modified. Signed-off-by: Shiji Yang Fixes: 3dd8012a8eeb ("mtd: spi-nor: add TB (Top/Bottom) protect support") Reviewed-by: Michael Walle Reviewed-by: Miquel Raynal Signed-off-by: Pratyush Yadav (Google) Signed-off-by: Sasha Levin --- drivers/mtd/spi-nor/swp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/swp.c b/drivers/mtd/spi-nor/swp.c index 9b07f83aeac76..e67a81dbb6bf6 100644 --- a/drivers/mtd/spi-nor/swp.c +++ b/drivers/mtd/spi-nor/swp.c @@ -28,8 +28,10 @@ static u8 spi_nor_get_sr_tb_mask(struct spi_nor *nor) { if (nor->flags & SNOR_F_HAS_SR_TB_BIT6) return SR_TB_BIT6; - else + else if (nor->flags & SNOR_F_HAS_SR_TB) return SR_TB_BIT5; + else + return 0; } static u64 spi_nor_get_min_prot_length_sr(struct spi_nor *nor) From c92dc1b31a1db0e8abcd4252c5ad2f691b70ceeb Mon Sep 17 00:00:00 2001 From: Cosmin Tanislav Date: Wed, 11 Mar 2026 17:39:56 +0200 Subject: [PATCH 0651/1518] mtd: parsers: ofpart: call of_node_put() only in ofpart_fail path [ Upstream commit 0c87dea1aab86116211cb37387c404c9e9231c39 ] ofpart_none can only be reached after the for_each_child_of_node() loop finishes. for_each_child_of_node() correctly calls of_node_put() for all device nodes it iterates over as long as we don't break or jump out of the loop. Calling of_node_put() inside the ofpart_none path will wrongly decrement the ref count of the last node in the for_each_child_of_node() loop. Move the call to of_node_put() under the ofpart_fail label to fix this. Fixes: ebd5a74db74e ("mtd: ofpart: Check availability of reg property instead of name property") Signed-off-by: Cosmin Tanislav Tested-by: Tommaso Merciai Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- drivers/mtd/parsers/ofpart_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index 09961c6f39496..a5ba78c6723ee 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -191,11 +191,11 @@ static int parse_fixed_partitions(struct mtd_info *master, ofpart_fail: pr_err("%s: error parsing ofpart partition %pOF (%pOF)\n", master->name, pp, mtd_node); + of_node_put(pp); ret = -EINVAL; ofpart_none: if (dedicated) of_node_put(ofpart_node); - of_node_put(pp); kfree(parts); return ret; } From 5a282a6f81299840898d176d739a897df966635f Mon Sep 17 00:00:00 2001 From: Cosmin Tanislav Date: Wed, 11 Mar 2026 17:39:57 +0200 Subject: [PATCH 0652/1518] mtd: parsers: ofpart: call of_node_get() for dedicated subpartitions [ Upstream commit e882626c1747653f1f01ea9d12e278e613b11d0f ] In order to parse sub-partitions, add_mtd_partitions() calls parse_mtd_partitions() for all previously found partitions. Each partition will end up being passed to parse_fixed_partitions(), and its of_node will be treated as the ofpart_node. Commit 7cce81df7d26 ("mtd: parsers: ofpart: fix OF node refcount leak in parse_fixed_partitions()") added of_node_put() calls for ofpart_node on all exit paths. In the case where the partition passed to parse_fixed_partitions() has a parent, it is treated as a dedicated partitions node, and of_node_put() is wrongly called for it, even if of_node_get() was not called explicitly. On repeated bind / unbinds of the MTD, the extra of_node_put() ends up decrementing the refcount down to 0, which should never happen, resulting in the following error: OF: ERROR: of_node_release() detected bad of_node_put() on /soc/spi@80007000/flash@0/partitions/partition@0 Call of_node_get() to balance the call to of_node_put() done for dedicated partitions nodes. Fixes: 7cce81df7d26 ("mtd: parsers: ofpart: fix OF node refcount leak in parse_fixed_partitions()") Signed-off-by: Cosmin Tanislav Tested-by: Tommaso Merciai Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- drivers/mtd/parsers/ofpart_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index a5ba78c6723ee..321002a1d0cae 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -71,7 +71,7 @@ static int parse_fixed_partitions(struct mtd_info *master, dedicated = false; } } else { /* Partition */ - ofpart_node = mtd_node; + ofpart_node = of_node_get(mtd_node); } of_id = of_match_node(parse_ofpart_match_table, ofpart_node); From 84688b608f013d7c21317c58dd6fe971a68c2a9d Mon Sep 17 00:00:00 2001 From: Li Ming Date: Sat, 14 Mar 2026 15:06:33 +0800 Subject: [PATCH 0653/1518] cxl/pci: Check memdev driver binding status in cxl_reset_done() [ Upstream commit e8069c66d09309579e53567be8ddfa6ccb2f452a ] cxl_reset_done() accesses the endpoint of the corresponding CXL memdev without endpoint validity checking. By default, cxlmd->endpoint is initialized to -ENXIO, if cxl_reset_done() is triggered after the corresponding CXL memdev probing failed, this results in access to an invalid endpoint. CXL subsystem can always check CXL memdev driver binding status to confirm its endpoint validity. So adding the CXL memdev driver checking inside cxl_reset_done() to avoid accessing an invalid endpoint. Fixes: 934edcd436dc ("cxl: Add post-reset warning if reset results in loss of previously committed HDM decoders") Reviewed-by: Dan Williams Reviewed-by: Dave Jiang Signed-off-by: Li Ming Link: https://patch.msgid.link/20260314-fix_access_endpoint_without_drv_check-v2-4-4c09edf2e1db@zohomail.com Signed-off-by: Dave Jiang Signed-off-by: Sasha Levin --- drivers/cxl/pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index bd100ac31672d..c78d7d88744bf 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -1104,6 +1104,9 @@ static void cxl_reset_done(struct pci_dev *pdev) * that no longer exists. */ guard(device)(&cxlmd->dev); + if (!cxlmd->dev.driver) + return; + if (cxlmd->endpoint && cxl_endpoint_decoder_reset_detected(cxlmd->endpoint)) { dev_crit(dev, "SBR happened without memory regions removal.\n"); From 34e666a256de327bc1fa79e9cd18105bd363f5c8 Mon Sep 17 00:00:00 2001 From: Richard Genoud Date: Tue, 17 Mar 2026 15:24:30 +0100 Subject: [PATCH 0654/1518] mtd: rawnand: sunxi: fix sunxi_nfc_hw_ecc_read_extra_oob [ Upstream commit 848c13996c55fe4ea6bf5acc3ce6c8c5c944b5f6 ] When dumping the OOB, the bytes at the end where actually copied from the beginning of the OOB instead of current_offset. That leads to something like: OOB: ff ff ff ff ff ff ff ff ea 19 00 3a 83 db aa 8d OOB: 99 09 c8 9a 90 36 35 7d aa 15 13 07 3d 97 b2 a4 OOB: a8 bb 19 b3 07 e9 f6 25 52 d7 1a 23 e2 7e 0a e4 OOB: 52 8a 09 d2 1a 86 3d cf b4 99 43 13 d3 90 33 0b OOB: ff ff ff ff ff ff ff ff ea 19 00 3a 83 db aa 8d OOB: 99 09 c8 9a 90 36 35 7d aa 15 13 07 3d 97 b2 a4 OOB: a8 bb 19 b3 07 e9 f6 25 52 d7 1a 23 e2 7e 0a e4 OOB: 52 8a 09 d2 1a 86 3d cf b4 99 43 13 d3 90 33 0b instead of: OOB: ff ff ff ff ff ff ff ff ea 19 00 3a 83 db aa 8d OOB: 99 09 c8 9a 90 36 35 7d aa 15 13 07 3d 97 b2 a4 OOB: a8 bb 19 b3 07 e9 f6 25 52 d7 1a 23 e2 7e 0a e4 OOB: 52 8a 09 d2 1a 86 3d cf b4 99 43 13 d3 90 33 0b OOB: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff OOB: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff OOB: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff OOB: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff (example with BCH16, user data [8,0], no scrambling) *cur_off (offset from the beginning of the page) was compared to offset (offset from the beginning of the OOB), and then, the nand_change_read_column_op() sets the current position to the beginning of the OOB instead of OOB+offset Fixes: 15d6f118285f ("mtd: rawnand: sunxi: Stop supporting ECC_HW_SYNDROME mode") Reviewed-by: Jernej Skrabec Signed-off-by: Richard Genoud Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/sunxi_nand.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index f6a8e8ae819d4..75db1713e6177 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -886,9 +886,9 @@ static void sunxi_nfc_hw_ecc_read_extra_oob(struct nand_chip *nand, if (len <= 0) return; - if (!cur_off || *cur_off != offset) - nand_change_read_column_op(nand, mtd->writesize, NULL, 0, - false); + if (!cur_off || *cur_off != (offset + mtd->writesize)) + nand_change_read_column_op(nand, mtd->writesize + offset, + NULL, 0, false); if (!randomize) sunxi_nfc_read_buf(nand, oob + offset, len); From b5804b3ae4b8556ef200c4209e372f90460de20d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:03 +0100 Subject: [PATCH 0655/1518] mtd: spinand: Add missing check [ Upstream commit aab8a4c656379a6a1a4ca716f48118680560eaab ] The update cache variant is mandatory, both read and write versions are being checked, but not this one. All chip drivers seem to implement this variant, so there should be no breakage. Reviewed-by: Tudor Ambarus Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 697877584a285..33e6b76944ab8 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -1436,6 +1436,9 @@ int spinand_match_and_init(struct spinand_device *spinand, op = spinand_select_op_variant(spinand, info->op_variants.update_cache); + if (!op) + return -ENOTSUPP; + spinand->op_templates.update_cache = op; return 0; From d5de6d39a3bb980639ea64a19b167e1828670e66 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:06 +0100 Subject: [PATCH 0656/1518] mtd: spinand: Decouple write enable and write disable operations [ Upstream commit c0ba929cf7a960c796cc9946b3f79d8405e9b805 ] In order to introduce templates for all operations and not only for page helpers (in order to introduce octal DDR support), decouple the WR_EN and WR_DIS operations into two separate macros. Adapt the callers accordingly. There is no functional change. Reviewed-by: Tudor Ambarus Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/core.c | 2 +- drivers/mtd/nand/spi/esmt.c | 2 +- drivers/mtd/nand/spi/micron.c | 2 +- include/linux/mtd/spinand.h | 10 ++++++++-- 4 files changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 33e6b76944ab8..d3029ce2fe9ae 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -362,7 +362,7 @@ static void spinand_ondie_ecc_save_status(struct nand_device *nand, u8 status) int spinand_write_enable_op(struct spinand_device *spinand) { - struct spi_mem_op op = SPINAND_WR_EN_DIS_1S_0_0_OP(true); + struct spi_mem_op op = SPINAND_WR_EN_1S_0_0_OP; return spi_mem_exec_op(spinand->spimem, &op); } diff --git a/drivers/mtd/nand/spi/esmt.c b/drivers/mtd/nand/spi/esmt.c index 9a9325c0bc497..f880c3b15ceab 100644 --- a/drivers/mtd/nand/spi/esmt.c +++ b/drivers/mtd/nand/spi/esmt.c @@ -137,7 +137,7 @@ static int f50l1g41lb_user_otp_info(struct spinand_device *spinand, size_t len, static int f50l1g41lb_otp_lock(struct spinand_device *spinand, loff_t from, size_t len) { - struct spi_mem_op write_op = SPINAND_WR_EN_DIS_1S_0_0_OP(true); + struct spi_mem_op write_op = SPINAND_WR_EN_1S_0_0_OP; struct spi_mem_op exec_op = SPINAND_PROG_EXEC_1S_1S_0_OP(0); u8 status; int ret; diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c index a49d7cb6a96da..b8130e04e8e79 100644 --- a/drivers/mtd/nand/spi/micron.c +++ b/drivers/mtd/nand/spi/micron.c @@ -251,7 +251,7 @@ static int mt29f2g01abagd_user_otp_info(struct spinand_device *spinand, static int mt29f2g01abagd_otp_lock(struct spinand_device *spinand, loff_t from, size_t len) { - struct spi_mem_op write_op = SPINAND_WR_EN_DIS_1S_0_0_OP(true); + struct spi_mem_op write_op = SPINAND_WR_EN_1S_0_0_OP; struct spi_mem_op exec_op = SPINAND_PROG_EXEC_1S_1S_0_OP(0); u8 status; int ret; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 1c741145e4971..c74c9ba0cd0a4 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -26,8 +26,14 @@ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_OP_NO_DATA) -#define SPINAND_WR_EN_DIS_1S_0_0_OP(enable) \ - SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1), \ +#define SPINAND_WR_EN_1S_0_0_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x06, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_WR_DIS_1S_0_0_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x04, 1), \ SPI_MEM_OP_NO_ADDR, \ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_OP_NO_DATA) From 7298335371044a6d6d3c2ce07311433ad3ed12b7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:07 +0100 Subject: [PATCH 0657/1518] mtd: spinand: Create an array of operation templates [ Upstream commit 408015023294958407925bc50cdd85718d12a335 ] Currently, the SPI NAND core implementation directly calls macros to get the various operations in shape. These macros are specific to the bus interface, currently only supporting the single SDR interface (any command following the 1S-XX-XX pattern). Introducing support for other bus interfaces (such as octal DTR) would mean that every user of these macros should become aware of the current bus interface and act accordingly, picking up and adapting to the current configuration. This would add quite a bit of boilerplate, be repetitive as well as error prone in case we miss one occurrence. Instead, let's create a table with all SPI NAND memory operations that are currently supported. We initialize them with the same single SDR _OP macros as before. This opens the possibility for users of the individual macros to make use of these templates instead. This way, when we will add another bus interface, we can just switch to another set of templates and all users will magically fill in their spi_mem_op structures with the correct ops. The existing read, write and update cache variants are also moved in this template array, which is barely noticeable by callers as we also add a structure member pointing to it. Reviewed-by: Tudor Ambarus Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/core.c | 38 ++++++++++++++++++++++-------- drivers/mtd/nand/spi/winbond.c | 4 ++-- include/linux/mtd/spinand.h | 43 +++++++++++++++++++++++++++------- 3 files changed, 64 insertions(+), 21 deletions(-) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index d3029ce2fe9ae..5c1797946a047 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -184,9 +184,9 @@ static int spinand_init_quad_enable(struct spinand_device *spinand) if (!(spinand->flags & SPINAND_HAS_QE_BIT)) return 0; - if (spinand->op_templates.read_cache->data.buswidth == 4 || - spinand->op_templates.write_cache->data.buswidth == 4 || - spinand->op_templates.update_cache->data.buswidth == 4) + if (spinand->op_templates->read_cache->data.buswidth == 4 || + spinand->op_templates->write_cache->data.buswidth == 4 || + spinand->op_templates->update_cache->data.buswidth == 4) enable = true; return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE, @@ -1162,7 +1162,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand, info.offset = plane << fls(nand->memorg.pagesize); info.length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); - info.op_tmpl = *spinand->op_templates.update_cache; + info.op_tmpl = *spinand->op_templates->update_cache; desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev, spinand->spimem, &info); if (IS_ERR(desc)) @@ -1170,7 +1170,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand, spinand->dirmaps[plane].wdesc = desc; - info.op_tmpl = *spinand->op_templates.read_cache; + info.op_tmpl = *spinand->op_templates->read_cache; desc = spinand_create_rdesc(spinand, &info); if (IS_ERR(desc)) return PTR_ERR(desc); @@ -1185,7 +1185,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand, } info.length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); - info.op_tmpl = *spinand->op_templates.update_cache; + info.op_tmpl = *spinand->op_templates->update_cache; info.op_tmpl.data.ecc = true; desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev, spinand->spimem, &info); @@ -1194,7 +1194,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand, spinand->dirmaps[plane].wdesc_ecc = desc; - info.op_tmpl = *spinand->op_templates.read_cache; + info.op_tmpl = *spinand->op_templates->read_cache; info.op_tmpl.data.ecc = true; desc = spinand_create_rdesc(spinand, &info); if (IS_ERR(desc)) @@ -1330,6 +1330,22 @@ static void spinand_manufacturer_cleanup(struct spinand_device *spinand) return spinand->manufacturer->ops->cleanup(spinand); } +static void spinand_init_ssdr_templates(struct spinand_device *spinand) +{ + struct spinand_mem_ops *tmpl = &spinand->ssdr_op_templates; + + tmpl->reset = (struct spi_mem_op)SPINAND_RESET_1S_0_0_OP; + tmpl->readid = (struct spi_mem_op)SPINAND_READID_1S_1S_1S_OP(0, 0, NULL, 0); + tmpl->wr_en = (struct spi_mem_op)SPINAND_WR_EN_1S_0_0_OP; + tmpl->wr_dis = (struct spi_mem_op)SPINAND_WR_DIS_1S_0_0_OP; + tmpl->set_feature = (struct spi_mem_op)SPINAND_SET_FEATURE_1S_1S_1S_OP(0, NULL); + tmpl->get_feature = (struct spi_mem_op)SPINAND_GET_FEATURE_1S_1S_1S_OP(0, NULL); + tmpl->blk_erase = (struct spi_mem_op)SPINAND_BLK_ERASE_1S_1S_0_OP(0); + tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_1S_1S_0_OP(0); + tmpl->prog_exec = (struct spi_mem_op)SPINAND_PROG_EXEC_1S_1S_0_OP(0); + spinand->op_templates = &spinand->ssdr_op_templates; +} + static const struct spi_mem_op * spinand_select_op_variant(struct spinand_device *spinand, const struct spinand_op_variants *variants) @@ -1425,21 +1441,21 @@ int spinand_match_and_init(struct spinand_device *spinand, if (!op) return -ENOTSUPP; - spinand->op_templates.read_cache = op; + spinand->ssdr_op_templates.read_cache = op; op = spinand_select_op_variant(spinand, info->op_variants.write_cache); if (!op) return -ENOTSUPP; - spinand->op_templates.write_cache = op; + spinand->ssdr_op_templates.write_cache = op; op = spinand_select_op_variant(spinand, info->op_variants.update_cache); if (!op) return -ENOTSUPP; - spinand->op_templates.update_cache = op; + spinand->ssdr_op_templates.update_cache = op; return 0; } @@ -1554,6 +1570,8 @@ static int spinand_init(struct spinand_device *spinand) if (!spinand->scratchbuf) return -ENOMEM; + spinand_init_ssdr_templates(spinand); + ret = spinand_detect(spinand); if (ret) goto err_free_bufs; diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index af377b917a107..b389c9ee58508 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -291,7 +291,7 @@ static int w25n0xjw_hs_cfg(struct spinand_device *spinand) u8 sr4; int ret; - op = spinand->op_templates.read_cache; + op = spinand->op_templates->read_cache; if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) hs = false; else if (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && @@ -355,7 +355,7 @@ static int w35n0xjw_vcr_cfg(struct spinand_device *spinand) u8 io_mode; int ret; - op = spinand->op_templates.read_cache; + op = spinand->op_templates->read_cache; single = (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && op->data.buswidth == 1); dtr = (op->cmd.dtr || op->addr.dtr || op->data.dtr); diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index c74c9ba0cd0a4..3825fe9e759a6 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -604,6 +604,36 @@ struct spinand_dirmap { struct spi_mem_dirmap_desc *rdesc_ecc; }; +/** + * struct spinand_mem_ops - SPI NAND memory operations + * @reset: reset op template + * @readid: read ID op template + * @wr_en: write enable op template + * @wr_dis: write disable op template + * @set_feature: set feature op template + * @get_feature: get feature op template + * @blk_erase: blk erase op template + * @page_read: page read op template + * @prog_exec: prog exec op template + * @read_cache: read cache op template + * @write_cache: write cache op template + * @update_cache: update cache op template + */ +struct spinand_mem_ops { + struct spi_mem_op reset; + struct spi_mem_op readid; + struct spi_mem_op wr_en; + struct spi_mem_op wr_dis; + struct spi_mem_op set_feature; + struct spi_mem_op get_feature; + struct spi_mem_op blk_erase; + struct spi_mem_op page_read; + struct spi_mem_op prog_exec; + const struct spi_mem_op *read_cache; + const struct spi_mem_op *write_cache; + const struct spi_mem_op *update_cache; +}; + /** * struct spinand_device - SPI NAND device instance * @base: NAND device instance @@ -611,10 +641,8 @@ struct spinand_dirmap { * @lock: lock used to serialize accesses to the NAND * @id: NAND ID as returned by READ_ID * @flags: NAND flags - * @op_templates: various SPI mem op templates - * @op_templates.read_cache: read cache op template - * @op_templates.write_cache: write cache op template - * @op_templates.update_cache: update cache op template + * @ssdr_op_templates: Templates for all single SDR SPI mem operations + * @op_templates: Templates for all SPI mem operations * @select_target: select a specific target/die. Usually called before sending * a command addressing a page or an eraseblock embedded in * this die. Only required if your chip exposes several dies @@ -648,11 +676,8 @@ struct spinand_device { struct spinand_id id; u32 flags; - struct { - const struct spi_mem_op *read_cache; - const struct spi_mem_op *write_cache; - const struct spi_mem_op *update_cache; - } op_templates; + struct spinand_mem_ops ssdr_op_templates; + struct spinand_mem_ops *op_templates; struct spinand_dirmap *dirmaps; From a5d27efc8e4f912b083a18423c85c81585a721fc Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:17 +0100 Subject: [PATCH 0658/1518] mtd: spinand: winbond: Rename IO_MODE register macro [ Upstream commit 57e1015cc9a96372f330195abe32a904ec8d1eab ] Suffix the macro name with *_REG to align with the rest of the driver. Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/winbond.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index b389c9ee58508..2361109101727 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -22,7 +22,7 @@ #define W25N0XJW_SR4 0xD0 #define W25N0XJW_SR4_HS BIT(2) -#define W35N01JW_VCR_IO_MODE 0x00 +#define W35N01JW_VCR_IO_MODE_REG 0x00 #define W35N01JW_VCR_IO_MODE_SINGLE_SDR 0xFF #define W35N01JW_VCR_IO_MODE_OCTAL_SDR 0xDF #define W35N01JW_VCR_IO_MODE_OCTAL_DDR_DS 0xE7 @@ -368,7 +368,7 @@ static int w35n0xjw_vcr_cfg(struct spinand_device *spinand) else return -EINVAL; - ret = w35n0xjw_write_vcr(spinand, W35N01JW_VCR_IO_MODE, io_mode); + ret = w35n0xjw_write_vcr(spinand, W35N01JW_VCR_IO_MODE_REG, io_mode); if (ret) return ret; From a602b7efb876d1086883d1bc227c9e3776ea341d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:18 +0100 Subject: [PATCH 0659/1518] mtd: spinand: winbond: Configure the IO mode after the dummy cycles [ Upstream commit ef1ed296fb9d9246256e1b5b2cf2e86e85606ac3 ] When we will change the bus interface, the action that actually performs the transition is the IO mode register write. This means after the IO mode register write, we should use the new bus interface. But the ->configure_chip() hook itself is not responsible of making this change official, it is the caller that must act according to the return value. Reorganize this helper to first configure the dummy cycles before possibly switching to another bus interface. Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/winbond.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 2361109101727..6cb5dd45e6fb7 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -357,21 +357,6 @@ static int w35n0xjw_vcr_cfg(struct spinand_device *spinand) op = spinand->op_templates->read_cache; - single = (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && op->data.buswidth == 1); - dtr = (op->cmd.dtr || op->addr.dtr || op->data.dtr); - if (single && !dtr) - io_mode = W35N01JW_VCR_IO_MODE_SINGLE_SDR; - else if (!single && !dtr) - io_mode = W35N01JW_VCR_IO_MODE_OCTAL_SDR; - else if (!single && dtr) - io_mode = W35N01JW_VCR_IO_MODE_OCTAL_DDR; - else - return -EINVAL; - - ret = w35n0xjw_write_vcr(spinand, W35N01JW_VCR_IO_MODE_REG, io_mode); - if (ret) - return ret; - dummy_cycles = ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1); switch (dummy_cycles) { case 8: @@ -388,6 +373,21 @@ static int w35n0xjw_vcr_cfg(struct spinand_device *spinand) if (ret) return ret; + single = (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && op->data.buswidth == 1); + dtr = (op->cmd.dtr && op->addr.dtr && op->data.dtr); + if (single && !dtr) + io_mode = W35N01JW_VCR_IO_MODE_SINGLE_SDR; + else if (!single && !dtr) + io_mode = W35N01JW_VCR_IO_MODE_OCTAL_SDR; + else if (!single && dtr) + io_mode = W35N01JW_VCR_IO_MODE_OCTAL_DDR; + else + return -EINVAL; + + ret = w35n0xjw_write_vcr(spinand, W35N01JW_VCR_IO_MODE_REG, io_mode); + if (ret) + return ret; + return 0; } From d4e22374b9b01139a350c30b181caab8e34166e7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:19 +0100 Subject: [PATCH 0660/1518] mtd: spinand: Gather all the bus interface steps in one single function [ Upstream commit be0b86c648bf811237cc17e274e9f9488fccb772 ] Writing the quad enable bit in one helper and doing the chip configuration in another does not make much sense from a bus interface setup point of view. Instead, let's create a broader helper which is going to be in charge of all the bus configuration steps at once. This will specifically allow to transition to octal DDR mode, and even fallback to quad (if suppoorted) or single mode otherwise. Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/core.c | 62 ++++++++++++++++++++++--------------- 1 file changed, 37 insertions(+), 25 deletions(-) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 5c1797946a047..b88f30ed746fc 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -177,18 +177,9 @@ static int spinand_init_cfg_cache(struct spinand_device *spinand) return 0; } -static int spinand_init_quad_enable(struct spinand_device *spinand) +static int spinand_init_quad_enable(struct spinand_device *spinand, + bool enable) { - bool enable = false; - - if (!(spinand->flags & SPINAND_HAS_QE_BIT)) - return 0; - - if (spinand->op_templates->read_cache->data.buswidth == 4 || - spinand->op_templates->write_cache->data.buswidth == 4 || - spinand->op_templates->update_cache->data.buswidth == 4) - enable = true; - return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE, enable ? CFG_QUAD_ENABLE : 0); } @@ -1314,12 +1305,6 @@ static int spinand_manufacturer_init(struct spinand_device *spinand) return ret; } - if (spinand->configure_chip) { - ret = spinand->configure_chip(spinand); - if (ret) - return ret; - } - return 0; } @@ -1496,6 +1481,31 @@ static int spinand_detect(struct spinand_device *spinand) return 0; } +static int spinand_configure_chip(struct spinand_device *spinand) +{ + bool quad_enable = false; + int ret; + + if (spinand->flags & SPINAND_HAS_QE_BIT) { + if (spinand->ssdr_op_templates.read_cache->data.buswidth == 4 || + spinand->ssdr_op_templates.write_cache->data.buswidth == 4 || + spinand->ssdr_op_templates.update_cache->data.buswidth == 4) + quad_enable = true; + } + + ret = spinand_init_quad_enable(spinand, quad_enable); + if (ret) + return ret; + + if (spinand->configure_chip) { + ret = spinand->configure_chip(spinand); + if (ret) + return ret; + } + + return ret; +} + static int spinand_init_flash(struct spinand_device *spinand) { struct device *dev = &spinand->spimem->spi->dev; @@ -1506,10 +1516,6 @@ static int spinand_init_flash(struct spinand_device *spinand) if (ret) return ret; - ret = spinand_init_quad_enable(spinand); - if (ret) - return ret; - ret = spinand_upd_cfg(spinand, CFG_OTP_ENABLE, 0); if (ret) return ret; @@ -1522,19 +1528,25 @@ static int spinand_init_flash(struct spinand_device *spinand) return ret; } + ret = spinand_configure_chip(spinand); + if (ret) + goto manuf_cleanup; + /* After power up, all blocks are locked, so unlock them here. */ for (i = 0; i < nand->memorg.ntargets; i++) { ret = spinand_select_target(spinand, i); if (ret) - break; + goto manuf_cleanup; ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED); if (ret) - break; + goto manuf_cleanup; } - if (ret) - spinand_manufacturer_cleanup(spinand); + return 0; + +manuf_cleanup: + spinand_manufacturer_cleanup(spinand); return ret; } From 6a5f5c25fb1f2c39be4fd4df309de7270f32e4ea Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:20 +0100 Subject: [PATCH 0661/1518] mtd: spinand: Add support for setting a bus interface [ Upstream commit 20387f2fe509eba46ecf758da052786d7b1203fb ] Create a bus interface enumeration, currently only containing the one we support: SSDR, for single SDR, so any operation whose command is sent over a single data line in SDR mode, ie. any operation matching 1S-XX-XX. The main spinand_device structure gets a new parameter to store this enumeration, for now unused. Of course it is set to SSDR during the SSDR templates initialization to further clarify the state we are in at the moment. This member is subject to be used to know in which bus configuration we and be updated by the core when we switch to faster mode(s). Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/core.c | 1 + include/linux/mtd/spinand.h | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index b88f30ed746fc..9f6682c0af102 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -1329,6 +1329,7 @@ static void spinand_init_ssdr_templates(struct spinand_device *spinand) tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_1S_1S_0_OP(0); tmpl->prog_exec = (struct spi_mem_op)SPINAND_PROG_EXEC_1S_1S_0_OP(0); spinand->op_templates = &spinand->ssdr_op_templates; + spinand->bus_iface = SSDR; } static const struct spi_mem_op * diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 3825fe9e759a6..c991c6c3bdedf 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -486,6 +486,14 @@ struct spinand_user_otp { const struct spinand_user_otp_ops *ops; }; +/** + * enum spinand_bus_interface - SPI NAND bus interface types + * @SSDR: Bus configuration supporting all 1S-XX-XX operations, including dual and quad + */ +enum spinand_bus_interface { + SSDR, +}; + /** * struct spinand_info - Structure used to describe SPI NAND chips * @model: model name @@ -643,6 +651,7 @@ struct spinand_mem_ops { * @flags: NAND flags * @ssdr_op_templates: Templates for all single SDR SPI mem operations * @op_templates: Templates for all SPI mem operations + * @bus_iface: Current bus interface * @select_target: select a specific target/die. Usually called before sending * a command addressing a page or an eraseblock embedded in * this die. Only required if your chip exposes several dies @@ -678,6 +687,7 @@ struct spinand_device { struct spinand_mem_ops ssdr_op_templates; struct spinand_mem_ops *op_templates; + enum spinand_bus_interface bus_iface; struct spinand_dirmap *dirmaps; From 52aaa647b02d0f9f81a36746e244ded9e82214f2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 9 Jan 2026 18:18:22 +0100 Subject: [PATCH 0662/1518] mtd: spinand: Give the bus interface to the configuration helper [ Upstream commit 0a331a1851aedd670b95a2d16c6a82496137378d ] The chip configuration hook is the one responsible to actually switch the switch between bus interfaces. It is natural to give it the bus interface we expect with a new parameter. For now the only value we can give is SSDR, but this is subject to change in the future, so add a bit of extra logic in the implementations of this callback to make sure both the core and the chip driver are aligned on the request. Signed-off-by: Miquel Raynal Stable-dep-of: 25a915fad503 ("mtd: spinand: winbond: Clarify when to enable the HS bit") Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/core.c | 2 +- drivers/mtd/nand/spi/winbond.c | 28 +++++++++++++++++++++------- include/linux/mtd/spinand.h | 6 ++++-- 3 files changed, 26 insertions(+), 10 deletions(-) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 9f6682c0af102..2f656a5e4af89 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -1499,7 +1499,7 @@ static int spinand_configure_chip(struct spinand_device *spinand) return ret; if (spinand->configure_chip) { - ret = spinand->configure_chip(spinand); + ret = spinand->configure_chip(spinand, SSDR); if (ret) return ret; } diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 6cb5dd45e6fb7..0ea5b1c97d33d 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -284,13 +284,17 @@ static int w25n02kv_ecc_get_status(struct spinand_device *spinand, return -EINVAL; } -static int w25n0xjw_hs_cfg(struct spinand_device *spinand) +static int w25n0xjw_hs_cfg(struct spinand_device *spinand, + enum spinand_bus_interface iface) { const struct spi_mem_op *op; bool hs; u8 sr4; int ret; + if (iface != SSDR) + return -EOPNOTSUPP; + op = spinand->op_templates->read_cache; if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) hs = false; @@ -347,17 +351,25 @@ static int w35n0xjw_write_vcr(struct spinand_device *spinand, u8 reg, u8 val) return 0; } -static int w35n0xjw_vcr_cfg(struct spinand_device *spinand) +static int w35n0xjw_vcr_cfg(struct spinand_device *spinand, + enum spinand_bus_interface iface) { - const struct spi_mem_op *op; + const struct spi_mem_op *ref_op; unsigned int dummy_cycles; bool dtr, single; u8 io_mode; int ret; - op = spinand->op_templates->read_cache; + switch (iface) { + case SSDR: + ref_op = spinand->ssdr_op_templates.read_cache; + break; + default: + return -EOPNOTSUPP; + }; - dummy_cycles = ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1); + dummy_cycles = ((ref_op->dummy.nbytes * 8) / ref_op->dummy.buswidth) / + (ref_op->dummy.dtr ? 2 : 1); switch (dummy_cycles) { case 8: case 12: @@ -373,8 +385,10 @@ static int w35n0xjw_vcr_cfg(struct spinand_device *spinand) if (ret) return ret; - single = (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && op->data.buswidth == 1); - dtr = (op->cmd.dtr && op->addr.dtr && op->data.dtr); + single = (ref_op->cmd.buswidth == 1 && + ref_op->addr.buswidth == 1 && + ref_op->data.buswidth == 1); + dtr = (ref_op->cmd.dtr && ref_op->addr.dtr && ref_op->data.dtr); if (single && !dtr) io_mode = W35N01JW_VCR_IO_MODE_SINGLE_SDR; else if (!single && !dtr) diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index c991c6c3bdedf..07e4d87019c64 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -532,7 +532,8 @@ struct spinand_info { } op_variants; int (*select_target)(struct spinand_device *spinand, unsigned int target); - int (*configure_chip)(struct spinand_device *spinand); + int (*configure_chip)(struct spinand_device *spinand, + enum spinand_bus_interface iface); int (*set_cont_read)(struct spinand_device *spinand, bool enable); struct spinand_fact_otp fact_otp; @@ -704,7 +705,8 @@ struct spinand_device { const struct spinand_manufacturer *manufacturer; void *priv; - int (*configure_chip)(struct spinand_device *spinand); + int (*configure_chip)(struct spinand_device *spinand, + enum spinand_bus_interface iface); bool cont_read_possible; int (*set_cont_read)(struct spinand_device *spinand, bool enable); From c3a6ee43246d4dc5e7d9fd0b7fd9685fb8d5191b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 18 Mar 2026 11:47:50 +0100 Subject: [PATCH 0663/1518] mtd: spinand: winbond: Clarify when to enable the HS bit [ Upstream commit 25a915fad503c2678902075565d47ddc2aa45db9 ] Above 104MHz when in fast dual or quad I/O reads, the delay between address and data cycles is too short. It is possible to reach higher frequencies, up to 166MHz, by adding a few more dummy cycles through the setting of the HS bit. Improve the condition for enabling this bit, and also make sure we set it at soon as we go over 104MHz. Fixes: f1a91175faaa ("mtd: spinand: winbond: Enable high-speed modes on w25n0xjw") Signed-off-by: Miquel Raynal Signed-off-by: Sasha Levin --- drivers/mtd/nand/spi/winbond.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 0ea5b1c97d33d..578924c98b90a 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -295,16 +295,19 @@ static int w25n0xjw_hs_cfg(struct spinand_device *spinand, if (iface != SSDR) return -EOPNOTSUPP; + /* + * SDR dual and quad I/O operations over 104MHz require the HS bit to + * enable a few more dummy cycles. + */ op = spinand->op_templates->read_cache; if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) hs = false; - else if (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && - op->dummy.buswidth == 1 && op->data.buswidth == 1) + else if (op->cmd.buswidth != 1 || op->addr.buswidth == 1) hs = false; - else if (!op->max_freq) - hs = true; - else + else if (op->max_freq && op->max_freq <= 104 * HZ_PER_MHZ) hs = false; + else + hs = true; ret = spinand_read_reg_op(spinand, W25N0XJW_SR4, &sr4); if (ret) From c7abd0e6c87441e99c759d40eb6fe589634e3041 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 24 Mar 2026 15:24:54 +0100 Subject: [PATCH 0664/1518] HID: usbhid: fix deadlock in hid_post_reset() [ Upstream commit 8df2c1b47ee3cd50fd454f75c7a7e2ae8a6adf72 ] You can build a USB device that includes a HID component and a storage or UAS component. The components can be reset only together. That means that hid_pre_reset() and hid_post_reset() are in the block IO error handling. Hence no memory allocation used in them may do block IO because the IO can deadlock on the mutex held while resetting a device and calling the interface drivers. Use GFP_NOIO for all allocations in them. Fixes: dc3c78e434690 ("HID: usbhid: Check HID report descriptor contents after device reset") Signed-off-by: Oliver Neukum Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/usbhid/hid-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 758eb21430cda..df3cc89dfb37f 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -1552,7 +1552,7 @@ static int hid_post_reset(struct usb_interface *intf) * configuration descriptors passed, we already know that * the size of the HID report descriptor has not changed. */ - rdesc = kmalloc(hid->dev_rsize, GFP_KERNEL); + rdesc = kmalloc(hid->dev_rsize, GFP_NOIO); if (!rdesc) return -ENOMEM; From 07793ce19221444556b91a615ffcc9ac8fe258ac Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Mon, 30 Mar 2026 21:30:35 +0800 Subject: [PATCH 0665/1518] ext4: fix possible null-ptr-deref in mbt_kunit_exit() [ Upstream commit 22f53f08d9eb837ce69b1a07641d414aac8d045f ] There's issue as follows: # test_new_blocks_simple: failed to initialize: -12 KASAN: null-ptr-deref in range [0x0000000000000638-0x000000000000063f] Tainted: [E]=UNSIGNED_MODULE, [N]=TEST RIP: 0010:mbt_kunit_exit+0x5e/0x3e0 [ext4_test] Call Trace: kunit_try_run_case_cleanup+0xbc/0x100 [kunit] kunit_generic_run_threadfn_adapter+0x89/0x100 [kunit] kthread+0x408/0x540 ret_from_fork+0xa76/0xdf0 ret_from_fork_asm+0x1a/0x30 If mbt_kunit_init() init testcase failed will lead to null-ptr-deref. So add test if 'sb' is inited success in mbt_kunit_exit(). Fixes: 7c9fa399a369 ("ext4: add first unit test for ext4_mb_new_blocks_simple in mballoc") Signed-off-by: Ye Bin Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Ojaswin Mujoo Link: https://patch.msgid.link/20260330133035.287842-6-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc-test.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c index 4abb40d4561ce..68aab8e45bc37 100644 --- a/fs/ext4/mballoc-test.c +++ b/fs/ext4/mballoc-test.c @@ -362,7 +362,6 @@ static int mbt_kunit_init(struct kunit *test) return ret; } - test->priv = sb; kunit_activate_static_stub(test, ext4_read_block_bitmap_nowait, ext4_read_block_bitmap_nowait_stub); @@ -383,6 +382,8 @@ static int mbt_kunit_init(struct kunit *test) return -ENOMEM; } + test->priv = sb; + return 0; } @@ -390,6 +391,9 @@ static void mbt_kunit_exit(struct kunit *test) { struct super_block *sb = (struct super_block *)test->priv; + if (!sb) + return; + mbt_mb_release(sb); mbt_ctx_release(sb); mbt_ext4_free_super_block(sb); From 1a113b5497297871699cd498b1b83542e0db7f15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Apr 2026 14:14:03 +0200 Subject: [PATCH 0666/1518] bpf, arm64: Fix off-by-one in check_imm signed range check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1dd8be4ec722ce54e4cace59f3a4ba658111b3ec ] check_imm(bits, imm) is used in the arm64 BPF JIT to verify that a branch displacement (in arm64 instruction units) fits into the signed N-bit immediate field of a B, B.cond or CBZ/CBNZ encoding before it is handed to the encoder. The macro currently tests for (imm > 0 && imm >> bits) || (imm < 0 && ~imm >> bits) which admits values in [-2^N, 2^N) — effectively a signed (N+1)-bit range. A signed N-bit field only holds [-2^(N-1), 2^(N-1)), so the check admits one extra bit of range on each side. In particular, for check_imm19(), values in [2^18, 2^19) slip past the check but do not fit into the 19-bit signed imm19 field of B.cond. aarch64_insn_encode_immediate() then masks the raw value into the 19-bit field, setting bit 18 (the sign bit) and flipping a forward branch into a backward one. Same class of issue exists for check_imm26() and the B/BL encoding. Shift by (bits - 1) instead of bits so the actual signed N-bit range is enforced. Fixes: e54bcde3d69d ("arm64: eBPF JIT compiler") Signed-off-by: Daniel Borkmann Reviewed-by: Puranjay Mohan Link: https://lore.kernel.org/r/20260415121403.639619-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- arch/arm64/net/bpf_jit_comp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 107eb71b533a0..4b2aacdd43221 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -35,8 +35,8 @@ #define ARENA_VM_START (MAX_BPF_JIT_REG + 5) #define check_imm(bits, imm) do { \ - if ((((imm) > 0) && ((imm) >> (bits))) || \ - (((imm) < 0) && (~(imm) >> (bits)))) { \ + if ((((imm) > 0) && ((imm) >> ((bits) - 1))) || \ + (((imm) < 0) && (~(imm) >> ((bits) - 1)))) { \ pr_info("[%2d] imm=%d(0x%x) out of range\n", \ i, imm, imm); \ return -EINVAL; \ From ca51684db023e96faf5d8fe94b5f9322e73dd675 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Mon, 13 Apr 2026 12:11:08 -0700 Subject: [PATCH 0667/1518] bpf, arm64: Remove redundant bpf_flush_icache() after pack allocator finalize [ Upstream commit 42f18ae53011826cfd3c84d041817e7f07bc645b ] bpf_flush_icache() calls flush_icache_range() to clean the data cache and invalidate the instruction cache for the JITed code region. However, since commit 1dad391daef1 ("bpf, arm64: use bpf_prog_pack for memory management"), this flush is redundant. bpf_jit_binary_pack_finalize() copies the JITed instructions to the ROX region via bpf_arch_text_copy() -> aarch64_insn_copy() -> __text_poke(), and __text_poke() already calls flush_icache_range() on the written range. The subsequent bpf_flush_icache() repeats the same cache maintenance on an overlapping range, including an unnecessary second synchronous IPI to all CPUs via kick_all_cpus_sync(). Remove the redundant bpf_flush_icache() call and its now-unused definition. Fixes: 1dad391daef1 ("bpf, arm64: use bpf_prog_pack for memory management") Acked-by: Song Liu Signed-off-by: Puranjay Mohan Acked-by: Breno Leitao Link: https://lore.kernel.org/r/20260413191111.3426023-2-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- arch/arm64/net/bpf_jit_comp.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 4b2aacdd43221..873c1b784a872 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -18,7 +18,6 @@ #include #include -#include #include #include #include @@ -1964,11 +1963,6 @@ static int validate_ctx(struct jit_ctx *ctx) return 0; } -static inline void bpf_flush_icache(void *start, void *end) -{ - flush_icache_range((unsigned long)start, (unsigned long)end); -} - static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size) { int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3; @@ -2207,12 +2201,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_off; } - /* - * The instructions have now been copied to the ROX region from - * where they will execute. Now the data cache has to be cleaned to - * the PoU and the I-cache has to be invalidated for the VAs. - */ - bpf_flush_icache(ro_header, ctx.ro_image + ctx.idx); } else { jit_data->ctx = ctx; jit_data->ro_image = ro_image_ptr; From 77ad43af264215d33b6a3a1ced1dbdaa3a85fc5c Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Mon, 13 Apr 2026 12:11:09 -0700 Subject: [PATCH 0668/1518] bpf, riscv: Remove redundant bpf_flush_icache() after pack allocator finalize [ Upstream commit 46ee1342b887c9387a933397d846ff6c9584322c ] bpf_flush_icache() calls flush_icache_range() to clean the data cache and invalidate the instruction cache for the JITed code region. However, since commit 48a8f78c50bd ("bpf, riscv: use prog pack allocator in the BPF JIT"), this flush is redundant. bpf_jit_binary_pack_finalize() copies the JITed instructions to the ROX region via bpf_arch_text_copy() -> patch_text_nosync(), and patch_text_nosync() already calls flush_icache_range() on the written range. The subsequent bpf_flush_icache() repeats the same cache maintenance on an overlapping range. Remove the redundant bpf_flush_icache() call and its now-unused definition. Fixes: 48a8f78c50bd ("bpf, riscv: use prog pack allocator in the BPF JIT") Acked-by: Song Liu Signed-off-by: Puranjay Mohan Reviewed-by: Pu Lehui Tested-by: Paul Chaignon Link: https://lore.kernel.org/r/20260413191111.3426023-3-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- arch/riscv/net/bpf_jit.h | 6 ------ arch/riscv/net/bpf_jit_core.c | 7 ------- 2 files changed, 13 deletions(-) diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 632ced07bca44..da02717902442 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -11,7 +11,6 @@ #include #include -#include /* verify runtime detection extension status */ #define rv_ext_enabled(ext) \ @@ -105,11 +104,6 @@ static inline void bpf_fill_ill_insns(void *area, unsigned int size) memset(area, 0, size); } -static inline void bpf_flush_icache(void *start, void *end) -{ - flush_icache_range((unsigned long)start, (unsigned long)end); -} - /* Emit a 4-byte riscv instruction. */ static inline void emit(const u32 insn, struct rv_jit_context *ctx) { diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index f6ca5cfa6b2fd..191bf0e66c824 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -183,13 +183,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } - /* - * The instructions have now been copied to the ROX region from - * where they will execute. - * Write any modified data cache blocks out to memory and - * invalidate the corresponding blocks in the instruction cache. - */ - bpf_flush_icache(jit_data->ro_header, ctx->ro_insns + ctx->ninsns); for (i = 0; i < prog->len; i++) ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); From 527057ebe8076dfbcaef51195ff1b7508646be2c Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Tue, 14 Apr 2026 16:13:16 +0200 Subject: [PATCH 0669/1518] bpf, sockmap: Fix af_unix iter deadlock [ Upstream commit 4d328dd695383224aa750ddee6b4ad40c0f8d205 ] bpf_iter_unix_seq_show() may deadlock when lock_sock_fast() takes the fast path and the iter prog attempts to update a sockmap. Which ends up spinning at sock_map_update_elem()'s bh_lock_sock(): WARNING: possible recursive locking detected test_progs/1393 is trying to acquire lock: ffff88811ec25f58 (slock-AF_UNIX){+...}-{3:3}, at: sock_map_update_elem+0xdb/0x1f0 but task is already holding lock: ffff88811ec25f58 (slock-AF_UNIX){+...}-{3:3}, at: __lock_sock_fast+0x37/0xe0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(slock-AF_UNIX); lock(slock-AF_UNIX); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by test_progs/1393: #0: ffff88814b59c790 (&p->lock){+.+.}-{4:4}, at: bpf_seq_read+0x59/0x10d0 #1: ffff88811ec25fd8 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: bpf_seq_read+0x42c/0x10d0 #2: ffff88811ec25f58 (slock-AF_UNIX){+...}-{3:3}, at: __lock_sock_fast+0x37/0xe0 #3: ffffffff85a6a7c0 (rcu_read_lock){....}-{1:3}, at: bpf_iter_run_prog+0x51d/0xb00 Call Trace: dump_stack_lvl+0x5d/0x80 print_deadlock_bug.cold+0xc0/0xce __lock_acquire+0x130f/0x2590 lock_acquire+0x14e/0x2b0 _raw_spin_lock+0x30/0x40 sock_map_update_elem+0xdb/0x1f0 bpf_prog_2d0075e5d9b721cd_dump_unix+0x55/0x4f4 bpf_iter_run_prog+0x5b9/0xb00 bpf_iter_unix_seq_show+0x1f7/0x2e0 bpf_seq_read+0x42c/0x10d0 vfs_read+0x171/0xb20 ksys_read+0xff/0x200 do_syscall_64+0x6b/0x3a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fixes: 2c860a43dd77 ("bpf: af_unix: Implement BPF iterator for UNIX domain socket.") Suggested-by: Kuniyuki Iwashima Suggested-by: Martin KaFai Lau Signed-off-by: Michal Luczaj Signed-off-by: Martin KaFai Lau Reviewed-by: Jiayuan Chen Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260414-unix-proto-update-null-ptr-deref-v4-2-2af6fe97918e@rbox.co Signed-off-by: Sasha Levin --- net/unix/af_unix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a09c732748945..cf022252d521c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3773,15 +3773,14 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) struct bpf_prog *prog; struct sock *sk = v; uid_t uid; - bool slow; int ret; if (v == SEQ_START_TOKEN) return 0; - slow = lock_sock_fast(sk); + lock_sock(sk); - if (unlikely(sk_unhashed(sk))) { + if (unlikely(sock_flag(sk, SOCK_DEAD))) { ret = SEQ_SKIP; goto unlock; } @@ -3791,7 +3790,7 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) prog = bpf_iter_get_info(&meta, false); ret = unix_prog_seq_show(prog, &meta, v, uid); unlock: - unlock_sock_fast(sk, slow); + release_sock(sk); return ret; } From 041eb6348d73ee5e15fc8161f1eac5a6e8289ca0 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Tue, 14 Apr 2026 16:13:18 +0200 Subject: [PATCH 0670/1518] bpf, sockmap: Fix af_unix null-ptr-deref in proto update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dca38b7734d2ea00af4818ff3ae836fab33d5d5a ] unix_stream_connect() sets sk_state (`WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED)`) _before_ it assigns a peer (`unix_peer(sk) = newsk`). sk_state == TCP_ESTABLISHED makes sock_map_sk_state_allowed() believe that socket is properly set up, which would include having a defined peer. IOW, there's a window when unix_stream_bpf_update_proto() can be called on socket which still has unix_peer(sk) == NULL. CPU0 bpf CPU1 connect -------- ------------ WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED) sock_map_sk_state_allowed(sk) ... sk_pair = unix_peer(sk) sock_hold(sk_pair) sock_hold(newsk) smp_mb__after_atomic() unix_peer(sk) = newsk BUG: kernel NULL pointer dereference, address: 0000000000000080 RIP: 0010:unix_stream_bpf_update_proto+0xa0/0x1b0 Call Trace: sock_map_link+0x564/0x8b0 sock_map_update_common+0x6e/0x340 sock_map_update_elem_sys+0x17d/0x240 __sys_bpf+0x26db/0x3250 __x64_sys_bpf+0x21/0x30 do_syscall_64+0x6b/0x3a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Initial idea was to move peer assignment _before_ the sk_state update[1], but that involved an additional memory barrier, and changing the hot path was rejected. Then a NULL check during proto update in unix_stream_bpf_update_proto() was considered[2], but the follow-up discussion[3] focused on the root cause, i.e. sockmap update taking a wrong lock. Or, more specifically, missing unix_state_lock()[4]. In the end it was concluded that teaching sockmap about the af_unix locking would be unnecessarily complex[5]. Complexity aside, since BPF_PROG_TYPE_SCHED_CLS and BPF_PROG_TYPE_SCHED_ACT are allowed to update sockmaps, sock_map_update_elem() taking the unix lock, as it is currently implemented in unix_state_lock(): spin_lock(&unix_sk(s)->lock), would be problematic. unix_state_lock() taken in a process context, followed by a softirq-context TC BPF program attempting to take the same spinlock -- deadlock[6]. This way we circled back to the peer check idea[2]. [1]: https://lore.kernel.org/netdev/ba5c50aa-1df4-40c2-ab33-a72022c5a32e@rbox.co/ [2]: https://lore.kernel.org/netdev/20240610174906.32921-1-kuniyu@amazon.com/ [3]: https://lore.kernel.org/netdev/7603c0e6-cd5b-452b-b710-73b64bd9de26@linux.dev/ [4]: https://lore.kernel.org/netdev/CAAVpQUA+8GL_j63CaKb8hbxoL21izD58yr1NvhOhU=j+35+3og@mail.gmail.com/ [5]: https://lore.kernel.org/bpf/CAAVpQUAHijOMext28Gi10dSLuMzGYh+jK61Ujn+fZ-wvcODR2A@mail.gmail.com/ [6]: https://lore.kernel.org/bpf/dd043c69-4d03-46fe-8325-8f97101435cf@linux.dev/ Summary of scenarios where af_unix/stream connect() may race a sockmap update: 1. connect() vs. bpf(BPF_MAP_UPDATE_ELEM), i.e. sock_map_update_elem_sys() Implemented NULL check is sufficient. Once assigned, socket peer won't be released until socket fd is released. And that's not an issue because sock_map_update_elem_sys() bumps fd refcnf. 2. connect() vs BPF program doing update Update restricted per verifier.c:may_update_sockmap() to BPF_PROG_TYPE_TRACING/BPF_TRACE_ITER BPF_PROG_TYPE_SOCK_OPS (bpf_sock_map_update() only) BPF_PROG_TYPE_SOCKET_FILTER BPF_PROG_TYPE_SCHED_CLS BPF_PROG_TYPE_SCHED_ACT BPF_PROG_TYPE_XDP BPF_PROG_TYPE_SK_REUSEPORT BPF_PROG_TYPE_FLOW_DISSECTOR BPF_PROG_TYPE_SK_LOOKUP Plus one more race to consider: CPU0 bpf CPU1 connect -------- ------------ WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED) sock_map_sk_state_allowed(sk) sock_hold(newsk) smp_mb__after_atomic() unix_peer(sk) = newsk sk_pair = unix_peer(sk) if (unlikely(!sk_pair)) return -EINVAL; CPU1 close ---------- skpair = unix_peer(sk); unix_peer(sk) = NULL; sock_put(skpair) // use after free? sock_hold(sk_pair) 2.1 BPF program invoking helper function bpf_sock_map_update() -> BPF_CALL_4(bpf_sock_map_update(), ...) Helper limited to BPF_PROG_TYPE_SOCK_OPS. Nevertheless, a unix sock might be accessible via bpf_map_lookup_elem(). Which implies sk already having psock, which in turn implies sk already having sk_pair. Since sk_psock_destroy() is queued as RCU work, sk_pair won't go away while BPF executes the update. 2.2 BPF program invoking helper function bpf_map_update_elem() -> sock_map_update_elem() 2.2.1 Unix sock accessible to BPF prog only via sockmap lookup in BPF_PROG_TYPE_SOCKET_FILTER, BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_SK_LOOKUP. Pretty much the same as case 2.1. 2.2.2 Unix sock accessible to BPF program directly: BPF_PROG_TYPE_TRACING, narrowed down to BPF_TRACE_ITER. Sockmap iterator (sock_map_seq_ops) is safe: unix sock residing in a sockmap means that the sock already went through the proto update step. Unix sock iterator (bpf_iter_unix_seq_ops), on the other hand, gives access to socks that may still be unconnected. Which means iterator prog can race sockmap/proto update against connect(). BUG: KASAN: null-ptr-deref in unix_stream_bpf_update_proto+0x253/0x4d0 Write of size 4 at addr 0000000000000080 by task test_progs/3140 Call Trace: dump_stack_lvl+0x5d/0x80 kasan_report+0xe4/0x1c0 kasan_check_range+0x125/0x200 unix_stream_bpf_update_proto+0x253/0x4d0 sock_map_link+0x71c/0xec0 sock_map_update_common+0xbc/0x600 sock_map_update_elem+0x19a/0x1f0 bpf_prog_bbbf56096cdd4f01_selective_dump_unix+0x20c/0x217 bpf_iter_run_prog+0x21e/0xae0 bpf_iter_unix_seq_show+0x1e0/0x2a0 bpf_seq_read+0x42c/0x10d0 vfs_read+0x171/0xb20 ksys_read+0xff/0x200 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e While the introduced NULL check prevents null-ptr-deref in the BPF program path as well, it is insufficient to guard against a poorly timed close() leading to a use-after-free. This will be addressed in a subsequent patch. Fixes: c63829182c37 ("af_unix: Implement ->psock_update_sk_prot()") Closes: https://lore.kernel.org/netdev/ba5c50aa-1df4-40c2-ab33-a72022c5a32e@rbox.co/ Reported-by: Michal Luczaj Reported-by: 钱一铭 Suggested-by: Kuniyuki Iwashima Suggested-by: Martin KaFai Lau Signed-off-by: Michal Luczaj Signed-off-by: Martin KaFai Lau Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260414-unix-proto-update-null-ptr-deref-v4-4-2af6fe97918e@rbox.co Signed-off-by: Sasha Levin --- net/unix/unix_bpf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index e0d30d6d22acb..57f3124c9d8db 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -185,6 +185,9 @@ int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool r */ if (!psock->sk_pair) { sk_pair = unix_peer(sk); + if (unlikely(!sk_pair)) + return -EINVAL; + sock_hold(sk_pair); psock->sk_pair = sk_pair; } From 921920c34cb591947dd30c692500795a69f1e3fa Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Tue, 14 Apr 2026 16:13:19 +0200 Subject: [PATCH 0671/1518] bpf, sockmap: Take state lock for af_unix iter [ Upstream commit 64c2f93fc3254d3bf5de4445fb732ee5c451edb6 ] When a BPF iterator program updates a sockmap, there is a race condition in unix_stream_bpf_update_proto() where the `peer` pointer can become stale[1] during a state transition TCP_ESTABLISHED -> TCP_CLOSE. CPU0 bpf CPU1 close -------- ---------- // unix_stream_bpf_update_proto() sk_pair = unix_peer(sk) if (unlikely(!sk_pair)) return -EINVAL; // unix_release_sock() skpair = unix_peer(sk); unix_peer(sk) = NULL; sock_put(skpair) sock_hold(sk_pair) // UaF More practically, this fix guarantees that the iterator program is consistently provided with a unix socket that remains stable during iterator execution. [1]: BUG: KASAN: slab-use-after-free in unix_stream_bpf_update_proto+0x155/0x490 Write of size 4 at addr ffff8881178c9a00 by task test_progs/2231 Call Trace: dump_stack_lvl+0x5d/0x80 print_report+0x170/0x4f3 kasan_report+0xe4/0x1c0 kasan_check_range+0x125/0x200 unix_stream_bpf_update_proto+0x155/0x490 sock_map_link+0x71c/0xec0 sock_map_update_common+0xbc/0x600 sock_map_update_elem+0x19a/0x1f0 bpf_prog_bbbf56096cdd4f01_selective_dump_unix+0x20c/0x217 bpf_iter_run_prog+0x21e/0xae0 bpf_iter_unix_seq_show+0x1e0/0x2a0 bpf_seq_read+0x42c/0x10d0 vfs_read+0x171/0xb20 ksys_read+0xff/0x200 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Allocated by task 2236: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_slab_alloc+0x63/0x80 kmem_cache_alloc_noprof+0x1d5/0x680 sk_prot_alloc+0x59/0x210 sk_alloc+0x34/0x470 unix_create1+0x86/0x8a0 unix_stream_connect+0x318/0x15b0 __sys_connect+0xfd/0x130 __x64_sys_connect+0x72/0xd0 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 2236: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x70 __kasan_slab_free+0x47/0x70 kmem_cache_free+0x11c/0x590 __sk_destruct+0x432/0x6e0 unix_release_sock+0x9b3/0xf60 unix_release+0x8a/0xf0 __sock_release+0xb0/0x270 sock_close+0x18/0x20 __fput+0x36e/0xac0 fput_close_sync+0xe5/0x1a0 __x64_sys_close+0x7d/0xd0 do_syscall_64+0xf7/0x5e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fixes: 2c860a43dd77 ("bpf: af_unix: Implement BPF iterator for UNIX domain socket.") Suggested-by: Kuniyuki Iwashima Signed-off-by: Michal Luczaj Signed-off-by: Martin KaFai Lau Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260414-unix-proto-update-null-ptr-deref-v4-5-2af6fe97918e@rbox.co Signed-off-by: Sasha Levin --- net/unix/af_unix.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cf022252d521c..33ed8ecb556dd 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3779,6 +3779,7 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) return 0; lock_sock(sk); + unix_state_lock(sk); if (unlikely(sock_flag(sk, SOCK_DEAD))) { ret = SEQ_SKIP; @@ -3790,6 +3791,7 @@ static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) prog = bpf_iter_get_info(&meta, false); ret = unix_prog_seq_show(prog, &meta, v, uid); unlock: + unix_state_unlock(sk); release_sock(sk); return ret; } From 5c04f89f9557ec52db4cf0d42bb602c0a15db5af Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 16 Apr 2026 14:27:19 +0200 Subject: [PATCH 0672/1518] bpf: Fix precedence bug in convert_bpf_ld_abs alignment check [ Upstream commit e5f635edd393aeaa7cad9e42831d397e6e2e1eed ] Fix an operator precedence issue in convert_bpf_ld_abs() where the expression offset + ip_align % size evaluates as offset + (ip_align % size) due to % having higher precedence than +. That latter evaluation does not make any sense. The intended check is (offset + ip_align) % size == 0 to verify that the packet load offset is properly aligned for direct access. With NET_IP_ALIGN == 2, the bug causes the inline fast-path for direct packet loads to almost never be taken on !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS platforms. This forces nearly all cBPF BPF_LD_ABS packet loads through the bpf_skb_load_helper slow path on the affected archs. Fixes: e0cea7ce988c ("bpf: implement ld_abs/ld_ind in native bpf") Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20260416122719.661033-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- net/core/filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/filter.c b/net/core/filter.c index 7fc01474c3781..ae6d0453cf123 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -508,7 +508,7 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) ((unaligned_ok && offset >= 0) || (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && - offset + ip_align % size == 0))) { + (offset + ip_align) % size == 0))) { bool ldx_off_ok = offset <= S16_MAX; *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); From 6982653ce5f119982aa58f1af58e7bfbebf39252 Mon Sep 17 00:00:00 2001 From: Mykyta Yatsenko Date: Thu, 16 Apr 2026 11:08:07 -0700 Subject: [PATCH 0673/1518] bpf: Fix NULL deref in map_kptr_match_type for scalar regs [ Upstream commit 4d0a375887ab4d49e4da1ff10f9606cab8f7c3ad ] Commit ab6c637ad027 ("bpf: Fix a bpf_kptr_xchg() issue with local kptr") refactored map_kptr_match_type() to branch on btf_is_kernel() before checking base_type(). A scalar register stored into a kptr slot has no btf, so the btf_is_kernel(reg->btf) call dereferences NULL. Move the base_type() != PTR_TO_BTF_ID guard before any reg->btf access. Fixes: ab6c637ad027 ("bpf: Fix a bpf_kptr_xchg() issue with local kptr") Reported-by: Hiker Cl Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221372 Signed-off-by: Mykyta Yatsenko Acked-by: Paul Chaignon Link: https://lore.kernel.org/r/20260416-kptr_crash-v1-1-5589356584b4@meta.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 153a7c1d32069..ebfa27d4002c5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5843,6 +5843,9 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, int perm_flags; const char *reg_name = ""; + if (base_type(reg->type) != PTR_TO_BTF_ID) + goto bad_type; + if (btf_is_kernel(reg->btf)) { perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU; @@ -5855,7 +5858,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, perm_flags |= MEM_PERCPU; } - if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) + if (type_flag(reg->type) & ~perm_flags) goto bad_type; /* We need to verify reg->type and reg->btf, before accessing reg->btf */ From 8abad856e2a5bfc15b53a8a6420910fa73021bff Mon Sep 17 00:00:00 2001 From: Yihan Ding Date: Thu, 16 Apr 2026 20:01:41 +0800 Subject: [PATCH 0674/1518] bpf: allow UTF-8 literals in bpf_bprintf_prepare() [ Upstream commit b960430ea8862ef37ce53c8bf74a8dc79d3f2404 ] bpf_bprintf_prepare() only needs ASCII parsing for conversion specifiers. Plain text can safely carry bytes >= 0x80, so allow UTF-8 literals outside '%' sequences while keeping ASCII control bytes rejected and format specifiers ASCII-only. This keeps existing parsing rules for format directives unchanged, while allowing helpers such as bpf_trace_printk() to emit UTF-8 literal text. Update test_snprintf_negative() in the same commit so selftests keep matching the new plain-text vs format-specifier split during bisection. Fixes: 48cac3f4a96d ("bpf: Implement formatted output helpers with bstr_printf") Signed-off-by: Yihan Ding Acked-by: Paul Chaignon Link: https://lore.kernel.org/r/20260416120142.1420646-2-dingyihan@uniontech.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/helpers.c | 17 ++++++++++++++++- .../testing/selftests/bpf/prog_tests/snprintf.c | 3 ++- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 68da6dcfb4bb7..b596452424481 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -848,7 +848,13 @@ int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, data->buf = buffers->buf; for (i = 0; i < fmt_size; i++) { - if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { + unsigned char c = fmt[i]; + + /* + * Permit bytes >= 0x80 in plain text so UTF-8 literals can pass + * through unchanged, while still rejecting ASCII control bytes. + */ + if (isascii(c) && !isprint(c) && !isspace(c)) { err = -EINVAL; goto out; } @@ -870,6 +876,15 @@ int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, * always access fmt[i + 1], in the worst case it will be a 0 */ i++; + c = fmt[i]; + /* + * The format parser below only understands ASCII conversion + * specifiers and modifiers, so reject non-ASCII after '%'. + */ + if (!isascii(c)) { + err = -EINVAL; + goto out; + } /* skip optional "[0 +-][num]" width formatting field */ while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c index 594441acb7071..4e4a82d54f799 100644 --- a/tools/testing/selftests/bpf/prog_tests/snprintf.c +++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c @@ -114,7 +114,8 @@ static void test_snprintf_negative(void) ASSERT_ERR(load_single_snprintf("%--------"), "invalid specifier 5"); ASSERT_ERR(load_single_snprintf("%lc"), "invalid specifier 6"); ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7"); - ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character"); + ASSERT_OK(load_single_snprintf("\x80"), "non ascii plain text"); + ASSERT_ERR(load_single_snprintf("%\x80"), "non ascii in specifier"); ASSERT_ERR(load_single_snprintf("\x1"), "non printable character"); ASSERT_ERR(load_single_snprintf("%p%"), "invalid specifier 8"); ASSERT_ERR(load_single_snprintf("%s%"), "invalid specifier 9"); From e8bd8274ae563ccabb4a778be9bd9c6d4754ab10 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 16 Apr 2026 12:00:34 +0200 Subject: [PATCH 0675/1518] libbpf: Prevent double close and leak of btf objects [ Upstream commit 380044c40b1636a72fd8f188b5806be6ae564279 ] Sashiko found possible double close of btf object fd [1], which happens when strdup in load_module_btfs fails at which point the obj->btf_module_cnt is already incremented. The error path close btf fd and so does later cleanup code in bpf_object_post_load_cleanup function. Also libbpf_ensure_mem failure leaves btf object not assigned and it's leaked. Replacing the err_out label with break to make the error path less confusing as suggested by Alan. Incrementing obj->btf_module_cnt only if there's no failure and releasing btf object in error path. Fixes: 91abb4a6d79d ("libbpf: Support attachment of BPF tracing programs to kernel modules") [1] https://sashiko.dev/#/patchset/20260324081846.2334094-1-jolsa%40kernel.org Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260416100034.1610852-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/lib/bpf/libbpf.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 9c98c6adb6d05..84b6fb47a2f79 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -5746,11 +5746,12 @@ static int load_module_btfs(struct bpf_object *obj) info.name = ptr_to_u64(name); info.name_len = sizeof(name); + btf = NULL; err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { err = -errno; pr_warn("failed to get BTF object #%d info: %s\n", id, errstr(err)); - goto err_out; + break; } /* ignore non-module BTFs */ @@ -5764,15 +5765,15 @@ static int load_module_btfs(struct bpf_object *obj) if (err) { pr_warn("failed to load module [%s]'s BTF object #%d: %s\n", name, id, errstr(err)); - goto err_out; + break; } err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap, sizeof(*obj->btf_modules), obj->btf_module_cnt + 1); if (err) - goto err_out; + break; - mod_btf = &obj->btf_modules[obj->btf_module_cnt++]; + mod_btf = &obj->btf_modules[obj->btf_module_cnt]; mod_btf->btf = btf; mod_btf->id = id; @@ -5780,16 +5781,16 @@ static int load_module_btfs(struct bpf_object *obj) mod_btf->name = strdup(name); if (!mod_btf->name) { err = -ENOMEM; - goto err_out; + break; } - continue; + obj->btf_module_cnt++; + } -err_out: + if (err) { + btf__free(btf); close(fd); - return err; } - - return 0; + return err; } static struct bpf_core_cand_list * From e15900888c09480a4c632bc598f1c5bd39bed6d6 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Fri, 17 Apr 2026 08:21:33 -0700 Subject: [PATCH 0676/1518] bpf: Validate node_id in arena_alloc_pages() [ Upstream commit 2845989f2ebaf7848e4eccf9a779daf3156ea0a5 ] arena_alloc_pages() accepts a plain int node_id and forwards it through the entire allocation chain without any bounds checking. Validate node_id before passing it down the allocation chain in arena_alloc_pages(). Fixes: 317460317a02 ("bpf: Introduce bpf_arena.") Signed-off-by: Puranjay Mohan Reviewed-by: Emil Tsalapatis Link: https://lore.kernel.org/r/20260417152135.1383754-1-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/arena.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index c67525847687f..dafa179da0c9c 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -446,6 +446,10 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt u32 uaddr32; int ret, i; + if (node_id != NUMA_NO_NODE && + ((unsigned int)node_id >= nr_node_ids || !node_online(node_id))) + return 0; + if (page_cnt > page_cnt_max) return 0; From 02c06e764fe5d37f0faab7da66cc50fc3152d924 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Fri, 17 Apr 2026 07:33:52 -0700 Subject: [PATCH 0677/1518] bpf, arm32: Reject BPF-to-BPF calls and callbacks in the JIT [ Upstream commit e1d486445af3c392628532229f7ce5f5cf7891b6 ] The ARM32 BPF JIT does not support BPF-to-BPF function calls (BPF_PSEUDO_CALL) or callbacks (BPF_PSEUDO_FUNC), but it does not reject them either. When a program with subprograms is loaded (e.g. libxdp's XDP dispatcher uses __noinline__ subprograms, or any program using callbacks like bpf_loop or bpf_for_each_map_elem), the verifier invokes bpf_jit_subprogs() which calls bpf_int_jit_compile() for each subprogram. For BPF_PSEUDO_CALL, since ARM32 does not reject it, the JIT silently emits code using the wrong address computation: func = __bpf_call_base + imm where imm is a pc-relative subprogram offset, producing a bogus function pointer. For BPF_PSEUDO_FUNC, the ldimm64 handler ignores src_reg and loads the immediate as a normal 64-bit value without error. In both cases, build_body() reports success and a JIT image is allocated. ARM32 lacks the jit_data/extra_pass mechanism needed for the second JIT pass in bpf_jit_subprogs(). On the second pass, bpf_int_jit_compile() performs a full fresh compilation, allocating a new JIT binary and overwriting prog->bpf_func. The first allocation is never freed. bpf_jit_subprogs() then detects the function pointer changed and aborts with -ENOTSUPP, but the original JIT binary has already been leaked. Each program load/unload cycle leaks one JIT binary allocation, as reported by kmemleak: unreferenced object 0xbf0a1000 (size 4096): backtrace: bpf_jit_binary_alloc+0x64/0xfc bpf_int_jit_compile+0x14c/0x348 bpf_jit_subprogs+0x4fc/0xa60 Fix this by rejecting both BPF_PSEUDO_CALL in the BPF_CALL handler and BPF_PSEUDO_FUNC in the BPF_LD_IMM64 handler, falling through to the existing 'notyet' path. This causes build_body() to fail before any JIT binary is allocated, so bpf_int_jit_compile() returns the original program unjitted. bpf_jit_subprogs() then sees !prog->jited and cleanly falls back to the interpreter with no leak. Acked-by: Daniel Borkmann Fixes: 1c2a088a6626 ("bpf: x64: add JIT support for multi-function programs") Reported-by: Jonas Rebmann Closes: https://lore.kernel.org/bpf/b63e9174-7a3d-4e22-8294-16df07a4af89@pengutronix.de Tested-by: Jonas Rebmann Signed-off-by: Puranjay Mohan Reviewed-by: Emil Tsalapatis Link: https://lore.kernel.org/r/20260417143353.838911-1-puranjay@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- arch/arm/net/bpf_jit_32.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index deeb8f292454b..a900aa9738855 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1852,6 +1852,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) { u64 val = (u32)imm | (u64)insn[1].imm << 32; + if (insn->src_reg == BPF_PSEUDO_FUNC) + goto notyet; + emit_a32_mov_i64(dst, val, ctx); return 1; @@ -2055,6 +2058,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const s8 *r5 = bpf2a32[BPF_REG_5]; const u32 func = (u32)__bpf_call_base + (u32)imm; + if (insn->src_reg == BPF_PSEUDO_CALL) + goto notyet; + emit_a32_mov_r64(true, r0, r1, ctx); emit_a32_mov_r64(true, r1, r2, ctx); emit_push_r64(r5, ctx); From dc3ece1d92e62210cba676d88f05a08ec3813530 Mon Sep 17 00:00:00 2001 From: wangguangju Date: Thu, 26 Feb 2026 20:22:08 +0800 Subject: [PATCH 0678/1518] perf trace: Fix IS_ERR() vs NULL check bug [ Upstream commit 96f202eab8133f94479b14a32902c636e9bdf6af ] The alloc_syscall_stats() function always returns an error pointer (ERR_PTR) on failure. So replace NULL check with IS_ERR() check after calling delete_syscall_stats() function. Fixes: ef2da619b132c6f74 ("perf trace: Convert syscall_stats to hashmap") Signed-off-by: wangguangju Reviewed-by: Howard Chu Acked-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index c607f39b8c8bb..1f0b9ba3cdc15 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1573,7 +1573,7 @@ static void delete_syscall_stats(struct hashmap *syscall_stats) struct hashmap_entry *pos; size_t bkt; - if (syscall_stats == NULL) + if (IS_ERR(syscall_stats)) return; hashmap__for_each_entry(syscall_stats, pos, bkt) From 4d994ff457272524105621d2bcf4c1b45a420088 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Fri, 27 Feb 2026 15:56:23 -0600 Subject: [PATCH 0679/1518] pinctrl: pinctrl-pic32: Fix resource leak [ Upstream commit fe5560688f3ba98364c7de7b4f8dc240ffd1ff75 ] Fix three possible resource leaks by using the devres version of clk_prepare_enable(). Also, update error message accordingly. Detected by Smatch: drivers/pinctrl/pinctrl-pic32.c:2211 pic32_pinctrl_probe() warn: 'pctl->clk' from clk_prepare_enable() not released on lines: 2208. drivers/pinctrl/pinctrl-pic32.c:2274 pic32_gpio_probe() warn: 'bank->clk' from clk_prepare_enable() not released on lines: 2264,2272. Fixes: 2ba384e6c3810 ("pinctrl: pinctrl-pic32: Add PIC32 pin control driver") Signed-off-by: Ethan Tidmore Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-pic32.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/pinctrl/pinctrl-pic32.c b/drivers/pinctrl/pinctrl-pic32.c index e8b481e87c779..506e95793adf3 100644 --- a/drivers/pinctrl/pinctrl-pic32.c +++ b/drivers/pinctrl/pinctrl-pic32.c @@ -2175,16 +2175,10 @@ static int pic32_pinctrl_probe(struct platform_device *pdev) if (IS_ERR(pctl->reg_base)) return PTR_ERR(pctl->reg_base); - pctl->clk = devm_clk_get(&pdev->dev, NULL); + pctl->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(pctl->clk)) { ret = PTR_ERR(pctl->clk); - dev_err(&pdev->dev, "clk get failed\n"); - return ret; - } - - ret = clk_prepare_enable(pctl->clk); - if (ret) { - dev_err(&pdev->dev, "clk enable failed\n"); + dev_err(&pdev->dev, "Failed to get and enable clock\n"); return ret; } @@ -2240,16 +2234,10 @@ static int pic32_gpio_probe(struct platform_device *pdev) if (irq < 0) return irq; - bank->clk = devm_clk_get(&pdev->dev, NULL); + bank->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(bank->clk)) { ret = PTR_ERR(bank->clk); - dev_err(&pdev->dev, "clk get failed\n"); - return ret; - } - - ret = clk_prepare_enable(bank->clk); - if (ret) { - dev_err(&pdev->dev, "clk enable failed\n"); + dev_err(&pdev->dev, "Failed to get and enable clock\n"); return ret; } From dbfb30248dbe405557a2c99fee9019047808878e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 2 Mar 2026 15:45:15 -0800 Subject: [PATCH 0680/1518] perf trace: Avoid an ERR_PTR in syscall_stats [ Upstream commit d05073adda0f047e9b2115a2932bcb2797eab238 ] hashmap__new may return an ERR_PTR and previously this would be assigned to syscall_stats meaning all use of syscall_stats needs to test for NULL (uninitialized) or an ERR_PTR. Given the only reason hashmap__new can fail is ENOMEM, just use NULL to indicate the allocation failure and avoid the code having to test for NULL and IS_ERR. Fixes: 96f202eab813 (perf trace: Fix IS_ERR() vs NULL check bug) Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 1f0b9ba3cdc15..96efe1fba8547 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1565,7 +1565,9 @@ static bool syscall_id_equal(long key1, long key2, void *ctx __maybe_unused) static struct hashmap *alloc_syscall_stats(void) { - return hashmap__new(syscall_id_hash, syscall_id_equal, NULL); + struct hashmap *result = hashmap__new(syscall_id_hash, syscall_id_equal, NULL); + + return IS_ERR(result) ? NULL : result; } static void delete_syscall_stats(struct hashmap *syscall_stats) @@ -1573,7 +1575,7 @@ static void delete_syscall_stats(struct hashmap *syscall_stats) struct hashmap_entry *pos; size_t bkt; - if (IS_ERR(syscall_stats)) + if (!syscall_stats) return; hashmap__for_each_entry(syscall_stats, pos, bkt) @@ -1589,7 +1591,7 @@ static struct thread_trace *thread_trace__new(struct trace *trace) ttrace->files.max = -1; if (trace->summary) { ttrace->syscall_stats = alloc_syscall_stats(); - if (IS_ERR(ttrace->syscall_stats)) + if (!ttrace->syscall_stats) zfree(&ttrace); } } @@ -4441,7 +4443,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->summary_mode == SUMMARY__BY_TOTAL && !trace->summary_bpf) { trace->syscall_stats = alloc_syscall_stats(); - if (IS_ERR(trace->syscall_stats)) + if (!trace->syscall_stats) goto out_delete_evlist; } @@ -4749,7 +4751,7 @@ static int trace__replay(struct trace *trace) if (trace->summary_mode == SUMMARY__BY_TOTAL) { trace->syscall_stats = alloc_syscall_stats(); - if (IS_ERR(trace->syscall_stats)) + if (!trace->syscall_stats) goto out; } From 815a7b8af68d4c7a3dd9f14664a5c0489136e527 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 23 Feb 2026 19:06:53 +0100 Subject: [PATCH 0681/1518] pinctrl: cy8c95x0: remove duplicate error message [ Upstream commit 970dacb3b9f0fedbbbcfd7dbf1f4f22340b3f359 ] The pin control core is covered to report any error via message. The devm_request_threaded_irq() already prints an error message. Remove the duplicates. While at it, drop the info message as the same information about an IRQ in use can be retrieved differently. Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij Stable-dep-of: 5ad32c3607cf ("pinctrl: cy8c95x0: Avoid returning positive values to user space") Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-cy8c95x0.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 5c055d344ac9d..c0f1d964f8397 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -1310,6 +1310,7 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq) { struct gpio_irq_chip *girq = &chip->gpio_chip.irq; DECLARE_BITMAP(pending_irqs, MAX_LINE); + struct device *dev = chip->dev; int ret; mutex_init(&chip->irq_lock); @@ -1336,17 +1337,9 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq) girq->handler = handle_simple_irq; girq->threaded = true; - ret = devm_request_threaded_irq(chip->dev, irq, - NULL, cy8c95x0_irq_handler, - IRQF_ONESHOT | IRQF_SHARED, - dev_name(chip->dev), chip); - if (ret) { - dev_err(chip->dev, "failed to request irq %d\n", irq); - return ret; - } - dev_info(chip->dev, "Registered threaded IRQ\n"); - - return 0; + return devm_request_threaded_irq(dev, irq, NULL, cy8c95x0_irq_handler, + IRQF_ONESHOT | IRQF_SHARED, + dev_name(chip->dev), chip); } static int cy8c95x0_setup_pinctrl(struct cy8c95x0_pinctrl *chip) @@ -1362,11 +1355,7 @@ static int cy8c95x0_setup_pinctrl(struct cy8c95x0_pinctrl *chip) pd->owner = THIS_MODULE; chip->pctldev = devm_pinctrl_register(chip->dev, pd, chip); - if (IS_ERR(chip->pctldev)) - return dev_err_probe(chip->dev, PTR_ERR(chip->pctldev), - "can't register controller\n"); - - return 0; + return PTR_ERR_OR_ZERO(chip->pctldev); } static int cy8c95x0_detect(struct i2c_client *client, From df50e63cdf1512b4d2e496d9f276b5a86951370c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 23 Feb 2026 19:06:54 +0100 Subject: [PATCH 0682/1518] pinctrl: cy8c95x0: Unify messages with help of dev_err_probe() [ Upstream commit 014884732095b982412d13d3220c3fe8483b9b3e ] Unify error messages that might appear during probe phase by switching to use dev_err_probe(). Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij Stable-dep-of: 5ad32c3607cf ("pinctrl: cy8c95x0: Avoid returning positive values to user space") Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-cy8c95x0.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index c0f1d964f8397..14d927035bc0f 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -1319,10 +1319,8 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq) /* Read IRQ status register to clear all pending interrupts */ ret = cy8c95x0_irq_pending(chip, pending_irqs); - if (ret) { - dev_err(chip->dev, "failed to clear irq status register\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "failed to clear irq status register\n"); /* Mask all interrupts */ bitmap_fill(chip->irq_mask, MAX_LINE); From 518ae2a82efebc0cb619538dfaad98d4a0c1eaf8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 27 Feb 2026 17:43:35 +0100 Subject: [PATCH 0683/1518] pinctrl: cy8c95x0: Avoid returning positive values to user space [ Upstream commit 5ad32c3607cf241a1a2680cabd64cbcd757227aa ] When probe fails due to unclear interrupt status register, it returns a positive number instead of the proper error code. Fix this accordingly. Fixes: e6cbbe42944d ("pinctrl: Add Cypress cy8c95x0 support") Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202602271847.vVWkqLBD-lkp@intel.com/ Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-cy8c95x0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 14d927035bc0f..54b117f32f0ea 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -1320,7 +1320,7 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq) /* Read IRQ status register to clear all pending interrupts */ ret = cy8c95x0_irq_pending(chip, pending_irqs); if (ret) - return dev_err_probe(dev, ret, "failed to clear irq status register\n"); + return dev_err_probe(dev, -EBUSY, "failed to clear irq status register\n"); /* Mask all interrupts */ bitmap_fill(chip->irq_mask, MAX_LINE); From 9878e6ed7ec520c5348a2cf306d657586aaf5246 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 12 Mar 2026 15:31:31 -0700 Subject: [PATCH 0684/1518] perf branch: Avoid incrementing NULL [ Upstream commit c969a9d7bbf46f983c4a48566b3b2f7340b02296 ] If the entry is NULL the value is meaningless so early return NULL to avoid an increment of NULL. This was happening in calls from has_stitched_lbr when running the "perf record LBR tests". The return value isn't used in that case, so returning NULL as no effect. Fixes: 42bbabed09ce ("perf tools: Add hw_idx in struct branch_stack") Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/branch.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index 7429530fa7749..a1d4736497c40 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -66,6 +66,9 @@ static inline struct branch_entry *perf_sample__branch_entries(struct perf_sampl { u64 *entry = (u64 *)sample->branch_stack; + if (entry == NULL) + return NULL; + entry++; if (sample->no_hw_idx) return (struct branch_entry *)entry; From be787fea6c66d2c24dbab6d5581b0d18a69ca332 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Wed, 18 Mar 2026 10:36:39 +0000 Subject: [PATCH 0685/1518] perf: tools: cs-etm: Fix print issue for Coresight debug in ETE/TRBE trace [ Upstream commit 6c478e7b3eba3f387a2d6c749e3e3ee0f8ad1c53 ] Building perf with CORESIGHT=1 and the optional CSTRACE_RAW=1 enables additional debug printing of raw trace data when using command:- perf report --dump. This raw trace prints the CoreSight formatted trace frames, which may be used to investigate suspected issues with trace quality / corruption / decode. These frames are not present in ETE + TRBE trace. This fix removes the unnecessary call to print these frames. This fix also rationalises implementation - original code had helper function that unnecessarily repeated initialisation calls that had already been made. Due to an addtional fault with the OpenCSD library, this call when ETE/TRBE are being decoded will cause a segfault in perf. This fix also prevents that problem for perf using older (<= 1.8.0 version) OpenCSD libraries. Fixes: 68ffe3902898 ("perf tools: Add decoder mechanic to support dumping trace data") Reported-by: Leo Yan Signed-off-by: Mike Leach Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 51 +++++-------------- 1 file changed, 13 insertions(+), 38 deletions(-) diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index b85a8837bddcd..43ac711a4e2ae 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -237,46 +237,24 @@ cs_etm_decoder__init_def_logger_printing(struct cs_etm_decoder_params *d_params, (void *)decoder, cs_etm_decoder__print_str_cb); if (ret != 0) - ret = -1; - - return 0; -} + return -1; #ifdef CS_LOG_RAW_FRAMES -static void -cs_etm_decoder__init_raw_frame_logging(struct cs_etm_decoder_params *d_params, - struct cs_etm_decoder *decoder) -{ - /* Only log these during a --dump operation */ - if (d_params->operation == CS_ETM_OPERATION_PRINT) { - /* set up a library default logger to process the - * raw frame printer we add later - */ - ocsd_def_errlog_init(OCSD_ERR_SEV_ERROR, 1); - - /* no stdout / err / file output */ - ocsd_def_errlog_config_output(C_API_MSGLOGOUT_FLG_NONE, NULL); - - /* set the string CB for the default logger, - * passes strings to perf print logger. - */ - ocsd_def_errlog_set_strprint_cb(decoder->dcd_tree, - (void *)decoder, - cs_etm_decoder__print_str_cb); - + /* + * Only log raw frames if --dump operation and hardware is actually + * generating formatted CoreSight trace frames + */ + if ((d_params->operation == CS_ETM_OPERATION_PRINT) && + (d_params->formatted == true)) { /* use the built in library printer for the raw frames */ - ocsd_dt_set_raw_frame_printer(decoder->dcd_tree, - CS_RAW_DEBUG_FLAGS); + ret = ocsd_dt_set_raw_frame_printer(decoder->dcd_tree, + CS_RAW_DEBUG_FLAGS); + if (ret != 0) + return -1; } -} -#else -static void -cs_etm_decoder__init_raw_frame_logging( - struct cs_etm_decoder_params *d_params __maybe_unused, - struct cs_etm_decoder *decoder __maybe_unused) -{ -} #endif + return 0; +} static ocsd_datapath_resp_t cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq, @@ -760,9 +738,6 @@ cs_etm_decoder__new(int decoders, struct cs_etm_decoder_params *d_params, if (ret != 0) goto err_free_decoder; - /* init raw frame logging if required */ - cs_etm_decoder__init_raw_frame_logging(d_params, decoder); - for (i = 0; i < decoders; i++) { ret = cs_etm_decoder__create_etm_decoder(d_params, &t_params[i], From 6476aac13805721e16439bd71f0e1703a4154517 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 17 Mar 2026 11:36:11 +0100 Subject: [PATCH 0686/1518] pinctrl: pinconf-generic: Fully validate 'pinmux' property [ Upstream commit c98324ea7849b6e5baa1774f71709b375a2c2f9e ] The pinconf_generic_parse_dt_pinmux() assumes that the 'pinmux' property is not empty when present. This might be not true. With that, the allocator will give a special value in return and not NULL which lead to the crash when trying to access that (invalid) memory. Fix that by fully validating 'pinmux' value, including its length. Fixes: 7112c05fff83 ("pinctrl: pinconf-generic: Add API for pinmux propertity in DTS file") Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinconf-generic.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index cad29abe4050a..8f6a83fdc3844 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -261,12 +261,17 @@ int pinconf_generic_parse_dt_pinmux(struct device_node *np, struct device *dev, return -ENOENT; } + npins_t = prop->length / sizeof(u32); + if (npins_t == 0) { + dev_info(dev, "pinmux property doesn't have entries\n"); + return -ENODATA; + } + if (!pid || !pmux || !npins) { dev_err(dev, "parameters error\n"); return -EINVAL; } - npins_t = prop->length / sizeof(u32); pid_t = devm_kcalloc(dev, npins_t, sizeof(*pid_t), GFP_KERNEL); pmux_t = devm_kcalloc(dev, npins_t, sizeof(*pmux_t), GFP_KERNEL); if (!pid_t || !pmux_t) { From bb548a3c26a1f902f483953a3c51102ed14c9883 Mon Sep 17 00:00:00 2001 From: Yu-Chun Lin Date: Tue, 17 Mar 2026 19:54:03 +0800 Subject: [PATCH 0687/1518] pinctrl: realtek: Fix function signature for config argument [ Upstream commit 1f5451844786ed203605528dca9e5d84ed378160 ] The argument originates from pinconf_to_config_argument(), which returns a u32. Therefore, the arg parameter should be an unsigned int instead of enum pin_config_param. Fixes: e99ce78030db ("pinctrl: realtek: Add common pinctrl driver for Realtek DHC RTD SoCs") Signed-off-by: Yu-Chun Lin Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/realtek/pinctrl-rtd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/realtek/pinctrl-rtd.c b/drivers/pinctrl/realtek/pinctrl-rtd.c index 2440604863327..4c876d1f6ad59 100644 --- a/drivers/pinctrl/realtek/pinctrl-rtd.c +++ b/drivers/pinctrl/realtek/pinctrl-rtd.c @@ -279,7 +279,7 @@ static const struct rtd_pin_sconfig_desc *rtd_pinctrl_find_sconfig(struct rtd_pi static int rtd_pconf_parse_conf(struct rtd_pinctrl *data, unsigned int pinnr, enum pin_config_param param, - enum pin_config_param arg) + unsigned int arg) { const struct rtd_pin_config_desc *config_desc; const struct rtd_pin_sconfig_desc *sconfig_desc; From 71e13d4c1d77ce1efad790f8c5ed65cfc71cf815 Mon Sep 17 00:00:00 2001 From: Yu-Chun Lin Date: Fri, 20 Mar 2026 23:15:06 +0800 Subject: [PATCH 0688/1518] pinctrl: abx500: Fix type of 'argument' variable [ Upstream commit 34006f77890d050e6d80cbee365b5d703c1140b4 ] The argument variable is assigned the return value of pinconf_to_config_argument(), which returns a u32. Change its type from enum pin_config_param to unsigned int to correctly store the configuration argument. Fixes: 03b054e9696c ("pinctrl: Pass all configs to driver on pin_config_set()") Signed-off-by: Yu-Chun Lin Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/nomadik/pinctrl-abx500.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c index fc7ebeda8440e..858fbaebcf8e5 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.c +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c @@ -852,7 +852,7 @@ static int abx500_pin_config_set(struct pinctrl_dev *pctldev, int ret = -EINVAL; int i; enum pin_config_param param; - enum pin_config_param argument; + unsigned int argument; for (i = 0; i < num_configs; i++) { param = pinconf_to_config_param(configs[i]); From 509d342d02fff0c7cc42e778a198317ba7b09dab Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 26 Mar 2026 16:24:51 +0000 Subject: [PATCH 0689/1518] pinctrl: renesas: rzg2l: Fix save/restore of {IOLH,IEN,PUPD,SMT} registers [ Upstream commit d9a60e367919752a1d398ebeba667f1e200fae1e ] The rzg2l_pinctrl_pm_setup_regs() handles save/restore of {IOLH,IEN,PUPD,SMT} registers during s2ram, but only for ports where all pins share the same pincfg. Extend the code to also support ports with variable pincfg per pin, so that {IOLH,IEN,PUPD,SMT} registers are correctly saved and restored for all pins. Fixes: 254203f9a94c ("pinctrl: renesas: rzg2l: Add suspend/resume support") Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260326162459.101414-1-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/pinctrl/renesas/pinctrl-rzg2l.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index c2711b2de374d..ca360185740a8 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -2997,6 +2997,13 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen off = RZG2L_PIN_CFG_TO_PORT_OFFSET(cfg); pincnt = hweight8(FIELD_GET(PIN_CFG_PIN_MAP_MASK, cfg)); + if (cfg & RZG2L_VARIABLE_CFG) { + unsigned int pin = port * RZG2L_PINS_PER_PORT; + + for (unsigned int i = 0; i < RZG2L_PINS_PER_PORT; i++) + cfg |= *(u64 *)pctrl->desc.pins[pin + i].drv_data; + } + caps = FIELD_GET(PIN_CFG_MASK, cfg); has_iolh = !!(caps & (PIN_CFG_IOLH_A | PIN_CFG_IOLH_B | PIN_CFG_IOLH_C)); has_ien = !!(caps & PIN_CFG_IEN); From 206ac6c702ca7955771e6617f9fe46c1b0f30e02 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 19 Mar 2026 16:33:48 -0700 Subject: [PATCH 0690/1518] perf lock: Fix option value type in parse_max_stack [ Upstream commit cfaade34b52aa1ec553044255702c4b31b57c005 ] The value is a void* and the address of an int, max_stack_depth, is set up in the perf lock options. The parse_max_stack function treats the int* as a long*, make this more correct by declaring the value to be an int*. Fixes: 0a277b622670 ("perf lock contention: Check --max-stack option") Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/builtin-lock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index e8962c985d34a..5585aeb97684d 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2250,7 +2250,7 @@ static int parse_map_entry(const struct option *opt, const char *str, static int parse_max_stack(const struct option *opt, const char *str, int unset __maybe_unused) { - unsigned long *len = (unsigned long *)opt->value; + int *len = opt->value; long val; char *endptr; From 3fb038e078ec9cc8f2f175112664ac4353b8e002 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 19 Mar 2026 16:33:49 -0700 Subject: [PATCH 0691/1518] perf stat: Fix opt->value type for parse_cache_level [ Upstream commit 44311ae84ad9177fb311aee856027861c22f17b2 ] Commit f5803651b4a4 ("perf stat: Choose the most disaggregate command line option") changed aggregation option handling for `perf stat` but not `perf stat report` leading to parse_cache_level being passed a struct in the `perf stat` case but erroneously an aggr_mode enum value for `perf stat report`. Change the `perf stat report` aggregation handling to use the same opt_aggr_mode as `perf stat`. Also, just pass the boolean for consistency with other boolean argument handling. Fixes: f5803651b4a4 ("perf stat: Choose the most disaggregate command line option") Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/builtin-stat.c | 43 +++++++++++++++++++++------------------ 1 file changed, 23 insertions(+), 20 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b6533dcf5465b..9eb0876633c05 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -153,7 +153,7 @@ struct opt_aggr_mode { }; /* Turn command line option into most generic aggregation mode setting. */ -static enum aggr_mode opt_aggr_mode_to_aggr_mode(struct opt_aggr_mode *opt_mode) +static enum aggr_mode opt_aggr_mode_to_aggr_mode(const struct opt_aggr_mode *opt_mode) { enum aggr_mode mode = AGGR_GLOBAL; @@ -1161,8 +1161,8 @@ static int parse_cache_level(const struct option *opt, int unset __maybe_unused) { int level; - struct opt_aggr_mode *opt_aggr_mode = (struct opt_aggr_mode *)opt->value; - u32 *aggr_level = (u32 *)opt->data; + bool *per_cache = opt->value; + u32 *aggr_level = opt->data; /* * If no string is specified, aggregate based on the topology of @@ -1200,7 +1200,7 @@ static int parse_cache_level(const struct option *opt, return -EINVAL; } out: - opt_aggr_mode->cache = true; + *per_cache = true; *aggr_level = level; return 0; } @@ -2262,24 +2262,23 @@ static struct perf_stat perf_stat = { static int __cmd_report(int argc, const char **argv) { struct perf_session *session; + struct opt_aggr_mode opt_mode = {}; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode, - "aggregate counts per processor socket", AGGR_SOCKET), - OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode, - "aggregate counts per processor die", AGGR_DIE), - OPT_SET_UINT(0, "per-cluster", &perf_stat.aggr_mode, - "aggregate counts perf processor cluster", AGGR_CLUSTER), - OPT_CALLBACK_OPTARG(0, "per-cache", &perf_stat.aggr_mode, &perf_stat.aggr_level, - "cache level", - "aggregate count at this cache level (Default: LLC)", + OPT_BOOLEAN(0, "per-thread", &opt_mode.thread, "aggregate counts per thread"), + OPT_BOOLEAN(0, "per-socket", &opt_mode.socket, + "aggregate counts per processor socket"), + OPT_BOOLEAN(0, "per-die", &opt_mode.die, "aggregate counts per processor die"), + OPT_BOOLEAN(0, "per-cluster", &opt_mode.cluster, + "aggregate counts per processor cluster"), + OPT_CALLBACK_OPTARG(0, "per-cache", &opt_mode.cache, &perf_stat.aggr_level, + "cache level", "aggregate count at this cache level (Default: LLC)", parse_cache_level), - OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode, - "aggregate counts per physical processor core", AGGR_CORE), - OPT_SET_UINT(0, "per-node", &perf_stat.aggr_mode, - "aggregate counts per numa node", AGGR_NODE), - OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode, - "disable CPU count aggregation", AGGR_NONE), + OPT_BOOLEAN(0, "per-core", &opt_mode.core, + "aggregate counts per physical processor core"), + OPT_BOOLEAN(0, "per-node", &opt_mode.node, "aggregate counts per numa node"), + OPT_BOOLEAN('A', "no-aggr", &opt_mode.no_aggr, + "disable aggregation across CPUs or PMUs"), OPT_END() }; struct stat st; @@ -2287,6 +2286,10 @@ static int __cmd_report(int argc, const char **argv) argc = parse_options(argc, argv, options, stat_report_usage, 0); + perf_stat.aggr_mode = opt_aggr_mode_to_aggr_mode(&opt_mode); + if (perf_stat.aggr_mode == AGGR_GLOBAL) + perf_stat.aggr_mode = AGGR_UNSET; /* No option found so leave unset. */ + if (!input_name || !strlen(input_name)) { if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) input_name = "-"; @@ -2462,7 +2465,7 @@ int cmd_stat(int argc, const char **argv) OPT_BOOLEAN(0, "per-die", &opt_mode.die, "aggregate counts per processor die"), OPT_BOOLEAN(0, "per-cluster", &opt_mode.cluster, "aggregate counts per processor cluster"), - OPT_CALLBACK_OPTARG(0, "per-cache", &opt_mode, &stat_config.aggr_level, + OPT_CALLBACK_OPTARG(0, "per-cache", &opt_mode.cache, &stat_config.aggr_level, "cache level", "aggregate count at this cache level (Default: LLC)", parse_cache_level), OPT_BOOLEAN(0, "per-core", &opt_mode.core, From 7377e48f9ca8b45420bde4e74da88af2b708d59e Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Mon, 23 Mar 2026 09:48:28 +0200 Subject: [PATCH 0692/1518] memblock: reserve_mem: fix end caclulation in reserve_mem_release_by_name() [ Upstream commit c12c3e1507809ad1fc0448f51c933f52e17d13cd ] free_reserved_area() expects end parameter to point to the first address after the area, but reserve_mem_release_by_name() passes it the last address inside the area. Remove subtraction of one in calculation of the area end. Fixes: 74e2498ccf7b ("mm/memblock: Add reserved memory release function") Link: https://patch.msgid.link/20260323074836.3653702-2-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Signed-off-by: Sasha Levin --- mm/memblock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memblock.c b/mm/memblock.c index f0f2dc66e9a20..757258d68425a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2433,7 +2433,7 @@ int reserve_mem_release_by_name(const char *name) return 0; start = phys_to_virt(map->start); - end = start + map->size - 1; + end = start + map->size; snprintf(buf, sizeof(buf), "reserve_mem:%s", name); free_reserved_area(start, end, 0, buf); map->size = 0; From 131e9cb0b93254db8a61f85edf303b6c3370b654 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 23 Mar 2026 11:58:04 -0400 Subject: [PATCH 0693/1518] perf tools: Fix module symbol resolution for non-zero .text sh_addr [ Upstream commit 9a82bfde4775b7a87cd1a7e791f46f83ae442848 ] When perf resolves symbols from kernel module ELF files (ET_REL), it converts symbol addresses to file offsets so that sample IPs can be matched to the correct symbol. The conversion adjusts each symbol's st_value: sym->st_value -= shdr->sh_addr - shdr->sh_offset; For vmlinux (ET_EXEC), st_value is a virtual address and sh_addr is the section's virtual base, so subtracting sh_addr and adding sh_offset correctly yields a file offset. For kernel modules (ET_REL), st_value is a section-relative offset. The module loader ignores sh_addr entirely and places symbols at module_base + st_value. Converting to file offset requires only adding sh_offset; subtracting sh_addr introduces an error equal to sh_addr bytes. When .text has sh_addr == 0 -- the historical norm for simple modules -- both formulas produce the same result and the bug is latent. As modules gain more metadata sections before .text (.note, .static_call.text, etc.), the linker assigns .text a non-zero sh_addr, exposing the defect. For example, nfsd.ko on this kernel has sh_addr=0xa80, kvm-intel.ko has sh_addr=0x1e90. The effect is that all .text symbols in affected modules shift by sh_addr bytes relative to sample IPs, causing perf report to attribute samples to incorrect, nearby symbols. This was observed as 13% of LLC-load-miss samples misattributed to nfsd_file_get_dio_attrs when the actual hot function was nfsd_cache_lookup, approximately 0xa80 bytes away in the symbol table. Use the existing dso__rel() flag (already set for ET_REL modules) to select the correct adjustment: add sh_offset for ET_REL, subtract (sh_addr - sh_offset) for ET_EXEC/ET_DYN. Fixes: 0131c4ec794a ("perf tools: Make it possible to read object code from kernel modules") Signed-off-by: Chuck Lever Reviewed-by: Ian Rogers Tested-by: Thomas Richter Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/symbol-elf.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 9d62386464680..9602cc51dcc65 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1353,8 +1353,12 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, char dso_name[PATH_MAX]; /* Adjust symbol to map to file offset */ - if (adjust_kernel_syms) - sym->st_value -= shdr->sh_addr - shdr->sh_offset; + if (adjust_kernel_syms) { + if (dso__rel(dso)) + sym->st_value += shdr->sh_offset; + else + sym->st_value -= shdr->sh_addr - shdr->sh_offset; + } if (strcmp(section_name, (dso__short_name(curr_dso) + dso__short_name_len(dso))) == 0) return 0; From e62ac39eb2ce1a3d98ac9bea92dcb7d6a697ac3c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 2 Apr 2026 17:04:47 +0100 Subject: [PATCH 0694/1518] perf expr: Return -EINVAL for syntax error in expr__find_ids() [ Upstream commit 3a61fd866ef9aaa1d3158b460f852b74a2df07f4 ] expr__find_ids() propagates the parser return value directly. For syntax errors, the parser can return a positive value, but callers treat it as success, e.g., for below case on Arm64 platform: metric expr 100 * (STALL_SLOT_BACKEND / (CPU_CYCLES * #slots) - BR_MIS_PRED * 3 / CPU_CYCLES) for backend_bound parsing metric: 100 * (STALL_SLOT_BACKEND / (CPU_CYCLES * #slots) - BR_MIS_PRED * 3 / CPU_CYCLES) Failure to read '#slots' literal: #slots = nan syntax error Convert positive parser returns in expr__find_ids() to -EINVAL, as a result, the error value will be respected by callers. Before: perf stat -C 5 Failure to read '#slots'Failure to read '#slots'Failure to read '#slots'Failure to read '#slots'Segmentation fault After: perf stat -C 5 Failure to read '#slots'Cannot find metric or group `Default' Fixes: ded80bda8bc9 ("perf expr: Migrate expr ids table to a hashmap") Signed-off-by: Leo Yan Reviewed-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/expr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 7fda0ff89c168..0893c88a4ef83 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -376,7 +376,8 @@ int expr__find_ids(const char *expr, const char *one, if (one) expr__del_id(ctx, one); - return ret; + /* A positive value means syntax error, convert to -EINVAL */ + return ret > 0 ? -EINVAL : ret; } double expr_id_data__value(const struct expr_id_data *data) From 3cce2a3f8f60c079fa779e385a4b45d246be918b Mon Sep 17 00:00:00 2001 From: Jian Zhang Date: Fri, 3 Apr 2026 17:05:59 +0800 Subject: [PATCH 0695/1518] ipmi: ssif_bmc: fix missing check for copy_to_user() partial failure [ Upstream commit ea641be7a4faee4351f9c5ed6b188e1bbf5586a6 ] copy_to_user() returns the number of bytes that could not be copied, with a non-zero value indicating a partial or complete failure. The current code only checks for negative return values and treats all non-negative results as success. Treating any positive return value from copy_to_user() as an error and returning -EFAULT. Fixes: dd2bc5cc9e25 ("ipmi: ssif_bmc: Add SSIF BMC driver") Signed-off-by: Jian Zhang Message-ID: <20260403090603.3988423-2-zhangjian.3032@bytedance.com> Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ssif_bmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c index 7a52e3ea49ed8..6cc5c210799ca 100644 --- a/drivers/char/ipmi/ssif_bmc.c +++ b/drivers/char/ipmi/ssif_bmc.c @@ -163,6 +163,8 @@ static ssize_t ssif_bmc_read(struct file *file, char __user *buf, size_t count, spin_unlock_irqrestore(&ssif_bmc->lock, flags); ret = copy_to_user(buf, &msg, count); + if (ret > 0) + ret = -EFAULT; } return (ret < 0) ? ret : count; From ca4d0555000f6e8cb4dd69a758f284d609cccd53 Mon Sep 17 00:00:00 2001 From: Jian Zhang Date: Fri, 3 Apr 2026 17:06:00 +0800 Subject: [PATCH 0696/1518] ipmi: ssif_bmc: fix message desynchronization after truncated response [ Upstream commit 1d38e849adb6851ee280aa1a1d687b2181549a66 ] A truncated response, caused by host power-off, or other conditions, can lead to message desynchronization. Raw trace data (STOP loss scenario, add state transition comment): 1. T-1: Read response phase (SSIF_RES_SENDING) 8271.955342 WR_RCV [03] <- Read polling cmd 8271.955348 RD_REQ [04] <== SSIF_RES_SENDING <- start sending response 8271.955436 RD_PRO [b4] 8271.955527 RD_PRO [00] 8271.955618 RD_PRO [c1] 8271.955707 RD_PRO [00] 8271.955814 RD_PRO [ad] <== SSIF_RES_SENDING <- last byte <- !! STOP lost (truncated response) 2. T: New Write request arrives, BMC still in SSIF_RES_SENDING 8271.967973 WR_REQ [] <== SSIF_RES_SENDING >> SSIF_ABORTING <- log: unexpected WR_REQ in RES_SENDING 8271.968447 WR_RCV [02] <== SSIF_ABORTING <- do nothing 8271.968452 WR_RCV [02] <== SSIF_ABORTING <- do nothing 8271.968454 WR_RCV [18] <== SSIF_ABORTING <- do nothing 8271.968456 WR_RCV [01] <== SSIF_ABORTING <- do nothing 8271.968458 WR_RCV [66] <== SSIF_ABORTING <- do nothing 8271.978714 STOP [] <== SSIF_ABORTING >> SSIF_READY <- log: unexpected SLAVE STOP in state=SSIF_ABORTING 3. T+1: Next Read polling, treated as a fresh transaction 8271.979125 WR_REQ [] <== SSIF_READY >> SSIF_START 8271.979326 WR_RCV [03] <== SSIF_START >> SSIF_SMBUS_CMD <- smbus_cmd=0x03 8271.979331 RD_REQ [04] <== SSIF_RES_SENDING <- sending response 8271.979427 RD_PRO [b4] <- !! this is T's stale response -> desynchronization When in SSIF_ABORTING state, a newly arrived command should still be handled to avoid dropping the request or causing message desynchronization. Fixes: dd2bc5cc9e25 ("ipmi: ssif_bmc: Add SSIF BMC driver") Signed-off-by: Jian Zhang Message-ID: <20260403090603.3988423-3-zhangjian.3032@bytedance.com> Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ssif_bmc.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c index 6cc5c210799ca..ca185793cf978 100644 --- a/drivers/char/ipmi/ssif_bmc.c +++ b/drivers/char/ipmi/ssif_bmc.c @@ -458,6 +458,15 @@ static bool supported_write_cmd(u8 cmd) return false; } +static bool supported_write_start_cmd(u8 cmd) +{ + if (cmd == SSIF_IPMI_SINGLEPART_WRITE || + cmd == SSIF_IPMI_MULTIPART_WRITE_START) + return true; + + return false; +} + /* Process the IPMI response that will be read by master */ static void handle_read_processed(struct ssif_bmc_ctx *ssif_bmc, u8 *val) { @@ -709,6 +718,11 @@ static void on_write_received_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) ssif_bmc->state = SSIF_ABORTING; else ssif_bmc->state = SSIF_REQ_RECVING; + } else if (ssif_bmc->state == SSIF_ABORTING) { + if (supported_write_start_cmd(*val)) { + ssif_bmc->state = SSIF_SMBUS_CMD; + ssif_bmc->aborting = false; + } } /* This is response sending state */ From e21bac13522020a5e5f05ac966dcf46188ed46b2 Mon Sep 17 00:00:00 2001 From: Jian Zhang Date: Fri, 3 Apr 2026 17:06:01 +0800 Subject: [PATCH 0697/1518] ipmi: ssif_bmc: change log level to dbg in irq callback [ Upstream commit c9c99b7b7051eb7121b3224bfce181fb023b0269 ] Long-running tests indicate that this logging can occasionally disrupt timing and lead to request/response corruption. Irq handler need to be executed as fast as possible, most I2C slave IRQ implementations are byte-level, logging here can significantly affect transfer behavior and timing. It is recommended to use dev_dbg() for these messages. Fixes: dd2bc5cc9e25 ("ipmi: ssif_bmc: Add SSIF BMC driver") Signed-off-by: Jian Zhang Message-ID: <20260403090603.3988423-4-zhangjian.3032@bytedance.com> Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ssif_bmc.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c index ca185793cf978..a45e80d13e10e 100644 --- a/drivers/char/ipmi/ssif_bmc.c +++ b/drivers/char/ipmi/ssif_bmc.c @@ -569,7 +569,7 @@ static void process_request_part(struct ssif_bmc_ctx *ssif_bmc) len = ssif_bmc->request.len + part->length; /* Do the bound check here, not allow the request len exceed 254 bytes */ if (len > IPMI_SSIF_PAYLOAD_MAX) { - dev_warn(&ssif_bmc->client->dev, + dev_dbg(&ssif_bmc->client->dev, "Warn: Request exceeded 254 bytes, aborting"); /* Request too long, aborting */ ssif_bmc->aborting = true; @@ -615,7 +615,7 @@ static void on_read_requested_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) ssif_bmc->state == SSIF_START || ssif_bmc->state == SSIF_REQ_RECVING || ssif_bmc->state == SSIF_RES_SENDING) { - dev_warn(&ssif_bmc->client->dev, + dev_dbg(&ssif_bmc->client->dev, "Warn: %s unexpected READ REQUESTED in state=%s\n", __func__, state_to_string(ssif_bmc->state)); ssif_bmc->state = SSIF_ABORTING; @@ -624,7 +624,7 @@ static void on_read_requested_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) } else if (ssif_bmc->state == SSIF_SMBUS_CMD) { if (!supported_read_cmd(ssif_bmc->part_buf.smbus_cmd)) { - dev_warn(&ssif_bmc->client->dev, "Warn: Unknown SMBus read command=0x%x", + dev_dbg(&ssif_bmc->client->dev, "Warn: Unknown SMBus read command=0x%x", ssif_bmc->part_buf.smbus_cmd); ssif_bmc->aborting = true; } @@ -659,7 +659,7 @@ static void on_read_processed_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) ssif_bmc->state == SSIF_START || ssif_bmc->state == SSIF_REQ_RECVING || ssif_bmc->state == SSIF_SMBUS_CMD) { - dev_warn(&ssif_bmc->client->dev, + dev_dbg(&ssif_bmc->client->dev, "Warn: %s unexpected READ PROCESSED in state=%s\n", __func__, state_to_string(ssif_bmc->state)); ssif_bmc->state = SSIF_ABORTING; @@ -684,7 +684,7 @@ static void on_write_requested_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) } else if (ssif_bmc->state == SSIF_START || ssif_bmc->state == SSIF_REQ_RECVING || ssif_bmc->state == SSIF_RES_SENDING) { - dev_warn(&ssif_bmc->client->dev, + dev_dbg(&ssif_bmc->client->dev, "Warn: %s unexpected WRITE REQUEST in state=%s\n", __func__, state_to_string(ssif_bmc->state)); ssif_bmc->state = SSIF_ABORTING; @@ -699,7 +699,7 @@ static void on_write_received_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) { if (ssif_bmc->state == SSIF_READY || ssif_bmc->state == SSIF_RES_SENDING) { - dev_warn(&ssif_bmc->client->dev, + dev_dbg(&ssif_bmc->client->dev, "Warn: %s unexpected WRITE RECEIVED in state=%s\n", __func__, state_to_string(ssif_bmc->state)); ssif_bmc->state = SSIF_ABORTING; @@ -709,7 +709,7 @@ static void on_write_received_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) } else if (ssif_bmc->state == SSIF_SMBUS_CMD) { if (!supported_write_cmd(ssif_bmc->part_buf.smbus_cmd)) { - dev_warn(&ssif_bmc->client->dev, "Warn: Unknown SMBus write command=0x%x", + dev_dbg(&ssif_bmc->client->dev, "Warn: Unknown SMBus write command=0x%x", ssif_bmc->part_buf.smbus_cmd); ssif_bmc->aborting = true; } @@ -738,7 +738,7 @@ static void on_stop_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) ssif_bmc->state == SSIF_START || ssif_bmc->state == SSIF_SMBUS_CMD || ssif_bmc->state == SSIF_ABORTING) { - dev_warn(&ssif_bmc->client->dev, + dev_dbg(&ssif_bmc->client->dev, "Warn: %s unexpected SLAVE STOP in state=%s\n", __func__, state_to_string(ssif_bmc->state)); ssif_bmc->state = SSIF_READY; @@ -805,7 +805,7 @@ static int ssif_bmc_cb(struct i2c_client *client, enum i2c_slave_event event, u8 break; default: - dev_warn(&ssif_bmc->client->dev, "Warn: Unknown i2c slave event\n"); + dev_dbg(&ssif_bmc->client->dev, "Warn: Unknown i2c slave event\n"); break; } From 2db35db04c030829ef609c332add0a7a16baf408 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 3 Apr 2026 23:05:52 -0700 Subject: [PATCH 0698/1518] perf cgroup: Update metric leader in evlist__expand_cgroup [ Upstream commit c9ef786c0970991578397043f1c819229e2b7197 ] When the evlist is expanded the metric leader wasn't being updated. As the original evsel is deleted this creates a use-after-free in stat-shadow's prepare_metric. This was detected running the "perf stat --bpf-counters --for-each-cgroup test" with sanitizers. The change itself puts the copied evsel into the priv field (known unused because of evsel__clone use) and then in a second pass over the list updates the copied values using the priv pointer. Fixes: d1c5a0e86a4e ("perf stat: Add --for-each-cgroup option") Signed-off-by: Ian Rogers Acked-by: Sun Jian Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/cgroup.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 25e2769b5e74f..0038d2ac647c4 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -416,7 +416,6 @@ static bool has_pattern_string(const char *str) int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgroup) { struct evlist *orig_list, *tmp_list; - struct evsel *pos, *evsel, *leader; struct rblist orig_metric_events; struct cgroup *cgrp = NULL; struct cgroup_name *cn; @@ -451,6 +450,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgro goto out_err; list_for_each_entry(cn, &cgroup_list, list) { + struct evsel *pos; char *name; if (!cn->used) @@ -466,21 +466,37 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgro if (cgrp == NULL) continue; - leader = NULL; + /* copy the list and set to the new cgroup. */ evlist__for_each_entry(orig_list, pos) { - evsel = evsel__clone(/*dest=*/NULL, pos); + struct evsel *evsel = evsel__clone(/*dest=*/NULL, pos); + if (evsel == NULL) goto out_err; + /* stash the copy during the copying. */ + pos->priv = evsel; cgroup__put(evsel->cgrp); evsel->cgrp = cgroup__get(cgrp); - if (evsel__is_group_leader(pos)) - leader = evsel; - evsel__set_leader(evsel, leader); - evlist__add(tmp_list, evsel); } + /* update leader information using stashed pointer to copy. */ + evlist__for_each_entry(orig_list, pos) { + struct evsel *evsel = pos->priv; + + if (evsel__leader(pos)) + evsel__set_leader(evsel, evsel__leader(pos)->priv); + + if (pos->metric_leader) + evsel->metric_leader = pos->metric_leader->priv; + + if (pos->first_wildcard_match) + evsel->first_wildcard_match = pos->first_wildcard_match->priv; + } + /* the stashed copy is no longer used. */ + evlist__for_each_entry(orig_list, pos) + pos->priv = NULL; + /* cgroup__new() has a refcount, release it here */ cgroup__put(cgrp); nr_cgroups++; From c98c71ed8834b2f4c6014e1f7de7494e0896d163 Mon Sep 17 00:00:00 2001 From: Inochi Amaoto Date: Wed, 1 Apr 2026 08:35:49 +0800 Subject: [PATCH 0699/1518] pinctrl: sophgo: pinctrl-sg2042: Fix wrong module description [ Upstream commit ca1c2ddff00480c213903a1479b56203536e92de ] Fix the SoC model in module description string, it should be sg2042 instead of sg2002. Fixes: 1e67465d3b74 ("pinctrl: sophgo: add support for SG2042 SoC") Signed-off-by: Inochi Amaoto Reviewed-by: Chen Wang Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/sophgo/pinctrl-sg2042.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/sophgo/pinctrl-sg2042.c b/drivers/pinctrl/sophgo/pinctrl-sg2042.c index 185305ac897d9..8dba12e122a45 100644 --- a/drivers/pinctrl/sophgo/pinctrl-sg2042.c +++ b/drivers/pinctrl/sophgo/pinctrl-sg2042.c @@ -651,5 +651,5 @@ static struct platform_driver sg2042_pinctrl_driver = { }; module_platform_driver(sg2042_pinctrl_driver); -MODULE_DESCRIPTION("Pinctrl driver for the SG2002 series SoC"); +MODULE_DESCRIPTION("Pinctrl driver for the SG2042 series SoC"); MODULE_LICENSE("GPL"); From 59a58ada259c314c3675bc7fb2a2b8ecb158ce1b Mon Sep 17 00:00:00 2001 From: Inochi Amaoto Date: Wed, 1 Apr 2026 08:35:50 +0800 Subject: [PATCH 0700/1518] pinctrl: sophgo: pinctrl-sg2044: Fix wrong module description [ Upstream commit 7648112358a4207916d3e38bfee49f85552fe95f ] Fix the SoC model in module description string, it should be sg2044 instead of sg2002. Fixes: 614a54cb5ac3 ("pinctrl: sophgo: add support for SG2044 SoC") Signed-off-by: Inochi Amaoto Reviewed-by: Chen Wang Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/sophgo/pinctrl-sg2044.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/sophgo/pinctrl-sg2044.c b/drivers/pinctrl/sophgo/pinctrl-sg2044.c index b0c46d8954ca1..cf0b674c038f0 100644 --- a/drivers/pinctrl/sophgo/pinctrl-sg2044.c +++ b/drivers/pinctrl/sophgo/pinctrl-sg2044.c @@ -714,5 +714,5 @@ static struct platform_driver sg2044_pinctrl_driver = { }; module_platform_driver(sg2044_pinctrl_driver); -MODULE_DESCRIPTION("Pinctrl driver for the SG2002 series SoC"); +MODULE_DESCRIPTION("Pinctrl driver for the SG2044 series SoC"); MODULE_LICENSE("GPL"); From def6cd4271e75abc10f0d90e3d50d62d6b672b1b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 7 Apr 2026 19:08:37 -0700 Subject: [PATCH 0701/1518] perf maps: Fix fixup_overlap_and_insert that can break sorted by name order [ Upstream commit c4f3ff3289380437d26177e8f2fe4b7507816ee3 ] When an entry in the address array is replaced, the corresponding name entry is replaced. The entries names may sort differently and so it is important that the sorted by name property be cleared on the maps. Fixes: 0d11fab32714 ("perf maps: Fixup maps_by_name when modifying maps_by_address") Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/maps.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index c51ec159ac769..ff82d1d937b2f 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -924,6 +924,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (maps_by_name) { map__put(maps_by_name[ni]); maps_by_name[ni] = map__get(new); + maps__set_maps_by_name_sorted(maps, false); } err = __maps__insert_sorted(maps, i + 1, after, NULL); @@ -949,6 +950,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (maps_by_name) { map__put(maps_by_name[ni]); maps_by_name[ni] = map__get(new); + maps__set_maps_by_name_sorted(maps, false); } check_invariants(maps); From e97cc0120390cf2e2579af0172f8bb6899a38077 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 7 Apr 2026 19:08:38 -0700 Subject: [PATCH 0702/1518] perf maps: Fix copy_from that can break sorted by name order [ Upstream commit f552b132e4d5248715828e7e5c2bf7889bf05b2e ] When an parent is copied into a child the name array is populated in address not name order. Make sure the name array isn't flagged as sorted. Fixes: 659ad3492b91 ("perf maps: Switch from rbtree to lazily sorted array for addresses") Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/maps.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index ff82d1d937b2f..23aa8a95d0454 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -1032,16 +1032,9 @@ int maps__copy_from(struct maps *dest, struct maps *parent) map__put(new); } maps__set_maps_by_address_sorted(dest, maps__maps_by_address_sorted(parent)); - if (!err) { - RC_CHK_ACCESS(dest)->last_search_by_name_idx = - RC_CHK_ACCESS(parent)->last_search_by_name_idx; - maps__set_maps_by_name_sorted(dest, - dest_maps_by_name && - maps__maps_by_name_sorted(parent)); - } else { - RC_CHK_ACCESS(dest)->last_search_by_name_idx = 0; - maps__set_maps_by_name_sorted(dest, false); - } + RC_CHK_ACCESS(dest)->last_search_by_name_idx = 0; + /* Values were copied into the name array in address order. */ + maps__set_maps_by_name_sorted(dest, false); } else { /* Unexpected copying to a maps containing entries. */ for (unsigned int i = 0; !err && i < n; i++) { From b0cdbc690dae7a80d47631d0acd8dc32fde540d6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 8 Apr 2026 14:31:57 -0300 Subject: [PATCH 0703/1518] perf util: Kill die() prototype, dead for a long time [ Upstream commit e5cce1b9c82fbd48e2f1f7a25a9fad8ee228176f ] In fef2a735167a827a ("perf tools: Kill die()") the die() function was removed, but not the prototype in util.h, now when building with LIBPERL=1, during a 'make -C tools/perf build-test' routine test, it is failing as perl likes die() calls and then this clashes with this remnant, remove it. Fixes: fef2a735167a827a ("perf tools: Kill die()") Reviewed-by: Ian Rogers Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin --- tools/perf/util/util.h | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 3423778e39a56..523550e7d7ed1 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -29,7 +29,6 @@ extern bool perf_guest; /* General helper functions */ void usage(const char *err) __noreturn; -void die(const char *err, ...) __noreturn __printf(1, 2); struct dirent; struct strlist; From c192859f277586732f865db6c59887d48bce3cf0 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Fri, 20 Mar 2026 22:18:02 +0800 Subject: [PATCH 0704/1518] i3c: master: dw-i3c: Fix missing reset assertion in remove() callback [ Upstream commit bef1eef667186cedb0bc6d152464acb3c97d5f72 ] The reset line acquired during probe is currently left deasserted when the driver is unbound. Switch to devm_reset_control_get_optional_exclusive_deasserted() to ensure the reset is automatically re-asserted by the devres core when the driver is removed. Fixes: 62fe9d06f570 ("i3c: dw: Add power management support") Reviewed-by: Philipp Zabel Signed-off-by: Felix Gu Reviewed-by: Frank Li Link: https://patch.msgid.link/20260320-dw-i3c-v3-1-477040c2e3f5@gmail.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/i3c/master/dw-i3c-master.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 825eb2d20e9eb..c6cfcacb18106 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1554,13 +1554,11 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, if (IS_ERR(master->pclk)) return PTR_ERR(master->pclk); - master->core_rst = devm_reset_control_get_optional_exclusive(&pdev->dev, - "core_rst"); + master->core_rst = devm_reset_control_get_optional_exclusive_deasserted(&pdev->dev, + "core_rst"); if (IS_ERR(master->core_rst)) return PTR_ERR(master->core_rst); - reset_control_deassert(master->core_rst); - spin_lock_init(&master->xferqueue.lock); INIT_LIST_HEAD(&master->xferqueue.list); @@ -1572,7 +1570,7 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, dw_i3c_master_irq_handler, 0, dev_name(&pdev->dev), master); if (ret) - goto err_assert_rst; + return ret; platform_set_drvdata(pdev, master); @@ -1610,9 +1608,6 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, pm_runtime_set_suspended(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); -err_assert_rst: - reset_control_assert(master->core_rst); - return ret; } EXPORT_SYMBOL_GPL(dw_i3c_common_probe); From 1b6a7e94be678d34a9ccb9db7e2443ae02ad2bc8 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Mon, 6 Apr 2026 20:43:16 +0800 Subject: [PATCH 0705/1518] i3c: master: renesas: Fix memory leak in renesas_i3c_i3c_xfers() [ Upstream commit d7665c3b4f575251e449e2656879392346ca612b ] The xfer structure allocated by renesas_i3c_alloc_xfer() was never freed in the renesas_i3c_i3c_xfers() function. Use the __free(kfree) cleanup attribute to automatically free the memory when the variable goes out of scope. Fixes: d028219a9f14 ("i3c: master: Add basic driver for the Renesas I3C controller") Tested-by: Tommaso Merciai Reviewed-by: Tommaso Merciai Reviewed-by: Frank Li Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260406-renesas-v3-1-4b724d7708f4@gmail.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/i3c/master/renesas-i3c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i3c/master/renesas-i3c.c b/drivers/i3c/master/renesas-i3c.c index 275f7b9242886..5b1bf5a0266cc 100644 --- a/drivers/i3c/master/renesas-i3c.c +++ b/drivers/i3c/master/renesas-i3c.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -800,13 +801,12 @@ static int renesas_i3c_priv_xfers(struct i3c_dev_desc *dev, struct i3c_priv_xfer struct i3c_master_controller *m = i3c_dev_get_master(dev); struct renesas_i3c *i3c = to_renesas_i3c(m); struct renesas_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); - struct renesas_i3c_xfer *xfer; int i; /* Enable I3C bus. */ renesas_i3c_bus_enable(m, true); - xfer = renesas_i3c_alloc_xfer(i3c, 1); + struct renesas_i3c_xfer *xfer __free(kfree) = renesas_i3c_alloc_xfer(i3c, 1); if (!xfer) return -ENOMEM; From b5a2893ce6fdb88bcfdc3217a19eb191866302be Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Sat, 4 Apr 2026 18:32:30 +0800 Subject: [PATCH 0706/1518] i3c: dw: Fix memory leak in dw_i3c_master_i3c_xfers() [ Upstream commit 256cc1f1305a8e5dcadf8ca208d04a3acadd26f1 ] The dw_i3c_master_i3c_xfers() function allocates memory for the xfer structure using dw_i3c_master_alloc_xfer(). If pm_runtime_resume_and_get() fails, the function returns without freeing the allocated xfer, resulting in a memory leak. Since dw_i3c_master_free_xfer() is a thin wrapper around kfree(), use the __free(kfree) cleanup attribute to handle the free automatically on all exit paths. Fixes: 62fe9d06f570 ("i3c: dw: Add power management support") Signed-off-by: Felix Gu Reviewed-by: Frank Li Link: https://patch.msgid.link/20260404-dw-i3c-2-v3-1-8f7d146549c1@gmail.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/i3c/master/dw-i3c-master.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index c6cfcacb18106..585f320119741 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -905,7 +906,6 @@ static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev, struct i3c_master_controller *m = i3c_dev_get_master(dev); struct dw_i3c_master *master = to_dw_i3c_master(m); unsigned int nrxwords = 0, ntxwords = 0; - struct dw_i3c_xfer *xfer; int i, ret = 0; if (!i3c_nxfers) @@ -925,7 +925,7 @@ static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev, nrxwords > master->caps.datafifodepth) return -EOPNOTSUPP; - xfer = dw_i3c_master_alloc_xfer(master, i3c_nxfers); + struct dw_i3c_xfer *xfer __free(kfree) = dw_i3c_master_alloc_xfer(master, i3c_nxfers); if (!xfer) return -ENOMEM; @@ -976,7 +976,6 @@ static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev, } ret = xfer->ret; - dw_i3c_master_free_xfer(xfer); pm_runtime_put_autosuspend(master->dev); return ret; From 1c70c5b933e21b8bbdc679b8431f6dbafb1d5758 Mon Sep 17 00:00:00 2001 From: Jorge Marques Date: Mon, 23 Mar 2026 17:11:33 +0100 Subject: [PATCH 0707/1518] i3c: master: adi: Fix error propagation for CCCs [ Upstream commit 0b73da96b6eb6b9354654f96a9d423ab22cb222d ] adi_i3c_master_send_ccc_cmd() always returned 0, ignoring the transfer result populated in the completion path. As a consequence, CCC command errors were silently dropped, including the default -ETIMEDOUT and later overwritten by adi_i3c_master_end_xfer_locked(). Fix this by returning xfer->ret so that callers correctly receive any transfer error codes. Fixes: a79ac2cdc91d ("i3c: master: Add driver for Analog Devices I3C Controller IP") Reviewed-by: Adrian Hunter Reviewed-by: Frank Li Signed-off-by: Jorge Marques Link: https://patch.msgid.link/20260323-ad4062-positive-error-fix-v3-5-30bdc68004be@analog.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/i3c/master/adi-i3c-master.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i3c/master/adi-i3c-master.c b/drivers/i3c/master/adi-i3c-master.c index 82ac0b3d057ab..d329faf4b3f96 100644 --- a/drivers/i3c/master/adi-i3c-master.c +++ b/drivers/i3c/master/adi-i3c-master.c @@ -362,7 +362,7 @@ static int adi_i3c_master_send_ccc_cmd(struct i3c_master_controller *m, cmd->err = adi_i3c_cmd_get_err(&xfer->cmds[0]); - return 0; + return xfer->ret; } static int adi_i3c_master_priv_xfers(struct i3c_dev_desc *dev, From 7d88f2e1a972ef3a41863f25643fb1356e0f1ee3 Mon Sep 17 00:00:00 2001 From: Billy Tsai Date: Tue, 7 Apr 2026 16:53:23 +0800 Subject: [PATCH 0708/1518] i3c: mipi-i3c-hci: fix IBI payload length calculation for final status [ Upstream commit d35a6db887eeae7c57b719521e39d64f929c6dc3 ] In DMA mode, the IBI status descriptor encodes the payload using CHUNKS (number of chunks) and DATA_LENGTH (valid bytes in the last chunk). All preceding chunks are implicitly full-sized. The current code accumulates full chunk sizes for non-final status descriptors, but for the final status descriptor it only adds DATA_LENGTH. This ignores the contribution of the preceding full chunks described by the same final status entry. As a result, the computed IBI payload length is truncated whenever the final status spans multiple chunks. For example, with a chunk size of 4 bytes, CHUNKS=2 and DATA_LENGTH=1 should result in a total payload size of 5 bytes, but the current code reports only 1 byte. Fix the calculation by adding the size of (CHUNKS - 1) full chunks plus DATA_LENGTH for the last chunk. Fixes: 9ad9a52cce28 ("i3c/master: introduce the mipi-i3c-hci driver") Signed-off-by: Billy Tsai Reviewed-by: Frank Li Link: https://patch.msgid.link/20260407-i3c-hci-dma-v2-1-a583187b9d22@aspeedtech.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/i3c/master/mipi-i3c-hci/dma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index fe8894f6fe607..42ee94767be3d 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -683,7 +683,10 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh) if (!(ibi_status & IBI_LAST_STATUS)) { ibi_size += chunks * rh->ibi_chunk_sz; } else { - ibi_size += FIELD_GET(IBI_DATA_LENGTH, ibi_status); + if (chunks) { + ibi_size += (chunks - 1) * rh->ibi_chunk_sz; + ibi_size += FIELD_GET(IBI_DATA_LENGTH, ibi_status); + } last_ptr = ptr; break; } From 834dece8ced2bdf781b16a62a17b9b5ed5a0c331 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Tue, 3 Feb 2026 10:16:25 +0800 Subject: [PATCH 0709/1518] backlight: sky81452-backlight: Check return value of devm_gpiod_get_optional() in sky81452_bl_parse_dt() [ Upstream commit 797cc011ae02bda26f93d25a4442d7a1a77d84df ] The devm_gpiod_get_optional() function may return an ERR_PTR in case of genuine GPIO acquisition errors, not just NULL which indicates the legitimate absence of an optional GPIO. Add an IS_ERR() check after the call in sky81452_bl_parse_dt(). On error, return the error code to ensure proper failure handling rather than proceeding with invalid pointers. Fixes: e1915eec54a6 ("backlight: sky81452: Convert to GPIO descriptors") Signed-off-by: Chen Ni Reviewed-by: Linus Walleij Reviewed-by: Daniel Thompson (RISCstar) Link: https://patch.msgid.link/20260203021625.578678-1-nichen@iscas.ac.cn Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/video/backlight/sky81452-backlight.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c index 2749231f03854..b2679b24de14b 100644 --- a/drivers/video/backlight/sky81452-backlight.c +++ b/drivers/video/backlight/sky81452-backlight.c @@ -202,6 +202,9 @@ static struct sky81452_bl_platform_data *sky81452_bl_parse_dt( pdata->dpwm_mode = of_property_read_bool(np, "skyworks,dpwm-mode"); pdata->phase_shift = of_property_read_bool(np, "skyworks,phase-shift"); pdata->gpiod_enable = devm_gpiod_get_optional(dev, NULL, GPIOD_OUT_HIGH); + if (IS_ERR(pdata->gpiod_enable)) + return dev_err_cast_probe(dev, pdata->gpiod_enable, + "failed to get gpio\n"); ret = of_property_count_u32_elems(np, "led-sources"); if (ret < 0) { From 34be68c52af8218d8d21e4b764cf32b0b9b36ce3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 4 Mar 2026 19:54:08 +0100 Subject: [PATCH 0710/1518] platform/surface: surfacepro3_button: Drop wakeup source on remove MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1410a228ab2d36fe2b383415a632ae12048d4f3a ] The wakeup source added by device_init_wakeup() in surface_button_add() needs to be dropped during driver removal, so update the driver to do that. Fixes: 19351f340765 ("platform/x86: surfacepro3: Support for wakeup from suspend-to-idle") Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/4368848.1IzOArtZ34@rafael.j.wysocki Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/surface/surfacepro3_button.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/surface/surfacepro3_button.c b/drivers/platform/surface/surfacepro3_button.c index 2755601f979cd..7c7622f8f8716 100644 --- a/drivers/platform/surface/surfacepro3_button.c +++ b/drivers/platform/surface/surfacepro3_button.c @@ -243,6 +243,7 @@ static void surface_button_remove(struct acpi_device *device) { struct surface_button *button = acpi_driver_data(device); + device_init_wakeup(&device->dev, false); input_unregister_device(button->input); kfree(button); } From 099494e4499dcbc54c4e44354c65d881aaf3678a Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Thu, 26 Feb 2026 11:30:48 +0800 Subject: [PATCH 0711/1518] leds: lgm-sso: Remove duplicate assignments for priv->mmap [ Upstream commit 7186d0330c3f3e86de577687a82f4ebd96dcb5ac ] Remove duplicate assignment of priv->mmap in intel_sso_led_probe(). Fixes: fba8a6f2263b ("leds: lgm-sso: Fix clock handling") Signed-off-by: Chen Ni Link: https://patch.msgid.link/20260226033048.3715915-1-nichen@iscas.ac.cn Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/blink/leds-lgm-sso.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/leds/blink/leds-lgm-sso.c b/drivers/leds/blink/leds-lgm-sso.c index 8923d2df47049..3d9ef9a54805c 100644 --- a/drivers/leds/blink/leds-lgm-sso.c +++ b/drivers/leds/blink/leds-lgm-sso.c @@ -808,8 +808,6 @@ static int intel_sso_led_probe(struct platform_device *pdev) priv->fpid_clkrate = clk_get_rate(priv->clocks[1].clk); - priv->mmap = syscon_node_to_regmap(dev->of_node); - priv->mmap = syscon_node_to_regmap(dev->of_node); if (IS_ERR(priv->mmap)) { dev_err(dev, "Failed to map iomem!\n"); From 19951118fb22b5ad512379ee64510fe0e2c40eb3 Mon Sep 17 00:00:00 2001 From: Ethan Tidmore Date: Wed, 18 Feb 2026 15:46:21 -0600 Subject: [PATCH 0712/1518] usb: typec: Fix error pointer dereference [ Upstream commit f2529d08fcb429ea01bb87c326342f41483f8b2f ] The variable tps->partner is checked for an error pointer and then if it is, it sends an error message but does not return and then immediately dereferenced a few lines below: tps->partner = typec_register_partner(tps->port, &desc); if (IS_ERR(tps->partner)) dev_warn(tps->dev, "%s: failed to register partnet\n", __func__); if (desc.identity) { typec_partner_set_identity(tps->partner); cd321x->cur_partner_identity = st.partner_identity; } Add early return and fix spelling mistake in error message. Detected by Smatch: drivers/usb/typec/tipd/core.c:827 cd321x_update_work() error: 'tps->partner' dereferencing possible ERR_PTR() Fixes: 82432bbfb9e83 ("usb: typec: tipd: Handle mode transitions for CD321x") Signed-off-by: Ethan Tidmore Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260218214621.38154-1-ethantidmore06@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/tipd/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 2b1049c9a6f3c..01c657bc84e68 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -814,8 +814,10 @@ static void cd321x_update_work(struct work_struct *work) desc.identity = &st.partner_identity; tps->partner = typec_register_partner(tps->port, &desc); - if (IS_ERR(tps->partner)) - dev_warn(tps->dev, "%s: failed to register partnet\n", __func__); + if (IS_ERR(tps->partner)) { + dev_warn(tps->dev, "%s: failed to register partner\n", __func__); + return; + } if (desc.identity) { typec_partner_set_identity(tps->partner); From 3104a3f40feb107f77d7116ad9bf6c210ab7babf Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 29 Jan 2026 23:29:37 -0800 Subject: [PATCH 0713/1518] tty: hvc_iucv: fix off-by-one in number of supported devices [ Upstream commit f2a880e802ad12d1e38039d1334fb1475d0f5241 ] MAX_HVC_IUCV_LINES == HVC_ALLOC_TTY_ADAPTERS == 8. This is the number of entries in: static struct hvc_iucv_private *hvc_iucv_table[MAX_HVC_IUCV_LINES]; Sometimes hvc_iucv_table[] is limited by: (a) if (num > hvc_iucv_devices) // for error detection or (b) for (i = 0; i < hvc_iucv_devices; i++) // in 2 places (so these 2 don't agree; second one appears to be correct to me.) hvc_iucv_devices can be 0..8. This is a counter. (c) if (hvc_iucv_devices > MAX_HVC_IUCV_LINES) If hvc_iucv_devices == 8, (a) allows the code to access hvc_iucv_table[8]. Oops. Fixes: 44a01d5ba8a4 ("[S390] s390/hvc_console: z/VM IUCV hypervisor console support") Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20260130072939.1535869-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/hvc/hvc_iucv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c index 4ca7472c38e01..612e13b6f22bc 100644 --- a/drivers/tty/hvc/hvc_iucv.c +++ b/drivers/tty/hvc/hvc_iucv.c @@ -131,7 +131,7 @@ static struct iucv_handler hvc_iucv_handler = { */ static struct hvc_iucv_private *hvc_iucv_get_private(uint32_t num) { - if (num > hvc_iucv_devices) + if (num >= hvc_iucv_devices) return NULL; return hvc_iucv_table[num]; } From 37a3d1b6827783f26d2f8e6c7683e253ba79ae93 Mon Sep 17 00:00:00 2001 From: Mostafa Saleh Date: Fri, 13 Mar 2026 15:55:34 +0000 Subject: [PATCH 0714/1518] usb: typec: ps883x: Fix Oops at unbind [ Upstream commit 381133848a033c2086cf9cafb226f425bd0414ff ] When trying to unbind a device in order to bind to it vfio-platform as: echo bc0000.geniqup > /sys/bus/platform/devices/bc0000.geniqup/driver/unbind I get the following Oops: [ 436.478639] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 [ 436.487762] Mem abort info: [ 436.490716] ESR = 0x0000000096000004 [ 436.494595] EC = 0x25: DABT (current EL), IL = 32 bits [ 436.500071] SET = 0, FnV = 0 [ 436.503250] EA = 0, S1PTW = 0 [ 436.506505] FSC = 0x04: level 0 translation fault [ 436.511533] Data abort info: [ 436.514558] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 436.520215] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 436.525436] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 436.530918] user pgtable: 4k pages, 48-bit VAs, pgdp=00000008861a9000 [ 436.537554] [0000000000000020] pgd=0000000000000000, p4d=0000000000000000 [ 436.544548] Internal error: Oops: 0000000096000004 [#1] SMP [ 436.550374] Modules linked in: [ 436.553542] CPU: 2 UID: 0 PID: 671 Comm: bash Tainted: G W 7.0.0-rc3-g56fcdd0911a5-dirty #2 PREEMPT [ 436.564440] Tainted: [W]=WARN [ 436.567515] Hardware name: LENOVO 91B6CTO1WW/3796, BIOS O6NKT3BA 05/02/2025 [ 436.574675] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 436.581841] pc : ps883x_retimer_remove+0x14/0x94 [ 436.586605] lr : i2c_device_remove+0x28/0x84 [ 436.591017] sp : ffff8000847137c0 That's because the ps883x_retimer_remove() retrieves the driver data from i2c_get_clientdata() which was never set at probe. So, add i2c_set_clientdata() at the end of the probe. Signed-off-by: Mostafa Saleh Reviewed-by: Konrad Dybcio Fixes: 257a087c8b52 ("usb: typec: Add support for Parade PS8830 Type-C Retimer") Link: https://patch.msgid.link/20260313155534.1916773-1-smostafa@google.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/mux/ps883x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/typec/mux/ps883x.c b/drivers/usb/typec/mux/ps883x.c index ad59babf7ccec..f1f65d4e5729b 100644 --- a/drivers/usb/typec/mux/ps883x.c +++ b/drivers/usb/typec/mux/ps883x.c @@ -411,6 +411,7 @@ static int ps883x_retimer_probe(struct i2c_client *client) goto err_switch_unregister; } + i2c_set_clientdata(client, retimer); return 0; err_switch_unregister: From e4a666652daece49053264c0590393a0a183c0e9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 20 Mar 2026 11:31:54 +0100 Subject: [PATCH 0715/1518] platform/x86: panasonic-laptop: Fix OPTD notifier registration and cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8baeff2c1d33dad8572216c6ad3a7425852507d4 ] An ACPI notify handler is leaked if device_create_file() returns an error in acpi_pcc_hotkey_add(). Also, it is pointless to call pcc_unregister_optd_notifier() in acpi_pcc_hotkey_remove() if pcc->platform is NULL and it is better to arrange the cleanup code in that function in the same order as the rollback code in acpi_pcc_hotkey_add(). Address the above by placing the pcc_register_optd_notifier() call in acpi_pcc_hotkey_add() after the device_create_file() return value check and placing the pcc_unregister_optd_notifier() call in acpi_pcc_hotkey_remove() right before the device_remove_file() call. Fixes: d5a81d8e864b ("platform/x86: panasonic-laptop: Add support for optical driver power in Y and W series") Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/2411055.ElGaqSPkdT@rafael.j.wysocki Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/panasonic-laptop.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 937f1a5b78edf..848ebf46a59b1 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -1093,9 +1093,10 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) } result = device_create_file(&pcc->platform->dev, &dev_attr_cdpower); - pcc_register_optd_notifier(pcc, "\\_SB.PCI0.EHCI.ERHB.OPTD"); if (result) goto out_platform; + + pcc_register_optd_notifier(pcc, "\\_SB.PCI0.EHCI.ERHB.OPTD"); } else { pcc->platform = NULL; } @@ -1129,10 +1130,10 @@ static void acpi_pcc_hotkey_remove(struct acpi_device *device) i8042_remove_filter(panasonic_i8042_filter); if (pcc->platform) { + pcc_unregister_optd_notifier(pcc, "\\_SB.PCI0.EHCI.ERHB.OPTD"); device_remove_file(&pcc->platform->dev, &dev_attr_cdpower); platform_device_unregister(pcc->platform); } - pcc_unregister_optd_notifier(pcc, "\\_SB.PCI0.EHCI.ERHB.OPTD"); sysfs_remove_group(&device->dev.kobj, &pcc_attr_group); From cc7716bd050be5bd8d69b9dacbac25780d7d8ca3 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 18 Mar 2026 19:56:17 -0700 Subject: [PATCH 0716/1518] platform/x86: barco-p50-gpio: normalize return value of gpio_get MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1c9d30d37aaffe3454d70b89a77f8aaecda257bf ] The GPIO get callback is expected to return 0 or 1 (or a negative error code). Ensure that the value returned by p50_gpio_get() is normalized to the [0, 1] range. Fixes: 86ef402d805d606a ("gpiolib: sanitize the return value of gpio_chip::get()") Reviewed-by: Linus Walleij Signed-off-by: Dmitry Torokhov Reviewed-by: Bartosz Golaszewski Link: https://patch.msgid.link/20260318-barco-p50-gpio-set-v2-1-c0a4a6416163@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/barco-p50-gpio.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/barco-p50-gpio.c b/drivers/platform/x86/barco-p50-gpio.c index 6f13e81f98fbb..360ffd8505d6c 100644 --- a/drivers/platform/x86/barco-p50-gpio.c +++ b/drivers/platform/x86/barco-p50-gpio.c @@ -275,8 +275,11 @@ static int p50_gpio_get(struct gpio_chip *gc, unsigned int offset) mutex_lock(&p50->lock); ret = p50_send_mbox_cmd(p50, P50_MBOX_CMD_READ_GPIO, gpio_params[offset], 0); - if (ret == 0) + if (ret == 0) { ret = p50_read_mbox_reg(p50, P50_MBOX_REG_DATA); + if (ret >= 0) + ret = !!ret; + } mutex_unlock(&p50->lock); From ac8551a4254d6d8939dd61147d74b449f15da774 Mon Sep 17 00:00:00 2001 From: Abdun Nihaal Date: Tue, 20 Jan 2026 15:56:20 +0530 Subject: [PATCH 0717/1518] mfd: mc13xxx-core: Fix memory leak in mc13xxx_add_subdevice_pdata() [ Upstream commit a5a65a7fb2f7796bbe492cd6be59c92cb64377d1 ] The memory allocated for cell.name using kmemdup() is not freed when mfd_add_devices() fails. Fix that by using devm_kmemdup(). Fixes: 8e00593557c3 ("mfd: Add mc13892 support to mc13xxx") Signed-off-by: Abdun Nihaal Link: https://patch.msgid.link/20260120102622.66921-1-nihaal@cse.iitm.ac.in Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/mc13xxx-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c index 920797b806ced..786eab3b2d03c 100644 --- a/drivers/mfd/mc13xxx-core.c +++ b/drivers/mfd/mc13xxx-core.c @@ -377,7 +377,7 @@ static int mc13xxx_add_subdevice_pdata(struct mc13xxx *mc13xxx, if (snprintf(buf, sizeof(buf), format, name) > sizeof(buf)) return -E2BIG; - cell.name = kmemdup(buf, strlen(buf) + 1, GFP_KERNEL); + cell.name = devm_kmemdup(mc13xxx->dev, buf, strlen(buf) + 1, GFP_KERNEL); if (!cell.name) return -ENOMEM; From 248e4b9cc719ffd92f939d4b85fc21480eb0c829 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Feb 2026 21:21:49 +0100 Subject: [PATCH 0718/1518] nfs/blocklayout: Fix compilation error (`make W=1`) in bl_write_pagelist() [ Upstream commit f83c8dda456ce4863f346aa26d88efa276eda35d ] Clang compiler is not happy about set but unused variable (when dprintk() is no-op): .../blocklayout/blocklayout.c:384:9: error: variable 'count' set but not used [-Werror,-Wunused-but-set-variable] Remove a leftover from the previous cleanup. Fixes: 3a6fd1f004fc ("pnfs/blocklayout: remove read-modify-write handling in bl_write_pagelist") Acked-by: Anna Schumaker Reviewed-by: Jeff Layton Signed-off-by: Andy Shevchenko Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfs/blocklayout/blocklayout.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 0e4c67373e4f9..83e4a32b30182 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -381,14 +381,13 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) sector_t isect, extent_length = 0; struct parallel_io *par = NULL; loff_t offset = header->args.offset; - size_t count = header->args.count; struct page **pages = header->args.pages; int pg_index = header->args.pgbase >> PAGE_SHIFT; unsigned int pg_len; struct blk_plug plug; int i; - dprintk("%s enter, %zu@%lld\n", __func__, count, offset); + dprintk("%s enter, %u@%lld\n", __func__, header->args.count, offset); /* At this point, header->page_aray is a (sequential) list of nfs_pages. * We want to write each, and if there is an error set pnfs_error @@ -429,7 +428,6 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) } offset += pg_len; - count -= pg_len; isect += (pg_len >> SECTOR_SHIFT); extent_length -= (pg_len >> SECTOR_SHIFT); } From 4584229395d0d65bd517780afe97ffea07cb2c3d Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Wed, 4 Feb 2026 13:07:43 -0800 Subject: [PATCH 0719/1518] NFSD: fix nfs4_file access extra count in nfsd4_add_rdaccess_to_wrdeleg [ Upstream commit b48f44f36e6607b2f818560f19deb86b4a9c717b ] In nfsd4_add_rdaccess_to_wrdeleg, if fp->fi_fds[O_RDONLY] is already set by another thread, __nfs4_file_get_access should not be called to increment the nfs4_file access count since that was already done by the thread that added READ access to the file. The extra fi_access count in nfs4_file can prevent the corresponding nfsd_file from being freed. When stopping nfs-server service, these extra access counts trigger a BUG in kmem_cache_destroy() that shows nfsd_file object remaining on __kmem_cache_shutdown. This problem can be reproduced by running the Git project's test suite over NFS. Fixes: 8072e34e1387 ("nfsd: fix nfsd_file reference leak in nfsd4_add_rdaccess_to_wrdeleg()") Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4state.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c5dba49c90356..adc33830438bb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -6255,12 +6255,12 @@ nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, return (false); fp = stp->st_stid.sc_file; spin_lock(&fp->fi_lock); - __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); if (!fp->fi_fds[O_RDONLY]) { + __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); fp->fi_fds[O_RDONLY] = nf; + fp->fi_rdeleg_file = nfsd_file_get(fp->fi_fds[O_RDONLY]); nf = NULL; } - fp->fi_rdeleg_file = nfsd_file_get(fp->fi_fds[O_RDONLY]); spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); From 38a9aa192ef73b6c0d3e96a39e8d81fbcb30b982 Mon Sep 17 00:00:00 2001 From: Denis Benato Date: Mon, 2 Mar 2026 18:44:30 +0100 Subject: [PATCH 0720/1518] platform/x86: asus-wmi: adjust screenpad power/brightness handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 130d29c5627cd50e786e926ad7ef66322c5a0c09 ] Fix illogical screen off control by hardcoding 0 and 1 depending on the requested brightness and also do not rely on the last screenpad power state to issue screen brightness commands. Fixes: 2c97d3e55b70 ("platform/x86: asus-wmi: add support for ASUS screenpad") Signed-off-by: Denis Benato Signed-off-by: Luke Jones Link: https://patch.msgid.link/20260302174431.349816-2-denis.benato@linux.dev Link: https://patch.msgid.link/20260326231154.856729-2-ethantidmore06@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/asus-wmi.c | 34 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 21 deletions(-) diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 8e3300f5c2943..e6fe6ed6a63da 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -4154,32 +4154,24 @@ static int read_screenpad_brightness(struct backlight_device *bd) static int update_screenpad_bl_status(struct backlight_device *bd) { - struct asus_wmi *asus = bl_get_data(bd); - int power, err = 0; - u32 ctrl_param; + u32 ctrl_param = bd->props.brightness; + int err = 0; - power = read_screenpad_backlight_power(asus); - if (power < 0) - return power; + if (bd->props.power) { + err = asus_wmi_set_devstate(ASUS_WMI_DEVID_SCREENPAD_POWER, 1, NULL); + if (err < 0) + return err; - if (bd->props.power != power) { - if (power != BACKLIGHT_POWER_ON) { - /* Only brightness > 0 can power it back on */ - ctrl_param = asus->driver->screenpad_brightness - ASUS_SCREENPAD_BRIGHT_MIN; - err = asus_wmi_set_devstate(ASUS_WMI_DEVID_SCREENPAD_LIGHT, - ctrl_param, NULL); - } else { - err = asus_wmi_set_devstate(ASUS_WMI_DEVID_SCREENPAD_POWER, 0, NULL); - } - } else if (power == BACKLIGHT_POWER_ON) { - /* Only set brightness if powered on or we get invalid/unsync state */ - ctrl_param = bd->props.brightness + ASUS_SCREENPAD_BRIGHT_MIN; err = asus_wmi_set_devstate(ASUS_WMI_DEVID_SCREENPAD_LIGHT, ctrl_param, NULL); + if (err < 0) + return err; } - /* Ensure brightness is stored to turn back on with */ - if (err == 0) - asus->driver->screenpad_brightness = bd->props.brightness + ASUS_SCREENPAD_BRIGHT_MIN; + if (!bd->props.power) { + err = asus_wmi_set_devstate(ASUS_WMI_DEVID_SCREENPAD_POWER, 0, NULL); + if (err < 0) + return err; + } return err; } From bfd3e5309503380fca1fe2d73c94a1b33dfc4801 Mon Sep 17 00:00:00 2001 From: Denis Benato Date: Mon, 2 Mar 2026 18:44:31 +0100 Subject: [PATCH 0721/1518] platform/x86: asus-wmi: fix screenpad brightness range MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8d95d1f4aa5c76202b0833a70998769384612488 ] Fix screenpad brightness range being too limited without reason: testing this patch on a Zenbook Duo showed the hardware minimum not being too low, therefore allow the user to configure the entire range, and expose to userspace the hardware brightness range and value. Fixes: 2c97d3e55b70 ("platform/x86: asus-wmi: add support for ASUS screenpad") Signed-off-by: Denis Benato Signed-off-by: Luke Jones Link: https://patch.msgid.link/20260302174431.349816-3-denis.benato@linux.dev Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/asus-wmi.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index e6fe6ed6a63da..9026744d72267 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -127,7 +127,6 @@ module_param(fnlock_default, bool, 0444); #define NVIDIA_TEMP_MIN 75 #define NVIDIA_TEMP_MAX 87 -#define ASUS_SCREENPAD_BRIGHT_MIN 20 #define ASUS_SCREENPAD_BRIGHT_MAX 255 #define ASUS_SCREENPAD_BRIGHT_DEFAULT 60 @@ -4143,13 +4142,13 @@ static int read_screenpad_brightness(struct backlight_device *bd) return err; /* The device brightness can only be read if powered, so return stored */ if (err == BACKLIGHT_POWER_OFF) - return asus->driver->screenpad_brightness - ASUS_SCREENPAD_BRIGHT_MIN; + return bd->props.brightness; err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_SCREENPAD_LIGHT, &retval); if (err < 0) return err; - return (retval & ASUS_WMI_DSTS_BRIGHTNESS_MASK) - ASUS_SCREENPAD_BRIGHT_MIN; + return retval & ASUS_WMI_DSTS_BRIGHTNESS_MASK; } static int update_screenpad_bl_status(struct backlight_device *bd) @@ -4189,22 +4188,19 @@ static int asus_screenpad_init(struct asus_wmi *asus) int err, power; int brightness = 0; - power = read_screenpad_backlight_power(asus); + power = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_SCREENPAD_POWER); if (power < 0) return power; - if (power != BACKLIGHT_POWER_OFF) { + if (power) { err = asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_SCREENPAD_LIGHT, &brightness); if (err < 0) return err; } - /* default to an acceptable min brightness on boot if too low */ - if (brightness < ASUS_SCREENPAD_BRIGHT_MIN) - brightness = ASUS_SCREENPAD_BRIGHT_DEFAULT; memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; /* ensure this bd is last to be picked */ - props.max_brightness = ASUS_SCREENPAD_BRIGHT_MAX - ASUS_SCREENPAD_BRIGHT_MIN; + props.max_brightness = ASUS_SCREENPAD_BRIGHT_MAX; bd = backlight_device_register("asus_screenpad", &asus->platform_device->dev, asus, &asus_screenpad_bl_ops, &props); @@ -4215,7 +4211,7 @@ static int asus_screenpad_init(struct asus_wmi *asus) asus->screenpad_backlight_device = bd; asus->driver->screenpad_brightness = brightness; - bd->props.brightness = brightness - ASUS_SCREENPAD_BRIGHT_MIN; + bd->props.brightness = brightness; bd->props.power = power; backlight_update_status(bd); From c44ad02d591bac06e57a701cff980150bcb2d356 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 2 Apr 2026 12:21:53 +0200 Subject: [PATCH 0722/1518] tty: serial: ip22zilog: Fix section mispatch warning [ Upstream commit a1a81aef99e853dec84241d701fbf587d713eb5b ] ip22zilog_prepare() is now called by driver probe routine, so it shouldn't be in the __init section any longer. Fixes: 3fc36ae6abd2 ("tty: serial: ip22zilog: Use platform device for probing") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202604020945.c9jAvCPs-lkp@intel.com/ Signed-off-by: Thomas Bogendoerfer Link: https://patch.msgid.link/20260402102154.136620-1-tbogendoerfer@suse.de Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/ip22zilog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/ip22zilog.c b/drivers/tty/serial/ip22zilog.c index 6e19c6713849a..a12101dc05546 100644 --- a/drivers/tty/serial/ip22zilog.c +++ b/drivers/tty/serial/ip22zilog.c @@ -1025,7 +1025,7 @@ static struct uart_driver ip22zilog_reg = { #endif }; -static void __init ip22zilog_prepare(struct uart_ip22zilog_port *up) +static void ip22zilog_prepare(struct uart_ip22zilog_port *up) { unsigned char sysrq_on = IS_ENABLED(CONFIG_SERIAL_IP22_ZILOG_CONSOLE); int brg; From 6136bbb054f7ab9f51ae99915541633b18bcef90 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Fri, 27 Mar 2026 14:19:55 +0800 Subject: [PATCH 0723/1518] fs/ntfs3: terminate the cached volume label after UTF-8 conversion [ Upstream commit a6cd43fe9b083fa23fe1595666d5738856cb261a ] ntfs_fill_super() loads the on-disk volume label with utf16s_to_utf8s() and stores the result in sbi->volume.label. The converted label is later exposed through ntfs3_label_show() using %s, but utf16s_to_utf8s() only returns the number of bytes written and does not add a trailing NUL. If the converted label fills the entire fixed buffer, ntfs3_label_show() can read past the end of sbi->volume.label while looking for a terminator. Terminate the cached label explicitly after a successful conversion and clamp the exact-full case to the last byte of the buffer. Fixes: 82cae269cfa9 ("fs/ntfs3: Add initialization of super block") Signed-off-by: Pengpeng Hou Signed-off-by: Konstantin Komarov Signed-off-by: Sasha Levin --- fs/ntfs3/super.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index e6c0908e27c29..9a2e3d0efd998 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1277,8 +1277,13 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) le32_to_cpu(attr->res.data_size) >> 1, UTF16_LITTLE_ENDIAN, sbi->volume.label, sizeof(sbi->volume.label)); - if (err < 0) + if (err < 0) { sbi->volume.label[0] = 0; + } else if (err >= sizeof(sbi->volume.label)) { + sbi->volume.label[sizeof(sbi->volume.label) - 1] = 0; + } else { + sbi->volume.label[err] = 0; + } } else { /* Should we break mounting here? */ //err = -EINVAL; From 58688eeaa3079ff20e85faa7c5727dee2074cfb1 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 3 Apr 2026 16:42:39 +0300 Subject: [PATCH 0724/1518] platform/x86: dell_rbu: avoid uninit value usage in packet_size_write() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f8fd138c2363c0e2d3235c32bfb4fb5c6474e4ae ] Ensure the temp value has been properly parsed from the user-provided buffer and initialized to be used in later operations. While at it, prefer a convenient kstrtoul() helper. Found by Linux Verification Center (linuxtesting.org) with Svace static analysis tool. Fixes: ad6ce87e5bd4 ("[PATCH] dell_rbu: changes in packet update mechanism") Signed-off-by: Fedor Pchelkin Link: https://patch.msgid.link/20260403134240.604837-1-pchelkin@ispras.ru [ij: add include] Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/dell/dell_rbu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c index 403df9bd9522b..69d7c0a931a7c 100644 --- a/drivers/platform/x86/dell/dell_rbu.c +++ b/drivers/platform/x86/dell/dell_rbu.c @@ -30,6 +30,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -619,9 +620,12 @@ static ssize_t packet_size_write(struct file *filp, struct kobject *kobj, char *buffer, loff_t pos, size_t count) { unsigned long temp; + + if (kstrtoul(buffer, 10, &temp)) + return -EINVAL; + spin_lock(&rbu_data.lock); packet_empty_list(); - sscanf(buffer, "%lu", &temp); if (temp < 0xffffffff) rbu_data.packetsize = temp; From c5683ca4949a514fbe656c6d0d08c4c126e21db9 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Wed, 8 Apr 2026 08:38:21 +0800 Subject: [PATCH 0725/1518] platform/x86: dell-wmi-sysman: bound enumeration string aggregation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3c34471c26abc52a37f5ad90949e2e4b8027eb14 ] populate_enum_data() aggregates firmware-provided value-modifier and possible-value strings into fixed 512-byte struct members. The current code bounds each individual source string but then appends every string and separator with raw strcat() and no remaining-space check. Switch the aggregation loops to a bounded append helper and reject enumeration packages whose combined strings do not fit in the destination buffers. Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems") Signed-off-by: Pengpeng Hou Link: https://patch.msgid.link/20260408084501.1-dell-wmi-sysman-v2-pengpeng@iscas.ac.cn [ij: add include] Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- .../dell/dell-wmi-sysman/enum-attributes.c | 34 +++++++++++++++---- 1 file changed, 28 insertions(+), 6 deletions(-) diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c index fc2f58b4cbc6e..7e44ba3015627 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c @@ -6,10 +6,32 @@ * Copyright (c) 2020 Dell Inc. */ +#include + #include "dell-wmi-sysman.h" get_instance_id(enumeration); +static int append_enum_string(char *dest, const char *src) +{ + size_t dest_len = strlen(dest); + ssize_t copied; + + if (WARN_ON_ONCE(dest_len >= MAX_BUFF)) + return -EINVAL; + + copied = strscpy(dest + dest_len, src, MAX_BUFF - dest_len); + if (copied < 0) + return -EINVAL; + + dest_len += copied; + copied = strscpy(dest + dest_len, ";", MAX_BUFF - dest_len); + if (copied < 0) + return -EINVAL; + + return 0; +} + static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { int instance_id = get_enumeration_instance_id(kobj); @@ -176,9 +198,9 @@ int populate_enum_data(union acpi_object *enumeration_obj, int instance_id, return -EINVAL; if (check_property_type(enumeration, next_obj, ACPI_TYPE_STRING)) return -EINVAL; - strcat(wmi_priv.enumeration_data[instance_id].dell_value_modifier, - enumeration_obj[next_obj++].string.pointer); - strcat(wmi_priv.enumeration_data[instance_id].dell_value_modifier, ";"); + if (append_enum_string(wmi_priv.enumeration_data[instance_id].dell_value_modifier, + enumeration_obj[next_obj++].string.pointer)) + return -EINVAL; } if (next_obj >= enum_property_count) @@ -193,9 +215,9 @@ int populate_enum_data(union acpi_object *enumeration_obj, int instance_id, return -EINVAL; if (check_property_type(enumeration, next_obj, ACPI_TYPE_STRING)) return -EINVAL; - strcat(wmi_priv.enumeration_data[instance_id].possible_values, - enumeration_obj[next_obj++].string.pointer); - strcat(wmi_priv.enumeration_data[instance_id].possible_values, ";"); + if (append_enum_string(wmi_priv.enumeration_data[instance_id].possible_values, + enumeration_obj[next_obj++].string.pointer)) + return -EINVAL; } return sysfs_create_group(attr_name_kobj, &enumeration_attr_group); From f2c7b39dde2e61df8157066969cc2a408cd3dcd9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 30 Mar 2026 14:27:39 +0200 Subject: [PATCH 0726/1518] RDMA/core: Prefer NLA_NUL_STRING [ Upstream commit 6ed3d14fc45d3da6025e7fe4a6a09066856698e2 ] These attributes are evaluated as c-string (passed to strcmp), but NLA_STRING doesn't check for the presence of a \0 terminator. Either this needs to switch to nla_strcmp() and needs to adjust printf fmt specifier to not use plain %s, or this needs to use NLA_NUL_STRING. As the code has been this way for long time, it seems to me that userspace does include the terminating nul, even tough its not enforced so far, and thus NLA_NUL_STRING use is the simpler solution. Fixes: 30dc5e63d6a5 ("RDMA/core: Add support for iWARP Port Mapper user space service") Link: https://patch.msgid.link/r/20260330122742.13315-1-fw@strlen.de Signed-off-by: Florian Westphal Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/core/iwpm_msg.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 3c9a9869212bb..feb09008eb9ca 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -365,9 +365,9 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) /* netlink attribute policy for the received response to register pid request */ static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = { [IWPM_NLA_RREG_PID_SEQ] = { .type = NLA_U32 }, - [IWPM_NLA_RREG_IBDEV_NAME] = { .type = NLA_STRING, + [IWPM_NLA_RREG_IBDEV_NAME] = { .type = NLA_NUL_STRING, .len = IWPM_DEVNAME_SIZE - 1 }, - [IWPM_NLA_RREG_ULIB_NAME] = { .type = NLA_STRING, + [IWPM_NLA_RREG_ULIB_NAME] = { .type = NLA_NUL_STRING, .len = IWPM_ULIBNAME_SIZE - 1 }, [IWPM_NLA_RREG_ULIB_VER] = { .type = NLA_U16 }, [IWPM_NLA_RREG_PID_ERR] = { .type = NLA_U16 } @@ -677,7 +677,7 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb) /* netlink attribute policy for the received request for mapping info */ static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = { - [IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_STRING, + [IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_NUL_STRING, .len = IWPM_ULIBNAME_SIZE - 1 }, [IWPM_NLA_MAPINFO_ULIB_VER] = { .type = NLA_U16 } }; From 927c8a511c2aa01d0f380fe36d13ef0c8d65a728 Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Mon, 2 Feb 2026 16:26:50 +0530 Subject: [PATCH 0727/1518] dt-bindings: clock: qcom: Add GCC video axi reset clock for Glymur [ Upstream commit 7c3260327fc874b7c89d7bb230cd569d2e78aff7 ] The global clock controller video axi reset clocks are required by the video SW driver to assert and deassert the clock resets. Signed-off-by: Taniya Das Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20260202-glymur_videocc-v2-1-8f7d8b4d8edd@oss.qualcomm.com Signed-off-by: Bjorn Andersson Stable-dep-of: 1c8ce43e1e07 ("clk: qcom: gcc-glymur: Add video axi clock resets for glymur") Signed-off-by: Sasha Levin --- include/dt-bindings/clock/qcom,glymur-gcc.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/dt-bindings/clock/qcom,glymur-gcc.h b/include/dt-bindings/clock/qcom,glymur-gcc.h index 10c12b8c51c34..6907653c79927 100644 --- a/include/dt-bindings/clock/qcom,glymur-gcc.h +++ b/include/dt-bindings/clock/qcom,glymur-gcc.h @@ -574,5 +574,6 @@ #define GCC_VIDEO_AXI0_CLK_ARES 89 #define GCC_VIDEO_AXI1_CLK_ARES 90 #define GCC_VIDEO_BCR 91 +#define GCC_VIDEO_AXI0C_CLK_ARES 92 #endif From 1e56e335bc86044539252ae238d5c3be281b38c7 Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Mon, 2 Feb 2026 16:26:52 +0530 Subject: [PATCH 0728/1518] clk: qcom: gcc-glymur: Add video axi clock resets for glymur [ Upstream commit 1c8ce43e1e07ecc531fb517f95620ed85e998608 ] The global clock controller video axi reset clocks are required by the video SW driver to assert and deassert the clock resets during their power down sequence. Hence add these clock resets. Fixes: efe504300a17 ("clk: qcom: gcc: Add support for Global Clock Controller") Signed-off-by: Taniya Das Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260202-glymur_videocc-v2-3-8f7d8b4d8edd@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-glymur.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/qcom/gcc-glymur.c b/drivers/clk/qcom/gcc-glymur.c index 17e860307fa10..eff3248d483ad 100644 --- a/drivers/clk/qcom/gcc-glymur.c +++ b/drivers/clk/qcom/gcc-glymur.c @@ -8508,6 +8508,7 @@ static const struct qcom_reset_map gcc_glymur_resets[] = { [GCC_VIDEO_AXI0_CLK_ARES] = { 0x3201c, 2 }, [GCC_VIDEO_AXI1_CLK_ARES] = { 0x32044, 2 }, [GCC_VIDEO_BCR] = { 0x32000 }, + [GCC_VIDEO_AXI0C_CLK_ARES] = { 0x32030, 2 }, }; static const struct clk_rcg_dfs_data gcc_dfs_clocks[] = { From 89715e519ab7900ea40c7f86a90072ed697b748d Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 12 Jan 2026 04:12:22 +0200 Subject: [PATCH 0729/1518] clk: qcom: dispcc-glymur: use RCG2 ops for DPTX1 AUX clock source [ Upstream commit e7c8eb1646db5d967d77ee67793dd95a2c5ff451 ] The clk_dp_ops are supposed to be used for DP-related clocks with a proper MND divier. Use shared RCG2 ops for dptx1_aux_clk_src, the same as all other DPTX AUX clocks in this driver. Fixes: b4d15211c408 ("clk: qcom: dispcc-glymur: Add support for Display Clock Controller") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abel Vesa Reviewed-by: Konrad Dybcio Reviewed-by: Taniya Das Link: https://lore.kernel.org/r/20260112-dp-aux-clks-v1-1-456b0c11b069@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-glymur.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/dispcc-glymur.c b/drivers/clk/qcom/dispcc-glymur.c index 5203fa6383f6a..f352165bf56fc 100644 --- a/drivers/clk/qcom/dispcc-glymur.c +++ b/drivers/clk/qcom/dispcc-glymur.c @@ -417,7 +417,7 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_aux_clk_src = { .parent_data = disp_cc_parent_data_1, .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_dp_ops, + .ops = &clk_rcg2_shared_ops, }, }; From e906a312ee06ef301e3401d24db5ff82aa22ab3a Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 12 Jan 2026 04:12:23 +0200 Subject: [PATCH 0730/1518] clk: qcom: dispcc-sm8450: use RCG2 ops for DPTX1 AUX clock source [ Upstream commit 141af1be817c42c7f1e1605348d4b1983d319bea ] The clk_dp_ops are supposed to be used for DP-related clocks with a proper MND divier. Use standard RCG2 ops for dptx1_aux_clk_src, the same as all other DPTX AUX clocks in this driver. Fixes: 16fb89f92ec4 ("clk: qcom: Add support for Display Clock Controller on SM8450") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abel Vesa Reviewed-by: Konrad Dybcio Reviewed-by: Taniya Das Link: https://lore.kernel.org/r/20260112-dp-aux-clks-v1-2-456b0c11b069@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-sm8450.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/dispcc-sm8450.c b/drivers/clk/qcom/dispcc-sm8450.c index 9ce9fd28e55b2..2e91332dd92ab 100644 --- a/drivers/clk/qcom/dispcc-sm8450.c +++ b/drivers/clk/qcom/dispcc-sm8450.c @@ -409,7 +409,7 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_aux_clk_src = { .parent_data = disp_cc_parent_data_1, .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_dp_ops, + .ops = &clk_rcg2_ops, }, }; From b9ab6cf1c2ef598e1d74dc37e171cda92d3884fa Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 17 Feb 2026 17:30:03 +0800 Subject: [PATCH 0731/1518] clk: sunxi-ng: sun55i-a523-r: Add missing r-spi module clock [ Upstream commit fb20ccf70cf695f178d7c32e2d33b376560df0ff ] When the PRCM clk driver was added, somehow the r-spi module clock was skipped over. Add it so that r-spi can actually work. Fixes: 8cea339cfb81 ("clk: sunxi-ng: add support for the A523/T527 PRCM CCU") Reviewed-by: Andre Przywara Reviewed-by: Jernej Skrabec Link: https://patch.msgid.link/20260217093004.3239051-1-wens@kernel.org Signed-off-by: Chen-Yu Tsai Signed-off-by: Sasha Levin --- drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c b/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c index 0339c4af0fe5b..db0e36d8838e7 100644 --- a/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c +++ b/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c @@ -83,9 +83,22 @@ static SUNXI_CCU_MUX_DATA_WITH_GATE(r_pwmctrl_clk, "r-pwmctrl", static SUNXI_CCU_GATE_HW(bus_r_pwmctrl_clk, "bus-r-pwmctrl", &r_apb0_clk.common.hw, 0x13c, BIT(0), 0); -/* SPI clock is /M/N (same as new MMC?) */ +static const struct clk_parent_data r_spi_parents[] = { + { .fw_name = "hosc" }, + { .fw_name = "pll-periph" }, + { .name = "pll-periph0-300M" }, + { .name = "pll-periph1-300M" }, + { .name = "pll-audio" }, +}; +static SUNXI_CCU_DUALDIV_MUX_GATE(r_spi_clk, "r-spi", r_spi_parents, 0x150, + 0, 5, /* M */ + 8, 5, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 0); static SUNXI_CCU_GATE_HW(bus_r_spi_clk, "bus-r-spi", &r_ahb_clk.common.hw, 0x15c, BIT(0), 0); + static SUNXI_CCU_GATE_HW(bus_r_spinlock_clk, "bus-r-spinlock", &r_ahb_clk.common.hw, 0x16c, BIT(0), 0); static SUNXI_CCU_GATE_HW(bus_r_msgbox_clk, "bus-r-msgbox", @@ -138,6 +151,7 @@ static struct ccu_common *sun55i_a523_r_ccu_clks[] = { &bus_r_twd_clk.common, &r_pwmctrl_clk.common, &bus_r_pwmctrl_clk.common, + &r_spi_clk.common, &bus_r_spi_clk.common, &bus_r_spinlock_clk.common, &bus_r_msgbox_clk.common, @@ -169,6 +183,7 @@ static struct clk_hw_onecell_data sun55i_a523_r_hw_clks = { [CLK_BUS_R_TWD] = &bus_r_twd_clk.common.hw, [CLK_R_PWMCTRL] = &r_pwmctrl_clk.common.hw, [CLK_BUS_R_PWMCTRL] = &bus_r_pwmctrl_clk.common.hw, + [CLK_R_SPI] = &r_spi_clk.common.hw, [CLK_BUS_R_SPI] = &bus_r_spi_clk.common.hw, [CLK_BUS_R_SPINLOCK] = &bus_r_spinlock_clk.common.hw, [CLK_BUS_R_MSGBOX] = &bus_r_msgbox_clk.common.hw, From 6a4ccbb9b40e9cb3b185890bddc48753a4baeff6 Mon Sep 17 00:00:00 2001 From: Yang Erkun Date: Tue, 27 Jan 2026 14:20:42 +0800 Subject: [PATCH 0732/1518] scsi: sg: Fix sysctl sg-big-buff register during sg_init() [ Upstream commit 3033c471aaf675254efaa0da431e95d91a104b41 ] Commit 26d1c80fd61e ("scsi/sg: move sg-big-buff sysctl to scsi/sg.c") made a mistake. sysctl sg-big-buff was not created because the call to register_sg_sysctls() was placed on the wrong code path. Fixes: 26d1c80fd61e ("scsi/sg: move sg-big-buff sysctl to scsi/sg.c") Signed-off-by: Yang Erkun Reviewed-by: Bart Van Assche Link: https://patch.msgid.link/20260127062044.3034148-2-yangerkun@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/sg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 57fba34832ad1..c93cc9323f563 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1689,13 +1689,13 @@ init_sg(void) sg_sysfs_valid = 1; rc = scsi_register_interface(&sg_interface); if (0 == rc) { + register_sg_sysctls(); #ifdef CONFIG_SCSI_PROC_FS sg_proc_init(); #endif /* CONFIG_SCSI_PROC_FS */ return 0; } class_unregister(&sg_sysfs_class); - register_sg_sysctls(); err_out: unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS); return rc; From 1afd963fcd963db0dc5d47df6dfcf010c9c4647e Mon Sep 17 00:00:00 2001 From: Yang Erkun Date: Tue, 27 Jan 2026 14:20:43 +0800 Subject: [PATCH 0733/1518] scsi: sg: Resolve soft lockup issue when opening /dev/sgX [ Upstream commit d06a310b45e153872033dd0cf19d5a2279121099 ] The parameter def_reserved_size defines the default buffer size reserved for each Sg_fd and should be restricted to a range between 0 and 1,048,576 (see https://tldp.org/HOWTO/SCSI-Generic-HOWTO/proc.html). Although the function sg_proc_write_dressz enforces this limit, it is possible to bypass it by directly modifying the module parameter as shown below, which then causes a soft lockup: echo -1 > /sys/module/sg/parameters/def_reserved_size exec 4<> /dev/sg0 watchdog: BUG: soft lockup - CPU#5 stuck for 26 seconds! [bash:537] Modules loaded: CPU: 5 UID: 0 PID: 537 Command: bash, kernel version 6.19.0-rc3+ #134, PREEMPT disabled Hardware: QEMU Standard PC (i440FX + PIIX, 1996), BIOS version 1.16.1-2.fc37 dated 04/01/2014 ... Call Trace: sg_build_reserve+0x5c/0xa0 sg_add_sfp+0x168/0x270 sg_open+0x16e/0x340 chrdev_open+0xbe/0x230 do_dentry_open+0x175/0x480 vfs_open+0x34/0xf0 do_open+0x265/0x3d0 path_openat+0x110/0x290 do_filp_open+0xc3/0x170 do_sys_openat2+0x71/0xe0 __x64_sys_openat+0x6d/0xa0 do_syscall_64+0x62/0x310 entry_SYSCALL_64_after_hwframe+0x76/0x7e The fix is to use module_param_cb to validate and reject invalid values assigned to def_reserved_size. Fixes: 6460e75a104d ("[SCSI] sg: fixes for large page_size") Signed-off-by: Yang Erkun Reviewed-by: Bart Van Assche Link: https://patch.msgid.link/20260127062044.3034148-3-yangerkun@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/sg.c | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index c93cc9323f563..21c3962ee1cb5 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1621,10 +1621,35 @@ sg_remove_device(struct device *cl_dev) } module_param_named(scatter_elem_sz, scatter_elem_sz, int, S_IRUGO | S_IWUSR); -module_param_named(def_reserved_size, def_reserved_size, int, - S_IRUGO | S_IWUSR); module_param_named(allow_dio, sg_allow_dio, int, S_IRUGO | S_IWUSR); +static int def_reserved_size_set(const char *val, const struct kernel_param *kp) +{ + int size, ret; + + if (!val) + return -EINVAL; + + ret = kstrtoint(val, 0, &size); + if (ret) + return ret; + + /* limit to 1 MB */ + if (size < 0 || size > 1048576) + return -ERANGE; + + def_reserved_size = size; + return 0; +} + +static const struct kernel_param_ops def_reserved_size_ops = { + .set = def_reserved_size_set, + .get = param_get_int, +}; + +module_param_cb(def_reserved_size, &def_reserved_size_ops, &def_reserved_size, + S_IRUGO | S_IWUSR); + MODULE_AUTHOR("Douglas Gilbert"); MODULE_DESCRIPTION("SCSI generic (sg) driver"); MODULE_LICENSE("GPL"); From 6c87b3a371fae179cb9788f2c61075c12cdd4265 Mon Sep 17 00:00:00 2001 From: White Lewis Date: Tue, 3 Mar 2026 19:55:50 +0800 Subject: [PATCH 0734/1518] clk: qcom: dispcc-sc8280xp: remove CLK_SET_RATE_PARENT from byte_div_clk_src dividers [ Upstream commit 0b151a6307205eb867250985a910a88787cbf12e ] The four byte_div_clk_src dividers (disp{0,1}_cc_mdss_byte{0,1}_div_clk_src) had CLK_SET_RATE_PARENT set. When the DSI driver calls clk_set_rate() on byte_intf_clk, the rate-change propagates through the divider up to the parent PLL (byte_clk_src), halving the byte clock rate. A simiar issue had been also encountered on SM8750. b8501febdc51 ("clk: qcom: dispcc-sm8750: Drop incorrect CLK_SET_RATE_PARENT on byte intf parent"). Likewise, remove CLK_SET_RATE_PARENT from all four byte divider clocks so that clk_set_rate() on the divider adjusts only the divider ratio, leaving the parent PLL untouched. Fixes: 4a66e76fdb6d ("clk: qcom: Add SC8280XP display clock controller") Signed-off-by: White Lewis [pengyu: reword] Signed-off-by: Pengyu Luo Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20260303115550.9279-1-mitltlatltl@gmail.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-sc8280xp.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/clk/qcom/dispcc-sc8280xp.c b/drivers/clk/qcom/dispcc-sc8280xp.c index 5903a759d4af4..e91dfed0f37e9 100644 --- a/drivers/clk/qcom/dispcc-sc8280xp.c +++ b/drivers/clk/qcom/dispcc-sc8280xp.c @@ -1160,7 +1160,6 @@ static struct clk_regmap_div disp0_cc_mdss_byte0_div_clk_src = { &disp0_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; @@ -1175,7 +1174,6 @@ static struct clk_regmap_div disp1_cc_mdss_byte0_div_clk_src = { &disp1_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; @@ -1190,7 +1188,6 @@ static struct clk_regmap_div disp0_cc_mdss_byte1_div_clk_src = { &disp0_cc_mdss_byte1_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; @@ -1205,7 +1202,6 @@ static struct clk_regmap_div disp1_cc_mdss_byte1_div_clk_src = { &disp1_cc_mdss_byte1_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; From 0c7a14a3d5808e0fbaceec6095d6395cf6177c04 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 4 Mar 2026 14:48:27 +0100 Subject: [PATCH 0735/1518] clk: qcom: dispcc-glymur: Fix DSI byte clock rate setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 98ea9eda030587601db56425efcd32263d853591 ] The clock tree for byte_clk_src is as follows: ┌──────byte0_clk_src─────┐ │ │ byte0_clk byte0_div_clk_src │ byte0_intf_clk If both of its direct children have CLK_SET_RATE_PARENT with different requests, byte0_clk_src (and its parent) will be reconfigured. In this case, byte0_intf should strictly follow the rate of byte0_clk (with some adjustments based on PHY mode). Remove CLK_SET_RATE_PARENT from byte0_div_clk_src to avoid this issue. Fixes: b4d15211c408 ("clk: qcom: dispcc-glymur: Add support for Display Clock Controller") Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260304-topic-dsi_byte_fixup-v1-1-b79b29f83176@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-glymur.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/clk/qcom/dispcc-glymur.c b/drivers/clk/qcom/dispcc-glymur.c index f352165bf56fc..bef74f58405ba 100644 --- a/drivers/clk/qcom/dispcc-glymur.c +++ b/drivers/clk/qcom/dispcc-glymur.c @@ -747,7 +747,6 @@ static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = { &disp_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; @@ -762,7 +761,6 @@ static struct clk_regmap_div disp_cc_mdss_byte1_div_clk_src = { &disp_cc_mdss_byte1_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; From b0015d7752afd9444d9fe06ad7604769ad9e5eb6 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 4 Mar 2026 14:48:29 +0100 Subject: [PATCH 0736/1518] clk: qcom: dispcc-milos: Fix DSI byte clock rate setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dd5b76257b4048151006620c9895e2f5f0d997eb ] The clock tree for byte_clk_src is as follows: ┌──────byte0_clk_src─────┐ │ │ byte0_clk byte0_div_clk_src │ byte0_intf_clk If both of its direct children have CLK_SET_RATE_PARENT with different requests, byte0_clk_src (and its parent) will be reconfigured. In this case, byte0_intf should strictly follow the rate of byte0_clk (with some adjustments based on PHY mode). Remove CLK_SET_RATE_PARENT from byte0_div_clk_src to avoid this issue. Fixes: f40b5217dce1 ("clk: qcom: Add Display Clock controller (DISPCC) driver for Milos") Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260304-topic-dsi_byte_fixup-v1-3-b79b29f83176@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-milos.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clk/qcom/dispcc-milos.c b/drivers/clk/qcom/dispcc-milos.c index 95b6dd89d9ae3..339cb1c63ba77 100644 --- a/drivers/clk/qcom/dispcc-milos.c +++ b/drivers/clk/qcom/dispcc-milos.c @@ -394,7 +394,6 @@ static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = { &disp_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; From b92a29da9f7e114c05fd549cc388c0c26c338492 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 4 Mar 2026 14:48:30 +0100 Subject: [PATCH 0737/1518] clk: qcom: dispcc-sm4450: Fix DSI byte clock rate setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7bc48fcdf9e77bf68ef04af015d50df2a9acac00 ] The clock tree for byte_clk_src is as follows: ┌──────byte0_clk_src─────┐ │ │ byte0_clk byte0_div_clk_src │ byte0_intf_clk If both of its direct children have CLK_SET_RATE_PARENT with different requests, byte0_clk_src (and its parent) will be reconfigured. In this case, byte0_intf should strictly follow the rate of byte0_clk (with some adjustments based on PHY mode). Remove CLK_SET_RATE_PARENT from byte0_div_clk_src to avoid this issue. Fixes: 76f05f1ec766 ("clk: qcom: Add DISPCC driver support for SM4450") Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260304-topic-dsi_byte_fixup-v1-4-b79b29f83176@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-sm4450.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clk/qcom/dispcc-sm4450.c b/drivers/clk/qcom/dispcc-sm4450.c index e8752d01c8e62..2fdacc26df698 100644 --- a/drivers/clk/qcom/dispcc-sm4450.c +++ b/drivers/clk/qcom/dispcc-sm4450.c @@ -335,7 +335,6 @@ static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = { &disp_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; From 87534f2a3842749973ea43b21efc5346ce196b86 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 4 Mar 2026 14:48:31 +0100 Subject: [PATCH 0738/1518] clk: qcom: dispcc[01]-sa8775p: Fix DSI byte clock rate setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2851b6c6a42e22c243aa4cd606a49e2b9acfb6d6 ] The clock tree for byte_clk_src is as follows: ┌──────byte0_clk_src─────┐ │ │ byte0_clk byte0_div_clk_src │ byte0_intf_clk If both of its direct children have CLK_SET_RATE_PARENT with different requests, byte0_clk_src (and its parent) will be reconfigured. In this case, byte0_intf should strictly follow the rate of byte0_clk (with some adjustments based on PHY mode). Remove CLK_SET_RATE_PARENT from byte0_div_clk_src to avoid this issue. Fixes: e700bfd2f976 ("clk: qcom: Add support for Display clock Controllers on SA8775P") Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260304-topic-dsi_byte_fixup-v1-5-b79b29f83176@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc0-sa8775p.c | 2 -- drivers/clk/qcom/dispcc1-sa8775p.c | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/clk/qcom/dispcc0-sa8775p.c b/drivers/clk/qcom/dispcc0-sa8775p.c index aeda9cf4bfee8..b248fa9705873 100644 --- a/drivers/clk/qcom/dispcc0-sa8775p.c +++ b/drivers/clk/qcom/dispcc0-sa8775p.c @@ -591,7 +591,6 @@ static struct clk_regmap_div mdss_0_disp_cc_mdss_byte0_div_clk_src = { &mdss_0_disp_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; @@ -606,7 +605,6 @@ static struct clk_regmap_div mdss_0_disp_cc_mdss_byte1_div_clk_src = { &mdss_0_disp_cc_mdss_byte1_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; diff --git a/drivers/clk/qcom/dispcc1-sa8775p.c b/drivers/clk/qcom/dispcc1-sa8775p.c index cd55d1c119024..9882edbb79f9e 100644 --- a/drivers/clk/qcom/dispcc1-sa8775p.c +++ b/drivers/clk/qcom/dispcc1-sa8775p.c @@ -591,7 +591,6 @@ static struct clk_regmap_div mdss_1_disp_cc_mdss_byte0_div_clk_src = { &mdss_1_disp_cc_mdss_byte0_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; @@ -606,7 +605,6 @@ static struct clk_regmap_div mdss_1_disp_cc_mdss_byte1_div_clk_src = { &mdss_1_disp_cc_mdss_byte1_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_regmap_div_ops, }, }; From 34e869e21080f137678ef978c70efd2fd0ef1197 Mon Sep 17 00:00:00 2001 From: Ovidiu Panait Date: Tue, 21 Oct 2025 08:07:00 +0000 Subject: [PATCH 0739/1518] clk: renesas: r9a09g057: Add clock and reset entries for RTC [ Upstream commit 7a03ef9f8223434f19e19a37acc32dcb581ab475 ] Add module clock and reset entries for the RTC module on the Renesas RZ/V2H (R9A09G057) SoC. Signed-off-by: Ovidiu Panait Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20251021080705.18116-2-ovidiu.panait.rb@renesas.com Signed-off-by: Geert Uytterhoeven Stable-dep-of: 1b4f047dc401 ("clk: renesas: r9a09g057: Remove entries for WDT{0,2,3}") Signed-off-by: Sasha Levin --- drivers/clk/renesas/r9a09g057-cpg.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/clk/renesas/r9a09g057-cpg.c b/drivers/clk/renesas/r9a09g057-cpg.c index 6389c4b6a5231..4e47fea3f8946 100644 --- a/drivers/clk/renesas/r9a09g057-cpg.c +++ b/drivers/clk/renesas/r9a09g057-cpg.c @@ -239,6 +239,8 @@ static const struct rzv2h_mod_clk r9a09g057_mod_clks[] __initconst = { BUS_MSTOP(5, BIT(13))), DEF_MOD("wdt_3_clk_loco", CLK_QEXTAL, 5, 2, 2, 18, BUS_MSTOP(5, BIT(13))), + DEF_MOD("rtc_0_clk_rtc", CLK_PLLCM33_DIV16, 5, 3, 2, 19, + BUS_MSTOP(3, BIT(11) | BIT(12))), DEF_MOD("rspi_0_pclk", CLK_PLLCLN_DIV8, 5, 4, 2, 20, BUS_MSTOP(11, BIT(0))), DEF_MOD("rspi_0_pclk_sfr", CLK_PLLCLN_DIV8, 5, 5, 2, 21, @@ -401,6 +403,8 @@ static const struct rzv2h_reset r9a09g057_resets[] __initconst = { DEF_RST(7, 6, 3, 7), /* WDT_1_RESET */ DEF_RST(7, 7, 3, 8), /* WDT_2_RESET */ DEF_RST(7, 8, 3, 9), /* WDT_3_RESET */ + DEF_RST(7, 9, 3, 10), /* RTC_0_RST_RTC */ + DEF_RST(7, 10, 3, 11), /* RTC_0_RST_RTC_V */ DEF_RST(7, 11, 3, 12), /* RSPI_0_PRESETN */ DEF_RST(7, 12, 3, 13), /* RSPI_0_TRESETN */ DEF_RST(7, 13, 3, 14), /* RSPI_1_PRESETN */ From 21aae9f766a3e43263ae3c98639b37c167beccc2 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Wed, 3 Dec 2025 09:41:47 +0000 Subject: [PATCH 0740/1518] clk: renesas: r9a09g057: Add entries for RSCIs [ Upstream commit 2efea3b35cc916f04f06b89f2e2557dbd9c48109 ] Add clock and reset entries for the RSCI IPs. Signed-off-by: Lad Prabhakar Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20251203094147.6429-3-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Geert Uytterhoeven Stable-dep-of: 1b4f047dc401 ("clk: renesas: r9a09g057: Remove entries for WDT{0,2,3}") Signed-off-by: Sasha Levin --- drivers/clk/renesas/r9a09g057-cpg.c | 126 ++++++++++++++++++++++++++++ 1 file changed, 126 insertions(+) diff --git a/drivers/clk/renesas/r9a09g057-cpg.c b/drivers/clk/renesas/r9a09g057-cpg.c index 4e47fea3f8946..ac3d309365b45 100644 --- a/drivers/clk/renesas/r9a09g057-cpg.c +++ b/drivers/clk/renesas/r9a09g057-cpg.c @@ -44,6 +44,9 @@ enum clk_ids { CLK_PLLCLN_DIV2, CLK_PLLCLN_DIV8, CLK_PLLCLN_DIV16, + CLK_PLLCLN_DIV64, + CLK_PLLCLN_DIV256, + CLK_PLLCLN_DIV1024, CLK_PLLDTY_ACPU, CLK_PLLDTY_ACPU_DIV2, CLK_PLLDTY_ACPU_DIV4, @@ -144,6 +147,9 @@ static const struct cpg_core_clk r9a09g057_core_clks[] __initconst = { DEF_FIXED(".pllcln_div2", CLK_PLLCLN_DIV2, CLK_PLLCLN, 1, 2), DEF_FIXED(".pllcln_div8", CLK_PLLCLN_DIV8, CLK_PLLCLN, 1, 8), DEF_FIXED(".pllcln_div16", CLK_PLLCLN_DIV16, CLK_PLLCLN, 1, 16), + DEF_FIXED(".pllcln_div64", CLK_PLLCLN_DIV64, CLK_PLLCLN, 1, 64), + DEF_FIXED(".pllcln_div256", CLK_PLLCLN_DIV256, CLK_PLLCLN, 1, 256), + DEF_FIXED(".pllcln_div1024", CLK_PLLCLN_DIV1024, CLK_PLLCLN, 1, 1024), DEF_DDIV(".plldty_acpu", CLK_PLLDTY_ACPU, CLK_PLLDTY, CDDIV0_DIVCTL2, dtable_2_64), DEF_FIXED(".plldty_acpu_div2", CLK_PLLDTY_ACPU_DIV2, CLK_PLLDTY_ACPU, 1, 2), @@ -239,6 +245,106 @@ static const struct rzv2h_mod_clk r9a09g057_mod_clks[] __initconst = { BUS_MSTOP(5, BIT(13))), DEF_MOD("wdt_3_clk_loco", CLK_QEXTAL, 5, 2, 2, 18, BUS_MSTOP(5, BIT(13))), + DEF_MOD("rsci0_pclk", CLK_PLLCLN_DIV16, 5, 13, 2, 29, + BUS_MSTOP(11, BIT(3))), + DEF_MOD("rsci0_tclk", CLK_PLLCLN_DIV16, 5, 14, 2, 30, + BUS_MSTOP(11, BIT(3))), + DEF_MOD("rsci0_ps_ps3_n", CLK_PLLCLN_DIV1024, 5, 15, 2, 31, + BUS_MSTOP(11, BIT(3))), + DEF_MOD("rsci0_ps_ps2_n", CLK_PLLCLN_DIV256, 6, 0, 3, 0, + BUS_MSTOP(11, BIT(3))), + DEF_MOD("rsci0_ps_ps1_n", CLK_PLLCLN_DIV64, 6, 1, 3, 1, + BUS_MSTOP(11, BIT(3))), + DEF_MOD("rsci1_pclk", CLK_PLLCLN_DIV16, 6, 2, 3, 2, + BUS_MSTOP(11, BIT(4))), + DEF_MOD("rsci1_tclk", CLK_PLLCLN_DIV16, 6, 3, 3, 3, + BUS_MSTOP(11, BIT(4))), + DEF_MOD("rsci1_ps_ps3_n", CLK_PLLCLN_DIV1024, 6, 4, 3, 4, + BUS_MSTOP(11, BIT(4))), + DEF_MOD("rsci1_ps_ps2_n", CLK_PLLCLN_DIV256, 6, 5, 3, 5, + BUS_MSTOP(11, BIT(4))), + DEF_MOD("rsci1_ps_ps1_n", CLK_PLLCLN_DIV64, 6, 6, 3, 6, + BUS_MSTOP(11, BIT(4))), + DEF_MOD("rsci2_pclk", CLK_PLLCLN_DIV16, 6, 7, 3, 7, + BUS_MSTOP(11, BIT(5))), + DEF_MOD("rsci2_tclk", CLK_PLLCLN_DIV16, 6, 8, 3, 8, + BUS_MSTOP(11, BIT(5))), + DEF_MOD("rsci2_ps_ps3_n", CLK_PLLCLN_DIV1024, 6, 9, 3, 9, + BUS_MSTOP(11, BIT(5))), + DEF_MOD("rsci2_ps_ps2_n", CLK_PLLCLN_DIV256, 6, 10, 3, 10, + BUS_MSTOP(11, BIT(5))), + DEF_MOD("rsci2_ps_ps1_n", CLK_PLLCLN_DIV64, 6, 11, 3, 11, + BUS_MSTOP(11, BIT(5))), + DEF_MOD("rsci3_pclk", CLK_PLLCLN_DIV16, 6, 12, 3, 12, + BUS_MSTOP(11, BIT(6))), + DEF_MOD("rsci3_tclk", CLK_PLLCLN_DIV16, 6, 13, 3, 13, + BUS_MSTOP(11, BIT(6))), + DEF_MOD("rsci3_ps_ps3_n", CLK_PLLCLN_DIV1024, 6, 14, 3, 14, + BUS_MSTOP(11, BIT(6))), + DEF_MOD("rsci3_ps_ps2_n", CLK_PLLCLN_DIV256, 6, 15, 3, 15, + BUS_MSTOP(11, BIT(6))), + DEF_MOD("rsci3_ps_ps1_n", CLK_PLLCLN_DIV64, 7, 0, 3, 16, + BUS_MSTOP(11, BIT(6))), + DEF_MOD("rsci4_pclk", CLK_PLLCLN_DIV16, 7, 1, 3, 17, + BUS_MSTOP(11, BIT(7))), + DEF_MOD("rsci4_tclk", CLK_PLLCLN_DIV16, 7, 2, 3, 18, + BUS_MSTOP(11, BIT(7))), + DEF_MOD("rsci4_ps_ps3_n", CLK_PLLCLN_DIV1024, 7, 3, 3, 19, + BUS_MSTOP(11, BIT(7))), + DEF_MOD("rsci4_ps_ps2_n", CLK_PLLCLN_DIV256, 7, 4, 3, 20, + BUS_MSTOP(11, BIT(7))), + DEF_MOD("rsci4_ps_ps1_n", CLK_PLLCLN_DIV64, 7, 5, 3, 21, + BUS_MSTOP(11, BIT(7))), + DEF_MOD("rsci5_pclk", CLK_PLLCLN_DIV16, 7, 6, 3, 22, + BUS_MSTOP(11, BIT(8))), + DEF_MOD("rsci5_tclk", CLK_PLLCLN_DIV16, 7, 7, 3, 23, + BUS_MSTOP(11, BIT(8))), + DEF_MOD("rsci5_ps_ps3_n", CLK_PLLCLN_DIV1024, 7, 8, 3, 24, + BUS_MSTOP(11, BIT(8))), + DEF_MOD("rsci5_ps_ps2_n", CLK_PLLCLN_DIV256, 7, 9, 3, 25, + BUS_MSTOP(11, BIT(8))), + DEF_MOD("rsci5_ps_ps1_n", CLK_PLLCLN_DIV64, 7, 10, 3, 26, + BUS_MSTOP(11, BIT(8))), + DEF_MOD("rsci6_pclk", CLK_PLLCLN_DIV16, 7, 11, 3, 27, + BUS_MSTOP(11, BIT(9))), + DEF_MOD("rsci6_tclk", CLK_PLLCLN_DIV16, 7, 12, 3, 28, + BUS_MSTOP(11, BIT(9))), + DEF_MOD("rsci6_ps_ps3_n", CLK_PLLCLN_DIV1024, 7, 13, 3, 29, + BUS_MSTOP(11, BIT(9))), + DEF_MOD("rsci6_ps_ps2_n", CLK_PLLCLN_DIV256, 7, 14, 3, 30, + BUS_MSTOP(11, BIT(9))), + DEF_MOD("rsci6_ps_ps1_n", CLK_PLLCLN_DIV64, 7, 15, 3, 31, + BUS_MSTOP(11, BIT(9))), + DEF_MOD("rsci7_pclk", CLK_PLLCLN_DIV16, 8, 0, 4, 0, + BUS_MSTOP(11, BIT(10))), + DEF_MOD("rsci7_tclk", CLK_PLLCLN_DIV16, 8, 1, 4, 1, + BUS_MSTOP(11, BIT(10))), + DEF_MOD("rsci7_ps_ps3_n", CLK_PLLCLN_DIV1024, 8, 2, 4, 2, + BUS_MSTOP(11, BIT(10))), + DEF_MOD("rsci7_ps_ps2_n", CLK_PLLCLN_DIV256, 8, 3, 4, 3, + BUS_MSTOP(11, BIT(10))), + DEF_MOD("rsci7_ps_ps1_n", CLK_PLLCLN_DIV64, 8, 4, 4, 4, + BUS_MSTOP(11, BIT(10))), + DEF_MOD("rsci8_pclk", CLK_PLLCLN_DIV16, 8, 5, 4, 5, + BUS_MSTOP(11, BIT(11))), + DEF_MOD("rsci8_tclk", CLK_PLLCLN_DIV16, 8, 6, 4, 6, + BUS_MSTOP(11, BIT(11))), + DEF_MOD("rsci8_ps_ps3_n", CLK_PLLCLN_DIV1024, 8, 7, 4, 7, + BUS_MSTOP(11, BIT(11))), + DEF_MOD("rsci8_ps_ps2_n", CLK_PLLCLN_DIV256, 8, 8, 4, 8, + BUS_MSTOP(11, BIT(11))), + DEF_MOD("rsci8_ps_ps1_n", CLK_PLLCLN_DIV64, 8, 9, 4, 9, + BUS_MSTOP(11, BIT(11))), + DEF_MOD("rsci9_pclk", CLK_PLLCLN_DIV16, 8, 10, 4, 10, + BUS_MSTOP(11, BIT(12))), + DEF_MOD("rsci9_tclk", CLK_PLLCLN_DIV16, 8, 11, 4, 11, + BUS_MSTOP(11, BIT(12))), + DEF_MOD("rsci9_ps_ps3_n", CLK_PLLCLN_DIV1024, 8, 12, 4, 12, + BUS_MSTOP(11, BIT(12))), + DEF_MOD("rsci9_ps_ps2_n", CLK_PLLCLN_DIV256, 8, 13, 4, 13, + BUS_MSTOP(11, BIT(12))), + DEF_MOD("rsci9_ps_ps1_n", CLK_PLLCLN_DIV64, 8, 14, 4, 14, + BUS_MSTOP(11, BIT(12))), DEF_MOD("rtc_0_clk_rtc", CLK_PLLCM33_DIV16, 5, 3, 2, 19, BUS_MSTOP(3, BIT(11) | BIT(12))), DEF_MOD("rspi_0_pclk", CLK_PLLCLN_DIV8, 5, 4, 2, 20, @@ -403,6 +509,26 @@ static const struct rzv2h_reset r9a09g057_resets[] __initconst = { DEF_RST(7, 6, 3, 7), /* WDT_1_RESET */ DEF_RST(7, 7, 3, 8), /* WDT_2_RESET */ DEF_RST(7, 8, 3, 9), /* WDT_3_RESET */ + DEF_RST(8, 1, 3, 18), /* RSCI0_PRESETN */ + DEF_RST(8, 2, 3, 19), /* RSCI0_TRESETN */ + DEF_RST(8, 3, 3, 20), /* RSCI1_PRESETN */ + DEF_RST(8, 4, 3, 21), /* RSCI1_TRESETN */ + DEF_RST(8, 5, 3, 22), /* RSCI2_PRESETN */ + DEF_RST(8, 6, 3, 23), /* RSCI2_TRESETN */ + DEF_RST(8, 7, 3, 24), /* RSCI3_PRESETN */ + DEF_RST(8, 8, 3, 25), /* RSCI3_TRESETN */ + DEF_RST(8, 9, 3, 26), /* RSCI4_PRESETN */ + DEF_RST(8, 10, 3, 27), /* RSCI4_TRESETN */ + DEF_RST(8, 11, 3, 28), /* RSCI5_PRESETN */ + DEF_RST(8, 12, 3, 29), /* RSCI5_TRESETN */ + DEF_RST(8, 13, 3, 30), /* RSCI6_PRESETN */ + DEF_RST(8, 14, 3, 31), /* RSCI6_TRESETN */ + DEF_RST(8, 15, 4, 0), /* RSCI7_PRESETN */ + DEF_RST(9, 0, 4, 1), /* RSCI7_TRESETN */ + DEF_RST(9, 1, 4, 2), /* RSCI8_PRESETN */ + DEF_RST(9, 2, 4, 3), /* RSCI8_TRESETN */ + DEF_RST(9, 3, 4, 4), /* RSCI9_PRESETN */ + DEF_RST(9, 4, 4, 5), /* RSCI9_TRESETN */ DEF_RST(7, 9, 3, 10), /* RTC_0_RST_RTC */ DEF_RST(7, 10, 3, 11), /* RTC_0_RST_RTC_V */ DEF_RST(7, 11, 3, 12), /* RSPI_0_PRESETN */ From 3c0a96358c1324b23b608efe4b04daecb6ea3e02 Mon Sep 17 00:00:00 2001 From: Ovidiu Panait Date: Sun, 25 Jan 2026 19:03:14 +0000 Subject: [PATCH 0741/1518] clk: renesas: r9a09g057: Fix ordering of module clocks array [ Upstream commit 79cac2b8dc1d9f63fbf6c6793e423052118cc51a ] The r9a09g057_mod_clks array is sorted by CPG_CLKON register number and bit position. Move the RTC and RSPI module clock entries to their correct position to restore the array sort order. Fixes: 2efea3b35cc9 ("clk: renesas: r9a09g057: Add entries for RSCIs") Signed-off-by: Ovidiu Panait Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260125190314.26729-1-ovidiu.panait.rb@renesas.com Signed-off-by: Geert Uytterhoeven Stable-dep-of: 1b4f047dc401 ("clk: renesas: r9a09g057: Remove entries for WDT{0,2,3}") Signed-off-by: Sasha Levin --- drivers/clk/renesas/r9a09g057-cpg.c | 40 ++++++++++++++--------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/clk/renesas/r9a09g057-cpg.c b/drivers/clk/renesas/r9a09g057-cpg.c index ac3d309365b45..647e394727f6b 100644 --- a/drivers/clk/renesas/r9a09g057-cpg.c +++ b/drivers/clk/renesas/r9a09g057-cpg.c @@ -245,6 +245,26 @@ static const struct rzv2h_mod_clk r9a09g057_mod_clks[] __initconst = { BUS_MSTOP(5, BIT(13))), DEF_MOD("wdt_3_clk_loco", CLK_QEXTAL, 5, 2, 2, 18, BUS_MSTOP(5, BIT(13))), + DEF_MOD("rtc_0_clk_rtc", CLK_PLLCM33_DIV16, 5, 3, 2, 19, + BUS_MSTOP(3, BIT(11) | BIT(12))), + DEF_MOD("rspi_0_pclk", CLK_PLLCLN_DIV8, 5, 4, 2, 20, + BUS_MSTOP(11, BIT(0))), + DEF_MOD("rspi_0_pclk_sfr", CLK_PLLCLN_DIV8, 5, 5, 2, 21, + BUS_MSTOP(11, BIT(0))), + DEF_MOD("rspi_0_tclk", CLK_PLLCLN_DIV8, 5, 6, 2, 22, + BUS_MSTOP(11, BIT(0))), + DEF_MOD("rspi_1_pclk", CLK_PLLCLN_DIV8, 5, 7, 2, 23, + BUS_MSTOP(11, BIT(1))), + DEF_MOD("rspi_1_pclk_sfr", CLK_PLLCLN_DIV8, 5, 8, 2, 24, + BUS_MSTOP(11, BIT(1))), + DEF_MOD("rspi_1_tclk", CLK_PLLCLN_DIV8, 5, 9, 2, 25, + BUS_MSTOP(11, BIT(1))), + DEF_MOD("rspi_2_pclk", CLK_PLLCLN_DIV8, 5, 10, 2, 26, + BUS_MSTOP(11, BIT(2))), + DEF_MOD("rspi_2_pclk_sfr", CLK_PLLCLN_DIV8, 5, 11, 2, 27, + BUS_MSTOP(11, BIT(2))), + DEF_MOD("rspi_2_tclk", CLK_PLLCLN_DIV8, 5, 12, 2, 28, + BUS_MSTOP(11, BIT(2))), DEF_MOD("rsci0_pclk", CLK_PLLCLN_DIV16, 5, 13, 2, 29, BUS_MSTOP(11, BIT(3))), DEF_MOD("rsci0_tclk", CLK_PLLCLN_DIV16, 5, 14, 2, 30, @@ -345,26 +365,6 @@ static const struct rzv2h_mod_clk r9a09g057_mod_clks[] __initconst = { BUS_MSTOP(11, BIT(12))), DEF_MOD("rsci9_ps_ps1_n", CLK_PLLCLN_DIV64, 8, 14, 4, 14, BUS_MSTOP(11, BIT(12))), - DEF_MOD("rtc_0_clk_rtc", CLK_PLLCM33_DIV16, 5, 3, 2, 19, - BUS_MSTOP(3, BIT(11) | BIT(12))), - DEF_MOD("rspi_0_pclk", CLK_PLLCLN_DIV8, 5, 4, 2, 20, - BUS_MSTOP(11, BIT(0))), - DEF_MOD("rspi_0_pclk_sfr", CLK_PLLCLN_DIV8, 5, 5, 2, 21, - BUS_MSTOP(11, BIT(0))), - DEF_MOD("rspi_0_tclk", CLK_PLLCLN_DIV8, 5, 6, 2, 22, - BUS_MSTOP(11, BIT(0))), - DEF_MOD("rspi_1_pclk", CLK_PLLCLN_DIV8, 5, 7, 2, 23, - BUS_MSTOP(11, BIT(1))), - DEF_MOD("rspi_1_pclk_sfr", CLK_PLLCLN_DIV8, 5, 8, 2, 24, - BUS_MSTOP(11, BIT(1))), - DEF_MOD("rspi_1_tclk", CLK_PLLCLN_DIV8, 5, 9, 2, 25, - BUS_MSTOP(11, BIT(1))), - DEF_MOD("rspi_2_pclk", CLK_PLLCLN_DIV8, 5, 10, 2, 26, - BUS_MSTOP(11, BIT(2))), - DEF_MOD("rspi_2_pclk_sfr", CLK_PLLCLN_DIV8, 5, 11, 2, 27, - BUS_MSTOP(11, BIT(2))), - DEF_MOD("rspi_2_tclk", CLK_PLLCLN_DIV8, 5, 12, 2, 28, - BUS_MSTOP(11, BIT(2))), DEF_MOD("scif_0_clk_pck", CLK_PLLCM33_DIV16, 8, 15, 4, 15, BUS_MSTOP(3, BIT(14))), DEF_MOD("i3c_0_pclkrw", CLK_PLLCLN_DIV16, 9, 0, 4, 16, From ac0411865e3e7a4d0446595df1d753c5040f0cf6 Mon Sep 17 00:00:00 2001 From: Fabrizio Castro Date: Tue, 3 Feb 2026 12:42:47 +0000 Subject: [PATCH 0742/1518] clk: renesas: r9a09g057: Remove entries for WDT{0,2,3} [ Upstream commit 1b4f047dc4010d51821694cc4ed73b52b3040a5c ] The HW user manual for the Renesas RZ/V2H(P) SoC specifies that only the WDT1 IP is supposed to be used by Linux, while the WDT{0,2,3} IPs are supposed to be used by the CM33 and CR8 cores. Remove the clock and reset entries for WDT{0,2,3} to prevent interfering with the CM33 and CR8 cores. This change is harmless as only WDT1 is used by Linux, there are no users for the WDT{0,2,3} cores. Fixes: 3aeccbe08171 ("clk: renesas: r9a09g057: Add clock and reset entries for GTM/RIIC/SDHI/WDT") Signed-off-by: Fabrizio Castro Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260203124247.7320-4-fabrizio.castro.jz@renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/clk/renesas/r9a09g057-cpg.c | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/drivers/clk/renesas/r9a09g057-cpg.c b/drivers/clk/renesas/r9a09g057-cpg.c index 647e394727f6b..5d799dd9fbfc1 100644 --- a/drivers/clk/renesas/r9a09g057-cpg.c +++ b/drivers/clk/renesas/r9a09g057-cpg.c @@ -229,22 +229,10 @@ static const struct rzv2h_mod_clk r9a09g057_mod_clks[] __initconst = { BUS_MSTOP(11, BIT(15))), DEF_MOD("gtm_7_pclk", CLK_PLLCLN_DIV16, 4, 10, 2, 10, BUS_MSTOP(12, BIT(0))), - DEF_MOD("wdt_0_clkp", CLK_PLLCM33_DIV16, 4, 11, 2, 11, - BUS_MSTOP(3, BIT(10))), - DEF_MOD("wdt_0_clk_loco", CLK_QEXTAL, 4, 12, 2, 12, - BUS_MSTOP(3, BIT(10))), DEF_MOD("wdt_1_clkp", CLK_PLLCLN_DIV16, 4, 13, 2, 13, BUS_MSTOP(1, BIT(0))), DEF_MOD("wdt_1_clk_loco", CLK_QEXTAL, 4, 14, 2, 14, BUS_MSTOP(1, BIT(0))), - DEF_MOD("wdt_2_clkp", CLK_PLLCLN_DIV16, 4, 15, 2, 15, - BUS_MSTOP(5, BIT(12))), - DEF_MOD("wdt_2_clk_loco", CLK_QEXTAL, 5, 0, 2, 16, - BUS_MSTOP(5, BIT(12))), - DEF_MOD("wdt_3_clkp", CLK_PLLCLN_DIV16, 5, 1, 2, 17, - BUS_MSTOP(5, BIT(13))), - DEF_MOD("wdt_3_clk_loco", CLK_QEXTAL, 5, 2, 2, 18, - BUS_MSTOP(5, BIT(13))), DEF_MOD("rtc_0_clk_rtc", CLK_PLLCM33_DIV16, 5, 3, 2, 19, BUS_MSTOP(3, BIT(11) | BIT(12))), DEF_MOD("rspi_0_pclk", CLK_PLLCLN_DIV8, 5, 4, 2, 20, @@ -505,10 +493,7 @@ static const struct rzv2h_reset r9a09g057_resets[] __initconst = { DEF_RST(7, 2, 3, 3), /* GTM_5_PRESETZ */ DEF_RST(7, 3, 3, 4), /* GTM_6_PRESETZ */ DEF_RST(7, 4, 3, 5), /* GTM_7_PRESETZ */ - DEF_RST(7, 5, 3, 6), /* WDT_0_RESET */ DEF_RST(7, 6, 3, 7), /* WDT_1_RESET */ - DEF_RST(7, 7, 3, 8), /* WDT_2_RESET */ - DEF_RST(7, 8, 3, 9), /* WDT_3_RESET */ DEF_RST(8, 1, 3, 18), /* RSCI0_PRESETN */ DEF_RST(8, 2, 3, 19), /* RSCI0_TRESETN */ DEF_RST(8, 3, 3, 20), /* RSCI1_PRESETN */ From 51075df70c46e60a9773f2dcd28299e40dac36fb Mon Sep 17 00:00:00 2001 From: Junrui Luo Date: Wed, 4 Mar 2026 23:42:58 +0800 Subject: [PATCH 0743/1518] scsi: target: core: Fix integer overflow in UNMAP bounds check [ Upstream commit 2bf2d65f76697820dbc4227d13866293576dd90a ] sbc_execute_unmap() checks LBA + range does not exceed the device capacity, but does not guard against LBA + range wrapping around on 64-bit overflow. Add an overflow check matching the pattern already used for WRITE_SAME in the same file. Fixes: 86d7182985d2 ("target: Add sbc_execute_unmap() helper") Reported-by: Yuhao Jiang Signed-off-by: Junrui Luo Link: https://patch.msgid.link/SYBPR01MB7881593C61AD52C69FBDB0BDAF7CA@SYBPR01MB7881.ausprd01.prod.outlook.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/target_core_sbc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index fe8beb7dbab12..4c828a3ac18c7 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -1136,7 +1136,8 @@ sbc_execute_unmap(struct se_cmd *cmd) goto err; } - if (lba + range > dev->transport->get_blocks(dev) + 1) { + if (lba + range < lba || + lba + range > dev->transport->get_blocks(dev) + 1) { ret = TCM_ADDRESS_OUT_OF_RANGE; goto err; } From a2fb7c42ab9b2fec12f39864b8aa0d81efbaa2d1 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Fri, 13 Mar 2026 10:21:07 +0800 Subject: [PATCH 0744/1518] scsi: ufs: rockchip,rk3576-ufshc: dt-bindings: Add new mphy reset item [ Upstream commit bdce3a69c578090dd5e3c77bcdaaca10c3a41e34 ] Add the mphy reset property to the devicetree bindings for the Rockchip RK3576 UFS host controller. The mphy reset signal is used to reset the physical adapter. Resetting other components while leaving the mphy unreset may occasionally prevent the UFS controller from successfully linking up with the device. This addresses an intermittent hardware bug where the UFS link fails to establish under specific timing conditions with certain chips. While difficult to reproduce initially, this issue was consistently observed in downstream testing and requires explicit mphy reset control for full stability. Although this change increases the maxItems for resets and adds a new entry (which technically alters the binding ABI), it does not break compatibility for existing Linux systems. The driver uses devm_reset_control_array_get_exclusive() to manage resets, allowing it to function correctly with both older Device Trees (without the mphy entry) and newer ones. Fixes: d90e92023771 ("scsi: ufs: dt-bindings: Document Rockchip UFS host controller") Signed-off-by: Shawn Lin Reviewed-by: Krzysztof Kozlowski Link: https://patch.msgid.link/1773368467-109650-1-git-send-email-shawn.lin@rock-chips.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- .../devicetree/bindings/ufs/rockchip,rk3576-ufshc.yaml | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/ufs/rockchip,rk3576-ufshc.yaml b/Documentation/devicetree/bindings/ufs/rockchip,rk3576-ufshc.yaml index c7d17cf4dc42b..e738153a309c8 100644 --- a/Documentation/devicetree/bindings/ufs/rockchip,rk3576-ufshc.yaml +++ b/Documentation/devicetree/bindings/ufs/rockchip,rk3576-ufshc.yaml @@ -41,7 +41,7 @@ properties: maxItems: 1 resets: - maxItems: 4 + maxItems: 5 reset-names: items: @@ -49,6 +49,7 @@ properties: - const: sys - const: ufs - const: grf + - const: mphy reset-gpios: maxItems: 1 @@ -98,8 +99,8 @@ examples: interrupts = ; power-domains = <&power RK3576_PD_USB>; resets = <&cru SRST_A_UFS_BIU>, <&cru SRST_A_UFS_SYS>, <&cru SRST_A_UFS>, - <&cru SRST_P_UFS_GRF>; - reset-names = "biu", "sys", "ufs", "grf"; + <&cru SRST_P_UFS_GRF>, <&cru SRST_MPHY_INIT>; + reset-names = "biu", "sys", "ufs", "grf", "mphy"; reset-gpios = <&gpio4 RK_PD0 GPIO_ACTIVE_LOW>; }; }; From 841d495177685c779a5b4c943ba95a4e08573427 Mon Sep 17 00:00:00 2001 From: Val Packett Date: Thu, 12 Mar 2026 08:12:06 -0300 Subject: [PATCH 0745/1518] dt-bindings: clock: qcom,gcc-sc8180x: Add missing GDSCs [ Upstream commit 76404ffbf07f28a5ec04748e18fce3dac2e78ef6 ] There are 5 more GDSCs that we were ignoring and not putting to sleep, which are listed in downstream DTS. Add them. Signed-off-by: Val Packett Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20260312112321.370983-2-val@packett.cool Signed-off-by: Bjorn Andersson Stable-dep-of: 3565741eb985 ("clk: qcom: gcc-sc8180x: Add missing GDSCs") Signed-off-by: Sasha Levin --- include/dt-bindings/clock/qcom,gcc-sc8180x.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/dt-bindings/clock/qcom,gcc-sc8180x.h b/include/dt-bindings/clock/qcom,gcc-sc8180x.h index b9d8438a15ffb..9ed7b794aacc4 100644 --- a/include/dt-bindings/clock/qcom,gcc-sc8180x.h +++ b/include/dt-bindings/clock/qcom,gcc-sc8180x.h @@ -322,5 +322,10 @@ #define USB30_MP_GDSC 8 #define USB30_PRIM_GDSC 9 #define USB30_SEC_GDSC 10 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC 11 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC 12 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF_GDSC 13 +#define HLOS1_VOTE_TURING_MMU_TBU0_GDSC 14 +#define HLOS1_VOTE_TURING_MMU_TBU1_GDSC 15 #endif From ed9ca2c4dc02934de42be1a240dcdc480994fb51 Mon Sep 17 00:00:00 2001 From: Val Packett Date: Thu, 12 Mar 2026 08:12:07 -0300 Subject: [PATCH 0746/1518] clk: qcom: gcc-sc8180x: Add missing GDSCs [ Upstream commit 3565741eb985a8a7cc6656eb33496195468cb99e ] There are 5 more GDSCs that we were ignoring and not putting to sleep, which are listed in downstream DTS. Add them. Fixes: 4433594bbe5d ("clk: qcom: gcc: Add global clock controller driver for SC8180x") Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Signed-off-by: Val Packett Link: https://lore.kernel.org/r/20260312112321.370983-3-val@packett.cool Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc8180x.c | 50 ++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/drivers/clk/qcom/gcc-sc8180x.c b/drivers/clk/qcom/gcc-sc8180x.c index 31e788e22ab4a..55dabf6259b29 100644 --- a/drivers/clk/qcom/gcc-sc8180x.c +++ b/drivers/clk/qcom/gcc-sc8180x.c @@ -4266,6 +4266,51 @@ static struct gdsc usb30_mp_gdsc = { .flags = POLL_CFG_GDSCR, }; +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { + .gdscr = 0x7d050, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = { + .gdscr = 0x7d058, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = { + .gdscr = 0x7d054, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_turing_mmu_tbu0_gdsc = { + .gdscr = 0x7d05c, + .pd = { + .name = "hlos1_vote_turing_mmu_tbu0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_turing_mmu_tbu1_gdsc = { + .gdscr = 0x7d060, + .pd = { + .name = "hlos1_vote_turing_mmu_tbu1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + static struct clk_regmap *gcc_sc8180x_clocks[] = { [GCC_AGGRE_NOC_PCIE_TBU_CLK] = &gcc_aggre_noc_pcie_tbu_clk.clkr, [GCC_AGGRE_UFS_CARD_AXI_CLK] = &gcc_aggre_ufs_card_axi_clk.clkr, @@ -4595,6 +4640,11 @@ static struct gdsc *gcc_sc8180x_gdscs[] = { [USB30_MP_GDSC] = &usb30_mp_gdsc, [USB30_PRIM_GDSC] = &usb30_prim_gdsc, [USB30_SEC_GDSC] = &usb30_sec_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf_gdsc, + [HLOS1_VOTE_TURING_MMU_TBU0_GDSC] = &hlos1_vote_turing_mmu_tbu0_gdsc, + [HLOS1_VOTE_TURING_MMU_TBU1_GDSC] = &hlos1_vote_turing_mmu_tbu1_gdsc, }; static const struct regmap_config gcc_sc8180x_regmap_config = { From a263813276f9a4bbe49c0ce4e2eb58d50b573336 Mon Sep 17 00:00:00 2001 From: Val Packett Date: Thu, 12 Mar 2026 08:12:08 -0300 Subject: [PATCH 0747/1518] clk: qcom: gcc-sc8180x: Use retention for USB power domains [ Upstream commit 25bc96f26cd6c19dde13a0b9859183e531d6fbfc ] The USB subsystem does not expect to lose its state on suspend: xhci-hcd xhci-hcd.0.auto: xHC error in resume, USBSTS 0x401, Reinit usb usb1: root hub lost power or was reset (The reinitialization usually succeeds, but it does slow down resume.) To maintain state during suspend, the relevant GDSCs need to stay in retention mode, like they do on other similar SoCs. Change the mode to PWRSTS_RET_ON to fix. Fixes: 4433594bbe5d ("clk: qcom: gcc: Add global clock controller driver for SC8180x") Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Signed-off-by: Val Packett Link: https://lore.kernel.org/r/20260312112321.370983-4-val@packett.cool Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc8180x.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/qcom/gcc-sc8180x.c b/drivers/clk/qcom/gcc-sc8180x.c index 55dabf6259b29..b116a9c0b2d94 100644 --- a/drivers/clk/qcom/gcc-sc8180x.c +++ b/drivers/clk/qcom/gcc-sc8180x.c @@ -4172,7 +4172,7 @@ static struct gdsc usb30_sec_gdsc = { .pd = { .name = "usb30_sec_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; @@ -4190,7 +4190,7 @@ static struct gdsc usb30_prim_gdsc = { .pd = { .name = "usb30_prim_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; @@ -4262,7 +4262,7 @@ static struct gdsc usb30_mp_gdsc = { .pd = { .name = "usb30_mp_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; From d79e6ca14c559e0e0add8431a57c82e321a8ce9b Mon Sep 17 00:00:00 2001 From: Val Packett Date: Thu, 12 Mar 2026 08:12:09 -0300 Subject: [PATCH 0748/1518] clk: qcom: gcc-sc8180x: Use retention for PCIe power domains [ Upstream commit ccb92c78b42edd26225b4d5920847dfee3e1b093 ] As the PCIe host controller driver does not yet support dealing with the loss of state during suspend, use retention for relevant GDSCs. This fixes the link not surviving upon resume: nvme 0002:01:00.0: Unable to change power state from D3cold to D0, device inaccessible nvme nvme0: controller is down; will reset: CSTS=0xffffffff, PCI_STATUS read failed (134) nvme 0002:01:00.0: Unable to change power state from D3cold to D0, device inaccessible nvme nvme0: Disabling device after reset failure: -19 Fixes: 4433594bbe5d ("clk: qcom: gcc: Add global clock controller driver for SC8180x") Reviewed-by: Dmitry Baryshkov Signed-off-by: Val Packett Reviewed-by: Konrad Dybcio Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20260312112321.370983-5-val@packett.cool Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc8180x.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/qcom/gcc-sc8180x.c b/drivers/clk/qcom/gcc-sc8180x.c index b116a9c0b2d94..4095a1f54a099 100644 --- a/drivers/clk/qcom/gcc-sc8180x.c +++ b/drivers/clk/qcom/gcc-sc8180x.c @@ -4199,7 +4199,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; @@ -4226,7 +4226,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; @@ -4235,7 +4235,7 @@ static struct gdsc pcie_2_gdsc = { .pd = { .name = "pcie_2_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; @@ -4253,7 +4253,7 @@ static struct gdsc pcie_3_gdsc = { .pd = { .name = "pcie_3_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, .flags = POLL_CFG_GDSCR, }; From d7f633fc6e4d2d4a96017c64e17f962e469b28c0 Mon Sep 17 00:00:00 2001 From: Val Packett Date: Thu, 12 Mar 2026 08:12:12 -0300 Subject: [PATCH 0749/1518] clk: qcom: dispcc-sm8250: Use shared ops on the mdss vsync clk [ Upstream commit 8c522da70f0c2e5148c4c13ccb1c64cca57a6fdb ] mdss_gdsc can get stuck on boot due to RCGs being left on from last boot. As a fix, commit 01a0a6cc8cfd ("clk: qcom: Park shared RCGs upon registration") introduced a callback to ensure the RCG is off upon init. However, the fix depends on all shared RCGs being marked as such in code. For SM8150/SC8180X/SM8250 the MDSS vsync clock was using regular ops, unlike the same clock in the SC7180 code. This was causing display to frequently fail to initialize after rebooting on the Surface Pro X. Fix by using shared ops for this clock. Fixes: 80a18f4a8567 ("clk: qcom: Add display clock controller driver for SM8150 and SM8250") Signed-off-by: Val Packett Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260312112321.370983-8-val@packett.cool Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-sm8250.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c index 8f433e1e70283..cdfdb2cfb02b2 100644 --- a/drivers/clk/qcom/dispcc-sm8250.c +++ b/drivers/clk/qcom/dispcc-sm8250.c @@ -632,7 +632,7 @@ static struct clk_rcg2 disp_cc_mdss_vsync_clk_src = { .parent_data = disp_cc_parent_data_1, .num_parents = ARRAY_SIZE(disp_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; From 8ae85245632c26da86a2936afd352364d96e7332 Mon Sep 17 00:00:00 2001 From: Val Packett Date: Thu, 12 Mar 2026 08:12:13 -0300 Subject: [PATCH 0750/1518] clk: qcom: dispcc-sm8250: Enable parents for pixel clocks [ Upstream commit acf7a91d0b0e9e3ef374944021de62062125b7e4 ] Add CLK_OPS_PARENT_ENABLE to MDSS pixel clock sources to ensure parent clocks are enabled during clock operations, preventing potential stability issues during display configuration. Fixes: 80a18f4a8567 ("clk: qcom: Add display clock controller driver for SM8150 and SM8250") Signed-off-by: Val Packett Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20260312112321.370983-9-val@packett.cool Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-sm8250.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c index cdfdb2cfb02b2..e59cdadd56479 100644 --- a/drivers/clk/qcom/dispcc-sm8250.c +++ b/drivers/clk/qcom/dispcc-sm8250.c @@ -578,7 +578,7 @@ static struct clk_rcg2 disp_cc_mdss_pclk0_clk_src = { .name = "disp_cc_mdss_pclk0_clk_src", .parent_data = disp_cc_parent_data_6, .num_parents = ARRAY_SIZE(disp_cc_parent_data_6), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, .ops = &clk_pixel_ops, }, }; @@ -592,7 +592,7 @@ static struct clk_rcg2 disp_cc_mdss_pclk1_clk_src = { .name = "disp_cc_mdss_pclk1_clk_src", .parent_data = disp_cc_parent_data_6, .num_parents = ARRAY_SIZE(disp_cc_parent_data_6), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, .ops = &clk_pixel_ops, }, }; From 3cb3f533424b2f07eddd7c33773782c655bdd1b7 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Tue, 3 Feb 2026 22:07:57 +0800 Subject: [PATCH 0751/1518] clk: imx: imx6q: Fix device node reference leak in pll6_bypassed() [ Upstream commit 4b84d496c804b470124cd3a08e928df6801d8eae ] The function pll6_bypassed() calls of_parse_phandle_with_args() but never calls of_node_put() to release the reference, causing a memory leak. Fix this by adding proper cleanup calls on all exit paths. Fixes: 3cc48976e9763 ("clk: imx6q: handle ENET PLL bypass") Signed-off-by: Felix Gu Reviewed-by: Frank Li Reviewed-by: Peng Fan Link: https://patch.msgid.link/20260203-clk-imx6q-v3-1-6cd2696bb371@gmail.com Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx6q.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c index bf4c1d9c99287..ba696cf34fe3b 100644 --- a/drivers/clk/imx/clk-imx6q.c +++ b/drivers/clk/imx/clk-imx6q.c @@ -238,8 +238,11 @@ static bool pll6_bypassed(struct device_node *node) return false; if (clkspec.np == node && - clkspec.args[0] == IMX6QDL_PLL6_BYPASS) + clkspec.args[0] == IMX6QDL_PLL6_BYPASS) { + of_node_put(clkspec.np); break; + } + of_node_put(clkspec.np); } /* PLL6 bypass is not part of the assigned clock list */ @@ -249,6 +252,9 @@ static bool pll6_bypassed(struct device_node *node) ret = of_parse_phandle_with_args(node, "assigned-clock-parents", "#clock-cells", index, &clkspec); + if (!ret) + of_node_put(clkspec.np); + if (clkspec.args[0] != IMX6QDL_CLK_PLL6) return true; From e3d41039263dde6bcc933cebff98e2c94d66e30f Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Tue, 3 Feb 2026 22:07:58 +0800 Subject: [PATCH 0752/1518] clk: imx: imx6q: Fix device node reference leak in of_assigned_ldb_sels() [ Upstream commit 9faf207208951460f3f7eefbc112246c8d28ff1b ] The function of_assigned_ldb_sels() calls of_parse_phandle_with_args() but never calls of_node_put() to release the reference, causing a memory leak. Fix this by adding proper cleanup calls on all exit paths. Fixes: 5d283b083800 ("clk: imx6: Fix procedure to switch the parent of LDB_DI_CLK") Signed-off-by: Felix Gu Reviewed-by: Frank Li Reviewed-by: Peng Fan Link: https://patch.msgid.link/20260203-clk-imx6q-v3-2-6cd2696bb371@gmail.com Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx6q.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c index ba696cf34fe3b..048e2ddba490b 100644 --- a/drivers/clk/imx/clk-imx6q.c +++ b/drivers/clk/imx/clk-imx6q.c @@ -188,9 +188,11 @@ static void of_assigned_ldb_sels(struct device_node *node, } if (clkspec.np != node || clkspec.args[0] >= IMX6QDL_CLK_END) { pr_err("ccm: parent clock %d not in ccm\n", index); + of_node_put(clkspec.np); return; } parent = clkspec.args[0]; + of_node_put(clkspec.np); rc = of_parse_phandle_with_args(node, "assigned-clocks", "#clock-cells", index, &clkspec); @@ -198,9 +200,11 @@ static void of_assigned_ldb_sels(struct device_node *node, return; if (clkspec.np != node || clkspec.args[0] >= IMX6QDL_CLK_END) { pr_err("ccm: child clock %d not in ccm\n", index); + of_node_put(clkspec.np); return; } child = clkspec.args[0]; + of_node_put(clkspec.np); if (child != IMX6QDL_CLK_LDB_DI0_SEL && child != IMX6QDL_CLK_LDB_DI1_SEL) From b55d2128faf54d10a9d116025cb788a09f22b0aa Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Wed, 28 Jan 2026 00:47:21 +0100 Subject: [PATCH 0753/1518] clk: imx8mq: Correct the CSI PHY sels [ Upstream commit d16f57caa78776e6e8a88b96cb2597797b376138 ] According to i.MX 8M Quad Reference Manual (Section 5.1.2 Table 5-1) MIPI_CSI1_PHY_REF_CLK_ROOT and MIPI_CSI2_PHY_REF_CLK_ROOT have SYSTEM_PLL2_DIV3 available as their second source, which corresponds to sys2_pll_333m rather than sys2_pll_125m. Fixes: b80522040cd3 ("clk: imx: Add clock driver for i.MX8MQ CCM") Signed-off-by: Sebastian Krzyszkowiak Reviewed-by: Peng Fan Link: https://patch.msgid.link/20260128-imx8mq-csi-clk-v1-1-ac028ed26e8c@puri.sm Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index f70ed231b92d6..cedc8a02aa1f0 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -237,7 +237,7 @@ static const char * const imx8mq_dsi_esc_sels[] = {"osc_25m", "sys2_pll_100m", " static const char * const imx8mq_csi1_core_sels[] = {"osc_25m", "sys1_pll_266m", "sys2_pll_250m", "sys1_pll_800m", "sys2_pll_1000m", "sys3_pll_out", "audio_pll2_out", "video_pll1_out", }; -static const char * const imx8mq_csi1_phy_sels[] = {"osc_25m", "sys2_pll_125m", "sys2_pll_100m", "sys1_pll_800m", +static const char * const imx8mq_csi1_phy_sels[] = {"osc_25m", "sys2_pll_333m", "sys2_pll_100m", "sys1_pll_800m", "sys2_pll_1000m", "clk_ext2", "audio_pll2_out", "video_pll1_out", }; static const char * const imx8mq_csi1_esc_sels[] = {"osc_25m", "sys2_pll_100m", "sys1_pll_80m", "sys1_pll_800m", @@ -246,7 +246,7 @@ static const char * const imx8mq_csi1_esc_sels[] = {"osc_25m", "sys2_pll_100m", static const char * const imx8mq_csi2_core_sels[] = {"osc_25m", "sys1_pll_266m", "sys2_pll_250m", "sys1_pll_800m", "sys2_pll_1000m", "sys3_pll_out", "audio_pll2_out", "video_pll1_out", }; -static const char * const imx8mq_csi2_phy_sels[] = {"osc_25m", "sys2_pll_125m", "sys2_pll_100m", "sys1_pll_800m", +static const char * const imx8mq_csi2_phy_sels[] = {"osc_25m", "sys2_pll_333m", "sys2_pll_100m", "sys1_pll_800m", "sys2_pll_1000m", "clk_ext2", "audio_pll2_out", "video_pll1_out", }; static const char * const imx8mq_csi2_esc_sels[] = {"osc_25m", "sys2_pll_100m", "sys1_pll_80m", "sys1_pll_800m", From 0f548ecd2d7812a27498bcf8b0b0656b9c21567a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 13 Oct 2025 12:40:21 +0200 Subject: [PATCH 0754/1518] x86/um/vdso: Drop VDSO64-y from Makefile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3c9b904f9033fb250db72d258bbdec791dc89405 ] This symbol is unnecessary, remove it. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20251013-uml-vdso-cleanup-v1-4-a079c7adcc69@weissschuh.net Signed-off-by: Johannes Berg Stable-dep-of: d1895c15fc7d ("x86/um: fix vDSO installation") Signed-off-by: Sasha Levin --- arch/x86/um/vdso/Makefile | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 7478d11dacb71..8a7c8b37cb6eb 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -3,16 +3,13 @@ # Building vDSO images for x86. # -VDSO64-y := y - -vdso-install-$(VDSO64-y) += vdso.so - +vdso-install-y += vdso.so # files to link into the vdso vobjs-y := vdso-note.o um_vdso.o # files to link into kernel -obj-$(VDSO64-y) += vdso.o vma.o +obj-y += vdso.o vma.o vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) From 07410592862686ad3be4906b1fcabc253d3961d8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 18 Mar 2026 22:03:26 +0100 Subject: [PATCH 0755/1518] x86/um: fix vDSO installation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d1895c15fc7d90a615bc8c455feb02acaf08ef1e ] The generic vDSO installation logic used by 'make vdso_install' requires that $(vdso-install-y) is defined by the top-level architecture Makefile and that it contains a path relative to the root of the tree. For UML neither of these is satisfied. Move the definition of $(vdso-install-y) to a place which is included by the arch/um/Makefile and use the full relative path. Fixes: f1c2bb8b9964 ("um: implement a x86_64 vDSO") Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20260318-um-vdso-install-v1-1-26a4ca5c4210@weissschuh.net Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- arch/x86/Makefile.um | 2 ++ arch/x86/um/vdso/Makefile | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index c86cbd9cbba38..19c13afa474e9 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -60,4 +60,6 @@ ELF_FORMAT := elf64-x86-64 LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib64 LINK-y += -m64 +vdso-install-y += arch/x86/um/vdso/vdso.so.dbg + endif diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 8a7c8b37cb6eb..7664cbedbe30f 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -3,8 +3,6 @@ # Building vDSO images for x86. # -vdso-install-y += vdso.so - # files to link into the vdso vobjs-y := vdso-note.o um_vdso.o From 558b2eb623f2fb1b128df7dd157e1077b60988e6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 20 Mar 2026 16:18:49 +0100 Subject: [PATCH 0756/1518] clk: qoriq: avoid format string warning [ Upstream commit 096abbb6682ee031a0f5ce9f4c71ead9fa63d31e ] clang-22 warns about the use of non-variadic format arguments passed into snprintf(): drivers/clk/clk-qoriq.c:925:39: error: diagnostic behavior may be improved by adding the 'format(printf, 7, 8)' attribute to the declaration of 'create_mux_common' [-Werror,-Wmissing-format-attribute] 910 | static struct clk * __init create_mux_common(struct clockgen *cg, | __attribute__((format(printf, 7, 8))) 911 | struct mux_hwclock *hwc, 912 | const struct clk_ops *ops, 913 | unsigned long min_rate, 914 | unsigned long max_rate, 915 | unsigned long pct80_rate, 916 | const char *fmt, int idx) 917 | { 918 | struct clk_init_data init = {}; 919 | struct clk *clk; 920 | const struct clockgen_pll_div *div; 921 | const char *parent_names[NUM_MUX_PARENTS]; 922 | char name[32]; 923 | int i, j; 924 | 925 | snprintf(name, sizeof(name), fmt, idx); | ^ drivers/clk/clk-qoriq.c:910:28: note: 'create_mux_common' declared here 910 | static struct clk * __init create_mux_common(struct clockgen *cg, Rework this to pass the 'int idx' as a varargs argument, allowing the format string to be verified at the caller location. Fixes: 0dfc86b3173f ("clk: qoriq: Move chip-specific knowledge into driver") Signed-off-by: Arnd Bergmann Reviewed-by: Kees Cook Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-qoriq.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c index a560edeb4b55a..03f9381e26fb7 100644 --- a/drivers/clk/clk-qoriq.c +++ b/drivers/clk/clk-qoriq.c @@ -907,13 +907,11 @@ static const struct clockgen_pll_div *get_pll_div(struct clockgen *cg, return &cg->pll[pll].div[div]; } -static struct clk * __init create_mux_common(struct clockgen *cg, - struct mux_hwclock *hwc, - const struct clk_ops *ops, - unsigned long min_rate, - unsigned long max_rate, - unsigned long pct80_rate, - const char *fmt, int idx) +static struct clk * __init __printf(7, 8) +create_mux_common(struct clockgen *cg, struct mux_hwclock *hwc, + const struct clk_ops *ops, unsigned long min_rate, + unsigned long max_rate, unsigned long pct80_rate, + const char *fmt, ...) { struct clk_init_data init = {}; struct clk *clk; @@ -921,8 +919,11 @@ static struct clk * __init create_mux_common(struct clockgen *cg, const char *parent_names[NUM_MUX_PARENTS]; char name[32]; int i, j; + va_list args; - snprintf(name, sizeof(name), fmt, idx); + va_start(args, fmt); + vsnprintf(name, sizeof(name), fmt, args); + va_end(args); for (i = 0, j = 0; i < NUM_MUX_PARENTS; i++) { unsigned long rate; From a0195eab4ed5d06a018e1c09302f7887c1a9a726 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 5 Mar 2026 11:11:16 +0100 Subject: [PATCH 0757/1518] clk: xgene: Fix mapping leak in xgene_pllclk_init() [ Upstream commit f520a492e07bc6718e26cfb7543ab4cadd8bb0e2 ] If xgene_register_clk_pll() fails, the mapped register block is never unmapped. Fixes: 308964caeebc45eb ("clk: Add APM X-Gene SoC clock driver") Signed-off-by: Geert Uytterhoeven Reviewed-by: Brian Masney Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-xgene.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c index 92e39f3237c2f..7dc247eb880fb 100644 --- a/drivers/clk/clk-xgene.c +++ b/drivers/clk/clk-xgene.c @@ -188,6 +188,8 @@ static void xgene_pllclk_init(struct device_node *np, enum xgene_pll_type pll_ty of_clk_add_provider(np, of_clk_src_simple_get, clk); clk_register_clkdev(clk, clk_name, NULL); pr_debug("Add %s clock PLL\n", clk_name); + } else { + iounmap(reg); } } From 28e796ac02793c75a017b0f055940cce112cdf4c Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 20 Jan 2026 12:19:25 +0100 Subject: [PATCH 0758/1518] dt-bindings: clock: qcom,dispcc-sc7180: Define MDSS resets [ Upstream commit fc6e29d42872680dca017f2e5169eefe971f8d89 ] The MDSS resets have so far been left undescribed. Fix that. Fixes: 75616da71291 ("dt-bindings: clock: Introduce QCOM sc7180 display clock bindings") Signed-off-by: Konrad Dybcio Reviewed-by: Taniya Das Acked-by: Krzysztof Kozlowski Tested-by: Val Packett # sc7180-ecs-liva-qc710 Link: https://lore.kernel.org/r/20260120-topic-7180_dispcc_bcr-v1-1-0b1b442156c3@oss.qualcomm.com Signed-off-by: Bjorn Andersson Stable-dep-of: b0bc6011c549 ("clk: qcom: dispcc-sc7180: Add missing MDSS resets") Signed-off-by: Sasha Levin --- include/dt-bindings/clock/qcom,dispcc-sc7180.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/include/dt-bindings/clock/qcom,dispcc-sc7180.h b/include/dt-bindings/clock/qcom,dispcc-sc7180.h index b9b51617a335d..0705103060748 100644 --- a/include/dt-bindings/clock/qcom,dispcc-sc7180.h +++ b/include/dt-bindings/clock/qcom,dispcc-sc7180.h @@ -6,6 +6,7 @@ #ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_SC7180_H #define _DT_BINDINGS_CLK_QCOM_DISP_CC_SC7180_H +/* Clocks */ #define DISP_CC_PLL0 0 #define DISP_CC_PLL0_OUT_EVEN 1 #define DISP_CC_MDSS_AHB_CLK 2 @@ -40,7 +41,11 @@ #define DISP_CC_MDSS_VSYNC_CLK_SRC 31 #define DISP_CC_XO_CLK 32 -/* DISP_CC GDSCR */ +/* Resets */ +#define DISP_CC_MDSS_CORE_BCR 0 +#define DISP_CC_MDSS_RSCC_BCR 1 + +/* GDSCs */ #define MDSS_GDSC 0 #endif From 16472129ffd728701716532224d8afc2007ed7fa Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 20 Jan 2026 12:19:26 +0100 Subject: [PATCH 0759/1518] clk: qcom: dispcc-sc7180: Add missing MDSS resets [ Upstream commit b0bc6011c5499bdfddd0390262bfa13dce1eff74 ] The MDSS resets have so far been left undescribed. Fix that. Fixes: dd3d06622138 ("clk: qcom: Add display clock controller driver for SC7180") Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Taniya Das Tested-by: Val Packett # sc7180-ecs-liva-qc710 Link: https://lore.kernel.org/r/20260120-topic-7180_dispcc_bcr-v1-2-0b1b442156c3@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/dispcc-sc7180.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/clk/qcom/dispcc-sc7180.c b/drivers/clk/qcom/dispcc-sc7180.c index ab1a8d419863d..d7e37fbbe87ed 100644 --- a/drivers/clk/qcom/dispcc-sc7180.c +++ b/drivers/clk/qcom/dispcc-sc7180.c @@ -17,6 +17,7 @@ #include "clk-regmap-divider.h" #include "common.h" #include "gdsc.h" +#include "reset.h" enum { P_BI_TCXO, @@ -636,6 +637,11 @@ static struct gdsc mdss_gdsc = { .flags = HW_CTRL, }; +static const struct qcom_reset_map disp_cc_sc7180_resets[] = { + [DISP_CC_MDSS_CORE_BCR] = { 0x2000 }, + [DISP_CC_MDSS_RSCC_BCR] = { 0x4000 }, +}; + static struct gdsc *disp_cc_sc7180_gdscs[] = { [MDSS_GDSC] = &mdss_gdsc, }; @@ -687,6 +693,8 @@ static const struct qcom_cc_desc disp_cc_sc7180_desc = { .config = &disp_cc_sc7180_regmap_config, .clks = disp_cc_sc7180_clocks, .num_clks = ARRAY_SIZE(disp_cc_sc7180_clocks), + .resets = disp_cc_sc7180_resets, + .num_resets = ARRAY_SIZE(disp_cc_sc7180_resets), .gdscs = disp_cc_sc7180_gdscs, .num_gdscs = ARRAY_SIZE(disp_cc_sc7180_gdscs), }; From da99d0302d3ccccfb13c69e663bf8eae698b9562 Mon Sep 17 00:00:00 2001 From: Shuwei Wu Date: Thu, 5 Mar 2026 20:46:08 +0800 Subject: [PATCH 0760/1518] clk: spacemit: ccu_mix: fix inverted condition in ccu_mix_trigger_fc() [ Upstream commit 54e97360b44bed6b4399dd3be3d65f392df940fa ] Fix inverted condition that skips frequency change trigger, causing kernel panics during cpufreq scaling. Fixes: 1b72c59db0ad ("clk: spacemit: Add clock support for SpacemiT K1 SoC") Signed-off-by: Shuwei Wu Reviewed-by: Yixun Lan Link: https://lore.kernel.org/r/20260305-k1-clk-fix-v1-1-abca85d6e266@mailbox.org Signed-off-by: Yixun Lan Signed-off-by: Sasha Levin --- drivers/clk/spacemit/ccu_mix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/spacemit/ccu_mix.c b/drivers/clk/spacemit/ccu_mix.c index 67f8b12b4f5b7..9a3fc9ea1ce56 100644 --- a/drivers/clk/spacemit/ccu_mix.c +++ b/drivers/clk/spacemit/ccu_mix.c @@ -69,7 +69,7 @@ static int ccu_mix_trigger_fc(struct clk_hw *hw) struct ccu_common *common = hw_to_ccu_common(hw); unsigned int val; - if (common->reg_fc) + if (!common->reg_fc) return 0; ccu_update(common, fc, common->mask_fc, common->mask_fc); From fa18659f883e0c31d178d0e81c90e421f4aeefed Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 14 Oct 2025 14:27:03 +0800 Subject: [PATCH 0761/1518] f2fs: use f2fs_filemap_get_folio() instead of f2fs_pagecache_get_page() [ Upstream commit e0b89d00ea9f846da42fc92f200c96254d0e2fef ] Let's use f2fs_filemap_get_folio() instead of f2fs_pagecache_get_page() in ra_data_block() and move_data_block(), then remove f2fs_pagecache_get_page() since it has no user. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Stable-dep-of: 570e2ccc7cb3 ("f2fs: avoid reading already updated pages during GC") Signed-off-by: Sasha Levin --- fs/f2fs/f2fs.h | 10 ---------- fs/f2fs/gc.c | 23 +++++++++++++---------- 2 files changed, 13 insertions(+), 20 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 939bd1fb57070..c0747dd2ce511 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2996,16 +2996,6 @@ static inline struct folio *f2fs_filemap_get_folio( return __filemap_get_folio(mapping, index, fgp_flags, gfp_mask); } -static inline struct page *f2fs_pagecache_get_page( - struct address_space *mapping, pgoff_t index, - fgf_t fgp_flags, gfp_t gfp_mask) -{ - if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) - return NULL; - - return pagecache_get_page(mapping, index, fgp_flags, gfp_mask); -} - static inline void f2fs_folio_put(struct folio *folio, bool unlock) { if (IS_ERR_OR_NULL(folio)) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 9d2f4f22fd396..5647e76c6bdb0 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1211,7 +1211,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index) struct address_space *mapping = f2fs_is_cow_file(inode) ? F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct dnode_of_data dn; - struct folio *folio; + struct folio *folio, *efolio; struct f2fs_io_info fio = { .sbi = sbi, .ino = inode->i_ino, @@ -1266,14 +1266,15 @@ static int ra_data_block(struct inode *inode, pgoff_t index) f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); - fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(sbi), - dn.data_blkaddr, + efolio = f2fs_filemap_get_folio(META_MAPPING(sbi), dn.data_blkaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); - if (!fio.encrypted_page) { - err = -ENOMEM; + if (IS_ERR(efolio)) { + err = PTR_ERR(efolio); goto put_folio; } + fio.encrypted_page = &efolio->page; + err = f2fs_submit_page_bio(&fio); if (err) goto put_encrypted_page; @@ -1313,7 +1314,7 @@ static int move_data_block(struct inode *inode, block_t bidx, struct dnode_of_data dn; struct f2fs_summary sum; struct node_info ni; - struct folio *folio, *mfolio; + struct folio *folio, *mfolio, *efolio; block_t newaddr; int err = 0; bool lfs_mode = f2fs_lfs_mode(fio.sbi); @@ -1407,14 +1408,16 @@ static int move_data_block(struct inode *inode, block_t bidx, goto up_out; } - fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), - newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); - if (!fio.encrypted_page) { - err = -ENOMEM; + efolio = f2fs_filemap_get_folio(META_MAPPING(fio.sbi), newaddr, + FGP_LOCK | FGP_CREAT, GFP_NOFS); + if (IS_ERR(efolio)) { + err = PTR_ERR(efolio); f2fs_folio_put(mfolio, true); goto recover_block; } + fio.encrypted_page = &efolio->page; + /* write target block */ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); memcpy(page_address(fio.encrypted_page), From 4623c251496b99c530ce225c05334f4eac8b933a Mon Sep 17 00:00:00 2001 From: Jianan Huang Date: Thu, 5 Mar 2026 09:18:10 +0800 Subject: [PATCH 0762/1518] f2fs: avoid reading already updated pages during GC [ Upstream commit 570e2ccc7cb35fe720106964e65060602d3d2ac4 ] We found the following issue during fuzz testing: page: refcount:3 mapcount:0 mapping:00000000b6e89c65 index:0x18b2dc pfn:0x161ba9 memcg:f8ffff800e269c00 aops:f2fs_meta_aops ino:2 flags: 0x52880000000080a9(locked|waiters|uptodate|lru|private|zone=1|kasantag=0x4a) raw: 52880000000080a9 fffffffec6e17588 fffffffec0ccc088 a7ffff8067063618 raw: 000000000018b2dc 0000000000000009 00000003ffffffff f8ffff800e269c00 page dumped because: VM_BUG_ON_FOLIO(folio_test_uptodate(folio)) page_owner tracks the page as allocated post_alloc_hook+0x58c/0x5ec prep_new_page+0x34/0x284 get_page_from_freelist+0x2dcc/0x2e8c __alloc_pages_noprof+0x280/0x76c __folio_alloc_noprof+0x18/0xac __filemap_get_folio+0x6bc/0xdc4 pagecache_get_page+0x3c/0x104 do_garbage_collect+0x5c78/0x77a4 f2fs_gc+0xd74/0x25f0 gc_thread_func+0xb28/0x2930 kthread+0x464/0x5d8 ret_from_fork+0x10/0x20 ------------[ cut here ]------------ kernel BUG at mm/filemap.c:1563! folio_end_read+0x140/0x168 f2fs_finish_read_bio+0x5c4/0xb80 f2fs_read_end_io+0x64c/0x708 bio_endio+0x85c/0x8c0 blk_update_request+0x690/0x127c scsi_end_request+0x9c/0xb8c scsi_io_completion+0xf0/0x250 scsi_finish_command+0x430/0x45c scsi_complete+0x178/0x6d4 blk_mq_complete_request+0xcc/0x104 scsi_done_internal+0x214/0x454 scsi_done+0x24/0x34 which is similar to the problem reported by syzbot: https://syzkaller.appspot.com/bug?extid=3686758660f980b402dc This case is consistent with the description in commit 9bf1a3f ("f2fs: avoid GC causing encrypted file corrupted"): Page 1 is moved from blkaddr A to blkaddr B by move_data_block, and after being written it is marked as uptodate. Then, Page 1 is moved from blkaddr B to blkaddr C, VM_BUG_ON_FOLIO was triggered in the endio initiated by ra_data_block. There is no need to read Page 1 again from blkaddr B, since it has already been updated. Therefore, avoid initiating I/O in this case. Fixes: 6aa58d8ad20a ("f2fs: readahead encrypted block during GC") Signed-off-by: Jianan Huang Signed-off-by: Sheng Yong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/gc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5647e76c6bdb0..3d9f326ae840a 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1222,7 +1222,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index) .encrypted_page = NULL, .in_list = 0, }; - int err; + int err = 0; folio = f2fs_grab_cache_folio(mapping, index, true); if (IS_ERR(folio)) @@ -1275,6 +1275,9 @@ static int ra_data_block(struct inode *inode, pgoff_t index) fio.encrypted_page = &efolio->page; + if (folio_test_uptodate(efolio)) + goto put_encrypted_page; + err = f2fs_submit_page_bio(&fio); if (err) goto put_encrypted_page; From 3547f6b9a110fc6b72ec49abda6969a0d32f6e81 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 28 Mar 2026 03:26:19 +0200 Subject: [PATCH 0763/1518] clk: qcom: gdsc: Fix error path on registration of multiple pm subdomains [ Upstream commit 16ba98dace9e7cfe25ad8a314e34befacd91f86f ] Some pm subdomains may be left in added to a parent domain state, if gdsc_add_subdomain_list() function fails in the middle and bails from a GDSC power domain controller registration out. Fixes: b489235b4dc0 ("clk: qcom: Support attaching GDSCs to multiple parents") Signed-off-by: Vladimir Zapolskiy Reviewed-by: Dmitry Baryshkov Reviewed-by: Bryan O'Donoghue Link: https://lore.kernel.org/r/20260328012619.832770-1-vladimir.zapolskiy@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gdsc.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c index 7deabf8400cf6..95aa071202455 100644 --- a/drivers/clk/qcom/gdsc.c +++ b/drivers/clk/qcom/gdsc.c @@ -518,10 +518,20 @@ static int gdsc_add_subdomain_list(struct dev_pm_domain_list *pd_list, ret = pm_genpd_add_subdomain(genpd, subdomain); if (ret) - return ret; + goto remove_added_subdomains; } return 0; + +remove_added_subdomains: + for (i--; i >= 0; i--) { + struct device *dev = pd_list->pd_devs[i]; + struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); + + pm_genpd_remove_subdomain(genpd, subdomain); + } + + return ret; } static void gdsc_remove_subdomain_list(struct dev_pm_domain_list *pd_list, From 480307ffa289dd528211a4c3da9fa4f6c9b41736 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 31 Mar 2026 17:21:43 +0200 Subject: [PATCH 0764/1518] lib/hexdump: print_hex_dump_bytes() calls print_hex_dump_debug() [ Upstream commit 36776b7f8a8955b4e75b5d490a75fee0c7a2a7ef ] print_hex_dump_bytes() claims to be a simple wrapper around print_hex_dump(), but it actally calls print_hex_dump_debug(), which means no output is printed if (dynamic) DEBUG is disabled. Update the documentation to match the implementation. Fixes: 091cb0994edd20d6 ("lib/hexdump: make print_hex_dump_bytes() a nop on !DEBUG builds") Signed-off-by: Geert Uytterhoeven Reviewed-by: Petr Mladek Link: https://patch.msgid.link/3d5c3069fd9102ecaf81d044b750cd613eb72a08.1774970392.git.geert+renesas@glider.be Signed-off-by: Petr Mladek Signed-off-by: Sasha Levin --- include/linux/printk.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/printk.h b/include/linux/printk.h index 9a8eaed5f8778..a98d64b45bc93 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -816,7 +816,8 @@ static inline void print_hex_dump_devel(const char *prefix_str, int prefix_type, #endif /** - * print_hex_dump_bytes - shorthand form of print_hex_dump() with default params + * print_hex_dump_bytes - shorthand form of print_hex_dump_debug() with default + * params * @prefix_str: string to prefix each line with; * caller supplies trailing spaces for alignment if desired * @prefix_type: controls whether prefix of an offset, address, or none @@ -824,7 +825,7 @@ static inline void print_hex_dump_devel(const char *prefix_str, int prefix_type, * @buf: data blob to dump * @len: number of bytes in the @buf * - * Calls print_hex_dump(), with log level of KERN_DEBUG, + * Calls print_hex_dump_debug(), with log level of KERN_DEBUG, * rowsize of 16, groupsize of 1, and ASCII output included. */ #define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ From ef72360aa88ad588f17bc248c3e30bd733b5163b Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 17 Nov 2025 20:45:59 +0800 Subject: [PATCH 0765/1518] f2fs: expand scalability of f2fs mount option [ Upstream commit 1627a303bca692edc6552630aa2f878c8a726a01 ] opt field in structure f2fs_mount_info and opt_mask field in structure f2fs_fs_context is 32-bits variable, now we're running out of available bits in them, let's expand them to 64-bits for better scalability. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Stable-dep-of: 01968164d947 ("f2fs: fix to preserve previous reserve_{blocks,node} value when remount") Signed-off-by: Sasha Levin --- fs/f2fs/f2fs.h | 85 ++++++++++++++++++++++++++----------------------- fs/f2fs/super.c | 36 ++++++++++----------- 2 files changed, 63 insertions(+), 58 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index c0747dd2ce511..b3731ba46f571 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -96,47 +96,52 @@ extern const char *f2fs_fault_name[FAULT_MAX]; /* * For mount options */ -#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000001 -#define F2FS_MOUNT_DISCARD 0x00000002 -#define F2FS_MOUNT_NOHEAP 0x00000004 -#define F2FS_MOUNT_XATTR_USER 0x00000008 -#define F2FS_MOUNT_POSIX_ACL 0x00000010 -#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000020 -#define F2FS_MOUNT_INLINE_XATTR 0x00000040 -#define F2FS_MOUNT_INLINE_DATA 0x00000080 -#define F2FS_MOUNT_INLINE_DENTRY 0x00000100 -#define F2FS_MOUNT_FLUSH_MERGE 0x00000200 -#define F2FS_MOUNT_NOBARRIER 0x00000400 -#define F2FS_MOUNT_FASTBOOT 0x00000800 -#define F2FS_MOUNT_READ_EXTENT_CACHE 0x00001000 -#define F2FS_MOUNT_DATA_FLUSH 0x00002000 -#define F2FS_MOUNT_FAULT_INJECTION 0x00004000 -#define F2FS_MOUNT_USRQUOTA 0x00008000 -#define F2FS_MOUNT_GRPQUOTA 0x00010000 -#define F2FS_MOUNT_PRJQUOTA 0x00020000 -#define F2FS_MOUNT_QUOTA 0x00040000 -#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00080000 -#define F2FS_MOUNT_RESERVE_ROOT 0x00100000 -#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x00200000 -#define F2FS_MOUNT_NORECOVERY 0x00400000 -#define F2FS_MOUNT_ATGC 0x00800000 -#define F2FS_MOUNT_MERGE_CHECKPOINT 0x01000000 -#define F2FS_MOUNT_GC_MERGE 0x02000000 -#define F2FS_MOUNT_COMPRESS_CACHE 0x04000000 -#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x08000000 -#define F2FS_MOUNT_NAT_BITS 0x10000000 -#define F2FS_MOUNT_INLINECRYPT 0x20000000 -/* - * Some f2fs environments expect to be able to pass the "lazytime" option - * string rather than using the MS_LAZYTIME flag, so this must remain. - */ -#define F2FS_MOUNT_LAZYTIME 0x40000000 -#define F2FS_MOUNT_RESERVE_NODE 0x80000000 +enum f2fs_mount_opt { + F2FS_MOUNT_DISABLE_ROLL_FORWARD, + F2FS_MOUNT_DISCARD, + F2FS_MOUNT_NOHEAP, + F2FS_MOUNT_XATTR_USER, + F2FS_MOUNT_POSIX_ACL, + F2FS_MOUNT_DISABLE_EXT_IDENTIFY, + F2FS_MOUNT_INLINE_XATTR, + F2FS_MOUNT_INLINE_DATA, + F2FS_MOUNT_INLINE_DENTRY, + F2FS_MOUNT_FLUSH_MERGE, + F2FS_MOUNT_NOBARRIER, + F2FS_MOUNT_FASTBOOT, + F2FS_MOUNT_READ_EXTENT_CACHE, + F2FS_MOUNT_DATA_FLUSH, + F2FS_MOUNT_FAULT_INJECTION, + F2FS_MOUNT_USRQUOTA, + F2FS_MOUNT_GRPQUOTA, + F2FS_MOUNT_PRJQUOTA, + F2FS_MOUNT_QUOTA, + F2FS_MOUNT_INLINE_XATTR_SIZE, + F2FS_MOUNT_RESERVE_ROOT, + F2FS_MOUNT_DISABLE_CHECKPOINT, + F2FS_MOUNT_NORECOVERY, + F2FS_MOUNT_ATGC, + F2FS_MOUNT_MERGE_CHECKPOINT, + F2FS_MOUNT_GC_MERGE, + F2FS_MOUNT_COMPRESS_CACHE, + F2FS_MOUNT_AGE_EXTENT_CACHE, + F2FS_MOUNT_NAT_BITS, + F2FS_MOUNT_INLINECRYPT, + /* + * Some f2fs environments expect to be able to pass the "lazytime" option + * string rather than using the MS_LAZYTIME flag, so this must remain. + */ + F2FS_MOUNT_LAZYTIME, + F2FS_MOUNT_RESERVE_NODE, +}; #define F2FS_OPTION(sbi) ((sbi)->mount_opt) -#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) -#define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option) -#define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option) +#define clear_opt(sbi, option) \ + (F2FS_OPTION(sbi).opt &= ~BIT(F2FS_MOUNT_##option)) +#define set_opt(sbi, option) \ + (F2FS_OPTION(sbi).opt |= BIT(F2FS_MOUNT_##option)) +#define test_opt(sbi, option) \ + (F2FS_OPTION(sbi).opt & BIT(F2FS_MOUNT_##option)) #define ver_after(a, b) (typecheck(unsigned long long, a) && \ typecheck(unsigned long long, b) && \ @@ -183,7 +188,7 @@ struct f2fs_rwsem { }; struct f2fs_mount_info { - unsigned int opt; + unsigned long long opt; block_t root_reserved_blocks; /* root reserved blocks */ block_t root_reserved_nodes; /* root reserved nodes */ kuid_t s_resuid; /* reserved blocks for uid */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 96325bbc70386..8790d9d4348a1 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -352,7 +352,7 @@ static match_table_t f2fs_checkpoint_tokens = { struct f2fs_fs_context { struct f2fs_mount_info info; - unsigned int opt_mask; /* Bits changed */ + unsigned long long opt_mask; /* Bits changed */ unsigned int spec_mask; unsigned short qname_mask; }; @@ -360,23 +360,23 @@ struct f2fs_fs_context { #define F2FS_CTX_INFO(ctx) ((ctx)->info) static inline void ctx_set_opt(struct f2fs_fs_context *ctx, - unsigned int flag) + enum f2fs_mount_opt flag) { - ctx->info.opt |= flag; - ctx->opt_mask |= flag; + ctx->info.opt |= BIT(flag); + ctx->opt_mask |= BIT(flag); } static inline void ctx_clear_opt(struct f2fs_fs_context *ctx, - unsigned int flag) + enum f2fs_mount_opt flag) { - ctx->info.opt &= ~flag; - ctx->opt_mask |= flag; + ctx->info.opt &= ~BIT(flag); + ctx->opt_mask |= BIT(flag); } static inline bool ctx_test_opt(struct f2fs_fs_context *ctx, - unsigned int flag) + enum f2fs_mount_opt flag) { - return ctx->info.opt & flag; + return ctx->info.opt & BIT(flag); } void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, @@ -1371,7 +1371,7 @@ static int f2fs_check_compression(struct fs_context *fc, ctx_test_opt(ctx, F2FS_MOUNT_COMPRESS_CACHE)) f2fs_info(sbi, "Image doesn't support compression"); clear_compression_spec(ctx); - ctx->opt_mask &= ~F2FS_MOUNT_COMPRESS_CACHE; + ctx->opt_mask &= ~BIT(F2FS_MOUNT_COMPRESS_CACHE); return 0; } if (ctx->spec_mask & F2FS_SPEC_compress_extension) { @@ -1439,42 +1439,42 @@ static int f2fs_check_opt_consistency(struct fs_context *fc, return -EINVAL; if (f2fs_hw_should_discard(sbi) && - (ctx->opt_mask & F2FS_MOUNT_DISCARD) && + (ctx->opt_mask & BIT(F2FS_MOUNT_DISCARD)) && !ctx_test_opt(ctx, F2FS_MOUNT_DISCARD)) { f2fs_warn(sbi, "discard is required for zoned block devices"); return -EINVAL; } if (!f2fs_hw_support_discard(sbi) && - (ctx->opt_mask & F2FS_MOUNT_DISCARD) && + (ctx->opt_mask & BIT(F2FS_MOUNT_DISCARD)) && ctx_test_opt(ctx, F2FS_MOUNT_DISCARD)) { f2fs_warn(sbi, "device does not support discard"); ctx_clear_opt(ctx, F2FS_MOUNT_DISCARD); - ctx->opt_mask &= ~F2FS_MOUNT_DISCARD; + ctx->opt_mask &= ~BIT(F2FS_MOUNT_DISCARD); } if (f2fs_sb_has_device_alias(sbi) && - (ctx->opt_mask & F2FS_MOUNT_READ_EXTENT_CACHE) && + (ctx->opt_mask & BIT(F2FS_MOUNT_READ_EXTENT_CACHE)) && !ctx_test_opt(ctx, F2FS_MOUNT_READ_EXTENT_CACHE)) { f2fs_err(sbi, "device aliasing requires extent cache"); return -EINVAL; } if (test_opt(sbi, RESERVE_ROOT) && - (ctx->opt_mask & F2FS_MOUNT_RESERVE_ROOT) && + (ctx->opt_mask & BIT(F2FS_MOUNT_RESERVE_ROOT)) && ctx_test_opt(ctx, F2FS_MOUNT_RESERVE_ROOT)) { f2fs_info(sbi, "Preserve previous reserve_root=%u", F2FS_OPTION(sbi).root_reserved_blocks); ctx_clear_opt(ctx, F2FS_MOUNT_RESERVE_ROOT); - ctx->opt_mask &= ~F2FS_MOUNT_RESERVE_ROOT; + ctx->opt_mask &= ~BIT(F2FS_MOUNT_RESERVE_ROOT); } if (test_opt(sbi, RESERVE_NODE) && - (ctx->opt_mask & F2FS_MOUNT_RESERVE_NODE) && + (ctx->opt_mask & BIT(F2FS_MOUNT_RESERVE_NODE)) && ctx_test_opt(ctx, F2FS_MOUNT_RESERVE_NODE)) { f2fs_info(sbi, "Preserve previous reserve_node=%u", F2FS_OPTION(sbi).root_reserved_nodes); ctx_clear_opt(ctx, F2FS_MOUNT_RESERVE_NODE); - ctx->opt_mask &= ~F2FS_MOUNT_RESERVE_NODE; + ctx->opt_mask &= ~BIT(F2FS_MOUNT_RESERVE_NODE); } err = f2fs_check_test_dummy_encryption(fc, sb); From a841167c1ef7bfeffa62e6f494e4ff9be7fa0812 Mon Sep 17 00:00:00 2001 From: Zhiguo Niu Date: Thu, 5 Mar 2026 11:22:46 +0800 Subject: [PATCH 0766/1518] f2fs: fix to preserve previous reserve_{blocks,node} value when remount [ Upstream commit 01968164d94762db2f703647c5acfa28613844f1 ] The following steps will change previous value of reserve_{blocks,node}, this dones not match the original intention. 1.mount -t f2fs -o reserve_root=8192 imgfile test_mount/ F2FS-fs (loop56): Mounted with checkpoint version = 1b69f8c7 mount info: /dev/block/loop56 on /data/test_mount type f2fs (xxx,reserve_root=8192,reserve_node=0,resuid=0,resgid=0,xxx) 2.mount -t f2fs -o remount,reserve_root=4096 /data/test_mount F2FS-fs (loop56): Preserve previous reserve_root=8192 check mount info: reserve_root change to 4096 /dev/block/loop56 on /data/test_mount type f2fs (xxx,reserve_root=4096,reserve_node=0,resuid=0,resgid=0,xxx) Prior to commit d18535132523 ("f2fs: separate the options parsing and options checking"), the value of reserve_{blocks,node} was only set during the first mount, along with the corresponding mount option F2FS_MOUNT_RESERVE_{ROOT,NODE} . If the mount option F2FS_MOUNT_RESERVE_{ROOT,NODE} was found to have been set during the mount/remount, the previously value of reserve_{blocks,node} would also be preserved, as shown in the code below. if (test_opt(sbi, RESERVE_ROOT)) { f2fs_info(sbi, "Preserve previous reserve_root=%u", F2FS_OPTION(sbi).root_reserved_blocks); } else { F2FS_OPTION(sbi).root_reserved_blocks = arg; set_opt(sbi, RESERVE_ROOT); } But commit d18535132523 ("f2fs: separate the options parsing and options checking") only preserved the previous mount option; it did not preserve the previous value of reserve_{blocks,node}. Since value of reserve_{blocks,node} value is assigned or not depends on ctx->spec_mask, ctx->spec_mask should be alos handled in f2fs_check_opt_consistency. This patch will clear the corresponding ctx->spec_mask bits in f2fs_check_opt_consistency to preserve the previously values of reserve_{blocks,node} if it already have a value. Fixes: d18535132523 ("f2fs: separate the options parsing and options checking") Signed-off-by: Zhiguo Niu Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 8790d9d4348a1..7e04ae8f32f0e 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1467,6 +1467,7 @@ static int f2fs_check_opt_consistency(struct fs_context *fc, F2FS_OPTION(sbi).root_reserved_blocks); ctx_clear_opt(ctx, F2FS_MOUNT_RESERVE_ROOT); ctx->opt_mask &= ~BIT(F2FS_MOUNT_RESERVE_ROOT); + ctx->spec_mask &= ~F2FS_SPEC_reserve_root; } if (test_opt(sbi, RESERVE_NODE) && (ctx->opt_mask & BIT(F2FS_MOUNT_RESERVE_NODE)) && @@ -1475,6 +1476,7 @@ static int f2fs_check_opt_consistency(struct fs_context *fc, F2FS_OPTION(sbi).root_reserved_nodes); ctx_clear_opt(ctx, F2FS_MOUNT_RESERVE_NODE); ctx->opt_mask &= ~BIT(F2FS_MOUNT_RESERVE_NODE); + ctx->spec_mask &= ~F2FS_SPEC_reserve_node; } err = f2fs_check_test_dummy_encryption(fc, sb); From cccefa34c09ac2a24c5953cd069bfa79af892086 Mon Sep 17 00:00:00 2001 From: Jagadeesh Kona Date: Fri, 27 Mar 2026 20:36:46 +0530 Subject: [PATCH 0767/1518] clk: qcom: gcc-x1e80100: Keep GCC USB QTB clock always ON [ Upstream commit 05566ebcc0cd170bd4f50c907ee3ed8e106251e3 ] In Hamoa, SMMU invalidation requires the GCC_AGGRE_USB_NOC_AXI_CLK to be on for the USB QTB to be functional. This is currently explicitly enabled by the DWC3 glue driver, so an invalidation happening while the USB controller is suspended will fault. Solve this by voting for the GCC MMU USB QTB clock. Fixes: 161b7c401f4b ("clk: qcom: Add Global Clock controller (GCC) driver for X1E80100") Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Signed-off-by: Jagadeesh Kona Reviewed-by: Taniya Das Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20260327-hamoa-usb-qtb-clk-always-on-v2-1-7d8a406e650f@oss.qualcomm.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-x1e80100.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c index ef8d2df188d3b..104b1bf6a5010 100644 --- a/drivers/clk/qcom/gcc-x1e80100.c +++ b/drivers/clk/qcom/gcc-x1e80100.c @@ -6751,6 +6751,7 @@ static int gcc_x1e80100_probe(struct platform_device *pdev) qcom_branch_set_clk_en(regmap, 0x32004); /* GCC_VIDEO_AHB_CLK */ qcom_branch_set_clk_en(regmap, 0x32030); /* GCC_VIDEO_XO_CLK */ qcom_branch_set_clk_en(regmap, 0x71004); /* GCC_GPU_CFG_AHB_CLK */ + qcom_branch_set_clk_en(regmap, 0x7d01c); /* GCC_HLOS1_VOTE_AGGRE_NOC_MMU_USB_QTB_CLK */ /* Clear GDSC_SLEEP_ENA_VOTE to stop votes being auto-removed in sleep. */ regmap_write(regmap, 0x52224, 0x0); From 1c5973c84ab453dd8e752aed0e33450292213943 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Mon, 30 Mar 2026 10:32:37 -0400 Subject: [PATCH 0768/1518] clk: visconti: pll: initialize clk_init_data to zero MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1603cbb64173a0e9fa7500f2a686f4aa011c58b9 ] Sashiko reported the following: > The struct clk_init_data init is declared on the stack without being > fully zero-initialized. While fields like name, flags, parent_names, > num_parents, and ops are explicitly assigned, the parent_data and > parent_hws fields are left containing stack garbage. clk_core_populate_parent_map() currently prefers the parent names over the parent data and hws, so this isn't a problem at the moment. If that ordering ever changed in the future, then this could lead to some unexpected crashes. Let's just go ahead and make sure that the struct clk_init_data is initialized to zero as a good practice. Fixes: b4cbe606dc367 ("clk: visconti: Add support common clock driver and reset driver") Link: https://sashiko.dev/#/patchset/20260326042317.122536-1-rosenp%40gmail.com Signed-off-by: Brian Masney Reviewed-by: Benoît Monin Reviewed-by: Nobuhiro Iwamatsu Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/visconti/pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/visconti/pll.c b/drivers/clk/visconti/pll.c index 681721d850320..9d088239a1b2c 100644 --- a/drivers/clk/visconti/pll.c +++ b/drivers/clk/visconti/pll.c @@ -249,7 +249,7 @@ static struct clk_hw *visconti_register_pll(struct visconti_pll_provider *ctx, const struct visconti_pll_rate_table *rate_table, spinlock_t *lock) { - struct clk_init_data init; + struct clk_init_data init = {}; struct visconti_pll *pll; struct clk_hw *pll_hw_clk; size_t len; From 2b0ae4b59ff5d277989bc5c477d01c0d48e093b1 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 30 Mar 2026 23:40:59 +0000 Subject: [PATCH 0769/1518] f2fs: allow empty mount string for Opt_usr|grp|projjquota [ Upstream commit 2a3db1e02ce08c14af04da70bb99e8a0a31eb9e8 ] The fsparam_string_empty() gives an error when mounting without string, since its type is set to fsparam_flag in VFS. So, let's allow the flag as well. This addresses xfstests/f2fs/015 and f2fs/021. Fixes: d18535132523 ("f2fs: separate the options parsing and options checking") Reviewed-by: Daeho Jeong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 7e04ae8f32f0e..cb8e8a587ba9e 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -285,9 +285,12 @@ static const struct fs_parameter_spec f2fs_param_specs[] = { fsparam_flag("usrquota", Opt_usrquota), fsparam_flag("grpquota", Opt_grpquota), fsparam_flag("prjquota", Opt_prjquota), - fsparam_string_empty("usrjquota", Opt_usrjquota), - fsparam_string_empty("grpjquota", Opt_grpjquota), - fsparam_string_empty("prjjquota", Opt_prjjquota), + fsparam_string("usrjquota", Opt_usrjquota), + fsparam_flag("usrjquota", Opt_usrjquota), + fsparam_string("grpjquota", Opt_grpjquota), + fsparam_flag("grpjquota", Opt_grpjquota), + fsparam_string("prjjquota", Opt_prjjquota), + fsparam_flag("prjjquota", Opt_prjjquota), fsparam_flag("nat_bits", Opt_nat_bits), fsparam_enum("jqfmt", Opt_jqfmt, f2fs_param_jqfmt), fsparam_enum("alloc_mode", Opt_alloc, f2fs_param_alloc_mode), @@ -931,26 +934,26 @@ static int f2fs_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx_set_opt(ctx, F2FS_MOUNT_PRJQUOTA); break; case Opt_usrjquota: - if (!*param->string) - ret = f2fs_unnote_qf_name(fc, USRQUOTA); - else + if (param->type == fs_value_is_string && *param->string) ret = f2fs_note_qf_name(fc, USRQUOTA, param); + else + ret = f2fs_unnote_qf_name(fc, USRQUOTA); if (ret) return ret; break; case Opt_grpjquota: - if (!*param->string) - ret = f2fs_unnote_qf_name(fc, GRPQUOTA); - else + if (param->type == fs_value_is_string && *param->string) ret = f2fs_note_qf_name(fc, GRPQUOTA, param); + else + ret = f2fs_unnote_qf_name(fc, GRPQUOTA); if (ret) return ret; break; case Opt_prjjquota: - if (!*param->string) - ret = f2fs_unnote_qf_name(fc, PRJQUOTA); - else + if (param->type == fs_value_is_string && *param->string) ret = f2fs_note_qf_name(fc, PRJQUOTA, param); + else + ret = f2fs_unnote_qf_name(fc, PRJQUOTA); if (ret) return ret; break; From d0e877810baf613b018fd9747440b9d4d9db1428 Mon Sep 17 00:00:00 2001 From: Yongpeng Yang Date: Fri, 10 Apr 2026 23:05:39 +0800 Subject: [PATCH 0770/1518] f2fs: protect extension_list reading with sb_lock in f2fs_sbi_show() [ Upstream commit 5909bedbed38c558bee7cb6758ceedf9bc3a9194 ] In f2fs_sbi_show(), the extension_list, extension_count and hot_ext_count are read without holding sbi->sb_lock. If a concurrent sysfs store modifies the extension list via f2fs_update_extension_list(), the show path may read inconsistent count and array contents, potentially leading to out-of-bounds access or displaying stale data. Fix this by holding sb_lock around the entire extension list read and format operation. Fixes: b6a06cbbb5f7 ("f2fs: support hot file extension") Signed-off-by: Yongpeng Yang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/sysfs.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a75c3ef300bd2..1f5982a0a6326 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -377,10 +377,12 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, if (!strcmp(a->attr.name, "extension_list")) { __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; - int cold_count = le32_to_cpu(sbi->raw_super->extension_count); - int hot_count = sbi->raw_super->hot_ext_count; + int cold_count, hot_count; int len = 0, i; + f2fs_down_read(&sbi->sb_lock); + cold_count = le32_to_cpu(sbi->raw_super->extension_count); + hot_count = sbi->raw_super->hot_ext_count; len += sysfs_emit_at(buf, len, "cold file extension:\n"); for (i = 0; i < cold_count; i++) len += sysfs_emit_at(buf, len, "%s\n", extlist[i]); @@ -388,6 +390,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, len += sysfs_emit_at(buf, len, "hot file extension:\n"); for (i = cold_count; i < cold_count + hot_count; i++) len += sysfs_emit_at(buf, len, "%s\n", extlist[i]); + f2fs_up_read(&sbi->sb_lock); return len; } From 60a6842061b49f5afdc605b801713fb831f44d0f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 24 Mar 2026 15:48:38 +0200 Subject: [PATCH 0771/1518] drm/i915/wm: Verify the correct plane DDB entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a97c88a176b6b8d116f4d3f508f3bd02bc77b462 ] Actually verify the DDB entry for the plane we're looking at instead of always verifying the cursor DDB. Fixes: 7d4561722c3b ("drm/i915: Tweak plane ddb allocation tracking") Signed-off-by: Ville Syrjälä Link: https://patch.msgid.link/20260324134843.2364-5-ville.syrjala@linux.intel.com Reviewed-by: Vinod Govindapillai (cherry picked from commit f002f7c7439de18117a31ca84dc87a59719c3dd6) Signed-off-by: Tvrtko Ursulin Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/display/skl_watermark.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index d74cbb43ae6fb..a5862998bf144 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -3935,8 +3935,8 @@ void intel_wm_state_verify(struct intel_atomic_state *state, } /* DDB */ - hw_ddb_entry = &hw->ddb[PLANE_CURSOR]; - sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb[PLANE_CURSOR]; + hw_ddb_entry = &hw->ddb[plane->id]; + sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb[plane->id]; if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) { drm_err(display->drm, From c6efc77954d8a59447c8560251ddad04d9859574 Mon Sep 17 00:00:00 2001 From: Sami Mujawar Date: Fri, 10 Apr 2026 17:36:36 +0100 Subject: [PATCH 0772/1518] virt: arm-cca-guest: fix error check for RSI_INCOMPLETE [ Upstream commit e534e9d13d0b7bdbb2cccdace7b96b769a10540e ] The RSI interface can return RSI_INCOMPLETE when a report spans multiple granules. This is an expected condition and should not be treated as a fatal error. Currently, arm_cca_report_new() checks for `info.result != RSI_SUCCESS` and bails out, which incorrectly flags RSI_INCOMPLETE as a failure. Fix the check to only break out on results other than RSI_SUCCESS or RSI_INCOMPLETE. This ensures partial reports are handled correctly and avoids spurious -ENXIO errors when generating attestation reports. Fixes: 7999edc484ca ("virt: arm-cca-guest: TSM_REPORT support for realms") Signed-off-by: Sami Mujawar Reported-by: Jagdish Gediya Reviewed-by: Steven Price Reviewed-by: Gavin Shan Reviewed-by: Suzuki K Poulose Reviewed-by: Yeoreum Yun Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- drivers/virt/coco/arm-cca-guest/arm-cca-guest.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c index 0c9ea24a200c9..66d00b6ceb789 100644 --- a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c +++ b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c @@ -157,7 +157,8 @@ static int arm_cca_report_new(struct tsm_report *report, void *data) } while (info.result == RSI_INCOMPLETE && info.offset < RSI_GRANULE_SIZE); - if (info.result != RSI_SUCCESS) { + /* Break out in case of failure */ + if (info.result != RSI_SUCCESS && info.result != RSI_INCOMPLETE) { ret = -ENXIO; token_size = 0; goto exit_free_granule_page; From fc9310d79fdb117b369a01eb00f4fd5fb4849d4e Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Sat, 11 Apr 2026 23:08:17 +0200 Subject: [PATCH 0773/1518] crypto: eip93 - fix hmac setkey algo selection [ Upstream commit 3ba3b02f897b14e34977e1886d95ffe64d907204 ] eip93_hmac_setkey() allocates a temporary ahash transform for computing HMAC ipad/opad key material. The allocation uses the driver-specific cra_driver_name (e.g. "sha256-eip93") but passes CRYPTO_ALG_ASYNC as the mask, which excludes async algorithms. Since the EIP93 hash algorithms are the only ones registered under those driver names and they are inherently async, the lookup is self-contradictory and always fails with -ENOENT. When called from the AEAD setkey path, this failure leaves the SA record partially initialized with zeroed digest fields. A subsequent crypto operation then dereferences a NULL pointer in the request context, resulting in a kernel panic: ``` pc : eip93_aead_handle_result+0xc8c/0x1240 [crypto_hw_eip93] lr : eip93_aead_handle_result+0xbec/0x1240 [crypto_hw_eip93] sp : ffffffc082feb820 x29: ffffffc082feb820 x28: ffffff8011043980 x27: 0000000000000000 x26: 0000000000000000 x25: ffffffc078da0bc8 x24: 0000000091043980 x23: ffffff8004d59e50 x22: ffffff8004d59410 x21: ffffff8004d593c0 x20: ffffff8004d593c0 x19: ffffff8004d4f300 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000007fda7aa498 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000000 x10: fffffffff8127a80 x9 : 0000000000000000 x8 : ffffff8004d4f380 x7 : 0000000000000000 x6 : 000000000000003f x5 : 0000000000000040 x4 : 0000000000000008 x3 : 0000000000000009 x2 : 0000000000000008 x1 : 0000000028000003 x0 : ffffff8004d388c0 Code: 910142b6 f94012e0 f9002aa0 f90006d3 (f9400740) ``` The reported symbol eip93_aead_handle_result+0xc8c is a resolution artifact from static functions being merged under the nearest exported symbol. Decoding the faulting sequence: ``` 910142b6 ADD X22, X21, #0x50 f94012e0 LDR X0, [X23, #0x20] f9002aa0 STR X0, [X21, #0x50] f90006d3 STR X19, [X22, #0x8] f9400740 LDR X0, [X26, #0x8] ``` The faulting LDR at [X26, #0x8] is loading ctx->flags (offset 8 in eip93_hash_ctx), where ctx has been resolved to NULL from a partially initialized or unreachable transform context following the failed setkey. Fix this by dropping the CRYPTO_ALG_ASYNC mask from the crypto_alloc_ahash() call. The code already handles async completion correctly via crypto_wait_req(), so there is no requirement to restrict the lookup to synchronous algorithms. Note that hashing a single 64-byte block through the hardware is likely slower than doing it in software due to the DMA round-trip overhead, but offloading it may still spare CPU cycles on the slower embedded cores where this IP is found. Fixes: 9739f5f93b78 ("crypto: eip93 - Add Inside Secure SafeXcel EIP-93 crypto engine support") Signed-off-by: Aleksander Jan Bajkowski [Detailed investigation report of this bug] Signed-off-by: Kenneth Kasilag Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/inside-secure/eip93/eip93-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/inside-secure/eip93/eip93-common.c b/drivers/crypto/inside-secure/eip93/eip93-common.c index 66153aa2493f2..43a2df542583b 100644 --- a/drivers/crypto/inside-secure/eip93/eip93-common.c +++ b/drivers/crypto/inside-secure/eip93/eip93-common.c @@ -731,7 +731,7 @@ int eip93_hmac_setkey(u32 ctx_flags, const u8 *key, unsigned int keylen, return -EINVAL; } - ahash_tfm = crypto_alloc_ahash(alg_name, 0, CRYPTO_ALG_ASYNC); + ahash_tfm = crypto_alloc_ahash(alg_name, 0, 0); if (IS_ERR(ahash_tfm)) return PTR_ERR(ahash_tfm); From d05ebf0d3f8c078852fbcb3aa5b59c748c47446a Mon Sep 17 00:00:00 2001 From: T Pratham Date: Wed, 15 Apr 2026 20:06:58 +0530 Subject: [PATCH 0774/1518] crypto: sa2ul - Fix AEAD fallback algorithm names [ Upstream commit 8451ab6ad686ffdcdf9ddadaa446a79ab48e5590 ] For authenc AEAD algorithms, sa2ul is trying to register very specific -ce version as a fallback. This causes registration failure on SoCs which do not have ARMv8-CE enabled/available. Change the fallback algorithm from the specific driver name to generic algorithm name so that the kernel can allocate any available fallback. Fixes: d2c8ac187fc92 ("crypto: sa2ul - Add AEAD algorithm support") Signed-off-by: T Pratham Reviewed-by: Manorit Chawdhry Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/sa2ul.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c index fdc0b24860691..52fe4baeff934 100644 --- a/drivers/crypto/sa2ul.c +++ b/drivers/crypto/sa2ul.c @@ -1744,13 +1744,13 @@ static int sa_cra_init_aead(struct crypto_aead *tfm, const char *hash, static int sa_cra_init_aead_sha1(struct crypto_aead *tfm) { return sa_cra_init_aead(tfm, "sha1", - "authenc(hmac(sha1-ce),cbc(aes-ce))"); + "authenc(hmac(sha1),cbc(aes))"); } static int sa_cra_init_aead_sha256(struct crypto_aead *tfm) { return sa_cra_init_aead(tfm, "sha256", - "authenc(hmac(sha256-ce),cbc(aes-ce))"); + "authenc(hmac(sha256),cbc(aes))"); } static void sa_exit_tfm_aead(struct crypto_aead *tfm) From df9784bb5b637ac80f4a2768a58ca9a50bef28a9 Mon Sep 17 00:00:00 2001 From: Paul Moses Date: Wed, 1 Apr 2026 03:07:49 -0500 Subject: [PATCH 0775/1518] crypto: ccp - copy IV using skcipher ivsize [ Upstream commit a7a1f3cdd64d8a165d9b8c9e9ad7fb46ac19dfc4 ] AF_ALG rfc3686-ctr-aes-ccp requests pass an 8-byte IV to the driver. ccp_aes_complete() restores AES_BLOCK_SIZE bytes into the caller's IV buffer while RFC3686 skciphers expose an 8-byte IV, so the restore overruns the provided buffer. Use crypto_skcipher_ivsize() to copy only the algorithm's IV length. Fixes: 2b789435d7f3 ("crypto: ccp - CCP AES crypto API support") Signed-off-by: Paul Moses Reviewed-by: Tom Lendacky Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccp/ccp-crypto-aes.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/ccp/ccp-crypto-aes.c b/drivers/crypto/ccp/ccp-crypto-aes.c index 685d42ec7adea..b5be3af8b2fe5 100644 --- a/drivers/crypto/ccp/ccp-crypto-aes.c +++ b/drivers/crypto/ccp/ccp-crypto-aes.c @@ -30,8 +30,11 @@ static int ccp_aes_complete(struct crypto_async_request *async_req, int ret) if (ret) return ret; - if (ctx->u.aes.mode != CCP_AES_MODE_ECB) - memcpy(req->iv, rctx->iv, AES_BLOCK_SIZE); + if (ctx->u.aes.mode != CCP_AES_MODE_ECB) { + size_t ivsize = crypto_skcipher_ivsize(crypto_skcipher_reqtfm(req)); + + memcpy(req->iv, rctx->iv, ivsize); + } return 0; } From 858e4d98a86adf34584767388deb6c9b217f70c5 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Mon, 20 Apr 2026 18:11:42 +0800 Subject: [PATCH 0776/1518] erofs: unify lcn as u64 for 32-bit platforms [ Upstream commit 2d8c7edcb661812249469f4a5b62e9339118846f ] As sashiko reported [1], `lcn` was typed as `unsigned long` (or `unsigned int` sometimes), which is only 32 bits wide on 32-bit platforms, which causes `(lcn << lclusterbits)` to be truncated at 4 GiB. In order to consolidate the logic, just use `u64` consistently around the codebase. [1] https://sashiko.dev/r/20260420034612.1899973-1-hsiangkao%40linux.alibaba.com Fixes: 152a333a5895 ("staging: erofs: add compacted compression indexes support") Signed-off-by: Gao Xiang Signed-off-by: Sasha Levin --- fs/erofs/zmap.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 30775502b56da..abf7ddc64c63b 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -10,7 +10,7 @@ struct z_erofs_maprecorder { struct inode *inode; struct erofs_map_blocks *map; - unsigned long lcn; + u64 lcn; /* compression extent information gathered */ u8 type, headtype; u16 clusterofs; @@ -20,8 +20,7 @@ struct z_erofs_maprecorder { bool partialref, in_mbox; }; -static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, - unsigned long lcn) +static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, u64 lcn) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); @@ -94,7 +93,7 @@ static int get_compacted_la_distance(unsigned int lobits, } static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, - unsigned long lcn, bool lookahead) + u64 lcn, bool lookahead) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); @@ -234,7 +233,7 @@ static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, } static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, - unsigned int lcn, bool lookahead) + u64 lcn, bool lookahead) { struct erofs_inode *vi = EROFS_I(m->inode); int err; @@ -249,7 +248,7 @@ static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, return err; if (m->type >= Z_EROFS_LCLUSTER_TYPE_MAX) { - erofs_err(m->inode->i_sb, "unknown type %u @ lcn %u of nid %llu", + erofs_err(m->inode->i_sb, "unknown type %u @ lcn %llu of nid %llu", m->type, lcn, EROFS_I(m->inode)->nid); DBG_BUGON(1); return -EOPNOTSUPP; @@ -269,7 +268,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, const unsigned int lclusterbits = vi->z_lclusterbits; while (m->lcn >= lookback_distance) { - unsigned long lcn = m->lcn - lookback_distance; + u64 lcn = m->lcn - lookback_distance; int err; if (!lookback_distance) @@ -286,7 +285,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, m->map->m_la = (lcn << lclusterbits) | m->clusterofs; return 0; } - erofs_err(sb, "bogus lookback distance %u @ lcn %lu of nid %llu", + erofs_err(sb, "bogus lookback distance %u @ lcn %llu of nid %llu", lookback_distance, m->lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; @@ -300,7 +299,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, struct erofs_inode *vi = EROFS_I(inode); bool bigpcl1 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; bool bigpcl2 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2; - unsigned long lcn = m->lcn + 1; + u64 lcn = m->lcn + 1; int err; DBG_BUGON(m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); @@ -331,7 +330,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD && m->delta[0] != 1) { - erofs_err(sb, "bogus CBLKCNT @ lcn %lu of nid %llu", lcn, vi->nid); + erofs_err(sb, "bogus CBLKCNT @ lcn %llu of nid %llu", lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } From 4a259bb367021df7f1520c80101a14190242aed7 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:05 +0800 Subject: [PATCH 0777/1518] arm64: dts: imx8mp-debix-model-a: Correct PAD settings for PMIC_nINT [ Upstream commit 3b778178997aee24537b521a8cb60970bc1ce01c ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there is interrupt storm for i.MX8MP DEBIX Model A. Per schematic, there is no on board PULL-UP resistors for GPIO1_IO03, so need to set PAD PUE and PU together to make pull up work properly. Fixes: c86d350aae68e ("arm64: dts: Add device tree for the Debix Model A Board") Reported-by: Laurent Pinchart Closes: https://lore.kernel.org/all/20260323105858.GA2185714@killaraus.ideasonboard.com/ Reviewed-by: Laurent Pinchart Tested-by: Laurent Pinchart Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts b/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts index af02af9e5334d..740cac4cb31d9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts @@ -440,7 +440,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From e821e5e0c61b85898c76ebcff51a47ca50a738f4 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:06 +0800 Subject: [PATCH 0778/1518] arm64: dts: imx8mp-debix-som-a: Correct PAD settings for PMIC_nINT [ Upstream commit 2ea7872048a179b0ea8dadc67771961df3f0fc4a ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there is interrupt storm for i.MX8MP DEBIX SOM A. Need to set PAD PUE and PU together to make pull up work properly. Fixes: 21baf0b47f81b ("arm64: dts: freescale: Add DEBIX SOM A and SOM A I/O Board support") Reported-by: Laurent Pinchart Closes: https://lore.kernel.org/all/20260323105858.GA2185714@killaraus.ideasonboard.com/ Reported-by: Kieran Bingham Closes: https://lore.kernel.org/imx/20260324194353.GB2352505@killaraus.ideasonboard.com/T/#m9a07fdc75496369a7d76d52c5e34ed140dcabfe3 Signed-off-by: Peng Fan Reviewed-by: Kieran Bingham Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts | 2 +- arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts index d241db3743a9c..ed89d2ccb6ce2 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a-bmb-08.dts @@ -452,7 +452,7 @@ pinctrl_pmic: pmicgrp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi index 91094c2277443..b31e8fe95ca74 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-som-a.dtsi @@ -241,7 +241,7 @@ pinctrl_pmic: pmicgrp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From 3a958f45a6767ce16e16fed33cfddf3df1e834d4 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:07 +0800 Subject: [PATCH 0779/1518] arm64: dts: imx8mp-navqp: Correct PAD settings for PMIC_nINT [ Upstream commit 741d6ac1a2a2e0f3e2cae5eef3516cdd75119e83 ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there will be interrupt storm for i.MX8MP NAVQP. Per schematic, there is no on board PULL-UP resistors for GPIO1_IO03, so need to set PAD PUE and PU together to make pull up work properly. Fixes: 682729a9d506d ("arm64: dts: freescale: Add device tree for Emcraft Systems NavQ+ Kit") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-navqp.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-navqp.dts b/arch/arm64/boot/dts/freescale/imx8mp-navqp.dts index 4a4f7c1adc23f..9dedb9f11145e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-navqp.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-navqp.dts @@ -356,7 +356,7 @@ pinctrl_pmic: pmicgrp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From 91c150b3760df2b815e83fbb74dd3e5a25aa4cab Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:09 +0800 Subject: [PATCH 0780/1518] arm64: dts: imx8mp-icore-mx8mp: Correct PAD settings for PMIC_nINT [ Upstream commit ea8c90f5c7ceeb6657a8fe564aa7b190dce298a6 ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: eefe06b295087 ("arm64: dts: imx8mp: Add Engicam i.Core MX8M Plus SoM") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-icore-mx8mp.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-icore-mx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-icore-mx8mp.dtsi index a6319824ea2eb..69558ffefa9a6 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-icore-mx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-icore-mx8mp.dtsi @@ -132,7 +132,7 @@ pinctrl_pmic: pmicgrp { fsl,pins = < - MX8MP_IOMUXC_NAND_CE0_B__GPIO3_IO01 0x41 + MX8MP_IOMUXC_NAND_CE0_B__GPIO3_IO01 0x1c0 >; }; From dde47488fb191faf054c6dae4634be689374bdd9 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:10 +0800 Subject: [PATCH 0781/1518] arm64: dts: imx8mp-edm-g: Correct PAD settings for PMIC_nINT [ Upstream commit c46c5a54443440ce0f71de9f4df9dd860f5c2afd ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: 95e882c021c8b ("arm64: dts: imx8mp: Add TechNexion EDM-G-IMX8M-PLUS SOM on WB-EDM-G carrier board") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-edm-g.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-edm-g.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-edm-g.dtsi index 3f1e0837f349f..91b87a7248dd1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-edm-g.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-edm-g.dtsi @@ -563,7 +563,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From 9011a6128935b19e2a038694adbb00a97bae5090 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:11 +0800 Subject: [PATCH 0782/1518] arm64: dts: imx8mp-aristainetos3a-som-v1: Correct PAD settings for PMIC_nINT [ Upstream commit e6d2d8e49ca34bb39126a69128794d08ffd7c83e ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: eead8f3536d5c ("arm64: dts: imx8mp: add aristainetos3 board support") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi index f654d866e58c0..e7666e54310be 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-aristainetos3a-som-v1.dtsi @@ -903,7 +903,7 @@ pinctrl_pmic: aristainetos3-pmic-grp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From 4ff0003fabd7cfd557005cefb86196f4373ad432 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:12 +0800 Subject: [PATCH 0783/1518] arm64: dts: imx8mp-nitrogen-som: Correct PAD settings for PMIC_nINT [ Upstream commit 16611eda2c7584a1a7d6f80511d825e5108f026c ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: ab4d874c9f44e ("arm64: dts: imx8mp: Add device tree for Nitrogen8M Plus ENC Carrier Board") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-nitrogen-som.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-nitrogen-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-nitrogen-som.dtsi index f658309612eff..8465b36d440ae 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-nitrogen-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-nitrogen-som.dtsi @@ -296,7 +296,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MP_IOMUXC_NAND_ALE__GPIO3_IO00 0x41 + MX8MP_IOMUXC_NAND_ALE__GPIO3_IO00 0x1c0 >; }; From e754961b2655e843ba6939a8a5071513b7bd5098 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:13 +0800 Subject: [PATCH 0784/1518] arm64: dts: imx8mp-sr-som: Correct PAD settings for PMIC_nINT [ Upstream commit 695a476275cfb9c798a696aeaa43967701d5c78a ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: a009c0c66ecb4 ("arm64: dts: add description for solidrun imx8mp som and cubox-m") Signed-off-by: Peng Fan Reviewed-by: Josua Mayer Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-sr-som.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-sr-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-sr-som.dtsi index 4e6629f940bfa..82a3ed80235a8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-sr-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-sr-som.dtsi @@ -174,7 +174,7 @@ pinctrl-0 = <&pmic_pins>; pinctrl-names = "default"; interrupt-parent = <&gpio1>; - interrupts = <3 GPIO_ACTIVE_LOW>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; nxp,i2c-lt-enable; regulators { @@ -417,7 +417,7 @@ pmic_pins: pinctrl-pmic-grp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x41 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From d8d75e1135329908a1a1254d0efba3471b624619 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:14 +0800 Subject: [PATCH 0785/1518] arm64: dts: imx8mp-ultra-mach-sbc: Correct PAD settings for PMIC_nINT [ Upstream commit daaf41ee72fb5fad936e7051a015cccae9b33937 ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: d1c1400bd3b8b ("arm64: dts: imx8mp: Add initial support for Ultratronik imx8mp-ultra-mach-sbc board") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-ultra-mach-sbc.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-ultra-mach-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-ultra-mach-sbc.dts index 9ecec1a418781..3e6f9c88cc200 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-ultra-mach-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-ultra-mach-sbc.dts @@ -275,7 +275,7 @@ reg = <0x25>; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; - interrupts = <3 GPIO_ACTIVE_LOW>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; /* * i.MX 8M Plus Data Sheet for Consumer Products @@ -739,7 +739,7 @@ pinctrl_pmic: pmic-grp { fsl,pins = < - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x40 /* #PMIC_INT */ + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 /* #PMIC_INT */ >; }; From 2b7db3e83f78f96c87718f8d3a6a76256a9dd6c8 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:15 +0800 Subject: [PATCH 0786/1518] arm64: dts: imx8mp-dhcom-som: Correct PAD settings for PMIC_nINT [ Upstream commit f9ed5afc988da3e22543725e35be6addbb0497bc ] PMIC_nINT is low level triggered, but the current PAD settings is PE=0,PUE=0,FSEL_1_FAST_SLEW_RATE=1,SION=1. So PAD needs to be configured as PULL UP with PULL Enable, no need SION. Correct it. Fixes: 8d6712695bc8e ("arm64: dts: imx8mp: Add support for DH electronics i.MX8M Plus DHCOM and PDK2") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index f8303b7e2bd22..0a6a60670f762 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -989,7 +989,7 @@ pinctrl_pmic: dhcom-pmic-grp { fsl,pins = < /* PMIC_nINT */ - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x40000090 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From 9e8087ac4636066578ded9e8aa52c310f9d58147 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 26 Mar 2026 15:28:16 +0800 Subject: [PATCH 0787/1518] arm64: dts: imx8mp-data-modul-edm-sbc: Correct PAD settings for PMIC_nINT [ Upstream commit 8ff145577e93f312ff398cb950ee3bd44835f5be ] PMIC_nINT is low level triggered, but the current PAD settings is PE=0,PUE=0,FSEL_1_FAST_SLEW_RATE=1,SION=1. So PAD needs to be configured as PULL UP with PULL Enable, no need SION. Correct it. Fixes: 562d222f23f0f ("arm64: dts: imx8mp: Add support for Data Modul i.MX8M Plus eDM SBC") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts index 16078ff60ef08..fa13662ca3667 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts @@ -900,7 +900,7 @@ pinctrl_pmic: pmic-grp { fsl,pins = < /* PMIC_nINT */ - MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x40000090 + MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03 0x1c0 >; }; From 4790bd29d626b052373f462f166fffb8e4c9cbad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Rebe?= Date: Wed, 26 Nov 2025 17:42:56 +0100 Subject: [PATCH 0788/1518] PCMCIA: Fix garbled log messages for KERN_CONT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit bfeaa6814bd3f9a1f6d525b3b35a03b9a0368961 ] For years the PCMCIA info messages are messed up by superfluous newlines. While f2e6cf76751d ("pcmcia: Convert dev_printk to dev_") converted the code to pr_cont(), dev_info enforces a \n via vprintk_store setting LOG_NEWLINE, breaking subsequent pr_cont. Fix by logging the device name manually to allow pr_cont to work for more readable and not \n distorted logs. Fixes: f2e6cf76751d ("pcmcia: Convert dev_printk to dev_") Signed-off-by: René Rebe Signed-off-by: Dominik Brodowski Signed-off-by: Sasha Levin --- drivers/pcmcia/rsrc_nonstatic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c index da494fe451baf..efc439c748862 100644 --- a/drivers/pcmcia/rsrc_nonstatic.c +++ b/drivers/pcmcia/rsrc_nonstatic.c @@ -188,7 +188,7 @@ static void do_io_probe(struct pcmcia_socket *s, unsigned int base, int any; u_char *b, hole, most; - dev_info(&s->dev, "cs: IO port probe %#x-%#x:", base, base+num-1); + pr_info("%s: cs: IO port probe %#x-%#x:", dev_name(&s->dev), base, base+num-1); /* First, what does a floating port look like? */ b = kzalloc(256, GFP_KERNEL); @@ -410,8 +410,8 @@ static int do_mem_probe(struct pcmcia_socket *s, u_long base, u_long num, struct socket_data *s_data = s->resource_data; u_long i, j, bad, fail, step; - dev_info(&s->dev, "cs: memory probe 0x%06lx-0x%06lx:", - base, base+num-1); + pr_info("%s: cs: memory probe 0x%06lx-0x%06lx:", + dev_name(&s->dev), base, base+num-1); bad = fail = 0; step = (num < 0x20000) ? 0x2000 : ((num>>4) & ~0x1fff); /* don't allow too large steps */ From cde69482d2e6834dcd4ed675d1ef84e48627ee9f Mon Sep 17 00:00:00 2001 From: Ronald Claveau Date: Tue, 31 Mar 2026 16:24:04 +0200 Subject: [PATCH 0789/1518] reset: amlogic: t7: Fix null reset ops [ Upstream commit 9797524ef2b69c6b187b55bd844eb72a8c1cbd99 ] Fix missing reset ops causing kernel null pointer dereference. This SOC's reset is currently not used yet. Signed-off-by: Ronald Claveau Fixes: fb4c31587adf ("reset: amlogic: add auxiliary reset driver support") Reviewed-by: Philipp Zabel Signed-off-by: Philipp Zabel Signed-off-by: Sasha Levin --- drivers/reset/amlogic/reset-meson.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/reset/amlogic/reset-meson.c b/drivers/reset/amlogic/reset-meson.c index 84610365a823c..c303e8590dd68 100644 --- a/drivers/reset/amlogic/reset-meson.c +++ b/drivers/reset/amlogic/reset-meson.c @@ -42,6 +42,7 @@ static const struct meson_reset_param meson_s4_param = { }; static const struct meson_reset_param t7_param = { + .reset_ops = &meson_reset_ops, .reset_num = 224, .reset_offset = 0x0, .level_offset = 0x40, From 33d043815ccc7588b7c07d82bb4a7415a350ddc5 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 29 Mar 2026 21:00:11 +0800 Subject: [PATCH 0790/1518] arm64: dts: imx8mm-emtop-som: Correct PAD settings for PMIC_nINT [ Upstream commit 721dec3ee9ff5231d13a412ff87df63b966d137b ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. While at here, also correct interrupt type as IRQ_TYPE_LEVEL_LOW. Fixes: cbd3ef64eb9d1 ("arm64: dts: Add support for Emtop SoM & Baseboard") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-emtop-som.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-emtop-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-emtop-som.dtsi index 67d22d3768aa8..507d1824d99d9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-emtop-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-emtop-som.dtsi @@ -60,7 +60,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; - interrupts = <3 IRQ_TYPE_EDGE_RISING>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; regulators { buck1: BUCK1 { @@ -194,7 +194,7 @@ pinctrl_pmic: emtop-pmic-grp { fsl,pins = < - MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3 0x41 + MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3 0x141 >; }; From 8002eb9b60a60451568988352df34f4aef3cef95 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 29 Mar 2026 21:00:12 +0800 Subject: [PATCH 0791/1518] arm64: dts: imx8mn-tqma8mqnl: Correct PAD settings for PMIC_nINT [ Upstream commit 0fb37990774113afd943eaa91323679388584b6d ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: 3e56e354db6d3 ("arm64: dts: freescale: add initial device tree for TQMa8MQNL with i.MX8MN") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi index e2ccebf6ee13f..5e2c6d6e94550 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi @@ -298,7 +298,7 @@ }; pinctrl_pmic: pmicgrp { - fsl,pins = ; + fsl,pins = ; }; pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp { From 5b5f8ff0a2e8fd366f24f9c10850732d0b420198 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 29 Mar 2026 21:00:13 +0800 Subject: [PATCH 0792/1518] arm64: dts: imx8mm-tqma8mqml: Correct PAD settings for PMIC_nINT [ Upstream commit 42a9f5a16328ed78a88e0498556965b6c6ec515c ] With commit 5d0efaf47ee90 ("regulator: pca9450: Correct interrupt type"), there might be interrupt storm for this board. Need to set PAD PUE and PU together to make pull up work properly. Fixes: dfcd1b6f7620e ("arm64: dts: freescale: add initial device tree for TQMa8MQML with i.MX8MM") Signed-off-by: Peng Fan Signed-off-by: Frank Li Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi index b82e9790ea205..a0e8b158c4edf 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi @@ -291,7 +291,7 @@ }; pinctrl_pmic: pmicgrp { - fsl,pins = ; + fsl,pins = ; }; pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp { From ad5dc433b34e7d8c33b35fdc0e4ad60080d4b59b Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Mon, 30 Mar 2026 17:25:16 +0200 Subject: [PATCH 0793/1518] arm64: dts: marvell: armada-37xx: use 'usb2-phy' in USB3 controller's phy-names [ Upstream commit 0fef19844624f8bc07651b4d26088d8940affba3 ] Instead of the generic 'usb2-phy' name, the Armada 37xx device trees are using a custom 'usb2-utmi-otg-phy' name for the USB2 PHY in the USB3 controller node. Since commit 53a2d95df836 ("usb: core: add phy notify connect and disconnect"), this triggers a bug [1] in the USB core which causes double use of the USB3 PHY. Change the PHY name to 'usb2-phy' in the SoC and in the uDPU specific dtsi files in order to avoid triggering the bug and also to keep the names in line with the ones used by other platforms. Link: https://lore.kernel.org/r/20260330-usb-avoid-usb3-phy-double-use-v1-1-d2113aecb535@gmail.com # [1] Fixes: 53a2d95df836 ("usb: core: add phy notify connect and disconnect") Signed-off-by: Gabor Juhos Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi | 2 +- arch/arm64/boot/dts/marvell/armada-37xx.dtsi | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi index cd856c0aba71e..12deacb741ccb 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi @@ -161,7 +161,7 @@ &usb3 { status = "okay"; phys = <&usb2_utmi_otg_phy>; - phy-names = "usb2-utmi-otg-phy"; + phy-names = "usb2-phy"; }; &uart0 { diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index c612317043ea7..a66157cb439b4 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -373,7 +373,7 @@ interrupts = ; clocks = <&sb_periph_clk 12>; phys = <&comphy0 0>, <&usb2_utmi_otg_phy>; - phy-names = "usb3-phy", "usb2-utmi-otg-phy"; + phy-names = "usb3-phy", "usb2-phy"; status = "disabled"; }; From 7b5501a62214e76ec5fbdb4dce324e1271dc46d2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 15 Apr 2026 16:50:12 +0200 Subject: [PATCH 0794/1518] pwm: stm32: Fix rounding issue for requests with inverted polarity MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5d087c485b6ecf200a9ebb2a032bf8571d330250 ] The calculation of the number of pwm clk ticks from a time length in nanoseconds involves a division and thus some rounding. That might result in duty_ticks + offset_ticks < period_ticks despite duty_length_ns + duty_offset_ns >= period_length_ns . The stm32 PWM cannot configure offset_ticks freely, it can only select 0 or period_length_ns - duty_length_ns---that is the classic normal and inverted polarity. The decision to select the hardware polarity must be done using the ticks values and not the nanoseconds times to adhere to the rounding rules by the pwm core. With the pwm clk running at 208900 kHz on my test machine (stm32mp135f-dk), a test case that was handled wrong is: # pwmround -P 9999962 -O 24970 -D 9974992 period_length = 9999962 duty_length = 9974840 duty_offset = 25123 With this change applied the rounding is done correctly: # pwmround -P 9999962 -O 24970 -D 9974992 period_length = 9999962 duty_length = 9974840 duty_offset = 0 Fixes: deaba9cff809 ("pwm: stm32: Implementation of the waveform callbacks") Signed-off-by: Uwe Kleine-König Link: https://patch.msgid.link/c5e7767cee821b5f6e00f95bd14a5e13015646fb.1776264104.git.u.kleine-koenig@baylibre.com Signed-off-by: Uwe Kleine-König Signed-off-by: Sasha Levin --- drivers/pwm/pwm-stm32.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index 2594fb771b04a..935257a890b06 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -68,7 +68,7 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip, struct stm32_pwm *priv = to_stm32_pwm_dev(chip); unsigned int ch = pwm->hwpwm; unsigned long rate; - u64 ccr, duty; + u64 duty_ticks, offset_ticks; int ret; if (wf->period_length_ns == 0) { @@ -164,23 +164,25 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip, wfhw->arr = min_t(u64, arr, priv->max_arr) - 1; } - duty = mul_u64_u64_div_u64(wf->duty_length_ns, rate, - (u64)NSEC_PER_SEC * (wfhw->psc + 1)); - duty = min_t(u64, duty, wfhw->arr + 1); + duty_ticks = mul_u64_u64_div_u64(wf->duty_length_ns, rate, + (u64)NSEC_PER_SEC * (wfhw->psc + 1)); + duty_ticks = min_t(u64, duty_ticks, wfhw->arr + 1); - if (wf->duty_length_ns && wf->duty_offset_ns && - wf->duty_length_ns + wf->duty_offset_ns >= wf->period_length_ns) { + offset_ticks = mul_u64_u64_div_u64(wf->duty_offset_ns, rate, + (u64)NSEC_PER_SEC * (wfhw->psc + 1)); + offset_ticks = min_t(u64, offset_ticks, wfhw->arr + 1); + + if (duty_ticks && offset_ticks && + duty_ticks + offset_ticks >= wfhw->arr + 1) { wfhw->ccer |= TIM_CCER_CCxP(ch + 1); if (priv->have_complementary_output) wfhw->ccer |= TIM_CCER_CCxNP(ch + 1); - ccr = wfhw->arr + 1 - duty; + wfhw->ccr = wfhw->arr + 1 - duty_ticks; } else { - ccr = duty; + wfhw->ccr = duty_ticks; } - wfhw->ccr = min_t(u64, ccr, wfhw->arr + 1); - out: dev_dbg(&chip->dev, "pwm#%u: %lld/%lld [+%lld] @%lu -> CCER: %08x, PSC: %08x, ARR: %08x, CCR: %08x\n", pwm->hwpwm, wf->duty_length_ns, wf->period_length_ns, wf->duty_offset_ns, From 7db3e4e03032261b1b519341123fc30d995478ca Mon Sep 17 00:00:00 2001 From: Dudu Lu Date: Mon, 13 Apr 2026 16:49:27 +0800 Subject: [PATCH 0795/1518] net/sched: act_mirred: fix wrong device for mac_header_xmit check in tcf_blockcast_redir MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4510d140524ca7d6e772db962e013f26f09a63b1 ] In tcf_blockcast_redir(), when iterating block ports to redirect packets to multiple devices, the mac_header_xmit flag is queried from the wrong device. The loop sends to dev_prev but queries dev_is_mac_header_xmit(dev) — which is the NEXT device in the iteration, not the one being sent to. This causes tcf_mirred_to_dev() to make incorrect decisions about whether to push or pull the MAC header. When the block contains mixed device types (e.g., an ethernet veth and a tunnel device), intermediate devices get the wrong mac_header_xmit flag, leading to skb header corruption. In the worst case, skb_push_rcsum with an incorrect mac_len can exhaust headroom and panic. The last device in the loop is handled correctly (line 365-366 uses dev_is_mac_header_xmit(dev_prev)), confirming this is a copy-paste oversight for the intermediate devices. Fix by using dev_prev instead of dev for the mac_header_xmit query, consistent with the device actually being sent to. Fixes: 42f39036cda8 ("net/sched: act_mirred: Allow mirred to block") Signed-off-by: Dudu Lu Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260413084927.71353-1-phx0fer@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/act_mirred.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 5f01f567c934d..18d9378a9c113 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -370,7 +370,7 @@ static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, goto assign_prev; tcf_mirred_to_dev(skb, m, dev_prev, - dev_is_mac_header_xmit(dev), + dev_is_mac_header_xmit(dev_prev), mirred_eaction, retval); assign_prev: dev_prev = dev; From b6b7154e9f5d75b608ceb2d05b376de8c638c40e Mon Sep 17 00:00:00 2001 From: Dudu Lu Date: Mon, 13 Apr 2026 16:53:49 +0800 Subject: [PATCH 0796/1518] macvlan: fix macvlan_get_size() not reserving space for IFLA_MACVLAN_BC_CUTOFF [ Upstream commit fa92a77b0ed4d5f11a71665a232ac5a54a4b055d ] macvlan_get_size() does not account for IFLA_MACVLAN_BC_CUTOFF, but macvlan_fill_info() conditionally includes it when port->bc_cutoff != 1. This causes nla_put_s32() to fail with -EMSGSIZE when the netlink skb runs out of space, triggering a WARN_ON in rtnetlink and preventing the interface from being dumped. The bug can be reproduced with: ip link add macvlan0 link eth0 type macvlan mode bridge ip link set macvlan0 type macvlan bc_cutoff 0 ip -d link show macvlan0 # fails with -EMSGSIZE The bc_cutoff feature was added in commit 954d1fa1ac93 ("macvlan: Add netlink attribute for broadcast cutoff"), which added the nla_put_s32() call in macvlan_fill_info() but missed adding the corresponding nla_total_size(4) in macvlan_get_size(). A follow-up commit 55cef78c244d ("macvlan: add forgotten nla_policy for IFLA_MACVLAN_BC_CUTOFF") fixed the missing nla_policy entry but still did not fix the size calculation. Fixes: 954d1fa1ac93 ("macvlan: Add netlink attribute for broadcast cutoff") Signed-off-by: Dudu Lu Reviewed-by: Vadim Fedorenko Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260413085349.73977-1-phx0fer@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/macvlan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index e9d288a05e39e..35dcaa985cfdc 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1682,6 +1682,7 @@ static size_t macvlan_get_size(const struct net_device *dev) + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */ + + nla_total_size(4) /* IFLA_MACVLAN_BC_CUTOFF */ ); } From 7ad66185052d9de36ad2dd299bb3473aa34edc9c Mon Sep 17 00:00:00 2001 From: Dudu Lu Date: Mon, 13 Apr 2026 19:00:41 +0800 Subject: [PATCH 0797/1518] net/sched: sch_cake: fix NAT destination port not being updated in cake_update_flowkeys MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f9e40664706927d7ae22a448a3383e23c38a4c0b ] cake_update_flowkeys() is supposed to update the flow dissector keys with the NAT-translated addresses and ports from conntrack, so that CAKE's per-flow fairness correctly identifies post-NAT flows as belonging to the same connection. For the source port, this works correctly: keys->ports.src = port; But for the destination port, the assignment is reversed: port = keys->ports.dst; This means the NAT destination port is never updated in the flow keys. As a result, when multiple connections are NATed to the same destination, CAKE treats them as separate flows because the original (pre-NAT) destination ports differ. This breaks CAKE's NAT-aware flow isolation when using the "nat" mode. The bug was introduced in commit b0c19ed6088a ("sch_cake: Take advantage of skb->hash where appropriate") which refactored the original direct assignment into a compare-and-conditionally-update pattern, but wrote the destination port update backwards. Fix by reversing the assignment direction to match the source port pattern. Fixes: b0c19ed6088a ("sch_cake: Take advantage of skb->hash where appropriate") Signed-off-by: Dudu Lu Acked-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20260413110041.44704-1-phx0fer@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_cake.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index d325a90cde9ee..1a2023cd55109 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -606,7 +606,7 @@ static bool cake_update_flowkeys(struct flow_keys *keys, } port = rev ? tuple.src.u.all : tuple.dst.u.all; if (port != keys->ports.dst) { - port = keys->ports.dst; + keys->ports.dst = port; upd = true; } } From 613c8f4a501421dd258b07ea614205d4e16ec845 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Mon, 13 Apr 2026 19:45:19 +0800 Subject: [PATCH 0798/1518] nexthop: fix IPv6 route referencing IPv4 nexthop [ Upstream commit 29c95185ba32b621fbc3800fb86e7dc3edf5c2be ] syzbot reported a panic [1] [2]. When an IPv6 nexthop is replaced with an IPv4 nexthop, the has_v4 flag of all groups containing this nexthop is not updated. This is because nh_group_v4_update is only called when replacing AF_INET to AF_INET6, but the reverse direction (AF_INET6 to AF_INET) is missed. This allows a stale has_v4=false to bypass fib6_check_nexthop, causing IPv6 routes to be attached to groups that effectively contain only AF_INET members. Subsequent route lookups then call nexthop_fib6_nh() which returns NULL for the AF_INET member, leading to a NULL pointer dereference. Fix by calling nh_group_v4_update whenever the family changes, not just AF_INET to AF_INET6. Reproducer: # AF_INET6 blackhole ip -6 nexthop add id 1 blackhole # group with has_v4=false ip nexthop add id 100 group 1 # replace with AF_INET (no -6), has_v4 stays false ip nexthop replace id 1 blackhole # pass stale has_v4 check ip -6 route add 2001:db8::/64 nhid 100 # panic ping -6 2001:db8::1 [1] https://syzkaller.appspot.com/bug?id=e17283eb2f8dcf3dd9b47fe6f67a95f71faadad0 [2] https://syzkaller.appspot.com/bug?id=8699b6ae54c9f35837d925686208402949e12ef3 Fixes: 7bf4796dd099 ("nexthops: add support for replace") Signed-off-by: Jiayuan Chen Reviewed-by: David Ahern Link: https://patch.msgid.link/20260413114522.147784-1-jiayuan.chen@linux.dev Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv4/nexthop.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index c958b8edfe540..5a95b64b61c59 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2469,10 +2469,10 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, goto err_notify; } - /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially + /* When replacing a nexthop with one of a different family, potentially * update IPv4 indication in all the groups using the nexthop. */ - if (oldi->family == AF_INET && newi->family == AF_INET6) { + if (oldi->family != newi->family) { list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; struct nh_group *nhg; From 75b6c361f41707b4fec21347d914353be9ceb9cc Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Apr 2026 16:08:52 +0200 Subject: [PATCH 0799/1518] net: airoha: Wait for NPU PPE configuration to complete in airoha_ppe_offload_setup() [ Upstream commit f3206328bb52c2787197d80d7cbd687946047d5f ] In order to properly enable flowtable hw offloading, poll REG_PPE_FLOW_CFG register in airoha_ppe_offload_setup routine and wait for NPU PPE configuration triggered by ppe_init callback to complete before running airoha_ppe_hw_init(). Fixes: 00a7678310fe3 ("net: airoha: Introduce flowtable offload support") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260414-airoha-wait-for-npu-config-offload-setup-v2-1-5a9bf6d43aee@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_ppe.c | 28 ++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 81a7056e3510a..e9994c794c703 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -1321,6 +1321,29 @@ static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth) return npu; } +static int airoha_ppe_wait_for_npu_init(struct airoha_eth *eth) +{ + int err; + u32 val; + + /* PPE_FLOW_CFG default register value is 0. Since we reset FE + * during the device probe we can just check the configured value + * is not 0 here. + */ + err = read_poll_timeout(airoha_fe_rr, val, val, USEC_PER_MSEC, + 100 * USEC_PER_MSEC, false, eth, + REG_PPE_PPE_FLOW_CFG(0)); + if (err) + return err; + + if (airoha_ppe_is_enabled(eth, 1)) + err = read_poll_timeout(airoha_fe_rr, val, val, USEC_PER_MSEC, + 100 * USEC_PER_MSEC, false, eth, + REG_PPE_PPE_FLOW_CFG(1)); + + return err; +} + static int airoha_ppe_offload_setup(struct airoha_eth *eth) { struct airoha_npu *npu = airoha_ppe_npu_get(eth); @@ -1334,6 +1357,11 @@ static int airoha_ppe_offload_setup(struct airoha_eth *eth) if (err) goto error_npu_put; + /* Wait for NPU PPE configuration to complete */ + err = airoha_ppe_wait_for_npu_init(eth); + if (err) + goto error_npu_put; + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); if (ppe_num_stats_entries > 0) { err = npu->ops.ppe_init_stats(npu, ppe->foe_stats_dma, From b73235da5dde77ed1264f9767b62c28c9d71fd78 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Fri, 10 Apr 2026 18:57:57 -0700 Subject: [PATCH 0800/1518] net/sched: taprio: fix use-after-free in advance_sched() on schedule switch [ Upstream commit 105425b1969c5affe532713cfac1c0b320d7ac2b ] In advance_sched(), when should_change_schedules() returns true, switch_schedules() is called to promote the admin schedule to oper. switch_schedules() queues the old oper schedule for RCU freeing via call_rcu(), but 'next' still points into an entry of the old oper schedule. The subsequent 'next->end_time = end_time' and rcu_assign_pointer(q->current_entry, next) are use-after-free. Fix this by selecting 'next' from the new oper schedule immediately after switch_schedules(), and using its pre-calculated end_time. setup_first_end_time() sets the first entry's end_time to base_time + interval when the schedule is installed, so the value is already correct. The deleted 'end_time = sched_base_time(admin)' assignment was also harmful independently: it would overwrite the new first entry's pre-calculated end_time with just base_time. Fixes: a3d43c0d56f1 ("taprio: Add support adding an admin schedule") Reported-by: Junxi Qian Signed-off-by: Vinicius Costa Gomes Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_taprio.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 39b735386996e..91b85360f8091 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -971,11 +971,12 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) } if (should_change_schedules(admin, oper, end_time)) { - /* Set things so the next time this runs, the new - * schedule runs. - */ - end_time = sched_base_time(admin); switch_schedules(q, &admin, &oper); + /* After changing schedules, the next entry is the first one + * in the new schedule, with a pre-calculated end_time. + */ + next = list_first_entry(&oper->entries, struct sched_entry, list); + end_time = next->end_time; } next->end_time = end_time; From f128f04a893da87e4616af3a75ebbb3855b06cf2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 22 Nov 2025 13:23:09 +0200 Subject: [PATCH 0801/1518] net: dsa: cpu_dp->orig_ethtool_ops might be NULL [ Upstream commit eba81b0a6de39e2466d37e410003642282b4e546 ] In theory this would have been seen by now, but it seems that all drivers used as DSA conduit interfaces thus far have had ethtool_ops set, and it's hard to even find modern Ethernet drivers (and not VF ones) which don't use ethtool. Here is the unfiltered list of drivers which register any sort of net_device but don't set its ethtool_ops pointer. I don't think any of them 'risks' being used as a DSA conduit, maybe except for moxart, rnpbge and icssm, I'm not sure. - drivers/net/can/dev/dev.c - drivers/net/wwan/qcom_bam_dmux.c - drivers/net/wwan/t7xx/t7xx_netdev.c - drivers/net/arcnet/arcnet.c - drivers/net/hamradio/ - drivers/net/slip/slip.c - drivers/net/ethernet/ezchip/nps_enet.c - drivers/net/ethernet/moxa/moxart_ether.c - drivers/net/ethernet/wangxun/txgbevf/txgbevf_main.c - drivers/net/ethernet/wangxun/ngbevf/ngbevf_main.c - drivers/net/ethernet/huawei/hinic3/hinic3_main.c - drivers/net/ethernet/i825xx/ - drivers/net/ethernet/ti/icssm/icssm_prueth.c - drivers/net/ethernet/seeq/ - drivers/net/ethernet/litex/litex_liteeth.c - drivers/net/ethernet/sunplus/spl2sw_driver.c - drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c - drivers/net/ipa/ - drivers/net/wireless/microchip/wilc1000/ - drivers/net/wireless/mediatek/mt76/dma.c - drivers/net/wireless/ath/ath12k/ - drivers/net/wireless/ath/ath11k/ - drivers/net/wireless/ath/ath6kl/ - drivers/net/wireless/ath/ath10k/ - drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans.c - drivers/net/wireless/virtual/mac80211_hwsim.c - drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c - drivers/net/wireless/realtek/rtw89/core.c - drivers/net/wireless/realtek/rtw88/pci.c - drivers/net/caif/ - drivers/net/plip/ - drivers/net/wan/ - drivers/net/mctp/ - drivers/net/ppp/ - drivers/net/thunderbolt/ Nonetheless, it's good for the framework not to make such assumptions, and not panic when coming across such kind of host device in the future. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20251122112311.138784-2-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Stable-dep-of: 0f99e0c3e19b ("net: dsa: remove redundant netdev_lock_ops() from conduit ethtool ops") Signed-off-by: Sasha Levin --- net/dsa/conduit.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c index 4ae255cfb23f8..f80795b3d0460 100644 --- a/net/dsa/conduit.c +++ b/net/dsa/conduit.c @@ -26,7 +26,7 @@ static int dsa_conduit_get_regs_len(struct net_device *dev) int ret = 0; int len; - if (ops->get_regs_len) { + if (ops && ops->get_regs_len) { netdev_lock_ops(dev); len = ops->get_regs_len(dev); netdev_unlock_ops(dev); @@ -59,7 +59,7 @@ static void dsa_conduit_get_regs(struct net_device *dev, int port = cpu_dp->index; int len; - if (ops->get_regs_len && ops->get_regs) { + if (ops && ops->get_regs_len && ops->get_regs) { netdev_lock_ops(dev); len = ops->get_regs_len(dev); if (len < 0) { @@ -97,7 +97,7 @@ static void dsa_conduit_get_ethtool_stats(struct net_device *dev, int port = cpu_dp->index; int count = 0; - if (ops->get_sset_count && ops->get_ethtool_stats) { + if (ops && ops->get_sset_count && ops->get_ethtool_stats) { netdev_lock_ops(dev); count = ops->get_sset_count(dev, ETH_SS_STATS); ops->get_ethtool_stats(dev, stats, data); @@ -118,11 +118,11 @@ static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, int port = cpu_dp->index; int count = 0; - if (dev->phydev && !ops->get_ethtool_phy_stats) { + if (dev->phydev && (!ops || !ops->get_ethtool_phy_stats)) { count = phy_ethtool_get_sset_count(dev->phydev); if (count >= 0) phy_ethtool_get_stats(dev->phydev, stats, data); - } else if (ops->get_sset_count && ops->get_ethtool_phy_stats) { + } else if (ops && ops->get_sset_count && ops->get_ethtool_phy_stats) { netdev_lock_ops(dev); count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); ops->get_ethtool_phy_stats(dev, stats, data); @@ -145,9 +145,9 @@ static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) netdev_lock_ops(dev); if (sset == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) + (!ops || !ops->get_ethtool_phy_stats)) count = phy_ethtool_get_sset_count(dev->phydev); - else if (ops->get_sset_count) + else if (ops && ops->get_sset_count) count = ops->get_sset_count(dev, sset); netdev_unlock_ops(dev); From 87bbc2e86439495f89017f4381d82e1d679505a3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 22 Nov 2025 13:23:10 +0200 Subject: [PATCH 0802/1518] net: dsa: use kernel data types for ethtool ops on conduit [ Upstream commit 8afabd27fe46ebf991b4aea20b74e08196c15c0c ] Suppress some checkpatch 'CHECK' messages about u8 being preferable over uint8_t, etc. No functional change. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20251122112311.138784-3-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Stable-dep-of: 0f99e0c3e19b ("net: dsa: remove redundant netdev_lock_ops() from conduit ethtool ops") Signed-off-by: Sasha Levin --- net/dsa/conduit.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c index f80795b3d0460..c210e31296558 100644 --- a/net/dsa/conduit.c +++ b/net/dsa/conduit.c @@ -89,7 +89,7 @@ static void dsa_conduit_get_regs(struct net_device *dev, static void dsa_conduit_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, - uint64_t *data) + u64 *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -110,7 +110,7 @@ static void dsa_conduit_get_ethtool_stats(struct net_device *dev, static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, struct ethtool_stats *stats, - uint64_t *data) + u64 *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -160,8 +160,8 @@ static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) return count; } -static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset, - uint8_t *data) +static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, + u8 *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -169,8 +169,7 @@ static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset, int port = cpu_dp->index; int len = ETH_GSTRING_LEN; int mcount = 0, count, i; - uint8_t pfx[4]; - uint8_t *ndata; + u8 pfx[4], *ndata; snprintf(pfx, sizeof(pfx), "p%.2d", port); /* We do not want to be NULL-terminated, since this is a prefix */ From 4c078a699a8c1e730d3c486381e11690fc2427c5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 22 Nov 2025 13:23:11 +0200 Subject: [PATCH 0803/1518] net: dsa: append ethtool counters of all hidden ports to conduit [ Upstream commit f647ed2ca78ec4efcc436915b441da9de0974926 ] Currently there is no way to see packet counters on cascade ports, and no clarity on how the API for that would look like. Because it's something that is currently needed, just extend the hack where ethtool -S on the conduit interface dumps CPU port counters, and also use it to dump counters of cascade ports. Note that the "pXX_" naming convention changes to "sXX_pYY", to distinguish between ports having the same index but belonging to different switches. This has a slight chance of causing regressions to existing tooling: - grepping for "p04_counter_name" still works, but might return more than one string now - grepping for " p04_counter_name" no longer works Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20251122112311.138784-4-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Stable-dep-of: 0f99e0c3e19b ("net: dsa: remove redundant netdev_lock_ops() from conduit ethtool ops") Signed-off-by: Sasha Levin --- net/dsa/conduit.c | 126 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 93 insertions(+), 33 deletions(-) diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c index c210e31296558..a1b044467bd6f 100644 --- a/net/dsa/conduit.c +++ b/net/dsa/conduit.c @@ -87,25 +87,51 @@ static void dsa_conduit_get_regs(struct net_device *dev, } } +static ssize_t dsa_conduit_append_port_stats(struct dsa_switch *ds, int port, + u64 *data, size_t start) +{ + int count; + + if (!ds->ops->get_sset_count) + return 0; + + count = ds->ops->get_sset_count(ds, port, ETH_SS_STATS); + if (count < 0) + return count; + + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, port, data + start); + + return count; +} + static void dsa_conduit_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { - struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; - int count = 0; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count, mcount = 0; if (ops && ops->get_sset_count && ops->get_ethtool_stats) { netdev_lock_ops(dev); - count = ops->get_sset_count(dev, ETH_SS_STATS); + mcount = ops->get_sset_count(dev, ETH_SS_STATS); ops->get_ethtool_stats(dev, stats, data); netdev_unlock_ops(dev); } - if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, port, data + count); + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + count = dsa_conduit_append_port_stats(dp->ds, dp->index, + data, mcount); + if (count < 0) + return; + + mcount += count; + } } static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, @@ -136,11 +162,18 @@ static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, ds->ops->get_ethtool_phy_stats(ds, port, data + count); } +static void dsa_conduit_append_port_sset_count(struct dsa_switch *ds, int port, + int sset, int *count) +{ + if (ds->ops->get_sset_count) + *count += ds->ops->get_sset_count(ds, port, sset); +} + static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) { - struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; + struct dsa_switch_tree *dst = cpu_dp->dst; int count = 0; netdev_lock_ops(dev); @@ -154,26 +187,57 @@ static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) if (count < 0) count = 0; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, cpu_dp->index, sset); + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + dsa_conduit_append_port_sset_count(dp->ds, dp->index, sset, + &count); + } return count; } -static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, - u8 *data) +static ssize_t dsa_conduit_append_port_strings(struct dsa_switch *ds, int port, + u32 stringset, u8 *data, + size_t start) { - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; int len = ETH_GSTRING_LEN; - int mcount = 0, count, i; - u8 pfx[4], *ndata; + u8 pfx[8], *ndata; + int count, i; + + if (!ds->ops->get_strings) + return 0; - snprintf(pfx, sizeof(pfx), "p%.2d", port); + snprintf(pfx, sizeof(pfx), "s%.2d_p%.2d", ds->index, port); /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; + ndata = data + start * len; + /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle + * the output after to prepend our CPU port prefix we + * constructed earlier + */ + ds->ops->get_strings(ds, port, stringset, ndata); + count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return count; + + for (i = 0; i < count; i++) { + memmove(ndata + (i * len + sizeof(pfx)), + ndata + i * len, len - sizeof(pfx)); + memcpy(ndata + i * len, pfx, sizeof(pfx)); + } + + return count; +} + +static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, + u8 *data) +{ + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count, mcount = 0; netdev_lock_ops(dev); if (stringset == ETH_SS_PHY_STATS && dev->phydev && @@ -191,21 +255,17 @@ static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, } netdev_unlock_ops(dev); - if (ds->ops->get_strings) { - ndata = data + mcount * len; - /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle - * the output after to prepend our CPU port prefix we - * constructed earlier - */ - ds->ops->get_strings(ds, port, stringset, ndata); - count = ds->ops->get_sset_count(ds, port, stringset); + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + count = dsa_conduit_append_port_strings(dp->ds, dp->index, + stringset, data, + mcount); if (count < 0) return; - for (i = 0; i < count; i++) { - memmove(ndata + (i * len + sizeof(pfx)), - ndata + i * len, len - sizeof(pfx)); - memcpy(ndata + i * len, pfx, sizeof(pfx)); - } + + mcount += count; } } From 74d64ae4254e99ef8c8215b057a76edac82c5f99 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 14 Apr 2026 16:10:35 -0700 Subject: [PATCH 0804/1518] net: dsa: remove redundant netdev_lock_ops() from conduit ethtool ops [ Upstream commit 0f99e0c3e19badaf3fdced0d3feba623e59eed41 ] DSA replaces the conduit (master) device's ethtool_ops with its own wrappers that aggregate stats from both the conduit and DSA switch ports. Taking the lock again inside the DSA wrappers causes a deadlock. Stumbled upon this when booting qemu with fbnic and CONFIG_NET_DSA_LOOP=y (which looks like some kind of testing device that auto-populates the ports of eth0). `ethtool -i` is enough to deadlock. This means we have basically zero coverage for DSA stuff with real ops locked devs. Remove the redundant netdev_lock_ops()/netdev_unlock_ops() calls from the DSA conduit ethtool wrappers. Fixes: 2bcf4772e45a ("net: ethtool: try to protect all callback with netdev instance lock") Signed-off-by: Stanislav Fomichev Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20260414231035.1917035-1-sdf@fomichev.me Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/dsa/conduit.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c index a1b044467bd6f..8398d72d7e4d3 100644 --- a/net/dsa/conduit.c +++ b/net/dsa/conduit.c @@ -27,9 +27,7 @@ static int dsa_conduit_get_regs_len(struct net_device *dev) int len; if (ops && ops->get_regs_len) { - netdev_lock_ops(dev); len = ops->get_regs_len(dev); - netdev_unlock_ops(dev); if (len < 0) return len; ret += len; @@ -60,15 +58,11 @@ static void dsa_conduit_get_regs(struct net_device *dev, int len; if (ops && ops->get_regs_len && ops->get_regs) { - netdev_lock_ops(dev); len = ops->get_regs_len(dev); - if (len < 0) { - netdev_unlock_ops(dev); + if (len < 0) return; - } regs->len = len; ops->get_regs(dev, regs, data); - netdev_unlock_ops(dev); data += regs->len; } @@ -115,10 +109,8 @@ static void dsa_conduit_get_ethtool_stats(struct net_device *dev, int count, mcount = 0; if (ops && ops->get_sset_count && ops->get_ethtool_stats) { - netdev_lock_ops(dev); mcount = ops->get_sset_count(dev, ETH_SS_STATS); ops->get_ethtool_stats(dev, stats, data); - netdev_unlock_ops(dev); } list_for_each_entry(dp, &dst->ports, list) { @@ -149,10 +141,8 @@ static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, if (count >= 0) phy_ethtool_get_stats(dev->phydev, stats, data); } else if (ops && ops->get_sset_count && ops->get_ethtool_phy_stats) { - netdev_lock_ops(dev); count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); ops->get_ethtool_phy_stats(dev, stats, data); - netdev_unlock_ops(dev); } if (count < 0) @@ -176,13 +166,11 @@ static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) struct dsa_switch_tree *dst = cpu_dp->dst; int count = 0; - netdev_lock_ops(dev); if (sset == ETH_SS_PHY_STATS && dev->phydev && (!ops || !ops->get_ethtool_phy_stats)) count = phy_ethtool_get_sset_count(dev->phydev); else if (ops && ops->get_sset_count) count = ops->get_sset_count(dev, sset); - netdev_unlock_ops(dev); if (count < 0) count = 0; @@ -239,7 +227,6 @@ static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, struct dsa_switch_tree *dst = cpu_dp->dst; int count, mcount = 0; - netdev_lock_ops(dev); if (stringset == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats) { mcount = phy_ethtool_get_sset_count(dev->phydev); @@ -253,7 +240,6 @@ static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, mcount = 0; ops->get_strings(dev, stringset, data); } - netdev_unlock_ops(dev); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) From 1f379216ccc882bf0a1e8aeb5b7ff5a4c0e3a027 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Wed, 15 Apr 2026 14:08:32 +0800 Subject: [PATCH 0805/1518] net: enetc: correct the command BD ring consumer index [ Upstream commit 759a32900b6f3db3d0f34a3b61123742723b50b4 ] The command BD ring cousumer index register has the consumer index as the lower 10 bits, and the bit 31 is SBE, which indicates whether a system bus error occurred during execution of the CBD command. So if a system bus error occurs, reading the register will get the SBE bit set. However, the current implementation directly uses the register value as the consumer index without masking it. Therefore, if a system bus error occurs, an incorrect consumer index will be obtained, causing errors in the processing of the command BD ring. Thus, we need to mask out the other bits to obtain the correct consumer index. In addition, this patch adds a check for the SBE bit after the polling loop and returns an error if the bit is set. Fixes: 4701073c3deb ("net: enetc: add initial netc-lib driver to support NTMP") Signed-off-by: Wei Fang Link: https://patch.msgid.link/20260415060833.2303846-2-wei.fang@nxp.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/enetc/ntmp.c | 13 ++++++++++--- drivers/net/ethernet/freescale/enetc/ntmp_private.h | 2 ++ 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/ntmp.c b/drivers/net/ethernet/freescale/enetc/ntmp.c index 0c1d343253bfb..b188eb2d40c0d 100644 --- a/drivers/net/ethernet/freescale/enetc/ntmp.c +++ b/drivers/net/ethernet/freescale/enetc/ntmp.c @@ -55,7 +55,7 @@ int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev, spin_lock_init(&cbdr->ring_lock); cbdr->next_to_use = netc_read(cbdr->regs.pir); - cbdr->next_to_clean = netc_read(cbdr->regs.cir); + cbdr->next_to_clean = netc_read(cbdr->regs.cir) & NETC_CBDRCIR_INDEX; /* Step 1: Configure the base address of the Control BD Ring */ netc_write(cbdr->regs.bar0, lower_32_bits(cbdr->dma_base_align)); @@ -98,7 +98,7 @@ static void ntmp_clean_cbdr(struct netc_cbdr *cbdr) int i; i = cbdr->next_to_clean; - while (netc_read(cbdr->regs.cir) != i) { + while ((netc_read(cbdr->regs.cir) & NETC_CBDRCIR_INDEX) != i) { cbd = ntmp_get_cbd(cbdr, i); memset(cbd, 0, sizeof(*cbd)); i = (i + 1) % cbdr->bd_num; @@ -135,12 +135,19 @@ static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd) cbdr->next_to_use = i; netc_write(cbdr->regs.pir, i); - err = read_poll_timeout_atomic(netc_read, val, val == i, + err = read_poll_timeout_atomic(netc_read, val, + (val & NETC_CBDRCIR_INDEX) == i, NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT, true, cbdr->regs.cir); if (unlikely(err)) goto cbdr_unlock; + if (unlikely(val & NETC_CBDRCIR_SBE)) { + dev_err(user->dev, "Command BD system bus error\n"); + err = -EIO; + goto cbdr_unlock; + } + dma_rmb(); /* Get the writeback command BD, because the caller may need * to check some other fields of the response header. diff --git a/drivers/net/ethernet/freescale/enetc/ntmp_private.h b/drivers/net/ethernet/freescale/enetc/ntmp_private.h index 34394e40fddd4..3459cc45b6103 100644 --- a/drivers/net/ethernet/freescale/enetc/ntmp_private.h +++ b/drivers/net/ethernet/freescale/enetc/ntmp_private.h @@ -12,6 +12,8 @@ #define NTMP_EID_REQ_LEN 8 #define NETC_CBDR_BD_NUM 256 +#define NETC_CBDRCIR_INDEX GENMASK(9, 0) +#define NETC_CBDRCIR_SBE BIT(31) union netc_cbd { struct { From 37c8933064be714ee672b0a0523c2fd045b73b3d Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Wed, 15 Apr 2026 14:08:33 +0800 Subject: [PATCH 0806/1518] net: enetc: fix NTMP DMA use-after-free issue [ Upstream commit 3cade698881eb238f88cbbfec82acc2110440a3f ] The AI-generated review reported a potential DMA use-after-free issue [1]. If netc_xmit_ntmp_cmd() times out and returns an error, the pending command is not explicitly aborted, while ntmp_free_data_mem() unconditionally frees the DMA buffer. If the buffer has already been reallocated elsewhere, this may lead to silent memory corruption. Because the hardware eventually processes the pending command and perform a DMA write of the response to the physical address of the freed buffer. To resolve this issue, this patch does the following modifications: 1. Convert cbdr->ring_lock from a spinlock to a mutex The lock was originally a spinlock in case NTMP operations might be invoked from atomic context. After downstream support for all NTMP tables, no such usage has materialized. A mutex lock is now required because the driver now needs to reclaim used BDs and release associated DMA memory within the lock's context, while dma_free_coherent() might sleep. 2. Introduce software command BD (struct netc_swcbd) The hardware write-back overwrites the addr and len fields of the BD, so the driver cannot rely on the hardware BD to free the associated DMA memory. The driver now maintains a software shadow BD storing the DMA buffer pointer, DMA address, and size. And netc_xmit_ntmp_cmd() only reclaims older BDs when the number of used BDs reaches NETC_CBDR_CLEAN_WORK (16). The software BD enables correct DMA memory release. With this, struct ntmp_dma_buf and ntmp_free_data_mem() are no longer needed and are removed. 3. Require callers to hold ring_lock across netc_xmit_ntmp_cmd() netc_xmit_ntmp_cmd() releases the ring_lock before the caller finishes consuming the response. At this point, if a concurrent thread submits a new command, it may trigger ntmp_clean_cbdr() and free the DMA buffer while it is still in use. Move ring_lock ownership to the caller to ensure the response buffer cannot be reclaimed prematurely. So the helpers ntmp_select_and_lock_cbdr() and ntmp_unlock_cbdr() are added. These changes eliminate the DMA use-after-free condition and ensure safe and consistent BD reclamation and DMA buffer lifecycle management. Fixes: 4701073c3deb ("net: enetc: add initial netc-lib driver to support NTMP") Link: https://lore.kernel.org/netdev/20260403011729.1795413-1-kuba@kernel.org/ # [1] Signed-off-by: Wei Fang Link: https://patch.msgid.link/20260415060833.2303846-3-wei.fang@nxp.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/enetc/ntmp.c | 214 ++++++++++-------- .../ethernet/freescale/enetc/ntmp_private.h | 8 +- include/linux/fsl/ntmp.h | 9 +- 3 files changed, 134 insertions(+), 97 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/ntmp.c b/drivers/net/ethernet/freescale/enetc/ntmp.c index b188eb2d40c0d..70bbc5d2d5d42 100644 --- a/drivers/net/ethernet/freescale/enetc/ntmp.c +++ b/drivers/net/ethernet/freescale/enetc/ntmp.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "ntmp_private.h" @@ -42,6 +43,12 @@ int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev, if (!cbdr->addr_base) return -ENOMEM; + cbdr->swcbd = vcalloc(cbd_num, sizeof(struct netc_swcbd)); + if (!cbdr->swcbd) { + dma_free_coherent(dev, size, cbdr->addr_base, cbdr->dma_base); + return -ENOMEM; + } + cbdr->dma_size = size; cbdr->bd_num = cbd_num; cbdr->regs = *regs; @@ -52,7 +59,7 @@ int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev, cbdr->addr_base_align = PTR_ALIGN(cbdr->addr_base, NTMP_BASE_ADDR_ALIGN); - spin_lock_init(&cbdr->ring_lock); + mutex_init(&cbdr->ring_lock); cbdr->next_to_use = netc_read(cbdr->regs.pir); cbdr->next_to_clean = netc_read(cbdr->regs.cir) & NETC_CBDRCIR_INDEX; @@ -71,10 +78,24 @@ int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev, } EXPORT_SYMBOL_GPL(ntmp_init_cbdr); +static void ntmp_free_data_mem(struct device *dev, struct netc_swcbd *swcbd) +{ + if (unlikely(!swcbd->buf)) + return; + + dma_free_coherent(dev, swcbd->size + NTMP_DATA_ADDR_ALIGN, + swcbd->buf, swcbd->dma); +} + void ntmp_free_cbdr(struct netc_cbdr *cbdr) { /* Disable the Control BD Ring */ netc_write(cbdr->regs.mr, 0); + + for (int i = 0; i < cbdr->bd_num; i++) + ntmp_free_data_mem(cbdr->dev, &cbdr->swcbd[i]); + + vfree(cbdr->swcbd); dma_free_coherent(cbdr->dev, cbdr->dma_size, cbdr->addr_base, cbdr->dma_base); memset(cbdr, 0, sizeof(*cbdr)); @@ -94,40 +115,59 @@ static union netc_cbd *ntmp_get_cbd(struct netc_cbdr *cbdr, int index) static void ntmp_clean_cbdr(struct netc_cbdr *cbdr) { - union netc_cbd *cbd; - int i; + int i = cbdr->next_to_clean; - i = cbdr->next_to_clean; while ((netc_read(cbdr->regs.cir) & NETC_CBDRCIR_INDEX) != i) { - cbd = ntmp_get_cbd(cbdr, i); + union netc_cbd *cbd = ntmp_get_cbd(cbdr, i); + struct netc_swcbd *swcbd = &cbdr->swcbd[i]; + + ntmp_free_data_mem(cbdr->dev, swcbd); + memset(swcbd, 0, sizeof(*swcbd)); memset(cbd, 0, sizeof(*cbd)); i = (i + 1) % cbdr->bd_num; } + dma_wmb(); cbdr->next_to_clean = i; } -static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd) +static void ntmp_select_and_lock_cbdr(struct ntmp_user *user, + struct netc_cbdr **cbdr) +{ + /* Currently only ENETC is supported, and it has only one command + * BD ring. + */ + *cbdr = &user->ring[0]; + + mutex_lock(&(*cbdr)->ring_lock); +} + +static void ntmp_unlock_cbdr(struct netc_cbdr *cbdr) +{ + mutex_unlock(&cbdr->ring_lock); +} + +static int netc_xmit_ntmp_cmd(struct netc_cbdr *cbdr, union netc_cbd *cbd, + struct netc_swcbd *swcbd) { union netc_cbd *cur_cbd; - struct netc_cbdr *cbdr; - int i, err; + int i, err, used_bds; u16 status; u32 val; - /* Currently only i.MX95 ENETC is supported, and it only has one - * command BD ring - */ - cbdr = &user->ring[0]; - - spin_lock_bh(&cbdr->ring_lock); - - if (unlikely(!ntmp_get_free_cbd_num(cbdr))) + used_bds = cbdr->bd_num - ntmp_get_free_cbd_num(cbdr); + if (unlikely(used_bds >= NETC_CBDR_CLEAN_WORK)) { ntmp_clean_cbdr(cbdr); + if (unlikely(!ntmp_get_free_cbd_num(cbdr))) { + ntmp_free_data_mem(cbdr->dev, swcbd); + return -EBUSY; + } + } i = cbdr->next_to_use; cur_cbd = ntmp_get_cbd(cbdr, i); *cur_cbd = *cbd; + cbdr->swcbd[i] = *swcbd; dma_wmb(); /* Update producer index of both software and hardware */ @@ -135,17 +175,16 @@ static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd) cbdr->next_to_use = i; netc_write(cbdr->regs.pir, i); - err = read_poll_timeout_atomic(netc_read, val, - (val & NETC_CBDRCIR_INDEX) == i, - NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT, - true, cbdr->regs.cir); + err = read_poll_timeout(netc_read, val, + (val & NETC_CBDRCIR_INDEX) == i, + NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT, + true, cbdr->regs.cir); if (unlikely(err)) - goto cbdr_unlock; + return err; if (unlikely(val & NETC_CBDRCIR_SBE)) { - dev_err(user->dev, "Command BD system bus error\n"); - err = -EIO; - goto cbdr_unlock; + dev_err(cbdr->dev, "Command BD system bus error\n"); + return -EIO; } dma_rmb(); @@ -157,40 +196,29 @@ static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd) /* Check the writeback error status */ status = le16_to_cpu(cbd->resp_hdr.error_rr) & NTMP_RESP_ERROR; if (unlikely(status)) { - err = -EIO; - dev_err(user->dev, "Command BD error: 0x%04x\n", status); + dev_err(cbdr->dev, "Command BD error: 0x%04x\n", status); + return -EIO; } - ntmp_clean_cbdr(cbdr); - dma_wmb(); - -cbdr_unlock: - spin_unlock_bh(&cbdr->ring_lock); - - return err; + return 0; } -static int ntmp_alloc_data_mem(struct ntmp_dma_buf *data, void **buf_align) +static int ntmp_alloc_data_mem(struct device *dev, struct netc_swcbd *swcbd, + void **buf_align) { void *buf; - buf = dma_alloc_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN, - &data->dma, GFP_KERNEL); + buf = dma_alloc_coherent(dev, swcbd->size + NTMP_DATA_ADDR_ALIGN, + &swcbd->dma, GFP_KERNEL); if (!buf) return -ENOMEM; - data->buf = buf; + swcbd->buf = buf; *buf_align = PTR_ALIGN(buf, NTMP_DATA_ADDR_ALIGN); return 0; } -static void ntmp_free_data_mem(struct ntmp_dma_buf *data) -{ - dma_free_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN, - data->buf, data->dma); -} - static void ntmp_fill_request_hdr(union netc_cbd *cbd, dma_addr_t dma, int len, int table_id, int cmd, int access_method) @@ -241,37 +269,39 @@ static int ntmp_delete_entry_by_id(struct ntmp_user *user, int tbl_id, u8 tbl_ver, u32 entry_id, u32 req_len, u32 resp_len) { - struct ntmp_dma_buf data = { - .dev = user->dev, + struct netc_swcbd swcbd = { .size = max(req_len, resp_len), }; struct ntmp_req_by_eid *req; + struct netc_cbdr *cbdr; union netc_cbd cbd; int err; - err = ntmp_alloc_data_mem(&data, (void **)&req); + err = ntmp_alloc_data_mem(user->dev, &swcbd, (void **)&req); if (err) return err; ntmp_fill_crd_eid(req, tbl_ver, 0, 0, entry_id); - ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(req_len, resp_len), + ntmp_fill_request_hdr(&cbd, swcbd.dma, NTMP_LEN(req_len, resp_len), tbl_id, NTMP_CMD_DELETE, NTMP_AM_ENTRY_ID); - err = netc_xmit_ntmp_cmd(user, &cbd); + ntmp_select_and_lock_cbdr(user, &cbdr); + err = netc_xmit_ntmp_cmd(cbdr, &cbd, &swcbd); if (err) dev_err(user->dev, "Failed to delete entry 0x%x of %s, err: %pe", entry_id, ntmp_table_name(tbl_id), ERR_PTR(err)); - - ntmp_free_data_mem(&data); + ntmp_unlock_cbdr(cbdr); return err; } -static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id, - u32 len, struct ntmp_req_by_eid *req, - dma_addr_t dma, bool compare_eid) +static int ntmp_query_entry_by_id(struct netc_cbdr *cbdr, int tbl_id, + struct ntmp_req_by_eid *req, + struct netc_swcbd *swcbd, + bool compare_eid) { + u32 len = NTMP_LEN(sizeof(*req), swcbd->size); struct ntmp_cmn_resp_query *resp; int cmd = NTMP_CMD_QUERY; union netc_cbd cbd; @@ -283,10 +313,11 @@ static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id, cmd = NTMP_CMD_QU; /* Request header */ - ntmp_fill_request_hdr(&cbd, dma, len, tbl_id, cmd, NTMP_AM_ENTRY_ID); - err = netc_xmit_ntmp_cmd(user, &cbd); + ntmp_fill_request_hdr(&cbd, swcbd->dma, len, tbl_id, cmd, + NTMP_AM_ENTRY_ID); + err = netc_xmit_ntmp_cmd(cbdr, &cbd, swcbd); if (err) { - dev_err(user->dev, + dev_err(cbdr->dev, "Failed to query entry 0x%x of %s, err: %pe\n", entry_id, ntmp_table_name(tbl_id), ERR_PTR(err)); return err; @@ -300,7 +331,7 @@ static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id, resp = (struct ntmp_cmn_resp_query *)req; if (unlikely(le32_to_cpu(resp->entry_id) != entry_id)) { - dev_err(user->dev, + dev_err(cbdr->dev, "%s: query EID 0x%x doesn't match response EID 0x%x\n", ntmp_table_name(tbl_id), entry_id, le32_to_cpu(resp->entry_id)); return -EIO; @@ -312,15 +343,15 @@ static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id, int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id, struct maft_entry_data *maft) { - struct ntmp_dma_buf data = { - .dev = user->dev, + struct netc_swcbd swcbd = { .size = sizeof(struct maft_req_add), }; struct maft_req_add *req; + struct netc_cbdr *cbdr; union netc_cbd cbd; int err; - err = ntmp_alloc_data_mem(&data, (void **)&req); + err = ntmp_alloc_data_mem(user->dev, &swcbd, (void **)&req); if (err) return err; @@ -329,14 +360,15 @@ int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id, req->keye = maft->keye; req->cfge = maft->cfge; - ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0), + ntmp_fill_request_hdr(&cbd, swcbd.dma, NTMP_LEN(swcbd.size, 0), NTMP_MAFT_ID, NTMP_CMD_ADD, NTMP_AM_ENTRY_ID); - err = netc_xmit_ntmp_cmd(user, &cbd); + + ntmp_select_and_lock_cbdr(user, &cbdr); + err = netc_xmit_ntmp_cmd(cbdr, &cbd, &swcbd); if (err) dev_err(user->dev, "Failed to add MAFT entry 0x%x, err: %pe\n", entry_id, ERR_PTR(err)); - - ntmp_free_data_mem(&data); + ntmp_unlock_cbdr(cbdr); return err; } @@ -345,31 +377,31 @@ EXPORT_SYMBOL_GPL(ntmp_maft_add_entry); int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id, struct maft_entry_data *maft) { - struct ntmp_dma_buf data = { - .dev = user->dev, + struct netc_swcbd swcbd = { .size = sizeof(struct maft_resp_query), }; struct maft_resp_query *resp; struct ntmp_req_by_eid *req; + struct netc_cbdr *cbdr; int err; - err = ntmp_alloc_data_mem(&data, (void **)&req); + err = ntmp_alloc_data_mem(user->dev, &swcbd, (void **)&req); if (err) return err; ntmp_fill_crd_eid(req, user->tbl.maft_ver, 0, 0, entry_id); - err = ntmp_query_entry_by_id(user, NTMP_MAFT_ID, - NTMP_LEN(sizeof(*req), data.size), - req, data.dma, true); + + ntmp_select_and_lock_cbdr(user, &cbdr); + err = ntmp_query_entry_by_id(cbdr, NTMP_MAFT_ID, req, &swcbd, true); if (err) - goto end; + goto unlock_cbdr; resp = (struct maft_resp_query *)req; maft->keye = resp->keye; maft->cfge = resp->cfge; -end: - ntmp_free_data_mem(&data); +unlock_cbdr: + ntmp_unlock_cbdr(cbdr); return err; } @@ -385,8 +417,9 @@ EXPORT_SYMBOL_GPL(ntmp_maft_delete_entry); int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table, int count) { - struct ntmp_dma_buf data = {.dev = user->dev}; struct rsst_req_update *req; + struct netc_swcbd swcbd; + struct netc_cbdr *cbdr; union netc_cbd cbd; int err, i; @@ -394,8 +427,8 @@ int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table, /* HW only takes in a full 64 entry table */ return -EINVAL; - data.size = struct_size(req, groups, count); - err = ntmp_alloc_data_mem(&data, (void **)&req); + swcbd.size = struct_size(req, groups, count); + err = ntmp_alloc_data_mem(user->dev, &swcbd, (void **)&req); if (err) return err; @@ -405,15 +438,15 @@ int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table, for (i = 0; i < count; i++) req->groups[i] = (u8)(table[i]); - ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0), + ntmp_fill_request_hdr(&cbd, swcbd.dma, NTMP_LEN(swcbd.size, 0), NTMP_RSST_ID, NTMP_CMD_UPDATE, NTMP_AM_ENTRY_ID); - err = netc_xmit_ntmp_cmd(user, &cbd); + ntmp_select_and_lock_cbdr(user, &cbdr); + err = netc_xmit_ntmp_cmd(cbdr, &cbd, &swcbd); if (err) dev_err(user->dev, "Failed to update RSST entry, err: %pe\n", ERR_PTR(err)); - - ntmp_free_data_mem(&data); + ntmp_unlock_cbdr(cbdr); return err; } @@ -421,8 +454,9 @@ EXPORT_SYMBOL_GPL(ntmp_rsst_update_entry); int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count) { - struct ntmp_dma_buf data = {.dev = user->dev}; struct ntmp_req_by_eid *req; + struct netc_swcbd swcbd; + struct netc_cbdr *cbdr; union netc_cbd cbd; int err, i; u8 *group; @@ -431,21 +465,23 @@ int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count) /* HW only takes in a full 64 entry table */ return -EINVAL; - data.size = NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count) + - RSST_CFGE_DATA_SIZE(count); - err = ntmp_alloc_data_mem(&data, (void **)&req); + swcbd.size = NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count) + + RSST_CFGE_DATA_SIZE(count); + err = ntmp_alloc_data_mem(user->dev, &swcbd, (void **)&req); if (err) return err; /* Set the request data buffer */ ntmp_fill_crd_eid(req, user->tbl.rsst_ver, 0, 0, 0); - ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(sizeof(*req), data.size), + ntmp_fill_request_hdr(&cbd, swcbd.dma, NTMP_LEN(sizeof(*req), swcbd.size), NTMP_RSST_ID, NTMP_CMD_QUERY, NTMP_AM_ENTRY_ID); - err = netc_xmit_ntmp_cmd(user, &cbd); + + ntmp_select_and_lock_cbdr(user, &cbdr); + err = netc_xmit_ntmp_cmd(cbdr, &cbd, &swcbd); if (err) { dev_err(user->dev, "Failed to query RSST entry, err: %pe\n", ERR_PTR(err)); - goto end; + goto unlock_cbdr; } group = (u8 *)req; @@ -453,8 +489,8 @@ int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count) for (i = 0; i < count; i++) table[i] = group[i]; -end: - ntmp_free_data_mem(&data); +unlock_cbdr: + ntmp_unlock_cbdr(cbdr); return err; } diff --git a/drivers/net/ethernet/freescale/enetc/ntmp_private.h b/drivers/net/ethernet/freescale/enetc/ntmp_private.h index 3459cc45b6103..f8dff3ba2c28a 100644 --- a/drivers/net/ethernet/freescale/enetc/ntmp_private.h +++ b/drivers/net/ethernet/freescale/enetc/ntmp_private.h @@ -14,6 +14,7 @@ #define NETC_CBDR_BD_NUM 256 #define NETC_CBDRCIR_INDEX GENMASK(9, 0) #define NETC_CBDRCIR_SBE BIT(31) +#define NETC_CBDR_CLEAN_WORK 16 union netc_cbd { struct { @@ -56,13 +57,6 @@ union netc_cbd { } resp_hdr; /* NTMP Response Message Header Format */ }; -struct ntmp_dma_buf { - struct device *dev; - size_t size; - void *buf; - dma_addr_t dma; -}; - struct ntmp_cmn_req_data { __le16 update_act; u8 dbg_opt; diff --git a/include/linux/fsl/ntmp.h b/include/linux/fsl/ntmp.h index 916dc4fe7de3b..83a449b4d6ec4 100644 --- a/include/linux/fsl/ntmp.h +++ b/include/linux/fsl/ntmp.h @@ -31,6 +31,12 @@ struct netc_tbl_vers { u8 rsst_ver; }; +struct netc_swcbd { + void *buf; + dma_addr_t dma; + size_t size; +}; + struct netc_cbdr { struct device *dev; struct netc_cbdr_regs regs; @@ -44,9 +50,10 @@ struct netc_cbdr { void *addr_base_align; dma_addr_t dma_base; dma_addr_t dma_base_align; + struct netc_swcbd *swcbd; /* Serialize the order of command BD ring */ - spinlock_t ring_lock; + struct mutex ring_lock; }; struct ntmp_user { From ff3e8515c1d92994db1b777c7ccc2058ae8256e0 Mon Sep 17 00:00:00 2001 From: ZhangGuoDong Date: Mon, 27 Oct 2025 15:12:54 +0800 Subject: [PATCH 0807/1518] smb: move smb_version_values to common/smbglob.h [ Upstream commit 34cf191bb6a349dc88ec2c4f6355fe006ac669e0 ] Merge the struct members of the server and the client: - req_capabilities: from client - header_preamble_size: from client - cap_unicode: from client - capabilities: from server, rename to req_capabilities - max_read_size: from server - max_write_size: from server - max_trans_size: from server - max_credits: from server - create_durable_size: from server - create_durable_v2_size: from server - create_mxac_size: from server - create_disk_id_size: from server - create_posix_size: from server Then move duplicate definitions to common header file. Co-developed-by: ChenXiaoSong Signed-off-by: ChenXiaoSong Signed-off-by: ZhangGuoDong Acked-by: Namjae Jeon Signed-off-by: Steve French Stable-dep-of: 1baff47b81f9 ("ksmbd: fix use-after-free in smb2_open during durable reconnect") Signed-off-by: Sasha Levin --- fs/smb/client/cifsglob.h | 22 ---------------------- fs/smb/common/cifsglob.h | 31 +++++++++++++++++++++++++++++++ fs/smb/server/smb2misc.c | 2 +- fs/smb/server/smb2ops.c | 32 ++++++++++++++++---------------- fs/smb/server/smb2pdu.c | 10 +++++----- fs/smb/server/smb_common.h | 29 ----------------------------- 6 files changed, 53 insertions(+), 73 deletions(-) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 3059fcf12ed13..69deb29502a8c 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -634,28 +634,6 @@ struct smb_version_operations { struct kvec *xattr_iov); }; -struct smb_version_values { - char *version_string; - __u16 protocol_id; - __u32 req_capabilities; - __u32 large_lock_type; - __u32 exclusive_lock_type; - __u32 shared_lock_type; - __u32 unlock_lock_type; - size_t header_preamble_size; - size_t header_size; - size_t max_header_size; - size_t read_rsp_size; - __le16 lock_cmd; - unsigned int cap_unix; - unsigned int cap_nt_find; - unsigned int cap_large_files; - unsigned int cap_unicode; - __u16 signing_enabled; - __u16 signing_required; - size_t create_lease_size; -}; - #define HEADER_SIZE(server) (server->vals->header_size) #define MAX_HEADER_SIZE(server) (server->vals->max_header_size) #define HEADER_PREAMBLE_SIZE(server) (server->vals->header_preamble_size) diff --git a/fs/smb/common/cifsglob.h b/fs/smb/common/cifsglob.h index 00fd215e3eb54..eda5e666a7617 100644 --- a/fs/smb/common/cifsglob.h +++ b/fs/smb/common/cifsglob.h @@ -9,6 +9,37 @@ #ifndef _COMMON_CIFS_GLOB_H #define _COMMON_CIFS_GLOB_H +struct smb_version_values { + char *version_string; + __u16 protocol_id; + __le16 lock_cmd; + __u32 req_capabilities; + __u32 max_read_size; + __u32 max_write_size; + __u32 max_trans_size; + __u32 max_credits; + __u32 large_lock_type; + __u32 exclusive_lock_type; + __u32 shared_lock_type; + __u32 unlock_lock_type; + size_t header_preamble_size; + size_t header_size; + size_t max_header_size; + size_t read_rsp_size; + unsigned int cap_unix; + unsigned int cap_nt_find; + unsigned int cap_large_files; + unsigned int cap_unicode; + __u16 signing_enabled; + __u16 signing_required; + size_t create_lease_size; + size_t create_durable_size; + size_t create_durable_v2_size; + size_t create_mxac_size; + size_t create_disk_id_size; + size_t create_posix_size; +}; + static inline void inc_rfc1001_len(void *buf, int count) { be32_add_cpu((__be32 *)buf, count); diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index ae501024665e1..67a2d7a793f6e 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -460,7 +460,7 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } validate_credit: - if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && + if ((work->conn->vals->req_capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && smb2_validate_credit_charge(work->conn, hdr)) return 1; diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index 606aa3c5189a2..bcf05caa2304d 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -15,7 +15,7 @@ static struct smb_version_values smb21_server_values = { .version_string = SMB21_VERSION_STRING, .protocol_id = SMB21_PROT_ID, - .capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, .max_read_size = SMB21_DEFAULT_IOSIZE, .max_write_size = SMB21_DEFAULT_IOSIZE, .max_trans_size = SMB21_DEFAULT_IOSIZE, @@ -41,7 +41,7 @@ static struct smb_version_values smb21_server_values = { static struct smb_version_values smb30_server_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, - .capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, .max_read_size = SMB3_DEFAULT_IOSIZE, .max_write_size = SMB3_DEFAULT_IOSIZE, .max_trans_size = SMB3_DEFAULT_TRANS_SIZE, @@ -68,7 +68,7 @@ static struct smb_version_values smb30_server_values = { static struct smb_version_values smb302_server_values = { .version_string = SMB302_VERSION_STRING, .protocol_id = SMB302_PROT_ID, - .capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, .max_read_size = SMB3_DEFAULT_IOSIZE, .max_write_size = SMB3_DEFAULT_IOSIZE, .max_trans_size = SMB3_DEFAULT_TRANS_SIZE, @@ -95,7 +95,7 @@ static struct smb_version_values smb302_server_values = { static struct smb_version_values smb311_server_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_LARGE_MTU, .max_read_size = SMB3_DEFAULT_IOSIZE, .max_write_size = SMB3_DEFAULT_IOSIZE, .max_trans_size = SMB3_DEFAULT_TRANS_SIZE, @@ -204,7 +204,7 @@ void init_smb2_1_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_LEASING; } /** @@ -221,20 +221,20 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; } /** @@ -251,19 +251,19 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_PERSISTENT_HANDLES; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_PERSISTENT_HANDLES; } /** @@ -280,14 +280,14 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_PERSISTENT_HANDLES; + conn->vals->req_capabilities |= SMB2_GLOBAL_CAP_PERSISTENT_HANDLES; INIT_LIST_HEAD(&conn->preauth_sess_table); return 0; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 006b386cf9122..16ea123f61223 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -291,7 +291,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) /* Not setting conn guid rsp->ServerGUID, as it * not used by client for identifying connection */ - rsp->Capabilities = cpu_to_le32(conn->vals->capabilities); + rsp->Capabilities = cpu_to_le32(conn->vals->req_capabilities); /* Default Max Message Size till SMB2.0, 64K*/ rsp->MaxTransactSize = cpu_to_le32(conn->vals->max_trans_size); rsp->MaxReadSize = cpu_to_le32(conn->vals->max_read_size); @@ -965,7 +965,7 @@ bool smb3_encryption_negotiated(struct ksmbd_conn *conn) * SMB 3.0 and 3.0.2 dialects use the SMB2_GLOBAL_CAP_ENCRYPTION flag. * SMB 3.1.1 uses the cipher_type field. */ - return (conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) || + return (conn->vals->req_capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) || conn->cipher_type; } @@ -1219,7 +1219,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) rc = -EINVAL; goto err_out; } - rsp->Capabilities = cpu_to_le32(conn->vals->capabilities); + rsp->Capabilities = cpu_to_le32(conn->vals->req_capabilities); /* For stats */ conn->connection_type = conn->dialect; @@ -3505,7 +3505,7 @@ int smb2_open(struct ksmbd_work *work) share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) || (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && - !(conn->vals->capabilities & SMB2_GLOBAL_CAP_LEASING))) { + !(conn->vals->req_capabilities & SMB2_GLOBAL_CAP_LEASING))) { if (share_ret < 0 && !S_ISDIR(file_inode(fp->filp)->i_mode)) { rc = share_ret; goto err_out1; @@ -8100,7 +8100,7 @@ static int fsctl_validate_negotiate_info(struct ksmbd_conn *conn, goto err_out; } - neg_rsp->Capabilities = cpu_to_le32(conn->vals->capabilities); + neg_rsp->Capabilities = cpu_to_le32(conn->vals->req_capabilities); memset(neg_rsp->Guid, 0, SMB2_CLIENT_GUID_SIZE); neg_rsp->SecurityMode = cpu_to_le16(conn->srv_sec_mode); neg_rsp->Dialect = cpu_to_le16(conn->dialect); diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index 863716207a0de..dac783b46545d 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -338,35 +338,6 @@ struct file_id_full_dir_info { char FileName[]; } __packed; /* level 0x105 FF rsp data */ -struct smb_version_values { - char *version_string; - __u16 protocol_id; - __le16 lock_cmd; - __u32 capabilities; - __u32 max_read_size; - __u32 max_write_size; - __u32 max_trans_size; - __u32 max_credits; - __u32 large_lock_type; - __u32 exclusive_lock_type; - __u32 shared_lock_type; - __u32 unlock_lock_type; - size_t header_size; - size_t max_header_size; - size_t read_rsp_size; - unsigned int cap_unix; - unsigned int cap_nt_find; - unsigned int cap_large_files; - __u16 signing_enabled; - __u16 signing_required; - size_t create_lease_size; - size_t create_durable_size; - size_t create_durable_v2_size; - size_t create_mxac_size; - size_t create_disk_id_size; - size_t create_posix_size; -}; - struct filesystem_posix_info { /* For undefined recommended transfer size return -1 in that field */ __le32 OptimalTransferSize; /* bsize on some os, iosize on other os */ From ce2e164c1c51c3f7813b80f8c926836e896bcbb3 Mon Sep 17 00:00:00 2001 From: Akif Date: Fri, 17 Apr 2026 23:57:09 +0530 Subject: [PATCH 0808/1518] ksmbd: fix use-after-free in smb2_open during durable reconnect [ Upstream commit 1baff47b81f94f9231c91236aa511420d0e266b9 ] In smb2_open, the call to ksmbd_put_durable_fd(fp) drops the reference to the durable file descriptor early during the durable reconnect process. If an error occurs subsequently (eg, ksmbd_iov_pin_rsp fails) or a scavenger accesses the file, it leads to a use-after-free when accessing fp properties (eg fp->create_time). Move the single put to the end of the function below err_out2 so fp stays valid until smb2_open returns. Fixes: c8efcc786146 ("ksmbd: add support for durable handles v1/v2") Signed-off-by: Akif Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/smb2pdu.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 16ea123f61223..4bfbfe53aa4eb 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3024,29 +3024,23 @@ int smb2_open(struct ksmbd_work *work) if (dh_info.reconnected == true) { rc = smb2_check_durable_oplock(conn, share, dh_info.fp, lc, sess->user, name); - if (rc) { - ksmbd_put_durable_fd(dh_info.fp); + if (rc) goto err_out2; - } rc = ksmbd_reopen_durable_fd(work, dh_info.fp); - if (rc) { - ksmbd_put_durable_fd(dh_info.fp); + if (rc) goto err_out2; - } fp = dh_info.fp; if (ksmbd_override_fsids(work)) { rc = -ENOMEM; - ksmbd_put_durable_fd(dh_info.fp); goto err_out2; } file_info = FILE_OPENED; rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); - ksmbd_put_durable_fd(fp); if (rc) goto err_out2; @@ -3816,6 +3810,9 @@ int smb2_open(struct ksmbd_work *work) ksmbd_debug(SMB, "Error response: %x\n", rsp->hdr.Status); } + if (dh_info.reconnected) + ksmbd_put_durable_fd(dh_info.fp); + kfree(name); kfree(lc); From 8e8a7c72a24f13a6854ef0f45acb96188eaeff43 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Mar 2026 12:23:02 +0000 Subject: [PATCH 0809/1518] tcp: move tp->chrono_type next tp->chrono_stat[] [ Upstream commit 4b78c9cbd8f1fbb9517aee48b372646f4cf05442 ] chrono_type is currently in tcp_sock_read_txrx group, which is supposed to hold read-mostly fields. But chrono_type is mostly written in tx path, it should be moved to tcp_sock_write_tx group, close to other chrono fields (chrono_stat[], chrono_start). Note this adds holes, but data locality is far more important. Use a full u8 for the time being, compiler can generate more efficient code. Signed-off-by: Eric Dumazet Reviewed-by: Neal Cardwell Link: https://patch.msgid.link/20260308122302.2895067-1-edumazet@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: 267bf3cf9a6f ("tcp: annotate data-races in tcp_get_info_chrono_stats()") Signed-off-by: Sasha Levin --- include/linux/tcp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 20b8c6e21fef3..8e1266cf8ef69 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -231,8 +231,7 @@ struct tcp_sock { u32 sacked_out; /* SACK'd packets */ u16 tcp_header_len; /* Bytes of tcp header to send */ u8 scaling_ratio; /* see tcp_win_from_space() */ - u8 chrono_type : 2, /* current chronograph type */ - repair : 1, + u8 repair : 1, tcp_usec_ts : 1, /* TSval values in usec */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ @@ -267,6 +266,7 @@ struct tcp_sock { * total number of data bytes sent. */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ + u8 chrono_type; /* current chronograph type */ u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ From c67c9032ce565dabe8b12198a52bc0ea3bb6e2d3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Mar 2026 12:35:49 +0000 Subject: [PATCH 0810/1518] tcp: inline tcp_chrono_start() [ Upstream commit d6d4ff335db2d9242937ca474d292010acd35c38 ] tcp_chrono_start() is small enough, and used in TCP sendmsg() fast path (from tcp_skb_entail()). Note clang is already inlining it from functions in tcp_output.c. Inlining it improves performance and reduces bloat : $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new add/remove: 0/2 grow/shrink: 1/0 up/down: 1/-84 (-83) Function old new delta tcp_skb_entail 280 281 +1 __pfx_tcp_chrono_start 16 - -16 tcp_chrono_start 68 - -68 Total: Before=25192434, After=25192351, chg -0.00% Note that tcp_chrono_stop() is too big. Signed-off-by: Eric Dumazet Reviewed-by: Neal Cardwell Link: https://patch.msgid.link/20260308123549.2924460-1-edumazet@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: 267bf3cf9a6f ("tcp: annotate data-races in tcp_get_info_chrono_stats()") Signed-off-by: Sasha Levin --- include/net/tcp.h | 25 ++++++++++++++++++++++++- net/ipv4/tcp_output.c | 24 ------------------------ 2 files changed, 24 insertions(+), 25 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 7647ed5c732c1..6805961726dc1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2124,7 +2124,30 @@ enum tcp_chrono { __TCP_CHRONO_MAX, }; -void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); +static inline void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) +{ + const u32 now = tcp_jiffies32; + enum tcp_chrono old = tp->chrono_type; + + if (old > TCP_CHRONO_UNSPEC) + tp->chrono_stat[old - 1] += now - tp->chrono_start; + tp->chrono_start = now; + tp->chrono_type = new; +} + +static inline void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) +{ + struct tcp_sock *tp = tcp_sk(sk); + + /* If there are multiple conditions worthy of tracking in a + * chronograph then the highest priority enum takes precedence + * over the other conditions. So that if something "more interesting" + * starts happening, stop the previous chrono and start a new one. + */ + if (type > tp->chrono_type) + tcp_chrono_set(tp, type); +} + void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b94efb3050d2f..b00bd5044b322 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2813,30 +2813,6 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, return false; } -static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) -{ - const u32 now = tcp_jiffies32; - enum tcp_chrono old = tp->chrono_type; - - if (old > TCP_CHRONO_UNSPEC) - tp->chrono_stat[old - 1] += now - tp->chrono_start; - tp->chrono_start = now; - tp->chrono_type = new; -} - -void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) -{ - struct tcp_sock *tp = tcp_sk(sk); - - /* If there are multiple conditions worthy of tracking in a - * chronograph then the highest priority enum takes precedence - * over the other conditions. So that if something "more interesting" - * starts happening, stop the previous chrono and start a new one. - */ - if (type > tp->chrono_type) - tcp_chrono_set(tp, type); -} - void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); From 2962660dc75af3bf9de4bf3171876c297a486e98 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:06 +0000 Subject: [PATCH 0811/1518] tcp: annotate data-races in tcp_get_info_chrono_stats() [ Upstream commit 267bf3cf9a6f0ffb98b8afd983c1950e835f07c9 ] tcp_get_timestamping_opt_stats() does not own the socket lock, this is intentional. It calls tcp_get_info_chrono_stats() while other threads could change chrono fields in tcp_chrono_set(). I do not think we need coherent TCP socket state snapshot in tcp_get_timestamping_opt_stats(), I chose to only add annotations to keep KCSAN happy. Fixes: 1c885808e456 ("tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-2-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 10 +++++++--- net/ipv4/tcp.c | 14 ++++++++++---- 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 6805961726dc1..236d9e0d35ed7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2129,10 +2129,14 @@ static inline void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new const u32 now = tcp_jiffies32; enum tcp_chrono old = tp->chrono_type; + /* Following WRITE_ONCE()s pair with READ_ONCE()s in + * tcp_get_info_chrono_stats(). + */ if (old > TCP_CHRONO_UNSPEC) - tp->chrono_stat[old - 1] += now - tp->chrono_start; - tp->chrono_start = now; - tp->chrono_type = new; + WRITE_ONCE(tp->chrono_stat[old - 1], + tp->chrono_stat[old - 1] + now - tp->chrono_start); + WRITE_ONCE(tp->chrono_start, now); + WRITE_ONCE(tp->chrono_type, new); } static inline void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 94e029c70247d..a33641b9ed7e4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4151,12 +4151,18 @@ static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) { u64 stats[__TCP_CHRONO_MAX], total = 0; - enum tcp_chrono i; + enum tcp_chrono i, cur; + /* Following READ_ONCE()s pair with WRITE_ONCE()s in tcp_chrono_set(). + * This is because socket lock might not be owned by us at this point. + * This is best effort, tcp_get_timestamping_opt_stats() can + * see wrong values. A real fix would be too costly for TCP fast path. + */ + cur = READ_ONCE(tp->chrono_type); for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { - stats[i] = tp->chrono_stat[i - 1]; - if (i == tp->chrono_type) - stats[i] += tcp_jiffies32 - tp->chrono_start; + stats[i] = READ_ONCE(tp->chrono_stat[i - 1]); + if (i == cur) + stats[i] += tcp_jiffies32 - READ_ONCE(tp->chrono_start); stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } From 9eb93126c0122c2c7a3b9c105a469934d6dec351 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:07 +0000 Subject: [PATCH 0812/1518] tcp: add data-race annotations around tp->data_segs_out and tp->total_retrans [ Upstream commit 21e92a38cfd891538598ba8f805e0165a820d532 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 7e98102f4897 ("tcp: record pkts sent and retransmistted") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-3-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_output.c | 8 +++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a33641b9ed7e4..4695b03f866f8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4386,9 +4386,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, - tp->data_segs_out, TCP_NLA_PAD); + READ_ONCE(tp->data_segs_out), TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, - tp->total_retrans, TCP_NLA_PAD); + READ_ONCE(tp->total_retrans), TCP_NLA_PAD); rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b00bd5044b322..c4cf76f71520f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1603,7 +1603,8 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); - tp->data_segs_out += tcp_skb_pcount(skb); + WRITE_ONCE(tp->data_segs_out, + tp->data_segs_out + tcp_skb_pcount(skb)); tp->bytes_sent += skb->len - tcp_header_size; } @@ -3556,7 +3557,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); - tp->total_retrans += segs; + WRITE_ONCE(tp->total_retrans, tp->total_retrans + segs); tp->bytes_retrans += skb->len; /* make sure skb->data is aligned on arches that require it @@ -4581,7 +4582,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) * However in this case, we are dealing with a passive fastopen * socket thus we can change total_retrans value. */ - tcp_sk_rw(sk)->total_retrans++; + WRITE_ONCE(tcp_sk_rw(sk)->total_retrans, + tcp_sk_rw(sk)->total_retrans + 1); } trace_tcp_retransmit_synack(sk, req); WRITE_ONCE(req->num_retrans, req->num_retrans + 1); From 9bce4d9c6da13991d84e2dc1711f09cd39e4df02 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:08 +0000 Subject: [PATCH 0813/1518] tcp: add data-races annotations around tp->reordering, tp->snd_cwnd [ Upstream commit 829ba1f329cb7cbd56d599a6d225997fba66dc32 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE(), WRITE_ONCE() data_race() annotations to keep KCSAN happy. Fixes: bb7c19f96012 ("tcp: add related fields into SCM_TIMESTAMPING_OPT_STATS") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-4-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 2 +- net/ipv4/tcp.c | 8 ++++---- net/ipv4/tcp_input.c | 14 ++++++++------ net/ipv4/tcp_metrics.c | 2 +- 4 files changed, 14 insertions(+), 12 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 236d9e0d35ed7..18381f4086d04 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1429,7 +1429,7 @@ static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) { WARN_ON_ONCE((int)val <= 0); - tp->snd_cwnd = val; + WRITE_ONCE(tp->snd_cwnd, val); } static inline bool tcp_in_slow_start(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4695b03f866f8..9e7e5ebcf14d5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4397,13 +4397,13 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, rate64 = tcp_compute_delivery_rate(tp); nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); - nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp)); - nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); - nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); + nla_put_u32(stats, TCP_NLA_SND_CWND, READ_ONCE(tp->snd_cwnd)); + nla_put_u32(stats, TCP_NLA_REORDERING, READ_ONCE(tp->reordering)); + nla_put_u32(stats, TCP_NLA_MIN_RTT, data_race(tcp_min_rtt(tp))); nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, READ_ONCE(inet_csk(sk)->icsk_retransmits)); - nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); + nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, data_race(!!tp->rate_app_limited)); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 96486eea26724..64e7bcbb42993 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1260,8 +1260,9 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, tp->sacked_out, tp->undo_marker ? tp->undo_retrans : 0); #endif - tp->reordering = min_t(u32, (metric + mss - 1) / mss, - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); + WRITE_ONCE(tp->reordering, + min_t(u32, (metric + mss - 1) / mss, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering))); } /* This exciting event is worth to be remembered. 8) */ @@ -2220,8 +2221,9 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) if (!tcp_limit_reno_sacked(tp)) return; - tp->reordering = min_t(u32, tp->packets_out + addend, - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); + WRITE_ONCE(tp->reordering, + min_t(u32, tp->packets_out + addend, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering))); tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } @@ -2360,8 +2362,8 @@ void tcp_enter_loss(struct sock *sk) reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering); if (icsk->icsk_ca_state <= TCP_CA_Disorder && tp->sacked_out >= reordering) - tp->reordering = min_t(unsigned int, tp->reordering, - reordering); + WRITE_ONCE(tp->reordering, + min_t(unsigned int, tp->reordering, reordering)); tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 45b6ecd164126..170ca11edf6b9 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -496,7 +496,7 @@ void tcp_init_metrics(struct sock *sk) } val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val && tp->reordering != val) - tp->reordering = val; + WRITE_ONCE(tp->reordering, val); crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); From d8068252f0435938ccb36e24e9c07475e5dff381 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:09 +0000 Subject: [PATCH 0814/1518] tcp: annotate data-races around tp->snd_ssthresh [ Upstream commit fd571afb05ebaeac5d8f09460a0640d4cf6755f8 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 7156d194a077 ("tcp: add snd_ssthresh stat in SCM_TIMESTAMPING_OPT_STATS") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-5-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/filter.c | 2 +- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_bbr.c | 6 +++--- net/ipv4/tcp_bic.c | 2 +- net/ipv4/tcp_cdg.c | 4 ++-- net/ipv4/tcp_cubic.c | 6 +++--- net/ipv4/tcp_dctcp.c | 2 +- net/ipv4/tcp_input.c | 8 ++++---- net/ipv4/tcp_metrics.c | 4 ++-- net/ipv4/tcp_nv.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++-- net/ipv4/tcp_vegas.c | 9 +++++---- net/ipv4/tcp_westwood.c | 4 ++-- net/ipv4/tcp_yeah.c | 3 ++- 14 files changed, 32 insertions(+), 30 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index ae6d0453cf123..bad3fb6318461 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5387,7 +5387,7 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, if (val <= 0) return -EINVAL; tp->snd_cwnd_clamp = val; - tp->snd_ssthresh = val; + WRITE_ONCE(tp->snd_ssthresh, val); break; case TCP_BPF_DELACK_MAX: timeout = usecs_to_jiffies(val); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9e7e5ebcf14d5..3de09b59663d8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3408,7 +3408,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_rto = TCP_TIMEOUT_INIT; WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN); WRITE_ONCE(icsk->icsk_delack_max, TCP_DELACK_MAX); - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + WRITE_ONCE(tp->snd_ssthresh, TCP_INFINITE_SSTHRESH); tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; tp->is_cwnd_limited = 0; @@ -4404,7 +4404,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, READ_ONCE(inet_csk(sk)->icsk_retransmits)); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, data_race(!!tp->rate_app_limited)); - nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); + nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, READ_ONCE(tp->snd_ssthresh)); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 760941e55153e..3df6160f51567 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -896,8 +896,8 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { bbr->mode = BBR_DRAIN; /* drain queue we created */ - tcp_sk(sk)->snd_ssthresh = - bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT); + WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, + bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT)); } /* fall through to check if in-flight is already small: */ if (bbr->mode == BBR_DRAIN && bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <= @@ -1042,7 +1042,7 @@ __bpf_kfunc static void bbr_init(struct sock *sk) struct bbr *bbr = inet_csk_ca(sk); bbr->prior_cwnd = 0; - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + WRITE_ONCE(tp->snd_ssthresh, TCP_INFINITE_SSTHRESH); bbr->rtt_cnt = 0; bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 58358bf92e1b8..65444ff142413 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -74,7 +74,7 @@ static void bictcp_init(struct sock *sk) bictcp_reset(ca); if (initial_ssthresh) - tcp_sk(sk)->snd_ssthresh = initial_ssthresh; + WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, initial_ssthresh); } /* diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index fbad6c35dee9c..37f094204b6d0 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -162,7 +162,7 @@ static void tcp_cdg_hystart_update(struct sock *sk) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINCWND, tcp_snd_cwnd(tp)); - tp->snd_ssthresh = tcp_snd_cwnd(tp); + WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp)); return; } } @@ -181,7 +181,7 @@ static void tcp_cdg_hystart_update(struct sock *sk) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYCWND, tcp_snd_cwnd(tp)); - tp->snd_ssthresh = tcp_snd_cwnd(tp); + WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp)); } } } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 76c23675ae50a..f891e8d1e5458 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -136,7 +136,7 @@ __bpf_kfunc static void cubictcp_init(struct sock *sk) bictcp_hystart_reset(sk); if (!hystart && initial_ssthresh) - tcp_sk(sk)->snd_ssthresh = initial_ssthresh; + WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, initial_ssthresh); } __bpf_kfunc static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) @@ -423,7 +423,7 @@ static void hystart_update(struct sock *sk, u32 delay) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINCWND, tcp_snd_cwnd(tp)); - tp->snd_ssthresh = tcp_snd_cwnd(tp); + WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp)); } } } @@ -443,7 +443,7 @@ static void hystart_update(struct sock *sk, u32 delay) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYCWND, tcp_snd_cwnd(tp)); - tp->snd_ssthresh = tcp_snd_cwnd(tp); + WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp)); } } } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 03abe0848420d..6f103038b0152 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -177,7 +177,7 @@ static void dctcp_react_to_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); ca->loss_cwnd = tcp_snd_cwnd(tp); - tp->snd_ssthresh = max(tcp_snd_cwnd(tp) >> 1U, 2U); + WRITE_ONCE(tp->snd_ssthresh, max(tcp_snd_cwnd(tp) >> 1U, 2U)); } __bpf_kfunc static void dctcp_state(struct sock *sk, u8 new_state) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 64e7bcbb42993..16bb525c04f1d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2348,7 +2348,7 @@ void tcp_enter_loss(struct sock *sk) (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) { tp->prior_ssthresh = tcp_current_ssthresh(sk); tp->prior_cwnd = tcp_snd_cwnd(tp); - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); + WRITE_ONCE(tp->snd_ssthresh, icsk->icsk_ca_ops->ssthresh(sk)); tcp_ca_event(sk, CA_EVENT_LOSS); tcp_init_undo(tp); } @@ -2641,7 +2641,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tcp_snd_cwnd_set(tp, icsk->icsk_ca_ops->undo_cwnd(sk)); if (tp->prior_ssthresh > tp->snd_ssthresh) { - tp->snd_ssthresh = tp->prior_ssthresh; + WRITE_ONCE(tp->snd_ssthresh, tp->prior_ssthresh); tcp_ecn_withdraw_cwr(tp); } } @@ -2759,7 +2759,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) tp->prior_cwnd = tcp_snd_cwnd(tp); tp->prr_delivered = 0; tp->prr_out = 0; - tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); + WRITE_ONCE(tp->snd_ssthresh, inet_csk(sk)->icsk_ca_ops->ssthresh(sk)); tcp_ecn_queue_cwr(tp); } @@ -2901,7 +2901,7 @@ static void tcp_non_congestion_loss_retransmit(struct sock *sk) if (icsk->icsk_ca_state != TCP_CA_Loss) { tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); + WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk)); tp->prior_ssthresh = 0; tp->undo_marker = 0; tcp_set_ca_state(sk, TCP_CA_Loss); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 170ca11edf6b9..7b08d3e58a741 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -490,9 +490,9 @@ void tcp_init_metrics(struct sock *sk) val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ? 0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val) { - tp->snd_ssthresh = val; + WRITE_ONCE(tp->snd_ssthresh, val); if (tp->snd_ssthresh > tp->snd_cwnd_clamp) - tp->snd_ssthresh = tp->snd_cwnd_clamp; + WRITE_ONCE(tp->snd_ssthresh, tp->snd_cwnd_clamp); } val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val && tp->reordering != val) diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index a60662f4bdf92..f345897a68dfc 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -396,8 +396,8 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) /* We have enough data to determine we are congested */ ca->nv_allow_cwnd_growth = 0; - tp->snd_ssthresh = - (nv_ssthresh_factor * max_win) >> 3; + WRITE_ONCE(tp->snd_ssthresh, + (nv_ssthresh_factor * max_win) >> 3); if (tcp_snd_cwnd(tp) - max_win > 2) { /* gap > 2, we do exponential cwnd decrease */ int dec; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c4cf76f71520f..3c25292ae72d8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -151,7 +151,7 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta) tcp_ca_event(sk, CA_EVENT_CWND_RESTART); - tp->snd_ssthresh = tcp_current_ssthresh(sk); + WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk)); restart_cwnd = min(restart_cwnd, cwnd); while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) @@ -2060,7 +2060,7 @@ static void tcp_cwnd_application_limited(struct sock *sk) u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 win_used = max(tp->snd_cwnd_used, init_win); if (win_used < tcp_snd_cwnd(tp)) { - tp->snd_ssthresh = tcp_current_ssthresh(sk); + WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk)); tcp_snd_cwnd_set(tp, (tcp_snd_cwnd(tp) + win_used) >> 1); } tp->snd_cwnd_used = 0; diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 786848ad37ea8..3ec7308441a78 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -240,7 +240,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) */ tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), (u32)target_cwnd + 1)); - tp->snd_ssthresh = tcp_vegas_ssthresh(tp); + WRITE_ONCE(tp->snd_ssthresh, + tcp_vegas_ssthresh(tp)); } else if (tcp_in_slow_start(tp)) { /* Slow start. */ @@ -256,8 +257,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) * we slow down. */ tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1); - tp->snd_ssthresh - = tcp_vegas_ssthresh(tp); + WRITE_ONCE(tp->snd_ssthresh, + tcp_vegas_ssthresh(tp)); } else if (diff < alpha) { /* We don't have enough extra packets * in the network, so speed up. @@ -275,7 +276,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) else if (tcp_snd_cwnd(tp) > tp->snd_cwnd_clamp) tcp_snd_cwnd_set(tp, tp->snd_cwnd_clamp); - tp->snd_ssthresh = tcp_current_ssthresh(sk); + WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk)); } /* Wipe the slate clean for the next RTT. */ diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index c6e97141eef25..b5a42adfd6ca1 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -244,11 +244,11 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event) switch (event) { case CA_EVENT_COMPLETE_CWR: - tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk); + WRITE_ONCE(tp->snd_ssthresh, tcp_westwood_bw_rttmin(sk)); tcp_snd_cwnd_set(tp, tp->snd_ssthresh); break; case CA_EVENT_LOSS: - tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk); + WRITE_ONCE(tp->snd_ssthresh, tcp_westwood_bw_rttmin(sk)); /* Update RTT_min when next ack arrives */ w->reset_rtt_min = 1; break; diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 18b07ff5d20e6..74a2538e79e06 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -147,7 +147,8 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) tcp_snd_cwnd_set(tp, max(tcp_snd_cwnd(tp), yeah->reno_count)); - tp->snd_ssthresh = tcp_snd_cwnd(tp); + WRITE_ONCE(tp->snd_ssthresh, + tcp_snd_cwnd(tp)); } if (yeah->reno_count <= 2) From 4215a5c7b07981fcb5c59470797f4d0e8718474e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:10 +0000 Subject: [PATCH 0815/1518] tcp: annotate data-races around tp->delivered and tp->delivered_ce [ Upstream commit faa886ad3ce5fc8f5156493491fe189b2b726bc9 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: feb5f2ec6464 ("tcp: export packets delivery info") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-6-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp_ecn.h | 2 +- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 8 ++++---- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index a709fb1756eb7..59d6944f8d103 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -189,7 +189,7 @@ static inline void tcp_accecn_third_ack(struct sock *sk, tcp_accecn_validate_syn_feedback(sk, ace, sent_ect)) { if ((tcp_accecn_extract_syn_ect(ace) == INET_ECN_CE) && !tp->delivered_ce) - tp->delivered_ce++; + WRITE_ONCE(tp->delivered_ce, 1); } break; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3de09b59663d8..515313ef0c642 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4405,8 +4405,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, READ_ONCE(inet_csk(sk)->icsk_retransmits)); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, data_race(!!tp->rate_app_limited)); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, READ_ONCE(tp->snd_ssthresh)); - nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); - nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); + nla_put_u32(stats, TCP_NLA_DELIVERED, READ_ONCE(tp->delivered)); + nla_put_u32(stats, TCP_NLA_DELIVERED_CE, READ_ONCE(tp->delivered_ce)); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 16bb525c04f1d..b5a3c7ca2605d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -476,14 +476,14 @@ static bool tcp_accecn_process_option(struct tcp_sock *tp, static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count) { - tp->delivered_ce += ecn_count; + WRITE_ONCE(tp->delivered_ce, tp->delivered_ce + ecn_count); } /* Updates the delivered and delivered_ce counts */ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, bool ece_ack) { - tp->delivered += delivered; + WRITE_ONCE(tp->delivered, tp->delivered + delivered); if (tcp_ecn_mode_rfc3168(tp) && ece_ack) tcp_count_delivered_ce(tp, delivered); } @@ -6576,7 +6576,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); /* SYN-data is counted as two separate packets in tcp_ack() */ if (tp->delivered > 1) - --tp->delivered; + WRITE_ONCE(tp->delivered, tp->delivered - 1); } tcp_fastopen_add_skb(sk, synack); @@ -7007,7 +7007,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) SKB_DR_SET(reason, NOT_SPECIFIED); switch (sk->sk_state) { case TCP_SYN_RECV: - tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */ + WRITE_ONCE(tp->delivered, tp->delivered + 1); /* SYN-ACK delivery isn't tracked in tcp_ack */ if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); From 5987cec30473c58f29df33625b9270ce2e5d88f6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:11 +0000 Subject: [PATCH 0816/1518] tcp: add data-race annotations for TCP_NLA_SNDQ_SIZE [ Upstream commit 124199444de467767175a9004e1574dc42523e62 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 87ecc95d81d9 ("tcp: add send queue size stat in SCM_TIMESTAMPING_OPT_STATS") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-7-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 4 +++- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_output.c | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 515313ef0c642..0d6e991155c95 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4408,7 +4408,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u32(stats, TCP_NLA_DELIVERED, READ_ONCE(tp->delivered)); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, READ_ONCE(tp->delivered_ce)); - nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); + nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, + max_t(int, 0, + READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_una))); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b5a3c7ca2605d..3e29134a54b19 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3694,7 +3694,7 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) sock_owned_by_me((struct sock *)tp); tp->bytes_acked += delta; tcp_snd_sne_update(tp, ack); - tp->snd_una = ack; + WRITE_ONCE(tp->snd_una, ack); } static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq) @@ -7035,7 +7035,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (sk->sk_socket) sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); - tp->snd_una = TCP_SKB_CB(skb)->ack_seq; + WRITE_ONCE(tp->snd_una, TCP_SKB_CB(skb)->ack_seq); tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3c25292ae72d8..e6aa54d2335c0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -4089,7 +4089,7 @@ static void tcp_connect_init(struct sock *sk) tp->snd_wnd = 0; tcp_init_wl(tp, 0); tcp_write_queue_purge(sk); - tp->snd_una = tp->write_seq; + WRITE_ONCE(tp->snd_una, tp->write_seq); tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; WRITE_ONCE(tp->snd_nxt, tp->write_seq); From d0ae38a0ee95441954137b4e4dde3f9493030269 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:12 +0000 Subject: [PATCH 0817/1518] tcp: annotate data-races around tp->bytes_sent [ Upstream commit ee43e957ce2ec77b2ec47fef28f3c0df6ab01a31 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: ba113c3aa79a ("tcp: add data bytes sent stats") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-8-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_output.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d6e991155c95..7d45a2aab18dd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4413,7 +4413,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_una))); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); - nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, + nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, READ_ONCE(tp->bytes_sent), TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e6aa54d2335c0..c2492f4be2151 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1605,7 +1605,8 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tcp_event_data_sent(tp, sk); WRITE_ONCE(tp->data_segs_out, tp->data_segs_out + tcp_skb_pcount(skb)); - tp->bytes_sent += skb->len - tcp_header_size; + WRITE_ONCE(tp->bytes_sent, + tp->bytes_sent + skb->len - tcp_header_size); } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) From b208984309842b8c13d7a4ea8c872b9bfb172e07 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:13 +0000 Subject: [PATCH 0818/1518] tcp: annotate data-races around tp->bytes_retrans [ Upstream commit 5efc7b9f7cbd43401f1af81d3d7f2be00f93390d ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: fb31c9b9f6c8 ("tcp: add data bytes retransmitted stats") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-9-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_output.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7d45a2aab18dd..35c444caab8a8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4415,8 +4415,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, READ_ONCE(tp->bytes_sent), TCP_NLA_PAD); - nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, - TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, + READ_ONCE(tp->bytes_retrans), TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c2492f4be2151..5a443fb14a973 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3559,7 +3559,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); WRITE_ONCE(tp->total_retrans, tp->total_retrans + segs); - tp->bytes_retrans += skb->len; + WRITE_ONCE(tp->bytes_retrans, tp->bytes_retrans + skb->len); /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom From 7fc9ef56acfe9d74f8d73b5a8b130200a37bcccb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:14 +0000 Subject: [PATCH 0819/1518] tcp: annotate data-races around tp->dsack_dups [ Upstream commit a984705ca88b976bf1087978fd98b7f3993da88c ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 7e10b6554ff2 ("tcp: add dsack blocks received stats") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-10-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_input.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 35c444caab8a8..3a5801ba3df1a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4417,7 +4417,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, READ_ONCE(tp->bytes_retrans), TCP_NLA_PAD); - nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); + nla_put_u32(stats, TCP_NLA_DSACK_DUPS, READ_ONCE(tp->dsack_dups)); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3e29134a54b19..90727e1e581e4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1213,7 +1213,7 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq, else if (tp->tlp_high_seq && tp->tlp_high_seq == end_seq) state->flag |= FLAG_DSACK_TLP; - tp->dsack_dups += dup_segs; + WRITE_ONCE(tp->dsack_dups, tp->dsack_dups + dup_segs); /* Skip the DSACK if dup segs weren't retransmitted by sender */ if (tp->dsack_dups > tp->total_retrans) return 0; From 3955bfec74ab41925252951f2364fb7e4c2b2752 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:15 +0000 Subject: [PATCH 0820/1518] tcp: annotate data-races around tp->reord_seen [ Upstream commit 62585690e6b2a112c408fe25f142b246ac833c42 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 7ec65372ca53 ("tcp: add stat of data packet reordering events") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-11-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_input.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3a5801ba3df1a..03299c21e4d68 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4418,7 +4418,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, READ_ONCE(tp->bytes_retrans), TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, READ_ONCE(tp->dsack_dups)); - nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); + nla_put_u32(stats, TCP_NLA_REORD_SEEN, READ_ONCE(tp->reord_seen)); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 90727e1e581e4..5a944b1ec320c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1266,7 +1266,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, } /* This exciting event is worth to be remembered. 8) */ - tp->reord_seen++; + WRITE_ONCE(tp->reord_seen, tp->reord_seen + 1); NET_INC_STATS(sock_net(sk), ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER); } @@ -2224,7 +2224,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) WRITE_ONCE(tp->reordering, min_t(u32, tp->packets_out + addend, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering))); - tp->reord_seen++; + WRITE_ONCE(tp->reord_seen, tp->reord_seen + 1); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } From cd6011dc4c339b83a853901d9772e8e07927ddc3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Oct 2025 14:59:26 +0000 Subject: [PATCH 0821/1518] tcp: better handle TCP_TX_DELAY on established flows [ Upstream commit 1c51450f1afff1e7419797720df3fbd9ccbf610c ] Some applications uses TCP_TX_DELAY socket option after TCP flow is established. Some metrics need to be updated, otherwise TCP might take time to adapt to the new (emulated) RTT. This patch adjusts tp->srtt_us, tp->rtt_min, icsk_rto and sk->sk_pacing_rate. This is best effort, and for instance icsk_rto is reset without taking backoff into account. Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20251013145926.833198-1-edumazet@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: 290b693ce7c9 ("tcp: annotate data-races around tp->srtt_us") Signed-off-by: Sasha Levin --- include/net/tcp.h | 2 ++ net/ipv4/tcp.c | 31 +++++++++++++++++++++++++++---- net/ipv4/tcp_input.c | 4 ++-- 3 files changed, 31 insertions(+), 6 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 18381f4086d04..cf507b989bff1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -462,6 +462,8 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); +void tcp_update_pacing_rate(struct sock *sk); +void tcp_set_rto(struct sock *sk); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 03299c21e4d68..2e62441515fee 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3585,9 +3585,12 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); EXPORT_IPV6_MOD(tcp_tx_delay_enabled); -static void tcp_enable_tx_delay(void) +static void tcp_enable_tx_delay(struct sock *sk, int val) { - if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { + struct tcp_sock *tp = tcp_sk(sk); + s32 delta = (val - tp->tcp_tx_delay) << 3; + + if (val && !static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { @@ -3595,6 +3598,22 @@ static void tcp_enable_tx_delay(void) pr_info("TCP_TX_DELAY enabled\n"); } } + /* If we change tcp_tx_delay on a live flow, adjust tp->srtt_us, + * tp->rtt_min, icsk_rto and sk->sk_pacing_rate. + * This is best effort. + */ + if (delta && sk->sk_state == TCP_ESTABLISHED) { + s64 srtt = (s64)tp->srtt_us + delta; + + tp->srtt_us = clamp_t(s64, srtt, 1, ~0U); + + /* Note: does not deal with non zero icsk_backoff */ + tcp_set_rto(sk); + + minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); + + tcp_update_pacing_rate(sk); + } } /* When set indicates to always queue non-full frames. Later the user clears @@ -4121,8 +4140,12 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, tp->recvmsg_inq = val; break; case TCP_TX_DELAY: - if (val) - tcp_enable_tx_delay(); + /* tp->srtt_us is u32, and is shifted by 3 */ + if (val < 0 || val >= (1U << (31 - 3))) { + err = -EINVAL; + break; + } + tcp_enable_tx_delay(sk, val); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5a944b1ec320c..e8ba52c908da1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1102,7 +1102,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->srtt_us = max(1U, srtt); } -static void tcp_update_pacing_rate(struct sock *sk) +void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u64 rate; @@ -1139,7 +1139,7 @@ static void tcp_update_pacing_rate(struct sock *sk) /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ -static void tcp_set_rto(struct sock *sk) +void tcp_set_rto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) From 0edffaf11267c84d9c285886ec591da9f1d83faf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:16 +0000 Subject: [PATCH 0822/1518] tcp: annotate data-races around tp->srtt_us [ Upstream commit 290b693ce7c9d48588d88b15a782a3efc6fa036b ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: e8bd8fca6773 ("tcp: add SRTT to SCM_TIMESTAMPING_OPT_STATS") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-12-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 5 +++-- net/ipv4/tcp_input.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2e62441515fee..a799329281532 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3605,7 +3605,8 @@ static void tcp_enable_tx_delay(struct sock *sk, int val) if (delta && sk->sk_state == TCP_ESTABLISHED) { s64 srtt = (s64)tp->srtt_us + delta; - tp->srtt_us = clamp_t(s64, srtt, 1, ~0U); + WRITE_ONCE(tp->srtt_us, + clamp_t(s64, srtt, 1, ~0U)); /* Note: does not deal with non zero icsk_backoff */ tcp_set_rto(sk); @@ -4442,7 +4443,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, READ_ONCE(tp->bytes_retrans), TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, READ_ONCE(tp->dsack_dups)); nla_put_u32(stats, TCP_NLA_REORD_SEEN, READ_ONCE(tp->reord_seen)); - nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); + nla_put_u32(stats, TCP_NLA_SRTT, READ_ONCE(tp->srtt_us) >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e8ba52c908da1..5fb5f3f6393c1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1099,7 +1099,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tcp_bpf_rtt(sk, mrtt_us, srtt); } - tp->srtt_us = max(1U, srtt); + WRITE_ONCE(tp->srtt_us, max(1U, srtt)); } void tcp_update_pacing_rate(struct sock *sk) From 37f33454b284ebfeccb8390c62a334df94ebdca2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:17 +0000 Subject: [PATCH 0823/1518] tcp: annotate data-races around tp->timeout_rehash [ Upstream commit 71c675358b711bbfd8528949249419dc2dfa4ce1 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 32efcc06d2a1 ("tcp: export count for rehash attempts") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-13-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a799329281532..888fe31e42f0b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4444,7 +4444,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u32(stats, TCP_NLA_DSACK_DUPS, READ_ONCE(tp->dsack_dups)); nla_put_u32(stats, TCP_NLA_REORD_SEEN, READ_ONCE(tp->reord_seen)); nla_put_u32(stats, TCP_NLA_SRTT, READ_ONCE(tp->srtt_us) >> 3); - nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); + nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, + READ_ONCE(tp->timeout_rehash)); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 2dd73a4e8e517..b2e5848b6980a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -296,7 +296,7 @@ static int tcp_write_timeout(struct sock *sk) } if (sk_rethink_txhash(sk)) { - tp->timeout_rehash++; + WRITE_ONCE(tp->timeout_rehash, tp->timeout_rehash + 1); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); } From 4d1ea8a2c6ac30d95948d1a02c77617d4f813418 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:18 +0000 Subject: [PATCH 0824/1518] tcp: annotate data-races around (tp->write_seq - tp->snd_nxt) [ Upstream commit 3a63b3d160560ef51e43fb4c880a5cde8078053c ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() annotations to keep KCSAN happy. WRITE_ONCE() annotations are already present. Fixes: e08ab0b377a1 ("tcp: add bytes not sent to SCM_TIMESTAMPING_OPT_STATS") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-14-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 888fe31e42f0b..fe91675ae5678 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4447,7 +4447,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, READ_ONCE(tp->timeout_rehash)); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, - max_t(int, 0, tp->write_seq - tp->snd_nxt)); + max_t(int, 0, + READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt))); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); if (ack_skb) From 1b579c2001d06c00f4424c240b8f68f6f97950aa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 20:03:19 +0000 Subject: [PATCH 0825/1518] tcp: annotate data-races around tp->plb_rehash [ Upstream commit 9e89b9d03a2d2e30dcca166d5af52f9a8eceab25 ] tcp_get_timestamping_opt_stats() intentionally runs lockless, we must add READ_ONCE() and WRITE_ONCE() annotations to keep KCSAN happy. Fixes: 29c1c44646ae ("tcp: add u32 counter in tcp_sock and an SNMP counter for PLB") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260416200319.3608680-15-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_plb.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fe91675ae5678..2de4748269ca9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4455,7 +4455,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); - nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); + nla_put_u32(stats, TCP_NLA_REHASH, + READ_ONCE(tp->plb_rehash) + READ_ONCE(tp->timeout_rehash)); return stats; } diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c index 4bcf7eff95e39..b7f9b60d8991f 100644 --- a/net/ipv4/tcp_plb.c +++ b/net/ipv4/tcp_plb.c @@ -79,7 +79,7 @@ void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb) sk_rethink_txhash(sk); plb->consec_cong_rounds = 0; - tcp_sk(sk)->plb_rehash++; + WRITE_ONCE(tcp_sk(sk)->plb_rehash, tcp_sk(sk)->plb_rehash + 1); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH); } EXPORT_SYMBOL_GPL(tcp_plb_check_rehash); From 722fcf831107ae25f258a4ec79263203dc3c3fd9 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Thu, 16 Apr 2026 17:53:25 -0700 Subject: [PATCH 0826/1518] ice: fix 'adjust' timer programming for E830 devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 885c5e57924dc040b23d0ad0d8388f0e35772159 ] Fix incorrect 'adjust the timer' programming sequence for E830 devices series. Only shadow registers GLTSYN_SHADJ were programmed in the current implementation. According to the specification [1], write to command GLTSYN_CMD register is also required with CMD field set to "Adjust the Time" value, for the timer adjustment to take the effect. The flow was broken for the adjustment less than S32_MAX/MIN range (around +/- 2 seconds). For bigger adjustment, non-atomic programming flow is used, involving set timer programming. Non-atomic flow is implemented correctly. Testing hints: Run command: phc_ctl /dev/ptpX get adj 2 get Expected result: Returned timestamps differ at least by 2 seconds [1] Intel® Ethernet Controller E830 Datasheet rev 1.3, chapter 9.7.5.4 https://cdrdv2.intel.com/v1/dl/getContent/787353?explicitVersion=true Fixes: f00307522786 ("ice: Implement PTP support for E830 devices") Reviewed-by: Aleksandr Loktionov Signed-off-by: Grzegorz Nitka Reviewed-by: Simon Horman Tested-by: Rinitha S Reviewed-by: Jacob Keller Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-1-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 35680dbe4a7f7..161a0ae8599c1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -5381,8 +5381,8 @@ int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval) */ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) { + int err = 0; u8 tmr_idx; - int err; tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; @@ -5399,8 +5399,8 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) err = ice_ptp_prep_phy_adj_e810(hw, adj); break; case ICE_MAC_E830: - /* E830 sync PHYs automatically after setting GLTSYN_SHADJ */ - return 0; + /* E830 sync PHYs automatically after setting cmd register */ + break; case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_adj_e82x(hw, adj); break; From 05fd391f9065561bf8cab4307aac96f7338c6a9e Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Thu, 16 Apr 2026 17:53:26 -0700 Subject: [PATCH 0827/1518] ice: update PCS latency settings for E825 10G/25Gb modes [ Upstream commit 05567e4052732d70c7ff9655217b3d14d25f639a ] Update MAC Rx/Tx offset registers settings (PHY_MAC_[RX|TX]_OFFSET registers) with the data obtained with the latest research. It applies to PCS latency settings for the following speeds/modes: * 10Gb NO-FEC - TX latency changed from 71.25 ns to 73 ns - RX latency changed from -25.6 ns to -28 ns * 25Gb NO-FEC - TX latency changed from 28.17 ns to 33 ns - RX latency changed from -12.45 ns to -12 ns * 25Gb RS-FEC - TX latency changed from 64.5 ns to 69 ns - RX latency changed from -3.6 ns to -3 ns The original data came from simulation and pre-production hardware. The new data measures the actual delays and as such is more accurate. Fixes: 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Co-developed-by: Zoltan Fodor Signed-off-by: Zoltan Fodor Reviewed-by: Aleksandr Loktionov Reviewed-by: Jacob Keller Signed-off-by: Grzegorz Nitka Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-2-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_consts.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index 19dddd9b53ddd..4d298c27bfb27 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -78,14 +78,14 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = { .blktime = 0x666, /* 3.2 */ .tx_offset = { .serdes = 0x234c, /* 17.6484848 */ - .no_fec = 0x8e80, /* 71.25 */ + .no_fec = 0x93d9, /* 73 */ .fc = 0xb4a4, /* 90.32 */ .sfd = 0x4a4, /* 2.32 */ .onestep = 0x4ccd /* 38.4 */ }, .rx_offset = { .serdes = 0xffffeb27, /* -10.42424 */ - .no_fec = 0xffffcccd, /* -25.6 */ + .no_fec = 0xffffc7b6, /* -28 */ .fc = 0xfffc557b, /* -469.26 */ .sfd = 0x4a4, /* 2.32 */ .bs_ds = 0x32 /* 0.0969697 */ @@ -118,17 +118,17 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = { .mktime = 0x147b, /* 10.24, only if RS-FEC enabled */ .tx_offset = { .serdes = 0xe1e, /* 7.0593939 */ - .no_fec = 0x3857, /* 28.17 */ + .no_fec = 0x4266, /* 33 */ .fc = 0x48c3, /* 36.38 */ - .rs = 0x8100, /* 64.5 */ + .rs = 0x8a00, /* 69 */ .sfd = 0x1dc, /* 0.93 */ .onestep = 0x1eb8 /* 15.36 */ }, .rx_offset = { .serdes = 0xfffff7a9, /* -4.1697 */ - .no_fec = 0xffffe71a, /* -12.45 */ + .no_fec = 0xffffe700, /* -12 */ .fc = 0xfffe894d, /* -187.35 */ - .rs = 0xfffff8cd, /* -3.6 */ + .rs = 0xfffff8cc, /* -3 */ .sfd = 0x1dc, /* 0.93 */ .bs_ds = 0x14 /* 0.0387879, RS-FEC 0 */ } From 55500245ec0420df96b2a89444aabf0cff2c60bc Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Thu, 5 Feb 2026 15:39:20 +0200 Subject: [PATCH 0828/1518] ice: Remove jumbo_remove step from TX path [ Upstream commit 8b76102c5e00d1f090e0c31d17b060c76d8fa859 ] Now that the kernel doesn't insert HBH for BIG TCP IPv6 packets, remove unnecessary steps from the ice TX path, that used to check and remove HBH. Signed-off-by: Alice Mikityanska Acked-by: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260205133925.526371-8-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski Stable-dep-of: 1a303baa715e ("ice: fix double-free of tx_buf skb") Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_txrx.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 73f08d02f9c76..90dbe5266ce78 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2594,9 +2594,6 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) ice_trace(xmit_frame_ring, tx_ring, skb); - if (unlikely(ipv6_hopopt_jumbo_remove(skb))) - goto out_drop; - count = ice_xmit_desc_count(skb); if (ice_chk_linearize(skb, count)) { if (__skb_linearize(skb)) From 7cb19ec8ac087f33bee60f5d6054b284a5b9bb6f Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Thu, 16 Apr 2026 17:53:28 -0700 Subject: [PATCH 0829/1518] ice: fix double-free of tx_buf skb [ Upstream commit 1a303baa715e6b78d6a406aaf335f87ff35acfcd ] If ice_tso() or ice_tx_csum() fail, the error path in ice_xmit_frame_ring() frees the skb, but the 'first' tx_buf still points to it and is marked as valid (ICE_TX_BUF_SKB). 'next_to_use' remains unchanged, so the potential problem will likely fix itself when the next packet is transmitted and the tx_buf gets overwritten. But if there is no next packet and the interface is brought down instead, ice_clean_tx_ring() -> ice_unmap_and_free_tx_buf() will find the tx_buf and free the skb for the second time. The fix is to reset the tx_buf type to ICE_TX_BUF_EMPTY in the error path, so that ice_unmap_and_free_tx_buf(). Move the initialization of 'first' up, to ensure it's already valid in case we hit the linearization error path. The bug was spotted by AI while I had it looking for something else. It also proposed an initial version of the patch. I reproduced the bug and tested the fix by adding code to inject failures, on a build with KASAN. I looked for similar bugs in related Intel drivers and did not find any. Fixes: d76a60ba7afb ("ice: Add support for VLANs and offloads") Assisted-by: Claude:claude-4.6-opus-high Cursor Signed-off-by: Michal Schmidt Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-4-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_txrx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 90dbe5266ce78..e0774a640955d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2594,6 +2594,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) ice_trace(xmit_frame_ring, tx_ring, skb); + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buf[tx_ring->next_to_use]; + count = ice_xmit_desc_count(skb); if (ice_chk_linearize(skb, count)) { if (__skb_linearize(skb)) @@ -2619,8 +2622,6 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.tx_ring = tx_ring; - /* record the location of the first descriptor for this packet */ - first = &tx_ring->tx_buf[tx_ring->next_to_use]; first->skb = skb; first->type = ICE_TX_BUF_SKB; first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN); @@ -2685,6 +2686,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) out_drop: ice_trace(xmit_frame_ring_drop, tx_ring, skb); dev_kfree_skb_any(skb); + first->type = ICE_TX_BUF_EMPTY; return NETDEV_TX_OK; } From 3c5c3ac308a762bdb57d9267ede849d7c5e5ebde Mon Sep 17 00:00:00 2001 From: Paul Greenwalt Date: Thu, 16 Apr 2026 17:53:30 -0700 Subject: [PATCH 0830/1518] ice: fix ICE_AQ_LINK_SPEED_M for 200G [ Upstream commit 4a3a940059e98539de293a6e36e464094c2e875b ] When setting PHY configuration during driver initialization, 200G link speed is not being advertised even when the PHY is capable. This is because the get PHY capabilities link speed response is being masked by ICE_AQ_LINK_SPEED_M, which does not include the 200G link speed bit. ICE_AQ_LINK_SPEED_200GB is defined as BIT(11), but the mask 0x7FF only covers bits 0-10. Fix ICE_AQ_LINK_SPEED_M to use GENMASK(11, 0) so that it covers all defined link speed bits including 200G. Fixes: 24407a01e57c ("ice: Add 200G speed/phy type use") Signed-off-by: Paul Greenwalt Signed-off-by: Aleksandr Loktionov Reviewed-by: Simon Horman Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-6-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 859e9c66f3e7e..3cbb1b0582e32 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1252,7 +1252,7 @@ struct ice_aqc_get_link_status_data { #define ICE_AQ_LINK_PWR_QSFP_CLASS_3 2 #define ICE_AQ_LINK_PWR_QSFP_CLASS_4 3 __le16 link_speed; -#define ICE_AQ_LINK_SPEED_M 0x7FF +#define ICE_AQ_LINK_SPEED_M GENMASK(11, 0) #define ICE_AQ_LINK_SPEED_10MB BIT(0) #define ICE_AQ_LINK_SPEED_100MB BIT(1) #define ICE_AQ_LINK_SPEED_1000MB BIT(2) From 3c29ddd46aba05b12801d07bed394f649e3e4cca Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Thu, 16 Apr 2026 17:53:33 -0700 Subject: [PATCH 0831/1518] i40e: don't advertise IFF_SUPP_NOFCS [ Upstream commit a24162f18825684ad04e3a5d0531f8a50d679347 ] i40e advertises IFF_SUPP_NOFCS, allowing users to use the SO_NOFCS socket option. However, this option is silently ignored, as the driver does not check skb->no_fcs, and always enables FCS insertion offload. Fix this by removing the advertisement of IFF_SUPP_NOFCS. This behavior can be reproduced with a simple AF_PACKET socket: import socket s = socket.socket(socket.AF_PACKET, socket.SOCK_RAW) s.setsockopt(socket.SOL_SOCKET, 43, 1) # SO_NOFCS s.bind(("eth0", 0)) s.send(b'\xff' * 64) Previously, send() succeeds but the driver ignores SO_NOFCS. With this change, send() fails with -EPROTONOSUPPORT, as expected. Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Kohei Enju Reviewed-by: Aleksandr Loktionov Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-9-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 598739220dfb9..9f19370f1c87a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13784,7 +13784,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->neigh_priv_len = sizeof(u32) * 4; netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->priv_flags |= IFF_SUPP_NOFCS; /* Setup netdev TC information */ i40e_vsi_config_netdev_tc(vsi, vsi->tc_config.enabled_tc); From 15c666a99626eb13889554d6df8ff90c54dff71c Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Thu, 16 Apr 2026 17:53:34 -0700 Subject: [PATCH 0832/1518] iavf: fix wrong VLAN mask for legacy Rx descriptors L2TAG2 [ Upstream commit 496d9f91062fa07956702e0f234c5203f03a974d ] The IAVF_RXD_LEGACY_L2TAG2_M mask was incorrectly defined as GENMASK_ULL(63, 32), extracting 32 bits from qw2 instead of the 16-bit VLAN tag. In the legacy Rx descriptor layout, the 2nd L2TAG2 (VLAN tag) occupies bits 63:48 of qw2, not 63:32. The oversized mask causes FIELD_GET to return a 32-bit value where the actual VLAN tag sits in bits 31:16. When this value is passed to iavf_receive_skb() as a u16 parameter, it gets truncated to the lower 16 bits (which contain the 1st L2TAG2, typically zero). As a result, __vlan_hwaccel_put_tag() is never called and software VLAN interfaces on VFs receive no traffic. This affects VFs behind ice PF (VIRTCHNL VLAN v2) when the PF advertises VLAN stripping into L2TAG2_2 and legacy descriptors are used. The flex descriptor path already uses the correct mask (IAVF_RXD_FLEX_L2TAG2_2_M = GENMASK_ULL(63, 48)). Reproducer: 1. Create 2 VFs on ice PF (echo 2 > sriov_numvfs) 2. Disable spoofchk on both VFs 3. Move each VF into a separate network namespace 4. On each VF: create VLAN interface (e.g. vlan 198), assign IP, bring up 5. Set rx-vlan-offload OFF on both VFs 6. Ping between VLAN interfaces -> expect PASS (VLAN tag stays in packet data, kernel matches in-band) 7. Set rx-vlan-offload ON on both VFs 8. Ping between VLAN interfaces -> expect FAIL if bug present (HW strips VLAN tag into descriptor L2TAG2 field, wrong mask extracts bits 47:32 instead of 63:48, truncated to u16 -> zero, __vlan_hwaccel_put_tag() never called, packet delivered to parent interface, not VLAN interface) The reproducer requires legacy Rx descriptors. On modern ice + iavf with full PTP support, flex descriptors are always negotiated and the buggy legacy path is never reached. Flex descriptors require all of: - CONFIG_PTP_1588_CLOCK enabled - VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC granted by PF - PTP capabilities negotiated (VIRTCHNL_VF_CAP_PTP) - VIRTCHNL_1588_PTP_CAP_RX_TSTAMP supported - VIRTCHNL_RXDID_2_FLEX_SQ_NIC present in DDP profile If any condition is not met, iavf_select_rx_desc_format() falls back to legacy descriptors (RXDID=1) and the wrong L2TAG2 mask is hit. Fixes: 2dc8e7c36d80 ("iavf: refactor iavf_clean_rx_irq to support legacy and flex descriptors") Signed-off-by: Petr Oros Reviewed-by: Aleksandr Loktionov Reviewed-by: Paul Menzel Reviewed-by: Jacob Keller Tested-by: Rafal Romanowski Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-10-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index 1d8cf29cb65ac..5bb1de1cfd33b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -277,7 +277,7 @@ struct iavf_rx_desc { /* L2 Tag 2 Presence */ #define IAVF_RXD_LEGACY_L2TAG2P_M BIT(0) /* Stripped S-TAG VLAN from the receive packet */ -#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 32) +#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 48) /* Stripped S-TAG VLAN from the receive packet */ #define IAVF_RXD_FLEX_L2TAG2_2_M GENMASK_ULL(63, 48) /* The packet is a UDP tunneled packet */ From d77baa6214b7ddf70aa6ae6840e466c1e283b82b Mon Sep 17 00:00:00 2001 From: Matt Vollrath Date: Thu, 16 Apr 2026 17:53:36 -0700 Subject: [PATCH 0833/1518] e1000e: Unroll PTP in probe error handling [ Upstream commit aa3f7fe409350857c25d050482a2eef2cfd69b58 ] If probe fails after registering the PTP clock and its delayed work, these resources must be released. This was not an issue until a 2016 fix moved the e1000e_ptp_init() call before the jump to err_register. Fixes: aa524b66c5ef ("e1000e: don't modify SYSTIM registers during SIOCSHWTSTAMP ioctl") Signed-off-by: Matt Vollrath Tested-by: Avigail Dahan Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260416-iwl-net-submission-2026-04-14-v2-12-686c33c9828d@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/e1000e/netdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 3e39032696100..833b2e7a86d8c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7705,6 +7705,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_register: if (!(adapter->flags & FLAG_HAS_AMT)) e1000e_release_hw_control(adapter); + e1000e_ptp_remove(adapter); err_eeprom: if (hw->phy.ops.check_reset_block && !hw->phy.ops.check_reset_block(hw)) e1000_phy_hw_reset(&adapter->hw); From 7c66b368c6ff453f99cb39d84af93e908e51eef2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Apr 2026 10:35:05 +0000 Subject: [PATCH 0834/1518] ipv6: fix possible UAF in icmpv6_rcv() [ Upstream commit f996edd7615e686ada141b7f3395025729ff8ccb ] Caching saddr and daddr before pskb_pull() is problematic since skb->head can change. Remove these temporary variables: - We only access &ipv6_hdr(skb)->saddr and &ipv6_hdr(skb)->daddr when net_dbg_ratelimited() is called in the slow path. - Avoid potential future misuse after pskb_pull() call. Fixes: 4b3418fba0fe ("ipv6: icmp: include addresses in debug messages") Signed-off-by: Eric Dumazet Reviewed-by: Fernando Fernandez Mancera Reviewed-by: Joe Damato Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260416103505.2380753-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/icmp.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index aa39aabe4417e..9cf0557d0ed29 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -904,7 +904,6 @@ static int icmpv6_rcv(struct sk_buff *skb) struct net *net = dev_net_rcu(skb->dev); struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); - const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; u8 type; @@ -935,12 +934,10 @@ static int icmpv6_rcv(struct sk_buff *skb) __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS); - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; - if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n", - saddr, daddr); + &ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr); goto csum_error; } @@ -1020,7 +1017,8 @@ static int icmpv6_rcv(struct sk_buff *skb) break; net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n", - saddr, daddr); + &ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr); /* * error of unknown type. From 70a089cc9590aa347a61e84434116ab74619e3c3 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Wed, 15 Apr 2026 23:19:03 -0400 Subject: [PATCH 0835/1518] sctp: fix OOB write to userspace in sctp_getsockopt_peer_auth_chunks [ Upstream commit 0cf004ffb61cd32d140531c3a84afe975f9fc7ea ] sctp_getsockopt_peer_auth_chunks() checks that the caller's optval buffer is large enough for the peer AUTH chunk list with if (len < num_chunks) return -EINVAL; but then writes num_chunks bytes to p->gauth_chunks, which lives at offset offsetof(struct sctp_authchunks, gauth_chunks) == 8 inside optval. The check is missing the sizeof(struct sctp_authchunks) = 8-byte header. When the caller supplies len == num_chunks (for any num_chunks > 0) the test passes but copy_to_user() writes sizeof(struct sctp_authchunks) = 8 bytes past the declared buffer. The sibling function sctp_getsockopt_local_auth_chunks() at the next line already has the correct check: if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; Align the peer variant with its sibling. Reproducer confirms on v7.0-13-generic: an unprivileged userspace caller that opens a loopback SCTP association with AUTH enabled, queries num_chunks with a short optval, then issues the real getsockopt with len == num_chunks and sentinel bytes painted past the buffer observes those sentinel bytes overwritten with the peer's AUTH chunk type. The bytes written are under the peer's control but land in the caller's own userspace; this is not a kernel memory corruption, but it is a kernel-side contract violation that can silently corrupt adjacent userspace data. Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.") Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Michael Bommarito Acked-by: Xin Long Link: https://patch.msgid.link/20260416031903.1447072-1-michael.bommarito@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c57a53192beef..2c5ad53984906 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6990,7 +6990,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, /* See if the user provided enough room for all the data */ num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); - if (len < num_chunks) + if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; if (copy_to_user(to, ch->chunks, num_chunks)) From 0cab5d077dd1efd2bd1a47271acc35894f945b4f Mon Sep 17 00:00:00 2001 From: Qingfang Deng Date: Wed, 15 Apr 2026 10:24:51 +0800 Subject: [PATCH 0836/1518] pppoe: drop PFC frames [ Upstream commit cc1ff87bce1ccd38410ab10960f576dcd17db679 ] RFC 2516 Section 7 states that Protocol Field Compression (PFC) is NOT RECOMMENDED for PPPoE. In practice, pppd does not support negotiating PFC for PPPoE sessions, and the current PPPoE driver assumes an uncompressed (2-byte) protocol field. However, the generic PPP layer function ppp_input() is not aware of the negotiation result, and still accepts PFC frames. If a peer with a broken implementation or an attacker sends a frame with a compressed (1-byte) protocol field, the subsequent PPP payload is shifted by one byte. This causes the network header to be 4-byte misaligned, which may trigger unaligned access exceptions on some architectures. To reduce the attack surface, drop PPPoE PFC frames. Introduce ppp_skb_is_compressed_proto() helper function to be used in both ppp_generic.c and pppoe.c to avoid open-coding. Fixes: 7fb1b8ca8fa1 ("ppp: Move PFC decompression to PPP generic layer") Signed-off-by: Qingfang Deng Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260415022456.141758-2-qingfang.deng@linux.dev Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ppp/ppp_generic.c | 2 +- drivers/net/ppp/pppoe.c | 8 +++++++- include/linux/ppp_defs.h | 16 ++++++++++++++++ 3 files changed, 24 insertions(+), 2 deletions(-) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 7ad6c241c3295..507d216256c0d 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2240,7 +2240,7 @@ ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) */ static void __ppp_decompress_proto(struct sk_buff *skb) { - if (skb->data[0] & 0x01) + if (ppp_skb_is_compressed_proto(skb)) *(u8 *)skb_push(skb, 1) = 0x00; } diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 4ac6afce267b9..dc6d139432387 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -424,7 +424,7 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (skb_mac_header_len(skb) < ETH_HLEN) goto drop; - if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) goto drop; ph = pppoe_hdr(skb); @@ -434,6 +434,12 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->len < len) goto drop; + /* skb->data points to the PPP protocol header after skb_pull_rcsum. + * Drop PFC frames. + */ + if (ppp_skb_is_compressed_proto(skb)) + goto drop; + if (pskb_trim_rcsum(skb, len)) goto drop; diff --git a/include/linux/ppp_defs.h b/include/linux/ppp_defs.h index b7e57fdbd4139..b1d1f46d7d3be 100644 --- a/include/linux/ppp_defs.h +++ b/include/linux/ppp_defs.h @@ -8,6 +8,7 @@ #define _PPP_DEFS_H_ #include +#include #include #define PPP_FCS(fcs, c) crc_ccitt_byte(fcs, c) @@ -25,4 +26,19 @@ static inline bool ppp_proto_is_valid(u16 proto) return !!((proto & 0x0101) == 0x0001); } +/** + * ppp_skb_is_compressed_proto - checks if PPP protocol in a skb is compressed + * @skb: skb to check + * + * Check if the PPP protocol field is compressed (the least significant + * bit of the most significant octet is 1). skb->data must point to the PPP + * protocol header. + * + * Return: Whether the PPP protocol field is compressed. + */ +static inline bool ppp_skb_is_compressed_proto(const struct sk_buff *skb) +{ + return unlikely(skb->data[0] & 0x01); +} + #endif /* _PPP_DEFS_H_ */ From d17830d050f7f051f8a0167ae28e9e1ad8a6a454 Mon Sep 17 00:00:00 2001 From: Prathamesh Deshpande Date: Wed, 15 Apr 2026 01:49:37 +0100 Subject: [PATCH 0837/1518] net/mlx5: Fix HCA caps leak on notifier init failure [ Upstream commit d03fc81a57956248383efec99967d0ae627390a8 ] mlx5_mdev_init() allocates HCA caps via mlx5_hca_caps_alloc() before calling mlx5_notifiers_init(). If notifier initialization fails, the error path jumps to err_hca_caps and skips mlx5_hca_caps_free(), leaking allocated caps. Add a dedicated unwind label for notifier-init failure that frees HCA caps before continuing the existing cleanup sequence. Fixes: b6b03097f982 ("net/mlx5: Initialize events outside devlink lock") Signed-off-by: Prathamesh Deshpande Reviewed-by: Cosmin Ratiu Reviewed-by: Tariq Toukan Link: https://patch.msgid.link/20260415005022.34764-1-prathameshdeshpande7@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5903a4af9173b..6e10a6de8ebcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1878,7 +1878,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) err = mlx5_notifiers_init(dev); if (err) - goto err_hca_caps; + goto err_notifiers_init; /* The conjunction of sw_vhca_id with sw_owner_id will be a global * unique id per function which uses mlx5_core. @@ -1894,6 +1894,8 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) return 0; +err_notifiers_init: + mlx5_hca_caps_free(dev); err_hca_caps: mlx5_adev_cleanup(dev); err_adev_init: From fa6e90bc443bed8dc0d55bc5ea5b27ffdfe37704 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 15 Apr 2026 19:46:54 -0700 Subject: [PATCH 0838/1518] openvswitch: cap upcall PID array size and pre-size vport replies [ Upstream commit 2091c6aa0df6aba47deb5c8ab232b1cb60af3519 ] The vport netlink reply helpers allocate a fixed-size skb with nlmsg_new(NLMSG_DEFAULT_SIZE, ...) but serialize the full upcall PID array via ovs_vport_get_upcall_portids(). Since ovs_vport_set_upcall_portids() accepts any non-zero multiple of sizeof(u32) with no upper bound, a CAP_NET_ADMIN user can install a PID array large enough to overflow the reply buffer, causing nla_put() to fail with -EMSGSIZE and hitting BUG_ON(err < 0). On systems with unprivileged user namespaces enabled (e.g., Ubuntu default), this is reachable via unshare -Urn since OVS vport mutation operations use GENL_UNS_ADMIN_PERM. kernel BUG at net/openvswitch/datapath.c:2414! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 1 UID: 0 PID: 65 Comm: poc Not tainted 7.0.0-rc7-00195-geb216e422044 #1 RIP: 0010:ovs_vport_cmd_set+0x34c/0x400 Call Trace: genl_family_rcv_msg_doit (net/netlink/genetlink.c:1116) genl_rcv_msg (net/netlink/genetlink.c:1194) netlink_rcv_skb (net/netlink/af_netlink.c:2550) genl_rcv (net/netlink/genetlink.c:1219) netlink_unicast (net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Kernel panic - not syncing: Fatal exception Reject attempts to set more PIDs than nr_cpu_ids in ovs_vport_set_upcall_portids(), and pre-compute the worst-case reply size in ovs_vport_cmd_msg_size() based on that bound, similar to the existing ovs_dp_cmd_msg_size(). nr_cpu_ids matches the cap already used by the per-CPU dispatch configuration on the datapath side (ovs_dp_cmd_fill_info() serialises at most nr_cpu_ids PIDs), so the two sides stay consistent. Fixes: 5cd667b0a456 ("openvswitch: Allow each vport to have an array of 'port_id's.") Reported-by: Xiang Mei Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Weiming Shi Reviewed-by: Ilya Maximets Link: https://patch.msgid.link/20260416024653.153456-2-bestswngs@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/openvswitch/datapath.c | 35 +++++++++++++++++++++++++++++++++-- net/openvswitch/vport.c | 3 +++ 2 files changed, 36 insertions(+), 2 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d5b6e2002bc1f..2304c8e3be4f7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2186,9 +2186,40 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, return err; } +static size_t ovs_vport_cmd_msg_size(void) +{ + size_t msgsize = NLMSG_ALIGN(sizeof(struct ovs_header)); + + msgsize += nla_total_size(sizeof(u32)); /* OVS_VPORT_ATTR_PORT_NO */ + msgsize += nla_total_size(sizeof(u32)); /* OVS_VPORT_ATTR_TYPE */ + msgsize += nla_total_size(IFNAMSIZ); /* OVS_VPORT_ATTR_NAME */ + msgsize += nla_total_size(sizeof(u32)); /* OVS_VPORT_ATTR_IFINDEX */ + msgsize += nla_total_size(sizeof(s32)); /* OVS_VPORT_ATTR_NETNSID */ + + /* OVS_VPORT_ATTR_STATS */ + msgsize += nla_total_size_64bit(sizeof(struct ovs_vport_stats)); + + /* OVS_VPORT_ATTR_UPCALL_STATS(OVS_VPORT_UPCALL_ATTR_SUCCESS + + * OVS_VPORT_UPCALL_ATTR_FAIL) + */ + msgsize += nla_total_size(nla_total_size_64bit(sizeof(u64)) + + nla_total_size_64bit(sizeof(u64))); + + /* OVS_VPORT_ATTR_UPCALL_PID */ + msgsize += nla_total_size(nr_cpu_ids * sizeof(u32)); + + /* OVS_VPORT_ATTR_OPTIONS(OVS_TUNNEL_ATTR_DST_PORT + + * OVS_TUNNEL_ATTR_EXTENSION(OVS_VXLAN_EXT_GBP)) + */ + msgsize += nla_total_size(nla_total_size(sizeof(u16)) + + nla_total_size(nla_total_size(0))); + + return msgsize; +} + static struct sk_buff *ovs_vport_cmd_alloc_info(void) { - return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + return genlmsg_new(ovs_vport_cmd_msg_size(), GFP_KERNEL); } /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ @@ -2198,7 +2229,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, struct sk_buff *skb; int retval; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + skb = ovs_vport_cmd_alloc_info(); if (!skb) return ERR_PTR(-ENOMEM); diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index f0ce8ce1dce0e..1f0c86a9f43b0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -407,6 +407,9 @@ int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids) if (!nla_len(ids) || nla_len(ids) % sizeof(u32)) return -EINVAL; + if (nla_len(ids) / sizeof(u32) > nr_cpu_ids) + return -EINVAL; + old = ovsl_dereference(vport->upcall_portids); vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids), From 8d298ece6db710005abf8b28a698490e11397a9c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 16 Apr 2026 12:30:12 +0200 Subject: [PATCH 0839/1518] net: airoha: Fix possible TX queue stall in airoha_qdma_tx_napi_poll() [ Upstream commit b94769eb2f30e61e86cd8551c084c34134290d89 ] Since multiple net_device TX queues can share the same hw QDMA TX queue, there is no guarantee we have inflight packets queued in hw belonging to a net_device TX queue stopped in the xmit path because hw QDMA TX queue can be full. In this corner case the net_device TX queue will never be re-activated. In order to avoid any potential net_device TX queue stall, we need to wake all the net_device TX queues feeding the same hw QDMA TX queue in airoha_qdma_tx_napi_poll routine. Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260416-airoha-txq-potential-stall-v2-1-42c732074540@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 37 ++++++++++++++++++++---- drivers/net/ethernet/airoha/airoha_eth.h | 1 + 2 files changed, 33 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index cbf21e15df6dd..f8db324b141fe 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -874,6 +874,21 @@ static int airoha_qdma_init_rx(struct airoha_qdma *qdma) return 0; } +static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q) +{ + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int i; + + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { + struct airoha_gdm_port *port = eth->ports[i]; + + if (port && port->qdma == qdma) + netif_tx_wake_all_queues(port->dev); + } + q->txq_stopped = false; +} + static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) { struct airoha_tx_irq_queue *irq_q; @@ -956,12 +971,21 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) txq = netdev_get_tx_queue(skb->dev, queue); netdev_tx_completed_queue(txq, 1, skb->len); - if (netif_tx_queue_stopped(txq) && - q->ndesc - q->queued >= q->free_thr) - netif_tx_wake_queue(txq); - dev_kfree_skb_any(skb); } + + if (q->txq_stopped && q->ndesc - q->queued >= q->free_thr) { + /* Since multiple net_device TX queues can share the + * same hw QDMA TX queue, there is no guarantee we have + * inflight packets queued in hw belonging to a + * net_device TX queue stopped in the xmit path. + * In order to avoid any potential net_device TX queue + * stall, we need to wake all the net_device TX queues + * feeding the same hw QDMA TX queue. + */ + airoha_qdma_wake_netdev_txqs(q); + } + unlock: spin_unlock_bh(&q->lock); } @@ -1978,6 +2002,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, if (airoha_dev_tx_queue_busy(q, nr_frags)) { /* not enough space in the queue */ netif_tx_stop_queue(txq); + q->txq_stopped = true; spin_unlock_bh(&q->lock); return NETDEV_TX_BUSY; } @@ -2030,8 +2055,10 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); - if (q->ndesc - q->queued < q->free_thr) + if (q->ndesc - q->queued < q->free_thr) { netif_tx_stop_queue(txq); + q->txq_stopped = true; + } spin_unlock_bh(&q->lock); diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index d76f71558f8c2..054fe86d67bd1 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -181,6 +181,7 @@ struct airoha_queue { int ndesc; int free_thr; int buf_size; + bool txq_stopped; struct napi_struct napi; struct page_pool *page_pool; From 6e9038e7b394569ad7e4faa6dc549563ae862a36 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 14 Apr 2026 13:06:38 +0200 Subject: [PATCH 0840/1518] netfilter: nft_osf: restrict it to ipv4 [ Upstream commit b336fdbb7103fb1484e1dcb6741151d4b5a41e35 ] This expression only supports for ipv4, restrict it. Fixes: b96af92d6eaf ("netfilter: nf_tables: implement Passive OS fingerprint module in nft_osf") Acked-by: Florian Westphal Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_osf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 1c0b493ef0a99..bdc2f6c90e2f7 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -28,6 +28,11 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nf_osf_data data; struct tcphdr _tcph; + if (nft_pf(pkt) != NFPROTO_IPV4) { + regs->verdict.code = NFT_BREAK; + return; + } + if (pkt->tprot != IPPROTO_TCP) { regs->verdict.code = NFT_BREAK; return; @@ -114,7 +119,6 @@ static int nft_osf_validate(const struct nft_ctx *ctx, switch (ctx->family) { case NFPROTO_IPV4: - case NFPROTO_IPV6: case NFPROTO_INET: hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_PRE_ROUTING) | From fb965b1cfe92b28d28b5ebe3116b81dbef9f2d2f Mon Sep 17 00:00:00 2001 From: Xiang Mei Date: Tue, 14 Apr 2026 15:14:01 -0700 Subject: [PATCH 0841/1518] netfilter: nfnetlink_osf: fix divide-by-zero in OSF_WSS_MODULO [ Upstream commit 2195574dc6d9017d32ac346987e12659f931d932 ] nf_osf_match_one() computes ctx->window % f->wss.val in the OSF_WSS_MODULO branch with no guard for f->wss.val == 0. A CAP_NET_ADMIN user can add such a fingerprint via nfnetlink; a subsequent matching TCP SYN divides by zero and panics the kernel. Reject the bogus fingerprint in nfnl_osf_add_callback() above the per-option for-loop. f->wss is per-fingerprint, not per-option, so the check must run regardless of f->opt_num (including 0). Also reject wss.wc >= OSF_WSS_MAX; nf_osf_match_one() already treats that as "should not happen". Crash: Oops: divide error: 0000 [#1] SMP KASAN NOPTI RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98) Call Trace: nf_osf_match (net/netfilter/nfnetlink_osf.c:220) xt_osf_match_packet (net/netfilter/xt_osf.c:32) ipt_do_table (net/ipv4/netfilter/ip_tables.c:348) nf_hook_slow (net/netfilter/core.c:622) ip_local_deliver (net/ipv4/ip_input.c:265) ip_rcv (include/linux/skbuff.h:1162) __netif_receive_skb_one_core (net/core/dev.c:6181) process_backlog (net/core/dev.c:6642) __napi_poll (net/core/dev.c:7710) net_rx_action (net/core/dev.c:7945) handle_softirqs (kernel/softirq.c:622) Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match") Reported-by: Weiming Shi Suggested-by: Florian Westphal Suggested-by: Pablo Neira Ayuso Signed-off-by: Xiang Mei Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nfnetlink_osf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 9fc9544d4bc53..2305c7d9761eb 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -320,6 +320,10 @@ static int nfnl_osf_add_callback(struct sk_buff *skb, if (f->opt_num > ARRAY_SIZE(f->opt)) return -EINVAL; + if (f->wss.wc >= OSF_WSS_MAX || + (f->wss.wc == OSF_WSS_MODULO && f->wss.val == 0)) + return -EINVAL; + for (i = 0; i < f->opt_num; i++) { if (!f->opt[i].length || f->opt[i].length > MAX_IPOPTLEN) return -EINVAL; From 8e3be0d12615a173fe260cd42753ca7a001acbf2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 14 Apr 2026 19:13:46 +0200 Subject: [PATCH 0842/1518] netfilter: conntrack: remove sprintf usage [ Upstream commit 6e7066bdb481a87fe88c4fa563e348c03b2d373d ] Replace it with scnprintf, the buffer sizes are expected to be large enough to hold the result, no need for snprintf+overflow check. Increase buffer size in mangle_content_len() while at it. BUG: KASAN: stack-out-of-bounds in vsnprintf+0xea5/0x1270 Write of size 1 at addr [..] vsnprintf+0xea5/0x1270 sprintf+0xb1/0xe0 mangle_content_len+0x1ac/0x280 nf_nat_sdp_session+0x1cc/0x240 process_sdp+0x8f8/0xb80 process_invite_request+0x108/0x2b0 process_sip_msg+0x5da/0xf50 sip_help_tcp+0x45e/0x780 nf_confirm+0x34d/0x990 [..] Fixes: 9fafcd7b2032 ("[NETFILTER]: nf_conntrack/nf_nat: add SIP helper port") Reported-by: Yiming Qian Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_nat_amanda.c | 2 +- net/netfilter/nf_nat_sip.c | 33 ++++++++++++++++++--------------- 2 files changed, 19 insertions(+), 16 deletions(-) diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c index 98deef6cde694..8f1054920a857 100644 --- a/net/netfilter/nf_nat_amanda.c +++ b/net/netfilter/nf_nat_amanda.c @@ -50,7 +50,7 @@ static unsigned int help(struct sk_buff *skb, return NF_DROP; } - sprintf(buffer, "%u", port); + snprintf(buffer, sizeof(buffer), "%u", port); if (!nf_nat_mangle_udp_packet(skb, exp->master, ctinfo, protoff, matchoff, matchlen, buffer, strlen(buffer))) { diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index cf4aeb299bdef..c845b6d1a2bdf 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -68,25 +68,27 @@ static unsigned int mangle_packet(struct sk_buff *skb, unsigned int protoff, } static int sip_sprintf_addr(const struct nf_conn *ct, char *buffer, + size_t size, const union nf_inet_addr *addr, bool delim) { if (nf_ct_l3num(ct) == NFPROTO_IPV4) - return sprintf(buffer, "%pI4", &addr->ip); + return scnprintf(buffer, size, "%pI4", &addr->ip); else { if (delim) - return sprintf(buffer, "[%pI6c]", &addr->ip6); + return scnprintf(buffer, size, "[%pI6c]", &addr->ip6); else - return sprintf(buffer, "%pI6c", &addr->ip6); + return scnprintf(buffer, size, "%pI6c", &addr->ip6); } } static int sip_sprintf_addr_port(const struct nf_conn *ct, char *buffer, + size_t size, const union nf_inet_addr *addr, u16 port) { if (nf_ct_l3num(ct) == NFPROTO_IPV4) - return sprintf(buffer, "%pI4:%u", &addr->ip, port); + return scnprintf(buffer, size, "%pI4:%u", &addr->ip, port); else - return sprintf(buffer, "[%pI6c]:%u", &addr->ip6, port); + return scnprintf(buffer, size, "[%pI6c]:%u", &addr->ip6, port); } static int map_addr(struct sk_buff *skb, unsigned int protoff, @@ -119,7 +121,7 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, if (nf_inet_addr_cmp(&newaddr, addr) && newport == port) return 1; - buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, ntohs(newport)); + buflen = sip_sprintf_addr_port(ct, buffer, sizeof(buffer), &newaddr, ntohs(newport)); return mangle_packet(skb, protoff, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen); } @@ -212,7 +214,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, &addr, true) > 0 && nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.src.u3) && !nf_inet_addr_cmp(&addr, &ct->tuplehash[!dir].tuple.dst.u3)) { - buflen = sip_sprintf_addr(ct, buffer, + buflen = sip_sprintf_addr(ct, buffer, sizeof(buffer), &ct->tuplehash[!dir].tuple.dst.u3, true); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, @@ -229,7 +231,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, &addr, false) > 0 && nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.dst.u3) && !nf_inet_addr_cmp(&addr, &ct->tuplehash[!dir].tuple.src.u3)) { - buflen = sip_sprintf_addr(ct, buffer, + buflen = sip_sprintf_addr(ct, buffer, sizeof(buffer), &ct->tuplehash[!dir].tuple.src.u3, false); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, @@ -247,7 +249,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, htons(n) == ct->tuplehash[dir].tuple.dst.u.udp.port && htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; - buflen = sprintf(buffer, "%u", ntohs(p)); + buflen = scnprintf(buffer, sizeof(buffer), "%u", ntohs(p)); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, poff, plen, buffer, buflen)) { nf_ct_helper_log(skb, ct, "cannot mangle rport"); @@ -418,7 +420,8 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, if (!nf_inet_addr_cmp(&exp->tuple.dst.u3, &exp->saved_addr) || exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { - buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, port); + buflen = sip_sprintf_addr_port(ct, buffer, sizeof(buffer), + &newaddr, port); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); @@ -438,8 +441,8 @@ static int mangle_content_len(struct sk_buff *skb, unsigned int protoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + char buffer[sizeof("4294967295")]; unsigned int matchoff, matchlen; - char buffer[sizeof("65536")]; int buflen, c_len; /* Get actual SDP length */ @@ -454,7 +457,7 @@ static int mangle_content_len(struct sk_buff *skb, unsigned int protoff, &matchoff, &matchlen) <= 0) return 0; - buflen = sprintf(buffer, "%u", c_len); + buflen = scnprintf(buffer, sizeof(buffer), "%u", c_len); return mangle_packet(skb, protoff, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen); } @@ -491,7 +494,7 @@ static unsigned int nf_nat_sdp_addr(struct sk_buff *skb, unsigned int protoff, char buffer[INET6_ADDRSTRLEN]; unsigned int buflen; - buflen = sip_sprintf_addr(ct, buffer, addr, false); + buflen = sip_sprintf_addr(ct, buffer, sizeof(buffer), addr, false); if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, type, term, buffer, buflen)) return 0; @@ -509,7 +512,7 @@ static unsigned int nf_nat_sdp_port(struct sk_buff *skb, unsigned int protoff, char buffer[sizeof("nnnnn")]; unsigned int buflen; - buflen = sprintf(buffer, "%u", port); + buflen = scnprintf(buffer, sizeof(buffer), "%u", port); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen)) return 0; @@ -529,7 +532,7 @@ static unsigned int nf_nat_sdp_session(struct sk_buff *skb, unsigned int protoff unsigned int buflen; /* Mangle session description owner and contact addresses */ - buflen = sip_sprintf_addr(ct, buffer, addr, false); + buflen = sip_sprintf_addr(ct, buffer, sizeof(buffer), addr, false); if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, SDP_HDR_OWNER, SDP_HDR_MEDIA, buffer, buflen)) return 0; From 76160e04440c9698b989dbd9492a7ec4f520c9ee Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 15 Apr 2026 12:21:00 +0200 Subject: [PATCH 0843/1518] netfilter: xtables: restrict several matches to inet family [ Upstream commit b6fe26f86a1649f84e057f3f15605b08eda15497 ] This is a partial revert of: commit ab4f21e6fb1c ("netfilter: xtables: use NFPROTO_UNSPEC in more extensions") to allow ipv4 and ipv6 only. - xt_mac - xt_owner - xt_physdev These extensions are not used by ebtables in userspace. Moreover, xt_realm is only for ipv4, since dst->tclassid is ipv4 specific. Fixes: ab4f21e6fb1c ("netfilter: xtables: use NFPROTO_UNSPEC in more extensions") Reported-by: "Kito Xu (veritas501)" Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/xt_mac.c | 34 +++++++++++++++++++++++----------- net/netfilter/xt_owner.c | 37 +++++++++++++++++++++++++------------ net/netfilter/xt_physdev.c | 29 +++++++++++++++++++---------- net/netfilter/xt_realm.c | 2 +- 4 files changed, 68 insertions(+), 34 deletions(-) diff --git a/net/netfilter/xt_mac.c b/net/netfilter/xt_mac.c index 81649da57ba5d..bd2354760895d 100644 --- a/net/netfilter/xt_mac.c +++ b/net/netfilter/xt_mac.c @@ -38,25 +38,37 @@ static bool mac_mt(const struct sk_buff *skb, struct xt_action_param *par) return ret; } -static struct xt_match mac_mt_reg __read_mostly = { - .name = "mac", - .revision = 0, - .family = NFPROTO_UNSPEC, - .match = mac_mt, - .matchsize = sizeof(struct xt_mac_info), - .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_FORWARD), - .me = THIS_MODULE, +static struct xt_match mac_mt_reg[] __read_mostly = { + { + .name = "mac", + .family = NFPROTO_IPV4, + .match = mac_mt, + .matchsize = sizeof(struct xt_mac_info), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD), + .me = THIS_MODULE, + }, + { + .name = "mac", + .family = NFPROTO_IPV6, + .match = mac_mt, + .matchsize = sizeof(struct xt_mac_info), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD), + .me = THIS_MODULE, + }, }; static int __init mac_mt_init(void) { - return xt_register_match(&mac_mt_reg); + return xt_register_matches(mac_mt_reg, ARRAY_SIZE(mac_mt_reg)); } static void __exit mac_mt_exit(void) { - xt_unregister_match(&mac_mt_reg); + xt_unregister_matches(mac_mt_reg, ARRAY_SIZE(mac_mt_reg)); } module_init(mac_mt_init); diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 50332888c8d23..7be2fe22b067e 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -127,26 +127,39 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } -static struct xt_match owner_mt_reg __read_mostly = { - .name = "owner", - .revision = 1, - .family = NFPROTO_UNSPEC, - .checkentry = owner_check, - .match = owner_mt, - .matchsize = sizeof(struct xt_owner_match_info), - .hooks = (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING), - .me = THIS_MODULE, +static struct xt_match owner_mt_reg[] __read_mostly = { + { + .name = "owner", + .revision = 1, + .family = NFPROTO_IPV4, + .checkentry = owner_check, + .match = owner_mt, + .matchsize = sizeof(struct xt_owner_match_info), + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING), + .me = THIS_MODULE, + }, + { + .name = "owner", + .revision = 1, + .family = NFPROTO_IPV6, + .checkentry = owner_check, + .match = owner_mt, + .matchsize = sizeof(struct xt_owner_match_info), + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING), + .me = THIS_MODULE, + } }; static int __init owner_mt_init(void) { - return xt_register_match(&owner_mt_reg); + return xt_register_matches(owner_mt_reg, ARRAY_SIZE(owner_mt_reg)); } static void __exit owner_mt_exit(void) { - xt_unregister_match(&owner_mt_reg); + xt_unregister_matches(owner_mt_reg, ARRAY_SIZE(owner_mt_reg)); } module_init(owner_mt_init); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 343e65f377d44..130842c35c6fa 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -115,24 +115,33 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) return 0; } -static struct xt_match physdev_mt_reg __read_mostly = { - .name = "physdev", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = physdev_mt_check, - .match = physdev_mt, - .matchsize = sizeof(struct xt_physdev_info), - .me = THIS_MODULE, +static struct xt_match physdev_mt_reg[] __read_mostly = { + { + .name = "physdev", + .family = NFPROTO_IPV4, + .checkentry = physdev_mt_check, + .match = physdev_mt, + .matchsize = sizeof(struct xt_physdev_info), + .me = THIS_MODULE, + }, + { + .name = "physdev", + .family = NFPROTO_IPV6, + .checkentry = physdev_mt_check, + .match = physdev_mt, + .matchsize = sizeof(struct xt_physdev_info), + .me = THIS_MODULE, + }, }; static int __init physdev_mt_init(void) { - return xt_register_match(&physdev_mt_reg); + return xt_register_matches(physdev_mt_reg, ARRAY_SIZE(physdev_mt_reg)); } static void __exit physdev_mt_exit(void) { - xt_unregister_match(&physdev_mt_reg); + xt_unregister_matches(physdev_mt_reg, ARRAY_SIZE(physdev_mt_reg)); } module_init(physdev_mt_init); diff --git a/net/netfilter/xt_realm.c b/net/netfilter/xt_realm.c index 6df485f4403d0..61b2f1e58d150 100644 --- a/net/netfilter/xt_realm.c +++ b/net/netfilter/xt_realm.c @@ -33,7 +33,7 @@ static struct xt_match realm_mt_reg __read_mostly = { .matchsize = sizeof(struct xt_realm_info), .hooks = (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), - .family = NFPROTO_UNSPEC, + .family = NFPROTO_IPV4, .me = THIS_MODULE }; From 32fdd2e38e7435a368d88f5977a7d6585ebc8b0e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 15 Apr 2026 17:29:45 +0200 Subject: [PATCH 0844/1518] netfilter: nat: use kfree_rcu to release ops [ Upstream commit 6eda0d771f94267f73f57c94630aa47e90957915 ] Florian Westphal says: "Historically this is not an issue, even for normal base hooks: the data path doesn't use the original nf_hook_ops that are used to register the callbacks. However, in v5.14 I added the ability to dump the active netfilter hooks from userspace. This code will peek back into the nf_hook_ops that are available at the tail of the pointer-array blob used by the datapath. The nat hooks are special, because they are called indirectly from the central nat dispatcher hook. They are currently invisible to the nfnl hook dump subsystem though. But once that changes the nat ops structures have to be deferred too." Update nf_nat_register_fn() to deal with partial exposition of the hooks from error path which can be also an issue for nfnetlink_hook. Fixes: e2cf17d3774c ("netfilter: add new hook nfnl subsystem") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/ipv4/netfilter/iptable_nat.c | 4 ++-- net/ipv6/netfilter/ip6table_nat.c | 4 ++-- net/netfilter/nf_nat_core.c | 10 ++++++---- 3 files changed, 10 insertions(+), 8 deletions(-) diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index a5db7c67d61be..625a1ca13b1ba 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -79,7 +79,7 @@ static int ipt_nat_register_lookups(struct net *net) while (i) nf_nat_ipv4_unregister_fn(net, &ops[--i]); - kfree(ops); + kfree_rcu(ops, rcu); return ret; } } @@ -100,7 +100,7 @@ static void ipt_nat_unregister_lookups(struct net *net) for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) nf_nat_ipv4_unregister_fn(net, &ops[i]); - kfree(ops); + kfree_rcu(ops, rcu); } static int iptable_nat_table_init(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index e119d4f090cc8..5be723232df8f 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -81,7 +81,7 @@ static int ip6t_nat_register_lookups(struct net *net) while (i) nf_nat_ipv6_unregister_fn(net, &ops[--i]); - kfree(ops); + kfree_rcu(ops, rcu); return ret; } } @@ -102,7 +102,7 @@ static void ip6t_nat_unregister_lookups(struct net *net) for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) nf_nat_ipv6_unregister_fn(net, &ops[i]); - kfree(ops); + kfree_rcu(ops, rcu); } static int ip6table_nat_table_init(struct net *net) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index e6b24586d2fed..8e36b4e3e5c47 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1228,9 +1228,11 @@ int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, ret = nf_register_net_hooks(net, nat_ops, ops_count); if (ret < 0) { mutex_unlock(&nf_nat_proto_mutex); - for (i = 0; i < ops_count; i++) - kfree(nat_ops[i].priv); - kfree(nat_ops); + for (i = 0; i < ops_count; i++) { + priv = nat_ops[i].priv; + kfree_rcu(priv, rcu_head); + } + kfree_rcu(nat_ops, rcu); return ret; } @@ -1294,7 +1296,7 @@ void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, } nat_proto_net->nat_hook_ops = NULL; - kfree(nat_ops); + kfree_rcu(nat_ops, rcu); } unlock: mutex_unlock(&nf_nat_proto_mutex); From 5b73746bd85f3a64c391973763aed0b3ff46f109 Mon Sep 17 00:00:00 2001 From: Yingnan Zhang <342144303@qq.com> Date: Wed, 15 Apr 2026 22:40:29 +0800 Subject: [PATCH 0845/1518] ipvs: fix MTU check for GSO packets in tunnel mode [ Upstream commit 67bf42cae41d847fd6e5749eb68278ca5d748b25 ] Currently, IPVS skips MTU checks for GSO packets by excluding them with the !skb_is_gso(skb) condition. This creates problems when IPVS tunnel mode encapsulates GSO packets with IPIP headers. The issue manifests in two ways: 1. MTU violation after encapsulation: When a GSO packet passes through IPVS tunnel mode, the original MTU check is bypassed. After adding the IPIP tunnel header, the packet size may exceed the outgoing interface MTU, leading to unexpected fragmentation at the IP layer. 2. Fragmentation with problematic IP IDs: When net.ipv4.vs.pmtu_disc=1 and a GSO packet with multiple segments is fragmented after encapsulation, each segment gets a sequentially incremented IP ID (0, 1, 2, ...). This happens because: a) The GSO packet bypasses MTU check and gets encapsulated b) At __ip_finish_output, the oversized GSO packet is split into separate SKBs (one per segment), with IP IDs incrementing c) Each SKB is then fragmented again based on the actual MTU This sequential IP ID allocation differs from the expected behavior and can cause issues with fragment reassembly and packet tracking. Fix this by properly validating GSO packets using skb_gso_validate_network_len(). This function correctly validates whether the GSO segments will fit within the MTU after segmentation. If validation fails, send an ICMP Fragmentation Needed message to enable proper PMTU discovery. Fixes: 4cdd34084d53 ("netfilter: nf_conntrack_ipv6: improve fragmentation handling") Signed-off-by: Yingnan Zhang <342144303@qq.com> Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipvs/ip_vs_xmit.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index ecbcdc43263d6..fc254d1f59de9 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -103,6 +103,18 @@ __ip_vs_dst_check(struct ip_vs_dest *dest) return dest_dst; } +/* Based on ip_exceeds_mtu(). */ +static bool ip_vs_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) + return false; + + return true; +} + static inline bool __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) { @@ -112,10 +124,9 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) */ if (IP6CB(skb)->frag_max_size > mtu) return true; /* largest fragment violate MTU */ - } - else if (skb->len > mtu && !skb_is_gso(skb)) { + } else if (ip_vs_exceeds_mtu(skb, mtu)) return true; /* Packet size violate MTU size */ - } + return false; } @@ -233,7 +244,7 @@ static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, return true; if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) && - skb->len > mtu && !skb_is_gso(skb) && + ip_vs_exceeds_mtu(skb, mtu) && !ip_vs_iph_icmp(ipvsh))) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); From 21883587593d7c8bb519a79460a0b5bc5ffbdabd Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Fri, 17 Apr 2026 18:20:56 +0200 Subject: [PATCH 0846/1518] netfilter: nfnetlink_osf: fix out-of-bounds read on option matching [ Upstream commit f5ca450087c3baf3651055e7a6de92600f827af3 ] In nf_osf_match(), the nf_osf_hdr_ctx structure is initialized once and passed by reference to nf_osf_match_one() for each fingerprint checked. During TCP option parsing, nf_osf_match_one() advances the shared ctx->optp pointer. If a fingerprint perfectly matches, the function returns early without restoring ctx->optp to its initial state. If the user has configured NF_OSF_LOGLEVEL_ALL, the loop continues to the next fingerprint. However, because ctx->optp was not restored, the next call to nf_osf_match_one() starts parsing from the end of the options buffer. This causes subsequent matches to read garbage data and fail immediately, making it impossible to log more than one match or logging incorrect matches. Instead of using a shared ctx->optp pointer, pass the context as a constant pointer and use a local pointer (optp) for TCP option traversal. This makes nf_osf_match_one() strictly stateless from the caller's perspective, ensuring every fingerprint check starts at the correct option offset. Fixes: 1a6a0951fc00 ("netfilter: nfnetlink_osf: add missing fmatch check") Suggested-by: Florian Westphal Signed-off-by: Fernando Fernandez Mancera Reviewed-by: Pablo Neira Ayuso Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nfnetlink_osf.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 2305c7d9761eb..832a973c41777 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -64,9 +64,9 @@ struct nf_osf_hdr_ctx { static bool nf_osf_match_one(const struct sk_buff *skb, const struct nf_osf_user_finger *f, int ttl_check, - struct nf_osf_hdr_ctx *ctx) + const struct nf_osf_hdr_ctx *ctx) { - const __u8 *optpinit = ctx->optp; + const __u8 *optp = ctx->optp; unsigned int check_WSS = 0; int fmatch = FMATCH_WRONG; int foptsize, optnum; @@ -95,17 +95,17 @@ static bool nf_osf_match_one(const struct sk_buff *skb, check_WSS = f->wss.wc; for (optnum = 0; optnum < f->opt_num; ++optnum) { - if (f->opt[optnum].kind == *ctx->optp) { + if (f->opt[optnum].kind == *optp) { __u32 len = f->opt[optnum].length; - const __u8 *optend = ctx->optp + len; + const __u8 *optend = optp + len; fmatch = FMATCH_OK; - switch (*ctx->optp) { + switch (*optp) { case OSFOPT_MSS: - mss = ctx->optp[3]; + mss = optp[3]; mss <<= 8; - mss |= ctx->optp[2]; + mss |= optp[2]; mss = ntohs((__force __be16)mss); break; @@ -113,7 +113,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb, break; } - ctx->optp = optend; + optp = optend; } else fmatch = FMATCH_OPT_WRONG; @@ -156,9 +156,6 @@ static bool nf_osf_match_one(const struct sk_buff *skb, } } - if (fmatch != FMATCH_OK) - ctx->optp = optpinit; - return fmatch == FMATCH_OK; } From 79b90a96688e521771fa6ed3dc7864b76b8df293 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Fri, 17 Apr 2026 18:20:57 +0200 Subject: [PATCH 0847/1518] netfilter: nfnetlink_osf: fix potential NULL dereference in ttl check [ Upstream commit 711987ba281fd806322a7cd244e98e2a81903114 ] The nf_osf_ttl() function accessed skb->dev to perform a local interface address lookup without verifying that the device pointer was valid. Additionally, the implementation utilized an in_dev_for_each_ifa_rcu loop to match the packet source address against local interface addresses. It assumed that packets from the same subnet should not see a decrement on the initial TTL. A packet might appear it is from the same subnet but it actually isn't especially in modern environments with containers and virtual switching. Remove the device dereference and interface loop. Replace the logic with a switch statement that evaluates the TTL according to the ttl_check. Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match") Reported-by: Kito Xu (veritas501) Closes: https://lore.kernel.org/netfilter-devel/20260414074556.2512750-1-hxzene@gmail.com/ Signed-off-by: Fernando Fernandez Mancera Reviewed-by: Pablo Neira Ayuso Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nfnetlink_osf.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 832a973c41777..c89efb951994a 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -31,26 +31,18 @@ EXPORT_SYMBOL_GPL(nf_osf_fingers); static inline int nf_osf_ttl(const struct sk_buff *skb, int ttl_check, unsigned char f_ttl) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); const struct iphdr *ip = ip_hdr(skb); - const struct in_ifaddr *ifa; - int ret = 0; - if (ttl_check == NF_OSF_TTL_TRUE) + switch (ttl_check) { + case NF_OSF_TTL_TRUE: return ip->ttl == f_ttl; - if (ttl_check == NF_OSF_TTL_NOCHECK) - return 1; - else if (ip->ttl <= f_ttl) + break; + case NF_OSF_TTL_NOCHECK: return 1; - - in_dev_for_each_ifa_rcu(ifa, in_dev) { - if (inet_ifa_match(ip->saddr, ifa)) { - ret = (ip->ttl == f_ttl); - break; - } + case NF_OSF_TTL_LESS: + default: + return ip->ttl <= f_ttl; } - - return ret; } struct nf_osf_hdr_ctx { From 9e1ff0eead073c4f46d874ad2526b7dda5465faf Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Thu, 16 Apr 2026 04:41:31 +0800 Subject: [PATCH 0848/1518] slip: reject VJ receive packets on instances with no rstate array [ Upstream commit e76607442d5b73e1ba6768f501ef815bb58c2c0e ] slhc_init() accepts rslots == 0 as a valid configuration, with the documented meaning of 'no receive compression'. In that case the allocation loop in slhc_init() is skipped, so comp->rstate stays NULL and comp->rslot_limit stays 0 (from the kzalloc of struct slcompress). The receive helpers do not defend against that configuration. slhc_uncompress() dereferences comp->rstate[x] when the VJ header carries an explicit connection ID, and slhc_remember() later assigns cs = &comp->rstate[...] after only comparing the packet's slot number to comp->rslot_limit. Because rslot_limit is 0, slot 0 passes the range check, and the code dereferences a NULL rstate. The configuration is reachable in-tree through PPP. PPPIOCSMAXCID stores its argument in a signed int, and (val >> 16) uses arithmetic shift. Passing 0xffff0000 therefore sign-extends to -1, so val2 + 1 is 0 and ppp_generic.c ends up calling slhc_init(0, 1). Because /dev/ppp open is gated by ns_capable(CAP_NET_ADMIN), the whole path is reachable from an unprivileged user namespace. Once the malformed VJ state is installed, any inbound VJ-compressed or VJ-uncompressed frame that selects slot 0 crashes the kernel in softirq context: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:slhc_uncompress (drivers/net/slip/slhc.c:519) Call Trace: ppp_receive_nonmp_frame (drivers/net/ppp/ppp_generic.c:2466) ppp_input (drivers/net/ppp/ppp_generic.c:2359) ppp_async_process (drivers/net/ppp/ppp_async.c:492) tasklet_action_common (kernel/softirq.c:926) handle_softirqs (kernel/softirq.c:623) run_ksoftirqd (kernel/softirq.c:1055) smpboot_thread_fn (kernel/smpboot.c:160) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:164) Reject the receive side on such instances instead of touching rstate. slhc_uncompress() falls through to its existing 'bad' label, which bumps sls_i_error and enters the toss state. slhc_remember() mirrors that with an explicit sls_i_error increment followed by slhc_toss(); the sls_i_runt counter is not used here because a missing rstate is an internal configuration state, not a runt packet. The transmit path is unaffected: the only in-tree caller that picks rslots from userspace (ppp_generic.c) still supplies tslots >= 1, and slip.c always calls slhc_init(16, 16), so comp->tstate remains valid and slhc_compress() continues to work. Fixes: 4ab42d78e37a ("ppp, slip: Validate VJ compression slot parameters completely") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260415204130.258866-2-bestswngs@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/slip/slhc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index ee9fd3a94b96f..fcb3eebe7311c 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -506,6 +506,8 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) comp->sls_i_error++; return 0; } + if (!comp->rstate) + goto bad; changes = *cp++; if(changes & NEW_C){ /* Make sure the state index is in range, then grab the state. @@ -649,6 +651,10 @@ slhc_remember(struct slcompress *comp, unsigned char *icp, int isize) struct cstate *cs; unsigned int ihl; + if (!comp->rstate) { + comp->sls_i_error++; + return slhc_toss(comp); + } /* The packet is shorter than a legal IP header. * Also make sure isize is positive. */ From 0511ecb00e61bf28e2fec4bb41fcce385c3a3b2d Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Thu, 16 Apr 2026 18:01:51 +0800 Subject: [PATCH 0849/1518] slip: bound decode() reads against the compressed packet length [ Upstream commit 4c1367a2d7aad643a6f87c6931b13cc1a25e8ca7 ] slhc_uncompress() parses a VJ-compressed TCP header by advancing a pointer through the packet via decode() and pull16(). Neither helper bounds-checks against isize, and decode() masks its return with & 0xffff so it can never return the -1 that callers test for -- those error paths are dead code. A short compressed frame whose change byte requests optional fields lets decode() read past the end of the packet. The over-read bytes are folded into the cached cstate and reflected into subsequent reconstructed packets. Make decode() and pull16() take the packet end pointer and return -1 when exhausted. Add a bounds check before the TCP-checksum read. The existing == -1 tests now do what they were always meant to. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Simon Horman Closes: https://lore.kernel.org/netdev/20260414134126.758795-2-horms@kernel.org/ Signed-off-by: Weiming Shi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260416100147.531855-5-bestswngs@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/slip/slhc.c | 43 ++++++++++++++++++++++++----------------- 1 file changed, 25 insertions(+), 18 deletions(-) diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index fcb3eebe7311c..daf086c283423 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -80,9 +80,9 @@ #include static unsigned char *encode(unsigned char *cp, unsigned short n); -static long decode(unsigned char **cpp); +static long decode(unsigned char **cpp, const unsigned char *end); static unsigned char * put16(unsigned char *cp, unsigned short x); -static unsigned short pull16(unsigned char **cpp); +static long pull16(unsigned char **cpp, const unsigned char *end); /* Allocate compression data structure * slots must be in range 0 to 255 (zero meaning no compression) @@ -190,30 +190,34 @@ encode(unsigned char *cp, unsigned short n) return cp; } -/* Pull a 16-bit integer in host order from buffer in network byte order */ -static unsigned short -pull16(unsigned char **cpp) +/* Pull a 16-bit integer in host order from buffer in network byte order. + * Returns -1 if the buffer is exhausted, otherwise the 16-bit value. + */ +static long +pull16(unsigned char **cpp, const unsigned char *end) { - short rval; + long rval; + if (*cpp + 2 > end) + return -1; rval = *(*cpp)++; rval <<= 8; rval |= *(*cpp)++; return rval; } -/* Decode a number */ +/* Decode a number. Returns -1 if the buffer is exhausted. */ static long -decode(unsigned char **cpp) +decode(unsigned char **cpp, const unsigned char *end) { int x; + if (*cpp >= end) + return -1; x = *(*cpp)++; - if(x == 0){ - return pull16(cpp) & 0xffff; /* pull16 returns -1 on error */ - } else { - return x & 0xff; /* -1 if PULLCHAR returned error */ - } + if (x == 0) + return pull16(cpp, end); + return x & 0xff; } /* @@ -499,6 +503,7 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) struct cstate *cs; int len, hdrlen; unsigned char *cp = icp; + const unsigned char *end = icp + isize; /* We've got a compressed packet; read the change byte */ comp->sls_i_compressed++; @@ -536,6 +541,8 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) thp = &cs->cs_tcp; ip = &cs->cs_ip; + if (cp + 2 > end) + goto bad; thp->check = *(__sum16 *)cp; cp += 2; @@ -566,26 +573,26 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) default: if(changes & NEW_U){ thp->urg = 1; - if((x = decode(&cp)) == -1) { + if((x = decode(&cp, end)) == -1) { goto bad; } thp->urg_ptr = htons(x); } else thp->urg = 0; if(changes & NEW_W){ - if((x = decode(&cp)) == -1) { + if((x = decode(&cp, end)) == -1) { goto bad; } thp->window = htons( ntohs(thp->window) + x); } if(changes & NEW_A){ - if((x = decode(&cp)) == -1) { + if((x = decode(&cp, end)) == -1) { goto bad; } thp->ack_seq = htonl( ntohl(thp->ack_seq) + x); } if(changes & NEW_S){ - if((x = decode(&cp)) == -1) { + if((x = decode(&cp, end)) == -1) { goto bad; } thp->seq = htonl( ntohl(thp->seq) + x); @@ -593,7 +600,7 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) break; } if(changes & NEW_I){ - if((x = decode(&cp)) == -1) { + if((x = decode(&cp, end)) == -1) { goto bad; } ip->id = htons (ntohs (ip->id) + x); From 86cf2eba2056bcf9c41fba260e599bd95bf9943b Mon Sep 17 00:00:00 2001 From: Chia-Yu Chang Date: Fri, 17 Apr 2026 17:25:51 +0200 Subject: [PATCH 0850/1518] net/sched: sch_dualpi2: drain both C-queue and L-queue in dualpi2_change() [ Upstream commit 478ed6b7d2577439c610f91fa8759a4c878a4264 ] Fix dualpi2_change() to correctly enforce updated limit and memlimit values after a configuration change of the dualpi2 qdisc. Before this patch, dualpi2_change() always attempted to dequeue packets via the root qdisc (C-queue) when reducing backlog or memory usage, and unconditionally assumed that a valid skb will be returned. When traffic classification results in packets being queued in the L-queue while the C-queue is empty, this leads to a NULL skb dereference during limit or memlimit enforcement. This is fixed by first dequeuing from the C-queue path if it is non-empty. Once the C-queue is empty, packets are dequeued directly from the L-queue. Return values from qdisc_dequeue_internal() are checked for both queues. When dequeuing from the L-queue, the parent qdisc qlen and backlog counters are updated explicitly to keep overall qdisc statistics consistent. Fixes: 320d031ad6e4 ("sched: Struct definition and parsing of dualpi2 qdisc") Reported-by: "Kito Xu (veritas501)" Closes: https://lore.kernel.org/netdev/20260413075740.2234828-1-hxzene@gmail.com/ Signed-off-by: Chia-Yu Chang Link: https://patch.msgid.link/20260417152551.71648-1-chia-yu.chang@nokia-bell-labs.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_dualpi2.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 4b975feb52b1f..efa32240c5a95 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -871,11 +871,35 @@ static int dualpi2_change(struct Qdisc *sch, struct nlattr *opt, old_backlog = sch->qstats.backlog; while (qdisc_qlen(sch) > sch->limit || q->memory_used > q->memory_limit) { - struct sk_buff *skb = qdisc_dequeue_internal(sch, true); + struct sk_buff *skb = NULL; - q->memory_used -= skb->truesize; - qdisc_qstats_backlog_dec(sch, skb); - rtnl_qdisc_drop(skb, sch); + if (qdisc_qlen(sch) > qdisc_qlen(q->l_queue)) { + skb = qdisc_dequeue_internal(sch, true); + if (unlikely(!skb)) { + WARN_ON_ONCE(1); + break; + } + q->memory_used -= skb->truesize; + rtnl_qdisc_drop(skb, sch); + } else if (qdisc_qlen(q->l_queue)) { + skb = qdisc_dequeue_internal(q->l_queue, true); + if (unlikely(!skb)) { + WARN_ON_ONCE(1); + break; + } + /* L-queue packets are counted in both sch and + * l_queue on enqueue; qdisc_dequeue_internal() + * handled l_queue, so we further account for sch. + */ + --sch->q.qlen; + qdisc_qstats_backlog_dec(sch, skb); + q->memory_used -= skb->truesize; + rtnl_qdisc_drop(skb, q->l_queue); + qdisc_qstats_drop(sch); + } else { + WARN_ON_ONCE(1); + break; + } } qdisc_tree_reduce_backlog(sch, old_qlen - qdisc_qlen(sch), old_backlog - sch->qstats.backlog); From 3a6dfd9f2cdb9f070ea867e22f05b725117ae987 Mon Sep 17 00:00:00 2001 From: Anand Moon Date: Thu, 19 Feb 2026 16:05:46 +0530 Subject: [PATCH 0851/1518] arm64: dts: amlogic: meson-axg: Add missing cache information to cpu0 [ Upstream commit 918273be0885362a9a00615b46e03f15f8b55667 ] Add missing L1 data and instruction cache parameters to the CPU node 0 for the Cortex-A53 caches on the Meson AXG SoC. Fixes: 3b6ad2a43367 ("arm64: dts: amlogic: Add cache information to the Amlogic AXG SoCS") Signed-off-by: Anand Moon Link: https://patch.msgid.link/20260219103548.18392-1-linux.amoon@gmail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-axg.dtsi | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index bbf94a1f92a10..3058b60338dbf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -72,6 +72,12 @@ compatible = "arm,cortex-a53"; reg = <0x0 0x0>; enable-method = "psci"; + d-cache-line-size = <32>; + d-cache-size = <0x8000>; + d-cache-sets = <32>; + i-cache-line-size = <32>; + i-cache-size = <0x8000>; + i-cache-sets = <32>; next-level-cache = <&l2>; clocks = <&scpi_dvfs 0>; dynamic-power-coefficient = <140>; From 83cc775fc8fd770148dbdba11c0d1d0c62f36892 Mon Sep 17 00:00:00 2001 From: Jun Yan Date: Mon, 30 Mar 2026 22:51:11 +0800 Subject: [PATCH 0852/1518] arm64: dts: meson-gxl-p230: fix ethernet PHY interrupt number [ Upstream commit 174a0ef3b33434f475c87e66f37980e39b73805a ] Correct the interrupt number assigned to the Realtek PHY in the p230 following the same logic as commit 3106507e1004 ("ARM64: dts: meson-gxm: fix q200 interrupt number"),as reported in [PATCH 0/2] Ethernet PHY interrupt improvements [1]. [1] https://lore.kernel.org/all/20171202214037.17017-1-martin.blumenstingl@googlemail.com/ Fixes: b94d22d94ad2 ("ARM64: dts: meson-gx: add external PHY interrupt on some platforms") Signed-off-by: Jun Yan Reviewed-by: Martin Blumenstingl Link: https://patch.msgid.link/20260330145111.115318-1-jerrysteve1101@gmail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts index 7dffeb5931c9b..701de57ff0f37 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-p230.dts @@ -84,7 +84,8 @@ reset-gpios = <&gpio GPIOZ_14 GPIO_ACTIVE_LOW>; interrupt-parent = <&gpio_intc>; - interrupts = <29 IRQ_TYPE_LEVEL_LOW>; + /* MAC_INTR on GPIOZ_15 */ + interrupts = <25 IRQ_TYPE_LEVEL_LOW>; eee-broken-1000t; }; }; From 9c59c79788e89055c07e23a10e0ef431c7996850 Mon Sep 17 00:00:00 2001 From: Sangyun Kim Date: Sun, 19 Apr 2026 17:08:38 +0900 Subject: [PATCH 0853/1518] pwm: atmel-tcb: Cache clock rates and mark chip as atomic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 68637b68afcc3cb4d56aca14a3a1d1b47b879369 ] atmel_tcb_pwm_apply() holds tcbpwmc->lock as a spinlock via guard(spinlock)() and then calls atmel_tcb_pwm_config(), which calls clk_get_rate() twice. clk_get_rate() acquires clk_prepare_lock (a mutex), so this is a sleep-in-atomic-context violation. On CONFIG_DEBUG_ATOMIC_SLEEP kernels every pwm_apply_state() that enables or reconfigures the PWM triggers a "BUG: sleeping function called from invalid context" warning. Acquire exclusive control over the clock rates with clk_rate_exclusive_get() at probe time and cache the rates in struct atmel_tcb_pwm_chip, then read the cached rates from atmel_tcb_pwm_config(). This keeps the spinlock-based mutual exclusion introduced in commit 37f7707077f5 ("pwm: atmel-tcb: Fix race condition and convert to guards") and removes the sleeping calls from the atomic section. With no sleeping calls left in .apply() and the regmap-mmio bus already running with fast_io=true, also mark the chip as atomic so consumers can use pwm_apply_atomic() from atomic context. Fixes: 37f7707077f5 ("pwm: atmel-tcb: Fix race condition and convert to guards") Signed-off-by: Sangyun Kim Link: https://patch.msgid.link/20260419080838.3192357-1-sangyun.kim@snu.ac.kr [ukleinek: Ensure .clk is enabled before calling clk_get_rate on it.] Signed-off-by: Uwe Kleine-König Signed-off-by: Sasha Levin --- drivers/pwm/pwm-atmel-tcb.c | 38 +++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c index f9ff78ba122d4..3d30aeab507e0 100644 --- a/drivers/pwm/pwm-atmel-tcb.c +++ b/drivers/pwm/pwm-atmel-tcb.c @@ -50,6 +50,8 @@ struct atmel_tcb_pwm_chip { spinlock_t lock; u8 channel; u8 width; + unsigned long rate; + unsigned long slow_rate; struct regmap *regmap; struct clk *clk; struct clk *gclk; @@ -266,7 +268,7 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, int slowclk = 0; unsigned period; unsigned duty; - unsigned rate = clk_get_rate(tcbpwmc->clk); + unsigned long rate = tcbpwmc->rate; unsigned long long min; unsigned long long max; @@ -294,7 +296,7 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, */ if (i == ARRAY_SIZE(atmel_tcb_divisors)) { i = slowclk; - rate = clk_get_rate(tcbpwmc->slow_clk); + rate = tcbpwmc->slow_rate; min = div_u64(NSEC_PER_SEC, rate); max = min << tcbpwmc->width; @@ -431,24 +433,49 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) } chip->ops = &atmel_tcb_pwm_ops; + chip->atomic = true; tcbpwmc->channel = channel; tcbpwmc->width = config->counter_width; - err = clk_prepare_enable(tcbpwmc->slow_clk); + err = clk_prepare_enable(tcbpwmc->clk); if (err) goto err_gclk; + err = clk_prepare_enable(tcbpwmc->slow_clk); + if (err) + goto err_disable_clk;; + + err = clk_rate_exclusive_get(tcbpwmc->clk); + if (err) + goto err_disable_slow_clk; + + err = clk_rate_exclusive_get(tcbpwmc->slow_clk); + if (err) + goto err_clk_unlock; + + tcbpwmc->rate = clk_get_rate(tcbpwmc->clk); + tcbpwmc->slow_rate = clk_get_rate(tcbpwmc->slow_clk); + spin_lock_init(&tcbpwmc->lock); err = pwmchip_add(chip); if (err < 0) - goto err_disable_clk; + goto err_slow_clk_unlock; platform_set_drvdata(pdev, chip); return 0; +err_slow_clk_unlock: + clk_rate_exclusive_put(tcbpwmc->slow_clk); + +err_clk_unlock: + clk_rate_exclusive_put(tcbpwmc->clk); + err_disable_clk: + clk_disable_unprepare(tcbpwmc->clk); + +err_disable_slow_clk: clk_disable_unprepare(tcbpwmc->slow_clk); err_gclk: @@ -470,6 +497,9 @@ static void atmel_tcb_pwm_remove(struct platform_device *pdev) pwmchip_remove(chip); + clk_rate_exclusive_put(tcbpwmc->slow_clk); + clk_rate_exclusive_put(tcbpwmc->clk); + clk_disable_unprepare(tcbpwmc->clk); clk_disable_unprepare(tcbpwmc->slow_clk); clk_put(tcbpwmc->gclk); clk_put(tcbpwmc->clk); From 6237cc0f7a4cf74daf33e1f559298d344cc42a60 Mon Sep 17 00:00:00 2001 From: DaeMyung Kang Date: Sun, 19 Apr 2026 20:02:54 +0900 Subject: [PATCH 0854/1518] ksmbd: destroy tree_conn_ida in ksmbd_session_destroy() [ Upstream commit c049ee14eb4343b69b6f7755563f961f5e153423 ] When per-session tree_conn_ida was converted from a dynamically allocated ksmbd_ida to an embedded struct ida, ksmbd_ida_free() was removed from ksmbd_session_destroy() but no matching ida_destroy() was added. The session is therefore freed with the IDA's backing xarray still intact. The kernel IDA API expects ida_init() and ida_destroy() to be paired over an object's lifetime, so add the missing cleanup before the enclosing session is freed. Also move ida_init() to right after the session is allocated so that it is always paired with the destroy call even on the early error paths of __session_create() (ksmbd_init_file_table() or __init_smb2_session() failures), both of which jump to the error label and invoke ksmbd_session_destroy() on a partially initialised session. No leak has been observed in testing; this is a pairing fix to match the IDA lifetime rules, not a response to a reproduced regression. Fixes: d40012a83f87 ("cifsd: declare ida statically") Signed-off-by: DaeMyung Kang Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/mgmt/user_session.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index ed343807660fa..afa0daa3f5d88 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -170,6 +170,7 @@ void ksmbd_session_destroy(struct ksmbd_session *sess) free_channel_list(sess); kfree(sess->Preauth_HashValue); ksmbd_release_id(&session_ida, sess->id); + ida_destroy(&sess->tree_conn_ida); kfree(sess); } @@ -444,6 +445,8 @@ static struct ksmbd_session *__session_create(int protocol) if (!sess) return NULL; + ida_init(&sess->tree_conn_ida); + if (ksmbd_init_file_table(&sess->file_table)) goto error; @@ -463,8 +466,6 @@ static struct ksmbd_session *__session_create(int protocol) if (ret) goto error; - ida_init(&sess->tree_conn_ida); - down_write(&sessions_table_lock); hash_add(sessions_table, &sess->hlist, sess->id); up_write(&sessions_table_lock); From 9c3936515a523406410279e0c9c05a26eeb0cf81 Mon Sep 17 00:00:00 2001 From: DaeMyung Kang Date: Sun, 19 Apr 2026 20:02:55 +0900 Subject: [PATCH 0855/1518] ksmbd: destroy async_ida in ksmbd_conn_free() [ Upstream commit b32c8db48212a34998c36d0bbc05b29d5c407ef5 ] When per-connection async_ida was converted from a dynamically allocated ksmbd_ida to an embedded struct ida, ksmbd_ida_free() was removed from the connection teardown path but no matching ida_destroy() was added. The connection is therefore freed with the IDA's backing xarray still intact. The kernel IDA API expects ida_init() and ida_destroy() to be paired over an object's lifetime, so add the missing cleanup before the connection is freed. No leak has been observed in testing; this is a pairing fix to match the IDA lifetime rules, not a response to a reproduced regression. Fixes: d40012a83f87 ("cifsd: declare ida statically") Signed-off-by: DaeMyung Kang Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/connection.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index b4ef62b9e660c..a03132adcc1e5 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -41,6 +41,15 @@ void ksmbd_conn_free(struct ksmbd_conn *conn) kfree(conn->preauth_info); kfree(conn->mechToken); if (atomic_dec_and_test(&conn->refcnt)) { + /* + * async_ida is embedded in struct ksmbd_conn, so pair + * ida_destroy() with the final kfree() rather than with + * the unconditional field teardown above. This keeps + * the IDA valid for the entire lifetime of the struct, + * even while other refcount holders (oplock / vfs + * durable handles) still reference the connection. + */ + ida_destroy(&conn->async_ida); conn->transport->ops->free_transport(conn->transport); kfree(conn); } From 06f709d0e531f3e54d88665dd426be3998a774e6 Mon Sep 17 00:00:00 2001 From: DaeMyung Kang Date: Tue, 21 Apr 2026 03:45:11 +0900 Subject: [PATCH 0856/1518] ksmbd: fix durable fd leak on ClientGUID mismatch in durable v2 open [ Upstream commit 804054d19886ac6628883d82410f6ee42a818664 ] ksmbd_lookup_fd_cguid() returns a ksmbd_file with its refcount incremented via ksmbd_fp_get(). parse_durable_handle_context() in the DURABLE_REQ_V2 case properly releases this reference on every path inside the ClientGUID-match branch, either by calling ksmbd_put_durable_fd() or by transferring ownership to dh_info->fp for a successful reconnect. However, when an entry exists in the global file table with the same CreateGuid but a different ClientGUID, the code simply falls through to the new-open path without dropping the reference obtained from ksmbd_lookup_fd_cguid(). Per MS-SMB2 section 3.3.5.9.10 ("Handling the SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 Create Context"), the server MUST locate an Open whose Open.CreateGuid matches the request's CreateGuid AND whose Open.ClientGuid matches the ClientGuid of the connection that received the request. If no such Open is found, the server MUST continue with the normal open execution phase. A CreateGuid hit with a ClientGUID mismatch is therefore the "Open not found" case: proceeding with a new open is correct, but the reference obtained purely as a side effect of the lookup must not be leaked. Repeated requests that hit this mismatch pin global_ft entries, prevent __ksmbd_close_fd() from ever running for the corresponding files, and defeat the durable scavenger, leading to long-lived resource leaks. Release the reference in the mismatch path and clear dh_info->fp so subsequent logic does not mistake a non-matching lookup result for a reconnect target. Fixes: c8efcc786146 ("ksmbd: add support for durable handles v1/v2") Signed-off-by: DaeMyung Kang Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4bfbfe53aa4eb..756624b4e90e0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2854,6 +2854,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work, dh_info->reconnected = true; goto out; } + ksmbd_put_durable_fd(dh_info->fp); + dh_info->fp = NULL; } if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || From 2cc8a4db633b10715450b291c1343859a4b2c509 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Tue, 21 Apr 2026 00:31:47 +0900 Subject: [PATCH 0857/1518] ksmbd: scope conn->binding slowpath to bound sessions only [ Upstream commit b0da97c034b6107d14e537e212d4ce8b22109a58 ] When the binding SESSION_SETUP sets conn->binding = true, the flag stays set after the call so that the global session lookup in ksmbd_session_lookup_all() can find the session, which was not added to conn->sessions. Because the flag is connection-wide, the global lookup path will also resolve any other session by id if asked. Tighten the global lookup so that the returned session must have this connection registered in its channel xarray (sess->ksmbd_chann_list). The channel entry is installed by the existing binding_session path in ntlm_authenticate()/krb5_authenticate() when a SESSION_SETUP completes successfully, so this condition is a strict equivalent of "this connection has been accepted as a channel of this session". Connections that have not bound to a given session cannot reach it via the global table. The existing conn->binding gate for entering the slowpath is preserved so that non-binding connections keep the fast-path-only behavior, and the session->state check is unchanged. Fixes: f5a544e3bab7 ("ksmbd: add support for SMB3 multichannel") Signed-off-by: Hyunwoo Kim Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/mgmt/user_session.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index afa0daa3f5d88..5bc2f18d68bbc 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -327,8 +327,13 @@ struct ksmbd_session *ksmbd_session_lookup_all(struct ksmbd_conn *conn, struct ksmbd_session *sess; sess = ksmbd_session_lookup(conn, id); - if (!sess && conn->binding) + if (!sess && conn->binding) { sess = ksmbd_session_lookup_slowpath(id); + if (sess && !xa_load(&sess->ksmbd_chann_list, (long)conn)) { + ksmbd_user_session_put(sess); + sess = NULL; + } + } if (sess && sess->state != SMB2_SESSION_VALID) { ksmbd_user_session_put(sess); sess = NULL; From 20e3b61e21c7c29e1ffe9c5b873822b1e55e4333 Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Mon, 20 Apr 2026 10:54:23 +0000 Subject: [PATCH 0858/1518] net: validate skb->napi_id in RX tracepoints [ Upstream commit 3bfcf396081ace536733b454ff128d53116581e5 ] Since commit 2bd82484bb4c ("xps: fix xps for stacked devices"), skb->napi_id shares storage with sender_cpu. RX tracepoints using net_dev_rx_verbose_template read skb->napi_id directly and can therefore report sender_cpu values as if they were NAPI IDs. For example, on the loopback path this can report 1 as napi_id, where 1 comes from raw_smp_processor_id() + 1 in the XPS path: # bpftrace -e 'tracepoint:net:netif_rx_entry{ print(args->napi_id); }' # taskset -c 0 ping -c 1 ::1 Report only valid NAPI IDs in these tracepoints and use 0 otherwise. Fixes: 2bd82484bb4c ("xps: fix xps for stacked devices") Signed-off-by: Kohei Enju Reviewed-by: Simon Horman Reviewed-by: Jiayuan Chen Link: https://patch.msgid.link/20260420105427.162816-1-kohei@enjuk.jp Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/trace/events/net.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/trace/events/net.h b/include/trace/events/net.h index d55162c12f90a..d3fe6acf85d28 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -10,6 +10,7 @@ #include #include #include +#include TRACE_EVENT(net_dev_start_xmit, @@ -193,7 +194,8 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, TP_fast_assign( __assign_str(name); #ifdef CONFIG_NET_RX_BUSY_POLL - __entry->napi_id = skb->napi_id; + __entry->napi_id = napi_id_valid(skb->napi_id) ? + skb->napi_id : 0; #else __entry->napi_id = 0; #endif From a2b26c4ade3ead6a2c0c3f9f04ac7ef979b5ab1b Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Sat, 18 Apr 2026 08:04:37 +0530 Subject: [PATCH 0859/1518] bnge: fix initial HWRM sequence [ Upstream commit 70d7c905a07ae8415b955569620bf2bf77423553 ] Firmware may not advertize correct resources if backing store is not enabled before resource information is queried. Fix the initial sequence of HWRMs so that driver gets capabilities and resource information correctly. Fixes: 3fa9e977a0cd ("bng_en: Initialize default configuration") Signed-off-by: Vikas Gupta Reviewed-by: Rahul Gupta Link: https://patch.msgid.link/20260418023438.1597876-2-vikas.gupta@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../net/ethernet/broadcom/bnge/bnge_core.c | 30 ++++++++++++++----- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_core.c b/drivers/net/ethernet/broadcom/bnge/bnge_core.c index 312a9db4d75d1..657cd7a880d29 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_core.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_core.c @@ -68,6 +68,13 @@ static int bnge_func_qcaps(struct bnge_dev *bd) return rc; } + return 0; +} + +static int bnge_func_qrcaps_qcfg(struct bnge_dev *bd) +{ + int rc; + rc = bnge_hwrm_func_resc_qcaps(bd); if (rc) { dev_err(bd->dev, "query resc caps failure rc: %d\n", rc); @@ -127,23 +134,28 @@ static int bnge_fw_register_dev(struct bnge_dev *bd) bnge_hwrm_fw_set_time(bd); - rc = bnge_hwrm_func_drv_rgtr(bd); + /* Get the resources and configuration from firmware */ + rc = bnge_func_qcaps(bd); if (rc) { - dev_err(bd->dev, "Failed to rgtr with firmware rc: %d\n", rc); + dev_err(bd->dev, "Failed querying caps rc: %d\n", rc); return rc; } rc = bnge_alloc_ctx_mem(bd); if (rc) { dev_err(bd->dev, "Failed to allocate ctx mem rc: %d\n", rc); - goto err_func_unrgtr; + goto err_free_ctx_mem; } - /* Get the resources and configuration from firmware */ - rc = bnge_func_qcaps(bd); + rc = bnge_hwrm_func_drv_rgtr(bd); if (rc) { - dev_err(bd->dev, "Failed initial configuration rc: %d\n", rc); - rc = -ENODEV; + dev_err(bd->dev, "Failed to rgtr with firmware rc: %d\n", rc); + goto err_free_ctx_mem; + } + + rc = bnge_func_qrcaps_qcfg(bd); + if (rc) { + dev_err(bd->dev, "Failed querying resources rc: %d\n", rc); goto err_func_unrgtr; } @@ -152,7 +164,9 @@ static int bnge_fw_register_dev(struct bnge_dev *bd) return 0; err_func_unrgtr: - bnge_fw_unregister_dev(bd); + bnge_hwrm_func_drv_unrgtr(bd); +err_free_ctx_mem: + bnge_free_ctx_mem(bd); return rc; } From 1269a7d38577efedec57f17a4c5b6e2d59548fa0 Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Sat, 18 Apr 2026 08:04:38 +0530 Subject: [PATCH 0860/1518] bnge: remove unsupported backing store type [ Upstream commit c6b34add67a5402f53359580956b5c318965a893 ] The backing store type, BNGE_CTX_MRAV, is not applicable in Thor Ultra devices. Remove it from the backing store configuration, as the firmware will not populate entities in this backing store type, due to which the driver load fails. Fixes: 29c5b358f385 ("bng_en: Add backing store support") Signed-off-by: Vikas Gupta Reviewed-by: Dharmender Garg Link: https://patch.msgid.link/20260418023438.1597876-3-vikas.gupta@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnge/bnge_rmem.c | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c index 79f5ce2e5d083..75d14e52a5bb2 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c @@ -325,7 +325,6 @@ int bnge_alloc_ctx_mem(struct bnge_dev *bd) u32 l2_qps, qp1_qps, max_qps; u32 ena, entries_sp, entries; u32 srqs, max_srqs, min; - u32 num_mr, num_ah; u32 extra_srqs = 0; u32 extra_qps = 0; u32 fast_qpmd_qps; @@ -391,21 +390,6 @@ int bnge_alloc_ctx_mem(struct bnge_dev *bd) if (!bnge_is_roce_en(bd)) goto skip_rdma; - ctxm = &ctx->ctx_arr[BNGE_CTX_MRAV]; - /* 128K extra is needed to accommodate static AH context - * allocation by f/w. - */ - num_mr = min_t(u32, ctxm->max_entries / 2, 1024 * 256); - num_ah = min_t(u32, num_mr, 1024 * 128); - ctxm->split_entry_cnt = BNGE_CTX_MRAV_AV_SPLIT_ENTRY + 1; - if (!ctxm->mrav_av_entries || ctxm->mrav_av_entries > num_ah) - ctxm->mrav_av_entries = num_ah; - - rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, num_mr + num_ah, 2); - if (rc) - return rc; - ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV; - ctxm = &ctx->ctx_arr[BNGE_CTX_TIM]; rc = bnge_setup_ctxm_pg_tbls(bd, ctxm, l2_qps + qp1_qps + extra_qps, 1); if (rc) From 91ce1bb6e4194dc2321748f68145359dcf86e350 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Sat, 18 Apr 2026 10:10:47 -0400 Subject: [PATCH 0861/1518] net/rds: zero per-item info buffer before handing it to visitors [ Upstream commit c88eb7e8d8397a8c1db59c425332c5a30b2a1682 ] rds_for_each_conn_info() and rds_walk_conn_path_info() both hand a caller-allocated on-stack u64 buffer to a per-connection visitor and then copy the full item_len bytes back to user space via rds_info_copy() regardless of how much of the buffer the visitor actually wrote. rds_ib_conn_info_visitor() and rds6_ib_conn_info_visitor() only write a subset of their output struct when the underlying rds_connection is not in state RDS_CONN_UP (src/dst addr, tos, sl and the two GIDs via explicit memsets). Several u32 fields (max_send_wr, max_recv_wr, max_send_sge, rdma_mr_max, rdma_mr_size, cache_allocs) and the 2-byte alignment hole between sl and cache_allocs remain as whatever stack contents preceded the visitor call and are then memcpy_to_user()'d out to user space. struct rds_info_rdma_connection and struct rds6_info_rdma_connection are the only rds_info_* structs in include/uapi/linux/rds.h that are not marked __attribute__((packed)), so they have a real alignment hole. The other info visitors (rds_conn_info_visitor, rds6_conn_info_visitor, rds_tcp_tc_info, ...) write all fields of their packed output struct today and are not known to be vulnerable, but a future visitor that adds a conditional write-path would have the same bug. Reproduction on a kernel built without CONFIG_INIT_STACK_ALL_ZERO=y: a local unprivileged user opens AF_RDS, sets SO_RDS_TRANSPORT=IB, binds to a local address on an RDMA-capable netdev (rxe soft-RoCE on any netdev is sufficient), sendto()'s any peer on the same subnet (fails cleanly but installs an rds_connection in the global hash in RDS_CONN_CONNECTING), then calls getsockopt(SOL_RDS, RDS_INFO_IB_CONNECTIONS). The returned 68-byte item contains 26 bytes of stack garbage including kernel text/data pointers: 0..7 0a 63 00 01 0a 63 00 02 src=10.99.0.1 dst=10.99.0.2 8..39 00 ... gids (memset-zeroed) 40..47 e0 92 a3 81 ff ff ff ff kernel pointer (max_send_wr) 48..55 7f 37 b5 81 ff ff ff ff kernel pointer (rdma_mr_max) 56..59 01 00 08 00 rdma_mr_size (garbage) 60..61 00 00 tos, sl 62..63 00 00 alignment padding 64..67 18 00 00 00 cache_allocs (garbage) Fix by zeroing the per-item buffer in both rds_for_each_conn_info() and rds_walk_conn_path_info() before invoking the visitor. This covers the IPv4/IPv6 IB visitors and hardens all current and future visitors against the same class of bug. No functional change for visitors that fully populate their output. Changes in v2: - retarget at the net tree (subject prefix "[PATCH net v2]", net/rds: prefix in the title) - pick up Reviewed-by tags from Sharath Srinivasan and Allison Henderson Fixes: ec16227e1414 ("RDS/IB: Infiniband transport") Signed-off-by: Michael Bommarito Reviewed-by: Sharath Srinivasan Reviewed-by: Allison Henderson Assisted-by: Claude:claude-opus-4-7 Link: https://patch.msgid.link/20260418141047.3398203-1-michael.bommarito@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/rds/connection.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/rds/connection.c b/net/rds/connection.c index dbfea6fa11260..4764628fe12a3 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -674,6 +674,13 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, i++, head++) { hlist_for_each_entry_rcu(conn, head, c_hash_node) { + /* Zero the per-item buffer before handing it to the + * visitor so any field the visitor does not write - + * including implicit alignment padding - cannot leak + * stack contents to user space via rds_info_copy(). + */ + memset(buffer, 0, item_len); + /* XXX no c_lock usage.. */ if (!visitor(conn, buffer)) continue; @@ -723,6 +730,13 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len, */ cp = conn->c_path; + /* Zero the per-item buffer for the same reason as + * rds_for_each_conn_info(): any byte the visitor + * does not write (including alignment padding) must + * not leak stack contents via rds_info_copy(). + */ + memset(buffer, 0, item_len); + /* XXX no cp_lock usage.. */ if (!visitor(cp, buffer)) continue; From 2496a593c6e35973c6c5ba64f437ef957d10b9b6 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Mon, 20 Apr 2026 17:51:25 -0700 Subject: [PATCH 0862/1518] ice: fix timestamp interrupt configuration for E825C [ Upstream commit c0a575a801a2040eb1e0db54b488f8c548c8458a ] The E825C ice_phy_cfg_intr_eth56g() function is responsible for programming the PHY interrupt for a given port. This function writes to the PHY_REG_TS_INT_CONFIG register of the port. The register is responsible for configuring whether the port interrupt logic is enabled, as well as programming the threshold of waiting timestamps that will trigger an interrupt from this port. This threshold value must not be programmed to zero while the interrupt is enabled. Doing so puts the port in a misconfigured state where the PHY timestamp interrupt for the quad of connected ports will become stuck. This occurs, because a threshold of zero results in the timestamp interrupt status for the port becoming stuck high. The four ports in the connected quad have their timestamp status indicators muxed together. A new interrupt cannot be generated until the timestamp status indicators return low for all four ports. Normally, the timestamp status for a port will clear once there are fewer timestamps in that ports timestamp memory bank than the threshold. A threshold of zero makes this impossible, so the timestamp status for the port does not clear. The ice driver never intentionally programs the threshold to zero, indeed the driver always programs it to a value of 1, intending to get an interrupt immediately as soon as even a single packet is waiting for a timestamp. However, there is a subtle flaw in the programming logic in the ice_phy_cfg_intr_eth56g() function. Due to the way that the hardware handles enabling the PHY interrupt. If the threshold value is modified at the same time as the interrupt is enabled, the HW PHY state machine might enable the interrupt before the new threshold value is actually updated. This leaves a potential race condition caused by the hardware logic where a PHY timestamp interrupt might be triggered before the non-zero threshold is written, resulting in the PHY timestamp logic becoming stuck. Once the PHY timestamp status is stuck high, it will remain stuck even after attempting to reprogram the PHY block by changing its threshold or disabling the interrupt. Even a typical PF or CORE reset will not reset the particular block of the PHY that becomes stuck. Even a warm power cycle is not guaranteed to cause the PHY block to reset, and a cold power cycle is required. Prevent this by always writing the PHY_REG_TS_INT_CONFIG in two stages. First write the threshold value with the interrupt disabled, and only write the enable bit after the threshold has been programmed. When disabling the interrupt, leave the threshold unchanged. Additionally, re-read the register after writing it to guarantee that the write to the PHY has been flushed upon exit of the function. While we're modifying this function implementation, explicitly reject programming a threshold of 0 when enabling the interrupt. No caller does this today, but the consequences of doing so are significant. An explicit rejection in the code makes this clear. Fixes: 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Signed-off-by: Grzegorz Nitka Reviewed-by: Aleksandr Loktionov Reviewed-by: Petr Oros Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260420-jk-iwl-net-2026-04-20-ptp-e825c-phy-interrupt-fixes-v1-1-bc2240f42251@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 36 ++++++++++++++++++--- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 161a0ae8599c1..0a20ae0c2901b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -1847,6 +1847,8 @@ static int ice_phy_cfg_mac_eth56g(struct ice_hw *hw, u8 port) * @ena: enable or disable interrupt * @threshold: interrupt threshold * + * The threshold cannot be 0 while the interrupt is enabled. + * * Configure TX timestamp interrupt for the specified port * * Return: @@ -1858,19 +1860,45 @@ int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold) int err; u32 val; + if (ena && !threshold) + return -EINVAL; + err = ice_read_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, &val); if (err) return err; + val &= ~PHY_TS_INT_CONFIG_ENA_M; if (ena) { - val |= PHY_TS_INT_CONFIG_ENA_M; val &= ~PHY_TS_INT_CONFIG_THRESHOLD_M; val |= FIELD_PREP(PHY_TS_INT_CONFIG_THRESHOLD_M, threshold); - } else { - val &= ~PHY_TS_INT_CONFIG_ENA_M; + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, + val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, + "Failed to update 'threshold' PHY_REG_TS_INT_CONFIG port=%u ena=%u threshold=%u\n", + port, !!ena, threshold); + return err; + } + val |= PHY_TS_INT_CONFIG_ENA_M; } - return ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, val); + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, + "Failed to update 'ena' PHY_REG_TS_INT_CONFIG port=%u ena=%u threshold=%u\n", + port, !!ena, threshold); + return err; + } + + err = ice_read_ptp_reg_eth56g(hw, port, PHY_REG_TS_INT_CONFIG, &val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, + "Failed to read PHY_REG_TS_INT_CONFIG port=%u ena=%u threshold=%u\n", + port, !!ena, threshold); + return err; + } + + return 0; } /** From 77803e30cdd02751d8aa1941d76f99d7c8e91214 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Mon, 20 Apr 2026 17:51:26 -0700 Subject: [PATCH 0863/1518] ice: perform PHY soft reset for E825C ports at initialization [ Upstream commit 3ec46e157c7fa420c77dfc23f7030e61f2f3fd55 ] In some cases the PHY timestamp block of the E825C can become stuck. This is known to occur if the software writes 0 to the Tx timestamp threshold, and with older versions of the ice driver the threshold configuration is buggy and can race in such that hardware briefly operates with a zero threshold enabled. There are no other known ways to trigger this behavior, but once it occurs, the hardware is not recovered by normal reset, a driver reload, or even a warm power cycle of the system. A cold power cycle is sufficient to recover hardware, but this is extremely invasive and can result in significant downtime on customer deployments. The PHY for each port has a timestamping block which has its own reset functionality accessible by programming the PHY_REG_GLOBAL register. Writing to the PHY_REG_GLOBAL_SOFT_RESET_BIT triggers the hardware to perform a complete reset of the timestamping block of the PHY. This includes clearing the timestamp status for the port, clearing all outstanding timestamps in the memory bank, and resetting the PHY timer. The new ice_ptp_phy_soft_reset_eth56g() function toggles the PHY_REG_GLOBAL soft reset bit with the required delays, ensuring the PHY is properly reinitialized without requiring a full device reset. The sequence clears the reset bit, asserts it, then clears it again, with short waits between transitions to allow hardware stabilization. Call this function in the new ice_ptp_init_phc_e825c(), implementing the E825C device specific variant of the ice_ptp_init_phc(). Note that if ice_ptp_init_phc() fails, PTP functionality may be disabled, but the driver will still load to allow basic functionality to continue. This causes the clock owning PF driver to perform a PHY soft reset for every port during initialization. This ensures the driver begins life in a known functional state regardless of how it was previously programmed. This ensures that we properly reconfigure the hardware after a device reset or when loading the driver, even if it was previously misconfigured with an out-of-date or modified driver. Fixes: 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Signed-off-by: Timothy Miskell Signed-off-by: Grzegorz Nitka Reviewed-by: Aleksandr Loktionov Reviewed-by: Petr Oros Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260420-jk-iwl-net-2026-04-20-ptp-e825c-phy-interrupt-fixes-v1-2-bc2240f42251@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 90 ++++++++++++++++++++- drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 4 + 2 files changed, 93 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 0a20ae0c2901b..1ae795405ac3c 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -377,6 +377,31 @@ static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay) * The following functions operate on devices with the ETH 56G PHY. */ +/** + * ice_ptp_init_phc_e825c - Perform E825C specific PHC initialization + * @hw: pointer to HW struct + * + * Perform E825C-specific PTP hardware clock initialization steps. + * + * Return: 0 on success, or a negative error value on failure. + */ +static int ice_ptp_init_phc_e825c(struct ice_hw *hw) +{ + int err; + + /* Soft reset all ports, to ensure everything is at a clean state */ + for (int port = 0; port < hw->ptp.num_lports; port++) { + err = ice_ptp_phy_soft_reset_eth56g(hw, port); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to soft reset port %d, err %d\n", + port, err); + return err; + } + } + + return 0; +} + /** * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number * @hw: pointer to the HW struct @@ -2179,6 +2204,69 @@ int ice_ptp_read_tx_hwtstamp_status_eth56g(struct ice_hw *hw, u32 *ts_status) return 0; } +/** + * ice_ptp_phy_soft_reset_eth56g - Perform a PHY soft reset on ETH56G + * @hw: pointer to the HW structure + * @port: PHY port number + * + * Trigger a soft reset of the ETH56G PHY by toggling the soft reset + * bit in the PHY global register. The reset sequence consists of: + * 1. Clearing the soft reset bit + * 2. Asserting the soft reset bit + * 3. Clearing the soft reset bit again + * + * Short delays are inserted between each step to allow the hardware + * to settle. This provides a controlled way to reinitialize the PHY + * without requiring a full device reset. + * + * Return: 0 on success, or a negative error code on failure when + * reading or writing the PHY register. + */ +int ice_ptp_phy_soft_reset_eth56g(struct ice_hw *hw, u8 port) +{ + u32 global_val; + int err; + + err = ice_read_ptp_reg_eth56g(hw, port, PHY_REG_GLOBAL, &global_val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_REG_GLOBAL for port %d, err %d\n", + port, err); + return err; + } + + global_val &= ~PHY_REG_GLOBAL_SOFT_RESET_M; + ice_debug(hw, ICE_DBG_PTP, "Clearing soft reset bit for port %d, val: 0x%x\n", + port, global_val); + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_GLOBAL, global_val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_REG_GLOBAL for port %d, err %d\n", + port, err); + return err; + } + + usleep_range(5000, 6000); + + global_val |= PHY_REG_GLOBAL_SOFT_RESET_M; + ice_debug(hw, ICE_DBG_PTP, "Set soft reset bit for port %d, val: 0x%x\n", + port, global_val); + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_GLOBAL, global_val); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_REG_GLOBAL for port %d, err %d\n", + port, err); + return err; + } + usleep_range(5000, 6000); + + global_val &= ~PHY_REG_GLOBAL_SOFT_RESET_M; + ice_debug(hw, ICE_DBG_PTP, "Clear soft reset bit for port %d, val: 0x%x\n", + port, global_val); + err = ice_write_ptp_reg_eth56g(hw, port, PHY_REG_GLOBAL, global_val); + if (err) + ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_REG_GLOBAL for port %d, err %d\n", + port, err); + return err; +} + /** * ice_get_phy_tx_tstamp_ready_eth56g - Read the Tx memory status register * @hw: pointer to the HW struct @@ -5592,7 +5680,7 @@ int ice_ptp_init_phc(struct ice_hw *hw) case ICE_MAC_GENERIC: return ice_ptp_init_phc_e82x(hw); case ICE_MAC_GENERIC_3K_E825: - return 0; + return ice_ptp_init_phc_e825c(hw); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 5896b346e5790..9d7acc7eb2ceb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -374,6 +374,7 @@ int ice_stop_phy_timer_eth56g(struct ice_hw *hw, u8 port, bool soft_reset); int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port); int ice_phy_cfg_intr_eth56g(struct ice_hw *hw, u8 port, bool ena, u8 threshold); int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); +int ice_ptp_phy_soft_reset_eth56g(struct ice_hw *hw, u8 port); #define ICE_ETH56G_NOMINAL_INCVAL 0x140000000ULL #define ICE_ETH56G_NOMINAL_PCS_REF_TUS 0x100000000ULL @@ -676,6 +677,9 @@ static inline u64 ice_get_base_incval(struct ice_hw *hw) #define ICE_P0_GNSS_PRSNT_N BIT(4) /* ETH56G PHY register addresses */ +#define PHY_REG_GLOBAL 0x0 +#define PHY_REG_GLOBAL_SOFT_RESET_M BIT(11) + /* Timestamp PHY incval registers */ #define PHY_REG_TIMETUS_L 0x8 #define PHY_REG_TIMETUS_U 0xC From 9fb0d0528177ac7376dd1d4d78aaf3613c934fbf Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 20 Apr 2026 17:51:27 -0700 Subject: [PATCH 0864/1518] ice: fix ready bitmap check for non-E822 devices [ Upstream commit 359dc1d41358c88955eeff1b75aee55da7a415d3 ] The E800 hardware (apart from E810) has a ready bitmap for the PHY indicating which timestamp slots currently have an outstanding timestamp waiting to be read by software. This bitmap is checked in multiple places using the ice_get_phy_tx_tstamp_ready(): * ice_ptp_process_tx_tstamp() calls it to determine which timestamps to attempt reading from the PHY * ice_ptp_tx_tstamps_pending() calls it in a loop at the end of the miscellaneous IRQ to check if new timestamps came in while the interrupt handler was executing. * ice_ptp_maybe_trigger_tx_interrupt() calls it in the auxiliary work task to trigger a software interrupt in the event that the hardware logic gets stuck. For E82X devices, multiple PHYs share the same block, and the parameter passed to the ready bitmap is a block number associated with the given port. For E825-C devices, the PHYs have their own independent blocks and do not share, so the parameter passed needs to be the port number. For E810 devices, the ice_get_phy_tx_tstamp_ready() always returns all 1s regardless of what port, since this hardware does not have a ready bitmap. Finally, for E830 devices, each PF has its own ready bitmap accessible via register, and the block parameter is unused. The first call correctly uses the Tx timestamp tracker block parameter to check the appropriate timestamp block. This works because the tracker is setup correctly for each timestamp device type. The second two callers behave incorrectly for all device types other than the older E822 devices. They both iterate in a loop using ICE_GET_QUAD_NUM() which is a macro only used by E822 devices. This logic is incorrect for devices other than the E822 devices. For E810 the calls would always return true, causing E810 devices to always attempt to trigger a software interrupt even when they have no reason to. For E830, this results in duplicate work as the ready bitmap is checked once per number of quads. Finally, for E825-C, this results in the pending checks failing to detect timestamps on ports other than the first two. Fix this by introducing a new hardware API function to ice_ptp_hw.c, ice_check_phy_tx_tstamp_ready(). This function will check if any timestamps are available and returns a positive value if any timestamps are pending. For E810, the function always returns false, so that the re-trigger checks never happen. For E830, check the ready bitmap just once. For E82x hardware, check each quad. Finally, for E825-C, check every port. The interface function returns an integer to enable reporting of error code if the driver is unable read the ready bitmap. This enables callers to handle this case properly. The previous implementation assumed that timestamps are available if they failed to read the bitmap. This is problematic as it could lead to continuous software IRQ triggering if the PHY timestamp registers somehow become inaccessible. This change is especially important for E825-C devices, as the missing checks could leave a window open where a new timestamp could arrive while the existing timestamps aren't completed. As a result, the hardware threshold logic would not trigger a new interrupt. Without the check, the timestamp is left unhandled, and new timestamps will not cause an interrupt again until the timestamp is handled. Since both the interrupt check and the backup check in the auxiliary task do not function properly, the device may have Tx timestamps permanently stuck failing on a given port. The faulty checks originate from commit d938a8cca88a ("ice: Auxbus devices & driver for E822 TS") and commit 712e876371f8 ("ice: periodically kick Tx timestamp interrupt"), however at the time of the original coding, both functions only operated on E822 hardware. This is no longer the case, and hasn't been since the introduction of the ETH56G PHY model in commit 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Fixes: 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Reviewed-by: Aleksandr Loktionov Reviewed-by: Petr Oros Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260420-jk-iwl-net-2026-04-20-ptp-e825c-phy-interrupt-fixes-v1-3-bc2240f42251@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp.c | 44 +++----- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 117 ++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 1 + 3 files changed, 136 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 02517772fb5f4..86eb3d0315a27 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2669,7 +2669,7 @@ static bool ice_any_port_has_timestamps(struct ice_pf *pf) bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - unsigned int i; + int ret; /* Check software indicator */ switch (pf->ptp.tx_interrupt_mode) { @@ -2690,16 +2690,19 @@ bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) } /* Check hardware indicator */ - for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) { - u64 tstamp_ready = 0; - int err; - - err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); - if (err || tstamp_ready) - return true; + ret = ice_check_phy_tx_tstamp_ready(hw); + if (ret < 0) { + dev_dbg(ice_pf_to_dev(pf), "Unable to read PHY Tx timestamp ready bitmap, err %d\n", + ret); + /* Stop triggering IRQs if we're unable to read PHY */ + return false; } - return false; + /* ice_check_phy_tx_tstamp_ready() returns 1 if there are timestamps + * available, 0 if there are no waiting timestamps, and a negative + * value if there was an error (which we checked for above). + */ + return ret > 0; } /** @@ -2783,8 +2786,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - bool trigger_oicr = false; - unsigned int i; + int ret; if (!pf->ptp.port.tx.has_ready_bitmap) return; @@ -2792,21 +2794,11 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) if (!ice_pf_src_tmr_owned(pf)) return; - for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) { - u64 tstamp_ready; - int err; - - err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); - if (!err && tstamp_ready) { - trigger_oicr = true; - break; - } - } - - if (trigger_oicr) { - /* Trigger a software interrupt, to ensure this data - * gets processed. - */ + ret = ice_check_phy_tx_tstamp_ready(hw); + if (ret < 0) { + dev_dbg(dev, "PTP periodic task unable to read PHY timestamp ready bitmap, err %d\n", + ret); + } else if (ret) { dev_dbg(dev, "PTP periodic task detected waiting timestamps. Triggering Tx timestamp interrupt now.\n"); wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 1ae795405ac3c..22d6df06b0bc7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -2168,6 +2168,35 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) return 0; } +/** + * ice_check_phy_tx_tstamp_ready_eth56g - Check Tx memory status for all ports + * @hw: pointer to the HW struct + * + * Check the PHY_REG_TX_MEMORY_STATUS for all ports. A set bit indicates + * a waiting timestamp. + * + * Return: 1 if any port has at least one timestamp ready bit set, + * 0 otherwise, and a negative error code if unable to read the bitmap. + */ +static int ice_check_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw) +{ + int port; + + for (port = 0; port < hw->ptp.num_lports; port++) { + u64 tstamp_ready; + int err; + + err = ice_get_phy_tx_tstamp_ready(hw, port, &tstamp_ready); + if (err) + return err; + + if (tstamp_ready) + return 1; + } + + return 0; +} + /** * ice_ptp_read_tx_hwtstamp_status_eth56g - Get TX timestamp status * @hw: pointer to the HW struct @@ -4318,6 +4347,35 @@ ice_get_phy_tx_tstamp_ready_e82x(struct ice_hw *hw, u8 quad, u64 *tstamp_ready) return 0; } +/** + * ice_check_phy_tx_tstamp_ready_e82x - Check Tx memory status for all quads + * @hw: pointer to the HW struct + * + * Check the Q_REG_TX_MEMORY_STATUS for all quads. A set bit indicates + * a waiting timestamp. + * + * Return: 1 if any quad has at least one timestamp ready bit set, + * 0 otherwise, and a negative error value if unable to read the bitmap. + */ +static int ice_check_phy_tx_tstamp_ready_e82x(struct ice_hw *hw) +{ + int quad; + + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); quad++) { + u64 tstamp_ready; + int err; + + err = ice_get_phy_tx_tstamp_ready(hw, quad, &tstamp_ready); + if (err) + return err; + + if (tstamp_ready) + return 1; + } + + return 0; +} + /** * ice_phy_cfg_intr_e82x - Configure TX timestamp interrupt * @hw: pointer to the HW struct @@ -4871,6 +4929,23 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) return 0; } +/** + * ice_check_phy_tx_tstamp_ready_e810 - Check Tx memory status register + * @hw: pointer to the HW struct + * + * The E810 devices do not have a Tx memory status register. Note this is + * intentionally different behavior from ice_get_phy_tx_tstamp_ready_e810 + * which always says that all bits are ready. This function is called in cases + * where code will trigger interrupts if timestamps are waiting, and should + * not be called for E810 hardware. + * + * Return: 0. + */ +static int ice_check_phy_tx_tstamp_ready_e810(struct ice_hw *hw) +{ + return 0; +} + /* E810 SMA functions * * The following functions operate specifically on E810 hardware and are used @@ -5125,6 +5200,21 @@ static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port, *tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L); } +/** + * ice_check_phy_tx_tstamp_ready_e830 - Check Tx memory status register + * @hw: pointer to the HW struct + * + * Return: 1 if the device has waiting timestamps, 0 otherwise. + */ +static int ice_check_phy_tx_tstamp_ready_e830(struct ice_hw *hw) +{ + u64 tstamp_ready; + + ice_get_phy_tx_tstamp_ready_e830(hw, 0, &tstamp_ready); + + return !!tstamp_ready; +} + /** * ice_ptp_init_phy_e830 - initialize PHY parameters * @ptp: pointer to the PTP HW struct @@ -5717,6 +5807,33 @@ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) } } +/** + * ice_check_phy_tx_tstamp_ready - Check PHY Tx timestamp memory status + * @hw: pointer to the HW struct + * + * Check the PHY for Tx timestamp memory status on all ports. If you need to + * see individual timestamp status for each index, use + * ice_get_phy_tx_tstamp_ready() instead. + * + * Return: 1 if any port has timestamps available, 0 if there are no timestamps + * available, and a negative error code on failure. + */ +int ice_check_phy_tx_tstamp_ready(struct ice_hw *hw) +{ + switch (hw->mac_type) { + case ICE_MAC_E810: + return ice_check_phy_tx_tstamp_ready_e810(hw); + case ICE_MAC_E830: + return ice_check_phy_tx_tstamp_ready_e830(hw); + case ICE_MAC_GENERIC: + return ice_check_phy_tx_tstamp_ready_e82x(hw); + case ICE_MAC_GENERIC_3K_E825: + return ice_check_phy_tx_tstamp_ready_eth56g(hw); + default: + return -EOPNOTSUPP; + } +} + /** * ice_cgu_get_pin_desc_e823 - get pin description array * @hw: pointer to the hw struct diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 9d7acc7eb2ceb..1b58b054f4a5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -300,6 +300,7 @@ void ice_ptp_reset_ts_memory(struct ice_hw *hw); int ice_ptp_init_phc(struct ice_hw *hw); void ice_ptp_init_hw(struct ice_hw *hw); int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready); +int ice_check_phy_tx_tstamp_ready(struct ice_hw *hw); int ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, enum ice_ptp_tmr_cmd configured_cmd); From 7846f1e20f9a221911e5a434bd59981baca21db6 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 20 Apr 2026 17:51:28 -0700 Subject: [PATCH 0865/1518] ice: fix ice_ptp_read_tx_hwtstamp_status_eth56g [ Upstream commit 1f75dbc53f68f0fb2acd99f92315e426a3d0b446 ] The ice_ptp_read_tx_hwtstamp_status_eth56g function calls ice_read_phy_eth56g with a PHY index. However the function actually expects a port index. This causes the function to read the wrong PHY_PTP_INT_STATUS registers, and effectively makes the status wrong for the second set of ports from 4 to 7. The ice_read_phy_eth56g function uses the provided port index to determine which PHY device to read. We could refactor the entire chain to take a PHY index, but this would impact many code sites. Instead, multiply the PHY index by the number of ports, so that we read from the first port of each PHY. Fixes: 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Reviewed-by: Aleksandr Loktionov Reviewed-by: Petr Oros Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260420-jk-iwl-net-2026-04-20-ptp-e825c-phy-interrupt-fixes-v1-4-bc2240f42251@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 22d6df06b0bc7..d461e00d15e9e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -2219,13 +2219,19 @@ int ice_ptp_read_tx_hwtstamp_status_eth56g(struct ice_hw *hw, u32 *ts_status) *ts_status = 0; for (phy = 0; phy < params->num_phys; phy++) { + u8 port; int err; - err = ice_read_phy_eth56g(hw, phy, PHY_PTP_INT_STATUS, &status); + /* ice_read_phy_eth56g expects a port index, so use the first + * port of the PHY + */ + port = phy * hw->ptp.ports_per_phy; + + err = ice_read_phy_eth56g(hw, port, PHY_PTP_INT_STATUS, &status); if (err) return err; - *ts_status |= (status & mask) << (phy * hw->ptp.ports_per_phy); + *ts_status |= (status & mask) << port; } ice_debug(hw, ICE_DBG_PTP, "PHY interrupt err: %x\n", *ts_status); From 48de5f5f0f7b92fecb4a03b8223584f4b8174234 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Apr 2026 14:33:49 +0000 Subject: [PATCH 0866/1518] net_sched: sch_hhf: annotate data-races in hhf_dump_stats() [ Upstream commit a6edf2cd4156b71e07258876b7626692e158f7e8 ] hhf_dump_stats() only runs with RTNL held, reading fields that can be changed in qdisc fast path. Add READ_ONCE()/WRITE_ONCE() annotations. Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260421143349.4052215-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_hhf.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 2d4855e28a286..81c3a388c9437 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -198,7 +198,8 @@ static struct hh_flow_state *seek_list(const u32 hash, return NULL; list_del(&flow->flowchain); kfree(flow); - q->hh_flows_current_cnt--; + WRITE_ONCE(q->hh_flows_current_cnt, + q->hh_flows_current_cnt - 1); } else if (flow->hash_id == hash) { return flow; } @@ -226,7 +227,7 @@ static struct hh_flow_state *alloc_new_hh(struct list_head *head, } if (q->hh_flows_current_cnt >= q->hh_flows_limit) { - q->hh_flows_overlimit++; + WRITE_ONCE(q->hh_flows_overlimit, q->hh_flows_overlimit + 1); return NULL; } /* Create new entry. */ @@ -234,7 +235,7 @@ static struct hh_flow_state *alloc_new_hh(struct list_head *head, if (!flow) return NULL; - q->hh_flows_current_cnt++; + WRITE_ONCE(q->hh_flows_current_cnt, q->hh_flows_current_cnt + 1); INIT_LIST_HEAD(&flow->flowchain); list_add_tail(&flow->flowchain, head); @@ -309,7 +310,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) return WDRR_BUCKET_FOR_NON_HH; flow->hash_id = hash; flow->hit_timestamp = now; - q->hh_flows_total_cnt++; + WRITE_ONCE(q->hh_flows_total_cnt, q->hh_flows_total_cnt + 1); /* By returning without updating counters in q->hhf_arrays, * we implicitly implement "shielding" (see Optimization O1). @@ -403,7 +404,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_SUCCESS; prev_backlog = sch->qstats.backlog; - q->drop_overlimit++; + WRITE_ONCE(q->drop_overlimit, q->drop_overlimit + 1); /* Return Congestion Notification only if we dropped a packet from this * bucket. */ @@ -687,10 +688,10 @@ static int hhf_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct hhf_sched_data *q = qdisc_priv(sch); struct tc_hhf_xstats st = { - .drop_overlimit = q->drop_overlimit, - .hh_overlimit = q->hh_flows_overlimit, - .hh_tot_count = q->hh_flows_total_cnt, - .hh_cur_count = q->hh_flows_current_cnt, + .drop_overlimit = READ_ONCE(q->drop_overlimit), + .hh_overlimit = READ_ONCE(q->hh_flows_overlimit), + .hh_tot_count = READ_ONCE(q->hh_flows_total_cnt), + .hh_cur_count = READ_ONCE(q->hh_flows_current_cnt), }; return gnet_stats_copy_app(d, &st, sizeof(st)); From 796fb2037d854e8fdf4f8d00ad01193762c6c346 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Apr 2026 14:29:44 +0000 Subject: [PATCH 0867/1518] net/sched: sch_pie: annotate data-races in pie_dump_stats() [ Upstream commit 5154561d9b119f781249f8e845fecf059b38b483 ] pie_dump_stats() only runs with RTNL held, reading fields that can be changed in qdisc fast path. Add READ_ONCE()/WRITE_ONCE() annotations. Alternative would be to acquire the qdisc spinlock, but our long-term goal is to make qdisc dump operations lockless as much as we can. tc_pie_xstats fields don't need to be latched atomically, otherwise this bug would have been caught earlier. Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260421142944.4009941-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/pie.h | 2 +- net/sched/sch_pie.c | 38 +++++++++++++++++++------------------- 2 files changed, 20 insertions(+), 20 deletions(-) diff --git a/include/net/pie.h b/include/net/pie.h index 01cbc66825a40..1f3db0c355149 100644 --- a/include/net/pie.h +++ b/include/net/pie.h @@ -104,7 +104,7 @@ static inline void pie_vars_init(struct pie_vars *vars) vars->dq_tstamp = DTIME_INVALID; vars->accu_prob = 0; vars->dq_count = DQCOUNT_INVALID; - vars->avg_dq_rate = 0; + WRITE_ONCE(vars->avg_dq_rate, 0); } static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 0a377313b6a9d..73650200482f4 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -90,7 +90,7 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, bool enqueue = false; if (unlikely(qdisc_qlen(sch) >= sch->limit)) { - q->stats.overlimit++; + WRITE_ONCE(q->stats.overlimit, q->stats.overlimit + 1); goto out; } @@ -104,7 +104,7 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If packet is ecn capable, mark it if drop probability * is lower than 10%, else drop it. */ - q->stats.ecn_mark++; + WRITE_ONCE(q->stats.ecn_mark, q->stats.ecn_mark + 1); enqueue = true; } @@ -114,15 +114,15 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (!q->params.dq_rate_estimator) pie_set_enqueue_time(skb); - q->stats.packets_in++; + WRITE_ONCE(q->stats.packets_in, q->stats.packets_in + 1); if (qdisc_qlen(sch) > q->stats.maxq) - q->stats.maxq = qdisc_qlen(sch); + WRITE_ONCE(q->stats.maxq, qdisc_qlen(sch)); return qdisc_enqueue_tail(skb, sch); } out: - q->stats.dropped++; + WRITE_ONCE(q->stats.dropped, q->stats.dropped + 1); q->vars.accu_prob = 0; return qdisc_drop_reason(skb, sch, to_free, reason); } @@ -267,11 +267,11 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, count = count / dtime; if (vars->avg_dq_rate == 0) - vars->avg_dq_rate = count; + WRITE_ONCE(vars->avg_dq_rate, count); else - vars->avg_dq_rate = + WRITE_ONCE(vars->avg_dq_rate, (vars->avg_dq_rate - - (vars->avg_dq_rate >> 3)) + (count >> 3); + (vars->avg_dq_rate >> 3)) + (count >> 3)); /* If the queue has receded below the threshold, we hold * on to the last drain rate calculated, else we reset @@ -381,7 +381,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, if (delta > 0) { /* prevent overflow */ if (vars->prob < oldprob) { - vars->prob = MAX_PROB; + WRITE_ONCE(vars->prob, MAX_PROB); /* Prevent normalization error. If probability is at * maximum value already, we normalize it here, and * skip the check to do a non-linear drop in the next @@ -392,7 +392,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, } else { /* prevent underflow */ if (vars->prob > oldprob) - vars->prob = 0; + WRITE_ONCE(vars->prob, 0); } /* Non-linear drop in probability: Reduce drop probability quickly if @@ -403,7 +403,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, /* Reduce drop probability to 98.4% */ vars->prob -= vars->prob / 64; - vars->qdelay = qdelay; + WRITE_ONCE(vars->qdelay, qdelay); vars->backlog_old = backlog; /* We restart the measurement cycle if the following conditions are met @@ -502,21 +502,21 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { .prob = q->vars.prob << BITS_PER_BYTE, - .delay = ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) / + .delay = ((u32)PSCHED_TICKS2NS(READ_ONCE(q->vars.qdelay))) / NSEC_PER_USEC, - .packets_in = q->stats.packets_in, - .overlimit = q->stats.overlimit, - .maxq = q->stats.maxq, - .dropped = q->stats.dropped, - .ecn_mark = q->stats.ecn_mark, + .packets_in = READ_ONCE(q->stats.packets_in), + .overlimit = READ_ONCE(q->stats.overlimit), + .maxq = READ_ONCE(q->stats.maxq), + .dropped = READ_ONCE(q->stats.dropped), + .ecn_mark = READ_ONCE(q->stats.ecn_mark), }; /* avg_dq_rate is only valid if dq_rate_estimator is enabled */ st.dq_rate_estimating = q->params.dq_rate_estimator; /* unscale and return dq_rate in bytes per sec */ - if (q->params.dq_rate_estimator) - st.avg_dq_rate = q->vars.avg_dq_rate * + if (st.dq_rate_estimating) + st.avg_dq_rate = READ_ONCE(q->vars.avg_dq_rate) * (PSCHED_TICKS_PER_SEC) >> PIE_SCALE; return gnet_stats_copy_app(d, &st, sizeof(st)); From 1dbe52b6a0aff9555297971cc6ecf169695f7e34 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Apr 2026 14:25:09 +0000 Subject: [PATCH 0868/1518] net/sched: sch_fq_codel: remove data-races from fq_codel_dump_stats() [ Upstream commit bbfaa73ea6871db03dc05d7f05f00557a8981f25 ] fq_codel_dump_stats() acquires the qdisc spinlock a bit too late. Move this acquisition before we fill st.qdisc_stats with live data. Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260421142509.3967231-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_fq_codel.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index a141423929394..90e1dfac6f594 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -584,6 +584,8 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) }; struct list_head *pos; + sch_tree_lock(sch); + st.qdisc_stats.maxpacket = q->cstats.maxpacket; st.qdisc_stats.drop_overlimit = q->drop_overlimit; st.qdisc_stats.ecn_mark = q->cstats.ecn_mark; @@ -592,7 +594,6 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.qdisc_stats.memory_usage = q->memory_usage; st.qdisc_stats.drop_overmemory = q->drop_overmemory; - sch_tree_lock(sch); list_for_each(pos, &q->new_flows) st.qdisc_stats.new_flows_len++; From 910213de955e40c5b9e2680f6e0eb6614caa3c59 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Apr 2026 14:23:09 +0000 Subject: [PATCH 0869/1518] net/sched: sch_red: annotate data-races in red_dump_stats() [ Upstream commit a8f5192809caf636d05ba47c144f282cfd0e3839 ] red_dump_stats() only runs with RTNL held, reading fields that can be changed in qdisc fast path. Add READ_ONCE()/WRITE_ONCE() annotations. Alternative would be to acquire the qdisc spinlock, but our long-term goal is to make qdisc dump operations lockless as much as we can. tc_red_xstats fields don't need to be latched atomically, otherwise this bug would have been caught earlier. Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260421142309.3964322-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_red.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 68ee41ce78c50..86651a68d4015 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -90,17 +90,20 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_PROB_MARK: qdisc_qstats_overlimit(sch); if (!red_use_ecn(q)) { - q->stats.prob_drop++; + WRITE_ONCE(q->stats.prob_drop, + q->stats.prob_drop + 1); goto congestion_drop; } if (INET_ECN_set_ce(skb)) { - q->stats.prob_mark++; + WRITE_ONCE(q->stats.prob_mark, + q->stats.prob_mark + 1); skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret); if (!skb) return NET_XMIT_CN | ret; } else if (!red_use_nodrop(q)) { - q->stats.prob_drop++; + WRITE_ONCE(q->stats.prob_drop, + q->stats.prob_drop + 1); goto congestion_drop; } @@ -111,17 +114,20 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, reason = SKB_DROP_REASON_QDISC_OVERLIMIT; qdisc_qstats_overlimit(sch); if (red_use_harddrop(q) || !red_use_ecn(q)) { - q->stats.forced_drop++; + WRITE_ONCE(q->stats.forced_drop, + q->stats.forced_drop + 1); goto congestion_drop; } if (INET_ECN_set_ce(skb)) { - q->stats.forced_mark++; + WRITE_ONCE(q->stats.forced_mark, + q->stats.forced_mark + 1); skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret); if (!skb) return NET_XMIT_CN | ret; } else if (!red_use_nodrop(q)) { - q->stats.forced_drop++; + WRITE_ONCE(q->stats.forced_drop, + q->stats.forced_drop + 1); goto congestion_drop; } @@ -135,7 +141,8 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { - q->stats.pdrop++; + WRITE_ONCE(q->stats.pdrop, + q->stats.pdrop + 1); qdisc_qstats_drop(sch); } return ret; @@ -463,9 +470,13 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &hw_stats_request); } - st.early = q->stats.prob_drop + q->stats.forced_drop; - st.pdrop = q->stats.pdrop; - st.marked = q->stats.prob_mark + q->stats.forced_mark; + st.early = READ_ONCE(q->stats.prob_drop) + + READ_ONCE(q->stats.forced_drop); + + st.pdrop = READ_ONCE(q->stats.pdrop); + + st.marked = READ_ONCE(q->stats.prob_mark) + + READ_ONCE(q->stats.forced_mark); return gnet_stats_copy_app(d, &st, sizeof(st)); } From ae68eb4f2fddcc631d6e429678931f3b4e649914 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Apr 2026 14:16:55 +0000 Subject: [PATCH 0870/1518] net/sched: sch_sfb: annotate data-races in sfb_dump_stats() [ Upstream commit 1ada03fdef82d3d7d2edb9dcd3acc91917675e48 ] sfb_dump_stats() only runs with RTNL held, reading fields that can be changed in qdisc fast path. Add READ_ONCE()/WRITE_ONCE() annotations. Alternative would be to acquire the qdisc spinlock, but our long-term goal is to make qdisc dump operations lockless as much as we can. tc_sfb_xstats fields don't need to be latched atomically, otherwise this bug would have been caught earlier. Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260421141655.3953721-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_sfb.c | 54 +++++++++++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 22 deletions(-) diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index d2835f1168e1d..00286c930b8de 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -130,7 +130,7 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) sfbhash >>= SFB_BUCKET_SHIFT; if (b[hash].qlen < 0xFFFF) - b[hash].qlen++; + WRITE_ONCE(b[hash].qlen, b[hash].qlen + 1); b += SFB_NUMBUCKETS; /* next level */ } } @@ -159,7 +159,7 @@ static void decrement_one_qlen(u32 sfbhash, u32 slot, sfbhash >>= SFB_BUCKET_SHIFT; if (b[hash].qlen > 0) - b[hash].qlen--; + WRITE_ONCE(b[hash].qlen, b[hash].qlen - 1); b += SFB_NUMBUCKETS; /* next level */ } } @@ -179,12 +179,12 @@ static void decrement_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) static void decrement_prob(struct sfb_bucket *b, struct sfb_sched_data *q) { - b->p_mark = prob_minus(b->p_mark, q->decrement); + WRITE_ONCE(b->p_mark, prob_minus(b->p_mark, q->decrement)); } static void increment_prob(struct sfb_bucket *b, struct sfb_sched_data *q) { - b->p_mark = prob_plus(b->p_mark, q->increment); + WRITE_ONCE(b->p_mark, prob_plus(b->p_mark, q->increment)); } static void sfb_zero_all_buckets(struct sfb_sched_data *q) @@ -202,11 +202,14 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da const struct sfb_bucket *b = &q->bins[q->slot].bins[0][0]; for (i = 0; i < SFB_LEVELS * SFB_NUMBUCKETS; i++) { - if (qlen < b->qlen) - qlen = b->qlen; - totalpm += b->p_mark; - if (prob < b->p_mark) - prob = b->p_mark; + u32 b_qlen = READ_ONCE(b->qlen); + u32 b_mark = READ_ONCE(b->p_mark); + + if (qlen < b_qlen) + qlen = b_qlen; + totalpm += b_mark; + if (prob < b_mark) + prob = b_mark; b++; } *prob_r = prob; @@ -295,7 +298,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(sch->q.qlen >= q->limit)) { qdisc_qstats_overlimit(sch); - q->stats.queuedrop++; + WRITE_ONCE(q->stats.queuedrop, + q->stats.queuedrop + 1); goto drop; } @@ -348,7 +352,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(minqlen >= q->max)) { qdisc_qstats_overlimit(sch); - q->stats.bucketdrop++; + WRITE_ONCE(q->stats.bucketdrop, + q->stats.bucketdrop + 1); goto drop; } @@ -374,7 +379,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (sfb_rate_limit(skb, q)) { qdisc_qstats_overlimit(sch); - q->stats.penaltydrop++; + WRITE_ONCE(q->stats.penaltydrop, + q->stats.penaltydrop + 1); goto drop; } goto enqueue; @@ -390,14 +396,17 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, * In either case, we want to start dropping packets. */ if (r < (p_min - SFB_MAX_PROB / 2) * 2) { - q->stats.earlydrop++; + WRITE_ONCE(q->stats.earlydrop, + q->stats.earlydrop + 1); goto drop; } } if (INET_ECN_set_ce(skb)) { - q->stats.marked++; + WRITE_ONCE(q->stats.marked, + q->stats.marked + 1); } else { - q->stats.earlydrop++; + WRITE_ONCE(q->stats.earlydrop, + q->stats.earlydrop + 1); goto drop; } } @@ -410,7 +419,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, sch->q.qlen++; increment_qlen(&cb, q); } else if (net_xmit_drop_count(ret)) { - q->stats.childdrop++; + WRITE_ONCE(q->stats.childdrop, + q->stats.childdrop + 1); qdisc_qstats_drop(sch); } return ret; @@ -599,12 +609,12 @@ static int sfb_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct sfb_sched_data *q = qdisc_priv(sch); struct tc_sfb_xstats st = { - .earlydrop = q->stats.earlydrop, - .penaltydrop = q->stats.penaltydrop, - .bucketdrop = q->stats.bucketdrop, - .queuedrop = q->stats.queuedrop, - .childdrop = q->stats.childdrop, - .marked = q->stats.marked, + .earlydrop = READ_ONCE(q->stats.earlydrop), + .penaltydrop = READ_ONCE(q->stats.penaltydrop), + .bucketdrop = READ_ONCE(q->stats.bucketdrop), + .queuedrop = READ_ONCE(q->stats.queuedrop), + .childdrop = READ_ONCE(q->stats.childdrop), + .marked = READ_ONCE(q->stats.marked), }; st.maxqlen = sfb_compute_qlen(&st.maxprob, &st.avgprob, q); From 56b99327a451917f1c17f85fc33ea8293c08a9ee Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:11 +0200 Subject: [PATCH 0871/1518] net: airoha: ppe: Dynamically allocate foe_check_time array in airoha_ppe struct [ Upstream commit 6d5b601d52a27aafff555b480e538507901c672c ] This is a preliminary patch to properly enable PPE support for AN7583 SoC. Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-2-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 3309965fe44c ("net: airoha: Add missing bits in airoha_qdma_cleanup_tx_queue()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.h | 2 +- drivers/net/ethernet/airoha/airoha_ppe.c | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 054fe86d67bd1..9929c44d84702 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -548,7 +548,7 @@ struct airoha_ppe { struct rhashtable l2_flows; struct hlist_head *foe_flow; - u16 foe_check_time[PPE_NUM_ENTRIES]; + u16 *foe_check_time; struct airoha_foe_stats *foe_stats; dma_addr_t foe_stats_dma; diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index e9994c794c703..072cc2dd50dda 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -1538,6 +1538,11 @@ int airoha_ppe_init(struct airoha_eth *eth) return -ENOMEM; } + ppe->foe_check_time = devm_kzalloc(eth->dev, PPE_NUM_ENTRIES, + GFP_KERNEL); + if (!ppe->foe_check_time) + return -ENOMEM; + err = rhashtable_init(ð->flow_table, &airoha_flow_table_params); if (err) return err; From 1a21910e32d788238b7f6d0de71e284df288b4c1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:15 +0200 Subject: [PATCH 0872/1518] net: airoha: ppe: Move PPE memory info in airoha_eth_soc_data struct [ Upstream commit 5bd1d1fd48ea9f8300b211540d946899c7f96480 ] AN7583 SoC runs a single PPE device while EN7581 runs two of them. Moreover PPE SRAM in AN7583 SoC is reduced to 8K (while SRAM is 16K on EN7581). Take into account PPE memory layout during PPE configuration. Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-6-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 3309965fe44c ("net: airoha: Add missing bits in airoha_qdma_cleanup_tx_queue()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.h | 10 +- drivers/net/ethernet/airoha/airoha_ppe.c | 133 +++++++++--------- .../net/ethernet/airoha/airoha_ppe_debugfs.c | 3 +- 3 files changed, 70 insertions(+), 76 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 9929c44d84702..8d121d12dc120 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -47,14 +47,9 @@ #define QDMA_METER_IDX(_n) ((_n) & 0xff) #define QDMA_METER_GROUP(_n) (((_n) >> 8) & 0x3) -#define PPE_NUM 2 -#define PPE1_SRAM_NUM_ENTRIES (8 * 1024) -#define PPE_SRAM_NUM_ENTRIES (PPE_NUM * PPE1_SRAM_NUM_ENTRIES) -#define PPE1_STATS_NUM_ENTRIES (4 * 1024) -#define PPE_STATS_NUM_ENTRIES (PPE_NUM * PPE1_STATS_NUM_ENTRIES) +#define PPE_SRAM_NUM_ENTRIES (8 * 1024) +#define PPE_STATS_NUM_ENTRIES (4 * 1024) #define PPE_DRAM_NUM_ENTRIES (16 * 1024) -#define PPE_NUM_ENTRIES (PPE_SRAM_NUM_ENTRIES + PPE_DRAM_NUM_ENTRIES) -#define PPE_HASH_MASK (PPE_NUM_ENTRIES - 1) #define PPE_ENTRY_SIZE 80 #define PPE_RAM_NUM_ENTRIES_SHIFT(_n) (__ffs((_n) >> 10)) @@ -635,6 +630,7 @@ int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data); int airoha_ppe_init(struct airoha_eth *eth); void airoha_ppe_deinit(struct airoha_eth *eth); void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port); +u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe); struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe, u32 hash); void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash, diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 072cc2dd50dda..239c43248b4f4 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -37,19 +37,36 @@ static int airoha_ppe_get_num_stats_entries(struct airoha_ppe *ppe) if (!IS_ENABLED(CONFIG_NET_AIROHA_FLOW_STATS)) return -EOPNOTSUPP; - return PPE1_STATS_NUM_ENTRIES; + return PPE_STATS_NUM_ENTRIES; } static int airoha_ppe_get_total_num_stats_entries(struct airoha_ppe *ppe) { int num_stats = airoha_ppe_get_num_stats_entries(ppe); - if (num_stats > 0) - num_stats = num_stats * PPE_NUM; + if (num_stats > 0) { + struct airoha_eth *eth = ppe->eth; + + num_stats = num_stats * eth->soc->num_ppe; + } return num_stats; } +static u32 airoha_ppe_get_total_sram_num_entries(struct airoha_ppe *ppe) +{ + struct airoha_eth *eth = ppe->eth; + + return PPE_SRAM_NUM_ENTRIES * eth->soc->num_ppe; +} + +u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe) +{ + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); + + return sram_num_entries + PPE_DRAM_NUM_ENTRIES; +} + bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index) { if (index >= eth->soc->num_ppe) @@ -67,14 +84,22 @@ static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe) static void airoha_ppe_hw_init(struct airoha_ppe *ppe) { - u32 sram_tb_size, sram_num_entries, dram_num_entries; + u32 sram_ppe_num_data_entries = PPE_SRAM_NUM_ENTRIES, sram_num_entries; + u32 sram_tb_size, dram_num_entries; struct airoha_eth *eth = ppe->eth; int i, sram_num_stats_entries; - sram_tb_size = PPE_SRAM_NUM_ENTRIES * sizeof(struct airoha_foe_entry); + sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); + sram_tb_size = sram_num_entries * sizeof(struct airoha_foe_entry); dram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(PPE_DRAM_NUM_ENTRIES); - for (i = 0; i < PPE_NUM; i++) { + sram_num_stats_entries = airoha_ppe_get_num_stats_entries(ppe); + if (sram_num_stats_entries > 0) + sram_ppe_num_data_entries -= sram_num_stats_entries; + sram_ppe_num_data_entries = + PPE_RAM_NUM_ENTRIES_SHIFT(sram_ppe_num_data_entries); + + for (i = 0; i < eth->soc->num_ppe; i++) { int p; airoha_fe_wr(eth, REG_PPE_TB_BASE(i), @@ -106,10 +131,16 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) airoha_fe_rmw(eth, REG_PPE_TB_CFG(i), PPE_TB_CFG_SEARCH_MISS_MASK | + PPE_SRAM_TB_NUM_ENTRY_MASK | + PPE_DRAM_TB_NUM_ENTRY_MASK | PPE_TB_CFG_KEEPALIVE_MASK | PPE_TB_ENTRY_SIZE_MASK, FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) | - FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0)); + FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0) | + FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, + sram_ppe_num_data_entries) | + FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, + dram_num_entries)); airoha_fe_rmw(eth, REG_PPE_BIND_RATE(i), PPE_BIND_RATE_L2B_BIND_MASK | @@ -130,45 +161,6 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) FIELD_PREP(FP1_EGRESS_MTU_MASK, AIROHA_MAX_MTU)); } - - if (airoha_ppe_is_enabled(eth, 1)) { - sram_num_entries = PPE1_SRAM_NUM_ENTRIES; - sram_num_stats_entries = - airoha_ppe_get_num_stats_entries(ppe); - if (sram_num_stats_entries > 0) - sram_num_entries -= sram_num_stats_entries; - sram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(sram_num_entries); - - airoha_fe_rmw(eth, REG_PPE_TB_CFG(0), - PPE_SRAM_TB_NUM_ENTRY_MASK | - PPE_DRAM_TB_NUM_ENTRY_MASK, - FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, - sram_num_entries) | - FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, - dram_num_entries)); - airoha_fe_rmw(eth, REG_PPE_TB_CFG(1), - PPE_SRAM_TB_NUM_ENTRY_MASK | - PPE_DRAM_TB_NUM_ENTRY_MASK, - FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, - sram_num_entries) | - FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, - dram_num_entries)); - } else { - sram_num_entries = PPE_SRAM_NUM_ENTRIES; - sram_num_stats_entries = - airoha_ppe_get_total_num_stats_entries(ppe); - if (sram_num_stats_entries > 0) - sram_num_entries -= sram_num_stats_entries; - sram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(sram_num_entries); - - airoha_fe_rmw(eth, REG_PPE_TB_CFG(0), - PPE_SRAM_TB_NUM_ENTRY_MASK | - PPE_DRAM_TB_NUM_ENTRY_MASK, - FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, - sram_num_entries) | - FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, - dram_num_entries)); - } } static void airoha_ppe_flow_mangle_eth(const struct flow_action_entry *act, void *eth) @@ -469,9 +461,11 @@ static int airoha_ppe_foe_entry_set_ipv6_tuple(struct airoha_foe_entry *hwe, return 0; } -static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe) +static u32 airoha_ppe_foe_get_entry_hash(struct airoha_ppe *ppe, + struct airoha_foe_entry *hwe) { int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1); + u32 ppe_hash_mask = airoha_ppe_get_total_num_entries(ppe) - 1; u32 hash, hv1, hv2, hv3; switch (type) { @@ -509,14 +503,14 @@ static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe) case PPE_PKT_TYPE_IPV6_6RD: default: WARN_ON_ONCE(1); - return PPE_HASH_MASK; + return ppe_hash_mask; } hash = (hv1 & hv2) | ((~hv1) & hv3); hash = (hash >> 24) | ((hash & 0xffffff) << 8); hash ^= hv1 ^ hv2 ^ hv3; hash ^= hash >> 16; - hash &= PPE_NUM_ENTRIES - 1; + hash &= ppe_hash_mask; return hash; } @@ -617,9 +611,11 @@ static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe, static struct airoha_foe_entry * airoha_ppe_foe_get_entry_locked(struct airoha_ppe *ppe, u32 hash) { + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); + lockdep_assert_held(&ppe_lock); - if (hash < PPE_SRAM_NUM_ENTRIES) { + if (hash < sram_num_entries) { u32 *hwe = ppe->foe + hash * sizeof(struct airoha_foe_entry); struct airoha_eth *eth = ppe->eth; bool ppe2; @@ -627,7 +623,7 @@ airoha_ppe_foe_get_entry_locked(struct airoha_ppe *ppe, u32 hash) int i; ppe2 = airoha_ppe_is_enabled(ppe->eth, 1) && - hash >= PPE1_SRAM_NUM_ENTRIES; + hash >= PPE_SRAM_NUM_ENTRIES; airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2), FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) | PPE_SRAM_CTRL_REQ_MASK); @@ -678,6 +674,7 @@ static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe, struct airoha_foe_entry *e, u32 hash, bool rx_wlan) { + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe); u32 ts = airoha_ppe_get_timestamp(ppe); struct airoha_eth *eth = ppe->eth; @@ -702,10 +699,10 @@ static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe, if (!rx_wlan) airoha_ppe_foe_flow_stats_update(ppe, npu, hwe, hash); - if (hash < PPE_SRAM_NUM_ENTRIES) { + if (hash < sram_num_entries) { dma_addr_t addr = ppe->foe_dma + hash * sizeof(*hwe); bool ppe2 = airoha_ppe_is_enabled(eth, 1) && - hash >= PPE1_SRAM_NUM_ENTRIES; + hash >= PPE_SRAM_NUM_ENTRIES; err = npu->ops.ppe_foe_commit_entry(npu, addr, sizeof(*hwe), hash, ppe2); @@ -832,7 +829,7 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, if (state == AIROHA_FOE_STATE_BIND) goto unlock; - index = airoha_ppe_foe_get_entry_hash(hwe); + index = airoha_ppe_foe_get_entry_hash(ppe, hwe); hlist_for_each_entry_safe(e, n, &ppe->foe_flow[index], list) { if (e->type == FLOW_TYPE_L2_SUBFLOW) { state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1); @@ -892,7 +889,7 @@ static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe, if (type == PPE_PKT_TYPE_BRIDGE) return airoha_ppe_foe_l2_flow_commit_entry(ppe, e); - hash = airoha_ppe_foe_get_entry_hash(&e->data); + hash = airoha_ppe_foe_get_entry_hash(ppe, &e->data); e->type = FLOW_TYPE_L4; e->hash = 0xffff; @@ -1296,17 +1293,15 @@ static int airoha_ppe_flow_offload_cmd(struct airoha_eth *eth, static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe, struct airoha_npu *npu) { - int i, sram_num_entries = PPE_SRAM_NUM_ENTRIES; + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); struct airoha_foe_entry *hwe = ppe->foe; + int i; - if (airoha_ppe_is_enabled(ppe->eth, 1)) - sram_num_entries = sram_num_entries / 2; - - for (i = 0; i < sram_num_entries; i++) + for (i = 0; i < PPE_SRAM_NUM_ENTRIES; i++) memset(&hwe[i], 0, sizeof(*hwe)); return npu->ops.ppe_flush_sram_entries(npu, ppe->foe_dma, - PPE_SRAM_NUM_ENTRIES); + sram_num_entries); } static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth) @@ -1410,9 +1405,10 @@ void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb, u16 hash, bool rx_wlan) { struct airoha_ppe *ppe = dev->priv; + u32 ppe_hash_mask = airoha_ppe_get_total_num_entries(ppe) - 1; u16 now, diff; - if (hash > PPE_HASH_MASK) + if (hash > ppe_hash_mask) return; now = (u16)jiffies; @@ -1503,6 +1499,7 @@ EXPORT_SYMBOL_GPL(airoha_ppe_put_dev); int airoha_ppe_init(struct airoha_eth *eth) { int foe_size, err, ppe_num_stats_entries; + u32 ppe_num_entries; struct airoha_ppe *ppe; ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL); @@ -1512,18 +1509,18 @@ int airoha_ppe_init(struct airoha_eth *eth) ppe->dev.ops.setup_tc_block_cb = airoha_ppe_setup_tc_block_cb; ppe->dev.ops.check_skb = airoha_ppe_check_skb; ppe->dev.priv = ppe; + ppe->eth = eth; + eth->ppe = ppe; - foe_size = PPE_NUM_ENTRIES * sizeof(struct airoha_foe_entry); + ppe_num_entries = airoha_ppe_get_total_num_entries(ppe); + foe_size = ppe_num_entries * sizeof(struct airoha_foe_entry); ppe->foe = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_dma, GFP_KERNEL); if (!ppe->foe) return -ENOMEM; - ppe->eth = eth; - eth->ppe = ppe; - ppe->foe_flow = devm_kzalloc(eth->dev, - PPE_NUM_ENTRIES * sizeof(*ppe->foe_flow), + ppe_num_entries * sizeof(*ppe->foe_flow), GFP_KERNEL); if (!ppe->foe_flow) return -ENOMEM; @@ -1538,7 +1535,7 @@ int airoha_ppe_init(struct airoha_eth *eth) return -ENOMEM; } - ppe->foe_check_time = devm_kzalloc(eth->dev, PPE_NUM_ENTRIES, + ppe->foe_check_time = devm_kzalloc(eth->dev, ppe_num_entries, GFP_KERNEL); if (!ppe->foe_check_time) return -ENOMEM; diff --git a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c index 05a756233f6a4..0112c41150bb0 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c +++ b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c @@ -53,9 +53,10 @@ static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private, [AIROHA_FOE_STATE_FIN] = "FIN", }; struct airoha_ppe *ppe = m->private; + u32 ppe_num_entries = airoha_ppe_get_total_num_entries(ppe); int i; - for (i = 0; i < PPE_NUM_ENTRIES; i++) { + for (i = 0; i < ppe_num_entries; i++) { const char *state_str, *type_str = "UNKNOWN"; void *src_addr = NULL, *dest_addr = NULL; u16 *src_port = NULL, *dest_port = NULL; From 8d913ab0141974d2d640ba3e8e14821f53800dee Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:20 +0200 Subject: [PATCH 0873/1518] net: airoha: Refactor src port configuration in airhoha_set_gdm2_loopback [ Upstream commit 9d5b5219f672c80bed4d4e15f0068e648cdca43b ] AN7583 chipset relies on different definitions for source-port identifier used for hw offloading. In order to support hw offloading in AN7583 controller, refactor src port configuration in airhoha_set_gdm2_loopback routine and introduce get_src_port_id callback. Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-11-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 3309965fe44c ("net: airoha: Add missing bits in airoha_qdma_cleanup_tx_queue()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 82 ++++++++++++++++------- drivers/net/ethernet/airoha/airoha_eth.h | 18 +++-- drivers/net/ethernet/airoha/airoha_regs.h | 6 +- 3 files changed, 73 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index f8db324b141fe..6e7f816cd7edb 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1751,13 +1751,17 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) return 0; } -static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) +static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) { - u32 pse_port = port->id == 3 ? FE_PSE_PORT_GDM3 : FE_PSE_PORT_GDM4; + u32 val, pse_port, chan = port->id == AIROHA_GDM3_IDX ? 4 : 0; struct airoha_eth *eth = port->qdma->eth; - u32 chan = port->id == 3 ? 4 : 0; + /* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */ + u32 nbq = port->id == AIROHA_GDM3_IDX ? 4 : 0; + int src_port; /* Forward the traffic to the proper GDM port */ + pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 + : FE_PSE_PORT_GDM4; airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port); airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC); @@ -1778,29 +1782,25 @@ static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2)); airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2)); - if (port->id == 3) { - /* FIXME: handle XSI_PCE1_PORT */ - airoha_fe_rmw(eth, REG_FE_WAN_PORT, - WAN1_EN_MASK | WAN1_MASK | WAN0_MASK, - FIELD_PREP(WAN0_MASK, HSGMII_LAN_PCIE0_SRCPORT)); - airoha_fe_rmw(eth, - REG_SP_DFT_CPORT(HSGMII_LAN_PCIE0_SRCPORT >> 3), - SP_CPORT_PCIE0_MASK, - FIELD_PREP(SP_CPORT_PCIE0_MASK, - FE_PSE_PORT_CDM2)); - } else { - /* FIXME: handle XSI_USB_PORT */ + src_port = eth->soc->ops.get_src_port_id(port, nbq); + if (src_port < 0) + return src_port; + + airoha_fe_rmw(eth, REG_FE_WAN_PORT, + WAN1_EN_MASK | WAN1_MASK | WAN0_MASK, + FIELD_PREP(WAN0_MASK, src_port)); + val = src_port & SP_CPORT_DFT_MASK; + airoha_fe_rmw(eth, + REG_SP_DFT_CPORT(src_port >> fls(SP_CPORT_DFT_MASK)), + SP_CPORT_MASK(val), + FE_PSE_PORT_CDM2 << __ffs(SP_CPORT_MASK(val))); + + if (port->id != AIROHA_GDM3_IDX) airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6, FC_ID_OF_SRC_PORT24_MASK, FIELD_PREP(FC_ID_OF_SRC_PORT24_MASK, 2)); - airoha_fe_rmw(eth, REG_FE_WAN_PORT, - WAN1_EN_MASK | WAN1_MASK | WAN0_MASK, - FIELD_PREP(WAN0_MASK, HSGMII_LAN_ETH_SRCPORT)); - airoha_fe_rmw(eth, - REG_SP_DFT_CPORT(HSGMII_LAN_ETH_SRCPORT >> 3), - SP_CPORT_ETH_MASK, - FIELD_PREP(SP_CPORT_ETH_MASK, FE_PSE_PORT_CDM2)); - } + + return 0; } static int airoha_dev_init(struct net_device *dev) @@ -1815,8 +1815,13 @@ static int airoha_dev_init(struct net_device *dev) case 3: case 4: /* If GDM2 is active we can't enable loopback */ - if (!eth->ports[1]) - airhoha_set_gdm2_loopback(port); + if (!eth->ports[1]) { + int err; + + err = airhoha_set_gdm2_loopback(port); + if (err) + return err; + } fallthrough; case 2: if (airoha_ppe_is_enabled(eth, 1)) { @@ -3135,11 +3140,38 @@ static const char * const en7581_xsi_rsts_names[] = { "xfp-mac", }; +static int airoha_en7581_get_src_port_id(struct airoha_gdm_port *port, int nbq) +{ + switch (port->id) { + case 3: + /* 7581 SoC supports PCIe serdes on GDM3 port */ + if (nbq == 4) + return HSGMII_LAN_7581_PCIE0_SRCPORT; + if (nbq == 5) + return HSGMII_LAN_7581_PCIE1_SRCPORT; + break; + case 4: + /* 7581 SoC supports eth and usb serdes on GDM4 port */ + if (!nbq) + return HSGMII_LAN_7581_ETH_SRCPORT; + if (nbq == 1) + return HSGMII_LAN_7581_USB_SRCPORT; + break; + default: + break; + } + + return -EINVAL; +} + static const struct airoha_eth_soc_data en7581_soc_data = { .version = 0x7581, .xsi_rsts_names = en7581_xsi_rsts_names, .num_xsi_rsts = ARRAY_SIZE(en7581_xsi_rsts_names), .num_ppe = 2, + .ops = { + .get_src_port_id = airoha_en7581_get_src_port_id, + }, }; static const struct of_device_id of_airoha_match[] = { diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 8d121d12dc120..8a2c68781e94b 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -67,10 +67,10 @@ enum { }; enum { - HSGMII_LAN_PCIE0_SRCPORT = 0x16, - HSGMII_LAN_PCIE1_SRCPORT, - HSGMII_LAN_ETH_SRCPORT, - HSGMII_LAN_USB_SRCPORT, + HSGMII_LAN_7581_PCIE0_SRCPORT = 0x16, + HSGMII_LAN_7581_PCIE1_SRCPORT, + HSGMII_LAN_7581_ETH_SRCPORT, + HSGMII_LAN_7581_USB_SRCPORT, }; enum { @@ -99,6 +99,13 @@ enum { CRSN_25 = 0x19, }; +enum airoha_gdm_index { + AIROHA_GDM1_IDX = 1, + AIROHA_GDM2_IDX = 2, + AIROHA_GDM3_IDX = 3, + AIROHA_GDM4_IDX = 4, +}; + enum { FE_PSE_PORT_CDM1, FE_PSE_PORT_GDM1, @@ -556,6 +563,9 @@ struct airoha_eth_soc_data { const char * const *xsi_rsts_names; int num_xsi_rsts; int num_ppe; + struct { + int (*get_src_port_id)(struct airoha_gdm_port *port, int nbq); + } ops; }; struct airoha_eth { diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h index 69c5a143db8c0..ebcce00d9bc6f 100644 --- a/drivers/net/ethernet/airoha/airoha_regs.h +++ b/drivers/net/ethernet/airoha/airoha_regs.h @@ -383,10 +383,8 @@ #define REG_MC_VLAN_DATA 0x2108 #define REG_SP_DFT_CPORT(_n) (0x20e0 + ((_n) << 2)) -#define SP_CPORT_PCIE1_MASK GENMASK(31, 28) -#define SP_CPORT_PCIE0_MASK GENMASK(27, 24) -#define SP_CPORT_USB_MASK GENMASK(7, 4) -#define SP_CPORT_ETH_MASK GENMASK(7, 4) +#define SP_CPORT_DFT_MASK GENMASK(2, 0) +#define SP_CPORT_MASK(_n) GENMASK(3 + ((_n) << 2), ((_n) << 2)) #define REG_SRC_PORT_FC_MAP6 0x2298 #define FC_ID_OF_SRC_PORT27_MASK GENMASK(28, 24) From b7c1bbf78b099723c32abbd6bcc7bc8c20d43129 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Oct 2025 11:06:22 +0200 Subject: [PATCH 0874/1518] net: airoha: Add AN7583 SoC support [ Upstream commit e4e5ce823bdd4601bd75ae7c206ae35e7c2fa60b ] Introduce support for AN7583 ethernet controller to airoha-eth dirver. Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251017-an7583-eth-support-v3-13-f28319666667@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 3309965fe44c ("net: airoha: Add missing bits in airoha_qdma_cleanup_tx_queue()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 68 ++++++++++++++++++++++-- drivers/net/ethernet/airoha/airoha_eth.h | 11 ++++ drivers/net/ethernet/airoha/airoha_ppe.c | 3 ++ 3 files changed, 77 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 6e7f816cd7edb..55de295e3acf2 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1753,10 +1753,8 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) { - u32 val, pse_port, chan = port->id == AIROHA_GDM3_IDX ? 4 : 0; struct airoha_eth *eth = port->qdma->eth; - /* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */ - u32 nbq = port->id == AIROHA_GDM3_IDX ? 4 : 0; + u32 val, pse_port, chan, nbq; int src_port; /* Forward the traffic to the proper GDM port */ @@ -1768,6 +1766,8 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) /* Enable GDM2 loopback */ airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff); airoha_fe_wr(eth, REG_GDM_RXCHN_EN(2), 0xffff); + + chan = port->id == AIROHA_GDM3_IDX ? airoha_is_7581(eth) ? 4 : 3 : 0; airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(2), LPBK_CHAN_MASK | LPBK_MODE_MASK | LPBK_EN_MASK, FIELD_PREP(LPBK_CHAN_MASK, chan) | @@ -1782,6 +1782,8 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2)); airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2)); + /* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */ + nbq = port->id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0; src_port = eth->soc->ops.get_src_port_id(port, nbq); if (src_port < 0) return src_port; @@ -1795,7 +1797,7 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) SP_CPORT_MASK(val), FE_PSE_PORT_CDM2 << __ffs(SP_CPORT_MASK(val))); - if (port->id != AIROHA_GDM3_IDX) + if (port->id != AIROHA_GDM3_IDX && airoha_is_7581(eth)) airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6, FC_ID_OF_SRC_PORT24_MASK, FIELD_PREP(FC_ID_OF_SRC_PORT24_MASK, 2)); @@ -1951,6 +1953,22 @@ static bool airoha_dev_tx_queue_busy(struct airoha_queue *q, u32 nr_frags) return index >= tail; } +static int airoha_get_fe_port(struct airoha_gdm_port *port) +{ + struct airoha_qdma *qdma = port->qdma; + struct airoha_eth *eth = qdma->eth; + + switch (eth->soc->version) { + case 0x7583: + return port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 + : port->id; + case 0x7581: + default: + return port->id == AIROHA_GDM4_IDX ? FE_PSE_PORT_GDM4 + : port->id; + } +} + static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -1991,7 +2009,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, } } - fport = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id; + fport = airoha_get_fe_port(port); msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) | FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f); @@ -3164,6 +3182,35 @@ static int airoha_en7581_get_src_port_id(struct airoha_gdm_port *port, int nbq) return -EINVAL; } +static const char * const an7583_xsi_rsts_names[] = { + "xsi-mac", + "hsi0-mac", + "hsi1-mac", + "xfp-mac", +}; + +static int airoha_an7583_get_src_port_id(struct airoha_gdm_port *port, int nbq) +{ + switch (port->id) { + case 3: + /* 7583 SoC supports eth serdes on GDM3 port */ + if (!nbq) + return HSGMII_LAN_7583_ETH_SRCPORT; + break; + case 4: + /* 7583 SoC supports PCIe and USB serdes on GDM4 port */ + if (!nbq) + return HSGMII_LAN_7583_PCIE_SRCPORT; + if (nbq == 1) + return HSGMII_LAN_7583_USB_SRCPORT; + break; + default: + break; + } + + return -EINVAL; +} + static const struct airoha_eth_soc_data en7581_soc_data = { .version = 0x7581, .xsi_rsts_names = en7581_xsi_rsts_names, @@ -3174,8 +3221,19 @@ static const struct airoha_eth_soc_data en7581_soc_data = { }, }; +static const struct airoha_eth_soc_data an7583_soc_data = { + .version = 0x7583, + .xsi_rsts_names = an7583_xsi_rsts_names, + .num_xsi_rsts = ARRAY_SIZE(an7583_xsi_rsts_names), + .num_ppe = 1, + .ops = { + .get_src_port_id = airoha_an7583_get_src_port_id, + }, +}; + static const struct of_device_id of_airoha_match[] = { { .compatible = "airoha,en7581-eth", .data = &en7581_soc_data }, + { .compatible = "airoha,an7583-eth", .data = &an7583_soc_data }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, of_airoha_match); diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 8a2c68781e94b..203e6ce29dbe0 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -73,6 +73,12 @@ enum { HSGMII_LAN_7581_USB_SRCPORT, }; +enum { + HSGMII_LAN_7583_ETH_SRCPORT = 0x16, + HSGMII_LAN_7583_PCIE_SRCPORT = 0x18, + HSGMII_LAN_7583_USB_SRCPORT, +}; + enum { XSI_PCIE0_VIP_PORT_MASK = BIT(22), XSI_PCIE1_VIP_PORT_MASK = BIT(23), @@ -630,6 +636,11 @@ static inline bool airoha_is_7581(struct airoha_eth *eth) return eth->soc->version == 0x7581; } +static inline bool airoha_is_7583(struct airoha_eth *eth) +{ + return eth->soc->version == 0x7583; +} + bool airoha_is_valid_gdm_port(struct airoha_eth *eth, struct airoha_gdm_port *port); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 239c43248b4f4..6cd5febce6b59 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -37,6 +37,9 @@ static int airoha_ppe_get_num_stats_entries(struct airoha_ppe *ppe) if (!IS_ENABLED(CONFIG_NET_AIROHA_FLOW_STATS)) return -EOPNOTSUPP; + if (airoha_is_7583(ppe->eth)) + return -EOPNOTSUPP; + return PPE_STATS_NUM_ENTRIES; } From ad02cb61c52cae5afa3e2de6adbb49ad884c26e9 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 6 Nov 2025 13:53:23 +0100 Subject: [PATCH 0875/1518] net: airoha: Add the capability to consume out-of-order DMA tx descriptors [ Upstream commit 3f47e67dff1f7266e112c50313d63824f6f17102 ] EN7581 and AN7583 SoCs are capable of DMA mapping non-linear tx skbs on non-consecutive DMA descriptors. This feature is useful when multiple flows are queued on the same hw tx queue since it allows to fully utilize the available tx DMA descriptors and to avoid the starvation of high-priority flow we have in the current codebase due to head-of-line blocking introduced by low-priority flows. Tested-by: Xuegang Lu Reviewed-by: Jacob Keller Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251106-airoha-tx-linked-list-v2-1-0706d4a322bd@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: 3309965fe44c ("net: airoha: Add missing bits in airoha_qdma_cleanup_tx_queue()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 85 +++++++++++------------- drivers/net/ethernet/airoha/airoha_eth.h | 7 +- 2 files changed, 45 insertions(+), 47 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 55de295e3acf2..9f6f517b5fdf9 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -952,19 +952,13 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) dma_unmap_single(eth->dev, e->dma_addr, e->dma_len, DMA_TO_DEVICE); - memset(e, 0, sizeof(*e)); + e->dma_addr = 0; + list_add_tail(&e->list, &q->tx_list); + WRITE_ONCE(desc->msg0, 0); WRITE_ONCE(desc->msg1, 0); q->queued--; - /* completion ring can report out-of-order indexes if hw QoS - * is enabled and packets with different priority are queued - * to same DMA ring. Take into account possible out-of-order - * reports incrementing DMA ring tail pointer - */ - while (q->tail != q->head && !q->entry[q->tail].dma_addr) - q->tail = (q->tail + 1) % q->ndesc; - if (skb) { u16 queue = skb_get_queue_mapping(skb); struct netdev_queue *txq; @@ -1018,6 +1012,7 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, q->ndesc = size; q->qdma = qdma; q->free_thr = 1 + MAX_SKB_FRAGS; + INIT_LIST_HEAD(&q->tx_list); q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), GFP_KERNEL); @@ -1030,9 +1025,9 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, return -ENOMEM; for (i = 0; i < q->ndesc; i++) { - u32 val; + u32 val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1); - val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1); + list_add_tail(&q->entry[i].list, &q->tx_list); WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val)); } @@ -1042,9 +1037,9 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr); airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, - FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); + FIELD_PREP(TX_RING_CPU_IDX_MASK, 0)); airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, - FIELD_PREP(TX_RING_DMA_IDX_MASK, q->head)); + FIELD_PREP(TX_RING_DMA_IDX_MASK, 0)); return 0; } @@ -1100,17 +1095,21 @@ static int airoha_qdma_init_tx(struct airoha_qdma *qdma) static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) { struct airoha_eth *eth = q->qdma->eth; + int i; spin_lock_bh(&q->lock); - while (q->queued) { - struct airoha_queue_entry *e = &q->entry[q->tail]; + for (i = 0; i < q->ndesc; i++) { + struct airoha_queue_entry *e = &q->entry[i]; + + if (!e->dma_addr) + continue; dma_unmap_single(eth->dev, e->dma_addr, e->dma_len, DMA_TO_DEVICE); dev_kfree_skb_any(e->skb); + e->dma_addr = 0; e->skb = NULL; - - q->tail = (q->tail + 1) % q->ndesc; + list_add_tail(&e->list, &q->tx_list); q->queued--; } spin_unlock_bh(&q->lock); @@ -1939,20 +1938,6 @@ static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev) #endif } -static bool airoha_dev_tx_queue_busy(struct airoha_queue *q, u32 nr_frags) -{ - u32 tail = q->tail <= q->head ? q->tail + q->ndesc : q->tail; - u32 index = q->head + nr_frags; - - /* completion napi can free out-of-order tx descriptors if hw QoS is - * enabled and packets with different priorities are queued to the same - * DMA ring. Take into account possible out-of-order reports checking - * if the tx queue is full using circular buffer head/tail pointers - * instead of the number of queued packets. - */ - return index >= tail; -} - static int airoha_get_fe_port(struct airoha_gdm_port *port) { struct airoha_qdma *qdma = port->qdma; @@ -1975,8 +1960,10 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct airoha_gdm_port *port = netdev_priv(dev); struct airoha_qdma *qdma = port->qdma; u32 nr_frags, tag, msg0, msg1, len; + struct airoha_queue_entry *e; struct netdev_queue *txq; struct airoha_queue *q; + LIST_HEAD(tx_list); void *data; int i, qid; u16 index; @@ -2022,7 +2009,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, txq = netdev_get_tx_queue(dev, qid); nr_frags = 1 + skb_shinfo(skb)->nr_frags; - if (airoha_dev_tx_queue_busy(q, nr_frags)) { + if (q->queued + nr_frags >= q->ndesc) { /* not enough space in the queue */ netif_tx_stop_queue(txq); q->txq_stopped = true; @@ -2032,11 +2019,13 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, len = skb_headlen(skb); data = skb->data; - index = q->head; + + e = list_first_entry(&q->tx_list, struct airoha_queue_entry, + list); + index = e - q->entry; for (i = 0; i < nr_frags; i++) { struct airoha_qdma_desc *desc = &q->desc[index]; - struct airoha_queue_entry *e = &q->entry[index]; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr; u32 val; @@ -2046,7 +2035,14 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, if (unlikely(dma_mapping_error(dev->dev.parent, addr))) goto error_unmap; - index = (index + 1) % q->ndesc; + list_move_tail(&e->list, &tx_list); + e->skb = i ? NULL : skb; + e->dma_addr = addr; + e->dma_len = len; + + e = list_first_entry(&q->tx_list, struct airoha_queue_entry, + list); + index = e - q->entry; val = FIELD_PREP(QDMA_DESC_LEN_MASK, len); if (i < nr_frags - 1) @@ -2059,15 +2055,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, WRITE_ONCE(desc->msg1, cpu_to_le32(msg1)); WRITE_ONCE(desc->msg2, cpu_to_le32(0xffff)); - e->skb = i ? NULL : skb; - e->dma_addr = addr; - e->dma_len = len; - data = skb_frag_address(frag); len = skb_frag_size(frag); } - - q->head = index; q->queued += i; skb_tx_timestamp(skb); @@ -2076,7 +2066,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, if (netif_xmit_stopped(txq) || !netdev_xmit_more()) airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, - FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); + FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); if (q->ndesc - q->queued < q->free_thr) { netif_tx_stop_queue(txq); @@ -2088,10 +2078,13 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, return NETDEV_TX_OK; error_unmap: - for (i--; i >= 0; i--) { - index = (q->head + i) % q->ndesc; - dma_unmap_single(dev->dev.parent, q->entry[index].dma_addr, - q->entry[index].dma_len, DMA_TO_DEVICE); + while (!list_empty(&tx_list)) { + e = list_first_entry(&tx_list, struct airoha_queue_entry, + list); + dma_unmap_single(dev->dev.parent, e->dma_addr, e->dma_len, + DMA_TO_DEVICE); + e->dma_addr = 0; + list_move_tail(&e->list, &q->tx_list); } spin_unlock_bh(&q->lock); diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 203e6ce29dbe0..28dfa35a3abed 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -169,7 +169,10 @@ enum trtcm_param { struct airoha_queue_entry { union { void *buf; - struct sk_buff *skb; + struct { + struct list_head list; + struct sk_buff *skb; + }; }; dma_addr_t dma_addr; u16 dma_len; @@ -194,6 +197,8 @@ struct airoha_queue { struct napi_struct napi; struct page_pool *page_pool; struct sk_buff *skb; + + struct list_head tx_list; }; struct airoha_tx_irq_queue { From c0cfce4d76702dba9601a4020df1a0bc35806efc Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Apr 2026 08:36:32 +0200 Subject: [PATCH 0876/1518] net: airoha: Add missing bits in airoha_qdma_cleanup_tx_queue() [ Upstream commit 3309965fe44c00fd65af7cef5016e9e782c021a7 ] Similar to airoha_qdma_cleanup_rx_queue(), reset DMA TX descriptors in airoha_qdma_cleanup_tx_queue routine. Moreover, reset TX_DMA_IDX to TX_CPU_IDX to notify the NIC the QDMA TX ring is empty. Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260417-airoha_qdma_cleanup_tx_queue-fix-net-v4-2-e04bcc2c9642@kernel.org Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 32 ++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 9f6f517b5fdf9..f088f25128eb4 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1094,12 +1094,15 @@ static int airoha_qdma_init_tx(struct airoha_qdma *qdma) static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) { - struct airoha_eth *eth = q->qdma->eth; - int i; + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int i, qid = q - &qdma->q_tx[0]; + u16 index = 0; spin_lock_bh(&q->lock); for (i = 0; i < q->ndesc; i++) { struct airoha_queue_entry *e = &q->entry[i]; + struct airoha_qdma_desc *desc = &q->desc[i]; if (!e->dma_addr) continue; @@ -1110,8 +1113,33 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) e->dma_addr = 0; e->skb = NULL; list_add_tail(&e->list, &q->tx_list); + + /* Reset DMA descriptor */ + WRITE_ONCE(desc->ctrl, 0); + WRITE_ONCE(desc->addr, 0); + WRITE_ONCE(desc->data, 0); + WRITE_ONCE(desc->msg0, 0); + WRITE_ONCE(desc->msg1, 0); + WRITE_ONCE(desc->msg2, 0); + q->queued--; } + + if (!list_empty(&q->tx_list)) { + struct airoha_queue_entry *e; + + e = list_first_entry(&q->tx_list, struct airoha_queue_entry, + list); + index = e - q->entry; + } + /* Set TX_DMA_IDX to TX_CPU_IDX to notify the hw the QDMA TX ring is + * empty. + */ + airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, + FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); + airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, + FIELD_PREP(TX_RING_DMA_IDX_MASK, index)); + spin_unlock_bh(&q->lock); } From b707f3109f1a7828b93f1633be39c0ebc9ce4afc Mon Sep 17 00:00:00 2001 From: Mieczyslaw Nalewaj Date: Sun, 19 Apr 2026 21:37:07 +0200 Subject: [PATCH 0877/1518] net: dsa: realtek: rtl8365mb: fix mode mask calculation [ Upstream commit 0c078021d3861966614d5e594ee03587f0c9e74d ] The RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK macro was shifting the 4-bit mask (0xF) by only (_extint % 2) bits instead of (_extint % 2) * 4. This caused the mask to overlap with the adjacent nibble when configuring odd-numbered external interfaces, selecting the wrong bits entirely. Align the shift calculation with the existing ...MODE_OFFSET macro. Fixes: 4af2950c50c8 ("net: dsa: realtek-smi: add rtl8365mb subdriver for RTL8365MB-VC") Signed-off-by: Abdulkader Alrezej Signed-off-by: Mieczyslaw Nalewaj Reviewed-by: Luiz Angelo Daros de Luca Link: https://patch.msgid.link/400a6387-a444-4576-af6d-26be5410bce3@yahoo.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/dsa/realtek/rtl8365mb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index 3a48db295e7e4..e10a789e22022 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -216,7 +216,7 @@ (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 : \ 0x0) #define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extint) \ - (0xF << (((_extint) % 2))) + (0xF << (((_extint) % 2) * 4)) #define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extint) \ (((_extint) % 2) * 4) From 4d4acfa348a1d8c0941004823662ede0fdb5dea5 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 20 Apr 2026 10:07:47 +0200 Subject: [PATCH 0878/1518] net: airoha: Move ndesc initialization at end of airoha_qdma_init_rx_queue() [ Upstream commit 379050947a1828826ad7ea50c95245a56929b35a ] If queue entry or DMA descriptor list allocation fails in airoha_qdma_init_rx_queue routine, airoha_qdma_cleanup() will trigger a NULL pointer dereference running netif_napi_del() for RX queue NAPIs since netif_napi_add() has never been executed to this particular RX NAPI. The issue is due to the early ndesc initialization in airoha_qdma_init_rx_queue() since airoha_qdma_cleanup() relies on ndesc value to check if the queue is properly initialized. Fix the issue moving ndesc initialization at end of airoha_qdma_init_tx routine. Move page_pool allocation after descriptor list allocation in order to avoid memory leaks if desc allocation fails. Fixes: 23020f049327 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260420-airoha_qdma_init_rx_queue-fix-v2-1-d99347e5c18d@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index f088f25128eb4..1d5447684ecab 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -776,14 +776,18 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q, dma_addr_t dma_addr; q->buf_size = PAGE_SIZE / 2; - q->ndesc = ndesc; q->qdma = qdma; - q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), + q->entry = devm_kzalloc(eth->dev, ndesc * sizeof(*q->entry), GFP_KERNEL); if (!q->entry) return -ENOMEM; + q->desc = dmam_alloc_coherent(eth->dev, ndesc * sizeof(*q->desc), + &dma_addr, GFP_KERNEL); + if (!q->desc) + return -ENOMEM; + q->page_pool = page_pool_create(&pp_params); if (IS_ERR(q->page_pool)) { int err = PTR_ERR(q->page_pool); @@ -792,11 +796,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q, return err; } - q->desc = dmam_alloc_coherent(eth->dev, q->ndesc * sizeof(*q->desc), - &dma_addr, GFP_KERNEL); - if (!q->desc) - return -ENOMEM; - + q->ndesc = ndesc; netif_napi_add(eth->napi_dev, &q->napi, airoha_qdma_rx_napi_poll); airoha_qdma_wr(qdma, REG_RX_RING_BASE(qid), dma_addr); From d8ad264e9a019808c858aeada39a9bf99467868c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 21 Mar 2026 15:41:44 +0100 Subject: [PATCH 0879/1518] net: airoha: Rework the code flow in airoha_remove() and in airoha_probe() error path [ Upstream commit b1c803d5c8167026791abfaed96fd3e6a1fcd750 ] As suggested by Simon in [0], rework the code flow in airoha_remove() and in the airoha_probe() error path in order to rely on a more common approach un-registering configured net-devices first and destroying the hw resources at the end of the code. Introduce airoha_qdma_cleanup routine to release QDMA resources. [0] https://lore.kernel.org/netdev/20251214-airoha-fix-dev-registration-v1-1-860e027ad4c6@kernel.org/ Suggested-by: Simon Horman Signed-off-by: Lorenzo Bianconi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260321-airoha-remove-rework-v2-1-16c7bade5fe5@kernel.org Signed-off-by: Paolo Abeni Stable-dep-of: 4b91cb65789b ("net: airoha: Add size check for TX NAPIs in airoha_qdma_cleanup()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 76 ++++++++++++++---------- 1 file changed, 44 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 1d5447684ecab..8416451f4786a 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1465,6 +1465,33 @@ static int airoha_qdma_init(struct platform_device *pdev, return airoha_qdma_hw_init(qdma); } +static void airoha_qdma_cleanup(struct airoha_qdma *qdma) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) + continue; + + netif_napi_del(&qdma->q_rx[i].napi); + airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]); + if (qdma->q_rx[i].page_pool) { + page_pool_destroy(qdma->q_rx[i].page_pool); + qdma->q_rx[i].page_pool = NULL; + } + } + + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) + netif_napi_del(&qdma->q_tx_irq[i].napi); + + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + if (!qdma->q_tx[i].ndesc) + continue; + + airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]); + } +} + static int airoha_hw_init(struct platform_device *pdev, struct airoha_eth *eth) { @@ -1492,41 +1519,30 @@ static int airoha_hw_init(struct platform_device *pdev, for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) { err = airoha_qdma_init(pdev, eth, ð->qdma[i]); if (err) - return err; + goto error; } err = airoha_ppe_init(eth); if (err) - return err; + goto error; set_bit(DEV_STATE_INITIALIZED, ð->state); return 0; +error: + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_qdma_cleanup(ð->qdma[i]); + + return err; } -static void airoha_hw_cleanup(struct airoha_qdma *qdma) +static void airoha_hw_cleanup(struct airoha_eth *eth) { int i; - for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { - if (!qdma->q_rx[i].ndesc) - continue; - - netif_napi_del(&qdma->q_rx[i].napi); - airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]); - if (qdma->q_rx[i].page_pool) - page_pool_destroy(qdma->q_rx[i].page_pool); - } - - for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) - netif_napi_del(&qdma->q_tx_irq[i].napi); - - for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { - if (!qdma->q_tx[i].ndesc) - continue; - - airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]); - } + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_qdma_cleanup(ð->qdma[i]); + airoha_ppe_deinit(eth); } static void airoha_qdma_start_napi(struct airoha_qdma *qdma) @@ -3096,7 +3112,7 @@ static int airoha_probe(struct platform_device *pdev) err = airoha_hw_init(pdev, eth); if (err) - goto error_hw_cleanup; + goto error_netdev_free; for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_qdma_start_napi(ð->qdma[i]); @@ -3125,10 +3141,6 @@ static int airoha_probe(struct platform_device *pdev) error_napi_stop: for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_qdma_stop_napi(ð->qdma[i]); - airoha_ppe_deinit(eth); -error_hw_cleanup: - for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) - airoha_hw_cleanup(ð->qdma[i]); for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; @@ -3140,6 +3152,8 @@ static int airoha_probe(struct platform_device *pdev) unregister_netdev(port->dev); airoha_metadata_dst_free(port); } + airoha_hw_cleanup(eth); +error_netdev_free: free_netdev(eth->napi_dev); platform_set_drvdata(pdev, NULL); @@ -3151,10 +3165,8 @@ static void airoha_remove(struct platform_device *pdev) struct airoha_eth *eth = platform_get_drvdata(pdev); int i; - for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) { + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_qdma_stop_napi(ð->qdma[i]); - airoha_hw_cleanup(ð->qdma[i]); - } for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; @@ -3165,9 +3177,9 @@ static void airoha_remove(struct platform_device *pdev) unregister_netdev(port->dev); airoha_metadata_dst_free(port); } - free_netdev(eth->napi_dev); + airoha_hw_cleanup(eth); - airoha_ppe_deinit(eth); + free_netdev(eth->napi_dev); platform_set_drvdata(pdev, NULL); } From 5a90c4cfd8b7ad779ef62a810a391ee88eaf2726 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 20 Apr 2026 10:07:48 +0200 Subject: [PATCH 0880/1518] net: airoha: Add size check for TX NAPIs in airoha_qdma_cleanup() [ Upstream commit 4b91cb65789b794bfc8d50554b8994f8e0f16309 ] If airoha_qdma_init routine fails before airoha_qdma_tx_irq_init() runs successfully for all TX NAPIs, airoha_qdma_cleanup() will unconditionally runs netif_napi_del() on TX NAPIs, triggering a NULL pointer dereference. Fix the issue relying on q_tx_irq size value to check if the TX NAPIs is properly initialized in airoha_qdma_cleanup(). Moreover, run netif_napi_add_tx() just if irq_q queue is properly allocated. Fixes: 23020f049327 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260420-airoha_qdma_init_rx_queue-fix-v2-2-d99347e5c18d@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 8416451f4786a..865b854bd4afc 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1051,8 +1051,6 @@ static int airoha_qdma_tx_irq_init(struct airoha_tx_irq_queue *irq_q, struct airoha_eth *eth = qdma->eth; dma_addr_t dma_addr; - netif_napi_add_tx(eth->napi_dev, &irq_q->napi, - airoha_qdma_tx_napi_poll); irq_q->q = dmam_alloc_coherent(eth->dev, size * sizeof(u32), &dma_addr, GFP_KERNEL); if (!irq_q->q) @@ -1062,6 +1060,9 @@ static int airoha_qdma_tx_irq_init(struct airoha_tx_irq_queue *irq_q, irq_q->size = size; irq_q->qdma = qdma; + netif_napi_add_tx(eth->napi_dev, &irq_q->napi, + airoha_qdma_tx_napi_poll); + airoha_qdma_wr(qdma, REG_TX_IRQ_BASE(id), dma_addr); airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK, FIELD_PREP(TX_IRQ_DEPTH_MASK, size)); @@ -1481,8 +1482,12 @@ static void airoha_qdma_cleanup(struct airoha_qdma *qdma) } } - for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + if (!qdma->q_tx_irq[i].size) + continue; + netif_napi_del(&qdma->q_tx_irq[i].napi); + } for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { if (!qdma->q_tx[i].ndesc) From 8709d4457faf3691e1b08a70fa157b53bedbc3d9 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Mon, 20 Apr 2026 05:47:35 -0700 Subject: [PATCH 0881/1518] net: mana: Init link_change_work before potential error paths in probe [ Upstream commit cb4a90744bcd1adf12f0d0c7c4f0dd2647444ec5 ] Move INIT_WORK(link_change_work) to right after the mana_context allocation, before any error path that could reach mana_remove(). Previously, if mana_create_eq() or mana_query_device_cfg() failed, mana_probe() would jump to the error path which calls mana_remove(). mana_remove() unconditionally calls disable_work_sync(link_change_work), but the work struct had not been initialized yet. This can trigger CONFIG_DEBUG_OBJECTS_WORK enabled. Fixes: 54133f9b4b53 ("net: mana: Support HW link state events") Signed-off-by: Erni Sri Satya Vennela Link: https://patch.msgid.link/20260420124741.1056179-2-ernis@linux.microsoft.com Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index c770fb86fd2d3..cd3a435485a19 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3483,6 +3483,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) ac->gdma_dev = gd; gd->driver_data = ac; + + INIT_WORK(&ac->link_change_work, mana_link_state_handle); } err = mana_create_eq(ac); @@ -3500,8 +3502,6 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!resuming) { ac->num_ports = num_ports; - - INIT_WORK(&ac->link_change_work, mana_link_state_handle); } else { if (ac->num_ports != num_ports) { dev_err(dev, "The number of vPorts changed: %d->%d\n", From a1ddfd2c0b7a48e5239fadd2a24cc4bc2cda90e6 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Mon, 20 Apr 2026 05:47:37 -0700 Subject: [PATCH 0882/1518] net: mana: Guard mana_remove against double invocation [ Upstream commit 50271d7ec95144d26808025b508f463780517d3c ] If PM resume fails (e.g., mana_attach() returns an error), mana_probe() calls mana_remove(), which tears down the device and sets gd->gdma_context = NULL and gd->driver_data = NULL. However, a failed resume callback does not automatically unbind the driver. When the device is eventually unbound, mana_remove() is invoked a second time. Without a NULL check, it dereferences gc->dev with gc == NULL, causing a kernel panic. Add an early return if gdma_context or driver_data is NULL so the second invocation is harmless. Move the dev = gc->dev assignment after the guard so it cannot dereference NULL. Fixes: 635096a86edb ("net: mana: Support hibernation and kexec") Signed-off-by: Erni Sri Satya Vennela Link: https://patch.msgid.link/20260420124741.1056179-4-ernis@linux.microsoft.com Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index cd3a435485a19..d90be4142e257 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3568,11 +3568,16 @@ void mana_remove(struct gdma_dev *gd, bool suspending) struct gdma_context *gc = gd->gdma_context; struct mana_context *ac = gd->driver_data; struct mana_port_context *apc; - struct device *dev = gc->dev; + struct device *dev; struct net_device *ndev; int err; int i; + if (!gc || !ac) + return; + + dev = gc->dev; + disable_work_sync(&ac->link_change_work); /* adev currently doesn't support suspending, always remove it */ From 8804f00ea0283ff5d0a4193385fde27f0a4892c3 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Fri, 14 Nov 2025 03:43:18 -0800 Subject: [PATCH 0883/1518] net: mana: Move hardware counter stats from per-port to per-VF context [ Upstream commit e275d9091c01b3b46f3ec534ce4ac77cffc9e3ae ] Move hardware counter (HC) statistics from mana_port_context to mana_context to enable sharing stats across multiple network ports on the same MANA VF. Previously, each network port queried hardware counters independently using MANA_QUERY_GF_STAT command (GF = Generic Function stats from GDMA hardware), resulting in redundant queries when multiple ports existed on the same device. Isolate hardware counter stats by introducing mana_ethtool_hc_stats in mana_context and update the code to ensure all stats are properly reported via ethtool -S , maintaining consistency with previous behavior. Signed-off-by: Erni Sri Satya Vennela Reviewed-by: Haiyang Zhang Link: https://patch.msgid.link/1763120599-6331-2-git-send-email-ernis@linux.microsoft.com Signed-off-by: Jakub Kicinski Stable-dep-of: a7fdaf069bd0 ("net: mana: Don't overwrite port probe error with add_adev result") Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 67 ++++++++------- .../ethernet/microsoft/mana/mana_ethtool.c | 85 ++++++++++--------- include/net/mana/mana.h | 14 +-- 3 files changed, 90 insertions(+), 76 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d90be4142e257..2e5efc03cacec 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2836,11 +2836,12 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } -void mana_query_gf_stats(struct mana_port_context *apc) +void mana_query_gf_stats(struct mana_context *ac) { + struct gdma_context *gc = ac->gdma_dev->gdma_context; struct mana_query_gf_stat_resp resp = {}; struct mana_query_gf_stat_req req = {}; - struct net_device *ndev = apc->ndev; + struct device *dev = gc->dev; int err; mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, @@ -2874,52 +2875,52 @@ void mana_query_gf_stats(struct mana_port_context *apc) STATISTICS_FLAGS_HC_TX_BCAST_BYTES | STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR; - err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + err = mana_send_request(ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to query GF stats: %d\n", err); + dev_err(dev, "Failed to query GF stats: %d\n", err); return; } err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, sizeof(resp)); if (err || resp.hdr.status) { - netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, - resp.hdr.status); + dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err, + resp.hdr.status); return; } - apc->eth_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; - apc->eth_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; - apc->eth_stats.hc_rx_bytes = resp.hc_rx_bytes; - apc->eth_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; - apc->eth_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; - apc->eth_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; - apc->eth_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; - apc->eth_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; - apc->eth_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; - apc->eth_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; - apc->eth_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; - apc->eth_stats.hc_tx_err_inval_vportoffset_pkt = + ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; + ac->hc_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; + ac->hc_stats.hc_rx_bytes = resp.hc_rx_bytes; + ac->hc_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; + ac->hc_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; + ac->hc_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; + ac->hc_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; + ac->hc_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; + ac->hc_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; + ac->hc_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; + ac->hc_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; + ac->hc_stats.hc_tx_err_inval_vportoffset_pkt = resp.tx_err_inval_vport_offset_pkt; - apc->eth_stats.hc_tx_err_vlan_enforcement = + ac->hc_stats.hc_tx_err_vlan_enforcement = resp.tx_err_vlan_enforcement; - apc->eth_stats.hc_tx_err_eth_type_enforcement = + ac->hc_stats.hc_tx_err_eth_type_enforcement = resp.tx_err_ethtype_enforcement; - apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; - apc->eth_stats.hc_tx_err_sqpdid_enforcement = + ac->hc_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; + ac->hc_stats.hc_tx_err_sqpdid_enforcement = resp.tx_err_SQPDID_enforcement; - apc->eth_stats.hc_tx_err_cqpdid_enforcement = + ac->hc_stats.hc_tx_err_cqpdid_enforcement = resp.tx_err_CQPDID_enforcement; - apc->eth_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; - apc->eth_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; - apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; - apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; - apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; - apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; - apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; - apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; - apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; - apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma; + ac->hc_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; + ac->hc_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; + ac->hc_stats.hc_tx_bytes = resp.hc_tx_bytes; + ac->hc_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; + ac->hc_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; + ac->hc_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; + ac->hc_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; + ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; + ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; + ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma; } void mana_query_phy_stats(struct mana_port_context *apc) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a1afa75a94631..3dfd96146424e 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -15,66 +15,69 @@ struct mana_stats_desc { static const struct mana_stats_desc mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_stats, + {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, + {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + tx_cqe_unknown_type)}, + {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, + rx_coalesced_err)}, + {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + rx_cqe_unknown_type)}, +}; + +static const struct mana_stats_desc mana_hc_stats[] = { + {"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_hc_stats, hc_rx_discards_no_wqe)}, - {"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_stats, + {"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats, hc_rx_err_vport_disabled)}, - {"hc_rx_bytes", offsetof(struct mana_ethtool_stats, hc_rx_bytes)}, - {"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_rx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bytes)}, + {"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_rx_ucast_pkts)}, - {"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_ucast_bytes)}, - {"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_rx_bcast_pkts)}, - {"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bcast_bytes)}, - {"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_stats, - hc_rx_mcast_pkts)}, - {"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats, + hc_rx_mcast_pkts)}, + {"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_mcast_bytes)}, - {"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_gf_disabled)}, - {"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_vport_disabled)}, {"hc_tx_err_inval_vportoffset_pkt", - offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_inval_vportoffset_pkt)}, - {"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_vlan_enforcement)}, {"hc_tx_err_eth_type_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)}, - {"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_eth_type_enforcement)}, + {"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sa_enforcement)}, {"hc_tx_err_sqpdid_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforcement)}, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sqpdid_enforcement)}, {"hc_tx_err_cqpdid_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)}, - {"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_cqpdid_enforcement)}, + {"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_mtu_violation)}, - {"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_inval_oob)}, - {"hc_tx_err_gdma", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_gdma", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_gdma)}, - {"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)}, - {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bytes)}, + {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_ucast_pkts)}, - {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_ucast_bytes)}, - {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_bcast_pkts)}, - {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bcast_bytes)}, - {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_mcast_pkts)}, - {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_mcast_bytes)}, - {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, - {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, - tx_cqe_unknown_type)}, - {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, - rx_coalesced_err)}, - {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, - rx_cqe_unknown_type)}, }; static const struct mana_stats_desc mana_phy_stats[] = { @@ -138,7 +141,7 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset) if (stringset != ETH_SS_STATS) return -EINVAL; - return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + + return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + ARRAY_SIZE(mana_hc_stats) + num_queues * (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT); } @@ -150,10 +153,12 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) if (stringset != ETH_SS_STATS) return; - for (i = 0; i < ARRAY_SIZE(mana_eth_stats); i++) ethtool_puts(&data, mana_eth_stats[i].name); + for (i = 0; i < ARRAY_SIZE(mana_hc_stats); i++) + ethtool_puts(&data, mana_hc_stats[i].name); + for (i = 0; i < ARRAY_SIZE(mana_phy_stats); i++) ethtool_puts(&data, mana_phy_stats[i].name); @@ -186,6 +191,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev, struct mana_port_context *apc = netdev_priv(ndev); unsigned int num_queues = apc->num_queues; void *eth_stats = &apc->eth_stats; + void *hc_stats = &apc->ac->hc_stats; void *phy_stats = &apc->phy_stats; struct mana_stats_rx *rx_stats; struct mana_stats_tx *tx_stats; @@ -208,7 +214,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev, if (!apc->port_is_up) return; /* we call mana function to update stats from GDMA */ - mana_query_gf_stats(apc); + mana_query_gf_stats(apc->ac); /* We call this mana function to get the phy stats from GDMA and includes * aggregate tx/rx drop counters, Per-TC(Traffic Channel) tx/rx and pause @@ -219,6 +225,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev, for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++) data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); + for (q = 0; q < ARRAY_SIZE(mana_hc_stats); q++) + data[i++] = *(u64 *)(hc_stats + mana_hc_stats[q].offset); + for (q = 0; q < ARRAY_SIZE(mana_phy_stats); q++) data[i++] = *(u64 *)(phy_stats + mana_phy_stats[q].offset); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index f9f264385405c..265f2d90027d6 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -375,6 +375,13 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 tx_cqe_err; + u64 tx_cqe_unknown_type; + u64 rx_coalesced_err; + u64 rx_cqe_unknown_type; +}; + +struct mana_ethtool_hc_stats { u64 hc_rx_discards_no_wqe; u64 hc_rx_err_vport_disabled; u64 hc_rx_bytes; @@ -402,10 +409,6 @@ struct mana_ethtool_stats { u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; u64 hc_tx_err_gdma; - u64 tx_cqe_err; - u64 tx_cqe_unknown_type; - u64 rx_coalesced_err; - u64 rx_cqe_unknown_type; }; struct mana_ethtool_phy_stats { @@ -473,6 +476,7 @@ struct mana_context { u16 num_ports; u8 bm_hostmode; + struct mana_ethtool_hc_stats hc_stats; struct mana_eq *eqs; struct dentry *mana_eqs_debugfs; @@ -578,7 +582,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); -void mana_query_gf_stats(struct mana_port_context *apc); +void mana_query_gf_stats(struct mana_context *ac); int mana_query_link_cfg(struct mana_port_context *apc); int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, int enable_clamping); From 95e4598b68052b9aea7f3ea062b7bafe3299e50a Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Fri, 14 Nov 2025 03:43:19 -0800 Subject: [PATCH 0884/1518] net: mana: Add standard counter rx_missed_errors [ Upstream commit be4f1d67ec56f23f37714ac73c01094e63c7ff28 ] Report standard counter stats->rx_missed_errors using hc_rx_discards_no_wqe from the hardware. Add a global workqueue to periodically run mana_query_gf_stats every 2 seconds to get the latest info in eth_stats and define a driver capability flag to notify hardware of the periodic queries. To avoid repeated failures and log flooding, the workqueue is not rescheduled if mana_query_gf_stats fails on HWC timeout error and the stats are reset to 0. Other errors are transient which will not need a VF reset for recovery. Signed-off-by: Erni Sri Satya Vennela Reviewed-by: Haiyang Zhang Link: https://patch.msgid.link/1763120599-6331-3-git-send-email-ernis@linux.microsoft.com Signed-off-by: Jakub Kicinski Stable-dep-of: a7fdaf069bd0 ("net: mana: Don't overwrite port probe error with add_adev result") Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 36 +++++++++++++++++-- .../ethernet/microsoft/mana/mana_ethtool.c | 2 -- include/net/mana/gdma.h | 6 +++- include/net/mana/mana.h | 6 +++- 4 files changed, 43 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 2e5efc03cacec..b0d411ab1067f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -534,6 +534,11 @@ static void mana_get_stats64(struct net_device *ndev, netdev_stats_to_stats64(st, &ndev->stats); + if (apc->ac->hwc_timeout_occurred) + netdev_warn_once(ndev, "HWC timeout occurred\n"); + + st->rx_missed_errors = apc->ac->hc_stats.hc_rx_discards_no_wqe; + for (q = 0; q < num_queues; q++) { rx_stats = &apc->rxqs[q]->stats; @@ -2836,7 +2841,7 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } -void mana_query_gf_stats(struct mana_context *ac) +int mana_query_gf_stats(struct mana_context *ac) { struct gdma_context *gc = ac->gdma_dev->gdma_context; struct mana_query_gf_stat_resp resp = {}; @@ -2879,14 +2884,14 @@ void mana_query_gf_stats(struct mana_context *ac) sizeof(resp)); if (err) { dev_err(dev, "Failed to query GF stats: %d\n", err); - return; + return err; } err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, sizeof(resp)); if (err || resp.hdr.status) { dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err, resp.hdr.status); - return; + return err; } ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; @@ -2921,6 +2926,8 @@ void mana_query_gf_stats(struct mana_context *ac) ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma; + + return 0; } void mana_query_phy_stats(struct mana_port_context *apc) @@ -3459,6 +3466,24 @@ int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type even return 0; } +#define MANA_GF_STATS_PERIOD (2 * HZ) + +static void mana_gf_stats_work_handler(struct work_struct *work) +{ + struct mana_context *ac = + container_of(to_delayed_work(work), struct mana_context, gf_stats_work); + int err; + + err = mana_query_gf_stats(ac); + if (err == -ETIMEDOUT) { + /* HWC timeout detected - reset stats and stop rescheduling */ + ac->hwc_timeout_occurred = true; + memset(&ac->hc_stats, 0, sizeof(ac->hc_stats)); + return; + } + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); +} + int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; @@ -3551,6 +3576,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } err = add_adev(gd, "eth"); + + INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); + out: if (err) { mana_remove(gd, false); @@ -3580,6 +3609,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) dev = gc->dev; disable_work_sync(&ac->link_change_work); + cancel_delayed_work_sync(&ac->gf_stats_work); /* adev currently doesn't support suspending, always remove it */ if (gd->adev) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 3dfd96146424e..99e8112086833 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -213,8 +213,6 @@ static void mana_get_ethtool_stats(struct net_device *ndev, if (!apc->port_is_up) return; - /* we call mana function to update stats from GDMA */ - mana_query_gf_stats(apc->ac); /* We call this mana function to get the phy stats from GDMA and includes * aggregate tx/rx drop counters, Per-TC(Traffic Channel) tx/rx and pause diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 637f42485dba6..2e4f2f3175e55 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -592,6 +592,9 @@ enum { #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) #define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) +/* Driver can send HWC periodically to query stats */ +#define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21) + #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ @@ -601,7 +604,8 @@ enum { GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \ GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \ GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \ - GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE) + GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ + GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 265f2d90027d6..7e946239effa9 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -480,6 +480,10 @@ struct mana_context { struct mana_eq *eqs; struct dentry *mana_eqs_debugfs; + /* Workqueue for querying hardware stats */ + struct delayed_work gf_stats_work; + bool hwc_timeout_occurred; + struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; /* Link state change work */ @@ -582,7 +586,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); -void mana_query_gf_stats(struct mana_context *ac); +int mana_query_gf_stats(struct mana_context *ac); int mana_query_link_cfg(struct mana_port_context *apc); int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, int enable_clamping); From 577441de198339d762b98b28c3c68dc4ade553e4 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Mon, 20 Apr 2026 05:47:38 -0700 Subject: [PATCH 0885/1518] net: mana: Don't overwrite port probe error with add_adev result [ Upstream commit a7fdaf069bd031fcc234581fa6a580be11bf2175 ] In mana_probe(), if mana_probe_port() fails for any port, the error is stored in 'err' and the loop breaks. However, the subsequent unconditional 'err = add_adev(gd, "eth")' overwrites this error. If add_adev() succeeds, mana_probe() returns success despite ports being left in a partially initialized state (ac->ports[i] == NULL). Only call add_adev() when there is no prior error, so the probe correctly fails and triggers mana_remove() cleanup. Fixes: a69839d4327d ("net: mana: Add support for auxiliary device") Signed-off-by: Erni Sri Satya Vennela Link: https://patch.msgid.link/20260420124741.1056179-5-ernis@linux.microsoft.com Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index b0d411ab1067f..02090edbd103f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3548,10 +3548,9 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!resuming) { for (i = 0; i < ac->num_ports; i++) { err = mana_probe_port(ac, i, &ac->ports[i]); - /* we log the port for which the probe failed and stop - * probes for subsequent ports. - * Note that we keep running ports, for which the probes - * were successful, unless add_adev fails too + /* Log the port for which the probe failed, stop probing + * subsequent ports, and skip add_adev. + * mana_remove() will clean up already-probed ports. */ if (err) { dev_err(dev, "Probe Failed for port %d\n", i); @@ -3563,10 +3562,9 @@ int mana_probe(struct gdma_dev *gd, bool resuming) rtnl_lock(); err = mana_attach(ac->ports[i]); rtnl_unlock(); - /* we log the port for which the attach failed and stop - * attach for subsequent ports - * Note that we keep running ports, for which the attach - * were successful, unless add_adev fails too + /* Log the port for which the attach failed, stop + * attaching subsequent ports, and skip add_adev. + * mana_remove() will clean up already-attached ports. */ if (err) { dev_err(dev, "Attach Failed for port %d\n", i); @@ -3575,7 +3573,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } } - err = add_adev(gd, "eth"); + if (!err) + err = add_adev(gd, "eth"); INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); From e0596009873e1137949cd87b84b38f97fb0177d8 Mon Sep 17 00:00:00 2001 From: Aditya Garg Date: Tue, 18 Nov 2025 03:11:08 -0800 Subject: [PATCH 0886/1518] net: mana: Handle SKB if TX SGEs exceed hardware limit [ Upstream commit 934fa943b53795339486cc0026b3ab7ad39dc600 ] The MANA hardware supports a maximum of 30 scatter-gather entries (SGEs) per TX WQE. Exceeding this limit can cause TX failures. Add ndo_features_check() callback to validate SKB layout before transmission. For GSO SKBs that would exceed the hardware SGE limit, clear NETIF_F_GSO_MASK to enforce software segmentation in the stack. Add a fallback in mana_start_xmit() to linearize non-GSO SKBs that still exceed the SGE limit. Also, Add ethtool counter for SKBs linearized Co-developed-by: Dipayaan Roy Signed-off-by: Dipayaan Roy Signed-off-by: Aditya Garg Reviewed-by: Eric Dumazet Reviewed-by: Haiyang Zhang Link: https://patch.msgid.link/1763464269-10431-2-git-send-email-gargaditya@linux.microsoft.com Signed-off-by: Jakub Kicinski Stable-dep-of: 65267c9c4f28 ("net: mana: Fix EQ leak in mana_remove on NULL port") Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 40 ++++++++++++++++++- .../ethernet/microsoft/mana/mana_ethtool.c | 2 + include/net/mana/gdma.h | 8 +++- include/net/mana/mana.h | 1 + 4 files changed, 48 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 02090edbd103f..b9cab61d0afe2 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -329,6 +330,21 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) cq = &apc->tx_qp[txq_idx].tx_cq; tx_stats = &txq->stats; + BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES); + if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES && + skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) { + /* GSO skb with Hardware SGE limit exceeded is not expected here + * as they are handled in mana_features_check() callback + */ + if (skb_linearize(skb)) { + netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n", + skb_shinfo(skb)->nr_frags, + skb_is_gso(skb)); + goto tx_drop_count; + } + apc->eth_stats.tx_linear_pkt_cnt++; + } + pkg.tx_oob.s_oob.vcq_num = cq->gdma_id; pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame; @@ -442,8 +458,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) } } - WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); - if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array; } else { @@ -518,6 +532,25 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES) +static netdev_features_t mana_features_check(struct sk_buff *skb, + struct net_device *ndev, + netdev_features_t features) +{ + if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) { + /* Exceeds HW SGE limit. + * GSO case: + * Disable GSO so the stack will software-segment the skb + * into smaller skbs that fit the SGE budget. + * Non-GSO case: + * The xmit path will attempt skb_linearize() as a fallback. + */ + features &= ~NETIF_F_GSO_MASK; + } + return features; +} +#endif + static void mana_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *st) { @@ -890,6 +923,9 @@ static const struct net_device_ops mana_devops = { .ndo_open = mana_open, .ndo_stop = mana_close, .ndo_select_queue = mana_select_queue, +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES) + .ndo_features_check = mana_features_check, +#endif .ndo_start_xmit = mana_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_get_stats64 = mana_get_stats64, diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 99e8112086833..0e2f4343ac67f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -18,6 +18,8 @@ static const struct mana_stats_desc mana_eth_stats[] = { {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, + {"tx_linear_pkt_cnt", offsetof(struct mana_ethtool_stats, + tx_linear_pkt_cnt)}, {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, rx_coalesced_err)}, {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 2e4f2f3175e55..a4cf307859f85 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -486,6 +486,8 @@ struct gdma_wqe { #define INLINE_OOB_SMALL_SIZE 8 #define INLINE_OOB_LARGE_SIZE 24 +#define MANA_MAX_TX_WQE_SGL_ENTRIES 30 + #define MAX_TX_WQE_SIZE 512 #define MAX_RX_WQE_SIZE 256 @@ -592,6 +594,9 @@ enum { #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) #define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) +/* Driver supports linearizing the skb when num_sge exceeds hardware limit */ +#define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20) + /* Driver can send HWC periodically to query stats */ #define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21) @@ -605,7 +610,8 @@ enum { GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \ GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \ GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ - GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY) + GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \ + GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 7e946239effa9..9fadff78568ea 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -377,6 +377,7 @@ struct mana_ethtool_stats { u64 wake_queue; u64 tx_cqe_err; u64 tx_cqe_unknown_type; + u64 tx_linear_pkt_cnt; u64 rx_coalesced_err; u64 rx_cqe_unknown_type; }; From 2c345eb03d2f9e3d3397d0761ea4f40c6da5f546 Mon Sep 17 00:00:00 2001 From: Long Li Date: Wed, 26 Nov 2025 13:45:52 -0800 Subject: [PATCH 0887/1518] net: mana: Handle hardware recovery events when probing the device [ Upstream commit 9bf66036d686b9a67000ba22bd94be13a4ea79ac ] When MANA is being probed, it's possible that hardware is in recovery mode and the device may get GDMA_EQE_HWC_RESET_REQUEST over HWC in the middle of the probe. Detect such condition and go through the recovery service procedure. Signed-off-by: Long Li Reviewed-by: Haiyang Zhang Link: https://patch.msgid.link/1764193552-9712-1-git-send-email-longli@linux.microsoft.com Signed-off-by: Jakub Kicinski Stable-dep-of: 65267c9c4f28 ("net: mana: Fix EQ leak in mana_remove on NULL port") Signed-off-by: Sasha Levin --- .../net/ethernet/microsoft/mana/gdma_main.c | 176 ++++++++++++++++-- include/net/mana/gdma.h | 12 +- 2 files changed, 170 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index d93cfb7f4e788..0ad082b566f5e 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -15,6 +15,20 @@ struct dentry *mana_debugfs_root; +struct mana_dev_recovery { + struct list_head list; + struct pci_dev *pdev; + enum gdma_eqe_type type; +}; + +static struct mana_dev_recovery_work { + struct list_head dev_list; + struct delayed_work work; + + /* Lock for dev_list above */ + spinlock_t lock; +} mana_dev_recovery_work; + static u32 mana_gd_r32(struct gdma_context *g, u64 offset) { return readl(g->bar0_va + offset); @@ -387,6 +401,25 @@ EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA"); #define MANA_SERVICE_PERIOD 10 +static void mana_serv_rescan(struct pci_dev *pdev) +{ + struct pci_bus *parent; + + pci_lock_rescan_remove(); + + parent = pdev->bus; + if (!parent) { + dev_err(&pdev->dev, "MANA service: no parent bus\n"); + goto out; + } + + pci_stop_and_remove_bus_device(pdev); + pci_rescan_bus(parent); + +out: + pci_unlock_rescan_remove(); +} + static void mana_serv_fpga(struct pci_dev *pdev) { struct pci_bus *bus, *parent; @@ -419,9 +452,12 @@ static void mana_serv_reset(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); struct hw_channel_context *hwc; + int ret; if (!gc) { - dev_err(&pdev->dev, "MANA service: no GC\n"); + /* Perform PCI rescan on device if GC is not set up */ + dev_err(&pdev->dev, "MANA service: GC not setup, rescanning\n"); + mana_serv_rescan(pdev); return; } @@ -440,9 +476,18 @@ static void mana_serv_reset(struct pci_dev *pdev) msleep(MANA_SERVICE_PERIOD * 1000); - mana_gd_resume(pdev); + ret = mana_gd_resume(pdev); + if (ret == -ETIMEDOUT || ret == -EPROTO) { + /* Perform PCI rescan on device if we failed on HWC */ + dev_err(&pdev->dev, "MANA service: resume failed, rescanning\n"); + mana_serv_rescan(pdev); + goto out; + } - dev_info(&pdev->dev, "MANA reset cycle completed\n"); + if (ret) + dev_info(&pdev->dev, "MANA reset cycle failed err %d\n", ret); + else + dev_info(&pdev->dev, "MANA reset cycle completed\n"); out: gc->in_service = false; @@ -454,18 +499,9 @@ struct mana_serv_work { enum gdma_eqe_type type; }; -static void mana_serv_func(struct work_struct *w) +static void mana_do_service(enum gdma_eqe_type type, struct pci_dev *pdev) { - struct mana_serv_work *mns_wk; - struct pci_dev *pdev; - - mns_wk = container_of(w, struct mana_serv_work, serv_work); - pdev = mns_wk->pdev; - - if (!pdev) - goto out; - - switch (mns_wk->type) { + switch (type) { case GDMA_EQE_HWC_FPGA_RECONFIG: mana_serv_fpga(pdev); break; @@ -475,12 +511,48 @@ static void mana_serv_func(struct work_struct *w) break; default: - dev_err(&pdev->dev, "MANA service: unknown type %d\n", - mns_wk->type); + dev_err(&pdev->dev, "MANA service: unknown type %d\n", type); break; } +} + +static void mana_recovery_delayed_func(struct work_struct *w) +{ + struct mana_dev_recovery_work *work; + struct mana_dev_recovery *dev; + unsigned long flags; + + work = container_of(w, struct mana_dev_recovery_work, work.work); + + spin_lock_irqsave(&work->lock, flags); + + while (!list_empty(&work->dev_list)) { + dev = list_first_entry(&work->dev_list, + struct mana_dev_recovery, list); + list_del(&dev->list); + spin_unlock_irqrestore(&work->lock, flags); + + mana_do_service(dev->type, dev->pdev); + pci_dev_put(dev->pdev); + kfree(dev); + + spin_lock_irqsave(&work->lock, flags); + } + + spin_unlock_irqrestore(&work->lock, flags); +} + +static void mana_serv_func(struct work_struct *w) +{ + struct mana_serv_work *mns_wk; + struct pci_dev *pdev; + + mns_wk = container_of(w, struct mana_serv_work, serv_work); + pdev = mns_wk->pdev; + + if (pdev) + mana_do_service(mns_wk->type, pdev); -out: pci_dev_put(pdev); kfree(mns_wk); module_put(THIS_MODULE); @@ -541,6 +613,17 @@ static void mana_gd_process_eqe(struct gdma_queue *eq) case GDMA_EQE_HWC_RESET_REQUEST: dev_info(gc->dev, "Recv MANA service type:%d\n", type); + if (!test_and_set_bit(GC_PROBE_SUCCEEDED, &gc->flags)) { + /* + * Device is in probe and we received a hardware reset + * event, the probe function will detect that the flag + * has changed and perform service procedure. + */ + dev_info(gc->dev, + "Service is to be processed in probe\n"); + break; + } + if (gc->in_service) { dev_info(gc->dev, "Already in service\n"); break; @@ -1943,8 +2026,19 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto cleanup_mana; + /* + * If a hardware reset event has occurred over HWC during probe, + * rollback and perform hardware reset procedure. + */ + if (test_and_set_bit(GC_PROBE_SUCCEEDED, &gc->flags)) { + err = -EPROTO; + goto cleanup_mana_rdma; + } + return 0; +cleanup_mana_rdma: + mana_rdma_remove(&gc->mana_ib); cleanup_mana: mana_remove(&gc->mana, false); cleanup_gd: @@ -1968,6 +2062,35 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) disable_dev: pci_disable_device(pdev); dev_err(&pdev->dev, "gdma probe failed: err = %d\n", err); + + /* + * Hardware could be in recovery mode and the HWC returns TIMEDOUT or + * EPROTO from mana_gd_setup(), mana_probe() or mana_rdma_probe(), or + * we received a hardware reset event over HWC interrupt. In this case, + * perform the device recovery procedure after MANA_SERVICE_PERIOD + * seconds. + */ + if (err == -ETIMEDOUT || err == -EPROTO) { + struct mana_dev_recovery *dev; + unsigned long flags; + + dev_info(&pdev->dev, "Start MANA recovery mode\n"); + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return err; + + dev->pdev = pci_dev_get(pdev); + dev->type = GDMA_EQE_HWC_RESET_REQUEST; + + spin_lock_irqsave(&mana_dev_recovery_work.lock, flags); + list_add_tail(&dev->list, &mana_dev_recovery_work.dev_list); + spin_unlock_irqrestore(&mana_dev_recovery_work.lock, flags); + + schedule_delayed_work(&mana_dev_recovery_work.work, + secs_to_jiffies(MANA_SERVICE_PERIOD)); + } + return err; } @@ -2072,6 +2195,10 @@ static int __init mana_driver_init(void) { int err; + INIT_LIST_HEAD(&mana_dev_recovery_work.dev_list); + spin_lock_init(&mana_dev_recovery_work.lock); + INIT_DELAYED_WORK(&mana_dev_recovery_work.work, mana_recovery_delayed_func); + mana_debugfs_root = debugfs_create_dir("mana", NULL); err = pci_register_driver(&mana_driver); @@ -2085,6 +2212,21 @@ static int __init mana_driver_init(void) static void __exit mana_driver_exit(void) { + struct mana_dev_recovery *dev; + unsigned long flags; + + disable_delayed_work_sync(&mana_dev_recovery_work.work); + + spin_lock_irqsave(&mana_dev_recovery_work.lock, flags); + while (!list_empty(&mana_dev_recovery_work.dev_list)) { + dev = list_first_entry(&mana_dev_recovery_work.dev_list, + struct mana_dev_recovery, list); + list_del(&dev->list); + pci_dev_put(dev->pdev); + kfree(dev); + } + spin_unlock_irqrestore(&mana_dev_recovery_work.lock, flags); + pci_unregister_driver(&mana_driver); debugfs_remove(mana_debugfs_root); diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index a4cf307859f85..eaa27483f99b2 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -382,6 +382,10 @@ struct gdma_irq_context { char name[MANA_IRQ_NAME_SZ]; }; +enum gdma_context_flags { + GC_PROBE_SUCCEEDED = 0, +}; + struct gdma_context { struct device *dev; struct dentry *mana_pci_debugfs; @@ -430,6 +434,8 @@ struct gdma_context { u64 pf_cap_flags1; struct workqueue_struct *service_wq; + + unsigned long flags; }; static inline bool mana_gd_is_mana(struct gdma_dev *gd) @@ -600,6 +606,9 @@ enum { /* Driver can send HWC periodically to query stats */ #define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21) +/* Driver can handle hardware recovery events during probe */ +#define GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY BIT(22) + #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ @@ -611,7 +620,8 @@ enum { GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \ GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \ - GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE) + GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \ + GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY) #define GDMA_DRV_CAP_FLAGS2 0 From fb9f98e1041a30dd5766620a2a64cb472b54caa9 Mon Sep 17 00:00:00 2001 From: Dipayaan Roy Date: Mon, 12 Jan 2026 05:05:52 -0800 Subject: [PATCH 0888/1518] net: mana: Implement ndo_tx_timeout and serialize queue resets per port. [ Upstream commit 3b194343c25084a8d2fa0c0f2c9e80f3080fd732 ] Implement .ndo_tx_timeout for MANA so any stalled TX queue can be detected and a device-controlled port reset for all queues can be scheduled to a ordered workqueue. The reset for all queues on stall detection is recomended by hardware team. Reviewed-by: Pavan Chebbi Reviewed-by: Haiyang Zhang Signed-off-by: Dipayaan Roy Link: https://patch.msgid.link/20260112130552.GA11785@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net Signed-off-by: Jakub Kicinski Stable-dep-of: 65267c9c4f28 ("net: mana: Fix EQ leak in mana_remove on NULL port") Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 77 ++++++++++++++++++- include/net/mana/gdma.h | 7 +- include/net/mana/mana.h | 3 +- 3 files changed, 84 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index b9cab61d0afe2..12952f7273eb6 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -299,6 +299,39 @@ static int mana_get_gso_hs(struct sk_buff *skb) return gso_hs; } +static void mana_per_port_queue_reset_work_handler(struct work_struct *work) +{ + struct mana_port_context *apc = container_of(work, + struct mana_port_context, + queue_reset_work); + struct net_device *ndev = apc->ndev; + int err; + + rtnl_lock(); + + /* Pre-allocate buffers to prevent failure in mana_attach later */ + err = mana_pre_alloc_rxbufs(apc, ndev->mtu, apc->num_queues); + if (err) { + netdev_err(ndev, "Insufficient memory for reset post tx stall detection\n"); + goto out; + } + + err = mana_detach(ndev, false); + if (err) { + netdev_err(ndev, "mana_detach failed: %d\n", err); + goto dealloc_pre_rxbufs; + } + + err = mana_attach(ndev); + if (err) + netdev_err(ndev, "mana_attach failed: %d\n", err); + +dealloc_pre_rxbufs: + mana_pre_dealloc_rxbufs(apc); +out: + rtnl_unlock(); +} + netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) { enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT; @@ -847,6 +880,23 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu) return err; } +static void mana_tx_timeout(struct net_device *netdev, unsigned int txqueue) +{ + struct mana_port_context *apc = netdev_priv(netdev); + struct mana_context *ac = apc->ac; + struct gdma_context *gc = ac->gdma_dev->gdma_context; + + /* Already in service, hence tx queue reset is not required.*/ + if (gc->in_service) + return; + + /* Note: If there are pending queue reset work for this port(apc), + * subsequent request queued up from here are ignored. This is because + * we are using the same work instance per port(apc). + */ + queue_work(ac->per_port_queue_reset_wq, &apc->queue_reset_work); +} + static int mana_shaper_set(struct net_shaper_binding *binding, const struct net_shaper *shaper, struct netlink_ext_ack *extack) @@ -932,6 +982,7 @@ static const struct net_device_ops mana_devops = { .ndo_bpf = mana_bpf, .ndo_xdp_xmit = mana_xdp_xmit, .ndo_change_mtu = mana_change_mtu, + .ndo_tx_timeout = mana_tx_timeout, .net_shaper_ops = &mana_shaper_ops, }; @@ -3319,6 +3370,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->min_mtu = ETH_MIN_MTU; ndev->needed_headroom = MANA_HEADROOM; ndev->dev_port = port_idx; + /* Recommended timeout based on HW FPGA re-config scenario. */ + ndev->watchdog_timeo = 15 * HZ; SET_NETDEV_DEV(ndev, gc->dev); netif_set_tso_max_size(ndev, GSO_MAX_SIZE); @@ -3335,6 +3388,10 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, if (err) goto reset_apc; + /* Initialize the per port queue reset work.*/ + INIT_WORK(&apc->queue_reset_work, + mana_per_port_queue_reset_work_handler); + netdev_lockdep_set_classes(ndev); ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; @@ -3524,6 +3581,7 @@ int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; struct mana_context *ac = gd->driver_data; + struct mana_port_context *apc = NULL; struct device *dev = gc->dev; u8 bm_hostmode = 0; u16 num_ports = 0; @@ -3581,6 +3639,14 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (ac->num_ports > MAX_PORTS_IN_MANA_DEV) ac->num_ports = MAX_PORTS_IN_MANA_DEV; + ac->per_port_queue_reset_wq = + create_singlethread_workqueue("mana_per_port_queue_reset_wq"); + if (!ac->per_port_queue_reset_wq) { + dev_err(dev, "Failed to allocate per port queue reset workqueue\n"); + err = -ENOMEM; + goto out; + } + if (!resuming) { for (i = 0; i < ac->num_ports; i++) { err = mana_probe_port(ac, i, &ac->ports[i]); @@ -3596,6 +3662,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } else { for (i = 0; i < ac->num_ports; i++) { rtnl_lock(); + apc = netdev_priv(ac->ports[i]); + enable_work(&apc->queue_reset_work); err = mana_attach(ac->ports[i]); rtnl_unlock(); /* Log the port for which the attach failed, stop @@ -3652,13 +3720,15 @@ void mana_remove(struct gdma_dev *gd, bool suspending) for (i = 0; i < ac->num_ports; i++) { ndev = ac->ports[i]; - apc = netdev_priv(ndev); if (!ndev) { if (i == 0) dev_err(dev, "No net device to remove\n"); goto out; } + apc = netdev_priv(ndev); + disable_work_sync(&apc->queue_reset_work); + /* All cleanup actions should stay after rtnl_lock(), otherwise * other functions may access partially cleaned up data. */ @@ -3685,6 +3755,11 @@ void mana_remove(struct gdma_dev *gd, bool suspending) mana_destroy_eq(ac); out: + if (ac->per_port_queue_reset_wq) { + destroy_workqueue(ac->per_port_queue_reset_wq); + ac->per_port_queue_reset_wq = NULL; + } + mana_gd_deregister_device(gd); if (suspending) diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index eaa27483f99b2..a59bd4035a992 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -598,6 +598,10 @@ enum { /* Driver can self reset on FPGA Reconfig EQE notification */ #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) + +/* Driver detects stalled send queues and recovers them */ +#define GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY BIT(18) + #define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) /* Driver supports linearizing the skb when num_sge exceeds hardware limit */ @@ -621,7 +625,8 @@ enum { GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \ GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \ - GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY) + GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \ + GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 9fadff78568ea..e199f1d44c8e3 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -480,7 +480,7 @@ struct mana_context { struct mana_ethtool_hc_stats hc_stats; struct mana_eq *eqs; struct dentry *mana_eqs_debugfs; - + struct workqueue_struct *per_port_queue_reset_wq; /* Workqueue for querying hardware stats */ struct delayed_work gf_stats_work; bool hwc_timeout_occurred; @@ -495,6 +495,7 @@ struct mana_context { struct mana_port_context { struct mana_context *ac; struct net_device *ndev; + struct work_struct queue_reset_work; u8 mac_addr[ETH_ALEN]; From c60545ffb9203f3adac5af0b1e75d9c3df468c69 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Mon, 20 Apr 2026 05:47:39 -0700 Subject: [PATCH 0889/1518] net: mana: Fix EQ leak in mana_remove on NULL port [ Upstream commit 65267c9c4f28199985505977bc2c628c82fc50ef ] In mana_remove(), when a NULL port is encountered in the port iteration loop, 'goto out' skips the mana_destroy_eq(ac) call, leaking the event queues allocated earlier by mana_create_eq(). This can happen when mana_probe_port() fails for port 0, leaving ac->ports[0] as NULL. On driver unload or error cleanup, mana_remove() hits the NULL entry and jumps past mana_destroy_eq(). Change 'goto out' to 'break' so the for-loop exits normally and mana_destroy_eq() is always reached. Remove the now-unreferenced out: label. Fixes: 1e2d0824a9c3 ("net: mana: Add support for EQ sharing") Signed-off-by: Erni Sri Satya Vennela Link: https://patch.msgid.link/20260420124741.1056179-6-ernis@linux.microsoft.com Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 12952f7273eb6..4b7e5acba7f76 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3723,7 +3723,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) if (!ndev) { if (i == 0) dev_err(dev, "No net device to remove\n"); - goto out; + break; } apc = netdev_priv(ndev); @@ -3754,7 +3754,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) } mana_destroy_eq(ac); -out: + if (ac->per_port_queue_reset_wq) { destroy_workqueue(ac->per_port_queue_reset_wq); ac->per_port_queue_reset_wq = NULL; From 6af1736b5810bc8a4a43a8518530113f5a757dc1 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 20 Apr 2026 15:20:51 +0200 Subject: [PATCH 0890/1518] vsock/virtio: fix MSG_ZEROCOPY pinned-pages accounting [ Upstream commit 1cb36e252211506f51095fe7ced8286cc77b4c80 ] virtio_transport_init_zcopy_skb() uses iter->count as the size argument for msg_zerocopy_realloc(), which in turn passes it to mm_account_pinned_pages() for RLIMIT_MEMLOCK accounting. However, this function is called after virtio_transport_fill_skb() has already consumed the iterator via __zerocopy_sg_from_iter(), so on the last skb, iter->count will be 0, skipping the RLIMIT_MEMLOCK enforcement. Pass pkt_len (the total bytes being sent) as an explicit parameter to virtio_transport_init_zcopy_skb() instead of reading the already-consumed iter->count. This matches TCP and UDP, which both call msg_zerocopy_realloc() with the original message size. Fixes: 581512a6dc93 ("vsock/virtio: MSG_ZEROCOPY flag support") Reported-by: Yiming Qian Signed-off-by: Stefano Garzarella Reviewed-by: Bobby Eshleman Link: https://patch.msgid.link/20260420132051.217589-1-sgarzare@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/vmw_vsock/virtio_transport_common.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 41be06c4bd7ff..495c93cddcdc0 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -75,6 +75,7 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk, struct sk_buff *skb, struct msghdr *msg, + size_t pkt_len, bool zerocopy) { struct ubuf_info *uarg; @@ -83,12 +84,10 @@ static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk, uarg = msg->msg_ubuf; net_zcopy_get(uarg); } else { - struct iov_iter *iter = &msg->msg_iter; struct ubuf_info_msgzc *uarg_zc; uarg = msg_zerocopy_realloc(sk_vsock(vsk), - iter->count, - NULL, false); + pkt_len, NULL, false); if (!uarg) return -1; @@ -385,11 +384,17 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, * each iteration. If this is last skb for this buffer * and MSG_ZEROCOPY mode is in use - we must allocate * completion for the current syscall. + * + * Pass pkt_len because msg iter is already consumed + * by virtio_transport_fill_skb(), so iter->count + * can not be used for RLIMIT_MEMLOCK pinned-pages + * accounting done by msg_zerocopy_realloc(). */ if (info->msg && info->msg->msg_flags & MSG_ZEROCOPY && skb_len == rest_len && info->op == VIRTIO_VSOCK_OP_RW) { if (virtio_transport_init_zcopy_skb(vsk, skb, info->msg, + pkt_len, can_zcopy)) { kfree_skb(skb); ret = -ENOMEM; From 1abf8c202cafc37aecb1db7c5b19b1240f934520 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Thu, 16 Apr 2026 14:21:21 -0700 Subject: [PATCH 0891/1518] virtio_net: sync rss_trailer.max_tx_vq on queue_pairs change via VQ_PAIRS_SET [ Upstream commit 3bc06da858ef17cfe94b49efc0d9713727012835 ] When netif_is_rxfh_configured() is true (i.e., the user has explicitly configured the RSS indirection table), virtnet_set_queues() skips the RSS update path and falls through to the VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET command to change the number of queue pairs. However, it does not update vi->rss_trailer.max_tx_vq to reflect the new queue_pairs value. This causes a mismatch between vi->curr_queue_pairs and vi->rss_trailer.max_tx_vq. Any subsequent RSS reconfiguration (e.g., via ethtool -X) calls virtnet_commit_rss_command(), which sends the stale max_tx_vq to the device, silently reverting the queue count. Reproduction: 1. User configured RSS ethtool -X eth0 equal 8 2. VQ_PAIRS_SET path; max_tx_vq stays 16 ethtool -L eth0 combined 12 3. RSS commit uses max_tx_vq=16 instead of 12 ethtool -X eth0 equal 4 Fix this by updating vi->rss_trailer.max_tx_vq after a successful VQ_PAIRS_SET command when RSS is enabled, keeping it in sync with curr_queue_pairs. Fixes: 50bfcaedd78e ("virtio_net: Update rss when set queue") Signed-off-by: Brett Creeley Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260416212121.29073-1-brett.creeley@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0cfe7ab59412c..aed65dbf3fca0 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3828,6 +3828,12 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) queue_pairs); return -EINVAL; } + + /* Keep max_tx_vq in sync so that a later RSS command does not + * revert queue_pairs to a stale value. + */ + if (vi->has_rss) + vi->rss_trailer.max_tx_vq = cpu_to_le16(queue_pairs); succ: vi->curr_queue_pairs = queue_pairs; if (dev->flags & IFF_UP) { From b5992dbb3bc521bd5bc16aa8144471b2f43cc68f Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Wed, 22 Apr 2026 16:05:36 +0000 Subject: [PATCH 0892/1518] nfp: fix swapped arguments in nfp_encode_basic_qdr() calls [ Upstream commit 4078c5611d7585548b249377ebd60c272e410490 ] There is a mismatch between the passed arguments and the actual nfp_encode_basic_qdr() function parameter names: static int nfp_encode_basic_qdr(u64 addr, int dest_island, int cpp_tgt, int mode, bool addr40, int isld1, int isld0) { ... But "dest_island" and "cpp_tgt" are swapped at every call-site. For example: return nfp_encode_basic_qdr(*addr, cpp_tgt, dest_island, mode, addr40, isld1, isld0); As a result, nfp_encode_basic_qdr() receives "dest_island" as CPP target type, which is always NFP_CPP_TARGET_QDR(2) for these calls, and "cpp_tgt" as the destination island ID, which can accidentally match or be outside the valid NFP_CPP_TARGET_* types (e.g. '-1' for any destination). Since code already worked for years, also add extra pr_warn() to error paths in nfp_encode_basic_qdr() to help identify any potential address verification failures. Detected using the static analysis tool - Svace. Fixes: 4cb584e0ee7d ("nfp: add CPP access core") Signed-off-by: Alexey Kodanev Link: https://patch.msgid.link/20260422160536.61855-1-aleksei.kodanev@bell-sw.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../ethernet/netronome/nfp/nfpcore/nfp_target.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c index 79470f198a62a..9cf19446657c6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c @@ -435,12 +435,17 @@ static int nfp_encode_basic_qdr(u64 addr, int dest_island, int cpp_tgt, /* Full Island ID and channel bits overlap? */ ret = nfp_decode_basic(addr, &v, cpp_tgt, mode, addr40, isld1, isld0); - if (ret) + if (ret) { + pr_warn("%s: decode dest_island failed: %d\n", __func__, ret); return ret; + } /* The current address won't go where expected? */ - if (dest_island != -1 && dest_island != v) + if (dest_island != -1 && dest_island != v) { + pr_warn("%s: dest_island mismatch: current (%d) != decoded (%d)\n", + __func__, dest_island, v); return -EINVAL; + } /* If dest_island was -1, we don't care where it goes. */ return 0; @@ -493,7 +498,7 @@ static int nfp_encode_basic(u64 *addr, int dest_island, int cpp_tgt, * the address but we can verify if the existing * contents will point to a valid island. */ - return nfp_encode_basic_qdr(*addr, cpp_tgt, dest_island, + return nfp_encode_basic_qdr(*addr, dest_island, cpp_tgt, mode, addr40, isld1, isld0); iid_lsb = addr40 ? 34 : 26; @@ -504,7 +509,7 @@ static int nfp_encode_basic(u64 *addr, int dest_island, int cpp_tgt, return 0; case 1: if (cpp_tgt == NFP_CPP_TARGET_QDR && !addr40) - return nfp_encode_basic_qdr(*addr, cpp_tgt, dest_island, + return nfp_encode_basic_qdr(*addr, dest_island, cpp_tgt, mode, addr40, isld1, isld0); idx_lsb = addr40 ? 39 : 31; @@ -530,7 +535,7 @@ static int nfp_encode_basic(u64 *addr, int dest_island, int cpp_tgt, * be set before hand and with them select an island. * So we need to confirm that it's at least plausible. */ - return nfp_encode_basic_qdr(*addr, cpp_tgt, dest_island, + return nfp_encode_basic_qdr(*addr, dest_island, cpp_tgt, mode, addr40, isld1, isld0); /* Make sure we compare against isldN values @@ -551,7 +556,7 @@ static int nfp_encode_basic(u64 *addr, int dest_island, int cpp_tgt, * iid<1> = addr<30> = channel<0> * channel<1> = addr<31> = Index */ - return nfp_encode_basic_qdr(*addr, cpp_tgt, dest_island, + return nfp_encode_basic_qdr(*addr, dest_island, cpp_tgt, mode, addr40, isld1, isld0); isld[0] &= ~3; From 671f743d2dd50a36b33f485ac2a745f0ecde3d72 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Wed, 22 Apr 2026 20:35:38 +0800 Subject: [PATCH 0893/1518] tcp: send a challenge ACK on SEG.ACK > SND.NXT [ Upstream commit 42726ec644cbdde0035c3e0417fee8ed9547e120 ] RFC 5961 Section 5.2 validates an incoming segment's ACK value against the range [SND.UNA - MAX.SND.WND, SND.NXT] and states: "All incoming segments whose ACK value doesn't satisfy the above condition MUST be discarded and an ACK sent back." Commit 354e4aa391ed ("tcp: RFC 5961 5.2 Blind Data Injection Attack Mitigation") opted Linux into this mitigation and implements the challenge ACK on the lower side (SEG.ACK < SND.UNA - MAX.SND.WND), but the symmetric upper side (SEG.ACK > SND.NXT) still takes the pre-RFC-5961 path and silently returns SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, even though RFC 793 Section 3.9 (now RFC 9293 Section 3.10.7.4) has always required: "If the ACK acknowledges something not yet sent (SEG.ACK > SND.NXT) then send an ACK, drop the segment, and return." Complete the mitigation by sending a challenge ACK on that branch, reusing the existing tcp_send_challenge_ack() path which already enforces the per-socket RFC 5961 Section 7 rate limit via __tcp_oow_rate_limited(). FLAG_NO_CHALLENGE_ACK is honoured for symmetry with the lower-edge case. Update the existing tcp_ts_recent_invalid_ack.pkt selftest, which drives this exact path, to consume the new challenge ACK. Fixes: 354e4aa391ed ("tcp: RFC 5961 5.2 Blind Data Injection Attack Mitigation") Signed-off-by: Jiayuan Chen Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260422123605.320000-2-jiayuan.chen@linux.dev Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_input.c | 10 +++++++--- .../net/packetdrill/tcp_ts_recent_invalid_ack.pkt | 4 +++- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5fb5f3f6393c1..b5cf32a56c04a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4025,11 +4025,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) goto old_ack; } - /* If the ack includes data we haven't sent yet, discard - * this segment (RFC793 Section 3.9). + /* If the ack includes data we haven't sent yet, drop the + * segment. RFC 793 Section 3.9 and RFC 5961 Section 5.2 + * require us to send an ACK back in that case. */ - if (after(ack, tp->snd_nxt)) + if (after(ack, tp->snd_nxt)) { + if (!(flag & FLAG_NO_CHALLENGE_ACK)) + tcp_send_challenge_ack(sk, false); return -SKB_DROP_REASON_TCP_ACK_UNSENT_DATA; + } if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt index 174ce9a1bfc07..ee6baf7c36cfa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt @@ -19,7 +19,9 @@ // bad packet with high tsval (its ACK sequence is above our sndnxt) +0 < F. 1:1(0) ack 9999 win 20000 - +// Challenge ACK for SEG.ACK > SND.NXT (RFC 5961 5.2 / RFC 793 3.9). +// ecr=200 (not 200000) proves ts_recent was not updated from the bad packet. + +0 > . 1:1(0) ack 1 +0 < . 1:1001(1000) ack 1 win 20000 +0 > . 1:1(0) ack 1001 From 1d5e589055880fae229e229e1929e087dbe08cf3 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 21 Apr 2026 13:45:26 +0100 Subject: [PATCH 0894/1518] tipc: fix double-free in tipc_buf_append() [ Upstream commit d293ca716e7d5dffdaecaf6b9b2f857a33dc3d3a ] tipc_msg_validate() can potentially reallocate the skb it is validating, freeing the old one. In tipc_buf_append(), it was being called with a pointer to a local variable which was a copy of the caller's skb pointer. If the skb was reallocated and validation subsequently failed, the error handling path would free the original skb pointer, which had already been freed, leading to double-free. Fix this by checking if head now points to a newly allocated reassembled skb. If it does, reassign *headbuf for later freeing operations. Fixes: d618d09a68e4 ("tipc: enforce valid ratio between skb truesize and contents") Suggested-by: Tung Nguyen Signed-off-by: Lee Jones Reviewed-by: Tung Nguyen Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/tipc/msg.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 76284fc538ebd..b0bba0feef564 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -177,8 +177,20 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == LAST_FRAGMENT) { TIPC_SKB_CB(head)->validated = 0; - if (unlikely(!tipc_msg_validate(&head))) + + /* If the reassembled skb has been freed in + * tipc_msg_validate() because of an invalid truesize, + * then head will point to a newly allocated reassembled + * skb, while *headbuf points to freed reassembled skb. + * In such cases, correct *headbuf for freeing the newly + * allocated reassembled skb later. + */ + if (unlikely(!tipc_msg_validate(&head))) { + if (head != *headbuf) + *headbuf = head; goto err; + } + *buf = head; TIPC_SKB_CB(head)->tail = NULL; *headbuf = NULL; From 70f788e22693e98957e61e64e9e9b0cfbe57d374 Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Wed, 22 Apr 2026 02:30:24 +0000 Subject: [PATCH 0895/1518] vhost_net: fix sleeping with preempt-disabled in vhost_net_busy_poll() [ Upstream commit e08a9fac5cf8c3fecf4755e7e3ac059f78b8f83d ] syzbot reported "sleeping function called from invalid context" in vhost_net_busy_poll(). Commit 030881372460 ("vhost_net: basic polling support") introduced a busy-poll loop and preempt_{disable,enable}() around it, where each iteration calls a sleepable function inside the loop. The purpose of disabling preemption was to keep local_clock()-based timeout accounting on a single CPU, rather than as a requirement of busy-poll itself: https://lore.kernel.org/1448435489-5949-4-git-send-email-jasowang@redhat.com From this perspective, migrate_disable() is sufficient here, so replace preempt_disable() with migrate_disable(), avoiding sleepable accesses from a preempt-disabled context. Fixes: 030881372460 ("vhost_net: basic polling support") Tested-by: syzbot+6985cb8e543ea90ba8ee@syzkaller.appspotmail.com Reported-by: syzbot+6985cb8e543ea90ba8ee@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/69e6a414.050a0220.24bfd3.002d.GAE@google.com/T/ Signed-off-by: Kohei Enju Acked-by: Michael S. Tsirkin Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/vhost/net.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 1e77c0482b849..e11b46a1c9374 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -562,7 +562,7 @@ static void vhost_net_busy_poll(struct vhost_net *net, busyloop_timeout = poll_rx ? rvq->busyloop_timeout: tvq->busyloop_timeout; - preempt_disable(); + migrate_disable(); endtime = busy_clock() + busyloop_timeout; while (vhost_can_busy_poll(endtime)) { @@ -579,7 +579,7 @@ static void vhost_net_busy_poll(struct vhost_net *net, cpu_relax(); } - preempt_enable(); + migrate_enable(); if (poll_rx || sock_has_rx_data(sock)) vhost_net_busy_poll_try_queue(net, vq); From bd501c86407da75bf7242fc89b71cdb9045e5a18 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 16 Apr 2026 14:54:29 -0700 Subject: [PATCH 0896/1518] nstree: fix func. parameter kernel-doc warnings [ Upstream commit 43eb354ecb471426e97b0ce6a0c922ec20f82027 ] Use the correct parameter name ("__ns") for function parameter kernel-doc to avoid 3 warnings: Warning: include/linux/nstree.h:68 function parameter '__ns' not described in 'ns_tree_add_raw' Warning: include/linux/nstree.h:77 function parameter '__ns' not described in 'ns_tree_add' Warning: include/linux/nstree.h:88 function parameter '__ns' not described in 'ns_tree_remove' Fixes: 885fc8ac0a4d ("nstree: make iterator generic") Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20260416215429.948898-1-rdunlap@infradead.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- include/linux/nstree.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/nstree.h b/include/linux/nstree.h index 8b86366904739..4e2af7a973684 100644 --- a/include/linux/nstree.h +++ b/include/linux/nstree.h @@ -45,7 +45,7 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) /** * ns_tree_add_raw - Add a namespace to a namespace - * @ns: Namespace to add + * @__ns: Namespace to add * * This function adds a namespace to the appropriate namespace tree * without assigning a id. @@ -54,7 +54,7 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) /** * ns_tree_add - Add a namespace to a namespace tree - * @ns: Namespace to add + * @__ns: Namespace to add * * This function assigns a new id to the namespace and adds it to the * appropriate namespace tree and list. @@ -63,7 +63,7 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) /** * ns_tree_remove - Remove a namespace from a namespace tree - * @ns: Namespace to remove + * @__ns: Namespace to remove * * This function removes a namespace from the appropriate namespace * tree and list. From 9348f4763aa9b9e97fb006edc7aabd2aa209e5eb Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 23 Apr 2026 11:56:04 +0200 Subject: [PATCH 0897/1518] eventpoll: use hlist_is_singular_node() in __ep_remove() [ Upstream commit 3d9fd0abc94d8cd430cc7cd7d37ce5e5aae2cd2b ] Replace the open-coded "epi is the only entry in file->f_ep" check with hlist_is_singular_node(). Same semantics, and the helper avoids the head-cacheline access in the common false case. Link: https://patch.msgid.link/20260423-work-epoll-uaf-v1-1-2470f9eec0f5@kernel.org Signed-off-by: Christian Brauner (Amutable) Stable-dep-of: a6dc643c6931 ("eventpoll: fix ep_remove struct eventpoll / struct file UAF") Signed-off-by: Sasha Levin --- fs/eventpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index a8e30414d996c..23602de08fed2 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -856,7 +856,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) to_free = NULL; head = file->f_ep; - if (head->first == &epi->fllink && !epi->fllink.next) { + if (hlist_is_singular_node(&epi->fllink, head)) { /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, NULL); if (!is_file_epoll(file)) { From 416b491cd2890470624a85d90ca53242f1ea68ef Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 23 Apr 2026 11:56:05 +0200 Subject: [PATCH 0898/1518] eventpoll: split __ep_remove() [ Upstream commit 0f7bdfd413000985de09fc39eb9efa1e091a3ce0 ] Split __ep_remove() to delineate file removal from epoll item removal. Suggested-by: Linus Torvalds Link: https://patch.msgid.link/20260423-work-epoll-uaf-v1-2-2470f9eec0f5@kernel.org Signed-off-by: Christian Brauner (Amutable) Stable-dep-of: a6dc643c6931 ("eventpoll: fix ep_remove struct eventpoll / struct file UAF") Signed-off-by: Sasha Levin --- fs/eventpoll.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 23602de08fed2..36f3545a71bfa 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -826,6 +826,9 @@ static void ep_free(struct eventpoll *ep) kfree_rcu(ep, rcu); } +static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file); +static bool __ep_remove_epi(struct eventpoll *ep, struct epitem *epi); + /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. @@ -837,8 +840,6 @@ static void ep_free(struct eventpoll *ep) static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; - struct epitems_head *to_free; - struct hlist_head *head; lockdep_assert_irqs_enabled(); @@ -854,8 +855,21 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) return false; } - to_free = NULL; - head = file->f_ep; + __ep_remove_file(ep, epi, file); + return __ep_remove_epi(ep, epi); +} + +/* + * Called with &file->f_lock held, + * returns with it released + */ +static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file) +{ + struct epitems_head *to_free = NULL; + struct hlist_head *head = file->f_ep; + + lockdep_assert_held(&ep->mtx); + if (hlist_is_singular_node(&epi->fllink, head)) { /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, NULL); @@ -869,6 +883,11 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); +} + +static bool __ep_remove_epi(struct eventpoll *ep, struct epitem *epi) +{ + lockdep_assert_held(&ep->mtx); rb_erase_cached(&epi->rbn, &ep->rbr); From e084713397a415afa4166994d5af5afea20c2ef4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 23 Apr 2026 11:56:06 +0200 Subject: [PATCH 0899/1518] eventpoll: kill __ep_remove() [ Upstream commit e9e5cd40d7c403e19f21d0f7b8b8ba3a76b58330 ] Remove the boolean conditional in __ep_remove() and restructure the code so the check for racing with eventpoll_release_file() are only done in the ep_remove_safe() path where they belong. Link: https://patch.msgid.link/20260423-work-epoll-uaf-v1-3-2470f9eec0f5@kernel.org Signed-off-by: Christian Brauner (Amutable) Stable-dep-of: a6dc643c6931 ("eventpoll: fix ep_remove struct eventpoll / struct file UAF") Signed-off-by: Sasha Levin --- fs/eventpoll.c | 67 ++++++++++++++++++++++---------------------------- 1 file changed, 30 insertions(+), 37 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 36f3545a71bfa..5d982c2503d68 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -826,49 +826,18 @@ static void ep_free(struct eventpoll *ep) kfree_rcu(ep, rcu); } -static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file); -static bool __ep_remove_epi(struct eventpoll *ep, struct epitem *epi); - -/* - * Removes a "struct epitem" from the eventpoll RB tree and deallocates - * all the associated resources. Must be called with "mtx" held. - * If the dying flag is set, do the removal only if force is true. - * This prevents ep_clear_and_put() from dropping all the ep references - * while running concurrently with eventpoll_release_file(). - * Returns true if the eventpoll can be disposed. - */ -static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) -{ - struct file *file = epi->ffd.file; - - lockdep_assert_irqs_enabled(); - - /* - * Removes poll wait queue hooks. - */ - ep_unregister_pollwait(ep, epi); - - /* Remove the current item from the list of epoll hooks */ - spin_lock(&file->f_lock); - if (epi->dying && !force) { - spin_unlock(&file->f_lock); - return false; - } - - __ep_remove_file(ep, epi, file); - return __ep_remove_epi(ep, epi); -} - /* * Called with &file->f_lock held, * returns with it released */ -static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file) +static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, + struct file *file) { struct epitems_head *to_free = NULL; struct hlist_head *head = file->f_ep; lockdep_assert_held(&ep->mtx); + lockdep_assert_held(&file->f_lock); if (hlist_is_singular_node(&epi->fllink, head)) { /* See eventpoll_release() for details. */ @@ -915,7 +884,25 @@ static bool __ep_remove_epi(struct eventpoll *ep, struct epitem *epi) */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { - if (__ep_remove(ep, epi, false)) + struct file *file = epi->ffd.file; + + lockdep_assert_irqs_enabled(); + lockdep_assert_held(&ep->mtx); + + ep_unregister_pollwait(ep, epi); + + /* sync with eventpoll_release_file() */ + if (unlikely(READ_ONCE(epi->dying))) + return; + + spin_lock(&file->f_lock); + if (epi->dying) { + spin_unlock(&file->f_lock); + return; + } + __ep_remove_file(ep, epi, file); + + if (__ep_remove_epi(ep, epi)) WARN_ON_ONCE(ep_refcount_dec_and_test(ep)); } @@ -1147,7 +1134,7 @@ void eventpoll_release_file(struct file *file) spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); - epi->dying = true; + WRITE_ONCE(epi->dying, true); spin_unlock(&file->f_lock); /* @@ -1156,7 +1143,13 @@ void eventpoll_release_file(struct file *file) */ ep = epi->ep; mutex_lock(&ep->mtx); - dispose = __ep_remove(ep, epi, true); + + ep_unregister_pollwait(ep, epi); + + spin_lock(&file->f_lock); + __ep_remove_file(ep, epi, file); + dispose = __ep_remove_epi(ep, epi); + mutex_unlock(&ep->mtx); if (dispose && ep_refcount_dec_and_test(ep)) From e644f892e1f27b7ed21a513a62b42dc1ca62d468 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 24 Apr 2026 00:23:18 +0200 Subject: [PATCH 0900/1518] eventpoll: drop vestigial __ prefix from ep_remove_{file,epi}() [ Upstream commit 0feaf644f7180c4a91b6b405a881afbfd958f1cf ] With __ep_remove() gone, the double-underscore on __ep_remove_file() and __ep_remove_epi() no longer contrasts with a __-less parent and just reads as noise. Rename both to ep_remove_file() and ep_remove_epi(). No functional change. Signed-off-by: Christian Brauner (Amutable) Stable-dep-of: a6dc643c6931 ("eventpoll: fix ep_remove struct eventpoll / struct file UAF") Signed-off-by: Sasha Levin --- fs/eventpoll.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 5d982c2503d68..68607634a60df 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -830,7 +830,7 @@ static void ep_free(struct eventpoll *ep) * Called with &file->f_lock held, * returns with it released */ -static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, +static void ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file) { struct epitems_head *to_free = NULL; @@ -854,7 +854,7 @@ static void __ep_remove_file(struct eventpoll *ep, struct epitem *epi, free_ephead(to_free); } -static bool __ep_remove_epi(struct eventpoll *ep, struct epitem *epi) +static bool ep_remove_epi(struct eventpoll *ep, struct epitem *epi) { lockdep_assert_held(&ep->mtx); @@ -900,9 +900,9 @@ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) spin_unlock(&file->f_lock); return; } - __ep_remove_file(ep, epi, file); + ep_remove_file(ep, epi, file); - if (__ep_remove_epi(ep, epi)) + if (ep_remove_epi(ep, epi)) WARN_ON_ONCE(ep_refcount_dec_and_test(ep)); } @@ -1147,8 +1147,8 @@ void eventpoll_release_file(struct file *file) ep_unregister_pollwait(ep, epi); spin_lock(&file->f_lock); - __ep_remove_file(ep, epi, file); - dispose = __ep_remove_epi(ep, epi); + ep_remove_file(ep, epi, file); + dispose = ep_remove_epi(ep, epi); mutex_unlock(&ep->mtx); From eb206b8f55e14985eb531e76cc741e0de6270df1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 23 Apr 2026 11:56:08 +0200 Subject: [PATCH 0901/1518] eventpoll: move epi_fget() up [ Upstream commit 86e87059e6d1fd5115a31949726450ed03c1073b ] We'll need it when removing files so move it up. No functional change. Link: https://patch.msgid.link/20260423-work-epoll-uaf-v1-5-2470f9eec0f5@kernel.org Signed-off-by: Christian Brauner (Amutable) Stable-dep-of: a6dc643c6931 ("eventpoll: fix ep_remove struct eventpoll / struct file UAF") Signed-off-by: Sasha Levin --- fs/eventpoll.c | 56 +++++++++++++++++++++++++------------------------- 1 file changed, 28 insertions(+), 28 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 68607634a60df..df6994943e59f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -826,6 +826,34 @@ static void ep_free(struct eventpoll *ep) kfree_rcu(ep, rcu); } +/* + * The ffd.file pointer may be in the process of being torn down due to + * being closed, but we may not have finished eventpoll_release() yet. + * + * Normally, even with the atomic_long_inc_not_zero, the file may have + * been free'd and then gotten re-allocated to something else (since + * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). + * + * But for epoll, users hold the ep->mtx mutex, and as such any file in + * the process of being free'd will block in eventpoll_release_file() + * and thus the underlying file allocation will not be free'd, and the + * file re-use cannot happen. + * + * For the same reason we can avoid a rcu_read_lock() around the + * operation - 'ffd.file' cannot go away even if the refcount has + * reached zero (but we must still not call out to ->poll() functions + * etc). + */ +static struct file *epi_fget(const struct epitem *epi) +{ + struct file *file; + + file = epi->ffd.file; + if (!file_ref_get(&file->f_ref)) + file = NULL; + return file; +} + /* * Called with &file->f_lock held, * returns with it released @@ -1018,34 +1046,6 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep return res; } -/* - * The ffd.file pointer may be in the process of being torn down due to - * being closed, but we may not have finished eventpoll_release() yet. - * - * Normally, even with the atomic_long_inc_not_zero, the file may have - * been free'd and then gotten re-allocated to something else (since - * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). - * - * But for epoll, users hold the ep->mtx mutex, and as such any file in - * the process of being free'd will block in eventpoll_release_file() - * and thus the underlying file allocation will not be free'd, and the - * file re-use cannot happen. - * - * For the same reason we can avoid a rcu_read_lock() around the - * operation - 'ffd.file' cannot go away even if the refcount has - * reached zero (but we must still not call out to ->poll() functions - * etc). - */ -static struct file *epi_fget(const struct epitem *epi) -{ - struct file *file; - - file = epi->ffd.file; - if (!file_ref_get(&file->f_ref)) - file = NULL; - return file; -} - /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() From ef4ca02e95363e78977ca04340d44fe3b4b2b81f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 23 Apr 2026 11:56:09 +0200 Subject: [PATCH 0902/1518] eventpoll: fix ep_remove struct eventpoll / struct file UAF [ Upstream commit a6dc643c69311677c574a0f17a3f4d66a5f3744b ] ep_remove() (via ep_remove_file()) cleared file->f_ep under file->f_lock but then kept using @file inside the critical section (is_file_epoll(), hlist_del_rcu() through the head, spin_unlock). A concurrent __fput() taking the eventpoll_release() fastpath in that window observed the transient NULL, skipped eventpoll_release_file() and ran to f_op->release / file_free(). For the epoll-watches-epoll case, f_op->release is ep_eventpoll_release() -> ep_clear_and_put() -> ep_free(), which kfree()s the watched struct eventpoll. Its embedded ->refs hlist_head is exactly where epi->fllink.pprev points, so the subsequent hlist_del_rcu()'s "*pprev = next" scribbles into freed kmalloc-192 memory. In addition, struct file is SLAB_TYPESAFE_BY_RCU, so the slot backing @file could be recycled by alloc_empty_file() -- reinitializing f_lock and f_ep -- while ep_remove() is still nominally inside that lock. The upshot is an attacker-controllable kmem_cache_free() against the wrong slab cache. Pin @file via epi_fget() at the top of ep_remove() and gate the critical section on the pin succeeding. With the pin held @file cannot reach refcount zero, which holds __fput() off and transitively keeps the watched struct eventpoll alive across the hlist_del_rcu() and the f_lock use, closing both UAFs. If the pin fails @file has already reached refcount zero and its __fput() is in flight. Because we bailed before clearing f_ep, that path takes the eventpoll_release() slow path into eventpoll_release_file() and blocks on ep->mtx until the waiter side's ep_clear_and_put() drops it. The bailed epi's share of ep->refcount stays intact, so the trailing ep_refcount_dec_and_test() in ep_clear_and_put() cannot free the eventpoll out from under eventpoll_release_file(); the orphaned epi is then cleaned up there. A successful pin also proves we are not racing eventpoll_release_file() on this epi, so drop the now-redundant re-check of epi->dying under f_lock. The cheap lockless READ_ONCE(epi->dying) fast-path bailout stays. Fixes: 58c9b016e128 ("epoll: use refcount to reduce ep_mutex contention") Reported-by: Jaeyoung Chung Link: https://patch.msgid.link/20260423-work-epoll-uaf-v1-6-2470f9eec0f5@kernel.org Signed-off-by: Christian Brauner (Amutable) Signed-off-by: Sasha Levin --- fs/eventpoll.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index df6994943e59f..e9e6938f7184a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -912,22 +912,26 @@ static bool ep_remove_epi(struct eventpoll *ep, struct epitem *epi) */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { - struct file *file = epi->ffd.file; + struct file *file __free(fput) = NULL; lockdep_assert_irqs_enabled(); lockdep_assert_held(&ep->mtx); ep_unregister_pollwait(ep, epi); - /* sync with eventpoll_release_file() */ + /* cheap sync with eventpoll_release_file() */ if (unlikely(READ_ONCE(epi->dying))) return; - spin_lock(&file->f_lock); - if (epi->dying) { - spin_unlock(&file->f_lock); + /* + * If we manage to grab a reference it means we're not in + * eventpoll_release_file() and aren't going to be. + */ + file = epi_fget(epi); + if (!file) return; - } + + spin_lock(&file->f_lock); ep_remove_file(ep, epi, file); if (ep_remove_epi(ep, epi)) From a3fd5dc1c7b0aae947a67dc2e2c037d57557a4de Mon Sep 17 00:00:00 2001 From: Bae Yeonju Date: Sat, 21 Mar 2026 13:45:02 +0900 Subject: [PATCH 0903/1518] fs/adfs: validate nzones in adfs_validate_bblk() [ Upstream commit dd9d3e16c2d5fa166e13dce07413be51f42c8f5d ] Reject ADFS disc records with a zero zone count during boot block validation, before the disc record is used. When nzones is 0, adfs_read_map() passes it to kmalloc_array(0, ...) which returns ZERO_SIZE_PTR, and adfs_map_layout() then writes to dm[-1], causing an out-of-bounds write before the allocated buffer. adfs_validate_dr0() already rejects nzones != 1 for old-format images. Add the equivalent check to adfs_validate_bblk() for new-format images so that a crafted image with nzones == 0 is rejected at probe time. Found by syzkaller. Fixes: f6f14a0d71b0 ("fs/adfs: map: move map-specific sb initialisation to map.c") Signed-off-by: Bae Yeonju Signed-off-by: Russell King (Oracle) Signed-off-by: Sasha Levin --- fs/adfs/super.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/adfs/super.c b/fs/adfs/super.c index fdccdbbfc2130..4f5279cd456fe 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -317,6 +317,9 @@ static int adfs_validate_bblk(struct super_block *sb, struct buffer_head *bh, if (adfs_checkdiscrecord(dr)) return -EILSEQ; + if ((dr->nzones | dr->nzones_high << 8) == 0) + return -EILSEQ; + *drp = dr; return 0; } From 03a8177556117aa3b0bac5c49a794bbd5863470b Mon Sep 17 00:00:00 2001 From: "Anthony Pighin (Nokia)" Date: Tue, 25 Nov 2025 18:00:10 +0000 Subject: [PATCH 0904/1518] rtc: abx80x: Disable alarm feature if no interrupt attached [ Upstream commit 0fedce7244e4b85c049ce579c87e298a1b0b811d ] Commit 795cda8338ea ("rtc: interface: Fix long-standing race when setting alarm") exposed an issue where the rtc-abx80x driver does not clear the alarm feature bit, but instead relies on the set_alarm operation to return invalid. For example, when a RTC_UIE_ON ioctl is handled, it should abort at the feature validation. Instead, it proceeds to the rtc_timer_enqueue(), which used to return an error from the set_alarm call. However, following the race condition handling, which likely should not be discarding predecing errors, a success condition is returned to the ioctl() caller. This results in (for example): hwclock: select() to /dev/rtc0 to wait for clock tick timed out Notwithstanding the validity of the race condition handling, if an interrupt wasn't specified, or could not be attached, the driver should clear the alarm feature bit. Fixes: 718a820a303c ("rtc: abx80x: add alarm support") Signed-off-by: Anthony Pighin Link: https://patch.msgid.link/BN0PR08MB69510928028C933749F4139383D1A@BN0PR08MB6951.namprd08.prod.outlook.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-abx80x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c index 3fee27914ba80..5f3a3e60a19d0 100644 --- a/drivers/rtc/rtc-abx80x.c +++ b/drivers/rtc/rtc-abx80x.c @@ -933,6 +933,8 @@ static int abx80x_probe(struct i2c_client *client) client->irq = 0; } } + if (client->irq <= 0) + clear_bit(RTC_FEATURE_ALARM, priv->rtc->features); err = rtc_add_group(priv->rtc, &rtc_calib_attr_group); if (err) { From 4b238fb04bd2dda8442b015ffc153f14877a5793 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Thu, 2 Apr 2026 16:51:16 +0200 Subject: [PATCH 0905/1518] kbuild: builddeb - avoid recompiles for non-cross-compiles [ Upstream commit 2452dcf4d740effff5aa71b7f6529ee8c04fd8f6 ] Commit e2c318225ac1 ("kbuild: deb-pkg: add pkg.linux-upstream.nokernelheaders build profile") changed how install-extmod-build gets called, making it always rebuild the host programs below scripts/ if HOSTCC wasn't specified with its full triplet on the make command line. That is, apparently, needed to fix up commit f1d87664b82a ("kbuild: cross-compile linux-headers package when possible") for cross-compiles. However, in the much more common case of non-cross-compile builds this will lead to unnecessary rebuilding of host tools including gcc plugins. This, in turn, will lead to a full kernel rebuild on the next 'make bindeb-pkg' which is unfortunate. Avoid that by only triggering the rebuild of host tools for actual cross-compile builds. Signed-off-by: Mathias Krause Fixes: e2c318225ac1 ("kbuild: deb-pkg: add pkg.linux-upstream.nokernelheaders build profile") Cc: Masahiro Yamada Reviewed-by: Nathan Chancellor Reviewed-by: Nicolas Schier Link: https://patch.msgid.link/20260402145116.1010901-1-minipli@grsecurity.net Signed-off-by: Nicolas Schier Signed-off-by: Sasha Levin --- scripts/package/builddeb | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 3627ca227e5a5..ba1defc616524 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -139,7 +139,13 @@ install_kernel_headers () { pdir=debian/$1 version=${1#linux-headers-} - CC="${DEB_HOST_GNU_TYPE}-gcc" "${srctree}/scripts/package/install-extmod-build" "${pdir}/usr/src/linux-headers-${version}" + # Override $CC only for cross-compiles, to not unnecessarily rebuild + # scripts/ including plugins, which may lead to a full kernel rebuild. + if [ -n "${CROSS_COMPILE}" ]; then + CC="${DEB_HOST_GNU_TYPE}-gcc" "${srctree}/scripts/package/install-extmod-build" "${pdir}/usr/src/linux-headers-${version}" + else + "${srctree}/scripts/package/install-extmod-build" "${pdir}/usr/src/linux-headers-${version}" + fi mkdir -p $pdir/lib/modules/$version/ ln -s /usr/src/linux-headers-$version $pdir/lib/modules/$version/build From c7a9cde132bfd7204c228214d24952ed833162aa Mon Sep 17 00:00:00 2001 From: Yuho Choi Date: Sun, 19 Apr 2026 21:01:18 -0400 Subject: [PATCH 0906/1518] fbdev: offb: fix PCI device reference leak on probe failure [ Upstream commit 869b93ba04088713596e68453c1146f52f713290 ] offb_init_nodriver() gets a referenced PCI device with pci_get_device(). If pci_enable_device() fails, the function returns without dropping that reference. Release the PCI device reference before returning from the pci_enable_device() failure path. Fixes: 5bda8f7b5468 ("video: fbdev: offb: Call pci_enable_device() before using the PCI VGA device") Co-developed-by: Myeonghun Pak Signed-off-by: Myeonghun Pak Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Co-developed-by: Taegyu Kim Signed-off-by: Taegyu Kim Signed-off-by: Yuho Choi Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/offb.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c index f85428e13996b..166b2dff36f59 100644 --- a/drivers/video/fbdev/offb.c +++ b/drivers/video/fbdev/offb.c @@ -640,8 +640,13 @@ static void offb_init_nodriver(struct platform_device *parent, struct device_nod vid = be32_to_cpup(vidp); did = be32_to_cpup(didp); pdev = pci_get_device(vid, did, NULL); - if (!pdev || pci_enable_device(pdev)) + if (!pdev) return; + + if (pci_enable_device(pdev)) { + pci_dev_put(pdev); + return; + } } #endif /* kludge for valkyrie */ From 8adeeef75597ec7bb8b6e13bebe161f3a5cb6020 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 10 Dec 2025 13:33:29 -0500 Subject: [PATCH 0907/1518] tools/power turbostat.8: Document the "--force" option [ Upstream commit 785953cf6e63aa5a9fcdfa9577b1411e0281c4bc ] Starting in turbostat v2025.01.14, turbostat refused to run on unsupported hardware, pointing to "RUN THE LATEST VERSION" on turbostat(8). At that time, turbostat supported and advertised the "--force" parameter to run anyway (with unsupported results). Also document "--force" on turbostat.8. Signed-off-by: Len Brown Stable-dep-of: ce012c966b51 ("tools/power turbostat: Fix unrecognized option '-P'") Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.8 | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 3340def58d015..6c9428f98cd2b 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -111,6 +111,8 @@ The column name "all" can be used to enable all disabled-by-default built-in cou .PP \fB--no-perf\fP Disable all the uses of the perf API. .PP +\fB--force\fPForce turbostat to run on an unsupported platform (minimal defaults). +.PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP \fB--num_iterations num\fP number of the measurement iterations. @@ -161,9 +163,9 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBC1, C2, C3...\fP The number times Linux requested the C1, C2, C3 idle state during the measurement interval. The system summary line shows the sum for all CPUs. These are C-state names as exported in /sys/devices/system/cpu/cpu*/cpuidle/state*/name. While their names are generic, their attributes are processor specific. They the system description section of output shows what MWAIT sub-states they are mapped to on each system. These counters are in the "cpuidle" group, which is disabled, by default. .PP -\fBC1+, C2+, C3+...\fP The idle governor idle state misprediction statistics. Inidcates the number times Linux requested the C1, C2, C3 idle state during the measurement interval, but should have requested a deeper idle state (if it exists and enabled). These statistics come from the /sys/devices/system/cpu/cpu*/cpuidle/state*/below file. These counters are in the "cpuidle" group, which is disabled, by default. +\fBC1+, C2+, C3+...\fP The idle governor idle state misprediction statistics. Indicates the number times Linux requested the C1, C2, C3 idle state during the measurement interval, but should have requested a deeper idle state (if it exists and enabled). These statistics come from the /sys/devices/system/cpu/cpu*/cpuidle/state*/below file. These counters are in the "cpuidle" group, which is disabled, by default. .PP -\fBC1-, C2-, C3-...\fP The idle governor idle state misprediction statistics. Inidcates the number times Linux requested the C1, C2, C3 idle state during the measurement interval, but should have requested a shallower idle state (if it exists and enabled). These statistics come from the /sys/devices/system/cpu/cpu*/cpuidle/state*/above file. These counters are in the "cpuidle" group, which is disabled, by default. +\fBC1-, C2-, C3-...\fP The idle governor idle state misprediction statistics. Indicates the number times Linux requested the C1, C2, C3 idle state during the measurement interval, but should have requested a shallower idle state (if it exists and enabled). These statistics come from the /sys/devices/system/cpu/cpu*/cpuidle/state*/above file. These counters are in the "cpuidle" group, which is disabled, by default. .PP \fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved. These counters are in the "pct_idle" group, which is enabled by default. .PP @@ -193,7 +195,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBGFX%C0\fP Percentage of time that at least one GFX compute engine is busy. .PP -\fBCPUGFX%\fP Percentage of time that at least one CPU is busy at the same time as at least one Graphics compute enginer is busy. +\fBCPUGFX%\fP Percentage of time that at least one CPU is busy at the same time as at least one Graphics compute engine is busy. .PP \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. .PP @@ -556,6 +558,8 @@ If the upstream version isn't new enough, the development tree can be found here If the development tree doesn't work, please contact the author via chat, or via email with the word "turbostat" on the Subject line. +An old turbostat binary may run on unknown hardware by using "--force", +but results are unsupported. .SH FILES .ta .nf From 481dbda367f460c298e7ff8ce3c5a20b6a4917fc Mon Sep 17 00:00:00 2001 From: Kaushlendra Kumar Date: Mon, 8 Dec 2025 08:38:04 +0530 Subject: [PATCH 0908/1518] tools/power turbostat: Use strtoul() for iteration parsing [ Upstream commit 8e5c0cc326f2e95a71bb6e6063e65caa60c8f951 ] Replace strtod() with strtoul() and check errno for -n/-N options, since num_iterations and header_iterations are unsigned long counters. Reject zero and conversion errors; negative inputs wrap to large positive values per standard unsigned semantics. Signed-off-by: Kaushlendra Kumar Signed-off-by: Len Brown Stable-dep-of: ce012c966b51 ("tools/power turbostat: Fix unrecognized option '-P'") Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 48677f1846347..29441e3c711d9 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -11133,18 +11133,20 @@ void cmdline(int argc, char **argv) /* Parsed earlier */ break; case 'n': - num_iterations = strtod(optarg, NULL); + num_iterations = strtoul(optarg, NULL, 0); + errno = 0; - if (num_iterations <= 0) { - fprintf(outf, "iterations %d should be positive number\n", num_iterations); + if (errno || num_iterations == 0) { + fprintf(outf, "invalid iteration count: %s\n", optarg); exit(2); } break; case 'N': - header_iterations = strtod(optarg, NULL); + header_iterations = strtoul(optarg, NULL, 0); + errno = 0; - if (header_iterations <= 0) { - fprintf(outf, "iterations %d should be positive number\n", header_iterations); + if (errno || header_iterations == 0) { + fprintf(outf, "invalid header iteration count: %s\n", optarg); exit(2); } break; From 262187aa6981dfd4af907f4458ade55bddb97527 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Fri, 13 Feb 2026 13:26:12 -0600 Subject: [PATCH 0909/1518] tools/power turbostat: Fix and document --header_iterations [ Upstream commit 96718ad296af4a6d984b3a09276b165ab6a3b0c8 ] The "header_iterations" option is commonly used to de-clutter the screen of redundant header label rows in an interactive session: Eg. every 10 rows: $ sudo turbostat --header_iterations 10 -S -q -i 1 But --header_iterations was missing from turbostat.8 Also turbostat help advertised the "-N" short option that did not actually work: $ turbostat --help -N, --header_iterations num print header every num iterations Repair "-N" Document "--header_iterations" on turbostat.8 Signed-off-by: Len Brown Stable-dep-of: ce012c966b51 ("tools/power turbostat: Fix unrecognized option '-P'") Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.8 | 4 +++- tools/power/x86/turbostat/turbostat.c | 20 +++++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 6c9428f98cd2b..3e0487cd6451e 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -111,12 +111,14 @@ The column name "all" can be used to enable all disabled-by-default built-in cou .PP \fB--no-perf\fP Disable all the uses of the perf API. .PP -\fB--force\fPForce turbostat to run on an unsupported platform (minimal defaults). +\fB--force\fP Force turbostat to run on an unsupported platform (minimal defaults). .PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP \fB--num_iterations num\fP number of the measurement iterations. .PP +\fB--header_iterations num\fP print header every num iterations. +.PP \fB--out output_file\fP turbostat output is written to the specified output_file. The file is truncated if it already exists, and it is created if it does not exist. .PP diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 29441e3c711d9..ec4b7ff8810b1 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -11040,7 +11040,7 @@ void cmdline(int argc, char **argv) * Parse some options early, because they may make other options invalid, * like adding the MSR counter with --add and at the same time using --no-msr. */ - while ((opt = getopt_long_only(argc, argv, "+MPn:", long_options, &option_index)) != -1) { + while ((opt = getopt_long_only(argc, argv, "+:MP", long_options, &option_index)) != -1) { switch (opt) { case 'M': no_msr = 1; @@ -11054,7 +11054,7 @@ void cmdline(int argc, char **argv) } optind = 0; - while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qMST:v", long_options, &option_index)) != -1) { + while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:N:o:qMST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': parse_add_command(optarg); @@ -11097,7 +11097,6 @@ void cmdline(int argc, char **argv) } break; case 'h': - default: help(); exit(1); case 'i': @@ -11136,19 +11135,15 @@ void cmdline(int argc, char **argv) num_iterations = strtoul(optarg, NULL, 0); errno = 0; - if (errno || num_iterations == 0) { - fprintf(outf, "invalid iteration count: %s\n", optarg); - exit(2); - } + if (errno || num_iterations == 0) + errx(-1, "invalid iteration count: %s", optarg); break; case 'N': header_iterations = strtoul(optarg, NULL, 0); errno = 0; - if (errno || header_iterations == 0) { - fprintf(outf, "invalid header iteration count: %s\n", optarg); - exit(2); - } + if (errno || header_iterations == 0) + errx(-1, "invalid header iteration count: %s", optarg); break; case 's': /* @@ -11171,6 +11166,9 @@ void cmdline(int argc, char **argv) print_version(); exit(0); break; + default: + help(); + exit(1); } } } From 4d837117d45dea05e63e8606e434cd921aebea27 Mon Sep 17 00:00:00 2001 From: David Arcari Date: Tue, 21 Apr 2026 10:32:17 -0400 Subject: [PATCH 0910/1518] tools/power turbostat: Fix unrecognized option '-P' [ Upstream commit ce012c966b518c53475ba9a4e979242d7322d819 ] The '-P' short option (shorthand for --no-perf) is not present in the optstring of the second call to getopt_long_only(). This results in the "unrecognized option" error when the tool reaches the main parsing loop. Add 'P' to the second getopt_long_only() call to ensure it is consistently recognized. Fixes: a0e86c90b83c ("tools/power turbostat: Add --no-perf option") Signed-off-by: David Arcari Signed-off-by: Len Brown Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index ec4b7ff8810b1..313872f64a9a9 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -11054,7 +11054,7 @@ void cmdline(int argc, char **argv) } optind = 0; - while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:N:o:qMST:v", long_options, &option_index)) != -1) { + while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:N:o:qMPST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': parse_add_command(optarg); From d07bc4ce8e24fa3a88c07137f79488d539589f8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 22 Apr 2026 17:10:27 +0200 Subject: [PATCH 0911/1518] kbuild: Never respect CONFIG_WERROR / W=e to fixdep MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 75f7c47ccd78c947cf1b6ddb18ea453ff0555716 ] The fixdep hostprog may be built multiple times during a single build. Once during the configuration phase and later during the regular phase. As only the regular build phase respects CONFIG_WERROR / W=e, the compiler flags might change between the phases, leading to rebuilds. Example, the rebuilds will happen twice on each invocation of the build: $ make allyesconfig prepare make[1]: Entering directory '/tmp/deleteme' HOSTCC scripts/basic/fixdep # # No change to .config # HOSTCC scripts/basic/fixdep DESCEND objtool INSTALL libsubcmd_headers make[1]: Leaving directory '/tmp/deleteme' Fix the compilation flags used for scripts/basic/ before scripts/Makefile.warn is evaluated to stop CONFIG_WERROR / W=e influencing the fixdep build to avoid the spurious rebuilds. Fixes: 7ded7d37e5f5 ("scripts/Makefile.extrawarn: Respect CONFIG_WERROR / W=e for hostprogs") Signed-off-by: Thomas Weißschuh Reviewed-by: Nathan Chancellor Link: https://patch.msgid.link/20260422-kbuild-scripts-basic-werror-v1-1-8c6912ff22e0@weissschuh.net Signed-off-by: Nicolas Schier Signed-off-by: Sasha Levin --- Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Makefile b/Makefile index d1fcec7cf9568..70e10b29b3859 100644 --- a/Makefile +++ b/Makefile @@ -655,6 +655,8 @@ export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o \ # Basic helpers built in scripts/basic/ PHONY += scripts_basic +scripts_basic: KBUILD_HOSTCFLAGS := $(KBUILD_HOSTCFLAGS) +scripts_basic: KBUILD_HOSTLDFLAGS := $(KBUILD_HOSTLDFLAGS) scripts_basic: $(Q)$(MAKE) $(build)=scripts/basic From d3da3c85cdd6a76787a43990c9977b2538af3c31 Mon Sep 17 00:00:00 2001 From: Jason-JH Lin Date: Mon, 23 Mar 2026 17:07:11 +0800 Subject: [PATCH 0912/1518] mailbox: mtk-cmdq: Fix CURR and END addr for task insert case [ Upstream commit d2591db9c8ef19fbb4d24ed15e0c6edfa6bc7917 ] Fix CURR and END address calculation for inserting a cmdq task into the task list by using cmdq_reg_shift_addr() for proper address converting. This ensures both CURR and END addresses are set correctly when enabling the thread. Fixes: a195c7ccfb7a ("mailbox: mtk-cmdq: Refine DMA address handling for the command buffer") Signed-off-by: Jason-JH Lin Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mtk-cmdq-mailbox.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index 5791f80f995ab..a1360b70b83fb 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -434,14 +434,14 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data) if (curr_pa == end_pa - CMDQ_INST_SIZE || curr_pa == end_pa) { /* set to this task directly */ - writel(task->pa_base >> cmdq->pdata->shift, - thread->base + CMDQ_THR_CURR_ADDR); + gce_addr = cmdq_convert_gce_addr(task->pa_base, cmdq->pdata); + writel(gce_addr, thread->base + CMDQ_THR_CURR_ADDR); } else { cmdq_task_insert_into_thread(task); smp_mb(); /* modify jump before enable thread */ } - writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->pdata->shift, - thread->base + CMDQ_THR_END_ADDR); + gce_addr = cmdq_convert_gce_addr(task->pa_base + pkt->cmd_buf_size, cmdq->pdata); + writel(gce_addr, thread->base + CMDQ_THR_END_ADDR); cmdq_thread_resume(thread); } list_move_tail(&task->list_entry, &thread->task_busy_list); From 742001919653e7313b4e91780c5d108be1692365 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 10 Apr 2026 14:53:00 +0200 Subject: [PATCH 0913/1518] mailbox: mailbox-test: free channels on probe error [ Upstream commit c02053a9055d5fdfd32432287cca8958db1d5bc5 ] On probe error, free the previously obtained channels. This not only prevents a leak, but also UAF scenarios because the client structure will be removed nonetheless because it was allocated with devm. Link: https://sashiko.dev/#/patchset/20260327151217.5327-2-wsa%2Brenesas%40sang-engineering.com Fixes: 8ea4484d0c2b ("mailbox: Add generic mechanism for testing Mailbox Controllers") Signed-off-by: Wolfram Sang Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox-test.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 3a28ab5c42e57..197cad7b3d401 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -404,18 +404,27 @@ static int mbox_test_probe(struct platform_device *pdev) if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->rx_buffer) - return -ENOMEM; + if (!tdev->rx_buffer) { + ret = -ENOMEM; + goto err_free_chans; + } } ret = mbox_test_add_debugfs(pdev, tdev); if (ret) - return ret; + goto err_free_chans; init_waitqueue_head(&tdev->waitq); dev_info(&pdev->dev, "Successfully registered\n"); return 0; + +err_free_chans: + if (tdev->tx_channel) + mbox_free_channel(tdev->tx_channel); + if (tdev->rx_channel) + mbox_free_channel(tdev->rx_channel); + return ret; } static void mbox_test_remove(struct platform_device *pdev) From 03dc070fa0fc3cb4068693f468ccd5f8a7e58282 Mon Sep 17 00:00:00 2001 From: Edward Adam Davis Date: Tue, 14 Apr 2026 14:15:43 +0800 Subject: [PATCH 0914/1518] sched/psi: fix race between file release and pressure write [ Upstream commit a5b98009f16d8a5fb4a8ff9a193f5735515c38fa ] A potential race condition exists between pressure write and cgroup file release regarding the priv member of struct kernfs_open_file, which triggers the uaf reported in [1]. Consider the following scenario involving execution on two separate CPUs: CPU0 CPU1 ==== ==== vfs_rmdir() kernfs_iop_rmdir() cgroup_rmdir() cgroup_kn_lock_live() cgroup_destroy_locked() cgroup_addrm_files() cgroup_rm_file() kernfs_remove_by_name() kernfs_remove_by_name_ns() vfs_write() __kernfs_remove() new_sync_write() kernfs_drain() kernfs_fop_write_iter() kernfs_drain_open_files() cgroup_file_write() kernfs_release_file() pressure_write() cgroup_file_release() ctx = of->priv; kfree(ctx); of->priv = NULL; cgroup_kn_unlock() cgroup_kn_lock_live() cgroup_get(cgrp) cgroup_kn_unlock() if (ctx->psi.trigger) // here, trigger uaf for ctx, that is of->priv The cgroup_rmdir() is protected by the cgroup_mutex, it also safeguards the memory deallocation of of->priv performed within cgroup_file_release(). However, the operations involving of->priv executed within pressure_write() are not entirely covered by the protection of cgroup_mutex. Consequently, if the code in pressure_write(), specifically the section handling the ctx variable executes after cgroup_file_release() has completed, a uaf vulnerability involving of->priv is triggered. Therefore, the issue can be resolved by extending the scope of the cgroup_mutex lock within pressure_write() to encompass all code paths involving of->priv, thereby properly synchronizing the race condition occurring between cgroup_file_release() and pressure_write(). And, if an live kn lock can be successfully acquired while executing the pressure write operation, it indicates that the cgroup deletion process has not yet reached its final stage; consequently, the priv pointer within open_file cannot be NULL. Therefore, the operation to retrieve the ctx value must be moved to a point *after* the live kn lock has been successfully acquired. In another situation, specifically after entering cgroup_kn_lock_live() but before acquiring cgroup_mutex, there exists a different class of race condition: CPU0: write memory.pressure CPU1: write cgroup.pressure=0 =========================== ============================= kernfs_fop_write_iter() kernfs_get_active_of(of) pressure_write() cgroup_kn_lock_live(memory.pressure) cgroup_tryget(cgrp) kernfs_break_active_protection(kn) ... blocks on cgroup_mutex cgroup_pressure_write() cgroup_kn_lock_live(cgroup.pressure) cgroup_file_show(memory.pressure, false) kernfs_show(false) kernfs_drain_open_files() cgroup_file_release(of) kfree(ctx) of->priv = NULL cgroup_kn_unlock() ... acquires cgroup_mutex ctx = of->priv; // may now be NULL if (ctx->psi.trigger) // NULL dereference Consequently, there is a possibility that of->priv is NULL, the pressure write needs to check for this. Now that the scope of the cgroup_mutex has been expanded, the original explicit cgroup_get/put operations are no longer necessary, this is because acquiring/releasing the live kn lock inherently executes a cgroup get/put operation. [1] BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011 Call Trace: pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011 cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311 kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352 Allocated by task 9352: cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256 kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724 do_dentry_open+0x83d/0x13e0 fs/open.c:949 Freed by task 9353: cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283 kernfs_release_file fs/kernfs/file.c:764 [inline] kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834 kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525 Fixes: 0e94682b73bf ("psi: introduce psi monitor") Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c Tested-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis Reviewed-by: Chen Ridong Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/cgroup/cgroup.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index da5f6f5400afa..b60fc0b2c6036 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3997,33 +3997,41 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { - struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_file_ctx *ctx; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; + ssize_t ret = 0; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; - cgroup_get(cgrp); - cgroup_kn_unlock(of->kn); + ctx = of->priv; + if (!ctx) { + ret = -ENODEV; + goto out_unlock; + } /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { - cgroup_put(cgrp); - return -EBUSY; + ret = -EBUSY; + goto out_unlock; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { - cgroup_put(cgrp); - return PTR_ERR(new); + ret = PTR_ERR(new); + goto out_unlock; } smp_store_release(&ctx->psi.trigger, new); - cgroup_put(cgrp); + +out_unlock: + cgroup_kn_unlock(of->kn); + if (ret) + return ret; return nbytes; } From 8d5e39df95ed07233e0c72a00ef17eea27faab1a Mon Sep 17 00:00:00 2001 From: cuitao Date: Tue, 14 Apr 2026 09:53:27 +0800 Subject: [PATCH 0915/1518] cgroup/rdma: fix integer overflow in rdmacg_try_charge() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c802f460dd485c1332b5a35e7adcfb2bc22536a2 ] The expression `rpool->resources[index].usage + 1` is computed in int arithmetic before being assigned to s64 variable `new`. When usage equals INT_MAX (the default "max" value), the addition overflows to INT_MIN. This negative value then passes the `new > max` check incorrectly, allowing a charge that should be rejected and corrupting usage to negative. Fix by casting usage to s64 before the addition so the arithmetic is done in 64-bit. Fixes: 39d3e7584a68 ("rdmacg: Added rdma cgroup controller") Signed-off-by: cuitao Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/cgroup/rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index ef5878fb20057..d544a747f3954 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -283,7 +283,7 @@ int rdmacg_try_charge(struct rdma_cgroup **rdmacg, ret = PTR_ERR(rpool); goto err; } else { - new = rpool->resources[index].usage + 1; + new = (s64)rpool->resources[index].usage + 1; if (new > rpool->resources[index].max) { ret = -EAGAIN; goto err; From 9dd7489943324298bb0f385495795a82f1dd6507 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 13 Apr 2026 12:42:38 +0200 Subject: [PATCH 0916/1518] mailbox: add sanity check for channel array [ Upstream commit c1aad75595fb67edc7fda8af249d3b886efa1be9 ] Fail gracefully if there is no channel array attached to the mailbox controller. Otherwise the later dereference will cause an OOPS which might not be seen because mailbox controllers might instantiate very early. Remove the comment explaining the obvious while here. Fixes: 2b6d83e2b8b7 ("mailbox: Introduce framework for mailbox") Signed-off-by: Wolfram Sang Reviewed-by: Geert Uytterhoeven Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 617ba505691d3..b77162db509f2 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -505,8 +505,7 @@ int mbox_controller_register(struct mbox_controller *mbox) { int i, txdone; - /* Sanity check */ - if (!mbox || !mbox->dev || !mbox->ops || !mbox->num_chans) + if (!mbox || !mbox->dev || !mbox->ops || !mbox->chans || !mbox->num_chans) return -EINVAL; if (mbox->txdone_irq) From 82f6dcea46cf5de65c4ba7283f7c7b34de4a324d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 17 Apr 2026 09:42:34 +0200 Subject: [PATCH 0917/1518] mailbox: mailbox-test: don't free the reused channel [ Upstream commit 88ebadbf0deefdaccdab868b44ff70a0a257f473 ] The RX channel can be aliased to the TX channel if it has a different MMIO. This special case needs to be handled when freeing the channels otherwise a double-free occurs. Fixes: 8ea4484d0c2b ("mailbox: Add generic mechanism for testing Mailbox Controllers") Signed-off-by: Wolfram Sang Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox-test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 197cad7b3d401..210f6077f475c 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -422,7 +422,7 @@ static int mbox_test_probe(struct platform_device *pdev) err_free_chans: if (tdev->tx_channel) mbox_free_channel(tdev->tx_channel); - if (tdev->rx_channel) + if (tdev->rx_channel && tdev->rx_channel != tdev->tx_channel) mbox_free_channel(tdev->rx_channel); return ret; } @@ -435,7 +435,7 @@ static void mbox_test_remove(struct platform_device *pdev) if (tdev->tx_channel) mbox_free_channel(tdev->tx_channel); - if (tdev->rx_channel) + if (tdev->rx_channel && tdev->rx_channel != tdev->tx_channel) mbox_free_channel(tdev->rx_channel); } From 3c791f6fb791f687f3cebf80e661af8d5d12cf5c Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 17 Apr 2026 09:42:35 +0200 Subject: [PATCH 0918/1518] mailbox: mailbox-test: initialize struct earlier [ Upstream commit bbcf9af68bfedb3d9cc3c7eae62f5c844d8b78b9 ] The waitqueue must be initialized before the debugfs files are created because from that time, requests from userspace can already be made. Similarily, drvdata and spinlock needs to be initialized before we request the channel, otherwise dangling irqs might run into problems like a NULL pointer exception. Fixes: 8ea4484d0c2b ("mailbox: Add generic mechanism for testing Mailbox Controllers") Signed-off-by: Wolfram Sang Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox-test.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 210f6077f475c..a0a7908c9cc26 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -366,6 +366,12 @@ static int mbox_test_probe(struct platform_device *pdev) if (!tdev) return -ENOMEM; + tdev->dev = &pdev->dev; + spin_lock_init(&tdev->lock); + mutex_init(&tdev->mutex); + init_waitqueue_head(&tdev->waitq); + platform_set_drvdata(pdev, tdev); + /* It's okay for MMIO to be NULL */ tdev->tx_mmio = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (PTR_ERR(tdev->tx_mmio) == -EBUSY) { @@ -395,12 +401,6 @@ static int mbox_test_probe(struct platform_device *pdev) if (!tdev->rx_channel && (tdev->rx_mmio != tdev->tx_mmio)) tdev->rx_channel = tdev->tx_channel; - tdev->dev = &pdev->dev; - platform_set_drvdata(pdev, tdev); - - spin_lock_init(&tdev->lock); - mutex_init(&tdev->mutex); - if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, MBOX_MAX_MSG_LEN, GFP_KERNEL); @@ -414,7 +414,6 @@ static int mbox_test_probe(struct platform_device *pdev) if (ret) goto err_free_chans; - init_waitqueue_head(&tdev->waitq); dev_info(&pdev->dev, "Successfully registered\n"); return 0; From f7f5d83b0dc2f9edd03f2bd47c296aa61f220caf Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 17 Apr 2026 09:42:36 +0200 Subject: [PATCH 0919/1518] mailbox: mailbox-test: make data_ready a per-instance variable [ Upstream commit 6e937f4e769e60947909e3525965f0137b9039e8 ] While not the default case, multiple tests can be run simultaneously. Then, data_ready being a global variable will be overwritten and the per-instance lock will not help. Turn the global variable into a per-instance one to avoid this problem. Fixes: e339c80af95e ("mailbox: mailbox-test: don't rely on rx_buffer content to signal data ready") Signed-off-by: Wolfram Sang Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox-test.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index a0a7908c9cc26..c429acd3af87c 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -28,8 +28,6 @@ #define MBOX_HEXDUMP_MAX_LEN (MBOX_HEXDUMP_LINE_LEN * \ (MBOX_MAX_MSG_LEN / MBOX_BYTES_PER_LINE)) -static bool mbox_data_ready; - struct mbox_test_device { struct device *dev; void __iomem *tx_mmio; @@ -42,6 +40,7 @@ struct mbox_test_device { spinlock_t lock; struct mutex mutex; wait_queue_head_t waitq; + bool data_ready; struct fasync_struct *async_queue; struct dentry *root_debugfs_dir; }; @@ -162,7 +161,7 @@ static bool mbox_test_message_data_ready(struct mbox_test_device *tdev) unsigned long flags; spin_lock_irqsave(&tdev->lock, flags); - data_ready = mbox_data_ready; + data_ready = tdev->data_ready; spin_unlock_irqrestore(&tdev->lock, flags); return data_ready; @@ -227,7 +226,7 @@ static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf, *(touser + l) = '\0'; memset(tdev->rx_buffer, 0, MBOX_MAX_MSG_LEN); - mbox_data_ready = false; + tdev->data_ready = false; spin_unlock_irqrestore(&tdev->lock, flags); @@ -297,7 +296,7 @@ static void mbox_test_receive_message(struct mbox_client *client, void *message) message, MBOX_MAX_MSG_LEN); memcpy(tdev->rx_buffer, message, MBOX_MAX_MSG_LEN); } - mbox_data_ready = true; + tdev->data_ready = true; spin_unlock_irqrestore(&tdev->lock, flags); wake_up_interruptible(&tdev->waitq); From b740cc86816bbc87902ae9db74cd21abde3c8d63 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 20 Apr 2026 14:58:00 +0200 Subject: [PATCH 0920/1518] fsnotify: fix inode reference leak in fsnotify_recalc_mask() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4aca914ac152f5d055ddcb36704d1e539ac08977 ] fsnotify_recalc_mask() fails to handle the return value of __fsnotify_recalc_mask(), which may return an inode pointer that needs to be released via fsnotify_drop_object() when the connector's HAS_IREF flag transitions from set to cleared. This manifests as a hung task with the following call trace: INFO: task umount:1234 blocked for more than 120 seconds. Call Trace: __schedule schedule fsnotify_sb_delete generic_shutdown_super kill_anon_super cleanup_mnt task_work_run do_exit do_group_exit The race window that triggers the iref leak: Thread A (adding mark) Thread B (removing mark) ────────────────────── ──────────────────────── fsnotify_add_mark_locked(): fsnotify_add_mark_list(): spin_lock(conn->lock) add mark_B(evictable) to list spin_unlock(conn->lock) return /* ---- gap: no lock held ---- */ fsnotify_detach_mark(mark_A): spin_lock(mark_A->lock) clear ATTACHED flag on mark_A spin_unlock(mark_A->lock) fsnotify_put_mark(mark_A) fsnotify_recalc_mask(): spin_lock(conn->lock) __fsnotify_recalc_mask(): /* mark_A skipped: ATTACHED cleared */ /* only mark_B(evictable) remains */ want_iref = false has_iref = true /* not yet cleared */ -> HAS_IREF transitions true -> false -> returns inode pointer spin_unlock(conn->lock) /* BUG: return value discarded! * iput() and fsnotify_put_sb_watched_objects() * are never called */ Fix this by deferring the transition true -> false of HAS_IREF flag from fsnotify_recalc_mask() (Thread A) to fsnotify_put_mark() (thread B). Fixes: c3638b5b1374 ("fsnotify: allow adding an inode mark without pinning inode") Signed-off-by: Xin Yin Signed-off-by: Amir Goldstein Link: https://patch.msgid.link/CAOQ4uxiPsbHb0o5voUKyPFMvBsDkG914FYDcs4C5UpBMNm0Vcg@mail.gmail.com Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/notify/mark.c | 39 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 36 insertions(+), 3 deletions(-) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index cedd84afbede5..78338075f08a1 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -237,7 +237,12 @@ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, return inode; } -static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) +/* + * Calculate mask of events for a list of marks. + * + * Return true if any of the attached marks want to hold an inode reference. + */ +static bool __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; @@ -261,6 +266,34 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) */ WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask); + return want_iref; +} + +/* + * Calculate mask of events for a list of marks after attach/modify mark + * and get an inode reference for the connector if needed. + * + * A concurrent add of evictable mark and detach of non-evictable mark can + * lead to __fsnotify_recalc_mask() returning false want_iref, but in this + * case we defer clearing iref to fsnotify_recalc_mask_clear_iref() called + * from fsnotify_put_mark(). + */ +static void fsnotify_recalc_mask_set_iref(struct fsnotify_mark_connector *conn) +{ + bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; + bool want_iref = __fsnotify_recalc_mask(conn) || has_iref; + + (void) fsnotify_update_iref(conn, want_iref); +} + +/* + * Calculate mask of events for a list of marks after detach mark + * and return the inode object if its reference is no longer needed. + */ +static void *fsnotify_recalc_mask_clear_iref(struct fsnotify_mark_connector *conn) +{ + bool want_iref = __fsnotify_recalc_mask(conn); + return fsnotify_update_iref(conn, want_iref); } @@ -297,7 +330,7 @@ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); - __fsnotify_recalc_mask(conn); + fsnotify_recalc_mask_set_iref(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* @@ -415,7 +448,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) /* Update watched objects after detaching mark */ if (sb) fsnotify_update_sb_watchers(sb, conn); - objp = __fsnotify_recalc_mask(conn); + objp = fsnotify_recalc_mask_clear_iref(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); From 64a5a3dfa8fd86511657799a30ab2f84bdd83fb0 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Thu, 16 Apr 2026 18:15:23 +0100 Subject: [PATCH 0921/1518] btrfs: fix double-decrement of bytes_may_use in submit_one_async_extent() [ Upstream commit 82323b1a7088b7a5c3e528a5d634bff447fa286f ] submit_one_async_extent() calls btrfs_reserve_extent(), which decrements bytes_may_use. If the call btrfs_create_io_em() fails, we jump to out_free_reserve, which calls extent_clear_unlock_delalloc(). Because we're specifying EXTENT_DO_ACCOUNTING, i.e. EXTENT_CLEAR_META_RESV | EXTENT_CLEAR_DATA_RESV, this decreases bytes_may_use again. This can lead to problems later on, as an initial write can fail only for the writeback to silently ENOSPC. Fix this by replacing EXTENT_DO_ACCOUNTING with EXTENT_CLEAR_META_RESV. This parallels a4fe134fc1d8eb ("btrfs: fix a double release on reserved extents in cow_one_range()"), which is the same fix in cow_one_range(). Fixes: 151a41bc46df ("Btrfs: fix what bits we clear when erroring out from delalloc") Reviewed-by: Qu Wenruo Signed-off-by: Mark Harmstone Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index feaa6de8a90f2..5b99f2941f577 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1208,7 +1208,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, NULL, &cached, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, + EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); free_async_extent_pages(async_extent); From 1aa08e1fd60ab92a241992f322991ea2e01319ff Mon Sep 17 00:00:00 2001 From: Petr Malat Date: Thu, 23 Apr 2026 04:48:26 -0500 Subject: [PATCH 0922/1518] cgroup: Increment nr_dying_subsys_* from rmdir context [ Upstream commit 13e786b64bd3fd81c7eb22aa32bf8305c32f2ccf ] Incrementing nr_dying_subsys_* in offline_css(), which is executed by cgroup_offline_wq worker, leads to a race where user can see the value to be 0 if he reads cgroup.stat after calling rmdir and before the worker executes. This makes the user wrongly expect resources released by the removed cgroup to be available for a new assignment. Increment nr_dying_subsys_* from kill_css(), which is called from the cgroup_rmdir() context. Fixes: ab0312526867 ("cgroup: Show # of subsystem CSSes in cgroup.stat") Signed-off-by: Petr Malat Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/cgroup/cgroup.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b60fc0b2c6036..1239bff9a994c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5773,16 +5773,6 @@ static void offline_css(struct cgroup_subsys_state *css) RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); - - css->cgroup->nr_dying_subsys[ss->id]++; - /* - * Parent css and cgroup cannot be freed until after the freeing - * of child css, see css_free_rwork_fn(). - */ - while ((css = css->parent)) { - css->nr_descendants--; - css->cgroup->nr_dying_subsys[ss->id]++; - } } /** @@ -6094,6 +6084,8 @@ static void css_killed_ref_fn(struct percpu_ref *ref) */ static void kill_css(struct cgroup_subsys_state *css) { + struct cgroup_subsys *ss = css->ss; + lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) @@ -6130,6 +6122,16 @@ static void kill_css(struct cgroup_subsys_state *css) * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); + + css->cgroup->nr_dying_subsys[ss->id]++; + /* + * Parent css and cgroup cannot be freed until after the freeing + * of child css, see css_free_rwork_fn(). + */ + while ((css = css->parent)) { + css->nr_descendants--; + css->cgroup->nr_dying_subsys[ss->id]++; + } } /** From 119e84719f983b8aaf76e2893849ea8f4733da78 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 20 Apr 2026 06:25:09 -0700 Subject: [PATCH 0923/1518] tracing: branch: Fix inverted check on stat tracer registration [ Upstream commit 3b75dd76e64a04771861bb5647951c264919e563 ] init_annotated_branch_stats() and all_annotated_branch_stats() check the return value of register_stat_tracer() with "if (!ret)", but register_stat_tracer() returns 0 on success and a negative errno on failure. The inverted check causes the warning to be printed on every successful registration, e.g.: Warning: could not register annotated branches stats while leaving real failures silent. The initcall also returned a hard-coded 1 instead of the actual error. Invert the check and propagate ret so that the warning fires on real errors and the initcall reports the correct status. Cc: Mathieu Desnoyers Cc: Ingo Molnar Cc: Frederic Weisbecker Link: https://patch.msgid.link/20260420-tracing-v1-1-d8f4cd0d6af1@debian.org Fixes: 002bb86d8d42 ("tracing/ftrace: separate events tracing and stats tracing engine") Signed-off-by: Breno Leitao Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt Signed-off-by: Sasha Levin --- kernel/trace/trace_branch.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 6809b370e991d..d1564db95a8f5 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -373,10 +373,10 @@ __init static int init_annotated_branch_stats(void) int ret; ret = register_stat_tracer(&annotated_branch_stats); - if (!ret) { + if (ret) { printk(KERN_WARNING "Warning: could not register " "annotated branches stats\n"); - return 1; + return ret; } return 0; } @@ -438,10 +438,10 @@ __init static int all_annotated_branch_stats(void) int ret; ret = register_stat_tracer(&all_branch_stats); - if (!ret) { + if (ret) { printk(KERN_WARNING "Warning: could not register " "all branches stats\n"); - return 1; + return ret; } return 0; } From c2a11441538bdbbc5aa003f190995eba93a89b88 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 16 Mar 2026 15:39:35 +0100 Subject: [PATCH 0924/1518] nvmet-tcp: propagate nvmet_tcp_build_pdu_iovec() errors to its callers [ Upstream commit ea8e356acb165cb1fd75537a52e1f66e5e76c538 ] Currently, when nvmet_tcp_build_pdu_iovec() detects an out-of-bounds PDU length or offset, it triggers nvmet_tcp_fatal_error(cmd->queue) and returns early. However, because the function returns void, the callers are entirely unaware that a fatal error has occurred and that the cmd->recv_msg.msg_iter was left uninitialized. Callers such as nvmet_tcp_handle_h2c_data_pdu() proceed to blindly overwrite the queue state with queue->rcv_state = NVMET_TCP_RECV_DATA Consequently, the socket receiving loop may attempt to read incoming network data into the uninitialized iterator. Fix this by shifting the error handling responsibility to the callers. Fixes: 52a0a9854934 ("nvmet-tcp: add bounds checks in nvmet_tcp_build_pdu_iovec") Reviewed-by: Hannes Reinecke Reviewed-by: Yunje Shin Reviewed-by: Chaitanya Kulkarni Signed-off-by: Maurizio Lombardi Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/target/tcp.c | 51 ++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 22 deletions(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 3d8810b42e9dc..97d8c1d3545b0 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -351,7 +351,7 @@ static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue); -static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) +static int nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct bio_vec *iov = cmd->iov; struct scatterlist *sg; @@ -364,22 +364,19 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; - if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } + if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) + return -EPROTO; + sg = &cmd->req.sg[cmd->sg_idx]; sg_remaining = cmd->req.sg_cnt - cmd->sg_idx; while (length) { - if (!sg_remaining) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } - if (!sg->length || sg->length <= sg_offset) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } + if (!sg_remaining) + return -EPROTO; + + if (!sg->length || sg->length <= sg_offset) + return -EPROTO; + u32 iov_len = min_t(u32, length, sg->length - sg_offset); bvec_set_page(iov, sg_page(sg), iov_len, @@ -394,6 +391,7 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) iov_iter_bvec(&cmd->recv_msg.msg_iter, ITER_DEST, cmd->iov, nr_pages, cmd->pdu_len); + return 0; } static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) @@ -958,7 +956,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) return 0; } -static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, +static int nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) { size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); @@ -974,19 +972,23 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, if (!nvme_is_write(cmd->req.cmd) || !data_len || data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); - return; + return 0; } ret = nvmet_tcp_map_data(cmd); if (unlikely(ret)) { pr_err("queue %d: failed to map data\n", queue->idx); nvmet_tcp_fatal_error(queue); - return; + return -EPROTO; } queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_build_pdu_iovec(cmd); cmd->flags |= NVMET_TCP_F_INIT_FAILED; + ret = nvmet_tcp_build_pdu_iovec(cmd); + if (unlikely(ret)) + pr_err("queue %d: failed to build PDU iovec\n", queue->idx); + + return ret; } static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) @@ -1038,7 +1040,10 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) goto err_proto; } cmd->pdu_recv = 0; - nvmet_tcp_build_pdu_iovec(cmd); + if (unlikely(nvmet_tcp_build_pdu_iovec(cmd))) { + pr_err("queue %d: failed to build PDU iovec\n", queue->idx); + goto err_proto; + } queue->cmd = cmd; queue->rcv_state = NVMET_TCP_RECV_DATA; @@ -1101,8 +1106,7 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) le32_to_cpu(req->cmd->common.dptr.sgl.length), le16_to_cpu(req->cqe->status)); - nvmet_tcp_handle_req_failure(queue, queue->cmd, req); - return 0; + return nvmet_tcp_handle_req_failure(queue, queue->cmd, req); } ret = nvmet_tcp_map_data(queue->cmd); @@ -1119,8 +1123,11 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (nvmet_tcp_need_data_in(queue->cmd)) { if (nvmet_tcp_has_inline_data(queue->cmd)) { queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_build_pdu_iovec(queue->cmd); - return 0; + ret = nvmet_tcp_build_pdu_iovec(queue->cmd); + if (unlikely(ret)) + pr_err("queue %d: failed to build PDU iovec\n", + queue->idx); + return ret; } /* send back R2T */ nvmet_tcp_queue_response(&queue->cmd->req); From 1c55053f8ffdc060006df898fd3664e3d1bfac7b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 20 Apr 2026 23:15:32 +0200 Subject: [PATCH 0925/1518] netfilter: arp_tables: fix IEEE1394 ARP payload parsing [ Upstream commit 1e8e3f449b1e73b73a843257635b9c50f0cc0f0a ] Weiming Shi says: "arp_packet_match() unconditionally parses the ARP payload assuming two hardware addresses are present (source and target). However, IPv4-over-IEEE1394 ARP (RFC 2734) omits the target hardware address field, and arp_hdr_len() already accounts for this by returning a shorter length for ARPHRD_IEEE1394 devices. As a result, on IEEE1394 interfaces arp_packet_match() advances past a nonexistent target hardware address and reads the wrong bytes for both the target device address comparison and the target IP address. This causes arptables rules to match against garbage data, leading to incorrect filtering decisions: packets that should be accepted may be dropped and vice versa. The ARP stack in net/ipv4/arp.c (arp_create and arp_process) already handles this correctly by skipping the target hardware address for ARPHRD_IEEE1394. Apply the same pattern to arp_packet_match()." Mangle the original patch to always return 0 (no match) in case user matches on the target hardware address which is never present in IEEE1394. Note that this returns 0 (no match) for either normal and inverse match because matching in the target hardware address in ARPHRD_IEEE1394 has never been supported by arptables. This is intentional, matching on the target hardware address should never evaluate true for ARPHRD_IEEE1394. Moreover, adjust arpt_mangle to drop the packet too as AI suggests: In arpt_mangle, the logic assumes a standard ARP layout. Because IEEE1394 (FireWire) omits the target hardware address, the linear pointer arithmetic miscalculates the offset for the target IP address. This causes mangling operations to write to the wrong location, leading to packet corruption. To ensure safety, this patch drops packets (NF_DROP) when mangling is requested for these fields on IEEE1394 devices, as the current implementation cannot correctly map the FireWire ARP payload. This omits both mangling target hardware and IP address. Even if IP address mangling should be possible in IEEE1394, this would require to adjust arpt_mangle offset calculation, which has never been supported. Based on patch from Weiming Shi . Fixes: 6752c8db8e0c ("firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection.") Reported-by: Xiang Mei Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/ipv4/netfilter/arp_tables.c | 18 +++++++++++++++--- net/ipv4/netfilter/arpt_mangle.c | 8 ++++++++ 2 files changed, 23 insertions(+), 3 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 1cdd9c28ab2da..97ead883e4a13 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -110,13 +110,25 @@ static inline int arp_packet_match(const struct arphdr *arphdr, arpptr += dev->addr_len; memcpy(&src_ipaddr, arpptr, sizeof(u32)); arpptr += sizeof(u32); - tgt_devaddr = arpptr; - arpptr += dev->addr_len; + + if (IS_ENABLED(CONFIG_FIREWIRE_NET) && dev->type == ARPHRD_IEEE1394) { + if (unlikely(memchr_inv(arpinfo->tgt_devaddr.mask, 0, + sizeof(arpinfo->tgt_devaddr.mask)))) + return 0; + + tgt_devaddr = NULL; + } else { + tgt_devaddr = arpptr; + arpptr += dev->addr_len; + } memcpy(&tgt_ipaddr, arpptr, sizeof(u32)); if (NF_INVF(arpinfo, ARPT_INV_SRCDEVADDR, arp_devaddr_compare(&arpinfo->src_devaddr, src_devaddr, - dev->addr_len)) || + dev->addr_len))) + return 0; + + if (tgt_devaddr && NF_INVF(arpinfo, ARPT_INV_TGTDEVADDR, arp_devaddr_compare(&arpinfo->tgt_devaddr, tgt_devaddr, dev->addr_len))) diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index a4e07e5e9c118..f65dd339208e8 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -40,6 +40,10 @@ target(struct sk_buff *skb, const struct xt_action_param *par) } arpptr += pln; if (mangle->flags & ARPT_MANGLE_TDEV) { + if (unlikely(IS_ENABLED(CONFIG_FIREWIRE_NET) && + skb->dev->type == ARPHRD_IEEE1394)) + return NF_DROP; + if (ARPT_DEV_ADDR_LEN_MAX < hln || (arpptr + hln > skb_tail_pointer(skb))) return NF_DROP; @@ -47,6 +51,10 @@ target(struct sk_buff *skb, const struct xt_action_param *par) } arpptr += hln; if (mangle->flags & ARPT_MANGLE_TIP) { + if (unlikely(IS_ENABLED(CONFIG_FIREWIRE_NET) && + skb->dev->type == ARPHRD_IEEE1394)) + return NF_DROP; + if (ARPT_MANGLE_ADDR_LEN_MAX < pln || (arpptr + pln > skb_tail_pointer(skb))) return NF_DROP; From 0bd93ce4f3c35e845532184331d7917d7e562c80 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 16 Apr 2026 15:14:51 +0200 Subject: [PATCH 0926/1518] netfilter: nf_tables: use list_del_rcu for netlink hooks [ Upstream commit f3224ee463f8f6f6ced7dcdf6081add4f8128527 ] nft_netdev_unregister_hooks and __nft_unregister_flowtable_net_hooks need to use list_del_rcu(), this list can be walked by concurrent dumpers. Add a new helper and use it consistently. Fixes: f9a43007d3f7 ("netfilter: nf_tables: double hook unregistration in netns path") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 44 ++++++++++++++--------------------- 1 file changed, 18 insertions(+), 26 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5b25b032e285d..64e6a95439abd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -373,6 +373,12 @@ static void nft_netdev_hook_free_rcu(struct nft_hook *hook) call_rcu(&hook->rcu, __nft_netdev_hook_free_rcu); } +static void nft_netdev_hook_unlink_free_rcu(struct nft_hook *hook) +{ + list_del_rcu(&hook->list); + nft_netdev_hook_free_rcu(hook); +} + static void nft_netdev_unregister_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) @@ -383,10 +389,8 @@ static void nft_netdev_unregister_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) nf_unregister_net_hook(net, ops); - if (release_netdev) { - list_del(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -2322,10 +2326,8 @@ void nf_tables_chain_destroy(struct nft_chain *chain) if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, - &basechain->hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + &basechain->hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { @@ -3025,6 +3027,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, list_for_each_entry(ops, &h->ops_list, list) nf_unregister_net_hook(ctx->net, ops); } + /* hook.list is on stack, no need for list_del_rcu() */ list_del(&h->list); nft_netdev_hook_free_rcu(h); } @@ -9069,10 +9072,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) nft_unregister_flowtable_ops(net, flowtable, ops); - if (release_netdev) { - list_del(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -9143,8 +9144,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, nft_unregister_flowtable_ops(net, flowtable, ops); } - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -9154,10 +9154,8 @@ static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; - list_for_each_entry_safe(hook, next, hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + list_for_each_entry_safe(hook, next, hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, @@ -9245,8 +9243,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, nft_unregister_flowtable_ops(ctx->net, flowtable, ops); } - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -9752,13 +9749,8 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { - struct nft_hook *hook, *next; - flowtable->data.type->free(&flowtable->data); - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + nft_hooks_destroy(&flowtable->hook_list); kfree(flowtable->name); module_put(flowtable->data.type->owner); kfree(flowtable); From 616af8df424c0a9dcd1064875a2f153fffe1f74a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 21 Apr 2026 09:14:02 -0700 Subject: [PATCH 0927/1518] nvme-pci: fix missed admin queue sq doorbell write [ Upstream commit 1cc4cdae2a3b7730d462d69e30f213fd2efe7807 ] We can batch admin commands submitted through io_uring_cmd passthrough, which means bd->last may be false and skips the doorbell write to aggregate multiple commands per write. If a subsequent command can't be dispatched for whatever reason, we have to provide the blk-mq ops' commit_rqs callback in order to ensure we properly update the doorbell. Fixes: 58e5bdeb9c2b ("nvme: enable uring-passthrough for admin commands") Reviewed-by: Christoph Hellwig Reviewed-by: Kanchan Joshi Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 8875855e45352..2e32242bed67c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2028,6 +2028,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) static const struct blk_mq_ops nvme_mq_admin_ops = { .queue_rq = nvme_queue_rq, .complete = nvme_pci_complete_rq, + .commit_rqs = nvme_commit_rqs, .init_hctx = nvme_admin_init_hctx, .init_request = nvme_pci_init_request, .timeout = nvme_timeout, From 24c55a9aa2982c74f1b4e6c77b2362c507270555 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sat, 18 Apr 2026 23:49:30 +0200 Subject: [PATCH 0928/1518] drm/amdgpu/gmc: Fix AMDGPU_GART_PLACEMENT_LOW to not overlap with VRAM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 36d65da7570bf72ce28504fa9a81abfc728e6d96 ] When the GART placement is set to AMDGPU_GART_PLACEMENT_LOW: Make sure that GART does not overlap with VRAM when VRAM is configured to be in the low address space. Solve this according to the following logic: - When GART fits before VRAM, use zero address for GART - Otherwise, put GART after the end of VRAM, aligned to 4 GiB Previously, I had assumed this was not possible so it was OK to not handle it, but now we got a report from a user who has a board that is configured this way. Fixes: 917f91d8d8e8 ("drm/amdgpu/gmc: add a way to force a particular placement for GART") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 3d9de5d86a1658cadb311461b001eb1df67263ad) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index b8613888c5c33..6d5f90512a74e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -313,7 +313,10 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc, mc->gart_start = max_mc_address - mc->gart_size + 1; break; case AMDGPU_GART_PLACEMENT_LOW: - mc->gart_start = 0; + if (size_bf >= mc->gart_size) + mc->gart_start = 0; + else + mc->gart_start = ALIGN(mc->fb_end, four_gb); break; case AMDGPU_GART_PLACEMENT_BEST_FIT: default: From a31c3feb54b15a90232e497ad0e27e8a82052d8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 17 Apr 2026 15:52:45 +0200 Subject: [PATCH 0929/1518] drm/amdgpu: fix AMDGPU_INFO_READ_MMR_REG MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0ef196a208385b7d7da79f411c161b04e97283e2 ] There were multiple issues in that code. First of all the order between the reset semaphore and the mm_lock was wrong (e.g. copy_to_user) was called while holding the lock. Then we allocated memory while holding the reset semaphore which is also a pretty big bug and can deadlock. Then we used down_read_trylock() instead of waiting for the reset to finish. Signed-off-by: Christian König Fixes: 9e823f307074 ("drm/amdgpu: Block MMR_READ IOCTL in reset") Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 361b6e6b303d4b691f6c5974d3eaab67ca6dd90e) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 57 +++++++++++-------------- 1 file changed, 24 insertions(+), 33 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d8c0154c5297d..915406ab9730d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -837,68 +837,59 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ? -EFAULT : 0; } case AMDGPU_INFO_READ_MMR_REG: { - int ret = 0; - unsigned int n, alloc_size; - uint32_t *regs; unsigned int se_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SE_INDEX_SHIFT) & AMDGPU_INFO_MMR_SE_INDEX_MASK; unsigned int sh_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SH_INDEX_SHIFT) & AMDGPU_INFO_MMR_SH_INDEX_MASK; - - if (!down_read_trylock(&adev->reset_domain->sem)) - return -ENOENT; + unsigned int alloc_size; + uint32_t *regs; + int ret; /* set full masks if the userspace set all bits * in the bitfields */ - if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) { + if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; - } else if (se_num >= AMDGPU_GFX_MAX_SE) { - ret = -EINVAL; - goto out; - } + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; - if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) { + if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; - } else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) { - ret = -EINVAL; - goto out; - } + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; - if (info->read_mmr_reg.count > 128) { - ret = -EINVAL; - goto out; - } + if (info->read_mmr_reg.count > 128) + return -EINVAL; - regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL); - if (!regs) { - ret = -ENOMEM; - goto out; - } + regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), + GFP_KERNEL); + if (!regs) + return -ENOMEM; + down_read(&adev->reset_domain->sem); alloc_size = info->read_mmr_reg.count * sizeof(*regs); - amdgpu_gfx_off_ctrl(adev, false); + ret = 0; for (i = 0; i < info->read_mmr_reg.count; i++) { if (amdgpu_asic_read_register(adev, se_num, sh_num, info->read_mmr_reg.dword_offset + i, ®s[i])) { DRM_DEBUG_KMS("unallowed offset %#x\n", info->read_mmr_reg.dword_offset + i); - kfree(regs); - amdgpu_gfx_off_ctrl(adev, true); ret = -EFAULT; - goto out; + break; } } amdgpu_gfx_off_ctrl(adev, true); - n = copy_to_user(out, regs, min(size, alloc_size)); - kfree(regs); - ret = (n ? -EFAULT : 0); -out: up_read(&adev->reset_domain->sem); + + if (!ret) { + ret = copy_to_user(out, regs, min(size, alloc_size)) + ? -EFAULT : 0; + } + kfree(regs); return ret; } case AMDGPU_INFO_DEV_INFO: { From 6d6cd5652c869ba1bb676c8631f108a699a2992c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sat, 18 Apr 2026 23:49:31 +0200 Subject: [PATCH 0930/1518] drm/amdgpu/uvd3.1: Don't validate the firmware when already validated MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 13e4cf116dbf7a1fb8123a59bea2c098f30d3736 ] UVD 3.1 firmware validation seems to always fail after attempting it when it had already been validated. (This works similarly with the VCE 1.0 as well.) Don't attempt repeating the validation when it's already done. This caused issues in situations when the system isn't able to suspend the GPU properly and so the GPU isn't actually powered down. Then amdgpu would fail when calling the IP block resume function. Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/2887 Fixes: bb7978111dd3 ("drm/amdgpu: fix SI UVD firmware validate resume fail") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 889a2cfd889c4a4dd9d0c89ce9a8e60b78be71dd) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 2e79a3afc7748..1df45633e8120 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -242,6 +242,10 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) uint64_t addr; uint32_t size; + /* When the keyselect is already set, don't perturb it. */ + if (RREG32(mmUVD_FW_START)) + return; + /* program the VCPU memory controller bits 0-27 */ addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3; size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3; @@ -284,6 +288,12 @@ static int uvd_v3_1_fw_validate(struct amdgpu_device *adev) int i; uint32_t keysel = adev->uvd.keyselect; + if (RREG32(mmUVD_FW_START) & UVD_FW_STATUS__PASS_MASK) { + dev_dbg(adev->dev, "UVD keyselect already set: 0x%x (on CPU: 0x%x)\n", + RREG32(mmUVD_FW_START), adev->uvd.keyselect); + return 0; + } + WREG32(mmUVD_FW_START, keysel); for (i = 0; i < 10; ++i) { From e0805ccf7917ddbab09700b296d6d9a40d445c8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Sat, 18 Apr 2026 23:49:33 +0200 Subject: [PATCH 0931/1518] drm/amdgpu/gfx6: Support harvested SI chips with disabled TCCs (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit fe2b84f9228e2a0903221a4d0d8c350b018e9c0c ] This commit fixes amdgpu to work on the Radeon HD 7870 XT which has never worked with the Linux open source drivers before. Some boards have "harvested" chips, meaning that some parts of the chip are disabled and fused, and it's sold for cheaper and under a different marketing name. On a harvested chip, any of the following can be disabled: - CUs (Compute Units) - RBs (Render Backend, aka. ROP) - Memory channels (ie. the chip has a lower bandwidth) - TCCs (ie. less L2 cache) Handle chips with harvested TCCs by patching the registers that configure how TCCs are mapped. If some TCCs are disabled, we need to make sure that the disabled TCCs are not used, and the remaining TCCs are used optimally. TCP_CHAN_STEER_LO/HI control which TCC is used by TCP channels. TCP_ADDR_CONFIG.NUM_TCC_BANKS controls how many channels are used. Note that the TCC configuration is highly relevant to performance. Suboptimal configuration (eg. CHAN_STEER=0) can significantly reduce gaming performance. For optimal performance: - Rely on the CHAN_STEER from the golden registers table, only skip disabled TCCs but keep the mapping order. - Limit NUM_TCC_BANKS to number of active TCCs to avoid thrashing, which performs better than using the same TCC twice. v2: - Also consider CGTS_USER_TCC_DISABLE for disabled TCCs. Link: https://bugs.freedesktop.org/show_bug.cgi?id=60879 Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/2664 Fixes: 2cd46ad22383 ("drm/amdgpu: add graphic pipeline implementation for si v8") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 00218d15528fab9f6b31241fe5904eea4fcaa30d) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 66 +++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 80565392313f1..066cdf6863e11 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -1571,6 +1571,71 @@ static void gfx_v6_0_setup_spi(struct amdgpu_device *adev) mutex_unlock(&adev->grbm_idx_mutex); } +/** + * gfx_v6_0_setup_tcc() - setup which TCCs are used + * + * @adev: amdgpu_device pointer + * + * Verify whether the current GPU has any TCCs disabled, + * which can happen when the GPU is harvested and some + * memory channels are disabled, reducing the memory bus width. + * For example, on the Radeon HD 7870 XT (Tahiti LE). + * + * If some TCCs are disabled, we need to make sure that + * the disabled TCCs are not used, and the remaining TCCs + * are used optimally. + * + * TCP_CHAN_STEER_LO/HI control which TCC is used by TCP channels. + * TCP_ADDR_CONFIG.NUM_TCC_BANKS controls how many channels are used. + * + * For optimal performance: + * - Rely on the CHAN_STEER from the golden registers table, + * only skip disabled TCCs but keep the mapping order. + * - Limit NUM_TCC_BANKS to number of active TCCs to avoid thrashing, + * which performs better than using the same TCC twice. + */ +static void gfx_v6_0_setup_tcc(struct amdgpu_device *adev) +{ + u32 i, tcc, tcp_addr_config, num_active_tcc = 0; + u64 chan_steer, patched_chan_steer = 0; + const u32 num_max_tcc = adev->gfx.config.max_texture_channel_caches; + const u32 dis_tcc_mask = + amdgpu_gfx_create_bitmask(num_max_tcc) & + (REG_GET_FIELD(RREG32(mmCGTS_TCC_DISABLE), + CGTS_TCC_DISABLE, TCC_DISABLE) | + REG_GET_FIELD(RREG32(mmCGTS_USER_TCC_DISABLE), + CGTS_USER_TCC_DISABLE, TCC_DISABLE)); + + /* When no TCC is disabled, the golden registers table already has optimal TCC setup */ + if (!dis_tcc_mask) + return; + + /* Each 4-bit nibble contains the index of a TCC used by all TCPs */ + chan_steer = RREG32(mmTCP_CHAN_STEER_LO) | ((u64)RREG32(mmTCP_CHAN_STEER_HI) << 32ull); + + /* Patch the TCP to TCC mapping to skip disabled TCCs */ + for (i = 0; i < num_max_tcc; ++i) { + tcc = (chan_steer >> (u64)(4 * i)) & 0xf; + + if (!((1 << tcc) & dis_tcc_mask)) { + /* Copy enabled TCC indices to the patched register value. */ + patched_chan_steer |= (u64)tcc << (u64)(4 * num_active_tcc); + ++num_active_tcc; + } + } + + WARN_ON(num_active_tcc != num_max_tcc - hweight32(dis_tcc_mask)); + + /* Patch number of TCCs used by TCPs */ + tcp_addr_config = REG_SET_FIELD(RREG32(mmTCP_ADDR_CONFIG), + TCP_ADDR_CONFIG, NUM_TCC_BANKS, + num_active_tcc - 1); + + WREG32(mmTCP_ADDR_CONFIG, tcp_addr_config); + WREG32(mmTCP_CHAN_STEER_HI, upper_32_bits(patched_chan_steer)); + WREG32(mmTCP_CHAN_STEER_LO, lower_32_bits(patched_chan_steer)); +} + static void gfx_v6_0_config_init(struct amdgpu_device *adev) { adev->gfx.config.double_offchip_lds_buf = 0; @@ -1729,6 +1794,7 @@ static void gfx_v6_0_constants_init(struct amdgpu_device *adev) gfx_v6_0_tiling_mode_table_init(adev); gfx_v6_0_setup_rb(adev); + gfx_v6_0_setup_tcc(adev); gfx_v6_0_setup_spi(adev); From 938867e870fb5471bb16f442aeac81326e05bf65 Mon Sep 17 00:00:00 2001 From: Jiexun Wang Date: Fri, 17 Apr 2026 20:25:06 +0800 Subject: [PATCH 0932/1518] netfilter: xt_policy: fix strict mode inbound policy matching [ Upstream commit 4b2b4d7d4e203c92db8966b163edfacb1f0e1e29 ] match_policy_in() walks sec_path entries from the last transform to the first one, but strict policy matching needs to consume info->pol[] in the same forward order as the rule layout. Derive the strict-match policy position from the number of transforms already consumed so that multi-element inbound rules are matched consistently. Fixes: c4b885139203 ("[NETFILTER]: x_tables: replace IPv4/IPv6 policy match by address family independant version") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Jiexun Wang Signed-off-by: Ren Wei Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/xt_policy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index cb6e8279010a4..b5fa65558318f 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -63,7 +63,7 @@ match_policy_in(const struct sk_buff *skb, const struct xt_policy_info *info, return 0; for (i = sp->len - 1; i >= 0; i--) { - pos = strict ? i - sp->len + 1 : 0; + pos = strict ? sp->len - i - 1 : 0; if (pos >= info->len) return 0; e = &info->pol[pos]; From 7df9863bf538a626e8a684e59cb2c43eac0ef3c8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Apr 2026 02:19:11 +0200 Subject: [PATCH 0933/1518] netfilter: nf_conntrack_sip: don't use simple_strtoul MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8cf6809cddcbe301aedfc6b51bcd4944d45795f6 ] Replace unsafe port parsing in epaddr_len(), ct_sip_parse_header_uri(), and ct_sip_parse_request() with a new sip_parse_port() helper that validates each digit against the buffer limit, eliminating the use of simple_strtoul() which assumes NUL-terminated strings. The previous code dereferenced pointers without bounds checks after sip_parse_addr() and relied on simple_strtoul() on non-NUL-terminated skb data. A port that reaches the buffer limit without a trailing character is also rejected as malformed. Also get rid of all simple_strtoul() usage in conntrack, prefer a stricter version instead. There are intentional changes: - Bail out if number is > UINT_MAX and indicate a failure, same for too long sequences. While we do accept 05535 as port 5535, we will not accept e.g. 'sip:10.0.0.1:005060'. While its syntactically valid under RFC 3261, we should restrict this to not waste cycles when presented with malformed packets with 64k '0' characters. - Force base 10 in ct_sip_parse_numerical_param(). This is used to fetch 'expire=' and 'rports='; both are expected to use base-10. - In nf_nat_sip.c, only accept the parsed value if its within the 1k-64k range. - epaddr_len now returns 0 if the port is invalid, as it already does for invalid ip addresses. This is intentional. nf_conntrack_sip performs lots of guesswork to find the right parts of the message to parse. Being stricter could break existing setups. Connection tracking helpers are designed to allow traffic to pass, not to block it. Based on an earlier patch from Jenny Guanni Qu . Fixes: 05e3ced297fe ("[NETFILTER]: nf_conntrack_sip: introduce SIP-URI parsing helper") Reported-by: Klaudia Kloc Reported-by: Dawid Moczadło Reported-by: Jenny Guanni Qu . Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_sip.c | 152 ++++++++++++++++++++++++------- net/netfilter/nf_nat_sip.c | 1 + 2 files changed, 119 insertions(+), 34 deletions(-) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 939502ff7c871..6eb39285fbd6c 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -181,6 +181,57 @@ static int sip_parse_addr(const struct nf_conn *ct, const char *cp, return 1; } +/* Parse optional port number after IP address. + * Returns false on malformed input, true otherwise. + * If port is non-NULL, stores parsed port in network byte order. + * If no port is present, sets *port to default SIP port. + */ +static bool sip_parse_port(const char *dptr, const char **endp, + const char *limit, __be16 *port) +{ + unsigned int p = 0; + int len = 0; + + if (dptr >= limit) + return false; + + if (*dptr != ':') { + if (port) + *port = htons(SIP_PORT); + if (endp) + *endp = dptr; + return true; + } + + dptr++; /* skip ':' */ + + while (dptr < limit && isdigit(*dptr)) { + p = p * 10 + (*dptr - '0'); + dptr++; + len++; + if (len > 5) /* max "65535" */ + return false; + } + + if (len == 0) + return false; + + /* reached limit while parsing port */ + if (dptr >= limit) + return false; + + if (p < 1024 || p > 65535) + return false; + + if (port) + *port = htons(p); + + if (endp) + *endp = dptr; + + return true; +} + /* skip ip address. returns its length. */ static int epaddr_len(const struct nf_conn *ct, const char *dptr, const char *limit, int *shift) @@ -193,11 +244,8 @@ static int epaddr_len(const struct nf_conn *ct, const char *dptr, return 0; } - /* Port number */ - if (*dptr == ':') { - dptr++; - dptr += digits_len(ct, dptr, limit, shift); - } + if (!sip_parse_port(dptr, &dptr, limit, NULL)) + return 0; return dptr - aux; } @@ -228,6 +276,51 @@ static int skp_epaddr_len(const struct nf_conn *ct, const char *dptr, return epaddr_len(ct, dptr, limit, shift); } +/* simple_strtoul stops after first non-number character. + * But as we're not dealing with c-strings, we can't rely on + * hitting \r,\n,\0 etc. before moving past end of buffer. + * + * This is a variant of simple_strtoul, but doesn't require + * a c-string. + * + * If value exceeds UINT_MAX, 0 is returned. + */ +static unsigned int sip_strtouint(const char *cp, unsigned int len, char **endp) +{ + const unsigned int max = sizeof("4294967295"); + unsigned int olen = len; + const char *s = cp; + u64 result = 0; + + if (len > max) + len = max; + + while (olen > 0 && isdigit(*s)) { + unsigned int value; + + if (len == 0) + goto err; + + value = *s - '0'; + result = result * 10 + value; + + if (result > UINT_MAX) + goto err; + s++; + len--; + olen--; + } + + if (endp) + *endp = (char *)s; + + return result; +err: + if (endp) + *endp = (char *)cp; + return 0; +} + /* Parse a SIP request line of the form: * * Request-Line = Method SP Request-URI SP SIP-Version CRLF @@ -241,7 +334,6 @@ int ct_sip_parse_request(const struct nf_conn *ct, { const char *start = dptr, *limit = dptr + datalen, *end; unsigned int mlen; - unsigned int p; int shift = 0; /* Skip method and following whitespace */ @@ -267,14 +359,8 @@ int ct_sip_parse_request(const struct nf_conn *ct, if (!sip_parse_addr(ct, dptr, &end, addr, limit, true)) return -1; - if (end < limit && *end == ':') { - end++; - p = simple_strtoul(end, (char **)&end, 10); - if (p < 1024 || p > 65535) - return -1; - *port = htons(p); - } else - *port = htons(SIP_PORT); + if (!sip_parse_port(end, &end, limit, port)) + return -1; if (end == dptr) return 0; @@ -509,7 +595,6 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr, union nf_inet_addr *addr, __be16 *port) { const char *c, *limit = dptr + datalen; - unsigned int p; int ret; ret = ct_sip_walk_headers(ct, dptr, dataoff ? *dataoff : 0, datalen, @@ -520,14 +605,8 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr, if (!sip_parse_addr(ct, dptr + *matchoff, &c, addr, limit, true)) return -1; - if (*c == ':') { - c++; - p = simple_strtoul(c, (char **)&c, 10); - if (p < 1024 || p > 65535) - return -1; - *port = htons(p); - } else - *port = htons(SIP_PORT); + if (!sip_parse_port(c, &c, limit, port)) + return -1; if (dataoff) *dataoff = c - dptr; @@ -609,7 +688,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, return 0; start += strlen(name); - *val = simple_strtoul(start, &end, 0); + *val = sip_strtouint(start, limit - start, (char **)&end); if (start == end) return -1; if (matchoff && matchlen) { @@ -1065,6 +1144,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, mediaoff = sdpoff; for (i = 0; i < ARRAY_SIZE(sdp_media_types); ) { + char *end; + if (ct_sip_get_sdp_header(ct, *dptr, mediaoff, *datalen, SDP_HDR_MEDIA, SDP_HDR_UNSPEC, &mediaoff, &medialen) <= 0) @@ -1080,8 +1161,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, mediaoff += t->len; medialen -= t->len; - port = simple_strtoul(*dptr + mediaoff, NULL, 10); - if (port == 0) + port = sip_strtouint(*dptr + mediaoff, *datalen - mediaoff, (char **)&end); + if (port == 0 || *dptr + mediaoff == end) continue; if (port < 1024 || port > 65535) { nf_ct_helper_log(skb, ct, "wrong port %u", port); @@ -1255,7 +1336,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, */ if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_EXPIRES, &matchoff, &matchlen) > 0) - expires = simple_strtoul(*dptr + matchoff, NULL, 10); + expires = sip_strtouint(*dptr + matchoff, *datalen - matchoff, NULL); ret = ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, SIP_HDR_CONTACT, NULL, @@ -1359,7 +1440,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int protoff, if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_EXPIRES, &matchoff, &matchlen) > 0) - expires = simple_strtoul(*dptr + matchoff, NULL, 10); + expires = sip_strtouint(*dptr + matchoff, *datalen - matchoff, NULL); while (1) { unsigned int c_expires = expires; @@ -1419,10 +1500,12 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); unsigned int matchoff, matchlen, matchend; unsigned int code, cseq, i; + char *end; if (*datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; - code = simple_strtoul(*dptr + strlen("SIP/2.0 "), NULL, 10); + code = sip_strtouint(*dptr + strlen("SIP/2.0 "), + *datalen - strlen("SIP/2.0 "), NULL); if (!code) { nf_ct_helper_log(skb, ct, "cannot get code"); return NF_DROP; @@ -1433,8 +1516,8 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, nf_ct_helper_log(skb, ct, "cannot parse cseq"); return NF_DROP; } - cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq && *(*dptr + matchoff) != '0') { + cseq = sip_strtouint(*dptr + matchoff, *datalen - matchoff, (char **)&end); + if (*dptr + matchoff == end) { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1483,6 +1566,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { const struct sip_handler *handler; + char *end; handler = &sip_handlers[i]; if (handler->request == NULL) @@ -1499,8 +1583,8 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, nf_ct_helper_log(skb, ct, "cannot parse cseq"); return NF_DROP; } - cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq && *(*dptr + matchoff) != '0') { + cseq = sip_strtouint(*dptr + matchoff, *datalen - matchoff, (char **)&end); + if (*dptr + matchoff == end) { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1576,7 +1660,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, &matchoff, &matchlen) <= 0) break; - clen = simple_strtoul(dptr + matchoff, (char **)&end, 10); + clen = sip_strtouint(dptr + matchoff, datalen - matchoff, (char **)&end); if (dptr + matchoff == end) break; diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index c845b6d1a2bdf..9fbfc6bff0c22 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -246,6 +246,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, if (ct_sip_parse_numerical_param(ct, *dptr, matchend, *datalen, "rport=", &poff, &plen, &n) > 0 && + n >= 1024 && n <= 65535 && htons(n) == ct->tuplehash[dir].tuple.dst.u.udp.port && htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; From 6c554462a6add299de557e74bd3112f52c56c7aa Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Thu, 23 Apr 2026 15:30:58 -0300 Subject: [PATCH 0934/1518] ASoC: amd: acp: Add DMI quirk for Valve Steam Deck OLED [ Upstream commit b0f6f4ac7d5d04fe2adcdd63ed1cd1ad505b8958 ] Commit 671dd2ffbd8b ("ASoC: amd: acp: Add new cpu dai and dailink creation for I2S BT instance") introduced a change that "broke" Steam Deck's audio probe, in the OLED model, as observed in the following dmesg snippet: [...] snd_sof_amd_vangogh 0000:04:00.5: Topology: ABI 3:26:0 Kernel ABI 3:23:1 sof_mach nau8821-max: ASoC: physical link acp-bt-codec (id 2) not exist sof_mach nau8821-max: ASoC: topology: could not load header: -22 snd_sof_amd_vangogh 0000:04:00.5: tplg amd/sof-tplg/sof-vangogh-nau8821-max.tplg component load failed -22 snd_sof_amd_vangogh 0000:04:00.5: error: failed to load DSP topology -22 snd_sof_amd_vangogh 0000:04:00.5: ASoC error (-22): at snd_soc_component_probe() on 0000:04:00.5 sof_mach nau8821-max: ASoC: failed to instantiate card -22 sof_mach nau8821-max: error -EINVAL: Failed to register card(sof-nau8821-max) sof_mach nau8821-max: probe with driver sof_mach failed with error -22 [...] Notice the quotes in "broke": it's not really a bug in such commit, but instead a problem with a topology file from Steam Deck OLED. This was discussed to great extent in [1], and Cristian proposed a pretty simple and functional change that resolved the issue for the Deck's issue. That change, though, would break other devices, so it wasn't accepted upstream. And the proper suggested solution (fix the topology) was never implemented, so Valve's kernel (and anyone that wants to boot the mainline on Steam Deck OLED) is carrying that fix downstream. So, we propose hereby a different approach: a DMI quirk, as many already present in the sound drivers, to address this issue solely on Steam Deck OLED, not breaking other devices and as a bonus, allowing simple patch up in case eventually the topology file gets fixed (we'd just need to check against any DMI info reflecting that or the topology/FW versions). The motivation of such upstream quirk is related to users that want to test latest kernel trees on their devices and get no only non-working sound device, but seems some games (like Ori and the Blind Forest) can't properly work without a proper functional audio device. Example of such report can be seen at [2]. Cc: Mark Brown Cc: Robert Beckett Cc: Umang Jain Fixes: 671dd2ffbd8b ("ASoC: amd: acp: Add new cpu dai and dailink creation for I2S BT instance") Link: https://lore.kernel.org/r/20231209205351.880797-11-cristian.ciocaltea@collabora.com/ [1] Link: https://bugzilla.kernel.org/show_bug.cgi?id=218677 [2] Reviewed-by: Cristian Ciocaltea Reviewed-by: Mario Limonciello Tested-by: Melissa Wen Signed-off-by: Guilherme G. Piccoli Link: https://patch.msgid.link/20260423183505.116445-1-gpiccoli@igalia.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/amd/acp/acp-legacy-mach.c | 2 +- sound/soc/amd/acp/acp-mach-common.c | 22 +++++++++++++++++++--- sound/soc/amd/acp/acp-mach.h | 4 ++++ sound/soc/amd/acp/acp-sof-mach.c | 2 +- 4 files changed, 25 insertions(+), 5 deletions(-) diff --git a/sound/soc/amd/acp/acp-legacy-mach.c b/sound/soc/amd/acp/acp-legacy-mach.c index a7a551366a409..235d6cc83fa98 100644 --- a/sound/soc/amd/acp/acp-legacy-mach.c +++ b/sound/soc/amd/acp/acp-legacy-mach.c @@ -174,7 +174,7 @@ static int acp_asoc_probe(struct platform_device *pdev) acp_card_drvdata->acp_rev = mach->mach_params.subsystem_rev; dmi_id = dmi_first_match(acp_quirk_table); - if (dmi_id && dmi_id->driver_data) + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_TDM_MODE_ENABLE) acp_card_drvdata->tdm_mode = dmi_id->driver_data; ret = acp_legacy_dai_links_create(card); diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c index c4bc8e849284c..a2031e7f61424 100644 --- a/sound/soc/amd/acp/acp-mach-common.c +++ b/sound/soc/amd/acp/acp-mach-common.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "../../codecs/rt5682.h" #include "../../codecs/rt1019.h" @@ -37,15 +38,21 @@ #define NAU8821_FREQ_OUT 12288000 #define MAX98388_CODEC_DAI "max98388-aif1" -#define TDM_MODE_ENABLE 1 - const struct dmi_system_id acp_quirk_table[] = { { /* Google skyrim proto-0 */ .matches = { DMI_EXACT_MATCH(DMI_PRODUCT_FAMILY, "Google_Skyrim"), }, - .driver_data = (void *)TDM_MODE_ENABLE, + .driver_data = (void *)QUIRK_TDM_MODE_ENABLE, + }, + { + /* Valve Steam Deck OLED */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Valve"), + DMI_MATCH(DMI_PRODUCT_NAME, "Galileo"), + }, + .driver_data = (void *)QUIRK_REMAP_DMIC_BT, }, {} }; @@ -1385,6 +1392,7 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card) struct snd_soc_dai_link *links; struct device *dev = card->dev; struct acp_card_drvdata *drv_data = card->drvdata; + const struct dmi_system_id *dmi_id = dmi_first_match(acp_quirk_table); int i = 0, num_links = 0; if (drv_data->hs_cpu_id) @@ -1556,6 +1564,9 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card) links[i].codecs = &snd_soc_dummy_dlc; links[i].num_codecs = 1; } + + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_REMAP_DMIC_BT) + links[i].id = DMIC_BE_ID; i++; } @@ -1571,6 +1582,11 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card) links[i].capture_only = 1; links[i].nonatomic = true; links[i].no_pcm = 1; + + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_REMAP_DMIC_BT) { + links[i].id = BT_BE_ID; + dev_dbg(dev, "quirk REMAP_DMIC_BT enabled\n"); + } } card->dai_link = links; diff --git a/sound/soc/amd/acp/acp-mach.h b/sound/soc/amd/acp/acp-mach.h index f94c30c20f20b..7177d3fd96192 100644 --- a/sound/soc/amd/acp/acp-mach.h +++ b/sound/soc/amd/acp/acp-mach.h @@ -26,6 +26,10 @@ #define acp_get_drvdata(card) ((struct acp_card_drvdata *)(card)->drvdata) +/* List of DMI quirks - check acp-mach-common.c for usage. */ +#define QUIRK_TDM_MODE_ENABLE 1 +#define QUIRK_REMAP_DMIC_BT 2 + enum be_id { HEADSET_BE_ID = 0, AMP_BE_ID, diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c index 6215e31eceddf..36ecef7013b9c 100644 --- a/sound/soc/amd/acp/acp-sof-mach.c +++ b/sound/soc/amd/acp/acp-sof-mach.c @@ -110,7 +110,7 @@ static int acp_sof_probe(struct platform_device *pdev) acp_card_drvdata = card->drvdata; dmi_id = dmi_first_match(acp_quirk_table); - if (dmi_id && dmi_id->driver_data) + if (dmi_id && dmi_id->driver_data == (void *)QUIRK_TDM_MODE_ENABLE) acp_card_drvdata->tdm_mode = dmi_id->driver_data; acp_card_drvdata->acp_rev = mach->mach_params.subsystem_rev; From 9834d8cc89feb6f8e39bb7c3247e03251fc44e59 Mon Sep 17 00:00:00 2001 From: John Madieu Date: Sat, 25 Apr 2026 09:29:34 +0000 Subject: [PATCH 0935/1518] spi: rockchip: Read ISR, not IMR, to detect cs-inactive IRQ [ Upstream commit b4683a239a409d65f88052f5630c748a8ba070cd ] rockchip_spi_isr() decides whether the current interrupt was the cs-inactive event by reading IMR: if (rs->cs_inactive && readl_relaxed(rs->regs + ROCKCHIP_SPI_IMR) & INT_CS_INACTIVE) ctlr->target_abort(ctlr); IMR is the interrupt mask register: it tells which sources are enabled, not which one fired. In the PIO path, rockchip_spi_prepare_irq() enables both INT_RF_FULL and INT_CS_INACTIVE in IMR when rs->cs_inactive is true: if (rs->cs_inactive) writel_relaxed(INT_RF_FULL | INT_CS_INACTIVE, rs->regs + ROCKCHIP_SPI_IMR); so the IMR check is always true once cs_inactive is enabled, and every PIO interrupt - including normal RF_FULL completions - is dispatched to ctlr->target_abort(), aborting the transfer. The bug is reachable on ROCKCHIP_SPI_VER2_TYPE2 in target mode with a DMA-capable controller when the transfer is short enough to fall back to PIO (rockchip_spi_can_dma() returns false below fifo_len). Read ISR (which is RISR masked by IMR) so the check actually reflects which interrupt fired, and parenthesise the expression for clarity while at it. Fixes: 869f2c94db92 ("spi: rockchip: Stop spi slave dma receiver when cs inactive") Signed-off-by: John Madieu Link: https://patch.msgid.link/20260425092936.2590132-2-john.madieu@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-rockchip.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 45b1ad40a7efc..f7001c7bbe109 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -357,7 +357,8 @@ static irqreturn_t rockchip_spi_isr(int irq, void *dev_id) struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); /* When int_cs_inactive comes, spi target abort */ - if (rs->cs_inactive && readl_relaxed(rs->regs + ROCKCHIP_SPI_IMR) & INT_CS_INACTIVE) { + if (rs->cs_inactive && + (readl_relaxed(rs->regs + ROCKCHIP_SPI_ISR) & INT_CS_INACTIVE)) { ctlr->target_abort(ctlr); writel_relaxed(0, rs->regs + ROCKCHIP_SPI_IMR); writel_relaxed(0xffffffff, rs->regs + ROCKCHIP_SPI_ICR); From 6c06e9ba8753d0b9c0748fe919d237b367a5cbe1 Mon Sep 17 00:00:00 2001 From: James Calligeros Date: Sat, 25 Apr 2026 10:44:03 +1000 Subject: [PATCH 0936/1518] ASoC: tas2764: Mark die temp register as volatile [ Upstream commit 4cfb5971c2fbfac061c23fb4224a3a008199de81 ] Reading the temperature register always returns the first value read from the chip due to regcache. Mark TAS2764_TEMP as volatile to prevent returning stale, cached values when reading the die temp. Fixes: 186dfc85f9a8 ("ASoC: tas2764: expose die temp to hwmon") Signed-off-by: James Calligeros Link: https://patch.msgid.link/20260425-tas27xx-hwmon-fixes-v1-1-83c13b8e8f54@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/tas2764.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c index 36e25e48b3546..9f351565dc82d 100644 --- a/sound/soc/codecs/tas2764.c +++ b/sound/soc/codecs/tas2764.c @@ -809,6 +809,7 @@ static bool tas2764_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { case TAS2764_SW_RST: + case TAS2764_TEMP: case TAS2764_INT_LTCH0 ... TAS2764_INT_LTCH4: case TAS2764_INT_CLK_CFG: return true; From f4343ddee93becbe549139d26d2d87f3f7cbc760 Mon Sep 17 00:00:00 2001 From: James Calligeros Date: Sat, 25 Apr 2026 10:44:05 +1000 Subject: [PATCH 0937/1518] ASoC: tas2770: Fix order of operations for temperature calculation [ Upstream commit c7ecb6a61908c2604dda6e42da66724d256de7b9 ] The order of operations to derive the temperature from the temp register values was wrong, since 1000 / 16 is not an integer. This resulted in the calculated temperature value deviating from the value represented by the registers slightly, which was most obvious when the registers were zeroed (-92.265 *C vs the expected -93.000 *C). Scale the reading before dividing the whole thing by 16 to correct this. Fixes: ff73e2780169 ("ASoC: tas2770: expose die temp to hwmon") Signed-off-by: James Calligeros Link: https://patch.msgid.link/20260425-tas27xx-hwmon-fixes-v1-3-83c13b8e8f54@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/tas2770.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c index 6f878b01716f7..2ce3011119bdb 100644 --- a/sound/soc/codecs/tas2770.c +++ b/sound/soc/codecs/tas2770.c @@ -549,7 +549,7 @@ static int tas2770_read_die_temp(struct tas2770_priv *tas2770, long *result) /* * As per datasheet: divide register by 16 and subtract 93 to get * degrees Celsius. hwmon requires millidegrees. Let's avoid rounding - * errors by subtracting 93 * 16 then multiplying by 1000 / 16. + * errors by subtracting 93 * 16 and scaling before dividing. * * NOTE: The ADC registers are initialised to 0 on reset. This means * that the temperature will read -93 *C until the chip is brought out @@ -558,7 +558,7 @@ static int tas2770_read_die_temp(struct tas2770_priv *tas2770, long *result) * value read back from its registers will be the last value sampled * before entering software shutdown. */ - *result = (reading - (93 * 16)) * (1000 / 16); + *result = (reading - (93 * 16)) * 1000 / 16; return 0; } From df332876455c9176d84e3f56b1ed1796f666615c Mon Sep 17 00:00:00 2001 From: Yuho Choi Date: Sun, 19 Apr 2026 20:25:13 -0400 Subject: [PATCH 0938/1518] drm/sysfb: ofdrm: fix PCI device reference leaks [ Upstream commit 4aa8110000b0d215deef8eed283565dd0c1def88 ] display_get_pci_dev_of() gets a referenced PCI device via pci_get_device(). Drop that reference when pci_enable_device() fails and release it during the managed teardown path after pci_disable_device(). Without that, ofdrm leaks the pci_dev reference on both the error path and the normal cleanup path. Fixes: c8a17756c425 ("drm/ofdrm: Add ofdrm for Open Firmware framebuffers") Co-developed-by: Myeonghun Pak Signed-off-by: Myeonghun Pak Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Co-developed-by: Taegyu Kim Signed-off-by: Taegyu Kim Signed-off-by: Yuho Choi Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260420002513.216-1-dbgh9129@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/sysfb/ofdrm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/sysfb/ofdrm.c b/drivers/gpu/drm/sysfb/ofdrm.c index 8d8ab39c5f363..f94fddea897a5 100644 --- a/drivers/gpu/drm/sysfb/ofdrm.c +++ b/drivers/gpu/drm/sysfb/ofdrm.c @@ -349,6 +349,7 @@ static void ofdrm_pci_release(void *data) struct pci_dev *pcidev = data; pci_disable_device(pcidev); + pci_dev_put(pcidev); } static int ofdrm_device_init_pci(struct ofdrm_device *odev) @@ -374,6 +375,7 @@ static int ofdrm_device_init_pci(struct ofdrm_device *odev) if (ret) { drm_err(dev, "pci_enable_device(%s) failed: %d\n", dev_name(&pcidev->dev), ret); + pci_dev_put(pcidev); return ret; } ret = devm_add_action_or_reset(&pdev->dev, ofdrm_pci_release, pcidev); From 793bae6ce71c7265d0e92425b18b2a20c50507e8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 21 Apr 2026 09:48:32 +0200 Subject: [PATCH 0939/1518] drm/color-mgmt: Typo s/R332/RGB332/ [ Upstream commit 9d5a2b8f6281f6090002517fb9272ea07038afe8 ] Fix a typo of "RGB332" in kerneldoc for the drm_crtc_fill_palette_332() helper. Fixes: 7ff61177b7116825 ("drm/color-mgmt: Prepare for RGB332 palettes") Signed-off-by: Geert Uytterhoeven Reviewed-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/c413e45c8f752a532a4ff377f7a8b9eaab4a082a.1776757681.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_color_mgmt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index 131c1c9ae92fc..302a32d050a6d 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -831,7 +831,7 @@ static void fill_palette_332(struct drm_crtc *crtc, u16 r, u16 g, u16 b, } /** - * drm_crtc_fill_palette_332 - Programs a default palette for R332-like formats + * drm_crtc_fill_palette_332 - Programs a default palette for RGB332-like formats * @crtc: The displaying CRTC * @set_palette: Callback for programming the hardware gamma LUT * From b69f420c98b2807e71ffb02cf6180da9494b01d3 Mon Sep 17 00:00:00 2001 From: Wentao Guan Date: Mon, 13 Apr 2026 17:54:59 +0800 Subject: [PATCH 0940/1518] arm64/scs: Fix potential sign extension issue of advance_loc4 [ Upstream commit 4023b7424ecd5d38cc75b650d6c1bf630ef8cb40 ] The expression (*opcode++ << 24) and exp * code_alignment_factor may overflow signed int and becomes negative. Fix this by casting each byte to u64 before shifting. Also fix the misaligned break statement while we are here. Example of the result can be seen here: Link: https://godbolt.org/z/zhY8d3595 It maybe not a real problem, but could be a issue in future. Fixes: d499e9627d70 ("arm64/scs: Fix handling of advance_loc4") Signed-off-by: Wentao Guan Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/kernel/pi/patch-scs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index dac568e4a54f2..3944ad899021c 100644 --- a/arch/arm64/kernel/pi/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -196,9 +196,9 @@ static int scs_handle_fde_frame(const struct eh_frame *frame, loc += *opcode++ * code_alignment_factor; loc += (*opcode++ << 8) * code_alignment_factor; loc += (*opcode++ << 16) * code_alignment_factor; - loc += (*opcode++ << 24) * code_alignment_factor; + loc += ((u64)*opcode++ << 24) * code_alignment_factor; size -= 4; - break; + break; case DW_CFA_def_cfa: case DW_CFA_offset_extended: From f6553cca177509c60e8e22d60805aa3245d2a715 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 21 Apr 2026 08:02:15 -0700 Subject: [PATCH 0941/1518] ACPICA: Provide #defines for EINJV2 error types [ Upstream commit 1f6008538384453eb4c13a3d7ff9e37ee8aee6b9 ] EINJV2 defined new error types by moving the severity (correctable, uncorrectable non-fatal, uncorrectable fatal) out of the "type". ACPI 6.5 introduced EINJV2 and defined a vendor defined error type using bit 31. This was dropped in ACPI 6.6. Link: https://github.com/acpica/acpica/commit/e82d2d2fd145 Signed-off-by: Tony Luck Link: https://patch.msgid.link/20260421150216.11666-2-tony.luck@intel.com Signed-off-by: Rafael J. Wysocki Stable-dep-of: 0c00cfbcfcff ("ACPI: APEI: EINJ: Fix EINJV2 memory error injection") Signed-off-by: Sasha Levin --- include/acpi/actbl1.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 7f35eb0e84586..b074244cbdcbf 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -1129,6 +1129,12 @@ enum acpi_einj_command_status { #define ACPI_EINJ_CXL_MEM_FATAL (1<<17) #define ACPI_EINJ_VENDOR_DEFINED (1<<31) +/* EINJV2 error types from EINJV2_GET_ERROR_TYPE (ACPI 6.6) */ + +#define ACPI_EINJV2_PROCESSOR (1) +#define ACPI_EINJV2_MEMORY (1<<1) +#define ACPI_EINJV2_PCIE (1<<2) + /******************************************************************************* * * ERST - Error Record Serialization Table (ACPI 4.0) From 156f410cafa2266bbcdf365c60d4dd5487556c98 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 21 Apr 2026 08:02:16 -0700 Subject: [PATCH 0942/1518] ACPI: APEI: EINJ: Fix EINJV2 memory error injection [ Upstream commit 0c00cfbcfcffa7085e4f0c7fd7a4caada4e7a90f ] Error types in EINJV2 use different bit positions for each flavor of injection from legacy EINJ. Two issues: 1) The address sanity checks in einj_error_inject() were skipped for EINJV2 injections. Noted by sashiko[1] 2) __einj_error_trigger() failed to drop the entry of the target physical address from the list of resources that need to be requested. Add a helper function that checks if an injection is to memory and use it to solve each of these issues. Note that the old test in __einj_error_trigger() checked that param2 was not zero. This isn't needed because the sanity checks in einj_error_inject() reject memory injections with param2 == 0. Fixes: b47610296d17 ("ACPI: APEI: EINJ: Enable EINJv2 error injections") Reported-by: sashiko Reported-by: Herman Li Signed-off-by: Tony Luck Tested-by: "Lai, Yi1" Link: https://sashiko.dev/#/patchset/20260415163620.12957-1-tony.luck%40intel.com # [1] Reviewed-by: Jiaqi Yan Reviewed-by: Zaid Alali Link: https://patch.msgid.link/20260421150216.11666-3-tony.luck@intel.com Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/apei/einj-core.c | 45 +++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index 305c240a303f6..02b81b7b5a2e2 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -401,8 +401,18 @@ static struct acpi_generic_address *einj_get_trigger_parameter_region( return NULL; } + +static bool is_memory_injection(u32 type, u32 flags) +{ + if (flags & SETWA_FLAGS_EINJV2) + return !!(type & ACPI_EINJV2_MEMORY); + if (type & ACPI5_VENDOR_BIT) + return !!(vendor_flags & SETWA_FLAGS_MEM); + return !!(type & MEM_ERROR_MASK) || !!(flags & SETWA_FLAGS_MEM); +} + /* Execute instructions in trigger error action table */ -static int __einj_error_trigger(u64 trigger_paddr, u32 type, +static int __einj_error_trigger(u64 trigger_paddr, u32 type, u32 flags, u64 param1, u64 param2) { struct acpi_einj_trigger trigger_tab; @@ -480,7 +490,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type, * This will cause resource conflict with regular memory. So * remove it from trigger table resources. */ - if ((param_extension || acpi5) && (type & MEM_ERROR_MASK) && param2) { + if ((param_extension || acpi5) && is_memory_injection(type, flags)) { struct apei_resources addr_resources; apei_resources_init(&addr_resources); @@ -660,7 +670,7 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, return rc; trigger_paddr = apei_exec_ctx_get_output(&ctx); if (notrigger == 0) { - rc = __einj_error_trigger(trigger_paddr, type, param1, param2); + rc = __einj_error_trigger(trigger_paddr, type, flags, param1, param2); if (rc) return rc; } @@ -718,35 +728,30 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3, SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2))) return -EINVAL; + /* + * Injections targeting a CXL 1.0/1.1 port have to be injected + * via the einj_cxl_rch_error_inject() path as that does the proper + * validation of the given RCRB base (MMIO) address. + */ + if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)) + return -EINVAL; + /* check if type is a valid EINJv2 error type */ if (is_v2) { if (!(type & available_error_type_v2)) return -EINVAL; } - /* - * We need extra sanity checks for memory errors. - * Other types leap directly to injection. - */ /* ensure param1/param2 existed */ if (!(param_extension || acpi5)) goto inject; - /* ensure injection is memory related */ - if (type & ACPI5_VENDOR_BIT) { - if (vendor_flags != SETWA_FLAGS_MEM) - goto inject; - } else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) { - goto inject; - } - /* - * Injections targeting a CXL 1.0/1.1 port have to be injected - * via the einj_cxl_rch_error_inject() path as that does the proper - * validation of the given RCRB base (MMIO) address. + * We need extra sanity checks for memory errors. + * Other types leap directly to injection. */ - if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)) - return -EINVAL; + if (!is_memory_injection(type, flags)) + goto inject; /* * Disallow crazy address masks that give BIOS leeway to pick From c9553e0567b0b843c15cacac62e2ff87bfdaa3ea Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Mon, 27 Apr 2026 22:01:39 +0100 Subject: [PATCH 0943/1518] cdrom, scsi: sr: propagate read-only status to block layer via set_disk_ro() [ Upstream commit 0898a817621a2f0cddca8122d9b974003fe5036d ] The cdrom core never calls set_disk_ro() for a registered device, so BLKROGET on a CD-ROM device always returns 0 (writable), even when the drive has no write capabilities and writes will inevitably fail. This causes problems for userspace that relies on BLKROGET to determine whether a block device is read-only. For example, systemd's loop device setup uses BLKROGET to decide whether to create a loop device with LO_FLAGS_READ_ONLY. Without the read-only flag, writes pass through the loop device to the CD-ROM and fail with I/O errors. systemd-fsck similarly checks BLKROGET to decide whether to run fsck in no-repair mode (-n). The write-capability bits in cdi->mask come from two different sources: CDC_DVD_RAM and CDC_CD_RW are populated by the driver from the MODE SENSE capabilities page (page 0x2A) before register_cdrom() is called, while CDC_MRW_W and CDC_RAM require the MMC GET CONFIGURATION command and were only probed by cdrom_open_write() at device open time. This meant that any attempt to compute the writable state from the full mask at probe time was incorrect, because the GET CONFIGURATION bits were still unset (and cdi->mask is initialized such that capabilities are assumed present). Fix this by factoring the GET CONFIGURATION probing out of cdrom_open_write() into a new exported helper, cdrom_probe_write_features(), and having sr call it from sr_probe() right after get_capabilities() has populated the MODE SENSE bits. register_cdrom() then calls set_disk_ro() based on the full write-capability mask (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW) so the block layer reflects the drive's actual write support. The feature queries used (CDF_MRW and CDF_RWRT via GET CONFIGURATION with RT=00) report drive-level capabilities that are persistent across media, so a single probe before register_cdrom() is sufficient and the redundant probe at open time is dropped. With set_disk_ro() now accurate, the long-vestigial cd->writeable flag in sr can go: get_capabilities() used to set cd->writeable based on the same four mask bits, but because CDC_MRW_W and CDC_RAM default to "capability present" in cdi->mask and aren't touched by MODE SENSE, the condition that gated cd->writeable was always true, making it unconditionally 1. Replace the corresponding gate in sr_init_command() with get_disk_ro(cd->disk), which turns a previously no-op check into a real one and also catches kernel-internal bio writers that bypass blkdev_write_iter()'s bdev_read_only() check. The sd driver (SCSI disks) does not have this problem because it checks the MODE SENSE Write Protect bit and calls set_disk_ro() accordingly. The sr driver cannot use the same approach because the MMC specification does not define the WP bit in the MODE SENSE device-specific parameter byte for CD-ROM devices. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Daan De Meyer Reviewed-by: Phillip Potter Reviewed-by: Martin K. Petersen Signed-off-by: Phillip Potter Link: https://patch.msgid.link/20260427210139.1400-2-phil@philpotter.co.uk Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/cdrom/cdrom.c | 73 ++++++++++++++++++++++++++++--------------- drivers/scsi/sr.c | 11 ++----- drivers/scsi/sr.h | 1 - include/linux/cdrom.h | 1 + 4 files changed, 51 insertions(+), 35 deletions(-) diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 31ba1f8c1f786..e30414f0d4560 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -631,6 +631,16 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) WARN_ON(!cdo->generic_packet); + /* + * Propagate the drive's write support to the block layer so BLKROGET + * reflects actual write capability. Drivers that use GET CONFIGURATION + * features (CDC_MRW_W, CDC_RAM) must have called + * cdrom_probe_write_features() before register_cdrom() so the mask is + * complete here. + */ + set_disk_ro(disk, !CDROM_CAN(CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | + CDC_CD_RW)); + cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" registered\n", cdi->name); mutex_lock(&cdrom_mutex); list_add(&cdi->list, &cdrom_list); @@ -742,6 +752,44 @@ static int cdrom_is_random_writable(struct cdrom_device_info *cdi, int *write) return 0; } +/* + * Probe write-related MMC features via GET CONFIGURATION and update + * cdi->mask accordingly. Drivers that populate cdi->mask from the MODE SENSE + * capabilities page (e.g. sr) should call this after those MODE SENSE bits + * have been set but before register_cdrom(), so that the full set of + * write-capability bits is known by the time register_cdrom() decides on the + * initial read-only state of the disk. + */ +void cdrom_probe_write_features(struct cdrom_device_info *cdi) +{ + int mrw, mrw_write, ram_write; + + mrw = 0; + if (!cdrom_is_mrw(cdi, &mrw_write)) + mrw = 1; + + if (CDROM_CAN(CDC_MO_DRIVE)) + ram_write = 1; + else + (void) cdrom_is_random_writable(cdi, &ram_write); + + if (mrw) + cdi->mask &= ~CDC_MRW; + else + cdi->mask |= CDC_MRW; + + if (mrw_write) + cdi->mask &= ~CDC_MRW_W; + else + cdi->mask |= CDC_MRW_W; + + if (ram_write) + cdi->mask &= ~CDC_RAM; + else + cdi->mask |= CDC_RAM; +} +EXPORT_SYMBOL(cdrom_probe_write_features); + static int cdrom_media_erasable(struct cdrom_device_info *cdi) { disc_information di; @@ -894,33 +942,8 @@ static int cdrom_is_dvd_rw(struct cdrom_device_info *cdi) */ static int cdrom_open_write(struct cdrom_device_info *cdi) { - int mrw, mrw_write, ram_write; int ret = 1; - mrw = 0; - if (!cdrom_is_mrw(cdi, &mrw_write)) - mrw = 1; - - if (CDROM_CAN(CDC_MO_DRIVE)) - ram_write = 1; - else - (void) cdrom_is_random_writable(cdi, &ram_write); - - if (mrw) - cdi->mask &= ~CDC_MRW; - else - cdi->mask |= CDC_MRW; - - if (mrw_write) - cdi->mask &= ~CDC_MRW_W; - else - cdi->mask |= CDC_MRW_W; - - if (ram_write) - cdi->mask &= ~CDC_RAM; - else - cdi->mask |= CDC_RAM; - if (CDROM_CAN(CDC_MRW_W)) ret = cdrom_mrw_open_write(cdi); else if (CDROM_CAN(CDC_DVD_RAM)) diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index add13e3068983..803fc9c132298 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -395,7 +395,7 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt) switch (req_op(rq)) { case REQ_OP_WRITE: - if (!cd->writeable) + if (get_disk_ro(cd->disk)) goto out; SCpnt->cmnd[0] = WRITE_10; cd->cdi.media_written = 1; @@ -681,6 +681,7 @@ static int sr_probe(struct device *dev) error = -ENOMEM; if (get_capabilities(cd)) goto fail_minor; + cdrom_probe_write_features(&cd->cdi); sr_vendor_init(cd); set_capacity(disk, cd->capacity); @@ -899,14 +900,6 @@ static int get_capabilities(struct scsi_cd *cd) /*else I don't think it can close its tray cd->cdi.mask |= CDC_CLOSE_TRAY; */ - /* - * if DVD-RAM, MRW-W or CD-RW, we are randomly writable - */ - if ((cd->cdi.mask & (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) != - (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) { - cd->writeable = 1; - } - kfree(buffer); return 0; } diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h index dc899277b3a44..2d92f9cb6fec7 100644 --- a/drivers/scsi/sr.h +++ b/drivers/scsi/sr.h @@ -35,7 +35,6 @@ typedef struct scsi_cd { struct scsi_device *device; unsigned int vendor; /* vendor code, see sr_vendor.c */ unsigned long ms_offset; /* for reading multisession-CD's */ - unsigned writeable : 1; unsigned use:1; /* is this device still supportable */ unsigned xa_flag:1; /* CD has XA sectors ? */ unsigned readcd_known:1; /* drive supports READ_CD (0xbe) */ diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index b907e6c2307d8..260d7968cf720 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -108,6 +108,7 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); +extern void cdrom_probe_write_features(struct cdrom_device_info *cdi); extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); From 750d0091bebf44975421268d37484ef87060d263 Mon Sep 17 00:00:00 2001 From: "Nikola Z. Ivanov" Date: Sun, 26 Apr 2026 23:14:34 +0300 Subject: [PATCH 0944/1518] netdevsim: zero initialize struct iphdr in dummy sk_buff [ Upstream commit 35eaa6d8d6c2ee65e96f507add856e0eacf24591 ] Syzbot reports a KMSAN uninit-value originating from nsim_dev_trap_skb_build, with the allocation also being performed in the same function. Fix this by calling skb_put_zero instead of skb_put to guarantee zero initialization of the whole IP header. Closes: https://syzkaller.appspot.com/bug?extid=23d7fcd204e3837866ff Fixes: da58f90f11f5 ("netdevsim: Add devlink-trap support") Signed-off-by: Nikola Z. Ivanov Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260426201434.742030-1-zlatistiv@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/netdevsim/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 56a47c060f2e1..4064c488439b4 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -773,7 +773,7 @@ static struct sk_buff *nsim_dev_trap_skb_build(void) skb->protocol = htons(ETH_P_IP); skb_set_network_header(skb, skb->len); - iph = skb_put(skb, sizeof(struct iphdr)); + iph = skb_put_zero(skb, sizeof(struct iphdr)); iph->protocol = IPPROTO_UDP; iph->saddr = in_aton("192.0.2.1"); iph->daddr = in_aton("198.51.100.1"); From 1633087d8a76a7a776740430685521b8fa0ffab3 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 17 Apr 2026 20:19:39 -0700 Subject: [PATCH 0945/1518] net/sched: netem: fix probability gaps in 4-state loss model [ Upstream commit 732b463449fd0ef90acd13cda68eab1c91adb00c ] The 4-state Markov chain in loss_4state() has gaps at the boundaries between transition probability ranges. The comparisons use: if (rnd < a4) else if (a4 < rnd && rnd < a1 + a4) When rnd equals a boundary value exactly, neither branch matches and no state transition occurs. The redundant lower-bound check (a4 < rnd) is already implied by being in the else branch. Remove the unnecessary lower-bound comparisons so the ranges are contiguous and every random value produces a transition, matching the GI (General and Intuitive) loss model specification. This bug goes back to original implementation of this model. Fixes: 661b79725fea ("netem: revised correlated loss generator") Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260418032027.900913-2-stephen@networkplumber.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 6f8fcc4b504ce..4eb6ed60ee9b6 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -227,10 +227,10 @@ static bool loss_4state(struct netem_sched_data *q) if (rnd < clg->a4) { clg->state = LOST_IN_GAP_PERIOD; return true; - } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { + } else if (rnd < clg->a1 + clg->a4) { clg->state = LOST_IN_BURST_PERIOD; return true; - } else if (clg->a1 + clg->a4 < rnd) { + } else { clg->state = TX_IN_GAP_PERIOD; } @@ -247,9 +247,9 @@ static bool loss_4state(struct netem_sched_data *q) case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; - else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { + else if (rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; - } else if (clg->a2 + clg->a3 < rnd) { + } else { clg->state = LOST_IN_BURST_PERIOD; return true; } From 8450462eaf91d5d2a9e863507b16d18e814baef3 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 17 Apr 2026 20:19:40 -0700 Subject: [PATCH 0946/1518] net/sched: netem: fix queue limit check to include reordered packets [ Upstream commit 4185701fcce6b426b6c3630b25330dddd9c47b0d ] The queue limit check in netem_enqueue() uses q->t_len which only counts packets in the internal tfifo. Packets placed in sch->q by the reorder path (__qdisc_enqueue_head) are not counted, allowing the total queue occupancy to exceed sch->limit under reordering. Include sch->q.qlen in the limit check. Fixes: f8d4bc455047 ("net/sched: netem: account for backlog updates from child qdisc") Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260418032027.900913-3-stephen@networkplumber.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 4eb6ed60ee9b6..da8dcc9b61cc7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -523,7 +523,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1 << get_random_u32_below(8); } - if (unlikely(q->t_len >= sch->limit)) { + if (unlikely(sch->q.qlen >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); From 33cc6a26898aea8d7d7738bca1b2cbdd398ef3b0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 17 Apr 2026 20:19:41 -0700 Subject: [PATCH 0947/1518] net/sched: netem: only reseed PRNG when seed is explicitly provided [ Upstream commit 986afaf809940577224a99c3a08d97a15eb37e93 ] netem_change() unconditionally reseeds the PRNG on every tc change command. If TCA_NETEM_PRNG_SEED is not specified, a new random seed is generated, destroying reproducibility for users who set a deterministic seed on a previous change. Move the initial random seed generation to netem_init() and only reseed in netem_change() when TCA_NETEM_PRNG_SEED is explicitly provided by the user. Fixes: 4072d97ddc44 ("netem: add prng attribute to netem_sched_data") Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260418032027.900913-4-stephen@networkplumber.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index da8dcc9b61cc7..4bf65fcdaff02 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -1111,11 +1111,10 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); - if (tb[TCA_NETEM_PRNG_SEED]) + if (tb[TCA_NETEM_PRNG_SEED]) { q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); - else - q->prng.seed = get_random_u64(); - prandom_seed_state(&q->prng.prng_state, q->prng.seed); + prandom_seed_state(&q->prng.prng_state, q->prng.seed); + } unlock: sch_tree_unlock(sch); @@ -1138,6 +1137,9 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; q->loss_model = CLG_RANDOM; + q->prng.seed = get_random_u64(); + prandom_seed_state(&q->prng.prng_state, q->prng.seed); + ret = netem_change(sch, opt, extack); if (ret) pr_info("netem: change failed\n"); From 2e2a8b077699d31b083a318a513b1b477ff44f43 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 17 Apr 2026 20:19:42 -0700 Subject: [PATCH 0948/1518] net/sched: netem: validate slot configuration [ Upstream commit 01801c359a74737b9b1aa28568b60374d857241a ] Reject slot configurations that have no defensible meaning: - negative min_delay or max_delay - min_delay greater than max_delay - negative dist_delay or dist_jitter - negative max_packets or max_bytes Negative or out-of-order delays underflow in get_slot_next(), producing garbage intervals. Negative limits trip the per-slot accounting (packets_left/bytes_left <= 0) on the first packet of every slot, defeating the rate-limiting half of the slot feature. Note that dist_jitter has been silently coerced to its absolute value by get_slot() since the feature was introduced; rejecting negatives here converts that silent coercion into -EINVAL. The abs() can be removed in a follow-up. Fixes: 836af83b54e3 ("netem: support delivering packets in delayed time slots") Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260418032027.900913-5-stephen@networkplumber.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 4bf65fcdaff02..41d60e904090d 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -826,6 +826,29 @@ static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) return 0; } +static int validate_slot(const struct nlattr *attr, struct netlink_ext_ack *extack) +{ + const struct tc_netem_slot *c = nla_data(attr); + + if (c->min_delay < 0 || c->max_delay < 0) { + NL_SET_ERR_MSG_ATTR(extack, attr, "negative slot delay"); + return -EINVAL; + } + if (c->min_delay > c->max_delay) { + NL_SET_ERR_MSG_ATTR(extack, attr, "slot min delay greater than max delay"); + return -EINVAL; + } + if (c->dist_delay < 0 || c->dist_jitter < 0) { + NL_SET_ERR_MSG_ATTR(extack, attr, "negative dist delay"); + return -EINVAL; + } + if (c->max_packets < 0 || c->max_bytes < 0) { + NL_SET_ERR_MSG_ATTR(extack, attr, "negative slot limit"); + return -EINVAL; + } + return 0; +} + static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_slot *c = nla_data(attr); @@ -1039,6 +1062,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, goto table_free; } + if (tb[TCA_NETEM_SLOT]) { + ret = validate_slot(tb[TCA_NETEM_SLOT], extack); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; From fabf2b2bbfa1f6a9f609a1419791049fa13f6b71 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 17 Apr 2026 20:19:43 -0700 Subject: [PATCH 0949/1518] net/sched: netem: fix slot delay calculation overflow [ Upstream commit 51e94e1e2fef351c74d69eb53666df808d26af95 ] get_slot_next() computes a random delay between min_delay and max_delay using: get_random_u32() * (max_delay - min_delay) >> 32 This overflows signed 64-bit arithmetic when the delay range exceeds approximately 2.1 seconds (2^31 nanoseconds), producing a negative result that effectively disables slot-based pacing. This is a realistic configuration for WAN emulation (e.g., slot 1s 5s). Use mul_u64_u32_shr() which handles the widening multiply without overflow. Fixes: 0a9fe5c375b5 ("netem: slotting with non-uniform distribution") Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260418032027.900913-6-stephen@networkplumber.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 41d60e904090d..6e221bdfb3871 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -658,9 +658,8 @@ static void get_slot_next(struct netem_sched_data *q, u64 now) if (!q->slot_dist) next_delay = q->slot_config.min_delay + - (get_random_u32() * - (q->slot_config.max_delay - - q->slot_config.min_delay) >> 32); + mul_u64_u32_shr(q->slot_config.max_delay - q->slot_config.min_delay, + get_random_u32(), 32); else next_delay = tabledist(q->slot_config.dist_delay, (s32)(q->slot_config.dist_jitter), From 7a72efd117227faf9571decce2d211101f471a31 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 17 Apr 2026 20:19:44 -0700 Subject: [PATCH 0950/1518] net/sched: netem: check for negative latency and jitter [ Upstream commit 90be9fedb218ee95a1cf59050d1306fbfb0e8b87 ] Reject requests with negative latency or jitter. A negative value added to current timestamp (u64) wraps to an enormous time_to_send, disabling dequeue. The original UAPI used u32 for these values; the conversion to 64-bit time values via TCA_NETEM_LATENCY64 and TCA_NETEM_JITTER64 allowed signed values to reach the kernel without validation. Jitter is already silently clamped by an abs() in netem_change(); that abs() can be removed in a follow-up once this rejection is in place. Fixes: 99803171ef04 ("netem: add uapi to express delay and jitter in nanoseconds") Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260418032027.900913-7-stephen@networkplumber.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 6e221bdfb3871..47db6da905c58 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -825,6 +825,16 @@ static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) return 0; } +static int validate_time(const struct nlattr *attr, const char *name, + struct netlink_ext_ack *extack) +{ + if (nla_get_s64(attr) < 0) { + NL_SET_ERR_MSG_ATTR_FMT(extack, attr, "negative %s", name); + return -EINVAL; + } + return 0; +} + static int validate_slot(const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct tc_netem_slot *c = nla_data(attr); @@ -1067,6 +1077,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, goto table_free; } + if (tb[TCA_NETEM_LATENCY64]) { + ret = validate_time(tb[TCA_NETEM_LATENCY64], "latency", extack); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_JITTER64]) { + ret = validate_time(tb[TCA_NETEM_JITTER64], "jitter", extack); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; From b48399bc63ffde0d4be0c38320ece8b7d7b4326e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 21 Apr 2026 08:43:07 +0200 Subject: [PATCH 0951/1518] net: airoha: stop net_device TX queue before updating CPU index [ Upstream commit 3854de7b38be742cf7558476956d12414cb274f2 ] Currently, airoha_eth driver updates the CPU index register prior of verifying whether the number of free descriptors has fallen below the threshold. Move net_device TX queue length check before updating the TX CPU index in order to update TX CPU index even if there are more packets to be transmitted but the net_device TX queue is going to be stopped accounting the inflight packets. Fixes: 1d304174106c ("net: airoha: Implement BQL support") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260421-airoha-xmit-stop-condition-v1-1-e670d6a48467@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 865b854bd4afc..fd612cc339e13 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2111,17 +2111,16 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, skb_tx_timestamp(skb); netdev_tx_sent_queue(txq, skb->len); + if (q->ndesc - q->queued < q->free_thr) { + netif_tx_stop_queue(txq); + q->txq_stopped = true; + } if (netif_xmit_stopped(txq) || !netdev_xmit_more()) airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); - if (q->ndesc - q->queued < q->free_thr) { - netif_tx_stop_queue(txq); - q->txq_stopped = true; - } - spin_unlock_bh(&q->lock); return NETDEV_TX_OK; From 546d998978dc20e36e19d29fe736f4a48c9e8827 Mon Sep 17 00:00:00 2001 From: Zhengping Zhang Date: Thu, 26 Feb 2026 10:37:08 +0800 Subject: [PATCH 0952/1518] net: airoha: fix typo in function name [ Upstream commit aebf15e8eb09b01e99f043e9f5d423798aac9d32 ] Corrected the typo in the function name from `airhoa_is_lan_gdm_port` to `airoha_is_lan_gdm_port`. This change ensures consistency in the API naming convention. Signed-off-by: Zhengping Zhang Reviewed-by: Simon Horman Acked-by: Lorenzo Bianconi Link: https://patch.msgid.link/tencent_E4FD5D6BC0131E617D848896F5F9FCED6E0A@qq.com Signed-off-by: Jakub Kicinski Stable-dep-of: e070aac63b42 ("net: airoha: Do not wake all netdev TX queues in airoha_qdma_wake_netdev_txqs()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 2 +- drivers/net/ethernet/airoha/airoha_eth.h | 2 +- drivers/net/ethernet/airoha/airoha_ppe.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index fd612cc339e13..9691b4134285f 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -76,7 +76,7 @@ static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr) struct airoha_eth *eth = port->qdma->eth; u32 val, reg; - reg = airhoa_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H + reg = airoha_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H : REG_FE_WAN_MAC_H; val = (addr[0] << 16) | (addr[1] << 8) | addr[2]; airoha_fe_wr(eth, reg, val); diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 28dfa35a3abed..abd996492cb7f 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -627,7 +627,7 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val); #define airoha_qdma_clear(qdma, offset, val) \ airoha_rmw((qdma)->regs, (offset), (val), 0) -static inline bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port) +static inline bool airoha_is_lan_gdm_port(struct airoha_gdm_port *port) { /* GDM1 port on EN7581 SoC is connected to the lan dsa switch. * GDM{2,3,4} can be used as wan port connected to an external diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 6cd5febce6b59..005128717a45c 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -331,7 +331,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth, /* For downlink traffic consume SRAM memory for hw * forwarding descriptors queue. */ - if (airhoa_is_lan_gdm_port(port)) + if (airoha_is_lan_gdm_port(port)) val |= AIROHA_FOE_IB2_FAST_PATH; if (dsa_port >= 0) val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, From f4b7ed23fae6ca595129810d8a1b9a70eb26818e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 21 Apr 2026 10:53:33 +0200 Subject: [PATCH 0953/1518] net: airoha: Do not wake all netdev TX queues in airoha_qdma_wake_netdev_txqs() [ Upstream commit e070aac63b42bf81f4dc565f9f841ff47e6c992f ] Do not wake every netdev TX queue across all ports sharing the QDMA running netif_tx_wake_all_queues routine in airoha_qdma_wake_netdev_txqs() but only the ones that are mapped the specific QDMA stopped hw TX queue. This patch can potentially avoid waking already stopped netdev TX queues that are mapped to a different QDMA hw TX queue. Introduce airoha_qdma_get_txq utility routine. Fixes: b94769eb2f30 ("net: airoha: Fix possible TX queue stall in airoha_qdma_tx_napi_poll()") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260421-airoha-wake_netdev_txqs-optmization-v1-1-e0be95115d53@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 19 +++++++++++++++---- drivers/net/ethernet/airoha/airoha_eth.h | 5 +++++ 2 files changed, 20 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 9691b4134285f..7d7f2bf6172a3 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -878,13 +878,24 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q) { struct airoha_qdma *qdma = q->qdma; struct airoha_eth *eth = qdma->eth; - int i; + int i, qid = q - &qdma->q_tx[0]; for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; + int j; + + if (!port) + continue; - if (port && port->qdma == qdma) - netif_tx_wake_all_queues(port->dev); + if (port->qdma != qdma) + continue; + + for (j = 0; j < port->dev->num_tx_queues; j++) { + if (airoha_qdma_get_txq(qdma, j) != qid) + continue; + + netif_wake_subqueue(port->dev, j); + } } q->txq_stopped = false; } @@ -2018,7 +2029,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, u16 index; u8 fport; - qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx); + qid = airoha_qdma_get_txq(qdma, skb_get_queue_mapping(skb)); tag = airoha_get_dsa_tag(skb, dev); msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK, diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index abd996492cb7f..33277cc577990 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -627,6 +627,11 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val); #define airoha_qdma_clear(qdma, offset, val) \ airoha_rmw((qdma)->regs, (offset), (val), 0) +static inline u16 airoha_qdma_get_txq(struct airoha_qdma *qdma, u16 qid) +{ + return qid % ARRAY_SIZE(qdma->q_tx); +} + static inline bool airoha_is_lan_gdm_port(struct airoha_gdm_port *port) { /* GDM1 port on EN7581 SoC is connected to the lan dsa switch. From f670fa4b19ceddc6d215dda4997888ccba9bbc61 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 24 Apr 2026 11:00:28 +0200 Subject: [PATCH 0954/1518] net: airoha: Do not read uninitialized fragment address in airoha_dev_xmit() [ Upstream commit bde34e84edc8b5571fbde7e941e175a4293ee1eb ] The transmit loop in airoha_dev_xmit() reads fragment address and length during its final iteration, when the loop index equals skb_shinfo(skb)->nr_frags, at which point the fragment data is uninitialized. While these values are never consumed, the read itself is unsafe and may trigger a page fault. Fix this by avoiding the fragment read on the last iteration. Additionally, move the skb pointer from the first to the last used packet descriptor, so that airoha_qdma_tx_napi_poll() defers freeing the skb until the final descriptor is processed. Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260424-airoha-xmit-fix-read-frag-v1-1-fdc0a83c79e8@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 7d7f2bf6172a3..a69544e785a2a 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2024,8 +2024,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct netdev_queue *txq; struct airoha_queue *q; LIST_HEAD(tx_list); + int i = 0, qid; void *data; - int i, qid; u16 index; u8 fport; @@ -2084,7 +2084,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, list); index = e - q->entry; - for (i = 0; i < nr_frags; i++) { + while (true) { struct airoha_qdma_desc *desc = &q->desc[index]; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr; @@ -2096,7 +2096,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, goto error_unmap; list_move_tail(&e->list, &tx_list); - e->skb = i ? NULL : skb; + e->skb = i == nr_frags - 1 ? skb : NULL; e->dma_addr = addr; e->dma_len = len; @@ -2115,6 +2115,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, WRITE_ONCE(desc->msg1, cpu_to_le32(msg1)); WRITE_ONCE(desc->msg2, cpu_to_le32(0xffff)); + if (++i == nr_frags) + break; + data = skb_frag_address(frag); len = skb_frag_size(frag); } From 10c242aa0c54872b3e77af33fb3d896adc8562a5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Apr 2026 06:28:39 +0000 Subject: [PATCH 0955/1518] net/sched: sch_choke: annotate data-races in choke_dump_stats() [ Upstream commit d3aeb889dcbd78e95f500d383799a23d949796e0 ] choke_dump_stats() only runs with RTNL held. It reads fields that can be changed in qdisc fast path. Add READ_ONCE()/WRITE_ONCE() annotations. Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260423062839.2524324-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_choke.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 59e7bdf5063e8..ea6ef76c29658 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -229,7 +229,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Draw a packet at random from queue and compare flow */ if (choke_match_random(q, skb, &idx)) { - q->stats.matched++; + WRITE_ONCE(q->stats.matched, q->stats.matched + 1); choke_drop_by_idx(sch, idx, to_free); goto congestion_drop; } @@ -241,11 +241,13 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, qdisc_qstats_overlimit(sch); if (use_harddrop(q) || !use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; + WRITE_ONCE(q->stats.forced_drop, + q->stats.forced_drop + 1); goto congestion_drop; } - q->stats.forced_mark++; + WRITE_ONCE(q->stats.forced_mark, + q->stats.forced_mark + 1); } else if (++q->vars.qcount) { if (red_mark_probability(p, &q->vars, q->vars.qavg)) { q->vars.qcount = 0; @@ -253,11 +255,13 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, qdisc_qstats_overlimit(sch); if (!use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; + WRITE_ONCE(q->stats.prob_drop, + q->stats.prob_drop + 1); goto congestion_drop; } - q->stats.prob_mark++; + WRITE_ONCE(q->stats.prob_mark, + q->stats.prob_mark + 1); } } else q->vars.qR = red_random(p); @@ -272,7 +276,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_SUCCESS; } - q->stats.pdrop++; + WRITE_ONCE(q->stats.pdrop, q->stats.pdrop + 1); return qdisc_drop(skb, sch, to_free); congestion_drop: @@ -461,10 +465,12 @@ static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct choke_sched_data *q = qdisc_priv(sch); struct tc_choke_xstats st = { - .early = q->stats.prob_drop + q->stats.forced_drop, - .marked = q->stats.prob_mark + q->stats.forced_mark, - .pdrop = q->stats.pdrop, - .matched = q->stats.matched, + .early = READ_ONCE(q->stats.prob_drop) + + READ_ONCE(q->stats.forced_drop), + .marked = READ_ONCE(q->stats.prob_mark) + + READ_ONCE(q->stats.forced_mark), + .pdrop = READ_ONCE(q->stats.pdrop), + .matched = READ_ONCE(q->stats.matched), }; return gnet_stats_copy_app(d, &st, sizeof(st)); From 02495cc4a33e2c98778d320dc2ab111d6fedd381 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Apr 2026 06:35:27 +0000 Subject: [PATCH 0956/1518] net/sched: sch_fq_pie: annotate data-races in fq_pie_dump_stats() [ Upstream commit 59b145771c7982cfe9020d4e9e22da92d6b5ae31 ] fq_codel_dump_stats() acquires the qdisc spinlock a bit too late. Move this acquisition before we fill tc_fq_pie_xstats with live data. Alternative would be to add READ_ONCE() and WRITE_ONCE() annotations, but the spinlock is needed anyway to scan q->new_flows and q->old_flows. Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20260423063527.2568262-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_fq_pie.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 7b96bc3ff8918..0c7b2095f8655 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -510,18 +510,19 @@ static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb) static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct fq_pie_sched_data *q = qdisc_priv(sch); - struct tc_fq_pie_xstats st = { - .packets_in = q->stats.packets_in, - .overlimit = q->stats.overlimit, - .overmemory = q->overmemory, - .dropped = q->stats.dropped, - .ecn_mark = q->stats.ecn_mark, - .new_flow_count = q->new_flow_count, - .memory_usage = q->memory_usage, - }; + struct tc_fq_pie_xstats st = { 0 }; struct list_head *pos; sch_tree_lock(sch); + + st.packets_in = q->stats.packets_in; + st.overlimit = q->stats.overlimit; + st.overmemory = q->overmemory; + st.dropped = q->stats.dropped; + st.ecn_mark = q->stats.ecn_mark; + st.new_flow_count = q->new_flow_count; + st.memory_usage = q->memory_usage; + list_for_each(pos, &q->new_flows) st.new_flows_len++; From a7a97f2303e63ede105c1d55ef53dc497364e11d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 23 Apr 2026 09:36:07 +0300 Subject: [PATCH 0957/1518] vrf: Fix a potential NPD when removing a port from a VRF [ Upstream commit 2674d603a9e6970463b2b9ebcf8e31e90beae169 ] RCU readers that identified a net device as a VRF port using netif_is_l3_slave() assume that a subsequent call to netdev_master_upper_dev_get_rcu() will return a VRF device. They then continue to dereference its l3mdev operations. This assumption is not always correct and can result in a NPD [1]. There is no RCU synchronization when removing a port from a VRF, so it is possible for an RCU reader to see a new master device (e.g., a bridge) that does not have l3mdev operations. Fix by adding RCU synchronization after clearing the IFF_L3MDEV_SLAVE flag. Skip this synchronization when a net device is removed from a VRF as part of its deletion and when the VRF device itself is deleted. In the latter case an RCU grace period will pass by the time RTNL is released. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] RIP: 0010:l3mdev_fib_table_rcu (net/l3mdev/l3mdev.c:181) [...] Call Trace: l3mdev_fib_table_by_index (net/l3mdev/l3mdev.c:201 net/l3mdev/l3mdev.c:189) __inet_bind (net/ipv4/af_inet.c:499 (discriminator 3)) inet_bind_sk (net/ipv4/af_inet.c:469) __sys_bind (./include/linux/file.h:62 (discriminator 1) ./include/linux/file.h:83 (discriminator 1) net/socket.c:1951 (discriminator 1)) __x64_sys_bind (net/socket.c:1969 (discriminator 1) net/socket.c:1967 (discriminator 1) net/socket.c:1967 (discriminator 1)) do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fixes: fdeea7be88b1 ("net: vrf: Set slave's private flag before linking") Reported-by: Haoze Xie Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Yuan Tan Closes: https://lore.kernel.org/netdev/20260419145332.3988923-1-n05ec@lzu.edu.cn/ Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/20260423063607.1208202-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/vrf.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 571847a7f86d7..4b62b167650ea 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1084,6 +1084,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + synchronize_net(); return ret; } @@ -1103,10 +1104,16 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, } /* inverse of do_vrf_add_slave */ -static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) +static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev, + bool needs_sync) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + /* Make sure that concurrent RCU readers that identified the device + * as a VRF port see a VRF master or no master at all. + */ + if (needs_sync) + synchronize_net(); cycle_netdev(port_dev, NULL); @@ -1115,7 +1122,7 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { - return do_vrf_del_slave(dev, port_dev); + return do_vrf_del_slave(dev, port_dev, true); } static void vrf_dev_uninit(struct net_device *dev) @@ -1669,7 +1676,7 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head) struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) - vrf_del_slave(dev, port_dev); + do_vrf_del_slave(dev, port_dev, false); vrf_map_unregister_dev(dev); @@ -1801,7 +1808,7 @@ static int vrf_device_event(struct notifier_block *unused, goto out; vrf_dev = netdev_master_upper_dev_get(dev); - vrf_del_slave(vrf_dev, dev); + do_vrf_del_slave(vrf_dev, dev, false); } out: return NOTIFY_DONE; From 6999d70e0eda39af029fa1891c48f0a8832b09d5 Mon Sep 17 00:00:00 2001 From: Zhan Jun Date: Thu, 23 Apr 2026 08:49:12 +0800 Subject: [PATCH 0958/1518] net: usb: rtl8150: fix use-after-free in rtl8150_start_xmit() [ Upstream commit 23f0e34c64acba15cad4d23e50f41f533da195fa ] syzbot reported a KASAN slab-use-after-free read in rtl8150_start_xmit() when accessing skb->len for tx statistics after usb_submit_urb() has been called: BUG: KASAN: slab-use-after-free in rtl8150_start_xmit+0x71f/0x760 drivers/net/usb/rtl8150.c:712 Read of size 4 at addr ffff88810eb7a930 by task kworker/0:4/5226 The URB completion handler write_bulk_callback() frees the skb via dev_kfree_skb_irq(dev->tx_skb). The URB may complete on another CPU in softirq context before usb_submit_urb() returns in the submitter, so by the time the submitter reads skb->len the skb has already been queued to the per-CPU completion_queue and freed by net_tx_action(): CPU A (xmit) CPU B (USB completion softirq) ------------ ------------------------------ dev->tx_skb = skb; usb_submit_urb() --+ |-------> write_bulk_callback() | dev_kfree_skb_irq(dev->tx_skb) | net_tx_action() | napi_skb_cache_put() <-- free netdev->stats.tx_bytes | += skb->len; <-- UAF read Fix it by caching skb->len before submitting the URB and using the cached value when updating the tx_bytes counter. The pre-existing tx_bytes semantics are preserved: the counter tracks the original frame length (skb->len), not the ETH_ZLEN/USB-alignment padded "count" value that is handed to the device. Changing that would be a user-visible accounting change and is out of scope for this UAF fix. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+3f46c095ac0ca048cb71@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/69e69ee7.050a0220.24bfd3.002b.GAE@google.com/ Closes: https://syzkaller.appspot.com/bug?extid=3f46c095ac0ca048cb71 Reviewed-by: Andrew Lunn Signed-off-by: Zhan Jun Link: https://patch.msgid.link/809895186B866C10+20260423004913.136655-1-zhangdandan@uniontech.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/usb/rtl8150.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index e40b0669d9f4b..8700ae392b10a 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -685,6 +685,7 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, struct net_device *netdev) { rtl8150_t *dev = netdev_priv(netdev); + unsigned int skb_len; int count, res; /* pad the frame and ensure terminating USB packet, datasheet 9.2.3 */ @@ -696,6 +697,8 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } + skb_len = skb->len; + netif_stop_queue(netdev); dev->tx_skb = skb; usb_fill_bulk_urb(dev->tx_urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), @@ -711,7 +714,7 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, } } else { netdev->stats.tx_packets++; - netdev->stats.tx_bytes += skb->len; + netdev->stats.tx_bytes += skb_len; netif_trans_update(netdev); } From 81fc967bf476d62fbbc0e77d7ce9546b13c39965 Mon Sep 17 00:00:00 2001 From: Morduan Zang Date: Fri, 24 Apr 2026 09:55:17 +0800 Subject: [PATCH 0959/1518] net: usb: rtl8150: free skb on usb_submit_urb() failure in xmit [ Upstream commit adbe2cdf75461891e50dbe11896ac78e9af1f874 ] When rtl8150_start_xmit() fails to submit the tx URB, the URB is never handed to the USB core and write_bulk_callback() will not run. The driver returns NETDEV_TX_OK, which tells the networking stack that the skb has been consumed, but nothing actually frees the skb on this error path: dev->tx_skb = skb; ... if ((res = usb_submit_urb(dev->tx_urb, GFP_ATOMIC))) { ... /* no kfree_skb here */ } return NETDEV_TX_OK; This leaks the skb on every submit failure and also leaves dev->tx_skb pointing at memory that the driver itself may later free, which is fragile. Free the skb with dev_kfree_skb_any() in the error path and clear dev->tx_skb so no stale pointer is left behind. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reviewed-by: Andrew Lunn Signed-off-by: Morduan Zang Link: https://patch.msgid.link/E7D3E1C013C5A859+20260424015517.9574-1-zhangdandan@uniontech.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/usb/rtl8150.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 8700ae392b10a..647f28b367b99 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -712,6 +712,13 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, netdev->stats.tx_errors++; netif_start_queue(netdev); } + /* + * The URB was not submitted, so write_bulk_callback() will + * never run to free dev->tx_skb. Drop the skb here and + * clear tx_skb to avoid leaving a stale pointer. + */ + dev->tx_skb = NULL; + dev_kfree_skb_any(skb); } else { netdev->stats.tx_packets++; netdev->stats.tx_bytes += skb_len; From 3dc58085988b5a1132182948bd8db02de5f0d1f4 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Tue, 28 Apr 2026 01:42:00 +0800 Subject: [PATCH 0960/1518] spi: amlogic-spisg: initialize completion before requesting IRQ [ Upstream commit 8d0189c1ea98b56481eb809e3d1bdbf85557e819 ] Move init_completion(&spisg->completion) to before devm_request_irq() to avoid a potential race condition where an interrupt could fire before the completion structure is initialized. Fixes: cef9991e04ae ("spi: Add Amlogic SPISG driver") Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260428-amlogic-spisg-v1-1-8eecc3b446d6@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-amlogic-spisg.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/spi/spi-amlogic-spisg.c b/drivers/spi/spi-amlogic-spisg.c index 56a6cf8471b9f..970fddbb25857 100644 --- a/drivers/spi/spi-amlogic-spisg.c +++ b/drivers/spi/spi-amlogic-spisg.c @@ -795,6 +795,7 @@ static int aml_spisg_probe(struct platform_device *pdev) dma_set_max_seg_size(&pdev->dev, SPISG_BLOCK_MAX); + init_completion(&spisg->completion); ret = devm_request_irq(&pdev->dev, irq, aml_spisg_irq, 0, NULL, spisg); if (ret) { dev_err(&pdev->dev, "irq request failed\n"); @@ -807,8 +808,6 @@ static int aml_spisg_probe(struct platform_device *pdev) goto out_clk; } - init_completion(&spisg->completion); - pm_runtime_put(&spisg->pdev->dev); return 0; From cca14c404c0e1d58ed62f3a0c676138c8b238a0e Mon Sep 17 00:00:00 2001 From: Paul Geurts Date: Wed, 22 Apr 2026 12:09:30 +0200 Subject: [PATCH 0961/1518] NFC: trf7970a: Ignore antenna noise when checking for RF field [ Upstream commit a9bc28aa4e64320668131349436a650bf42591a5 ] The main channel Received Signal Strength Indicator (RSSI) measurement is used to determine whether an RF field is present or not. RSSI != 0 is interpreted as an RF Field is present. This does not take RF noise and measurement inaccuracy into account, and results in false positives in the field. Define a noise level and make sure the RF field is only interpreted as present when the RSSI is above the noise level. Fixes: 851ee3cbf850 ("NFC: trf7970a: Don't turn on RF if there is already an RF field") Signed-off-by: Paul Geurts Reviewed-by: Krzysztof Kozlowski Reviewed-by: Mark Greer Link: https://patch.msgid.link/20260422100930.581237-1-paul.geurts@prodrive-technologies.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/nfc/trf7970a.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index d17c701c7888b..08c27bb438b59 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -317,6 +317,7 @@ #define TRF7970A_RSSI_OSC_STATUS_RSSI_MASK (BIT(2) | BIT(1) | BIT(0)) #define TRF7970A_RSSI_OSC_STATUS_RSSI_X_MASK (BIT(5) | BIT(4) | BIT(3)) #define TRF7970A_RSSI_OSC_STATUS_RSSI_OSC_OK BIT(6) +#define TRF7970A_RSSI_OSC_STATUS_RSSI_NOISE_LEVEL 1 #define TRF7970A_SPECIAL_FCN_REG1_COL_7_6 BIT(0) #define TRF7970A_SPECIAL_FCN_REG1_14_ANTICOLL BIT(1) @@ -1300,7 +1301,7 @@ static int trf7970a_is_rf_field(struct trf7970a *trf, bool *is_rf_field) if (ret) return ret; - if (rssi & TRF7970A_RSSI_OSC_STATUS_RSSI_MASK) + if ((rssi & TRF7970A_RSSI_OSC_STATUS_RSSI_MASK) > TRF7970A_RSSI_OSC_STATUS_RSSI_NOISE_LEVEL) *is_rf_field = true; else *is_rf_field = false; From 48b26d48e76221dc90b02bf5428bab53643461ca Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Thu, 23 Apr 2026 00:19:58 +0800 Subject: [PATCH 0962/1518] net/sched: taprio: fix NULL pointer dereference in class dump [ Upstream commit 3d07ca5c0fae311226f737963984bd94bb159a87 ] When a TAPRIO child qdisc is deleted via RTM_DELQDISC, taprio_graft() is called with new == NULL and stores NULL into q->qdiscs[cl - 1]. Subsequent RTM_GETTCLASS dump operations walk all classes via taprio_walk() and call taprio_dump_class(), which calls taprio_leaf() returning the NULL pointer, then dereferences it to read child->handle, causing a kernel NULL pointer dereference. The bug is reachable with namespace-scoped CAP_NET_ADMIN on any kernel with CONFIG_NET_SCH_TAPRIO enabled. On systems with unprivileged user namespaces enabled, an unprivileged local user can trigger a kernel panic by creating a taprio qdisc inside a new network namespace, grafting an explicit child qdisc, deleting it, and requesting a class dump. The RTM_GETTCLASS dump itself requires no capability. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000007: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:taprio_dump_class (net/sched/sch_taprio.c:2478) Call Trace: tc_fill_tclass (net/sched/sch_api.c:1966) qdisc_class_dump (net/sched/sch_api.c:2326) taprio_walk (net/sched/sch_taprio.c:2514) tc_dump_tclass_qdisc (net/sched/sch_api.c:2352) tc_dump_tclass_root (net/sched/sch_api.c:2370) tc_dump_tclass (net/sched/sch_api.c:2431) rtnl_dumpit (net/core/rtnetlink.c:6864) netlink_dump (net/netlink/af_netlink.c:2325) rtnetlink_rcv_msg (net/core/rtnetlink.c:6959) netlink_rcv_skb (net/netlink/af_netlink.c:2550) Fix this by substituting &noop_qdisc when new is NULL in taprio_graft(), a common pattern used by other qdiscs (e.g., multiq_graft()) to ensure the q->qdiscs[] slots are never NULL. This makes control-plane dump paths safe without requiring individual NULL checks. Since the data-plane paths (taprio_enqueue and taprio_dequeue_from_txq) previously had explicit NULL guards that would drop/skip the packet cleanly, update those checks to test for &noop_qdisc instead. Without this, packets would reach taprio_enqueue_one() which increments the root qdisc's qlen and backlog before calling the child's enqueue; noop_qdisc drops the packet but those counters are never rolled back, permanently inflating the root qdisc's statistics. After this change *old can be a valid qdisc, NULL, or &noop_qdisc. Only call qdisc_put(*old) in the first case to avoid decreasing noop_qdisc's refcount, which was never increased. Fixes: 665338b2a7a0 ("net/sched: taprio: dump class stats for the actual q->qdiscs[]") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Acked-by: Jamal Hadi Salim Tested-by: Weiming Shi Link: https://patch.msgid.link/20260422161958.2517539-3-bestswngs@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_taprio.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 91b85360f8091..b3481cafa6eca 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -633,7 +633,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, queue = skb_get_queue_mapping(skb); child = q->qdiscs[queue]; - if (unlikely(!child)) + if (unlikely(child == &noop_qdisc)) return qdisc_drop(skb, sch, to_free); if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { @@ -716,7 +716,7 @@ static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, int len; u8 tc; - if (unlikely(!child)) + if (unlikely(child == &noop_qdisc)) return NULL; if (TXTIME_ASSIST_IS_ENABLED(q->flags)) @@ -2185,6 +2185,9 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl, if (!dev_queue) return -EINVAL; + if (!new) + new = &noop_qdisc; + if (dev->flags & IFF_UP) dev_deactivate(dev); @@ -2198,14 +2201,14 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl, *old = q->qdiscs[cl - 1]; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old); - if (new) + if (new != &noop_qdisc) qdisc_refcount_inc(new); - if (*old) + if (*old && *old != &noop_qdisc) qdisc_put(*old); } q->qdiscs[cl - 1] = new; - if (new) + if (new != &noop_qdisc) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) From 63063ba60d2dc334e34f1e3f9271d7f3f6f30307 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 24 Apr 2026 16:58:38 +0200 Subject: [PATCH 0963/1518] neigh: let neigh_xmit take skb ownership [ Upstream commit 4438113be604ee67a7bf4f81da6e1cca41332ce4 ] neigh_xmit always releases the skb, except when no neighbour table is found. But even the first added user of neigh_xmit (mpls) relied on neigh_xmit to release the skb (or queue it for tx). sashiko reported: If neigh_xmit() is called with an uninitialized neighbor table (for example, NEIGH_ND_TABLE when IPv6 is disabled), it returns -EAFNOSUPPORT and bypasses its internal out_kfree_skb error path. Because the return value of neigh_xmit() is ignored here, does this leak the SKB? Assume full ownership and remove the last code path that doesn't xmit or free skb. Fixes: 4fd3d7d9e868 ("neigh: Add helper function neigh_xmit") Signed-off-by: Florian Westphal Reviewed-by: Kuniyuki Iwashima Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260424145843.74055-1-fw@strlen.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/neighbour.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6dab4d1c2263d..dabd368eaa4e7 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3182,8 +3182,10 @@ int neigh_xmit(int index, struct net_device *dev, rcu_read_lock(); tbl = rcu_dereference(neigh_tables[index]); - if (!tbl) - goto out_unlock; + if (!tbl) { + rcu_read_unlock(); + goto out_kfree_skb; + } if (index == NEIGH_ARP_TABLE) { u32 key = *((u32 *)addr); @@ -3199,7 +3201,6 @@ int neigh_xmit(int index, struct net_device *dev, goto out_kfree_skb; } err = READ_ONCE(neigh->output)(neigh, skb); -out_unlock: rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { @@ -3209,11 +3210,10 @@ int neigh_xmit(int index, struct net_device *dev, goto out_kfree_skb; err = dev_queue_xmit(skb); } -out: return err; out_kfree_skb: kfree_skb(skb); - goto out; + return err; } EXPORT_SYMBOL(neigh_xmit); From 9544ca41e1ec6900610af46b3abebcb9d62ddea1 Mon Sep 17 00:00:00 2001 From: Altan Hacigumus Date: Thu, 23 Apr 2026 18:46:38 -0700 Subject: [PATCH 0964/1518] tcp: make probe0 timer handle expired user timeout [ Upstream commit 2b9f6f7065d4cfb65ba19126e0b35ac4544c3f3a ] tcp_clamp_probe0_to_user_timeout() computes remaining time in jiffies using subtraction with an unsigned lvalue. If elapsed probing time exceeds the configured TCP_USER_TIMEOUT, the underflow yields a large value. This ends up re-arming the probe timer for a full backoff interval instead of expiring immediately, delaying connection teardown beyond the configured timeout. Fix this by preventing underflow so user-set timeout expiration is handled correctly without extending the probe timer. Fixes: 344db93ae3ee ("tcp: make TCP_USER_TIMEOUT accurate for zero window probes") Link: https://lore.kernel.org/r/20260414013634.43997-1-ahacigu.linux@gmail.com Signed-off-by: Altan Hacigumus Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260424014639.54110-1-ahacigu.linux@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_timer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b2e5848b6980a..1e6d7d90371a9 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -49,7 +49,8 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { const struct inet_connection_sock *icsk = inet_csk(sk); - u32 remaining, user_timeout; + u32 user_timeout; + s32 remaining; s32 elapsed; user_timeout = READ_ONCE(icsk->icsk_user_timeout); @@ -60,7 +61,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) if (unlikely(elapsed < 0)) elapsed = 0; remaining = msecs_to_jiffies(user_timeout) - elapsed; - remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); + remaining = max_t(int, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when); } From f9e6b2f22b1f70de3f2af2145b69a58dfa1d7b3e Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 24 Apr 2026 08:31:16 -0700 Subject: [PATCH 0965/1518] netpoll: fix IPv6 local-address corruption [ Upstream commit 3bc179bc7146c26c9dff75d2943d10528274e301 ] netpoll_setup() decides whether to auto-populate the local source address by testing np->local_ip.ip, which only inspects the first 4 bytes of the union inet_addr storage. For an IPv6 netpoll whose caller-supplied local address has a zero high-32 bits (::1, ::, IPv4-mapped ::ffff:a.b.c.d, etc.), this misdetects the address as unset (which they are not, but the first 4 bytes are empty), calls netpoll_take_ipv6() and overwrites it with whatever matching link-local/global address the device happens to expose first. Introduce a helper netpoll_local_ip_unset() that picks the correct family-aware test (ipv6_addr_any() for IPv6, !.ip for IPv4) and use it from netpoll_setup(). Reproducer is something like: echo "::2" > local_ip echo 1 > enabled cat local_ip # before this fix: 2001:db8::1 (caller-supplied ::2 was clobbered) # after this fix: ::2 Fixes: b7394d2429c1 ("netpoll: prepare for ipv6") Signed-off-by: Breno Leitao Link: https://patch.msgid.link/20260424-netpoll_fix-v1-1-3a55348c625f@debian.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/netpoll.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6b1f470264c12..854e37c41653b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -706,6 +706,23 @@ static int netpoll_take_ipv4(struct netpoll *np, struct net_device *ndev) return 0; } +/* + * Test whether the caller left np->local_ip unset, so that + * netpoll_setup() should auto-populate it from the egress device. + * + * np->local_ip is a union of __be32 (IPv4) and struct in6_addr (IPv6), + * so an IPv6 address whose first 4 bytes are zero (e.g. ::1, ::2, + * IPv4-mapped ::ffff:a.b.c.d) must not be tested via the IPv4 arm — + * doing so would misclassify a caller-supplied address as unset and + * silently overwrite it with whatever address the device exposes. + */ +static bool netpoll_local_ip_unset(const struct netpoll *np) +{ + if (np->ipv6) + return ipv6_addr_any(&np->local_ip.in6); + return !np->local_ip.ip; +} + int netpoll_setup(struct netpoll *np) { struct net *net = current->nsproxy->net_ns; @@ -750,7 +767,7 @@ int netpoll_setup(struct netpoll *np) rtnl_lock(); } - if (!np->local_ip.ip) { + if (netpoll_local_ip_unset(np)) { if (!np->ipv6) { err = netpoll_take_ipv4(np, ndev); if (err) From 67bdf14af6b8fabd52df8ed20827e4ad7696abff Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 27 Apr 2026 17:15:04 +0200 Subject: [PATCH 0966/1518] ALSA: usb-audio: Fix potential leak of pd at parsing UAC3 streams [ Upstream commit c39f0bc03f84ba64c9144c95714df1dc36150f6d ] At parsing UAC3 streams, we allocate a PD object at each time, and either assign or free it. But there is a case where the PD object may be leaked; namely, in __snd_usb_parse_audio_interface() loop, when an audioformat shares the same endpoint with others, it's put to a link and returns from snd_usb_add_audio_stream(), but the PD is forgotten afterwards. Overall, the treatment of PD object in the parser code is a bit flaky, and we should be more careful about the object ownership. This patch tries to fix the above case and improve the code a bit. The pd object is now managed with the auto-cleanup in the loop, and the ownership is updated when the pd object gets assigned to the stream, which guarantees the release of the leftover object. Fixes: 7edf3b5e6a45 ("ALSA: usb-audio: AudioStreaming Power Domain parsing") Link: https://patch.msgid.link/20260427151508.12544-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/quirks.c | 2 +- sound/usb/stream.c | 58 ++++++++++++++++++---------------------------- sound/usb/stream.h | 3 ++- 3 files changed, 25 insertions(+), 38 deletions(-) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index f21e708675422..1b4cfc2b68f9d 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -122,7 +122,7 @@ static int add_audio_stream_from_fixed_fmt(struct snd_usb_audio *chip, snd_usb_audioformat_set_sync_ep(chip, fp); - err = snd_usb_add_audio_stream(chip, stream, fp); + err = snd_usb_add_audio_stream(chip, stream, fp, NULL); if (err < 0) return err; diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 8b83092a1999e..34a50fb4e50b9 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -79,7 +79,7 @@ static void snd_usb_audio_pcm_free(struct snd_pcm *pcm) static void snd_usb_init_substream(struct snd_usb_stream *as, int stream, struct audioformat *fp, - struct snd_usb_power_domain *pd) + struct snd_usb_power_domain **pdptr) { struct snd_usb_substream *subs = &as->substream[stream]; @@ -105,10 +105,11 @@ static void snd_usb_init_substream(struct snd_usb_stream *as, if (fp->channels > subs->channels_max) subs->channels_max = fp->channels; - if (pd) { - subs->str_pd = pd; + if (pdptr && *pdptr) { + subs->str_pd = *pdptr; + *pdptr = NULL; /* assigned */ /* Initialize Power Domain to idle status D1 */ - snd_usb_power_domain_set(subs->stream->chip, pd, + snd_usb_power_domain_set(subs->stream->chip, subs->str_pd, UAC3_PD_STATE_D1); } @@ -486,11 +487,14 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor * if not, create a new pcm stream. note, fp is added to the substream * fmt_list and will be freed on the chip instance release. do not free * fp or do remove it from the substream fmt_list to avoid double-free. + * + * pdptr is optional and can be NULL. When it's non-NULL and the PD gets + * assigned to the stream, *pdptr is cleared to NULL upon return. */ -static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, - int stream, - struct audioformat *fp, - struct snd_usb_power_domain *pd) +int snd_usb_add_audio_stream(struct snd_usb_audio *chip, + int stream, + struct audioformat *fp, + struct snd_usb_power_domain **pdptr) { struct snd_usb_stream *as; @@ -523,7 +527,7 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, err = snd_pcm_new_stream(as->pcm, stream, 1); if (err < 0) return err; - snd_usb_init_substream(as, stream, fp, pd); + snd_usb_init_substream(as, stream, fp, pdptr); return add_chmap(as->pcm, stream, subs); } @@ -552,7 +556,7 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, else strscpy(pcm->name, "USB Audio"); - snd_usb_init_substream(as, stream, fp, pd); + snd_usb_init_substream(as, stream, fp, pdptr); /* * Keep using head insertion for M-Audio Audiophile USB (tm) which has a @@ -570,21 +574,6 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, return add_chmap(pcm, stream, &as->substream[stream]); } -int snd_usb_add_audio_stream(struct snd_usb_audio *chip, - int stream, - struct audioformat *fp) -{ - return __snd_usb_add_audio_stream(chip, stream, fp, NULL); -} - -static int snd_usb_add_audio_stream_v3(struct snd_usb_audio *chip, - int stream, - struct audioformat *fp, - struct snd_usb_power_domain *pd) -{ - return __snd_usb_add_audio_stream(chip, stream, fp, pd); -} - static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip, struct usb_host_interface *alts, int protocol, int iface_no) @@ -1109,8 +1098,7 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, } } - if (pd) - *pd_out = pd; + *pd_out = pd; return fp; } @@ -1125,7 +1113,6 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, struct usb_interface_descriptor *altsd; int i, altno, err, stream; struct audioformat *fp = NULL; - struct snd_usb_power_domain *pd = NULL; bool set_iface_first; int num, protocol; @@ -1167,6 +1154,12 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, if (snd_usb_apply_interface_quirk(chip, iface_no, altno)) continue; + /* pd may be allocated at snd_usb_get_audioformat_uac3() and + * assigned at snd_usb_add_audio_stream(); otherwise it'll be + * freed automatically by cleanup at each loop. + */ + struct snd_usb_power_domain *pd __free(kfree) = NULL; + /* * Roland audio streaming interfaces are marked with protocols * 0/1/2, but are UAC 1 compatible. @@ -1222,23 +1215,16 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, *has_non_pcm = true; if ((fp->fmt_type == UAC_FORMAT_TYPE_I) == non_pcm) { audioformat_free(fp); - kfree(pd); fp = NULL; - pd = NULL; continue; } snd_usb_audioformat_set_sync_ep(chip, fp); dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint); - if (protocol == UAC_VERSION_3) - err = snd_usb_add_audio_stream_v3(chip, stream, fp, pd); - else - err = snd_usb_add_audio_stream(chip, stream, fp); - + err = snd_usb_add_audio_stream(chip, stream, fp, &pd); if (err < 0) { audioformat_free(fp); - kfree(pd); return err; } diff --git a/sound/usb/stream.h b/sound/usb/stream.h index d92e18d5818fe..61b9a133da018 100644 --- a/sound/usb/stream.h +++ b/sound/usb/stream.h @@ -7,7 +7,8 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int snd_usb_add_audio_stream(struct snd_usb_audio *chip, int stream, - struct audioformat *fp); + struct audioformat *fp, + struct snd_usb_power_domain **pdptr); #endif /* __USBAUDIO_STREAM_H */ From 7ce7a08cde16bd28d406e870fa0baa076e0eb160 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 12 Nov 2025 12:25:21 +0000 Subject: [PATCH 0967/1518] sched/fair: Reimplement NEXT_BUDDY to align with EEVDF goals [ Upstream commit e837456fdca81899a3c8e47b3fd39e30eae6e291 ] Reimplement NEXT_BUDDY preemption to take into account the deadline and eligibility of the wakee with respect to the waker. In the event multiple buddies could be considered, the one with the earliest deadline is selected. Sync wakeups are treated differently to every other type of wakeup. The WF_SYNC assumption is that the waker promises to sleep in the very near future. This is violated in enough cases that WF_SYNC should be treated as a suggestion instead of a contract. If a waker does go to sleep almost immediately then the delay in wakeup is negligible. In other cases, it's throttled based on the accumulated runtime of the waker so there is a chance that some batched wakeups have been issued before preemption. For all other wakeups, preemption happens if the wakee has a earlier deadline than the waker and eligible to run. While many workloads were tested, the two main targets were a modified dbench4 benchmark and hackbench because the are on opposite ends of the spectrum -- one prefers throughput by avoiding preemption and the other relies on preemption. First is the dbench throughput data even though it is a poor metric but it is the default metric. The test machine is a 2-socket machine and the backing filesystem is XFS as a lot of the IO work is dispatched to kernel threads. It's important to note that these results are not representative across all machines, especially Zen machines, as different bottlenecks are exposed on different machines and filesystems. dbench4 Throughput (misleading but traditional) 6.18-rc1 6.18-rc1 vanilla sched-preemptnext-v5 Hmean 1 1268.80 ( 0.00%) 1269.74 ( 0.07%) Hmean 4 3971.74 ( 0.00%) 3950.59 ( -0.53%) Hmean 7 5548.23 ( 0.00%) 5420.08 ( -2.31%) Hmean 12 7310.86 ( 0.00%) 7165.57 ( -1.99%) Hmean 21 8874.53 ( 0.00%) 9149.04 ( 3.09%) Hmean 30 9361.93 ( 0.00%) 10530.04 ( 12.48%) Hmean 48 9540.14 ( 0.00%) 11820.40 ( 23.90%) Hmean 79 9208.74 ( 0.00%) 12193.79 ( 32.42%) Hmean 110 8573.12 ( 0.00%) 11933.72 ( 39.20%) Hmean 141 7791.33 ( 0.00%) 11273.90 ( 44.70%) Hmean 160 7666.60 ( 0.00%) 10768.72 ( 40.46%) As throughput is misleading, the benchmark is modified to use a short loadfile report the completion time duration in milliseconds. dbench4 Loadfile Execution Time 6.18-rc1 6.18-rc1 vanilla sched-preemptnext-v5 Amean 1 14.62 ( 0.00%) 14.69 ( -0.46%) Amean 4 18.76 ( 0.00%) 18.85 ( -0.45%) Amean 7 23.71 ( 0.00%) 24.38 ( -2.82%) Amean 12 31.25 ( 0.00%) 31.87 ( -1.97%) Amean 21 45.12 ( 0.00%) 43.69 ( 3.16%) Amean 30 61.07 ( 0.00%) 54.33 ( 11.03%) Amean 48 95.91 ( 0.00%) 77.22 ( 19.49%) Amean 79 163.38 ( 0.00%) 123.08 ( 24.66%) Amean 110 243.91 ( 0.00%) 175.11 ( 28.21%) Amean 141 343.47 ( 0.00%) 239.10 ( 30.39%) Amean 160 401.15 ( 0.00%) 283.73 ( 29.27%) Stddev 1 0.52 ( 0.00%) 0.51 ( 2.45%) Stddev 4 1.36 ( 0.00%) 1.30 ( 4.04%) Stddev 7 1.88 ( 0.00%) 1.87 ( 0.72%) Stddev 12 3.06 ( 0.00%) 2.45 ( 19.83%) Stddev 21 5.78 ( 0.00%) 3.87 ( 33.06%) Stddev 30 9.85 ( 0.00%) 5.25 ( 46.76%) Stddev 48 22.31 ( 0.00%) 8.64 ( 61.27%) Stddev 79 35.96 ( 0.00%) 18.07 ( 49.76%) Stddev 110 59.04 ( 0.00%) 30.93 ( 47.61%) Stddev 141 85.38 ( 0.00%) 40.93 ( 52.06%) Stddev 160 96.38 ( 0.00%) 39.72 ( 58.79%) That is still looking good and the variance is reduced quite a bit. Finally, fairness is a concern so the next report tracks how many milliseconds does it take for all clients to complete a workfile. This one is tricky because dbench makes to effort to synchronise clients so the durations at benchmark start time differ substantially from typical runtimes. This problem could be mitigated by warming up the benchmark for a number of minutes but it's a matter of opinion whether that counts as an evasion of inconvenient results. dbench4 All Clients Loadfile Execution Time 6.18-rc1 6.18-rc1 vanilla sched-preemptnext-v5 Amean 1 15.06 ( 0.00%) 15.07 ( -0.03%) Amean 4 603.81 ( 0.00%) 524.29 ( 13.17%) Amean 7 855.32 ( 0.00%) 1331.07 ( -55.62%) Amean 12 1890.02 ( 0.00%) 2323.97 ( -22.96%) Amean 21 3195.23 ( 0.00%) 2009.29 ( 37.12%) Amean 30 13919.53 ( 0.00%) 4579.44 ( 67.10%) Amean 48 25246.07 ( 0.00%) 5705.46 ( 77.40%) Amean 79 29701.84 ( 0.00%) 15509.26 ( 47.78%) Amean 110 22803.03 ( 0.00%) 23782.08 ( -4.29%) Amean 141 36356.07 ( 0.00%) 25074.20 ( 31.03%) Amean 160 17046.71 ( 0.00%) 13247.62 ( 22.29%) Stddev 1 0.47 ( 0.00%) 0.49 ( -3.74%) Stddev 4 395.24 ( 0.00%) 254.18 ( 35.69%) Stddev 7 467.24 ( 0.00%) 764.42 ( -63.60%) Stddev 12 1071.43 ( 0.00%) 1395.90 ( -30.28%) Stddev 21 1694.50 ( 0.00%) 1204.89 ( 28.89%) Stddev 30 7945.63 ( 0.00%) 2552.59 ( 67.87%) Stddev 48 14339.51 ( 0.00%) 3227.55 ( 77.49%) Stddev 79 16620.91 ( 0.00%) 8422.15 ( 49.33%) Stddev 110 12912.15 ( 0.00%) 13560.95 ( -5.02%) Stddev 141 20700.13 ( 0.00%) 14544.51 ( 29.74%) Stddev 160 9079.16 ( 0.00%) 7400.69 ( 18.49%) This is more of a mixed bag but it at least shows that fairness is not crippled. The hackbench results are more neutral but this is still important. It's possible to boost the dbench figures by a large amount but only by crippling the performance of a workload like hackbench. The WF_SYNC behaviour is important for these workloads and is why the WF_SYNC changes are not a separate patch. hackbench-process-pipes 6.18-rc1 6.18-rc1 vanilla sched-preemptnext-v5 Amean 1 0.2657 ( 0.00%) 0.2150 ( 19.07%) Amean 4 0.6107 ( 0.00%) 0.6060 ( 0.76%) Amean 7 0.7923 ( 0.00%) 0.7440 ( 6.10%) Amean 12 1.1500 ( 0.00%) 1.1263 ( 2.06%) Amean 21 1.7950 ( 0.00%) 1.7987 ( -0.20%) Amean 30 2.3207 ( 0.00%) 2.5053 ( -7.96%) Amean 48 3.5023 ( 0.00%) 3.9197 ( -11.92%) Amean 79 4.8093 ( 0.00%) 5.2247 ( -8.64%) Amean 110 6.1160 ( 0.00%) 6.6650 ( -8.98%) Amean 141 7.4763 ( 0.00%) 7.8973 ( -5.63%) Amean 172 8.9560 ( 0.00%) 9.3593 ( -4.50%) Amean 203 10.4783 ( 0.00%) 10.8347 ( -3.40%) Amean 234 12.4977 ( 0.00%) 13.0177 ( -4.16%) Amean 265 14.7003 ( 0.00%) 15.5630 ( -5.87%) Amean 296 16.1007 ( 0.00%) 17.4023 ( -8.08%) Processes using pipes are impacted but the variance (not presented) indicates it's close to noise and the results are not always reproducible. If executed across multiple reboots, it may show neutral or small gains so the worst measured results are presented. Hackbench using sockets is more reliably neutral as the wakeup mechanisms are different between sockets and pipes. hackbench-process-sockets 6.18-rc1 6.18-rc1 vanilla sched-preemptnext-v2 Amean 1 0.3073 ( 0.00%) 0.3263 ( -6.18%) Amean 4 0.7863 ( 0.00%) 0.7930 ( -0.85%) Amean 7 1.3670 ( 0.00%) 1.3537 ( 0.98%) Amean 12 2.1337 ( 0.00%) 2.1903 ( -2.66%) Amean 21 3.4683 ( 0.00%) 3.4940 ( -0.74%) Amean 30 4.7247 ( 0.00%) 4.8853 ( -3.40%) Amean 48 7.6097 ( 0.00%) 7.8197 ( -2.76%) Amean 79 14.7957 ( 0.00%) 16.1000 ( -8.82%) Amean 110 21.3413 ( 0.00%) 21.9997 ( -3.08%) Amean 141 29.0503 ( 0.00%) 29.0353 ( 0.05%) Amean 172 36.4660 ( 0.00%) 36.1433 ( 0.88%) Amean 203 39.7177 ( 0.00%) 40.5910 ( -2.20%) Amean 234 42.1120 ( 0.00%) 43.5527 ( -3.42%) Amean 265 45.7830 ( 0.00%) 50.0560 ( -9.33%) Amean 296 50.7043 ( 0.00%) 54.3657 ( -7.22%) As schbench has been mentioned in numerous bugs recently, the results are interesting. A test case that represents the default schbench behaviour is schbench Wakeup Latency (usec) 6.18.0-rc1 6.18.0-rc1 vanilla sched-preemptnext-v5 Amean Wakeup-50th-80 7.17 ( 0.00%) 6.00 ( 16.28%) Amean Wakeup-90th-80 46.56 ( 0.00%) 19.78 ( 57.52%) Amean Wakeup-99th-80 119.61 ( 0.00%) 89.94 ( 24.80%) Amean Wakeup-99.9th-80 3193.78 ( 0.00%) 328.22 ( 89.72%) schbench Requests Per Second (ops/sec) 6.18.0-rc1 6.18.0-rc1 vanilla sched-preemptnext-v5 Hmean RPS-20th-80 8900.91 ( 0.00%) 9176.78 ( 3.10%) Hmean RPS-50th-80 8987.41 ( 0.00%) 9217.89 ( 2.56%) Hmean RPS-90th-80 9123.73 ( 0.00%) 9273.25 ( 1.64%) Hmean RPS-max-80 9193.50 ( 0.00%) 9301.47 ( 1.17%) Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20251112122521.1331238-3-mgorman@techsingularity.net Stable-dep-of: ac8e69e69363 ("sched/fair: Fix wakeup_preempt_fair() vs delayed dequeue") Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 152 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 130 insertions(+), 22 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d9777c81db0da..293a8804428b0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1021,6 +1021,16 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect) if (cfs_rq->nr_queued == 1) return curr && curr->on_rq ? curr : se; + /* + * Picking the ->next buddy will affect latency but not fairness. + */ + if (sched_feat(PICK_BUDDY) && + cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) { + /* ->next will never be delayed */ + WARN_ON_ONCE(cfs_rq->next->sched_delayed); + return cfs_rq->next; + } + if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr))) curr = NULL; @@ -1260,6 +1270,8 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) return delta_exec; } +static void set_next_buddy(struct sched_entity *se); + /* * Used by other classes to account runtime. */ @@ -5576,16 +5588,6 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq) { struct sched_entity *se; - /* - * Picking the ->next buddy will affect latency but not fairness. - */ - if (sched_feat(PICK_BUDDY) && - cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) { - /* ->next will never be delayed */ - WARN_ON_ONCE(cfs_rq->next->sched_delayed); - return cfs_rq->next; - } - se = pick_eevdf(cfs_rq); if (se->sched_delayed) { dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED); @@ -7099,8 +7101,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) hrtick_update(rq); } -static void set_next_buddy(struct sched_entity *se); - /* * Basically dequeue_task_fair(), except it can deal with dequeue_entity() * failing half-way through and resume the dequeue later. @@ -8796,16 +8796,81 @@ static void set_next_buddy(struct sched_entity *se) } } +enum preempt_wakeup_action { + PREEMPT_WAKEUP_NONE, /* No preemption. */ + PREEMPT_WAKEUP_SHORT, /* Ignore slice protection. */ + PREEMPT_WAKEUP_PICK, /* Let __pick_eevdf() decide. */ + PREEMPT_WAKEUP_RESCHED, /* Force reschedule. */ +}; + +static inline bool +set_preempt_buddy(struct cfs_rq *cfs_rq, int wake_flags, + struct sched_entity *pse, struct sched_entity *se) +{ + /* + * Keep existing buddy if the deadline is sooner than pse. + * The older buddy may be cache cold and completely unrelated + * to the current wakeup but that is unpredictable where as + * obeying the deadline is more in line with EEVDF objectives. + */ + if (cfs_rq->next && entity_before(cfs_rq->next, pse)) + return false; + + set_next_buddy(pse); + return true; +} + +/* + * WF_SYNC|WF_TTWU indicates the waker expects to sleep but it is not + * strictly enforced because the hint is either misunderstood or + * multiple tasks must be woken up. + */ +static inline enum preempt_wakeup_action +preempt_sync(struct rq *rq, int wake_flags, + struct sched_entity *pse, struct sched_entity *se) +{ + u64 threshold, delta; + + /* + * WF_SYNC without WF_TTWU is not expected so warn if it happens even + * though it is likely harmless. + */ + WARN_ON_ONCE(!(wake_flags & WF_TTWU)); + + threshold = sysctl_sched_migration_cost; + delta = rq_clock_task(rq) - se->exec_start; + if ((s64)delta < 0) + delta = 0; + + /* + * WF_RQ_SELECTED implies the tasks are stacking on a CPU when they + * could run on other CPUs. Reduce the threshold before preemption is + * allowed to an arbitrary lower value as it is more likely (but not + * guaranteed) the waker requires the wakee to finish. + */ + if (wake_flags & WF_RQ_SELECTED) + threshold >>= 2; + + /* + * As WF_SYNC is not strictly obeyed, allow some runtime for batch + * wakeups to be issued. + */ + if (entity_before(pse, se) && delta >= threshold) + return PREEMPT_WAKEUP_RESCHED; + + return PREEMPT_WAKEUP_NONE; +} + /* * Preempt the current task with a newly woken task if needed: */ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags) { + enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK; struct task_struct *donor = rq->donor; struct sched_entity *se = &donor->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(donor); int cse_is_idle, pse_is_idle; - bool do_preempt_short = false; if (unlikely(se == pse)) return; @@ -8819,10 +8884,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if (task_is_throttled(p)) return; - if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) { - set_next_buddy(pse); - } - /* * We can come here with TIF_NEED_RESCHED already set from new task * wake up path. @@ -8854,7 +8915,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int * When non-idle entity preempt an idle entity, * don't give idle entity slice protection. */ - do_preempt_short = true; + preempt_action = PREEMPT_WAKEUP_SHORT; goto preempt; } @@ -8873,21 +8934,68 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int * If @p has a shorter slice than current and @p is eligible, override * current's slice protection in order to allow preemption. */ - do_preempt_short = sched_feat(PREEMPT_SHORT) && (pse->slice < se->slice); + if (sched_feat(PREEMPT_SHORT) && (pse->slice < se->slice)) { + preempt_action = PREEMPT_WAKEUP_SHORT; + goto pick; + } + /* + * Ignore wakee preemption on WF_FORK as it is less likely that + * there is shared data as exec often follow fork. Do not + * preempt for tasks that are sched_delayed as it would violate + * EEVDF to forcibly queue an ineligible task. + */ + if ((wake_flags & WF_FORK) || pse->sched_delayed) + return; + + /* + * If @p potentially is completing work required by current then + * consider preemption. + * + * Reschedule if waker is no longer eligible. */ + if (in_task() && !entity_eligible(cfs_rq, se)) { + preempt_action = PREEMPT_WAKEUP_RESCHED; + goto preempt; + } + + /* Prefer picking wakee soon if appropriate. */ + if (sched_feat(NEXT_BUDDY) && + set_preempt_buddy(cfs_rq, wake_flags, pse, se)) { + + /* + * Decide whether to obey WF_SYNC hint for a new buddy. Old + * buddies are ignored as they may not be relevant to the + * waker and less likely to be cache hot. + */ + if (wake_flags & WF_SYNC) + preempt_action = preempt_sync(rq, wake_flags, pse, se); + } + + switch (preempt_action) { + case PREEMPT_WAKEUP_NONE: + return; + case PREEMPT_WAKEUP_RESCHED: + goto preempt; + case PREEMPT_WAKEUP_SHORT: + fallthrough; + case PREEMPT_WAKEUP_PICK: + break; + } + +pick: /* * If @p has become the most eligible task, force preemption. */ - if (__pick_eevdf(cfs_rq, !do_preempt_short) == pse) + if (__pick_eevdf(cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT) == pse) goto preempt; - if (sched_feat(RUN_TO_PARITY) && do_preempt_short) + if (sched_feat(RUN_TO_PARITY)) update_protect_slice(cfs_rq, se); return; preempt: - if (do_preempt_short) + if (preempt_action == PREEMPT_WAKEUP_SHORT) cancel_protect_slice(se); resched_curr_lazy(rq); From 63273472430ea50b7e1ea1c4e2b4a385af4c78b1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 22 Apr 2026 11:34:00 +0200 Subject: [PATCH 0968/1518] sched/fair: Fix wakeup_preempt_fair() vs delayed dequeue [ Upstream commit ac8e69e693631689d74d8f1ebee6f84f737f797f ] Similar to how pick_next_entity() must dequeue delayed entities, so too must wakeup_preempt_fair(). Any delayed task being found means it is eligible and hence past the 0-lag point, ready for removal. Worse, by not removing delayed entities from consideration, it can skew the preemption decision, with the end result that a short slice wakeup will not result in a preemption. tip/sched/core tip/sched/core +this patch cyclictest slice (ms) (default)2.8 8 8 hackbench slice (ms) (default)2.8 20 20 Total Samples | 22559 22595 22683 Average (us) | 157 64( 59%) 59( 8%) Median (P50) (us) | 57 57( 0%) 58(- 2%) 90th Percentile (us) | 64 60( 6%) 60( 0%) 99th Percentile (us) | 2407 67( 97%) 67( 0%) 99.9th Percentile (us) | 3400 2288( 33%) 727( 68%) Maximum (us) | 5037 9252(-84%) 7461( 19%) Fixes: f12e148892ed ("sched/fair: Prepare pick_next_task() for delayed dequeue") Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260422093400.319251-1-vincent.guittot@linaro.org Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 293a8804428b0..565a96d6811e7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1007,7 +1007,7 @@ static inline void cancel_protect_slice(struct sched_entity *se) * * Which allows tree pruning through eligibility. */ -static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect) +static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq, bool protect) { struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node; struct sched_entity *se = __pick_first_entity(cfs_rq); @@ -1078,11 +1078,6 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect) return best; } -static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) -{ - return __pick_eevdf(cfs_rq, true); -} - struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) { struct rb_node *last = rb_last(&cfs_rq->tasks_timeline.rb_root); @@ -5584,11 +5579,11 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags); * 4) do not run the "skip" process, if something else is available */ static struct sched_entity * -pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq) +pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool protect) { struct sched_entity *se; - se = pick_eevdf(cfs_rq); + se = pick_eevdf(cfs_rq, protect); if (se->sched_delayed) { dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED); /* @@ -8868,7 +8863,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int { enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK; struct task_struct *donor = rq->donor; - struct sched_entity *se = &donor->se, *pse = &p->se; + struct sched_entity *nse, *se = &donor->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(donor); int cse_is_idle, pse_is_idle; @@ -8983,11 +8978,17 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int } pick: + nse = pick_next_entity(rq, cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT); + /* If @p has become the most eligible task, force preemption */ + if (nse == pse) + goto preempt; + /* - * If @p has become the most eligible task, force preemption. + * Because p is enqueued, nse being null can only mean that we + * dequeued a delayed task. */ - if (__pick_eevdf(cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT) == pse) - goto preempt; + if (!nse) + goto pick; if (sched_feat(RUN_TO_PARITY)) update_protect_slice(cfs_rq, se); @@ -9022,7 +9023,7 @@ static struct task_struct *pick_task_fair(struct rq *rq) throttled |= check_cfs_rq_runtime(cfs_rq); - se = pick_next_entity(rq, cfs_rq); + se = pick_next_entity(rq, cfs_rq, true); if (!se) goto again; cfs_rq = group_cfs_rq(se); From f3c16e1f4a314a20717ab90a41885f8111a242ab Mon Sep 17 00:00:00 2001 From: Zicheng Qu Date: Fri, 24 Apr 2026 07:11:13 +0000 Subject: [PATCH 0969/1518] sched/fair: Clear rel_deadline when initializing forked entities [ Upstream commit 3da56dc063cd77b9c0b40add930767fab4e389f3 ] A yield-triggered crash can happen when a newly forked sched_entity enters the fair class with se->rel_deadline unexpectedly set. The failing sequence is: 1. A task is forked while se->rel_deadline is still set. 2. __sched_fork() initializes vruntime, vlag and other sched_entity state, but does not clear rel_deadline. 3. On the first enqueue, enqueue_entity() calls place_entity(). 4. Because se->rel_deadline is set, place_entity() treats se->deadline as a relative deadline and converts it to an absolute deadline by adding the current vruntime. 5. However, the forked entity's deadline is not a valid inherited relative deadline for this new scheduling instance, so the conversion produces an abnormally large deadline. 6. If the task later calls sched_yield(), yield_task_fair() advances se->vruntime to se->deadline. 7. The inflated vruntime is then used by the following enqueue path, where the vruntime-derived key can overflow when multiplied by the entity weight. 8. This corrupts cfs_rq->sum_w_vruntime, breaks EEVDF eligibility calculation, and can eventually make all entities appear ineligible. pick_next_entity() may then return NULL unexpectedly, leading to a later NULL dereference. A captured trace shows the effect clearly. Before yield, the entity's vruntime was around: 9834017729983308 After yield_task_fair() executed: se->vruntime = se->deadline the vruntime jumped to: 19668035460670230 and the deadline was later advanced further to: 19668035463470230 This shows that the deadline had already become abnormally large before yield_task_fair() copied it into vruntime. rel_deadline is only meaningful when se->deadline really carries a relative deadline that still needs to be placed against vruntime. A freshly forked sched_entity should not inherit or retain this state. Clear se->rel_deadline in __sched_fork(), together with the other sched_entity runtime state, so that the first enqueue does not interpret the new entity's deadline as a stale relative deadline. Fixes: 82e9d0456e06 ("sched/fair: Avoid re-setting virtual deadline on 'migrations'") Analyzed-by: Hui Tang Analyzed-by: Zhang Qiao Signed-off-by: Zicheng Qu Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260424071113.1199600-1-quzicheng@huawei.com Signed-off-by: Sasha Levin --- kernel/sched/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 421efba7db5a1..0d93f60fed20a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4453,6 +4453,7 @@ static void __sched_fork(u64 clone_flags, struct task_struct *p) p->se.nr_migrations = 0; p->se.vruntime = 0; p->se.vlag = 0; + p->se.rel_deadline = 0; INIT_LIST_HEAD(&p->se.group_node); /* A delayed task cannot be in clone(). */ From 8252ae66cfc4da6657d7dfee925970e6c301b821 Mon Sep 17 00:00:00 2001 From: "William A. Kennington III" Date: Thu, 23 Apr 2026 00:46:52 -0700 Subject: [PATCH 0970/1518] net: mctp i2c: check length before marking flow active [ Upstream commit 4ca07b9239bd0478ae586632a2ed72be37ed8407 ] Currently, mctp_i2c_get_tx_flow_state() is called before the packet length sanity check. This function marks a new flow as active in the MCTP core. If the sanity check fails, mctp_i2c_xmit() returns early without calling mctp_i2c_lock_nest(). This results in a mismatched locking state: the flow is active, but the I2C bus lock was never acquired for it. When the flow is later released, mctp_i2c_release_flow() will see the active state and queue an unlock marker. The TX thread will then decrement midev->i2c_lock_count from 0, causing it to underflow to -1. This underflow permanently breaks the driver's locking logic, allowing future transmissions to occur without holding the I2C bus lock, leading to bus collisions and potential hardware hangs. Move the mctp_i2c_get_tx_flow_state() call to after the length sanity check to ensure we only transition the flow state if we are actually going to proceed with the transmission and locking. Fixes: f5b8abf9fc3d ("mctp i2c: MCTP I2C binding driver") Signed-off-by: William A. Kennington III Acked-by: Jeremy Kerr Link: https://patch.msgid.link/20260423074741.201460-1-william@wkennington.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/mctp/mctp-i2c.c | 4 ++-- net/sched/cls_flower.c | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index f138b0251313e..115494f15e87a 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -496,8 +496,6 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) u8 *pecp; int rc; - fs = mctp_i2c_get_tx_flow_state(midev, skb); - hdr = (void *)skb_mac_header(skb); /* Sanity check that packet contents matches skb length, * and can't exceed MCTP_I2C_BUFSZ @@ -509,6 +507,8 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) return; } + fs = mctp_i2c_get_tx_flow_state(midev, skb); + if (skb_tailroom(skb) >= 1) { /* Linear case with space, we can just append the PEC */ skb_put(skb, 1); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 099ff6a3e1f51..f3af0ac892a86 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -560,6 +560,7 @@ static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { struct cls_fl_head *head = fl_head_dereference(tp); + struct fl_flow_mask *mask; *last = false; @@ -576,11 +577,12 @@ static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, list_del_rcu(&f->list); spin_unlock(&tp->lock); - *last = fl_mask_put(head, f->mask); + mask = f->mask; if (!tc_skip_hw(f->flags)) fl_hw_destroy_filter(tp, f, rtnl_held, extack); tcf_unbind_filter(tp, &f->res); __fl_put(f); + *last = fl_mask_put(head, mask); return 0; } From d934a2bbed534e995431f9e0f9bf17d285f5d109 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 16 Apr 2026 07:03:45 -0700 Subject: [PATCH 0971/1518] md/raid1,raid10: don't fail devices for invalid IO errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f7b24c7b41f23b5f9caa8b913afe79cd4c397d39 ] BLK_STS_INVAL indicates the IO request itself was invalid, not that the device has failed. When raid1 treats this as a device error, it retries on alternate mirrors which fail the same way, eventually exceeding the read error threshold and removing the device from the array. This happens when stacking configurations bypass bio_split_to_limits() in the IO path: dm-raid calls md_handle_request() directly without going through md_submit_bio(), skipping the alignment validation that would otherwise reject invalid bios early. The invalid bio reaches the lower block layers, which fail the bio with BLK_STS_INVAL, and raid1 wrongly interprets this as a device failure. Add BLK_STS_INVAL to raid1_should_handle_error() so that invalid IO errors are propagated back to the caller rather than triggering device removal. This is consistent with the previous kernel behavior when alignment checks were done earlier in the direct-io path. Fixes: 5ff3f74e145adc7 ("block: simplify direct io validity check") Reported-by: Tomáš Trnka Closes: https://lore.kernel.org/linux-block/2982107.4sosBPzcNG@electra/ Signed-off-by: Keith Busch Tested-by: Tomáš Trnka Link: https://lore.kernel.org/r/20260416140345.3872265-1-kbusch@meta.com Signed-off-by: Yu Kuai Signed-off-by: Sasha Levin --- drivers/md/raid1-10.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index 521625756128a..aba8c751e1922 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -298,8 +298,13 @@ static inline bool raid1_should_read_first(struct mddev *mddev, * bio with REQ_RAHEAD or REQ_NOWAIT can fail at anytime, before such IO is * submitted to the underlying disks, hence don't record badblocks or retry * in this case. + * + * BLK_STS_INVAL means the bio was not valid for the underlying device. This + * is a user error, not a device failure, so retrying or recording bad blocks + * would be wrong. */ static inline bool raid1_should_handle_error(struct bio *bio) { - return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)); + return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)) && + bio->bi_status != BLK_STS_INVAL; } From 00d5ae2b3b0f08c9ec17b40f1a83fc39aba9ba17 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 23 Mar 2026 13:46:42 +0800 Subject: [PATCH 0972/1518] md: add fallback to correct bitmap_ops on version mismatch [ Upstream commit 09af773650024279a60348e7319d599e6571b15c ] If default bitmap version and on-disk version doesn't match, and mdadm is not the latest version to set bitmap_type, set bitmap_ops based on the disk version. Link: https://lore.kernel.org/linux-raid/20260323054644.3351791-2-yukuai@fnnas.com/ Signed-off-by: Yu Kuai Stable-dep-of: f2926a533d03 ("md/md-bitmap: add a none backend for bitmap grow") Signed-off-by: Sasha Levin --- drivers/md/md.c | 111 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 110 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index b91ac1b7d7a15..4520c485c0c06 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6329,15 +6329,124 @@ static void md_safemode_timeout(struct timer_list *t) static int start_dirty_degraded; +/* + * Read bitmap superblock and return the bitmap_id based on disk version. + * This is used as fallback when default bitmap version and on-disk version + * doesn't match, and mdadm is not the latest version to set bitmap_type. + */ +static enum md_submodule_id md_bitmap_get_id_from_sb(struct mddev *mddev) +{ + struct md_rdev *rdev; + struct page *sb_page; + bitmap_super_t *sb; + enum md_submodule_id id = ID_BITMAP_NONE; + sector_t sector; + u32 version; + + if (!mddev->bitmap_info.offset) + return ID_BITMAP_NONE; + + sb_page = alloc_page(GFP_KERNEL); + if (!sb_page) { + pr_warn("md: %s: failed to allocate memory for bitmap\n", + mdname(mddev)); + return ID_BITMAP_NONE; + } + + sector = mddev->bitmap_info.offset; + + rdev_for_each(rdev, mddev) { + u32 iosize; + + if (!test_bit(In_sync, &rdev->flags) || + test_bit(Faulty, &rdev->flags) || + test_bit(Bitmap_sync, &rdev->flags)) + continue; + + iosize = roundup(sizeof(bitmap_super_t), + bdev_logical_block_size(rdev->bdev)); + if (sync_page_io(rdev, sector, iosize, sb_page, REQ_OP_READ, + true)) + goto read_ok; + } + pr_warn("md: %s: failed to read bitmap from any device\n", + mdname(mddev)); + goto out; + +read_ok: + sb = kmap_local_page(sb_page); + if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) { + pr_warn("md: %s: invalid bitmap magic 0x%x\n", + mdname(mddev), le32_to_cpu(sb->magic)); + goto out_unmap; + } + + version = le32_to_cpu(sb->version); + switch (version) { + case BITMAP_MAJOR_LO: + case BITMAP_MAJOR_HI: + case BITMAP_MAJOR_CLUSTERED: + id = ID_BITMAP; + break; + case BITMAP_MAJOR_LOCKLESS: + id = ID_LLBITMAP; + break; + default: + pr_warn("md: %s: unknown bitmap version %u\n", + mdname(mddev), version); + break; + } + +out_unmap: + kunmap_local(sb); +out: + __free_page(sb_page); + return id; +} + static int md_bitmap_create(struct mddev *mddev) { + enum md_submodule_id orig_id = mddev->bitmap_id; + enum md_submodule_id sb_id; + int err; + if (mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; if (!mddev_set_bitmap_ops(mddev)) return -ENOENT; - return mddev->bitmap_ops->create(mddev); + err = mddev->bitmap_ops->create(mddev); + if (!err) + return 0; + + /* + * Create failed, if default bitmap version and on-disk version + * doesn't match, and mdadm is not the latest version to set + * bitmap_type, set bitmap_ops based on the disk version. + */ + mddev_clear_bitmap_ops(mddev); + + sb_id = md_bitmap_get_id_from_sb(mddev); + if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) + return err; + + pr_info("md: %s: bitmap version mismatch, switching from %d to %d\n", + mdname(mddev), orig_id, sb_id); + + mddev->bitmap_id = sb_id; + if (!mddev_set_bitmap_ops(mddev)) { + mddev->bitmap_id = orig_id; + return -ENOENT; + } + + err = mddev->bitmap_ops->create(mddev); + if (err) { + mddev_clear_bitmap_ops(mddev); + mddev->bitmap_id = orig_id; + } + + return err; } static void md_bitmap_destroy(struct mddev *mddev) From 4d48143103919abc6b037a727256f9a366a78f9f Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sat, 25 Apr 2026 10:46:13 +0800 Subject: [PATCH 0973/1518] md: factor bitmap creation away from sysfs handling [ Upstream commit 8776d342cf8fa0b98ca5e6fb2d956966fb5ca364 ] Factor bitmap creation and destruction into helpers that do not touch bitmap sysfs registration. This prepares the bitmap sysfs rework so callers such as the sysfs bitmap location path can create or destroy a bitmap backend without coupling that to sysfs group lifetime management. Reviewed-by: Su Yue Link: https://lore.kernel.org/r/20260425024615.1696892-2-yukuai@fnnas.com Signed-off-by: Yu Kuai Stable-dep-of: f2926a533d03 ("md/md-bitmap: add a none backend for bitmap grow") Signed-off-by: Sasha Levin --- drivers/md/md.c | 78 +++++++++++++++++++++++++++++++------------------ 1 file changed, 49 insertions(+), 29 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 4520c485c0c06..3061370e959b3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -686,7 +686,25 @@ static void active_io_release(struct percpu_ref *ref) static void no_op(struct percpu_ref *r) {} -static bool mddev_set_bitmap_ops(struct mddev *mddev) +static void md_bitmap_sysfs_add(struct mddev *mddev) +{ + if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) + pr_warn("md: cannot register extra bitmap attributes for %s\n", + mdname(mddev)); + else + /* + * Inform user with KOBJ_CHANGE about new bitmap + * attributes. + */ + kobject_uevent(&mddev->kobj, KOBJ_CHANGE); +} + +static void md_bitmap_sysfs_del(struct mddev *mddev) +{ + sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group); +} + +static bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) { struct bitmap_operations *old = mddev->bitmap_ops; struct md_submodule_head *head; @@ -710,18 +728,6 @@ static bool mddev_set_bitmap_ops(struct mddev *mddev) mddev->bitmap_ops = (void *)head; xa_unlock(&md_submodule); - - if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) { - if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) - pr_warn("md: cannot register extra bitmap attributes for %s\n", - mdname(mddev)); - else - /* - * Inform user with KOBJ_CHANGE about new bitmap - * attributes. - */ - kobject_uevent(&mddev->kobj, KOBJ_CHANGE); - } return true; err: @@ -729,15 +735,6 @@ static bool mddev_set_bitmap_ops(struct mddev *mddev) return false; } -static void mddev_clear_bitmap_ops(struct mddev *mddev) -{ - if (!mddev_is_dm(mddev) && mddev->bitmap_ops && - mddev->bitmap_ops->group) - sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group); - - mddev->bitmap_ops = NULL; -} - int mddev_init(struct mddev *mddev) { int err = 0; @@ -6404,7 +6401,7 @@ static enum md_submodule_id md_bitmap_get_id_from_sb(struct mddev *mddev) return id; } -static int md_bitmap_create(struct mddev *mddev) +static int md_bitmap_create_nosysfs(struct mddev *mddev) { enum md_submodule_id orig_id = mddev->bitmap_id; enum md_submodule_id sb_id; @@ -6413,7 +6410,7 @@ static int md_bitmap_create(struct mddev *mddev) if (mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; - if (!mddev_set_bitmap_ops(mddev)) + if (!mddev_set_bitmap_ops_nosysfs(mddev)) return -ENOENT; err = mddev->bitmap_ops->create(mddev); @@ -6425,7 +6422,7 @@ static int md_bitmap_create(struct mddev *mddev) * doesn't match, and mdadm is not the latest version to set * bitmap_type, set bitmap_ops based on the disk version. */ - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; sb_id = md_bitmap_get_id_from_sb(mddev); if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) @@ -6435,27 +6432,50 @@ static int md_bitmap_create(struct mddev *mddev) mdname(mddev), orig_id, sb_id); mddev->bitmap_id = sb_id; - if (!mddev_set_bitmap_ops(mddev)) { + if (!mddev_set_bitmap_ops_nosysfs(mddev)) { mddev->bitmap_id = orig_id; return -ENOENT; } err = mddev->bitmap_ops->create(mddev); if (err) { - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; mddev->bitmap_id = orig_id; } return err; } -static void md_bitmap_destroy(struct mddev *mddev) +static int md_bitmap_create(struct mddev *mddev) +{ + int err; + + err = md_bitmap_create_nosysfs(mddev); + if (err) + return err; + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) + md_bitmap_sysfs_add(mddev); + + return 0; +} + +static void md_bitmap_destroy_nosysfs(struct mddev *mddev) { if (!md_bitmap_registered(mddev)) return; mddev->bitmap_ops->destroy(mddev); - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; +} + +static void md_bitmap_destroy(struct mddev *mddev) +{ + if (!mddev_is_dm(mddev) && mddev->bitmap_ops && + mddev->bitmap_ops->group) + md_bitmap_sysfs_del(mddev); + + md_bitmap_destroy_nosysfs(mddev); } int md_run(struct mddev *mddev) From 7035caaa1b6f9344824060d4435d8a194195187e Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sat, 25 Apr 2026 10:46:14 +0800 Subject: [PATCH 0974/1518] md/md-bitmap: split bitmap sysfs groups [ Upstream commit aba3d6d6cb55c6e1116d1215140559dd7ecdf9a9 ] Split the classic bitmap sysfs files into a common bitmap group with the location attribute and a separate internal bitmap group for the remaining files. At the same time, convert bitmap operations from a single sysfs group to a sysfs group array so backends can share part of their sysfs layout while adding backend-specific attributes separately. Switch the bitmap sysfs helpers to use sysfs_update_groups() for the add and update path, and remove groups in reverse order so shared named groups are unmerged before the last group removes the directory. Also make bitmap operation lookup depend only on the currently selected bitmap id matching the installed backend. This prepares the lookup path for a later registered none backend. Reviewed-by: Su Yue Link: https://lore.kernel.org/r/20260425024615.1696892-3-yukuai@fnnas.com Signed-off-by: Yu Kuai Stable-dep-of: f2926a533d03 ("md/md-bitmap: add a none backend for bitmap grow") Signed-off-by: Sasha Levin --- drivers/md/md-bitmap.c | 23 +++++++++++++++++++---- drivers/md/md-bitmap.h | 2 +- drivers/md/md-llbitmap.c | 7 ++++++- drivers/md/md.c | 21 ++++++++++++++------- 4 files changed, 40 insertions(+), 13 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 7bb56d0491a2f..7a96600949139 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2956,8 +2956,12 @@ static struct md_sysfs_entry max_backlog_used = __ATTR(max_backlog_used, S_IRUGO | S_IWUSR, behind_writes_used_show, behind_writes_used_reset); -static struct attribute *md_bitmap_attrs[] = { +static struct attribute *md_bitmap_common_attrs[] = { &bitmap_location.attr, + NULL +}; + +static struct attribute *md_bitmap_internal_attrs[] = { &bitmap_space.attr, &bitmap_timeout.attr, &bitmap_backlog.attr, @@ -2968,9 +2972,20 @@ static struct attribute *md_bitmap_attrs[] = { NULL }; -static struct attribute_group md_bitmap_group = { +static struct attribute_group md_bitmap_common_group = { + .name = "bitmap", + .attrs = md_bitmap_common_attrs, +}; + +static struct attribute_group md_bitmap_internal_group = { .name = "bitmap", - .attrs = md_bitmap_attrs, + .attrs = md_bitmap_internal_attrs, +}; + +static const struct attribute_group *bitmap_groups[] = { + &md_bitmap_common_group, + &md_bitmap_internal_group, + NULL, }; static struct bitmap_operations bitmap_ops = { @@ -3014,7 +3029,7 @@ static struct bitmap_operations bitmap_ops = { .set_pages = bitmap_set_pages, .free = md_bitmap_free, - .group = &md_bitmap_group, + .groups = bitmap_groups, }; int md_bitmap_init(void) diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index b42a28fa83a0f..214f623c7e790 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -125,7 +125,7 @@ struct bitmap_operations { void (*set_pages)(void *data, unsigned long pages); void (*free)(void *data); - struct attribute_group *group; + const struct attribute_group **groups; }; /* the bitmap API */ diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index 0526e742062ac..50eeddf7f539b 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -1562,6 +1562,11 @@ static struct attribute_group md_llbitmap_group = { .attrs = md_llbitmap_attrs, }; +static const struct attribute_group *md_llbitmap_groups[] = { + &md_llbitmap_group, + NULL, +}; + static struct bitmap_operations llbitmap_ops = { .head = { .type = MD_BITMAP, @@ -1598,7 +1603,7 @@ static struct bitmap_operations llbitmap_ops = { .dirty_bits = llbitmap_dirty_bits, .write_all = llbitmap_write_all, - .group = &md_llbitmap_group, + .groups = md_llbitmap_groups, }; int md_llbitmap_init(void) diff --git a/drivers/md/md.c b/drivers/md/md.c index 3061370e959b3..213221abc44c3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -688,7 +688,7 @@ static void no_op(struct percpu_ref *r) {} static void md_bitmap_sysfs_add(struct mddev *mddev) { - if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) + if (sysfs_update_groups(&mddev->kobj, mddev->bitmap_ops->groups)) pr_warn("md: cannot register extra bitmap attributes for %s\n", mdname(mddev)); else @@ -701,16 +701,23 @@ static void md_bitmap_sysfs_add(struct mddev *mddev) static void md_bitmap_sysfs_del(struct mddev *mddev) { - sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group); + int nr_groups = 0; + + for (nr_groups = 0; mddev->bitmap_ops->groups[nr_groups]; nr_groups++) + ; + + while (--nr_groups >= 1) + sysfs_unmerge_group(&mddev->kobj, + mddev->bitmap_ops->groups[nr_groups]); + sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->groups[0]); } static bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) { - struct bitmap_operations *old = mddev->bitmap_ops; struct md_submodule_head *head; - if (mddev->bitmap_id == ID_BITMAP_NONE || - (old && old->head.id == mddev->bitmap_id)) + if (mddev->bitmap_ops && + mddev->bitmap_ops->head.id == mddev->bitmap_id) return true; xa_lock(&md_submodule); @@ -6454,7 +6461,7 @@ static int md_bitmap_create(struct mddev *mddev) if (err) return err; - if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) md_bitmap_sysfs_add(mddev); return 0; @@ -6472,7 +6479,7 @@ static void md_bitmap_destroy_nosysfs(struct mddev *mddev) static void md_bitmap_destroy(struct mddev *mddev) { if (!mddev_is_dm(mddev) && mddev->bitmap_ops && - mddev->bitmap_ops->group) + mddev->bitmap_ops->groups) md_bitmap_sysfs_del(mddev); md_bitmap_destroy_nosysfs(mddev); From 0f5bca930f8d57725b3856eea80327b182869a3b Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sat, 25 Apr 2026 10:46:15 +0800 Subject: [PATCH 0975/1518] md/md-bitmap: add a none backend for bitmap grow [ Upstream commit f2926a533d03fe70d753b512b713e06a2aa174af ] Add a real none bitmap backend that exposes the common bitmap sysfs group and use it to keep bitmap/location available when an array has no bitmap. Then switch the bitmap location sysfs path to move only between none and the classic bitmap backend, using the no-sysfs bitmap helpers while merging or unmerging the internal bitmap sysfs group. This restores mdadm --grow bitmap addition through bitmap/location. Fixes: fb8cc3b0d9db ("md/md-bitmap: delay registration of bitmap_ops until creating bitmap") Reviewed-by: Su Yue Link: https://lore.kernel.org/r/20260425024615.1696892-4-yukuai@fnnas.com Signed-off-by: Yu Kuai Signed-off-by: Sasha Levin --- drivers/md/md-bitmap.c | 108 ++++++++++++++++++++++++++++++++++++++--- drivers/md/md.c | 42 +++++++++++++--- drivers/md/md.h | 3 ++ 3 files changed, 137 insertions(+), 16 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 7a96600949139..35943f5f68347 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -216,6 +216,7 @@ struct bitmap { }; static struct workqueue_struct *md_bitmap_wq; +static struct attribute_group md_bitmap_internal_group; static int __bitmap_resize(struct bitmap *bitmap, sector_t blocks, int chunksize, bool init); @@ -2581,6 +2582,30 @@ static int bitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize) return __bitmap_resize(bitmap, blocks, chunksize, false); } +static bool bitmap_none_enabled(void *data, bool flush) +{ + return false; +} + +static int bitmap_none_create(struct mddev *mddev) +{ + return 0; +} + +static int bitmap_none_load(struct mddev *mddev) +{ + return 0; +} + +static void bitmap_none_destroy(struct mddev *mddev) +{ +} + +static int bitmap_none_get_stats(void *data, struct md_bitmap_stats *stats) +{ + return -ENOENT; +} + static ssize_t location_show(struct mddev *mddev, char *page) { @@ -2619,7 +2644,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len) goto out; } - bitmap_destroy(mddev); + sysfs_unmerge_group(&mddev->kobj, &md_bitmap_internal_group); + md_bitmap_destroy_nosysfs(mddev); + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + goto none_err; mddev->bitmap_info.offset = 0; if (mddev->bitmap_info.file) { struct file *f = mddev->bitmap_info.file; @@ -2655,16 +2684,25 @@ location_store(struct mddev *mddev, const char *buf, size_t len) } mddev->bitmap_info.offset = offset; - rv = bitmap_create(mddev); + md_bitmap_destroy_nosysfs(mddev); + mddev->bitmap_id = ID_BITMAP; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + goto bitmap_err; + + rv = md_bitmap_create_nosysfs(mddev); if (rv) - goto out; + goto create_err; - rv = bitmap_load(mddev); + rv = mddev->bitmap_ops->load(mddev); if (rv) { mddev->bitmap_info.offset = 0; - bitmap_destroy(mddev); - goto out; + goto load_err; } + + rv = sysfs_merge_group(&mddev->kobj, + &md_bitmap_internal_group); + if (rv) + goto merge_err; } } if (!mddev->external) { @@ -2680,6 +2718,22 @@ location_store(struct mddev *mddev, const char *buf, size_t len) if (rv) return rv; return len; + +merge_err: + mddev->bitmap_info.offset = 0; +load_err: + md_bitmap_destroy_nosysfs(mddev); +create_err: + mddev->bitmap_info.offset = 0; + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + rv = -ENOENT; + goto out; +bitmap_err: + rv = -ENOENT; +none_err: + mddev->bitmap_info.offset = 0; + goto out; } static struct md_sysfs_entry bitmap_location = @@ -2988,6 +3042,27 @@ static const struct attribute_group *bitmap_groups[] = { NULL, }; +static const struct attribute_group *bitmap_none_groups[] = { + &md_bitmap_common_group, + NULL, +}; + +static struct bitmap_operations bitmap_none_ops = { + .head = { + .type = MD_BITMAP, + .id = ID_BITMAP_NONE, + .name = "none", + }, + + .enabled = bitmap_none_enabled, + .create = bitmap_none_create, + .load = bitmap_none_load, + .destroy = bitmap_none_destroy, + .get_stats = bitmap_none_get_stats, + + .groups = bitmap_none_groups, +}; + static struct bitmap_operations bitmap_ops = { .head = { .type = MD_BITMAP, @@ -3034,16 +3109,33 @@ static struct bitmap_operations bitmap_ops = { int md_bitmap_init(void) { + int err; + md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!md_bitmap_wq) return -ENOMEM; - return register_md_submodule(&bitmap_ops.head); + err = register_md_submodule(&bitmap_none_ops.head); + if (err) + goto err_wq; + + err = register_md_submodule(&bitmap_ops.head); + if (err) + goto err_none; + + return 0; + +err_none: + unregister_md_submodule(&bitmap_none_ops.head); +err_wq: + destroy_workqueue(md_bitmap_wq); + return err; } void md_bitmap_exit(void) { - destroy_workqueue(md_bitmap_wq); unregister_md_submodule(&bitmap_ops.head); + unregister_md_submodule(&bitmap_none_ops.head); + destroy_workqueue(md_bitmap_wq); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 213221abc44c3..b7d47c018a12f 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -712,7 +712,7 @@ static void md_bitmap_sysfs_del(struct mddev *mddev) sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->groups[0]); } -static bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) +bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) { struct md_submodule_head *head; @@ -4274,7 +4274,7 @@ bitmap_type_show(struct mddev *mddev, char *page) xa_lock(&md_submodule); xa_for_each(&md_submodule, i, head) { - if (head->type != MD_BITMAP) + if (head->type != MD_BITMAP || head->id == ID_BITMAP_NONE) continue; if (mddev->bitmap_id == head->id) @@ -6408,7 +6408,7 @@ static enum md_submodule_id md_bitmap_get_id_from_sb(struct mddev *mddev) return id; } -static int md_bitmap_create_nosysfs(struct mddev *mddev) +int md_bitmap_create_nosysfs(struct mddev *mddev) { enum md_submodule_id orig_id = mddev->bitmap_id; enum md_submodule_id sb_id; @@ -6417,8 +6417,10 @@ static int md_bitmap_create_nosysfs(struct mddev *mddev) if (mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; - if (!mddev_set_bitmap_ops_nosysfs(mddev)) + if (!mddev_set_bitmap_ops_nosysfs(mddev)) { + mddev->bitmap_id = orig_id; return -ENOENT; + } err = mddev->bitmap_ops->create(mddev); if (!err) @@ -6432,8 +6434,10 @@ static int md_bitmap_create_nosysfs(struct mddev *mddev) mddev->bitmap_ops = NULL; sb_id = md_bitmap_get_id_from_sb(mddev); - if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) + if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) { + mddev->bitmap_id = orig_id; return err; + } pr_info("md: %s: bitmap version mismatch, switching from %d to %d\n", mdname(mddev), orig_id, sb_id); @@ -6467,7 +6471,7 @@ static int md_bitmap_create(struct mddev *mddev) return 0; } -static void md_bitmap_destroy_nosysfs(struct mddev *mddev) +void md_bitmap_destroy_nosysfs(struct mddev *mddev) { if (!md_bitmap_registered(mddev)) return; @@ -6485,6 +6489,16 @@ static void md_bitmap_destroy(struct mddev *mddev) md_bitmap_destroy_nosysfs(mddev); } +static void md_bitmap_set_none(struct mddev *mddev) +{ + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + return; + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) + md_bitmap_sysfs_add(mddev); +} + int md_run(struct mddev *mddev) { int err; @@ -6694,6 +6708,10 @@ int md_run(struct mddev *mddev) if (mddev->sb_flags) md_update_sb(mddev, 0); + if (IS_ENABLED(CONFIG_MD_BITMAP) && !mddev->bitmap_info.file && + !mddev->bitmap_info.offset) + md_bitmap_set_none(mddev); + md_new_event(); return 0; @@ -7638,7 +7656,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd) { int err = 0; - if (!md_bitmap_registered(mddev)) + if (!md_bitmap_registered(mddev) || + mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; if (mddev->pers) { @@ -7703,10 +7722,12 @@ static int set_bitmap_file(struct mddev *mddev, int fd) if (err) { md_bitmap_destroy(mddev); + md_bitmap_set_none(mddev); fd = -1; } } else if (fd < 0) { md_bitmap_destroy(mddev); + md_bitmap_set_none(mddev); } } @@ -8013,12 +8034,16 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; + mddev->bitmap_id = ID_BITMAP; rv = md_bitmap_create(mddev); if (!rv) rv = mddev->bitmap_ops->load(mddev); - if (rv) + if (rv) { md_bitmap_destroy(mddev); + mddev->bitmap_info.offset = 0; + md_bitmap_set_none(mddev); + } } else { struct md_bitmap_stats stats; @@ -8046,6 +8071,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) } md_bitmap_destroy(mddev); mddev->bitmap_info.offset = 0; + md_bitmap_set_none(mddev); } } md_update_sb(mddev, 1); diff --git a/drivers/md/md.h b/drivers/md/md.h index 9d66afb8cc6e6..da312d4692858 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -932,6 +932,9 @@ extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); +bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev); +int md_bitmap_create_nosysfs(struct mddev *mddev); +void md_bitmap_destroy_nosysfs(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); From 1c07b968a5d7bef0c0e2aaee820f8a85251bd1c8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 21 Apr 2026 07:52:44 +0200 Subject: [PATCH 0976/1518] s390/mm: Fix phys_to_folio() usage in do_secure_storage_access() [ Upstream commit b95e0e792822bad8fc9eb33ea3a90005e29e75e9 ] In case of a Secure-Storage-Access exception the effective aka virtual address which caused the exception is contained within the TEID. do_secure_storage_access() incorrectly uses phys_to_folio() instead of virt_to_folio() to translate the virtual address to the corresponding folio. Fix this by using virt_to_folio() instead of phys_to_folio(). Fixes: 084ea4d611a3 ("s390/mm: add (non)secure page access exceptions handlers") Reviewed-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev Signed-off-by: Sasha Levin --- arch/s390/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index d1f165048055b..069f72703a915 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,7 +433,7 @@ void do_secure_storage_access(struct pt_regs *regs) panic("Unexpected PGM 0x3d with TEID bit 61=0"); } if (is_kernel_fault(regs)) { - folio = phys_to_folio(addr); + folio = virt_to_folio((void *)addr); if (unlikely(!folio_try_get(folio))) return; rc = uv_convert_from_secure(folio_to_phys(folio)); From fb128a905f7a648bae6fe517ef8b406b579ebc71 Mon Sep 17 00:00:00 2001 From: Heiko Schocher Date: Sat, 25 Apr 2026 05:13:39 +0200 Subject: [PATCH 0977/1518] net: phy: dp83869: fix setting CLK_O_SEL field. [ Upstream commit 46f74a3f7d57d9cc0110b09cbc8163fa0a01afa2 ] Table 7-121 in datasheet says we have to set register 0xc6 to value 0x10 before CLK_O_SEL can be modified. No more infos about this field found in datasheet. With this fix, setting of CLK_O_SEL field in IO_MUX_CFG register worked through dts property "ti,clk-output-sel" on a DP83869HMRGZR. Signed-off-by: Heiko Schocher Reviewed-by: Simon Horman Fixes: 01db923e8377 ("net: phy: dp83869: Add TI dp83869 phy") Link: https://patch.msgid.link/20260425031339.3318-1-hs@nabladev.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/phy/dp83869.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 1f381d7b13ff3..96a7d255f50fd 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -31,6 +31,7 @@ #define DP83869_RGMIICTL 0x0032 #define DP83869_STRAP_STS1 0x006e #define DP83869_RGMIIDCTL 0x0086 +#define DP83869_ANA_PLL_PROG_PI 0x00c6 #define DP83869_RXFCFG 0x0134 #define DP83869_RXFPMD1 0x0136 #define DP83869_RXFPMD2 0x0137 @@ -826,12 +827,22 @@ static int dp83869_config_init(struct phy_device *phydev) dp83869_config_port_mirroring(phydev); /* Clock output selection if muxing property is set */ - if (dp83869->clk_output_sel != DP83869_CLK_O_SEL_REF_CLK) + if (dp83869->clk_output_sel != DP83869_CLK_O_SEL_REF_CLK) { + /* + * Table 7-121 in datasheet says we have to set register 0xc6 + * to value 0x10 before CLK_O_SEL can be modified. + */ + ret = phy_write_mmd(phydev, DP83869_DEVADDR, + DP83869_ANA_PLL_PROG_PI, 0x10); + if (ret) + return ret; + ret = phy_modify_mmd(phydev, DP83869_DEVADDR, DP83869_IO_MUX_CFG, DP83869_IO_MUX_CFG_CLK_O_SEL_MASK, dp83869->clk_output_sel << DP83869_IO_MUX_CFG_CLK_O_SEL_SHIFT); + } if (phy_interface_is_rgmii(phydev)) { ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIIDCTL, From ac06ce5cac9e711281585d09d00c6efcd9b86396 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:35 -0400 Subject: [PATCH 0978/1518] drm/amdgpu/vcn: set no_user_fence for VCN v2.0 enc/dec rings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8d80b293b41fcb5e9396db93e788b0f4ebcbafb7 ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 1b61de45dfaf ("drm/amdgpu: add initial VCN2.0 support (v2)") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit e2b5499fca55f1a32960a311bbb62e35891eaf73) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index e35fae9cdaf66..0442bfcfd384d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -2113,6 +2113,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs vcn_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v2_0_dec_ring_get_rptr, .get_wptr = vcn_v2_0_dec_ring_get_wptr, @@ -2145,6 +2146,7 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v2_0_enc_ring_get_rptr, .get_wptr = vcn_v2_0_enc_ring_get_wptr, .set_wptr = vcn_v2_0_enc_ring_set_wptr, From 602d4c5872b25ddd4d82fb2025efb9a05b187bb3 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:35 -0400 Subject: [PATCH 0979/1518] drm/amdgpu/vcn: set no_user_fence for VCN v2.5 enc/dec rings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4f317863a3ab212a027d8c8c3cc3af4e3fb95704 ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 28c17d72072b ("drm/amdgpu: add VCN2.5 basic supports") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit efc9dd5590894109bce9a0bfe1fa5592dd6b20b1) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 006a154511971..8b8184fe6764b 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -1778,6 +1778,7 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring) static const struct amdgpu_ring_funcs vcn_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v2_5_dec_ring_get_rptr, .get_wptr = vcn_v2_5_dec_ring_get_wptr, @@ -1879,6 +1880,7 @@ static const struct amdgpu_ring_funcs vcn_v2_5_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v2_5_enc_ring_get_rptr, .get_wptr = vcn_v2_5_enc_ring_get_wptr, .set_wptr = vcn_v2_5_enc_ring_set_wptr, From 2d6525e7b2504f5bbfe9417cddc1e8da858791dd Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:35 -0400 Subject: [PATCH 0980/1518] drm/amdgpu/vcn: set no_user_fence for VCN v3.0 enc/dec rings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f1e5a6660d7cbf006079126d9babbf0ccf538c6b ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: cf14826cdfb5 ("drm/amdgpu: add VCN3.0 support for Sienna_Cichlid") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 663bed3c7b8b9a7624b0d95d300ddae034ad0614) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 8b226edfbea3e..f773f7ddfd13c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1856,6 +1856,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0x3f, .nop = VCN_DEC_SW_CMD_NO_OP, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -2037,6 +2038,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -2139,6 +2141,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v3_0_enc_ring_get_rptr, .get_wptr = vcn_v3_0_enc_ring_get_wptr, .set_wptr = vcn_v3_0_enc_ring_set_wptr, From 1286b6872de0aee1feeeaa6dbac86369806de9a5 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:36 -0400 Subject: [PATCH 0981/1518] drm/amdgpu/vcn: set no_user_fence for VCN v4.0 enc ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 51f694221047c84fa185be98210eb2c354ffb8c6 ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 8da1170a16e4 ("drm/amdgpu: add VCN4 ip block support") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit fd852c048b46f9825e904a4f3f4538fe9d8827d9) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 64bda0e944a7c..21e40eb2078d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1995,6 +1995,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .extra_bytes = sizeof(struct amdgpu_vcn_rb_metadata), .get_rptr = vcn_v4_0_unified_ring_get_rptr, .get_wptr = vcn_v4_0_unified_ring_get_wptr, From 9076a83e5adefd10dc5c967c7b8bde601c4c512a Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:36 -0400 Subject: [PATCH 0982/1518] drm/amdgpu/vcn: set no_user_fence for VCN v4.0.3 enc ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4532b52b34e4e4310386e6fdf6a643368599f522 ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: b889ef4ac988 ("drm/amdgpu/vcn: add vcn support for VCN4_0_3") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit ff1a5a125c5a70c328806b9bc01d7d942cf3f9aa) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index cb7123ec1a5d1..88d1139e931e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -1628,6 +1628,7 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v4_0_3_unified_ring_get_rptr, .get_wptr = vcn_v4_0_3_unified_ring_get_wptr, .set_wptr = vcn_v4_0_3_unified_ring_set_wptr, From 6d9a98c5ed65ba92a09e4ca5a5f6941448145529 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:36 -0400 Subject: [PATCH 0983/1518] drm/amdgpu/vcn: set no_user_fence for VCN v4.0.5 enc ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 589a254bf3e88204c8402b9cbccd5e23a0af990f ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 547aad32edac ("drm/amdgpu: add VCN4 ip block support") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 084d94ac93707bdda07efb5cee786f632de4219b) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 1f6a22983c0dd..1571cc5a148c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -1483,6 +1483,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v4_0_5_unified_ring_get_rptr, .get_wptr = vcn_v4_0_5_unified_ring_get_wptr, .set_wptr = vcn_v4_0_5_unified_ring_set_wptr, From 139a8a52ef4349c62129703b3a3e3a6ae4d634eb Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:36 -0400 Subject: [PATCH 0984/1518] drm/amdgpu/vcn: set no_user_fence for VCN v5.0.0 enc ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8cae0ce77de492d7c31c1532a2e80c0c6e7e58cb ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: b6d1a0632051 ("drm/amdgpu: add VCN_5_0_0 IP block support") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 49b1fbbb5a071197ee71e2d70959b1cb29bdc317) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index 6109124f852e5..d5f49fa33bee4 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -1207,6 +1207,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_0_unified_ring_get_rptr, .get_wptr = vcn_v5_0_0_unified_ring_get_wptr, .set_wptr = vcn_v5_0_0_unified_ring_set_wptr, From 081ef0e46c9cdd26c0db0ef721470393d36b6655 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:45:36 -0400 Subject: [PATCH 0985/1518] drm/amdgpu/vcn: set no_user_fence for VCN v5.0.1 enc ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8f4954722eab88e10c4ea0c0d3b1269c31421d3a ] VCN encoder and decoder rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 346492f30ce3 ("drm/amdgpu: Add VCN_5_0_1 support") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit e16be95a2c3ee712b142cb27d2dca0b461181359) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index 8bd457dea4cff..972d4a7147a12 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -1330,6 +1330,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_1_unified_ring_get_rptr, .get_wptr = vcn_v5_0_1_unified_ring_get_wptr, .set_wptr = vcn_v5_0_1_unified_ring_set_wptr, From b41248d1c18384835f6532e68592ee07605da283 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:10 -0400 Subject: [PATCH 0986/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v2.0 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e5f612dc91650561fe2b5b76dd6d2898ec9ad480 ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 6ac27241106b ("drm/amdgpu: add JPEG v2.0 function supports") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 96179da0c6b059eb31706a0abe8dd6381c533143) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 27c76bd424cfb..1e214b493402c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -802,6 +802,7 @@ static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_0_dec_ring_get_rptr, .get_wptr = jpeg_v2_0_dec_ring_get_wptr, .set_wptr = jpeg_v2_0_dec_ring_set_wptr, From 3a96fee676fc0caf08f03ad915bec6fcd144d551 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:10 -0400 Subject: [PATCH 0987/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v2.5 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 79405e774ede411c6b47ed41c651e40b92de64a2 ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 14f43e8f88c5 ("drm/amdgpu: move JPEG2.5 out from VCN2.5") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 3216a7f4e2642bda5fd14f57586e835ae9202587) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 20983f126b490..13a6e24c624a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -693,6 +693,7 @@ static const struct amd_ip_funcs jpeg_v2_6_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, @@ -724,6 +725,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, From 5ada37d7f736f9feeaa06a25e470a4c74e67a61a Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:10 -0400 Subject: [PATCH 0988/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v3.0 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a2baf12eec41f246689e6a3f8619af1200031576 ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: dfd57dbf44dd ("drm/amdgpu: add JPEG3.0 support for Sienna_Cichlid") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 4d7d774f100efb5089c86a1fb8c5bf47c63fc9ef) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index d1a011c40ba23..af231d093a3ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -594,6 +594,7 @@ static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v3_0_dec_ring_get_rptr, .get_wptr = jpeg_v3_0_dec_ring_get_wptr, .set_wptr = jpeg_v3_0_dec_ring_set_wptr, From 6876d05b899102f4dfdb9ad560132126144c1c72 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:11 -0400 Subject: [PATCH 0989/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v4.0 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e7e90b5839aeb8805ec83bb4da610b8dab8e184d ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: b13111de32a9 ("drm/amdgpu/jpeg: add jpeg support for VCN4_0_0") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 8d0cac9478a3f046279c657d6a2545de49ae675a) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 33db2c1ae6cca..90582066e6a1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -759,6 +759,7 @@ static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_dec_ring_set_wptr, From 8549b3933038e68dc61cb934b9a54223dd244a78 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:11 -0400 Subject: [PATCH 0990/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v4.0.3 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 83e37c0987ca92f9e87789b46dd311dcf5a4a6c8 ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: e684e654eba9 ("drm/amdgpu/jpeg: add jpeg support for VCN4_0_3") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 2f6afc97d259d530f4f86c7743efbc573a8da927) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 47f2192fc7e7e..99e6dabc36ee8 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -1214,6 +1214,7 @@ static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, From f26e3f7186cd6ecc93e6af102744d64c798dea7e Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:11 -0400 Subject: [PATCH 0991/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v4.0.5 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b65b7f3f3c18f797f81a2af7c97e2079900ad6db ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: 8f98a715da8e ("drm/amdgpu/jpeg: add jpeg support for VCN4_0_5") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit f05d0a4f21fc720116d6e238f23308b199891058) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 54fd9c800c40a..a43582b9c876c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -804,6 +804,7 @@ static const struct amd_ip_funcs jpeg_v4_0_5_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_5_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_5_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_5_dec_ring_set_wptr, From a7e63bb93a7fde3c8920984c3deee9acfe461562 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:11 -0400 Subject: [PATCH 0992/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v5.0.0 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ea7c61c5f895e8f9ea0ffffa180498ef9c740152 ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: dfad65c65728 ("drm/amdgpu: Add JPEG5 support") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 0f43893d3cd478fa57836697525b338817c9c23d) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index 46bf15dce2bd0..72a4b2d0676fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -680,6 +680,7 @@ static const struct amd_ip_funcs jpeg_v5_0_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr, From d0f6ae14c0452be4fc3aa5cf81c74e68b3243050 Mon Sep 17 00:00:00 2001 From: Yinjie Yao Date: Mon, 27 Apr 2026 11:46:11 -0400 Subject: [PATCH 0993/1518] drm/amdgpu/jpeg: set no_user_fence for JPEG v5.0.1 ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2f8e3da71a1b469b6e157aa3972f1448b3157840 ] JPEG rings do not support 64-bit user fence writes, reject CS submissions with user fences. Fixes: b8f57b69942b ("drm/amdgpu: Add JPEG5_0_1 support") Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Yinjie Yao Signed-off-by: Alex Deucher (cherry picked from commit 742a98e2e81702df8fe1b1eccee5223220a03dc2) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index ab0bf880d3d8a..1fb2386352ccb 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -875,6 +875,7 @@ static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_1_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_1_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_1_dec_ring_set_wptr, From 39767f944a8c9e696566c37ad5b20131406c4b8d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 27 Apr 2026 14:42:18 -0600 Subject: [PATCH 0994/1518] io_uring/napi: cap busy_poll_to 10 msec [ Upstream commit df8599ee18c0e5fe343ffe0b4c379636b8bb839a ] Currently there's no cap on the maximum amount of time that napi is allowed to poll if no events are found, which can lead to kernel complaints on a task being stuck as there's no conditional rescheduling done within that loop. Just cap it to 10 msec in total, that's already way above any kind of sane value that will reap any benefits, yet low enough that it's nowhere near being able to trigger preemption complaints. Fixes: 8d0c12a80cde ("io-uring: add napi busy poll support") Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/napi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/napi.c b/io_uring/napi.c index 4a10de03e4269..8d68366a4b903 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -276,6 +276,8 @@ static int io_napi_register_napi(struct io_ring_ctx *ctx, /* clean the napi list for new settings */ io_napi_free(ctx); WRITE_ONCE(ctx->napi_track_mode, napi->op_param); + /* cap NAPI at 10 msec of spin time */ + napi->busy_poll_to = min(10000, napi->busy_poll_to); WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll); return 0; From d90df5ce6deb2424de3ad89bcc693ac1b67accc9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 27 Apr 2026 12:06:06 -0700 Subject: [PATCH 0995/1518] net: psp: check for device unregister when creating assoc [ Upstream commit b89769f936a8fa9e66de72ddc1b71a9745a488e6 ] psp_assoc_device_get_locked() obtains a psp_dev reference via psp_dev_get_for_sock() (which uses psp_dev_tryget() under RCU); it then acquires psd->lock and drops the reference. Before the lock is taken, psp_dev_unregister() can run to completion: take psd->lock, clear out state, unlock, drop the registration reference. The expectation is that the lock prevents device unregistration, but much like with netdevs special care has to be taken when "upgrading" a reference to a locked device. Add the missing check if device is still alive. psp_dev_is_registered() exists already but had no callers, which makes me wonder if I either forgot to add this or lost the check during refactoring... Reported-by: Yiming Qian Fixes: 6b46ca260e22 ("net: psp: add socket security association code") Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260427190606.366101-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/psp/psp_nl.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/psp/psp_nl.c b/net/psp/psp_nl.c index 8aaca62744c3c..3f63ffbc5c575 100644 --- a/net/psp/psp_nl.c +++ b/net/psp/psp_nl.c @@ -303,8 +303,13 @@ int psp_assoc_device_get_locked(const struct genl_split_ops *ops, psd = psp_dev_get_for_sock(socket->sk); if (psd) { - err = psp_dev_check_access(psd, genl_info_net(info)); - if (err) { + /* Extra care needed here, psp_dev_get_for_sock() only gives + * us access to struct psp_dev's memory, which is quite weak. + */ + mutex_lock(&psd->lock); + if (!psp_dev_is_registered(psd) || + psp_dev_check_access(psd, genl_info_net(info))) { + mutex_unlock(&psd->lock); psp_dev_put(psd); psd = NULL; } @@ -317,7 +322,6 @@ int psp_assoc_device_get_locked(const struct genl_split_ops *ops, id = info->attrs[PSP_A_ASSOC_DEV_ID]; if (psd) { - mutex_lock(&psd->lock); if (id && psd->id != nla_get_u32(id)) { mutex_unlock(&psd->lock); NL_SET_ERR_MSG_ATTR(info->extack, id, From aa1a08a4632af5d1117779e7ff0e32e3c69f29bd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 27 Apr 2026 12:58:56 -0700 Subject: [PATCH 0996/1518] net: psp: require admin permission for dev-set and key-rotate [ Upstream commit b718342a7fbaa2dff5fefc31988c07af8c6cbc21 ] The dev-set and key-rotate netlink operations modify shared device state (PSP version configuration and cryptographic key material, respectively) but do not require CAP_NET_ADMIN. The only access control is psp_dev_check_access() which merely verifies netns membership. Fixes: 00c94ca2b99e ("psp: base PSP device support") Reviewed-by: Daniel Zahka Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260427195856.401223-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- Documentation/netlink/specs/psp.yaml | 2 ++ net/psp/psp-nl-gen.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/Documentation/netlink/specs/psp.yaml b/Documentation/netlink/specs/psp.yaml index 944429e5c9a84..d41ea6155e52e 100644 --- a/Documentation/netlink/specs/psp.yaml +++ b/Documentation/netlink/specs/psp.yaml @@ -111,6 +111,7 @@ operations: name: dev-set doc: Set the configuration of a PSP device. attribute-set: dev + flags: [admin-perm] do: request: attributes: @@ -130,6 +131,7 @@ operations: name: key-rotate doc: Rotate the device key. attribute-set: dev + flags: [admin-perm] do: request: attributes: diff --git a/net/psp/psp-nl-gen.c b/net/psp/psp-nl-gen.c index 9fdd6f831803e..85cf90999c9f1 100644 --- a/net/psp/psp-nl-gen.c +++ b/net/psp/psp-nl-gen.c @@ -70,7 +70,7 @@ static const struct genl_split_ops psp_nl_ops[] = { .post_doit = psp_device_unlock, .policy = psp_dev_set_nl_policy, .maxattr = PSP_A_DEV_PSP_VERSIONS_ENA, - .flags = GENL_CMD_CAP_DO, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { .cmd = PSP_CMD_KEY_ROTATE, @@ -79,7 +79,7 @@ static const struct genl_split_ops psp_nl_ops[] = { .post_doit = psp_device_unlock, .policy = psp_key_rotate_nl_policy, .maxattr = PSP_A_DEV_ID, - .flags = GENL_CMD_CAP_DO, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { .cmd = PSP_CMD_RX_ASSOC, From 841133395b4214f40119ba6da35516e25999ea5d Mon Sep 17 00:00:00 2001 From: "Christian A. Ehrhardt" Date: Tue, 28 Apr 2026 21:22:49 +0200 Subject: [PATCH 0997/1518] ASoC: codecs: ab8500: Fix casting of private data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a201aef1a88b675e9eb8487e27d14e2eef3cef80 ] ab8500_filter_controls[i].private_value is initialized using .private_value = (unsigned long)&(struct filter_control) {.count = xcount, .min = xmin, .max = xmax} thus it's a pointer to a struct filter_control casted to unsigned long. So to get back that pointer .private_data must be cast back, not its address. Fixes: 679d7abdc754 ("ASoC: codecs: Add AB8500 codec-driver") Signed-off-by: Christian A. Ehrhardt Signed-off-by: Uwe Kleine-König (The Capable Hub) Link: https://patch.msgid.link/20260428192255.2294705-2-u.kleine-koenig@baylibre.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/ab8500-codec.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c index 04b5e1d5a6530..32d9cdbc8c310 100644 --- a/sound/soc/codecs/ab8500-codec.c +++ b/sound/soc/codecs/ab8500-codec.c @@ -2496,13 +2496,13 @@ static int ab8500_codec_probe(struct snd_soc_component *component) return status; } fc = (struct filter_control *) - &ab8500_filter_controls[AB8500_FILTER_ANC_FIR].private_value; + ab8500_filter_controls[AB8500_FILTER_ANC_FIR].private_value; drvdata->anc_fir_values = (long *)fc->value; fc = (struct filter_control *) - &ab8500_filter_controls[AB8500_FILTER_ANC_IIR].private_value; + ab8500_filter_controls[AB8500_FILTER_ANC_IIR].private_value; drvdata->anc_iir_values = (long *)fc->value; fc = (struct filter_control *) - &ab8500_filter_controls[AB8500_FILTER_SID_FIR].private_value; + ab8500_filter_controls[AB8500_FILTER_SID_FIR].private_value; drvdata->sid_fir_values = (long *)fc->value; snd_soc_dapm_disable_pin(dapm, "ANC Configure Input"); From 50c450bae38dbf01e8039d3b8fa1b61421f66423 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 26 Apr 2026 10:46:40 -0400 Subject: [PATCH 0998/1518] netfilter: skip recording stale or retransmitted INIT [ Upstream commit 576a5d2bad4814c881a829576b1261b9b8159d2b ] An INIT whose init_tag matches the peer's vtag does not provide new state information. It indicates either: - a stale INIT (after INIT-ACK has already been seen on the same side), or - a retransmitted INIT (after INIT has already been recorded on the same side). In both cases, the INIT must not update ct->proto.sctp.init[] state, since it does not advance the handshake tracking and may otherwise corrupt INIT/INIT-ACK validation logic. Allow INIT processing only when the conntrack entry is newly created (SCTP_CONNTRACK_NONE), or when the init_tag differs from the stored peer vtag. Note it skips the check for the ct with old_state SCTP_CONNTRACK_NONE in nf_conntrack_sctp_packet(), as it is just created in sctp_new() where it set ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag. Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Xin Long Reviewed-by: Marcelo Ricardo Leitner Acked-by: Florian Westphal Link: https://patch.msgid.link/ee56c3e416452b2a40589a2a85245ac2ad5e9f4b.1777214801.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_proto_sctp.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 645d2c43ebf7a..7e10fa65cbdd3 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -466,9 +466,13 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!ih) goto out_unlock; - if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) - ct->proto.sctp.init[!dir] = 0; - ct->proto.sctp.init[dir] = 1; + /* Do not record INIT matching peer vtag (stale or retransmitted INIT). */ + if (old_state == SCTP_CONNTRACK_NONE || + ct->proto.sctp.vtag[!dir] != ih->init_tag) { + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) + ct->proto.sctp.init[!dir] = 0; + ct->proto.sctp.init[dir] = 1; + } pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; From ea9b4f07da5d163f201cd6699e6c6793ce565a8e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 26 Apr 2026 10:46:41 -0400 Subject: [PATCH 0999/1518] sctp: discard stale INIT after handshake completion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8a92cb475ca90d84db769e4d4383e631ace0d6e5 ] After an association reaches ESTABLISHED, the peer’s init_tag is already known from the handshake. Any subsequent INIT with the same init_tag is not a valid restart, but a delayed or duplicate INIT. Drop such INIT chunks in sctp_sf_do_unexpected_init() instead of processing them as new association attempts. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Link: https://patch.msgid.link/5788c76c1ee122a3ed00189e88dcf9df1fba226c.1777214801.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/sm_statefuns.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7b823d7591419..8e89a870780c4 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1556,6 +1556,12 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( /* Tag the variable length parameters. */ chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); + if (asoc->state >= SCTP_STATE_ESTABLISHED) { + /* Discard INIT matching peer vtag after handshake completion (stale INIT). */ + if (ntohl(chunk->subh.init_hdr->init_tag) == asoc->peer.i.init_tag) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, From 74a02921c48fcd35a7881956c9e5c52b86595f5d Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Sun, 26 Apr 2026 09:53:51 -0700 Subject: [PATCH 1000/1518] bareudp: fix NULL pointer dereference in bareudp_fill_metadata_dst() [ Upstream commit aa6c6d9ee064aabfede4402fd1283424e649ca19 ] bareudp_fill_metadata_dst() passes bareudp->sock to udp_tunnel6_dst_lookup() in the IPv6 path without a NULL check. The socket is only created in bareudp_open() and NULLed in bareudp_stop(), so calling this function while the device is down triggers a NULL dereference via sock->sk. BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:udp_tunnel6_dst_lookup (net/ipv6/ip6_udp_tunnel.c:160) Call Trace: bareudp_fill_metadata_dst (drivers/net/bareudp.c:532) do_execute_actions (net/openvswitch/actions.c:901) ovs_execute_actions (net/openvswitch/actions.c:1589) ovs_packet_cmd_execute (net/openvswitch/datapath.c:700) genl_family_rcv_msg_doit (net/netlink/genetlink.c:1114) genl_rcv_msg (net/netlink/genetlink.c:1209) netlink_rcv_skb (net/netlink/af_netlink.c:2550) Add a NULL check returning -ESHUTDOWN, consistent with the xmit paths in the same driver. Fixes: 571912c69f0e ("net: UDP tunnel encapsulation module for tunnelling different protocols like MPLS, IP, NSH etc.") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260426165350.1663137-2-bestswngs@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/bareudp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 0df3208783ad9..da5866ba06999 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -529,6 +529,9 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, struct in6_addr saddr; struct socket *sock = rcu_dereference(bareudp->sock); + if (!sock) + return -ESHUTDOWN; + dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr, &info->key, sport, bareudp->port, info->key.tos, From cd0401593b2d551df2677fd0102bc67daee93d78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Apr 2026 08:36:04 +0000 Subject: [PATCH 1001/1518] net/sched: sch_cake: annotate data-races in cake_dump_stats() (III) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 276a98a434964088fccd4745db5b34d6e831e358 ] cake_dump_stats() runs without qdisc spinlock being held. In this third patch, I add READ_ONCE()/WRITE_ONCE() annotations for the following fields: - packets - tin_dropped - tin_ecn_mark - ack_drops - peak_delay - avge_delay - base_delay Other annotations are added in following patches, to ease code review. Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Eric Dumazet Acked-by: "Toke Høiland-Jørgensen" Link: https://patch.msgid.link/20260427083606.459355-4-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_cake.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 1a2023cd55109..7b97f6b57cb17 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1590,7 +1590,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) sch->qstats.backlog -= len; flow->dropped++; - b->tin_dropped++; + WRITE_ONCE(b->tin_dropped, b->tin_dropped + 1); if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, skb, now, true); @@ -1808,7 +1808,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, numsegs++; slen += segs->len; q->buffer_used += segs->truesize; - b->packets++; + WRITE_ONCE(b->packets, b->packets + 1); } /* stats */ @@ -1832,7 +1832,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, ack = cake_ack_filter(q, flow); if (ack) { - b->ack_drops++; + WRITE_ONCE(b->ack_drops, b->ack_drops + 1); sch->qstats.drops++; ack_pkt_len = qdisc_pkt_len(ack); b->bytes += ack_pkt_len; @@ -1848,7 +1848,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, } /* stats */ - b->packets++; + WRITE_ONCE(b->packets, b->packets + 1); b->bytes += len - ack_pkt_len; b->backlogs[idx] += len - ack_pkt_len; b->tin_backlog += len - ack_pkt_len; @@ -2191,7 +2191,7 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) b->tin_deficit -= len; } flow->dropped++; - b->tin_dropped++; + WRITE_ONCE(b->tin_dropped, b->tin_dropped + 1); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); kfree_skb_reason(skb, reason); @@ -2199,16 +2199,18 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) goto retry; } - b->tin_ecn_mark += !!flow->cvars.ecn_marked; + WRITE_ONCE(b->tin_ecn_mark, b->tin_ecn_mark + !!flow->cvars.ecn_marked); qdisc_bstats_update(sch, skb); /* collect delay stats */ delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); - b->avge_delay = cake_ewma(b->avge_delay, delay, 8); - b->peak_delay = cake_ewma(b->peak_delay, delay, - delay > b->peak_delay ? 2 : 8); - b->base_delay = cake_ewma(b->base_delay, delay, - delay < b->base_delay ? 2 : 8); + WRITE_ONCE(b->avge_delay, cake_ewma(b->avge_delay, delay, 8)); + WRITE_ONCE(b->peak_delay, + cake_ewma(b->peak_delay, delay, + delay > b->peak_delay ? 2 : 8)); + WRITE_ONCE(b->base_delay, + cake_ewma(b->base_delay, delay, + delay < b->base_delay ? 2 : 8)); len = cake_advance_shaper(q, b, skb, now, false); flow->deficit -= len; @@ -2940,17 +2942,17 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) PUT_TSTAT_U32(INTERVAL_US, ktime_to_us(ns_to_ktime(b->cparams.interval))); - PUT_TSTAT_U32(SENT_PACKETS, b->packets); - PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); - PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); - PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); + PUT_TSTAT_U32(SENT_PACKETS, READ_ONCE(b->packets)); + PUT_TSTAT_U32(DROPPED_PACKETS, READ_ONCE(b->tin_dropped)); + PUT_TSTAT_U32(ECN_MARKED_PACKETS, READ_ONCE(b->tin_ecn_mark)); + PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, READ_ONCE(b->ack_drops)); PUT_TSTAT_U32(PEAK_DELAY_US, - ktime_to_us(ns_to_ktime(b->peak_delay))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->peak_delay)))); PUT_TSTAT_U32(AVG_DELAY_US, - ktime_to_us(ns_to_ktime(b->avge_delay))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->avge_delay)))); PUT_TSTAT_U32(BASE_DELAY_US, - ktime_to_us(ns_to_ktime(b->base_delay))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->base_delay)))); PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); PUT_TSTAT_U32(WAY_MISSES, b->way_misses); From b19a6804d4980e780a176de288d205bd29fb7c3b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Apr 2026 08:36:06 +0000 Subject: [PATCH 1002/1518] net/sched: sch_cake: annotate data-races in cake_dump_stats() (V) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a6c95b833dc17e84d16a8ac0f40fd0931616a52d ] cake_dump_stats() runs without qdisc spinlock being held. In this final patch, I add READ_ONCE()/WRITE_ONCE() annotations for cparams.target and cparams.interval. Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Eric Dumazet Acked-by: "Toke Høiland-Jørgensen" Link: https://patch.msgid.link/20260427083606.459355-6-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_cake.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 7b97f6b57cb17..f2ad946a519c2 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2305,10 +2305,11 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, byte_target_ns = (byte_target * rate_ns) >> rate_shft; - b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); - b->cparams.interval = max(rtt_est_ns + - b->cparams.target - target_ns, - b->cparams.target * 2); + WRITE_ONCE(b->cparams.target, + max((byte_target_ns * 3) / 2, target_ns)); + WRITE_ONCE(b->cparams.interval, + max(rtt_est_ns + b->cparams.target - target_ns, + b->cparams.target * 2)); b->cparams.mtu_time = byte_target_ns; b->cparams.p_inc = 1 << 24; /* 1/256 */ b->cparams.p_dec = 1 << 20; /* 1/4096 */ @@ -2938,9 +2939,9 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); PUT_TSTAT_U32(TARGET_US, - ktime_to_us(ns_to_ktime(b->cparams.target))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->cparams.target)))); PUT_TSTAT_U32(INTERVAL_US, - ktime_to_us(ns_to_ktime(b->cparams.interval))); + ktime_to_us(ns_to_ktime(READ_ONCE(b->cparams.interval)))); PUT_TSTAT_U32(SENT_PACKETS, READ_ONCE(b->packets)); PUT_TSTAT_U32(DROPPED_PACKETS, READ_ONCE(b->tin_dropped)); From 47984e9db9caaf76fc88c0080bd6402df58ff7ce Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 27 Apr 2026 07:30:37 -0700 Subject: [PATCH 1003/1518] netconsole: propagate device name truncation in dev_name_store() [ Upstream commit 92ceb7bff62c2606f664c204750eca0b85d44112 ] dev_name_store() calls strscpy(nt->np.dev_name, buf, IFNAMSIZ) without checking the return value. If userspace writes an interface name longer than IFNAMSIZ - 1, strscpy() silently truncates and returns -E2BIG, but the function ignores it and reports a fully successful write back to userspace. If a real interface happens to match the truncated name, netconsole will bind to the wrong device on the next enable, sending kernel logs and panic output to an unintended network segment with no indication to userspace that anything was rewritten. Reject writes whose length cannot fit in nt->np.dev_name up front: if (count >= IFNAMSIZ) return -ENAMETOOLONG; This is not a big deal of a problem, but, it is still the correct approach. Fixes: 0bcc1816188e57 ("[NET] netconsole: Support dynamic reconfiguration using configfs") Signed-off-by: Breno Leitao Link: https://patch.msgid.link/20260427-netconsole_ai_fixes-v2-3-59965f29d9cc@debian.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/netconsole.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 7523f7763d36a..06345487d6aac 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -694,6 +694,13 @@ static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + size_t len = count; + + /* Account for a trailing newline appended by tools like echo */ + if (len && buf[len - 1] == '\n') + len--; + if (len >= IFNAMSIZ) + return -ENAMETOOLONG; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { From f837c7b85143a7c54140ff41ad5c076b73cd9933 Mon Sep 17 00:00:00 2001 From: wangdicheng Date: Tue, 28 Apr 2026 16:04:50 +0800 Subject: [PATCH 1004/1518] ALSA: hda/conexant: Fix missing error check for jack detection [ Upstream commit b0e2333a231107adedd38c6fcfe1adc6162716fc ] In cx_probe(), the return value of snd_hda_jack_detect_enable_callback() is ignored. This function returns a pointer, and if it fails (e.g., due to memory allocation failure), it returns an error pointer which must be checked using IS_ERR(). If the registration fails, the driver continues to probe, but the jack detection callback will not be registered. This can lead to a kernel crash later when the driver attempts to handle jack events or accesses the uninitialized structure. Check the return value using IS_ERR() and propagate the error via PTR_ERR() to the probe caller. Fixes: 7aeb25908648 ("ALSA: hda/conexant: Fix headset auto detect fail in cx8070 and SN6140") Signed-off-by: wangdicheng Link: https://patch.msgid.link/20260428080450.108801-1-wangdich9700@163.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/conexant.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index f71123a475464..263773f8bd6ae 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -1183,6 +1183,7 @@ static void add_cx5051_fake_mutes(struct hda_codec *codec) static int cx_probe(struct hda_codec *codec, const struct hda_device_id *id) { struct conexant_spec *spec; + struct hda_jack_callback *callback; int err; codec_info(codec, "%s: BIOS auto-probing.\n", codec->core.chip_name); @@ -1198,7 +1199,12 @@ static int cx_probe(struct hda_codec *codec, const struct hda_device_id *id) case 0x14f11f86: case 0x14f11f87: spec->is_cx11880_sn6140 = true; - snd_hda_jack_detect_enable_callback(codec, 0x19, cx_update_headset_mic_vref); + callback = snd_hda_jack_detect_enable_callback(codec, 0x19, + cx_update_headset_mic_vref); + if (IS_ERR(callback)) { + err = PTR_ERR(callback); + goto error; + } break; } From 7e6f7ac79abe22d6a665903c0a539e7e0b43e54d Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 28 Apr 2026 14:05:31 +0100 Subject: [PATCH 1005/1518] ALSA: hda: cs35l56: Fix uninitialized value in cs35l56_hda_read_acpi() [ Upstream commit 90df4957a3271adf391b3432cd76a40887cf3273 ] Eliminate the uninitialized 'nval' in cs35l56_hda_read_acpi() if a system-specific quirk overrides processing of the dev-index property. The value is now stored in a new 'num_amps' member of struct cs35l56_hda so that the quirk handler can set the value. The quirk for the Lenovo Yoga Book 9i GenX replaces the values from the dev-index property with hardcoded indexes. So cs35l56_hda_read_acpi() would then skip reading the property. But this left the 'nval' local variable uninitialized when it is later passed to cirrus_scodec_get_speaker_id(). Fixes: 40b1c2f9b299 ("ALSA: hda/cs35l56: Workaround bad dev-index on Lenovo Yoga Book 9i GenX") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-sound/aenFesLAStjrVNy8@stanley.mountain/T/#u Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260428130531.169600-1-rf@opensource.cirrus.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/side-codecs/cs35l56_hda.c | 12 +++++++----- sound/hda/codecs/side-codecs/cs35l56_hda.h | 1 + 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c index 82b7352e7ea97..79c15e21d4bcb 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c @@ -884,6 +884,7 @@ static int cs35l56_hda_system_resume(struct device *dev) static int cs35l56_hda_fixup_yoga9(struct cs35l56_hda *cs35l56, int *bus_addr) { /* The cirrus,dev-index property has the wrong values */ + cs35l56->num_amps = 2; switch (*bus_addr) { case 0x30: cs35l56->index = 1; @@ -933,7 +934,6 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) char hid_string[8]; struct acpi_device *adev; const char *property, *sub; - size_t nval; int i, ret; /* @@ -969,13 +969,14 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) ret = -EINVAL; goto err; } - nval = ret; + cs35l56->num_amps = ret; - ret = device_property_read_u32_array(cs35l56->base.dev, property, values, nval); + ret = device_property_read_u32_array(cs35l56->base.dev, property, values, + cs35l56->num_amps); if (ret) goto err; - for (i = 0; i < nval; i++) { + for (i = 0; i < cs35l56->num_amps; i++) { if (values[i] == id) { cs35l56->index = i; break; @@ -998,7 +999,8 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) "Read ACPI _SUB failed(%ld): fallback to generic firmware\n", PTR_ERR(sub)); } else { - ret = cirrus_scodec_get_speaker_id(cs35l56->base.dev, cs35l56->index, nval, -1); + ret = cirrus_scodec_get_speaker_id(cs35l56->base.dev, cs35l56->index, + cs35l56->num_amps, -1); if (ret == -ENOENT) { cs35l56->system_name = sub; } else if (ret >= 0) { diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.h b/sound/hda/codecs/side-codecs/cs35l56_hda.h index 38d94fb213a50..0074e8f5f18cb 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.h +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.h @@ -25,6 +25,7 @@ struct cs35l56_hda { struct work_struct dsp_work; int index; + int num_amps; const char *system_name; const char *amp_name; From 24c22c644ea535f669bb4cdf1006a6df21874168 Mon Sep 17 00:00:00 2001 From: Shenghao Ding Date: Wed, 29 Apr 2026 13:42:06 +0800 Subject: [PATCH 1006/1518] ALSA: hda/tas2781: Fix incorrect bit update for non-book-zero or book 0 pages >1 [ Upstream commit e052a1f7199260eda4d6ca08a59c3b98738f8491 ] In TAS2781 SPI mode, when accessing non-book-zero or page numbers greater than 1 in book 0, an additional byte must be read. The first byte in such cases is a dummy byte and should be ignored. Fixes: 9fa6a693ad8d ("ALSA: hda/tas2781: Remove tas2781_spi_fwlib.c and leverage SND_SOC_TAS2781_FMWLIB") Signed-off-by: Shenghao Ding Link: https://patch.msgid.link/20260429054206.429-1-shenghao-ding@ti.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/side-codecs/tas2781_hda_spi.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c index 488e35dac9524..a64f2c899d50c 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c @@ -135,10 +135,18 @@ static int tasdevice_spi_dev_update_bits(struct tasdevice_priv *tas_priv, int ret, val; /* - * In our TAS2781 SPI mode, read/write was masked in last bit of - * address, it cause regmap_update_bits() not work as expected. + * In TAS2781 SPI mode, when accessing non-book-zero or page numbers + * greater than 1 in book 0, an additional byte must be read. The + * first byte in such cases is a dummy byte and should be ignored. */ - ret = tasdevice_dev_read(tas_priv, chn, reg, &val); + if ((TASDEVICE_BOOK_ID(reg) > 0) || (TASDEVICE_PAGE_ID(reg) > 1)) { + unsigned char buf[2]; + + ret = tasdevice_dev_bulk_read(tas_priv, chn, reg, buf, 2); + val = buf[1]; + } else { + ret = tasdevice_dev_read(tas_priv, chn, reg, &val); + } if (ret < 0) { dev_err(tas_priv->dev, "%s, E=%d\n", __func__, ret); return ret; From 69a7cfc66405aeaa2483147653d031b3592ffc9c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 28 Apr 2026 12:34:25 +0200 Subject: [PATCH 1007/1518] futex: Prevent lockup in requeue-PI during signal/ timeout wakeup [ Upstream commit bc7304f3ae20972d11db6e0b1b541c63feda5f05 ] During wait-requeue-pi (task A) and requeue-PI (task B) the following race can happen: Task A Task B futex_wait_requeue_pi() futex_setup_timer() futex_do_wait() futex_requeue() CLASS(hb, hb1)(&key1); CLASS(hb, hb2)(&key2); *timeout* futex_requeue_pi_wakeup_sync() requeue_state = Q_REQUEUE_PI_IGNORE *blocks on hb->lock* futex_proxy_trylock_atomic() futex_requeue_pi_prepare() Q_REQUEUE_PI_IGNORE => -EAGAIN double_unlock_hb(hb1, hb2) *retry* Task B acquires both hb locks and attempts to acquire the PI-lock of the top most waiter (task B). Task A is leaving early due to a signal/ timeout and started removing itself from the queue. It updates its requeue_state but can not remove it from the list because this requires the hb lock which is owned by task B. Usually task A is able to swoop the lock after task B unlocked it. However if task B is of higher priority then task A may not be able to wake up in time and acquire the lock before task B gets it again. Especially on a UP system where A is never scheduled. As a result task A blocks on the lock and task B busy loops, trying to make progress but live locks the system instead. Tragic. This can be fixed by removing the top most waiter from the list in this case. This allows task B to grab the next top waiter (if any) in the next iteration and make progress. Remove the top most waiter if futex_requeue_pi_prepare() fails. Let the waiter conditionally remove itself from the list in handle_early_requeue_pi_wakeup(). Fixes: 07d91ef510fb1 ("futex: Prevent requeue_pi() lock nesting issue on RT") Reported-by: Moritz Klammler Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260428103425.dywXyPd3@linutronix.de Closes: https://lore.kernel.org/all/VE1PR06MB6894BE61C173D802365BE19DFF4CA@VE1PR06MB6894.eurprd06.prod.outlook.com Signed-off-by: Sasha Levin --- kernel/futex/requeue.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c index d818b4d47f1ba..b597cb3d17fc1 100644 --- a/kernel/futex/requeue.c +++ b/kernel/futex/requeue.c @@ -319,8 +319,11 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, return -EINVAL; /* Ensure that this does not race against an early wakeup */ - if (!futex_requeue_pi_prepare(top_waiter, NULL)) + if (!futex_requeue_pi_prepare(top_waiter, NULL)) { + plist_del(&top_waiter->list, &hb1->chain); + futex_hb_waiters_dec(hb1); return -EAGAIN; + } /* * Try to take the lock for top_waiter and set the FUTEX_WAITERS bit @@ -722,10 +725,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, /* * We were woken prior to requeue by a timeout or a signal. - * Unqueue the futex_q and determine which it was. + * Conditionally unqueue the futex_q and determine which it was. */ - plist_del(&q->list, &hb->chain); - futex_hb_waiters_dec(hb); + if (!plist_node_empty(&q->list)) { + plist_del(&q->list, &hb->chain); + futex_hb_waiters_dec(hb); + } /* Handle spurious wakeups gracefully */ ret = -EWOULDBLOCK; From 9b84d67ce8c93770f5d42005ba82500ffa34dc39 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Tue, 28 Apr 2026 13:40:41 +0200 Subject: [PATCH 1008/1518] drm/amd/display: Allow DCE link encoder without AUX registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ac27e3f99035f132f23bc0409d0e57f11f054c70 ] Allow constructing the DCE link encoder without DDC, which means the AUX registers array will be NULL. This is necessary to support embedded connectors without DDC. Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)") Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/5192 Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit 87f30b101af62590faf6020d106da07efdda199b) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index 0c50fe266c8a1..4103213a572ad 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -989,7 +989,9 @@ void dce110_link_encoder_hw_init( ASSERT(result == BP_RESULT_OK); } - aux_initialize(enc110); + + if (enc110->aux_regs) + aux_initialize(enc110); /* reinitialize HPD. * hpd_initialize() will pass DIG_FE id to HW context. From e0f874f209d4ce5825bc468dbc8f924676af0aac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Tue, 28 Apr 2026 13:40:42 +0200 Subject: [PATCH 1009/1518] drm/amd/display: Allow constructing DCE6 link encoder without DDC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 880498a1943f865529819f778df3b9945ca57262 ] When the DDC channel ID is set to CHANNEL_ID_UNKNOWN, pass NULL to the AUX regs array. This is necessary to support embedded connectors without DDC. Fixes: 7c15fd86aaec ("drm/amd/display: dc/dce: add initial DCE6 support (v10)") Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/5192 Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit 38a70e50b22a188ff601740d64dd75f46213121f) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c index f2e47f1ff4b33..e94af8522083c 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c @@ -728,7 +728,8 @@ static struct link_encoder *dce60_link_encoder_create( enc_init_data, &link_enc_feature, &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->channel == CHANNEL_ID_UNKNOWN ? + NULL : &link_enc_aux_regs[enc_init_data->channel - 1], enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; From 07822f1d9bdbd4a1809d0baac6856e36da1c1015 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Tue, 28 Apr 2026 13:40:43 +0200 Subject: [PATCH 1010/1518] drm/amd/display: Allow constructing DCE8 link encoder without DDC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 60af4605ef35ecb7ad649a8534b83a2f7c69576d ] When the DDC channel ID is set to CHANNEL_ID_UNKNOWN, pass NULL to the AUX regs array. This is necessary to support embedded connectors without DDC. Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)") Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/5192 Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit 155baf3038c1af50b602723022ed869b38e86a99) Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c index 8822d5818d29e..b645c0c8ec3c5 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c @@ -734,7 +734,8 @@ static struct link_encoder *dce80_link_encoder_create( enc_init_data, &link_enc_feature, &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->channel == CHANNEL_ID_UNKNOWN ? + NULL : &link_enc_aux_regs[enc_init_data->channel - 1], enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; From 8b85ffe5205262682b4dc9e2e35beaeb7365aceb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Tue, 28 Apr 2026 13:40:44 +0200 Subject: [PATCH 1011/1518] drm/amd/display: Read EDID from VBIOS embedded panel info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9ea16f64189bf7b6ba50fc7f0325b3c1f836d105 ] Some board manufacturers hardcode the EDID for the embedded panel in the VBIOS. This EDID should be used when the panel doesn't have a DDC. For reference, see the legacy non-DC display code: amdgpu_atombios_encoder_get_lcd_info() This is necessary to support embedded connectors without DDC. Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)") Link: https://gitlab.freedesktop.org/drm/amd/-/work_items/5192 Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit eb105e63b474c11ef6a84a1c6b18100d851ff364) Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/dc/bios/bios_parser.c | 62 +++++++++++++++++++ .../display/include/grph_object_ctrl_defs.h | 4 ++ 2 files changed, 66 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index 154fd2c18e884..c800c603bf708 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -1215,6 +1215,60 @@ static enum bp_result bios_parser_get_embedded_panel_info( return BP_RESULT_FAILURE; } +static enum bp_result get_embedded_panel_extra_info( + struct bios_parser *bp, + struct embedded_panel_info *info, + const uint32_t table_offset) +{ + uint8_t *record = bios_get_image(&bp->base, table_offset, 1); + ATOM_PANEL_RESOLUTION_PATCH_RECORD *panel_res_record; + ATOM_FAKE_EDID_PATCH_RECORD *fake_edid_record; + + while (*record != ATOM_RECORD_END_TYPE) { + switch (*record) { + case LCD_MODE_PATCH_RECORD_MODE_TYPE: + record += sizeof(ATOM_PATCH_RECORD_MODE); + break; + case LCD_RTS_RECORD_TYPE: + record += sizeof(ATOM_LCD_RTS_RECORD); + break; + case LCD_CAP_RECORD_TYPE: + record += sizeof(ATOM_LCD_MODE_CONTROL_CAP); + break; + case LCD_FAKE_EDID_PATCH_RECORD_TYPE: + fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; + if (fake_edid_record->ucFakeEDIDLength) { + if (fake_edid_record->ucFakeEDIDLength == 128) + info->fake_edid_size = + fake_edid_record->ucFakeEDIDLength; + else + info->fake_edid_size = + fake_edid_record->ucFakeEDIDLength * 128; + + info->fake_edid = fake_edid_record->ucFakeEDIDString; + + record += struct_size(fake_edid_record, + ucFakeEDIDString, + info->fake_edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; + } + break; + case LCD_PANEL_RESOLUTION_RECORD_TYPE: + panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; + info->panel_width_mm = panel_res_record->usHSize; + info->panel_height_mm = panel_res_record->usVSize; + record += sizeof(ATOM_PANEL_RESOLUTION_PATCH_RECORD); + break; + default: + return BP_RESULT_BADBIOSTABLE; + } + } + + return BP_RESULT_OK; +} + static enum bp_result get_embedded_panel_info_v1_2( struct bios_parser *bp, struct embedded_panel_info *info) @@ -1331,6 +1385,10 @@ static enum bp_result get_embedded_panel_info_v1_2( if (ATOM_PANEL_MISC_API_ENABLED & lvds->ucLVDS_Misc) info->lcd_timing.misc_info.API_ENABLED = true; + if (lvds->usExtInfoTableOffset) + return get_embedded_panel_extra_info(bp, info, + le16_to_cpu(lvds->usExtInfoTableOffset) + DATA_TABLES(LCD_Info)); + return BP_RESULT_OK; } @@ -1456,6 +1514,10 @@ static enum bp_result get_embedded_panel_info_v1_3( (uint32_t) (ATOM_PANEL_MISC_V13_GREY_LEVEL & lvds->ucLCD_Misc) >> ATOM_PANEL_MISC_V13_GREY_LEVEL_SHIFT; + if (lvds->usExtInfoTableOffset) + return get_embedded_panel_extra_info(bp, info, + le16_to_cpu(lvds->usExtInfoTableOffset) + DATA_TABLES(LCD_Info)); + return BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index cc467031651da..05eda9b28b328 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -153,6 +153,10 @@ struct embedded_panel_info { uint32_t drr_enabled; uint32_t min_drr_refresh_rate; bool realtek_eDPToLVDS; + uint16_t panel_width_mm; + uint16_t panel_height_mm; + uint16_t fake_edid_size; + const uint8_t *fake_edid; }; struct dc_firmware_info { From 2d8656c27ff60442e50d97205260aac3dc89acaa Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 8 Apr 2026 15:27:44 -0700 Subject: [PATCH 1012/1518] drm/xe/debugfs: Correct printing of register whitelist ranges [ Upstream commit 03f2499c51dffce611b065b2894406beb9f2ebe0 ] The register-save-restore debugfs prints whitelist entries as offset ranges. E.g., REG[0x39319c-0x39319f]: allow read access for a single dword-sized register. However the GENMASK value used to set the lower bits to '1' for the upper bound of the whitelist range incorrectly included one more bit than it should have, causing the whitelist ranges to sometimes appear twice as large as they really were. For example, REG[0x6210-0x6217]: allow rw access was also intended to be a single dword-sized register whitelist (with a range 0x6210-0x6213) but was printed incorrectly as a qword-sized range because one too many bits was flipped on. Similar 'off by one' logic was applied when printing 4-dword register ranges and 64-dword register ranges as well. Correct the GENMASK logic to print these ranges in debugfs correctly. No impact outside of correcting the misleading debugfs output. Fixes: d855d2246ea6 ("drm/xe: Print whitelist while applying") Reviewed-by: Stuart Summers Link: https://patch.msgid.link/20260408-regsr_wl_range-v1-1-e9a28c8b4264@intel.com Signed-off-by: Matt Roper (cherry picked from commit 1a2a722ff96749734a5585dfe7f0bea7719caa8b) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_reg_whitelist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_reg_whitelist.c b/drivers/gpu/drm/xe/xe_reg_whitelist.c index 23f6c81d99946..21763dc51150b 100644 --- a/drivers/gpu/drm/xe/xe_reg_whitelist.c +++ b/drivers/gpu/drm/xe/xe_reg_whitelist.c @@ -174,7 +174,7 @@ void xe_reg_whitelist_print_entry(struct drm_printer *p, unsigned int indent, } range_start = reg & REG_GENMASK(25, range_bit); - range_end = range_start | REG_GENMASK(range_bit, 0); + range_end = range_start | REG_GENMASK(range_bit - 1, 0); switch (val & RING_FORCE_TO_NONPRIV_ACCESS_MASK) { case RING_FORCE_TO_NONPRIV_ACCESS_RW: From 753b149d5a433eb19e0c1b0eb4526a6e26120d1f Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Wed, 8 Apr 2026 02:06:47 +0000 Subject: [PATCH 1013/1518] drm/xe: Fix error cleanup in xe_exec_queue_create_ioctl() [ Upstream commit f3cc22d4df3ed58439ea7e21daa54c3608e03b78 ] Two error handling issues exist in xe_exec_queue_create_ioctl(): 1. When xe_hw_engine_group_add_exec_queue() fails, the error path jumps to put_exec_queue which skips xe_exec_queue_kill(). If the VM is in preempt fence mode, xe_vm_add_compute_exec_queue() has already added the queue to the VM's compute exec queue list. Skipping the kill leaves the queue on that list, leading to a dangling pointer after the queue is freed. 2. When xa_alloc() fails after xe_hw_engine_group_add_exec_queue() has succeeded, the error path does not call xe_hw_engine_group_del_exec_queue() to remove the queue from the hw engine group list. The queue is then freed while still linked into the hw engine group, causing a use-after-free. Fix both by: - Changing the xe_hw_engine_group_add_exec_queue() failure path to jump to kill_exec_queue so that xe_exec_queue_kill() properly removes the queue from the VM's compute list. - Adding a del_hw_engine_group label before kill_exec_queue for the xa_alloc() failure path, which removes the queue from the hw engine group before proceeding with the rest of the cleanup. Fixes: 7970cb36966c ("'drm/xe/hw_engine_group: Register hw engine group's exec queues") Cc: Francois Dugast Cc: Matthew Brost Cc: Niranjana Vishwanathapura Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Matthew Brost Link: https://patch.msgid.link/20260408020647.3397933-1-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 37c831f401746a45d510b312b0ed7a77b1e06ec8) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_exec_queue.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 231d1fbe5eefa..0df11f054cfba 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -789,7 +789,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (q->vm && q->hwe->hw_engine_group) { err = xe_hw_engine_group_add_exec_queue(q->hwe->hw_engine_group, q); if (err) - goto put_exec_queue; + goto kill_exec_queue; } } @@ -798,12 +798,15 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, /* user id alloc must always be last in ioctl to prevent UAF */ err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL); if (err) - goto kill_exec_queue; + goto del_hw_engine_group; args->exec_queue_id = id; return 0; +del_hw_engine_group: + if (q->vm && q->hwe && q->hwe->hw_engine_group) + xe_hw_engine_group_del_exec_queue(q->hwe->hw_engine_group, q); kill_exec_queue: xe_exec_queue_kill(q); put_exec_queue: From bebce43f34b5feb8a760aa832eba81e0f8a38871 Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Wed, 15 Apr 2026 22:54:28 +0000 Subject: [PATCH 1014/1518] drm/xe/eustall: Fix drm_dev_put called before stream disable in close [ Upstream commit dc2d9842c67d883d3200ae33b9c3859dd9492408 ] In xe_eu_stall_stream_close(), drm_dev_put() is called before the stream is disabled and its resources are freed. If this drops the last reference, the device structures could be freed while the subsequent cleanup code still accesses them, leading to a use-after-free. Fix this by moving drm_dev_put() after all device accesses are complete. This matches the ordering in xe_oa_release(). Fixes: 9a0b11d4cf3b ("drm/xe/eustall: Add support to init, enable and disable EU stall sampling") Cc: Harish Chegondi Assisted-by: Claude:claude-opus-4.6 Signed-off-by: Shuicheng Lin Reviewed-by: Harish Chegondi Link: https://patch.msgid.link/20260415225428.3399934-1-shuicheng.lin@intel.com Signed-off-by: Matt Roper (cherry picked from commit 35aff528f7297e949e5e19c9cd7fd748cf1cf21c) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_eu_stall.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index 33a3764e3e71b..d7392250e0b3a 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -845,14 +845,14 @@ static int xe_eu_stall_stream_close(struct inode *inode, struct file *file) struct xe_eu_stall_data_stream *stream = file->private_data; struct xe_gt *gt = stream->gt; - drm_dev_put(>->tile->xe->drm); - mutex_lock(>->eu_stall->stream_lock); xe_eu_stall_disable_locked(stream); xe_eu_stall_data_buf_destroy(stream); xe_eu_stall_stream_free(stream); mutex_unlock(>->eu_stall->stream_lock); + drm_dev_put(>->tile->xe->drm); + return 0; } From d1469eb93af78191ac416962840d3323621c2e4b Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Fri, 17 Apr 2026 16:33:08 +0000 Subject: [PATCH 1015/1518] drm/xe/gsc: Fix BO leak on error in query_compatibility_version() [ Upstream commit 3762d6c36549accea7068c4a175483fafdd03657 ] When xe_gsc_read_out_header() fails, query_compatibility_version() returns directly instead of jumping to the out_bo label. This skips the xe_bo_unpin_map_no_vm() call, leaving the BO pinned and mapped with no remaining reference to free it. Fix by using goto out_bo so the error path properly cleans up the BO, consistent with the other error handling in the same function. Fixes: 0881cbe04077 ("drm/xe/gsc: Query GSC compatibility version") Cc: Daniele Ceraolo Spurio Reviewed-by: Daniele Ceraolo Spurio Link: https://patch.msgid.link/20260417163308.3416147-1-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 8de86d0a843c32ca9d36864bdb92f0376a830bce) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_gsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index 83d61bf8ec62e..8371ec002e4ed 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -166,7 +166,7 @@ static int query_compatibility_version(struct xe_gsc *gsc) &rd_offset); if (err) { xe_gt_err(gt, "HuC: invalid GSC reply for version query (err=%d)\n", err); - return err; + goto out_bo; } compat->major = version_query_rd(xe, &bo->vmap, rd_offset, proj_major); From aaad53a55812acd2355c0e5478896381e78b0110 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 21 Apr 2026 08:35:11 +0200 Subject: [PATCH 1016/1518] net: airoha: fix BQL imbalance in TX path [ Upstream commit 2d9f5a118205da2683ffcec78b9347f1f01a820e ] Fix a possible BQL imbalance in airoha_dev_xmit(), where inflight packets are accounted only for the AIROHA_NUM_TX_RING netdev TX queues. The queue index is computed as: qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx) txq = netdev_get_tx_queue(dev, qid); However, airoha_qdma_tx_napi_poll() accounts completions across all netdev TX queues (num_tx_queues), leading to inconsistent BQL accounting. Also reset all netdev TX queues in the ndo_stop callback. Fixes: 1d304174106c ("net: airoha: Implement BQL support") Fixes: c9f947769b77 ("net: airoha: Reset BQL stopping the netdevice") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260421-airoha-fix-bql-v1-1-f135afe4275b@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: 4ca01292ea2f ("net: airoha: Do not return err in ndo_stop() callback") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index a69544e785a2a..6742d0d9068df 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -971,10 +971,9 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) q->queued--; if (skb) { - u16 queue = skb_get_queue_mapping(skb); struct netdev_queue *txq; - txq = netdev_get_tx_queue(skb->dev, queue); + txq = skb_get_tx_queue(skb->dev, skb); netdev_tx_completed_queue(txq, 1, skb->len); dev_kfree_skb_any(skb); } @@ -1777,7 +1776,7 @@ static int airoha_dev_stop(struct net_device *dev) if (err) return err; - for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) + for (i = 0; i < dev->num_tx_queues; i++) netdev_tx_reset_subqueue(dev, i); if (atomic_dec_and_test(&qdma->users)) { @@ -2066,7 +2065,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, spin_lock_bh(&q->lock); - txq = netdev_get_tx_queue(dev, qid); + txq = skb_get_tx_queue(dev, skb); nr_frags = 1 + skb_shinfo(skb)->nr_frags; if (q->queued + nr_frags >= q->ndesc) { From c1e0b5eccdf09d8dbd849c459d03f969f4a01cd6 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 28 Apr 2026 08:53:16 +0200 Subject: [PATCH 1017/1518] net: airoha: Do not return err in ndo_stop() callback [ Upstream commit 4ca01292ea2f2363660610a65ba0285d7c3309ed ] Always complete the airoha_dev_stop() routine regardless of the airoha_set_vip_for_gdm_port() return value, since errors from ndo_stop() are ignored by the networking stack and the interface is always considered down after the call. Fixes: 23020f049327 ("net: airoha: Introduce ethernet support for EN7581 SoC") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260428-airoha-ndo-stop-not-err-v1-1-674506d29a91@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 6742d0d9068df..81ecfc1a1094c 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1769,13 +1769,10 @@ static int airoha_dev_stop(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); struct airoha_qdma *qdma = port->qdma; - int i, err; + int i; netif_tx_disable(dev); - err = airoha_set_vip_for_gdm_port(port, false); - if (err) - return err; - + airoha_set_vip_for_gdm_port(port, false); for (i = 0; i < dev->num_tx_queues; i++) netdev_tx_reset_subqueue(dev, i); From f2edb41645bf0a8112ef806a7a34b803d2ce538c Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 24 Feb 2026 02:02:14 +0000 Subject: [PATCH 1018/1518] bonding: print churn state via netlink [ Upstream commit 4916f2e2f3fc9aef289fcd07949301e5c29094c2 ] Currently, the churn state is printed only in sysfs. Add netlink support so users could get the state via netlink. Signed-off-by: Hangbin Liu Link: https://patch.msgid.link/20260224020215.6012-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni Stable-dep-of: c4f050ce06c5 ("bonding: 3ad: implement proper RCU rules for port->aggregator") Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_netlink.c | 9 +++++++++ include/uapi/linux/if_link.h | 2 ++ 2 files changed, 11 insertions(+) diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 286f11c517f76..ea1a80e658aeb 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -29,6 +29,8 @@ static size_t bond_get_slave_size(const struct net_device *bond_dev, nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */ nla_total_size(sizeof(s32)) + /* IFLA_BOND_SLAVE_PRIO */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_ACTOR_PORT_PRIO */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE */ 0; } @@ -77,6 +79,13 @@ static int bond_fill_slave_info(struct sk_buff *skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, + ad_port->sm_churn_actor_state)) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, + ad_port->sm_churn_partner_state)) + goto nla_put_failure; } if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3b491d96e52eb..69f19759b79d5 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1567,6 +1567,8 @@ enum { IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, IFLA_BOND_SLAVE_PRIO, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, + IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, + IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, __IFLA_BOND_SLAVE_MAX, }; From c169c5837525ad842df6a542facf52b6f866a519 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2026 12:32:07 +0000 Subject: [PATCH 1019/1518] bonding: 3ad: implement proper RCU rules for port->aggregator [ Upstream commit c4f050ce06c56cfb5993268af4a5cb66ed1cd04e ] syzbot found a data-race in bond_3ad_get_active_agg_info / bond_3ad_state_machine_handler [1] which hints at lack of proper RCU implementation. Add __rcu qualifier to port->aggregator, and add proper RCU API. [1] BUG: KCSAN: data-race in bond_3ad_get_active_agg_info / bond_3ad_state_machine_handler write to 0xffff88813cf5c4b0 of 8 bytes by task 36 on cpu 0: ad_port_selection_logic drivers/net/bonding/bond_3ad.c:1659 [inline] bond_3ad_state_machine_handler+0x9d5/0x2d60 drivers/net/bonding/bond_3ad.c:2569 process_one_work kernel/workqueue.c:3302 [inline] process_scheduled_works+0x4f0/0x9c0 kernel/workqueue.c:3385 worker_thread+0x58a/0x780 kernel/workqueue.c:3466 kthread+0x22a/0x280 kernel/kthread.c:436 ret_from_fork+0x146/0x330 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 read to 0xffff88813cf5c4b0 of 8 bytes by task 22063 on cpu 1: __bond_3ad_get_active_agg_info drivers/net/bonding/bond_3ad.c:2858 [inline] bond_3ad_get_active_agg_info+0x8c/0x230 drivers/net/bonding/bond_3ad.c:2881 bond_fill_info+0xe0f/0x10f0 drivers/net/bonding/bond_netlink.c:853 rtnl_link_info_fill net/core/rtnetlink.c:906 [inline] rtnl_link_fill+0x1d7/0x4e0 net/core/rtnetlink.c:927 rtnl_fill_ifinfo+0xf8e/0x1380 net/core/rtnetlink.c:2168 rtmsg_ifinfo_build_skb+0x11c/0x1b0 net/core/rtnetlink.c:4453 rtmsg_ifinfo_event net/core/rtnetlink.c:4486 [inline] rtmsg_ifinfo+0x6d/0x110 net/core/rtnetlink.c:4495 __dev_notify_flags+0x76/0x390 net/core/dev.c:9790 netif_change_flags+0xac/0xd0 net/core/dev.c:9823 do_setlink+0x905/0x2950 net/core/rtnetlink.c:3180 rtnl_group_changelink net/core/rtnetlink.c:3813 [inline] __rtnl_newlink net/core/rtnetlink.c:3981 [inline] rtnl_newlink+0xf55/0x1400 net/core/rtnetlink.c:4109 rtnetlink_rcv_msg+0x64b/0x720 net/core/rtnetlink.c:6995 netlink_rcv_skb+0x123/0x220 net/netlink/af_netlink.c:2550 rtnetlink_rcv+0x1c/0x30 net/core/rtnetlink.c:7022 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x5a8/0x680 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x5c8/0x6f0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:787 [inline] __sock_sendmsg net/socket.c:802 [inline] ____sys_sendmsg+0x563/0x5b0 net/socket.c:2698 ___sys_sendmsg+0x195/0x1e0 net/socket.c:2752 __sys_sendmsg net/socket.c:2784 [inline] __do_sys_sendmsg net/socket.c:2789 [inline] __se_sys_sendmsg net/socket.c:2787 [inline] __x64_sys_sendmsg+0xd4/0x160 net/socket.c:2787 x64_sys_call+0x194c/0x3020 arch/x86/include/generated/asm/syscalls_64.h:47 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f value changed: 0x0000000000000000 -> 0xffff88813cf5c400 Reported by Kernel Concurrency Sanitizer on: CPU: 1 UID: 0 PID: 22063 Comm: syz.0.31122 Tainted: G W syzkaller #0 PREEMPT(full) Tainted: [W]=WARN Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026 Fixes: 47e91f56008b ("bonding: use RCU protection for 3ad xmit path") Reported-by: syzbot+9bb2ff2a4ab9e17307e1@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/69f0a82f.050a0220.3aadc4.0000.GAE@google.com/ Signed-off-by: Eric Dumazet Cc: Jay Vosburgh Cc: Andrew Lunn Link: https://patch.msgid.link/20260428123207.3809211-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_3ad.c | 109 ++++++++++++++----------- drivers/net/bonding/bond_main.c | 8 +- drivers/net/bonding/bond_netlink.c | 16 ++-- drivers/net/bonding/bond_procfs.c | 3 +- drivers/net/bonding/bond_sysfs_slave.c | 17 ++-- include/net/bond_3ad.h | 2 +- 6 files changed, 89 insertions(+), 66 deletions(-) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 49717b7b82a2c..f1ef99f7515b0 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1014,6 +1014,7 @@ static void ad_cond_set_peer_notif(struct port *port) static void ad_mux_machine(struct port *port, bool *update_slave_arr) { struct bonding *bond = __get_bond_by_port(port); + struct aggregator *aggregator; mux_states_t last_state; /* keep current State Machine state to compare later if it was @@ -1021,6 +1022,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ last_state = port->sm_mux_state; + aggregator = rcu_dereference(port->aggregator); if (port->sm_vars & AD_PORT_BEGIN) { port->sm_mux_state = AD_MUX_DETACHED; } else { @@ -1040,7 +1042,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; break; } @@ -1055,7 +1057,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * update ready variable, we check READY_N and update * READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); /* if the wait_while_timer expired, and the port is * in READY state, move to ATTACHED state @@ -1071,7 +1073,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { - if (port->aggregator->is_active) { + if (aggregator->is_active) { int state = AD_MUX_COLLECTING_DISTRIBUTING; if (!bond->params.coupled_control) @@ -1087,9 +1089,9 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; - } else if (port->aggregator->is_active) { + } else if (aggregator->is_active) { port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; } @@ -1100,7 +1102,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator->is_active && + if (aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; @@ -1119,7 +1121,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ struct slave *slave = port->slave; - if (port->aggregator->is_active && + if (aggregator->is_active && bond_is_slave_rx_disabled(slave)) { ad_enable_collecting(port); *update_slave_arr = true; @@ -1139,8 +1141,8 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator && - port->aggregator->is_active && + if (aggregator && + aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; @@ -1172,7 +1174,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); break; case AD_MUX_ATTACHED: - if (port->aggregator->is_active) + if (aggregator->is_active) port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; else @@ -1546,9 +1548,9 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) bond = __get_bond_by_port(port); /* if the port is connected to other aggregator, detach it */ - if (port->aggregator) { + temp_aggregator = rcu_dereference(port->aggregator); + if (temp_aggregator) { /* detach the port from its former aggregator */ - temp_aggregator = port->aggregator; for (curr_port = temp_aggregator->lag_ports; curr_port; last_port = curr_port, curr_port = curr_port->next_port_in_aggregator) { @@ -1571,7 +1573,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) /* clear the port's relations to this * aggregator */ - port->aggregator = NULL; + RCU_INIT_POINTER(port->aggregator, NULL); port->next_port_in_aggregator = NULL; port->actor_port_aggregator_identifier = 0; @@ -1594,7 +1596,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) port->slave->bond->dev->name, port->slave->dev->name, port->actor_port_number, - port->aggregator->aggregator_identifier); + temp_aggregator->aggregator_identifier); } } /* search on all aggregators for a suitable aggregator for this port */ @@ -1618,15 +1620,15 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) ) ) { /* attach to the founded aggregator */ - port->aggregator = aggregator; + rcu_assign_pointer(port->aggregator, aggregator); port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + aggregator->aggregator_identifier; port->next_port_in_aggregator = aggregator->lag_ports; - port->aggregator->num_of_ports++; + aggregator->num_of_ports++; aggregator->lag_ports = port; slave_dbg(bond->dev, slave->dev, "Port %d joined LAG %d (existing LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; @@ -1641,39 +1643,40 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) if (!found) { if (free_aggregator) { /* assign port a new aggregator */ - port->aggregator = free_aggregator; port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + free_aggregator->aggregator_identifier; /* update the new aggregator's parameters * if port was responsed from the end-user */ if (port->actor_oper_port_key & AD_DUPLEX_KEY_MASKS) /* if port is full duplex */ - port->aggregator->is_individual = false; + free_aggregator->is_individual = false; else - port->aggregator->is_individual = true; + free_aggregator->is_individual = true; - port->aggregator->actor_admin_aggregator_key = + free_aggregator->actor_admin_aggregator_key = port->actor_admin_port_key; - port->aggregator->actor_oper_aggregator_key = + free_aggregator->actor_oper_aggregator_key = port->actor_oper_port_key; - port->aggregator->partner_system = + free_aggregator->partner_system = port->partner_oper.system; - port->aggregator->partner_system_priority = + free_aggregator->partner_system_priority = port->partner_oper.system_priority; - port->aggregator->partner_oper_aggregator_key = port->partner_oper.key; - port->aggregator->receive_state = 1; - port->aggregator->transmit_state = 1; - port->aggregator->lag_ports = port; - port->aggregator->num_of_ports++; + free_aggregator->partner_oper_aggregator_key = port->partner_oper.key; + free_aggregator->receive_state = 1; + free_aggregator->transmit_state = 1; + free_aggregator->lag_ports = port; + free_aggregator->num_of_ports++; + + rcu_assign_pointer(port->aggregator, free_aggregator); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; slave_dbg(bond->dev, port->slave->dev, "Port %d joined LAG %d (new LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + free_aggregator->aggregator_identifier); } else { slave_err(bond->dev, port->slave->dev, "Port %d did not find a suitable aggregator\n", @@ -1685,13 +1688,12 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) * in all aggregator's ports, else set ready=FALSE in all * aggregator's ports */ - __set_agg_ports_ready(port->aggregator, - __agg_ports_are_ready(port->aggregator)); + aggregator = rcu_dereference(port->aggregator); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); - aggregator = __get_first_agg(port); - ad_agg_selection_logic(aggregator, update_slave_arr); + ad_agg_selection_logic(__get_first_agg(port), update_slave_arr); - if (!port->aggregator->is_active) + if (!aggregator->is_active) port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; } @@ -2060,13 +2062,15 @@ static void ad_initialize_port(struct port *port, const struct bond_params *bond */ static void ad_enable_collecting(struct port *port) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { struct slave *slave = port->slave; slave_dbg(slave->bond->dev, slave->dev, "Enabling collecting on port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_collecting_port(port); } } @@ -2078,11 +2082,13 @@ static void ad_enable_collecting(struct port *port) */ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && __agg_has_partner(port->aggregator)) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling distributing on port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_distributing_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2099,11 +2105,13 @@ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Enabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_port(port); /* Slave array needs update */ *update_slave_arr = true; @@ -2120,11 +2128,13 @@ static void ad_enable_collecting_distributing(struct port *port, static void ad_disable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && __agg_has_partner(port->aggregator)) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2364,7 +2374,7 @@ void bond_3ad_unbind_slave(struct slave *slave) */ for (temp_port = aggregator->lag_ports; temp_port; temp_port = temp_port->next_port_in_aggregator) { - temp_port->aggregator = new_aggregator; + rcu_assign_pointer(temp_port->aggregator, new_aggregator); temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; } @@ -2833,15 +2843,16 @@ int bond_3ad_set_carrier(struct bonding *bond) int __bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) { - struct aggregator *aggregator = NULL; + struct aggregator *aggregator = NULL, *tmp; struct list_head *iter; struct slave *slave; struct port *port; bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); - if (port->aggregator && port->aggregator->is_active) { - aggregator = port->aggregator; + tmp = rcu_dereference(port->aggregator); + if (tmp && tmp->is_active) { + aggregator = tmp; break; } } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1d84e348f2cc7..8b1422dda4c08 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1402,7 +1402,7 @@ static void bond_poll_controller(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = - SLAVE_AD_INFO(slave)->port.aggregator; + rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg && agg->aggregator_identifier != ad_info.aggregator_id) @@ -5155,15 +5155,16 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } + rcu_read_lock(); bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { - struct aggregator *agg; + const struct aggregator *agg; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (!agg || agg->aggregator_identifier != agg_id) continue; } @@ -5175,6 +5176,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) usable_slaves->arr[usable_slaves->count++] = slave; } + rcu_read_unlock(); bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index ea1a80e658aeb..c7d3e0602c831 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -66,27 +66,29 @@ static int bond_fill_slave_info(struct sk_buff *skb, const struct port *ad_port; ad_port = &SLAVE_AD_INFO(slave)->port; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg) { if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, agg->aggregator_identifier)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, ad_port->actor_oper_port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, ad_port->sm_churn_actor_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, ad_port->sm_churn_partner_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; } + rcu_read_unlock(); if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, SLAVE_AD_INFO(slave)->port_priority)) @@ -95,6 +97,8 @@ static int bond_fill_slave_info(struct sk_buff *skb, return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: return -EMSGSIZE; } diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 7edf72ec816ab..0c0146b761772 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -187,6 +187,7 @@ static void bond_info_show_master(struct seq_file *seq) } } +/* Note: runs under rcu_read_lock() */ static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) { @@ -213,7 +214,7 @@ static void bond_info_show_slave(struct seq_file *seq, if (BOND_MODE(bond) == BOND_MODE_8023AD) { const struct port *port = &SLAVE_AD_INFO(slave)->port; - const struct aggregator *agg = port->aggregator; + const struct aggregator *agg = rcu_dereference(port->aggregator); if (agg) { seq_printf(seq, "Aggregator ID: %d\n", diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 36d0e8440b5b9..fc6fe7181789d 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -62,10 +62,15 @@ static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) const struct aggregator *agg; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { - agg = SLAVE_AD_INFO(slave)->port.aggregator; - if (agg) - return sysfs_emit(buf, "%d\n", - agg->aggregator_identifier); + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); + if (agg) { + ssize_t res = sysfs_emit(buf, "%d\n", + agg->aggregator_identifier); + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); } return sysfs_emit(buf, "N/A\n"); @@ -78,7 +83,7 @@ static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) + if (rcu_access_pointer(ad_port->aggregator)) return sysfs_emit(buf, "%u\n", ad_port->actor_oper_port_state); } @@ -93,7 +98,7 @@ static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) + if (rcu_access_pointer(ad_port->aggregator)) return sysfs_emit(buf, "%u\n", ad_port->partner_oper.port_state); } diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index c92d4a976246d..05572c19e14b7 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -243,7 +243,7 @@ typedef struct port { churn_state_t sm_churn_actor_state; churn_state_t sm_churn_partner_state; struct slave *slave; /* pointer to the bond slave that this port belongs to */ - struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ + struct aggregator __rcu *aggregator; /* pointer to an aggregator that this port related to */ struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ u32 transaction_id; /* continuous number for identification of Marker PDU's; */ struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */ From 864577384d7232c3fcbd6994e6c2864a5ef8b846 Mon Sep 17 00:00:00 2001 From: Hasan Basbunar Date: Tue, 28 Apr 2026 19:07:39 +0200 Subject: [PATCH 1020/1518] page_pool: fix memory-provider leak in page_pool_create_percpu() error path [ Upstream commit 5ef343614db766acdc01c56d66e780a1b43c6ac6 ] When page_pool_create_percpu() fails on page_pool_list(), it falls through to its err_uninit: label, which calls page_pool_uninit(). At that point page_pool_init() has already taken two references when the user requested PP_FLAG_ALLOW_UNREADABLE_NETMEM: pool->mp_ops->init(pool) static_branch_inc(&page_pool_mem_providers); Neither is undone by page_pool_uninit(); both are only undone by __page_pool_destroy() (success-side teardown). The error path therefore leaks the per-provider reference taken by mp_ops->init (io_zcrx_ifq->refs in the io_uring zcrx provider, the dmabuf binding refcount in the devmem provider) plus one increment of the page_pool_mem_providers static branch on every failure of xa_alloc_cyclic() inside page_pool_list(). The leaked io_zcrx_ifq->refs in turn pins everything io_zcrx_ifq_free() would release on cleanup: ifq->user (uid), ifq->mm_account (mmdrop), ifq->dev (device refcount), ifq->netdev_tracker (netdev refcount), and the rbuf region. The leaked static branch increment forces all subsequent page_pool_alloc_netmems() and page_pool_return_page() callers to take the slow mp_ops branch for the lifetime of the kernel. Reachable via the io_uring zcrx path: io_uring_register(IORING_REGISTER_ZCRX_IFQ) /* CAP_NET_ADMIN */ -> __io_uring_register -> io_register_zcrx -> zcrx_register_netdev -> netif_mp_open_rxq -> driver ndo_queue_mem_alloc -> page_pool_create_percpu -> page_pool_init succeeds (mp_ops->init runs, branch++) -> page_pool_list fails (xa_alloc_cyclic -ENOMEM) -> goto err_uninit <-- leak The same shape applies to the devmem dmabuf provider via mp_dmabuf_devmem_init()/mp_dmabuf_devmem_destroy(). Restore the cleanup symmetry by moving the mp_ops->destroy() and static_branch_dec() calls out of __page_pool_destroy() and into page_pool_uninit(), so page_pool_uninit() is again the strict inverse of page_pool_init(). page_pool_uninit() has only two callers (the err_uninit: path and __page_pool_destroy()), so this preserves the single-call invariant on the success path while fixing the err path. The error path of page_pool_init() itself still skips the mp_ops cleanup correctly: mp_ops->init is the last action that takes a reference before page_pool_init() returns 0, so when it returns an error neither the refcount nor the static branch has been touched. Triggering the bug requires xa_alloc_cyclic() to fail with -ENOMEM, which under normal GFP_KERNEL retry behaviour is rare. It is deterministic under CONFIG_FAULT_INJECTION with fail_page_alloc / xa fault injection, or under sustained memory pressure. The leak is silent: there is no warning, and the released kernel build continues running with a permanently-incremented static branch. Fixes: 0f9214046893 ("memory-provider: dmabuf devmem memory provider") Signed-off-by: Hasan Basbunar Link: https://patch.msgid.link/20260428170739.34881-1-basbunarhasan@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/page_pool.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1a5edec485f14..b775b6305fb78 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -323,6 +323,11 @@ static void page_pool_uninit(struct page_pool *pool) if (!pool->system) free_percpu(pool->recycle_stats); #endif + + if (pool->mp_ops) { + pool->mp_ops->destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } } /** @@ -1122,11 +1127,6 @@ static void __page_pool_destroy(struct page_pool *pool) page_pool_unlist(pool); page_pool_uninit(pool); - if (pool->mp_ops) { - pool->mp_ops->destroy(pool); - static_branch_dec(&page_pool_mem_providers); - } - kfree(pool); } From 033fa40dff770259c0819f76df1c67176d4e125c Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:13 -0700 Subject: [PATCH 1021/1518] iavf: rename IAVF_VLAN_IS_NEW to IAVF_VLAN_ADDING [ Upstream commit 70d62b669f1f9080a25278fc90b64309f4ae8959 ] Rename the IAVF_VLAN_IS_NEW state to IAVF_VLAN_ADDING to better describe what the state represents: an ADD request has been sent to the PF and is waiting for a response. This is a pure rename with no behavioral change, preparing for a cleanup of the VLAN filter state machine. Signed-off-by: Petr Oros Reviewed-by: Aleksandr Loktionov Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Reviewed-by: Przemek Kitszel Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-1-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Stable-dep-of: f2ce65b9b917 ("iavf: stop removing VLAN filters from PF on interface down") Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e9fb0a0919e37..47a862ca5e2c3 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -158,7 +158,7 @@ struct iavf_vlan { enum iavf_vlan_state_t { IAVF_VLAN_INVALID, IAVF_VLAN_ADD, /* filter needs to be added */ - IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ + IAVF_VLAN_ADDING, /* ADD sent to PF, waiting for response */ IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 291b21230b65f..9dab61f198c0d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -746,7 +746,7 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_IS_NEW) { + if (f->state == IAVF_VLAN_ADDING) { list_del(&f->list); kfree(f); adapter->num_vlan_filters--; @@ -811,7 +811,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->state = IAVF_VLAN_IS_NEW; + f->state = IAVF_VLAN_ADDING; if (i == count) break; } @@ -872,7 +872,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->state = IAVF_VLAN_IS_NEW; + f->state = IAVF_VLAN_ADDING; } } @@ -2906,7 +2906,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_IS_NEW) + if (f->state == IAVF_VLAN_ADDING) f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); From b0173c36977c4e977e6f0a01ab3a8d4a9fde8371 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:14 -0700 Subject: [PATCH 1022/1518] iavf: stop removing VLAN filters from PF on interface down [ Upstream commit f2ce65b9b917474a1a6ce68d357e15fac2aca0f2 ] When a VF goes down, the driver currently sends DEL_VLAN to the PF for every VLAN filter (ACTIVE -> DISABLE -> send DEL -> INACTIVE), then re-adds them all on UP (INACTIVE -> ADD -> send ADD -> ADDING -> ACTIVE). This round-trip is unnecessary because: 1. The PF disables the VF's queues via VIRTCHNL_OP_DISABLE_QUEUES, which already prevents all RX/TX traffic regardless of VLAN filter state. 2. The VLAN filters remaining in PF HW while the VF is down is harmless - packets matching those filters have nowhere to go with queues disabled. 3. The DEL+ADD cycle during down/up creates race windows where the VLAN filter list is incomplete. With spoofcheck enabled, the PF enables TX VLAN filtering on the first non-zero VLAN add, blocking traffic for any VLANs not yet re-added. Remove the entire DISABLE/INACTIVE state machinery: - Remove IAVF_VLAN_DISABLE and IAVF_VLAN_INACTIVE enum values - Remove iavf_restore_filters() and its call from iavf_open() - Remove VLAN filter handling from iavf_clear_mac_vlan_filters(), rename it to iavf_clear_mac_filters() - Remove DEL_VLAN_FILTER scheduling from iavf_down() - Remove all DISABLE/INACTIVE handling from iavf_del_vlans() VLAN filters now stay ACTIVE across down/up cycles. Only explicit user removal (ndo_vlan_rx_kill_vid) or PF/VF reset triggers VLAN filter deletion/re-addition. Fixes: ed1f5b58ea01 ("i40evf: remove VLAN filters on close") Signed-off-by: Petr Oros Reviewed-by: Aleksandr Loktionov Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Reviewed-by: Przemek Kitszel Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-2-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf.h | 6 +-- drivers/net/ethernet/intel/iavf/iavf_main.c | 39 ++----------------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 33 +++------------- 3 files changed, 12 insertions(+), 66 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 47a862ca5e2c3..5765715914d6b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -159,10 +159,8 @@ enum iavf_vlan_state_t { IAVF_VLAN_INVALID, IAVF_VLAN_ADD, /* filter needs to be added */ IAVF_VLAN_ADDING, /* ADD sent to PF, waiting for response */ - IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ - IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ - IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ - IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ + IAVF_VLAN_ACTIVE, /* PF confirmed, filter is in HW */ + IAVF_VLAN_REMOVE, /* filter queued for DEL from PF */ }; struct iavf_vlan_filter { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 0a72d419782e5..a12ae6446c06c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -801,27 +801,6 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) spin_unlock_bh(&adapter->mac_vlan_list_lock); } -/** - * iavf_restore_filters - * @adapter: board private structure - * - * Restore existing non MAC filters when VF netdev comes back up - **/ -static void iavf_restore_filters(struct iavf_adapter *adapter) -{ - struct iavf_vlan_filter *f; - - /* re-add all VLAN filters */ - spin_lock_bh(&adapter->mac_vlan_list_lock); - - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_INACTIVE) - f->state = IAVF_VLAN_ADD; - } - - spin_unlock_bh(&adapter->mac_vlan_list_lock); - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; -} /** * iavf_get_num_vlans_added - get number of VLANs added @@ -1240,13 +1219,12 @@ static void iavf_up_complete(struct iavf_adapter *adapter) } /** - * iavf_clear_mac_vlan_filters - Remove mac and vlan filters not sent to PF - * yet and mark other to be removed. + * iavf_clear_mac_filters - Remove MAC filters not sent to PF yet and mark + * others to be removed. * @adapter: board private structure **/ -static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) +static void iavf_clear_mac_filters(struct iavf_adapter *adapter) { - struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_mac_filter *f, *ftmp; spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1265,11 +1243,6 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* disable all VLAN filters */ - list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) - vlf->state = IAVF_VLAN_DISABLE; - spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -1365,7 +1338,7 @@ void iavf_down(struct iavf_adapter *adapter) iavf_napi_disable_all(adapter); iavf_irq_disable(adapter); - iavf_clear_mac_vlan_filters(adapter); + iavf_clear_mac_filters(adapter); iavf_clear_cloud_filters(adapter); iavf_clear_fdir_filters(adapter); iavf_clear_adv_rss_conf(adapter); @@ -1382,8 +1355,6 @@ void iavf_down(struct iavf_adapter *adapter) */ if (!list_empty(&adapter->mac_filter_list)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; - if (!list_empty(&adapter->vlan_filter_list)) - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; if (!list_empty(&adapter->cloud_filter_list)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; if (!list_empty(&adapter->fdir_list_head)) @@ -4492,8 +4463,6 @@ static int iavf_open(struct net_device *netdev) iavf_add_filter(adapter, adapter->hw.mac.addr); spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore filters that were removed with IFF_DOWN */ - iavf_restore_filters(adapter); iavf_restore_fdir_filters(adapter); iavf_configure(adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 9dab61f198c0d..8a856ec5ef480 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -909,22 +909,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - /* since VLAN capabilities are not allowed, we dont want to send - * a VLAN delete request because it will most likely fail and - * create unnecessary errors/noise, so just free the VLAN - * filters marked for removal to enable bailing out before - * sending a virtchnl message - */ if (f->state == IAVF_VLAN_REMOVE && !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); adapter->num_vlan_filters--; - } else if (f->state == IAVF_VLAN_DISABLE && - !VLAN_FILTERING_ALLOWED(adapter)) { - f->state = IAVF_VLAN_INACTIVE; - } else if (f->state == IAVF_VLAN_REMOVE || - f->state == IAVF_VLAN_DISABLE) { + } else if (f->state == IAVF_VLAN_REMOVE) { count++; } } @@ -956,13 +946,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_DISABLE) { - vvfl->vlan_id[i] = f->vlan.vid; - f->state = IAVF_VLAN_INACTIVE; - i++; - if (i == count) - break; - } else if (f->state == IAVF_VLAN_REMOVE) { + if (f->state == IAVF_VLAN_REMOVE) { vvfl->vlan_id[i] = f->vlan.vid; list_del(&f->list); kfree(f); @@ -1003,8 +987,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_DISABLE || - f->state == IAVF_VLAN_REMOVE) { + if (f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -1018,13 +1001,9 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - if (f->state == IAVF_VLAN_DISABLE) { - f->state = IAVF_VLAN_INACTIVE; - } else { - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; - } + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; i++; if (i == count) break; From e469b1ff33192f5ff2ed9f4e7bc0951e31ddcb83 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:15 -0700 Subject: [PATCH 1023/1518] iavf: wait for PF confirmation before removing VLAN filters [ Upstream commit bbcbe4ed70dea948849549af7edf44bd42bbd695 ] The VLAN filter DELETE path was asymmetric with the ADD path: ADD waits for PF confirmation (ADD -> ADDING -> ACTIVE), but DELETE immediately frees the filter struct after sending the DEL message without waiting for the PF response. This is problematic because: - If the PF rejects the DEL, the filter remains in HW but the driver has already freed the tracking structure, losing sync. - Race conditions between DEL pending and other operations (add, reset) cannot be properly resolved if the filter struct is already gone. Add IAVF_VLAN_REMOVING state to make the DELETE path symmetric: REMOVE -> REMOVING (send DEL) -> PF confirms -> kfree -> PF rejects -> ACTIVE In iavf_del_vlans(), transition filters from REMOVE to REMOVING instead of immediately freeing them. The new DEL completion handler in iavf_virtchnl_completion() frees filters on success or reverts them to ACTIVE on error. Update iavf_add_vlan() to handle the REMOVING state: if a DEL is pending and the user re-adds the same VLAN, queue it for ADD so it gets re-programmed after the PF processes the DEL. The !VLAN_FILTERING_ALLOWED early-exit path still frees filters directly since no PF message is sent in that case. Also update iavf_del_vlan() to skip filters already in REMOVING state: DEL has been sent to PF and the completion handler will free the filter when PF confirms. Without this guard, the sequence DEL(pending) -> user-del -> second DEL could cause the PF to return an error for the second DEL (filter already gone), causing the completion handler to incorrectly revert a deleted filter back to ACTIVE. Fixes: 968996c070ef ("iavf: Fix VLAN_V2 addition/rejection") Signed-off-by: Petr Oros Reviewed-by: Aleksandr Loktionov Tested-by: Rafal Romanowski Reviewed-by: Przemek Kitszel Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-3-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf.h | 1 + drivers/net/ethernet/intel/iavf/iavf_main.c | 13 ++++--- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 37 +++++++++++++------ 3 files changed, 34 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 5765715914d6b..050f8241ef5e6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -161,6 +161,7 @@ enum iavf_vlan_state_t { IAVF_VLAN_ADDING, /* ADD sent to PF, waiting for response */ IAVF_VLAN_ACTIVE, /* PF confirmed, filter is in HW */ IAVF_VLAN_REMOVE, /* filter queued for DEL from PF */ + IAVF_VLAN_REMOVING, /* DEL sent to PF, waiting for response */ }; struct iavf_vlan_filter { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index a12ae6446c06c..d09add9a110ea 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -757,10 +757,10 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); } else if (f->state == IAVF_VLAN_REMOVE) { - /* Re-add the filter since we cannot tell whether the - * pending delete has already been processed by the PF. - * A duplicate add is harmless. - */ + /* DEL not yet sent to PF, cancel it */ + f->state = IAVF_VLAN_ACTIVE; + } else if (f->state == IAVF_VLAN_REMOVING) { + /* DEL already sent to PF, re-add after completion */ f->state = IAVF_VLAN_ADD; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); @@ -791,11 +791,14 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) list_del(&f->list); kfree(f); adapter->num_vlan_filters--; - } else { + } else if (f->state != IAVF_VLAN_REMOVING) { f->state = IAVF_VLAN_REMOVE; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); } + /* If REMOVING, DEL is already sent to PF; completion + * handler will free the filter when PF confirms. + */ } spin_unlock_bh(&adapter->mac_vlan_list_lock); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8a856ec5ef480..9132f16d853e5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -945,12 +945,10 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + list_for_each_entry(f, &adapter->vlan_filter_list, list) { if (f->state == IAVF_VLAN_REMOVE) { vvfl->vlan_id[i] = f->vlan.vid; - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; + f->state = IAVF_VLAN_REMOVING; i++; if (i == count) break; @@ -986,7 +984,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + list_for_each_entry(f, &adapter->vlan_filter_list, list) { if (f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; @@ -1001,9 +999,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; + f->state = IAVF_VLAN_REMOVING; i++; if (i == count) break; @@ -2366,10 +2362,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); wake_up(&adapter->vc_waitqueue); break; - case VIRTCHNL_OP_DEL_VLAN: - dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", - iavf_stat_str(&adapter->hw, v_retval)); - break; case VIRTCHNL_OP_DEL_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", iavf_stat_str(&adapter->hw, v_retval)); @@ -2891,6 +2883,27 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->mac_vlan_list_lock); } break; + case VIRTCHNL_OP_DEL_VLAN: + case VIRTCHNL_OP_DEL_VLAN_V2: { + struct iavf_vlan_filter *f, *ftmp; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, + list) { + if (f->state == IAVF_VLAN_REMOVING) { + if (v_retval) { + /* PF rejected DEL, keep filter */ + f->state = IAVF_VLAN_ACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); + } + break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: /* PF enabled vlan strip on this VF. * Update netdev->features if needed to be in sync with ethtool. From b166453d8d015df38eddcb147de64cbb07544531 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:16 -0700 Subject: [PATCH 1024/1518] iavf: add VIRTCHNL_OP_ADD_VLAN to success completion handler [ Upstream commit 34d33313b52eeac3a97ad2e3176d523ec70d9283 ] The V1 ADD_VLAN opcode had no success handler; filters sent via V1 stayed in ADDING state permanently. Add a fallthrough case so V1 filters also transition ADDING -> ACTIVE on PF confirmation. Critically, add an `if (v_retval) break` guard: the error switch in iavf_virtchnl_completion() does NOT return after handling errors, it falls through to the success switch. Without this guard, a PF-rejected ADD would incorrectly mark ADDING filters as ACTIVE, creating a driver/HW mismatch where the driver believes the filter is installed but the PF never accepted it. For V2, this is harmless: iavf_vlan_add_reject() in the error block already kfree'd all ADDING filters, so the success handler finds nothing to transition. Fixes: 968996c070ef ("iavf: Fix VLAN_V2 addition/rejection") Signed-off-by: Petr Oros Reviewed-by: Aleksandr Loktionov Tested-by: Rafal Romanowski Reviewed-by: Przemek Kitszel Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-4-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 9132f16d853e5..f1a01b8e2235c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2872,9 +2872,13 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); } break; + case VIRTCHNL_OP_ADD_VLAN: case VIRTCHNL_OP_ADD_VLAN_V2: { struct iavf_vlan_filter *f; + if (v_retval) + break; + spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { if (f->state == IAVF_VLAN_ADDING) From 1e9185b13ce57b86844447e092e58abb3be849b1 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:17 -0700 Subject: [PATCH 1025/1518] ice: fix NULL pointer dereference in ice_reset_all_vfs() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 54ef02487914c24170c7e1c061e45212dc55365e ] ice_reset_all_vfs() ignores the return value of ice_vf_rebuild_vsi(). When the VSI rebuild fails (e.g. during NVM firmware update via nvmupdate64e), ice_vsi_rebuild() tears down the VSI on its error path, leaving txq_map and rxq_map as NULL. The subsequent unconditional call to ice_vf_post_vsi_rebuild() leads to a NULL pointer dereference in ice_ena_vf_q_mappings() when it accesses vsi->txq_map[0]. The single-VF reset path in ice_reset_vf() already handles this correctly by checking the return value of ice_vf_reconfig_vsi() and skipping ice_vf_post_vsi_rebuild() on failure. Apply the same pattern to ice_reset_all_vfs(): check the return value of ice_vf_rebuild_vsi() and skip ice_vf_post_vsi_rebuild() and ice_eswitch_attach_vf() on failure. The VF is left safely disabled (ICE_VF_STATE_INIT not set, VFGEN_RSTAT not set to VFACTIVE) and can be recovered via a VFLR triggered by a PCI reset of the VF (sysfs reset or driver rebind). Note that this patch does not prevent the VF VSI rebuild from failing during NVM update — the underlying cause is firmware being in a transitional state while the EMP reset is processed, which can cause Admin Queue commands (ice_add_vsi, ice_cfg_vsi_lan) to fail. This patch only prevents the subsequent NULL pointer dereference that crashes the kernel when the rebuild does fail. crash> bt PID: 50795 TASK: ff34c9ee708dc680 CPU: 1 COMMAND: "kworker/u512:5" #0 [ff72159bcfe5bb50] machine_kexec at ffffffffaa8850ee #1 [ff72159bcfe5bba8] __crash_kexec at ffffffffaaa15fba #2 [ff72159bcfe5bc68] crash_kexec at ffffffffaaa16540 #3 [ff72159bcfe5bc70] oops_end at ffffffffaa837eda #4 [ff72159bcfe5bc90] page_fault_oops at ffffffffaa893997 #5 [ff72159bcfe5bce8] exc_page_fault at ffffffffab528595 #6 [ff72159bcfe5bd10] asm_exc_page_fault at ffffffffab600bb2 [exception RIP: ice_ena_vf_q_mappings+0x79] RIP: ffffffffc0a85b29 RSP: ff72159bcfe5bdc8 RFLAGS: 00010206 RAX: 00000000000f0000 RBX: ff34c9efc9c00000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000010 RDI: ff34c9efc9c00000 RBP: ff34c9efc27d4828 R8: 0000000000000093 R9: 0000000000000040 R10: ff34c9efc27d4828 R11: 0000000000000040 R12: 0000000000100000 R13: 0000000000000010 R14: R15: ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ff72159bcfe5bdf8] ice_sriov_post_vsi_rebuild at ffffffffc0a85e2e [ice] #8 [ff72159bcfe5be08] ice_reset_all_vfs at ffffffffc0a920b4 [ice] #9 [ff72159bcfe5be48] ice_service_task at ffffffffc0a31519 [ice] #10 [ff72159bcfe5be88] process_one_work at ffffffffaa93dca4 #11 [ff72159bcfe5bec8] worker_thread at ffffffffaa93e9de #12 [ff72159bcfe5bf18] kthread at ffffffffaa946663 #13 [ff72159bcfe5bf50] ret_from_fork at ffffffffaa8086b9 The panic occurs attempting to dereference the NULL pointer in RDX at ice_sriov.c:294, which loads vsi->txq_map (offset 0x4b8 in ice_vsi). The faulting VSI is an allocated slab object but not fully initialized after a failed ice_vsi_rebuild(): crash> struct ice_vsi 0xff34c9efc27d4828 netdev = 0x0, rx_rings = 0x0, tx_rings = 0x0, q_vectors = 0x0, txq_map = 0x0, rxq_map = 0x0, alloc_txq = 0x10, num_txq = 0x10, alloc_rxq = 0x10, num_rxq = 0x10, The nvmupdate64e process was performing NVM firmware update: crash> bt 0xff34c9edd1a30000 PID: 49858 TASK: ff34c9edd1a30000 CPU: 1 COMMAND: "nvmupdate64e" #0 [ff72159bcd617618] __schedule at ffffffffab5333f8 #4 [ff72159bcd617750] ice_sq_send_cmd at ffffffffc0a35347 [ice] #5 [ff72159bcd6177a8] ice_sq_send_cmd_retry at ffffffffc0a35b47 [ice] #6 [ff72159bcd617810] ice_aq_send_cmd at ffffffffc0a38018 [ice] #7 [ff72159bcd617848] ice_aq_read_nvm at ffffffffc0a40254 [ice] #8 [ff72159bcd6178b8] ice_read_flat_nvm at ffffffffc0a4034c [ice] #9 [ff72159bcd617918] ice_devlink_nvm_snapshot at ffffffffc0a6ffa5 [ice] dmesg: ice 0000:13:00.0: firmware recommends not updating fw.mgmt, as it may result in a downgrade. continuing anyways ice 0000:13:00.1: ice_init_nvm failed -5 ice 0000:13:00.1: Rebuild failed, unload and reload driver Fixes: 12bb018c538c ("ice: Refactor VF reset") Signed-off-by: Petr Oros Tested-by: Rafal Romanowski Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-5-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index de9e81ccee664..e53a1e4247cb1 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -804,7 +804,12 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_ctrl_invalidate_vsi(vf); ice_vf_pre_vsi_rebuild(vf); - ice_vf_rebuild_vsi(vf); + if (ice_vf_rebuild_vsi(vf)) { + dev_err(dev, "VF %u VSI rebuild failed, leaving VF disabled\n", + vf->vf_id); + mutex_unlock(&vf->cfg_lock); + continue; + } ice_vf_post_vsi_rebuild(vf); ice_eswitch_attach_vf(pf, vf); From c3cad2ae8088e384259c950ae92941318a5d9071 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:18 -0700 Subject: [PATCH 1026/1518] ice: fix infinite recursion in ice_cfg_tx_topo via ice_init_dev_hw [ Upstream commit 70ad216411e030f67b1743774e245601194aee6a ] On certain E810 configurations where firmware supports Tx scheduler topology switching (tx_sched_topo_comp_mode_en), ice_cfg_tx_topo() may need to apply a new 5-layer or 9-layer topology from the DDP package. If the AQ command to set the topology fails (e.g. due to invalid DDP data or firmware limitations), the global configuration lock must still be cleared via a CORER reset. Commit 86aae43f21cf ("ice: don't leave device non-functional if Tx scheduler config fails") correctly fixed this by refactoring ice_cfg_tx_topo() to always trigger CORER after acquiring the global lock and re-initialize hardware via ice_init_hw() afterwards. However, commit 8a37f9e2ff40 ("ice: move ice_deinit_dev() to the end of deinit paths") later moved ice_init_dev_hw() into ice_init_hw(), breaking the reinit path introduced by 86aae43f21cf. This creates an infinite recursive call chain: ice_init_hw() ice_init_dev_hw() ice_cfg_tx_topo() # topology change needed ice_deinit_hw() ice_init_hw() # reinit after CORER ice_init_dev_hw() # recurse ice_cfg_tx_topo() ... # stack overflow Fix by moving ice_init_dev_hw() back out of ice_init_hw() and calling it explicitly from ice_probe() and ice_devlink_reinit_up(). The third caller, ice_cfg_tx_topo(), intentionally does not need ice_init_dev_hw() during its reinit, it only needs the core HW reinitialization. This breaks the recursion cleanly without adding flags or guards. The deinit ordering changes from commit 8a37f9e2ff40 ("ice: move ice_deinit_dev() to the end of deinit paths") which fixed slow rmmod are preserved, only the init-side placement of ice_init_dev_hw() is reverted. Fixes: 8a37f9e2ff40 ("ice: move ice_deinit_dev() to the end of deinit paths") Signed-off-by: Petr Oros Reviewed-by: Paul Menzel Reviewed-by: Jacob Keller Reviewed-by: Aleksandr Loktionov Reviewed-by: Przemek Kitszel Tested-by: Alexander Nowlin Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-6-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/devlink/devlink.c | 2 ++ drivers/net/ethernet/intel/ice/ice_common.c | 2 -- drivers/net/ethernet/intel/ice/ice_main.c | 2 ++ 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 862ff1cdd46d6..839b7bfa19359 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1243,6 +1243,8 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) return err; } + ice_init_dev_hw(pf); + /* load MSI-X values */ ice_set_min_max_msix(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index c23a31ec3c413..4dcc3b41800b3 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1162,8 +1162,6 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; - ice_init_dev_hw(hw->back); - mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a4ae032f2161b..c064c3653c540 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5321,6 +5321,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return err; } + ice_init_dev_hw(pf); + adapter = ice_adapter_get(pdev); if (IS_ERR(adapter)) { err = PTR_ERR(adapter); From 0c56810ce1ba61bfec4e1dab65691aeb7fbe2671 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:19 -0700 Subject: [PATCH 1027/1518] ice: fix missing SMA pin initialization in DPLL subsystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 56a643aed0f0af5c29ebb4593d4917b78344dd48 ] The DPLL SMA/U.FL pin redesign introduced ice_dpll_sw_pin_frequency_get() which gates frequency reporting on the pin's active flag. This flag is determined by ice_dpll_sw_pins_update() from the PCA9575 GPIO expander state. Before the redesign, SMA pins were exposed as direct HW input/output pins and ice_dpll_frequency_get() returned the CGU frequency unconditionally — the PCA9575 state was never consulted. The PCA9575 powers on with all outputs high, setting ICE_SMA1_DIR_EN, ICE_SMA1_TX_EN, ICE_SMA2_DIR_EN and ICE_SMA2_TX_EN. Nothing in the driver writes the register during initialization, so ice_dpll_sw_pins_update() sees all pins as inactive and ice_dpll_sw_pin_frequency_get() permanently returns 0 Hz for every SW pin. Fix this by writing a default SMA configuration in ice_dpll_init_info_sw_pins(): clear all SMA bits, then set SMA1 and SMA2 as active inputs (DIR_EN=0) with U.FL1 output and U.FL2 input disabled. Each SMA/U.FL pair shares a physical signal path so only one pin per pair can be active at a time. U.FL pins still report frequency 0 after this fix: U.FL1 (output-only) is disabled by ICE_SMA1_TX_EN which keeps the TX output buffer off, and U.FL2 (input-only) is disabled by ICE_SMA2_UFL2_RX_DIS. They can be activated by changing the corresponding SMA pin direction via dpll netlink. Fixes: 2dd5d03c77e2 ("ice: redesign dpll sma/u.fl pins control") Signed-off-by: Petr Oros Reviewed-by: Ivan Vecera Reviewed-by: Arkadiusz Kubalewski Tested-by: Alexander Nowlin Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-7-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_dpll.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 53b54e395a2ed..c2ad39bfe177d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -3545,6 +3545,7 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) struct ice_dpll_pin *pin; u32 phase_adj_max, caps; int i, ret; + u8 data; if (pf->hw.device_id == ICE_DEV_ID_E810C_QSFP) input_idx_offset = ICE_E810_RCLK_PINS_NUM; @@ -3604,6 +3605,22 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) } ice_dpll_phase_range_set(&pin->prop.phase_range, phase_adj_max); } + + /* Initialize the SMA control register to a known-good default state. + * Without this write the PCA9575 GPIO expander retains its power-on + * default (all outputs high) which makes all SW pins appear inactive. + * Set SMA1 and SMA2 as active inputs, disable U.FL1 output and + * U.FL2 input. + */ + ret = ice_read_sma_ctrl(&pf->hw, &data); + if (ret) + return ret; + data &= ~ICE_ALL_SMA_MASK; + data |= ICE_SMA1_TX_EN | ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS; + ret = ice_write_sma_ctrl(&pf->hw, data); + if (ret) + return ret; + ret = ice_dpll_pin_state_update(pf, pin, ICE_DPLL_PIN_TYPE_SOFTWARE, NULL); if (ret) From 3b3aab57e33f9d07bc2583a62b17c1539dadc77a Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:20 -0700 Subject: [PATCH 1028/1518] ice: fix SMA and U.FL pin state changes affecting paired pin [ Upstream commit 6f9d8393c9f50fbc68b9c9e99f78ca5a7b43ff44 ] SMA and U.FL pins share physical signal paths in pairs (SMA1/U.FL1 and SMA2/U.FL2) controlled by the PCA9575 GPIO expander. Each pair can only have one active pin at a time: SMA1 output and U.FL1 output share the same CGU output, SMA2 input and U.FL2 input share the same CGU input. The PCA9575 register bits determine which connector in each pair owns the signal path. The driver does not account for this pairing in two places: ice_dpll_ufl_pin_state_set() modifies PCA9575 bits and disables the backing CGU pin without checking whether the U.FL pin is currently active. Disconnecting an already inactive U.FL pin flips bits that the paired SMA pin relies on, breaking its connection. ice_dpll_sma_direction_set() does not propagate direction changes to the paired U.FL pin. For SMA2/U.FL2 the ICE_SMA2_UFL2_RX_DIS bit is never managed, so U.FL2 stays disconnected after SMA2 switches to output. For both pairs the backing CGU pin of the U.FL side is never enabled when a direction change activates it, so userspace sees the pin as disconnected even though the routing is correct. Fix by guarding the U.FL disconnect path against inactive pins and by updating the paired U.FL pin fully on SMA direction changes: manage ICE_SMA2_UFL2_RX_DIS for the SMA2/U.FL2 pair and enable the backing CGU pin whenever the peer becomes active. Fixes: 2dd5d03c77e2 ("ice: redesign dpll sma/u.fl pins control") Signed-off-by: Petr Oros Tested-by: Alexander Nowlin Reviewed-by: Arkadiusz Kubalewski Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-8-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_dpll.c | 50 ++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index c2ad39bfe177d..3254be7b0dca8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1090,6 +1090,8 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, enum dpll_pin_direction direction, struct netlink_ext_ack *extack) { + struct ice_dplls *d = &p->pf->dplls; + struct ice_dpll_pin *peer; u8 data; int ret; @@ -1108,8 +1110,9 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, case ICE_DPLL_PIN_SW_2_IDX: if (direction == DPLL_PIN_DIRECTION_INPUT) { data &= ~ICE_SMA2_DIR_EN; + data |= ICE_SMA2_UFL2_RX_DIS; } else { - data &= ~ICE_SMA2_TX_EN; + data &= ~(ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS); data |= ICE_SMA2_DIR_EN; } break; @@ -1121,6 +1124,34 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, ret = ice_dpll_pin_state_update(p->pf, p, ICE_DPLL_PIN_TYPE_SOFTWARE, extack); + if (ret) + return ret; + + /* When a direction change activates the paired U.FL pin, enable + * its backing CGU pin so the pin reports as connected. Without + * this the U.FL routing is correct but the CGU pin stays disabled + * and userspace sees the pin as disconnected. Do not disable the + * backing pin when U.FL becomes inactive because the SMA pin may + * still be using it. + */ + peer = &d->ufl[p->idx]; + if (peer->active) { + struct ice_dpll_pin *target; + enum ice_dpll_pin_type type; + + if (peer->output) { + target = peer->output; + type = ICE_DPLL_PIN_TYPE_OUTPUT; + } else { + target = peer->input; + type = ICE_DPLL_PIN_TYPE_INPUT; + } + ret = ice_dpll_pin_enable(&p->pf->hw, target, + d->eec.dpll_idx, type, extack); + if (!ret) + ret = ice_dpll_pin_state_update(p->pf, target, + type, extack); + } return ret; } @@ -1172,6 +1203,14 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, data &= ~ICE_SMA1_MASK; enable = true; } else if (state == DPLL_PIN_STATE_DISCONNECTED) { + /* Skip if U.FL1 is not active, setting TX_EN + * while DIR_EN is set would also deactivate + * the paired SMA1 output. + */ + if (data & (ICE_SMA1_DIR_EN | ICE_SMA1_TX_EN)) { + ret = 0; + goto unlock; + } data |= ICE_SMA1_TX_EN; enable = false; } else { @@ -1186,6 +1225,15 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, data &= ~ICE_SMA2_UFL2_RX_DIS; enable = true; } else if (state == DPLL_PIN_STATE_DISCONNECTED) { + /* Skip if U.FL2 is not active, setting + * UFL2_RX_DIS could also disable the paired + * SMA2 input. + */ + if (!(data & ICE_SMA2_DIR_EN) || + (data & ICE_SMA2_UFL2_RX_DIS)) { + ret = 0; + goto unlock; + } data |= ICE_SMA2_UFL2_RX_DIS; enable = false; } else { From a723643ee05542c6544fbb7e23bc1981f67381aa Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:22 -0700 Subject: [PATCH 1029/1518] ice: fix missing dpll notifications for SW pins [ Upstream commit 1a41b58fd4dc80dca16c717e6e77c88b9d4e83a7 ] The SMA/U.FL pin redesign (commit 2dd5d03c77e2 ("ice: redesign dpll sma/u.fl pins control")) introduced software-controlled pins that wrap backing CGU input/output pins, but never updated the notification and data paths to propagate pin events to these SW wrappers. The periodic work sends dpll_pin_change_ntf() only for direct CGU input pins. SW pins that wrap these inputs never receive change or phase offset notifications, so userspace consumers such as synce4l monitoring SMA pins via dpll netlink never learn about state transitions or phase offset updates. Similarly, ice_dpll_phase_offset_get() reads the SW pin's own phase_offset field which is never updated; the PPS monitor writes to the backing CGU input's field instead. Fix by introducing ice_dpll_pin_ntf(), a wrapper around dpll_pin_change_ntf() that also notifies any registered SMA/U.FL pin whose backing CGU input matches. Replace all direct dpll_pin_change_ntf() calls in the periodic notification paths with this wrapper. Fix ice_dpll_phase_offset_get() to return the backing CGU input's phase_offset for input-direction SW pins. Fixes: 2dd5d03c77e2 ("ice: redesign dpll sma/u.fl pins control") Signed-off-by: Petr Oros Tested-by: Alexander Nowlin Reviewed-by: Arkadiusz Kubalewski Reviewed-by: Aleksandr Loktionov Reviewed-by: Ivan Vecera Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-10-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_dpll.c | 47 +++++++++++++++++------ 1 file changed, 36 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 3254be7b0dca8..baf492f5c4925 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1882,7 +1882,10 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, d->active_input == p->input->pin)) *phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; else if (d->phase_offset_monitor_period) - *phase_offset = p->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; + *phase_offset = (p->input && + p->direction == DPLL_PIN_DIRECTION_INPUT ? + p->input->phase_offset : + p->phase_offset) * ICE_DPLL_PHASE_OFFSET_FACTOR; else *phase_offset = 0; mutex_unlock(&pf->dplls.lock); @@ -2510,6 +2513,27 @@ static u64 ice_generate_clock_id(struct ice_pf *pf) return pci_get_dsn(pf->pdev); } +/** + * ice_dpll_pin_ntf - notify pin change including any SW pin wrappers + * @dplls: pointer to dplls struct + * @pin: the dpll_pin that changed + * + * Send a change notification for @pin and for any registered SMA/U.FL pin + * whose backing CGU input matches @pin. + */ +static void ice_dpll_pin_ntf(struct ice_dplls *dplls, struct dpll_pin *pin) +{ + dpll_pin_change_ntf(pin); + for (int i = 0; i < ICE_DPLL_PIN_SW_NUM; i++) { + if (dplls->sma[i].pin && dplls->sma[i].input && + dplls->sma[i].input->pin == pin) + dpll_pin_change_ntf(dplls->sma[i].pin); + if (dplls->ufl[i].pin && dplls->ufl[i].input && + dplls->ufl[i].input->pin == pin) + dpll_pin_change_ntf(dplls->ufl[i].pin); + } +} + /** * ice_dpll_notify_changes - notify dpll subsystem about changes * @d: pointer do dpll @@ -2518,6 +2542,7 @@ static u64 ice_generate_clock_id(struct ice_pf *pf) */ static void ice_dpll_notify_changes(struct ice_dpll *d) { + struct ice_dplls *dplls = &d->pf->dplls; bool pin_notified = false; if (d->prev_dpll_state != d->dpll_state) { @@ -2526,17 +2551,17 @@ static void ice_dpll_notify_changes(struct ice_dpll *d) } if (d->prev_input != d->active_input) { if (d->prev_input) - dpll_pin_change_ntf(d->prev_input); + ice_dpll_pin_ntf(dplls, d->prev_input); d->prev_input = d->active_input; if (d->active_input) { - dpll_pin_change_ntf(d->active_input); + ice_dpll_pin_ntf(dplls, d->active_input); pin_notified = true; } } if (d->prev_phase_offset != d->phase_offset) { d->prev_phase_offset = d->phase_offset; if (!pin_notified && d->active_input) - dpll_pin_change_ntf(d->active_input); + ice_dpll_pin_ntf(dplls, d->active_input); } } @@ -2565,6 +2590,7 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) /** * ice_dpll_pins_notify_mask - notify dpll subsystem about bulk pin changes + * @dplls: pointer to dplls struct * @pins: array of ice_dpll_pin pointers registered within dpll subsystem * @pin_num: number of pins * @phase_offset_ntf_mask: bitmask of pin indexes to notify @@ -2574,15 +2600,14 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) * * Context: Must be called while pf->dplls.lock is released. */ -static void ice_dpll_pins_notify_mask(struct ice_dpll_pin *pins, +static void ice_dpll_pins_notify_mask(struct ice_dplls *dplls, + struct ice_dpll_pin *pins, u8 pin_num, u32 phase_offset_ntf_mask) { - int i = 0; - - for (i = 0; i < pin_num; i++) - if (phase_offset_ntf_mask & (1 << i)) - dpll_pin_change_ntf(pins[i].pin); + for (int i = 0; i < pin_num; i++) + if (phase_offset_ntf_mask & BIT(i)) + ice_dpll_pin_ntf(dplls, pins[i].pin); } /** @@ -2758,7 +2783,7 @@ static void ice_dpll_periodic_work(struct kthread_work *work) ice_dpll_notify_changes(de); ice_dpll_notify_changes(dp); if (phase_offset_ntf) - ice_dpll_pins_notify_mask(d->inputs, d->num_inputs, + ice_dpll_pins_notify_mask(d, d->inputs, d->num_inputs, phase_offset_ntf); resched: From 8bcfd78bbc329cb7f1e5b35322ac979e7c1e18cc Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Tue, 3 Feb 2026 18:39:54 +0100 Subject: [PATCH 1030/1518] dpll: Allow associating dpll pin with a firmware node [ Upstream commit d0f4771e2befbe8de3a16a564c6bbd1d5502cec3 ] Extend the DPLL core to support associating a DPLL pin with a firmware node. This association is required to allow other subsystems (such as network drivers) to locate and request specific DPLL pins defined in the Device Tree or ACPI. * Add a .fwnode field to the struct dpll_pin * Introduce dpll_pin_fwnode_set() helper to allow the provider driver to associate a pin with a fwnode after the pin has been allocated * Introduce fwnode_dpll_pin_find() helper to allow consumers to search for a registered DPLL pin using its associated fwnode handle * Ensure the fwnode reference is properly released in dpll_pin_put() Reviewed-by: Aleksandr Loktionov Reviewed-by: Vadim Fedorenko Signed-off-by: Ivan Vecera Reviewed-by: Arkadiusz Kubalewski Link: https://patch.msgid.link/20260203174002.705176-2-ivecera@redhat.com Signed-off-by: Paolo Abeni Stable-dep-of: 9e5dead140af ("ice: add dpll peer notification for paired SMA and U.FL pins") Signed-off-by: Sasha Levin --- drivers/dpll/dpll_core.c | 49 ++++++++++++++++++++++++++++++++++++++++ drivers/dpll/dpll_core.h | 2 ++ include/linux/dpll.h | 11 +++++++++ 3 files changed, 62 insertions(+) diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 8879a72351561..f04ed7195cadd 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -10,6 +10,7 @@ #include #include +#include #include #include @@ -595,12 +596,60 @@ void dpll_pin_put(struct dpll_pin *pin) xa_destroy(&pin->parent_refs); xa_destroy(&pin->ref_sync_pins); dpll_pin_prop_free(&pin->prop); + fwnode_handle_put(pin->fwnode); kfree_rcu(pin, rcu); } mutex_unlock(&dpll_lock); } EXPORT_SYMBOL_GPL(dpll_pin_put); +/** + * dpll_pin_fwnode_set - set dpll pin firmware node reference + * @pin: pointer to a dpll pin + * @fwnode: firmware node handle + * + * Set firmware node handle for the given dpll pin. + */ +void dpll_pin_fwnode_set(struct dpll_pin *pin, struct fwnode_handle *fwnode) +{ + mutex_lock(&dpll_lock); + fwnode_handle_put(pin->fwnode); /* Drop fwnode previously set */ + pin->fwnode = fwnode_handle_get(fwnode); + mutex_unlock(&dpll_lock); +} +EXPORT_SYMBOL_GPL(dpll_pin_fwnode_set); + +/** + * fwnode_dpll_pin_find - find dpll pin by firmware node reference + * @fwnode: reference to firmware node + * + * Get existing object of a pin that is associated with given firmware node + * reference. + * + * Context: Acquires a lock (dpll_lock) + * Return: + * * valid dpll_pin pointer on success + * * NULL when no such pin exists + */ +struct dpll_pin *fwnode_dpll_pin_find(struct fwnode_handle *fwnode) +{ + struct dpll_pin *pin, *ret = NULL; + unsigned long index; + + mutex_lock(&dpll_lock); + xa_for_each(&dpll_pin_xa, index, pin) { + if (pin->fwnode == fwnode) { + ret = pin; + refcount_inc(&ret->refcount); + break; + } + } + mutex_unlock(&dpll_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(fwnode_dpll_pin_find); + static int __dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, const struct dpll_pin_ops *ops, void *priv, void *cookie) diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h index 8ce969bbeb64e..d3e17ff0ecef0 100644 --- a/drivers/dpll/dpll_core.h +++ b/drivers/dpll/dpll_core.h @@ -42,6 +42,7 @@ struct dpll_device { * @pin_idx: index of a pin given by dev driver * @clock_id: clock_id of creator * @module: module of creator + * @fwnode: optional reference to firmware node * @dpll_refs: hold referencees to dplls pin was registered with * @parent_refs: hold references to parent pins pin was registered with * @ref_sync_pins: hold references to pins for Reference SYNC feature @@ -54,6 +55,7 @@ struct dpll_pin { u32 pin_idx; u64 clock_id; struct module *module; + struct fwnode_handle *fwnode; struct xarray dpll_refs; struct xarray parent_refs; struct xarray ref_sync_pins; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 562f520b23c27..f0c31a111c304 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -16,6 +16,7 @@ struct dpll_device; struct dpll_pin; struct dpll_pin_esync; +struct fwnode_handle; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, @@ -173,6 +174,8 @@ void dpll_netdev_pin_clear(struct net_device *dev); size_t dpll_netdev_pin_handle_size(const struct net_device *dev); int dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev); + +struct dpll_pin *fwnode_dpll_pin_find(struct fwnode_handle *fwnode); #else static inline void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { } @@ -188,6 +191,12 @@ dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev) { return 0; } + +static inline struct dpll_pin * +fwnode_dpll_pin_find(struct fwnode_handle *fwnode) +{ + return NULL; +} #endif struct dpll_device * @@ -213,6 +222,8 @@ void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, void dpll_pin_put(struct dpll_pin *pin); +void dpll_pin_fwnode_set(struct dpll_pin *pin, struct fwnode_handle *fwnode); + int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, const struct dpll_pin_ops *ops, void *priv); From 47e53940451c977313c4660cbc880904ef3fd8f1 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Tue, 3 Feb 2026 18:39:56 +0100 Subject: [PATCH 1031/1518] dpll: Add notifier chain for dpll events [ Upstream commit 2be467588d6bc6ec5988fc254e62a44b865912a0 ] Currently, the DPLL subsystem reports events (creation, deletion, changes) to userspace via Netlink. However, there is no mechanism for other kernel components to be notified of these events directly. Add a raw notifier chain to the DPLL core protected by dpll_lock. This allows other kernel subsystems or drivers to register callbacks and receive notifications when DPLL devices or pins are created, deleted, or modified. Define the following: - Registration helpers: {,un}register_dpll_notifier() - Event types: DPLL_DEVICE_CREATED, DPLL_PIN_CREATED, etc. - Context structures: dpll_{device,pin}_notifier_info to pass relevant data to the listeners. The notification chain is invoked alongside the existing Netlink event generation to ensure in-kernel listeners are kept in sync with the subsystem state. Reviewed-by: Vadim Fedorenko Co-developed-by: Ivan Vecera Signed-off-by: Ivan Vecera Signed-off-by: Petr Oros Reviewed-by: Arkadiusz Kubalewski Reviewed-by: Aleksandr Loktionov Link: https://patch.msgid.link/20260203174002.705176-4-ivecera@redhat.com Signed-off-by: Paolo Abeni Stable-dep-of: 9e5dead140af ("ice: add dpll peer notification for paired SMA and U.FL pins") Signed-off-by: Sasha Levin --- drivers/dpll/dpll_core.c | 57 +++++++++++++++++++++++++++++++++++++ drivers/dpll/dpll_core.h | 4 +++ drivers/dpll/dpll_netlink.c | 6 ++++ include/linux/dpll.h | 29 +++++++++++++++++++ 4 files changed, 96 insertions(+) diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index f04ed7195cadd..b05fe2ba46d91 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -23,6 +23,8 @@ DEFINE_MUTEX(dpll_lock); DEFINE_XARRAY_FLAGS(dpll_device_xa, XA_FLAGS_ALLOC); DEFINE_XARRAY_FLAGS(dpll_pin_xa, XA_FLAGS_ALLOC); +static RAW_NOTIFIER_HEAD(dpll_notifier_chain); + static u32 dpll_device_xa_id; static u32 dpll_pin_xa_id; @@ -46,6 +48,39 @@ struct dpll_pin_registration { void *cookie; }; +static int call_dpll_notifiers(unsigned long action, void *info) +{ + lockdep_assert_held(&dpll_lock); + return raw_notifier_call_chain(&dpll_notifier_chain, action, info); +} + +void dpll_device_notify(struct dpll_device *dpll, unsigned long action) +{ + struct dpll_device_notifier_info info = { + .dpll = dpll, + .id = dpll->id, + .idx = dpll->device_idx, + .clock_id = dpll->clock_id, + .type = dpll->type, + }; + + call_dpll_notifiers(action, &info); +} + +void dpll_pin_notify(struct dpll_pin *pin, unsigned long action) +{ + struct dpll_pin_notifier_info info = { + .pin = pin, + .id = pin->id, + .idx = pin->pin_idx, + .clock_id = pin->clock_id, + .fwnode = pin->fwnode, + .prop = &pin->prop, + }; + + call_dpll_notifiers(action, &info); +} + struct dpll_device *dpll_device_get_by_id(int id) { if (xa_get_mark(&dpll_device_xa, id, DPLL_REGISTERED)) @@ -539,6 +574,28 @@ void dpll_netdev_pin_clear(struct net_device *dev) } EXPORT_SYMBOL(dpll_netdev_pin_clear); +int register_dpll_notifier(struct notifier_block *nb) +{ + int ret; + + mutex_lock(&dpll_lock); + ret = raw_notifier_chain_register(&dpll_notifier_chain, nb); + mutex_unlock(&dpll_lock); + return ret; +} +EXPORT_SYMBOL_GPL(register_dpll_notifier); + +int unregister_dpll_notifier(struct notifier_block *nb) +{ + int ret; + + mutex_lock(&dpll_lock); + ret = raw_notifier_chain_unregister(&dpll_notifier_chain, nb); + mutex_unlock(&dpll_lock); + return ret; +} +EXPORT_SYMBOL_GPL(unregister_dpll_notifier); + /** * dpll_pin_get - find existing or create new dpll pin * @clock_id: clock_id of creator diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h index d3e17ff0ecef0..b7b4bb251f739 100644 --- a/drivers/dpll/dpll_core.h +++ b/drivers/dpll/dpll_core.h @@ -91,4 +91,8 @@ struct dpll_pin_ref *dpll_xa_ref_dpll_first(struct xarray *xa_refs); extern struct xarray dpll_device_xa; extern struct xarray dpll_pin_xa; extern struct mutex dpll_lock; + +void dpll_device_notify(struct dpll_device *dpll, unsigned long action); +void dpll_pin_notify(struct dpll_pin *pin, unsigned long action); + #endif diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 64944f601ee5a..fe9c3d9073f0f 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -742,17 +742,20 @@ dpll_device_event_send(enum dpll_cmd event, struct dpll_device *dpll) int dpll_device_create_ntf(struct dpll_device *dpll) { + dpll_device_notify(dpll, DPLL_DEVICE_CREATED); return dpll_device_event_send(DPLL_CMD_DEVICE_CREATE_NTF, dpll); } int dpll_device_delete_ntf(struct dpll_device *dpll) { + dpll_device_notify(dpll, DPLL_DEVICE_DELETED); return dpll_device_event_send(DPLL_CMD_DEVICE_DELETE_NTF, dpll); } static int __dpll_device_change_ntf(struct dpll_device *dpll) { + dpll_device_notify(dpll, DPLL_DEVICE_CHANGED); return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll); } @@ -810,16 +813,19 @@ dpll_pin_event_send(enum dpll_cmd event, struct dpll_pin *pin) int dpll_pin_create_ntf(struct dpll_pin *pin) { + dpll_pin_notify(pin, DPLL_PIN_CREATED); return dpll_pin_event_send(DPLL_CMD_PIN_CREATE_NTF, pin); } int dpll_pin_delete_ntf(struct dpll_pin *pin) { + dpll_pin_notify(pin, DPLL_PIN_DELETED); return dpll_pin_event_send(DPLL_CMD_PIN_DELETE_NTF, pin); } int __dpll_pin_change_ntf(struct dpll_pin *pin) { + dpll_pin_notify(pin, DPLL_PIN_CHANGED); return dpll_pin_event_send(DPLL_CMD_PIN_CHANGE_NTF, pin); } diff --git a/include/linux/dpll.h b/include/linux/dpll.h index f0c31a111c304..34b005bb4df6f 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -11,6 +11,7 @@ #include #include #include +#include #include struct dpll_device; @@ -167,6 +168,30 @@ struct dpll_pin_properties { u32 phase_gran; }; +#define DPLL_DEVICE_CREATED 1 +#define DPLL_DEVICE_DELETED 2 +#define DPLL_DEVICE_CHANGED 3 +#define DPLL_PIN_CREATED 4 +#define DPLL_PIN_DELETED 5 +#define DPLL_PIN_CHANGED 6 + +struct dpll_device_notifier_info { + struct dpll_device *dpll; + u32 id; + u32 idx; + u64 clock_id; + enum dpll_type type; +}; + +struct dpll_pin_notifier_info { + struct dpll_pin *pin; + u32 id; + u32 idx; + u64 clock_id; + const struct fwnode_handle *fwnode; + const struct dpll_pin_properties *prop; +}; + #if IS_ENABLED(CONFIG_DPLL) void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); void dpll_netdev_pin_clear(struct net_device *dev); @@ -237,4 +262,8 @@ int dpll_device_change_ntf(struct dpll_device *dpll); int dpll_pin_change_ntf(struct dpll_pin *pin); +int register_dpll_notifier(struct notifier_block *nb); + +int unregister_dpll_notifier(struct notifier_block *nb); + #endif From f5f1b59bdb129d3abd0d413d256dacf0a6b3e28c Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Mon, 27 Apr 2026 22:22:21 -0700 Subject: [PATCH 1032/1518] dpll: export __dpll_pin_change_ntf() for use under dpll_lock [ Upstream commit 620055cb1036a6125fd912e7a14b47a6572b809b ] Export __dpll_pin_change_ntf() so that drivers can send pin change notifications from within pin callbacks, which are already called under dpll_lock. Using dpll_pin_change_ntf() in that context would deadlock. Add lockdep_assert_held() to catch misuse without the lock held. Acked-by: Vadim Fedorenko Signed-off-by: Ivan Vecera Signed-off-by: Petr Oros Tested-by: Alexander Nowlin Reviewed-by: Arkadiusz Kubalewski Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-9-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Stable-dep-of: 9e5dead140af ("ice: add dpll peer notification for paired SMA and U.FL pins") Signed-off-by: Sasha Levin --- drivers/dpll/dpll_netlink.c | 10 ++++++++++ drivers/dpll/dpll_netlink.h | 2 -- include/linux/dpll.h | 1 + 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index fe9c3d9073f0f..de8b065280d15 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -823,11 +823,21 @@ int dpll_pin_delete_ntf(struct dpll_pin *pin) return dpll_pin_event_send(DPLL_CMD_PIN_DELETE_NTF, pin); } +/** + * __dpll_pin_change_ntf - notify that the pin has been changed + * @pin: registered pin pointer + * + * Context: caller must hold dpll_lock. Suitable for use inside pin + * callbacks which are already invoked under dpll_lock. + * Return: 0 if succeeds, error code otherwise. + */ int __dpll_pin_change_ntf(struct dpll_pin *pin) { + lockdep_assert_held(&dpll_lock); dpll_pin_notify(pin, DPLL_PIN_CHANGED); return dpll_pin_event_send(DPLL_CMD_PIN_CHANGE_NTF, pin); } +EXPORT_SYMBOL_GPL(__dpll_pin_change_ntf); /** * dpll_pin_change_ntf - notify that the pin has been changed diff --git a/drivers/dpll/dpll_netlink.h b/drivers/dpll/dpll_netlink.h index dd28b56d27c56..a9cfd55f57fc4 100644 --- a/drivers/dpll/dpll_netlink.h +++ b/drivers/dpll/dpll_netlink.h @@ -11,5 +11,3 @@ int dpll_device_delete_ntf(struct dpll_device *dpll); int dpll_pin_create_ntf(struct dpll_pin *pin); int dpll_pin_delete_ntf(struct dpll_pin *pin); - -int __dpll_pin_change_ntf(struct dpll_pin *pin); diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 34b005bb4df6f..480ea3cbe709b 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -260,6 +260,7 @@ int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin, int dpll_device_change_ntf(struct dpll_device *dpll); +int __dpll_pin_change_ntf(struct dpll_pin *pin); int dpll_pin_change_ntf(struct dpll_pin *pin); int register_dpll_notifier(struct notifier_block *nb); From f5c5692a61f7d5bbc47086870c1660a87f2df29c Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 27 Apr 2026 22:22:23 -0700 Subject: [PATCH 1033/1518] ice: add dpll peer notification for paired SMA and U.FL pins [ Upstream commit 9e5dead140af10e8b5f975b8f04e46197d48d274 ] SMA and U.FL pins share physical signal paths in pairs (SMA1/U.FL1 and SMA2/U.FL2). When one pin's state changes via a PCA9575 GPIO write, the paired pin's state also changes, but no notification is sent for the peer pin. Userspace consumers monitoring the peer via dpll netlink subscribe never learn about the update. Add ice_dpll_sw_pin_notify_peer() which sends a change notification for the paired SW pin. Call it from ice_dpll_pin_sma_direction_set(), ice_dpll_sma_pin_state_set(), and ice_dpll_ufl_pin_state_set() after pf->dplls.lock is released. Use __dpll_pin_change_ntf() because dpll_lock is still held by the dpll netlink layer (dpll_pin_pre_doit). Fixes: 2dd5d03c77e2 ("ice: redesign dpll sma/u.fl pins control") Signed-off-by: Petr Oros Tested-by: Alexander Nowlin Reviewed-by: Arkadiusz Kubalewski Reviewed-by: Aleksandr Loktionov Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260427-jk-iwl-net-petr-oros-fixes-v1-11-cdcb48303fd8@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_dpll.c | 32 +++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index baf492f5c4925..14048ac5eff56 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1073,6 +1073,32 @@ ice_dpll_input_state_get(const struct dpll_pin *pin, void *pin_priv, extack, ICE_DPLL_PIN_TYPE_INPUT); } +/** + * ice_dpll_sw_pin_notify_peer - notify the paired SW pin after a state change + * @d: pointer to dplls struct + * @changed: the SW pin that was explicitly changed (already notified by dpll core) + * + * SMA and U.FL pins share physical signal paths in pairs (SMA1/U.FL1 and + * SMA2/U.FL2). When one pin's routing changes via the PCA9575 GPIO + * expander, the paired pin's state may also change. Send a change + * notification for the peer pin so userspace consumers monitoring the + * peer via dpll netlink learn about the update. + * + * Context: Called from dpll_pin_ops callbacks after pf->dplls.lock is + * released. Uses __dpll_pin_change_ntf() because dpll_lock is + * still held by the dpll netlink layer. + */ +static void ice_dpll_sw_pin_notify_peer(struct ice_dplls *d, + struct ice_dpll_pin *changed) +{ + struct ice_dpll_pin *peer; + + peer = (changed >= d->sma && changed < d->sma + ICE_DPLL_PIN_SW_NUM) ? + &d->ufl[changed->idx] : &d->sma[changed->idx]; + if (peer->pin) + __dpll_pin_change_ntf(peer->pin); +} + /** * ice_dpll_sma_direction_set - set direction of SMA pin * @p: pointer to a pin @@ -1263,6 +1289,8 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, unlock: mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, p); return ret; } @@ -1381,6 +1409,8 @@ ice_dpll_sma_pin_state_set(const struct dpll_pin *pin, void *pin_priv, unlock: mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, sma); return ret; } @@ -1576,6 +1606,8 @@ ice_dpll_pin_sma_direction_set(const struct dpll_pin *pin, void *pin_priv, mutex_lock(&pf->dplls.lock); ret = ice_dpll_sma_direction_set(p, direction, extack); mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, p); return ret; } From 9c54e76f8d6eb11735918777ef0e0509e089557d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 28 Apr 2026 16:15:59 -0700 Subject: [PATCH 1034/1518] net: tls: fix strparser anchor skb leak on offload RX setup failure [ Upstream commit 58689498ca3384851145a754dbb1d8ed1cf9fb54 ] When tls_set_device_offload_rx() fails at tls_dev_add(), the error path calls tls_sw_free_resources_rx() to clean up the SW context that was initialized by tls_set_sw_offload(). This function calls tls_sw_release_resources_rx() (which stops the strparser via tls_strp_stop()) and tls_sw_free_ctx_rx() (which kfrees the context), but never frees the anchor skb that was allocated by alloc_skb(0) in tls_strp_init(). Note that tls_sw_free_resources_rx() is exclusively used for this "failed to start offload" code path, there's no other caller. The leak did not exist before commit 84c61fe1a75b ("tls: rx: do not use the standard strparser"), because the standard strparser doesn't try to pre-allocate an skb. The normal close path in tls_sk_proto_close() handles cleanup by calling tls_sw_strparser_done() (which calls tls_strp_done()) after dropping the socket lock, because tls_strp_done() does cancel_work_sync() and the strparser work handler takes the socket lock. Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Signed-off-by: Jakub Kicinski Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20260428231559.1358502-1-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/tls/tls.h | 1 + net/tls/tls_strp.c | 6 ++++++ net/tls/tls_sw.c | 4 ++++ 3 files changed, 11 insertions(+) diff --git a/net/tls/tls.h b/net/tls/tls.h index 2f86baeb71fcb..a1d8467bece33 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -188,6 +188,7 @@ int tls_strp_dev_init(void); void tls_strp_dev_exit(void); void tls_strp_done(struct tls_strparser *strp); +void __tls_strp_done(struct tls_strparser *strp); void tls_strp_stop(struct tls_strparser *strp); int tls_strp_init(struct tls_strparser *strp, struct sock *sk); void tls_strp_data_ready(struct tls_strparser *strp); diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 98e12f0ff57e5..c72e883176273 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -624,6 +624,12 @@ void tls_strp_done(struct tls_strparser *strp) WARN_ON(!strp->stopped); cancel_work_sync(&strp->work); + __tls_strp_done(strp); +} + +/* For setup error paths where the strparser was initialized but never armed. */ +void __tls_strp_done(struct tls_strparser *strp) +{ tls_strp_anchor_free(strp); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 16aaf41a8cc09..f2ea190777f0b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2625,8 +2625,12 @@ void tls_sw_free_ctx_rx(struct tls_context *tls_ctx) void tls_sw_free_resources_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx; + + ctx = tls_sw_ctx_rx(tls_ctx); tls_sw_release_resources_rx(sk); + __tls_strp_done(&ctx->strp); tls_sw_free_ctx_rx(tls_ctx); } From 3f4a3f740c2337a5e9ad1a49726f62045a7f7c1e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 29 Apr 2026 09:48:17 +0300 Subject: [PATCH 1035/1518] sfc: fix error code in efx_devlink_info_running_versions() [ Upstream commit 051ffb001b8a232cfa6e72f38bb5f51c4270a60b ] Return -EIO if efx_mcdi_rpc() doesn't return enough space. Fixes: 14743ddd2495 ("sfc: add devlink info support for ef100") Signed-off-by: Dan Carpenter Reviewed-by: Edward Cree Link: https://patch.msgid.link/afGpsbLRHL4_H0KS@stanley.mountain Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/efx_devlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c index d842c60dfc100..e5c6f81af48be 100644 --- a/drivers/net/ethernet/sfc/efx_devlink.c +++ b/drivers/net/ethernet/sfc/efx_devlink.c @@ -531,7 +531,7 @@ static int efx_devlink_info_running_versions(struct efx_nic *efx, if (rc || outlength < MC_CMD_GET_VERSION_OUT_LEN) { netif_err(efx, drv, efx->net_dev, "mcdi MC_CMD_GET_VERSION failed\n"); - return rc; + return rc ?: -EIO; } /* Handle previous output */ From 5704a90c09708040067abcbd2d837865ec6a49a5 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 29 Apr 2026 09:39:11 +0200 Subject: [PATCH 1036/1518] net/sched: cls_flower: revert unintended changes [ Upstream commit 1e01abec856593e02cd69fd95b784c10dd46880c ] While applying the blamed commit 4ca07b9239bd ("net: mctp i2c: check length before marking flow active"), I unintentionally included unrelated and unacceptable changes. Revert them. Fixes: 4ca07b9239bd ("net: mctp i2c: check length before marking flow active") Reported-by: Jeremy Kerr Closes: https://lore.kernel.org/netdev/bd8704fe0bd53e278add5cde4873256656623e2e.camel@codeconstruct.com.au/ Signed-off-by: Paolo Abeni Link: https://patch.msgid.link/043026a53ff84da88b17648c4b0d17f0331749cb.1777447863.git.pabeni@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/cls_flower.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f3af0ac892a86..099ff6a3e1f51 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -560,7 +560,6 @@ static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { struct cls_fl_head *head = fl_head_dereference(tp); - struct fl_flow_mask *mask; *last = false; @@ -577,12 +576,11 @@ static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, list_del_rcu(&f->list); spin_unlock(&tp->lock); - mask = f->mask; + *last = fl_mask_put(head, f->mask); if (!tc_skip_hw(f->flags)) fl_hw_destroy_filter(tp, f, rtnl_held, extack); tcf_unbind_filter(tp, &f->res); __fl_put(f); - *last = fl_mask_put(head, mask); return 0; } From b9d854388988ccaf0d3d4f674cffd731d246ad0c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 29 Apr 2026 15:30:10 +0100 Subject: [PATCH 1037/1518] kselftest/arm64: Include for user_gcs definition [ Upstream commit bb7235e226888607e6aac1288062fcb1ac105589 ] kselftest includes kernel uAPI headers with option: -isystem $(top_srcdir)/usr/include Include in libc-gcs.c for the definition of struct user_gcs from the uAPI headers, and remove the redundant definition in gcs-util.h. This fixes a compilation error on systems where the toolchain defines NT_ARM_GCS. Fixes: a505a52b4e29 ("kselftest/arm64: Add a GCS test program built with the system libc") Signed-off-by: Leo Yan Reviewed-by: Mark Brown Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- tools/testing/selftests/arm64/gcs/gcs-util.h | 6 ------ tools/testing/selftests/arm64/gcs/libc-gcs.c | 1 + 2 files changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/testing/selftests/arm64/gcs/gcs-util.h b/tools/testing/selftests/arm64/gcs/gcs-util.h index c99a6b39ac147..7a81bb07ed4b8 100644 --- a/tools/testing/selftests/arm64/gcs/gcs-util.h +++ b/tools/testing/selftests/arm64/gcs/gcs-util.h @@ -18,12 +18,6 @@ #ifndef NT_ARM_GCS #define NT_ARM_GCS 0x410 - -struct user_gcs { - __u64 features_enabled; - __u64 features_locked; - __u64 gcspr_el0; -}; #endif /* Shadow Stack/Guarded Control Stack interface */ diff --git a/tools/testing/selftests/arm64/gcs/libc-gcs.c b/tools/testing/selftests/arm64/gcs/libc-gcs.c index 17b2fabfec386..72e82bfbecc99 100644 --- a/tools/testing/selftests/arm64/gcs/libc-gcs.c +++ b/tools/testing/selftests/arm64/gcs/libc-gcs.c @@ -16,6 +16,7 @@ #include #include +#include #include From dcb89deed40ba55ff7020061712fdabf098cc2cc Mon Sep 17 00:00:00 2001 From: Zhaoyang Huang Date: Thu, 30 Apr 2026 16:58:08 +0800 Subject: [PATCH 1038/1518] arm64: Reserve an extra page for early kernel mapping [ Upstream commit 4d8e74ad4585672489da6145b3328d415f50db82 ] The final part of [data, end) segment may overflow into the next page of init_pg_end[1] which is the gap page before early_init_stack[2]: [1] crash_arm64_v9.0.1> vtop ffffffed00601000 VIRTUAL PHYSICAL ffffffed00601000 83401000 PAGE DIRECTORY: ffffffecffd62000 PGD: ffffffecffd62da0 => 10000000833fb003 PMD: ffffff80033fb018 => 10000000833fe003 PTE: ffffff80033fe008 => 68000083401f03 PAGE: 83401000 PTE PHYSICAL FLAGS 68000083401f03 83401000 (VALID|SHARED|AF|NG|PXN|UXN) PAGE PHYSICAL MAPPING INDEX CNT FLAGS fffffffec00d0040 83401000 0 0 1 4000 reserved [2] ffffffed002c8000 (r) __pi__data ffffffed0054e000 (d) __pi___bss_start ffffffed005f5000 (b) __pi_init_pg_dir ffffffed005fe000 (b) __pi_init_pg_end ffffffed005ff000 (B) early_init_stack ffffffed00608000 (b) __pi__end For 4K pages, the early kernel mapping may use 2MB block entries but the kernel segments are only 64KB aligned. Segment boundaries that fall within a 2MB block therefore require a PTE table so that different attributes can be applied on either side of the boundary. KERNEL_SEGMENT_COUNT still correctly counts the five permanent kernel VMAs registered by declare_kernel_vmas(). However, since commit 5973a62efa34 ("arm64: map [_text, _stext) virtual address range non-executable+read-only"), the early mapper also maps [_text, _stext) separately from [_stext, _etext). This adds one more early-only split and can require one more page-table page than the existing EARLY_SEGMENT_EXTRA_PAGES allowance reserves. Increase the 4K-page early mapping allowance by one page to cover that additional split. Fixes: 5973a62efa34 ("arm64: map [_text, _stext) virtual address range non-executable+read-only") Assisted-by: TRAE:GLM-5.1 Suggested-by: Ard Biesheuvel Signed-off-by: Zhaoyang Huang [catalin.marinas@arm.com: rewrote part of the commit log] [catalin.marinas@arm.com: expanded the code comment] Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/include/asm/kernel-pgtable.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 74a4f738c5f52..229ee7976f693 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -68,7 +68,12 @@ #define KERNEL_SEGMENT_COUNT 5 #if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN -#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1) +/* + * KERNEL_SEGMENT_COUNT counts the permanent kernel VMAs. The early mapping + * has one additional split, [_text, _stext). Reserve one more page for the + * SWAPPER_BLOCK_SIZE-unaligned boundaries. + */ +#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 2) /* * The initial ID map consists of the kernel image, mapped as two separate * segments, and may appear misaligned wrt the swapper block size. This means From 1dcd36420af2da5bd59306dba9caf78e3d248b1d Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 1 May 2026 12:41:23 -0700 Subject: [PATCH 1039/1518] futex: Drop CLONE_THREAD requirement for private default hash alloc [ Upstream commit ee9dce44362b2d8132c32964656ab6dff7dfbc6a ] Currently need_futex_hash_allocate_default() depends on strict pthread semantics, abusing CLONE_THREAD. This breaks the non-concurrency assumptions when doing the mm->futex_ref pcpu allocations, leading to bugs[0] when sharing the mm in other ways; ie: BUG: KASAN: slab-use-after-free in futex_hash_put ... where the +1 bias can end up on a percpu counter that mm->futex_ref no longer points at. Loosen the check to cover any CLONE_VM clone, except vfork(). Excluding vfork keeps the existing paths untouched (no overhead), and we can't race in the first place: either the parent is suspended and the child runs alone, or mm->futex_ref is already allocated from an earlier CLONE_VM. Link: https://lore.kernel.org/all/CAL_bE8LsmCQ-FAtYDuwbJhOkt9p2wwYQwAbMh=PifC=VsiBM6A@mail.gmail.com/ [0] Fixes: d9b05321e21e ("futex: Move futex_hash_free() back to __mmput()") Reported-by: Yiming Qian Signed-off-by: Davidlohr Bueso Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- kernel/fork.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 3ad76c2cf5af5..1215d3f52c6d2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1911,9 +1911,11 @@ static void rv_task_fork(struct task_struct *p) static bool need_futex_hash_allocate_default(u64 clone_flags) { - if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM)) - return false; - return true; + /* + * Allocate a default futex hash for any sibling that will + * share the parent's mm, except vfork. + */ + return (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM; } /* @@ -2296,10 +2298,6 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cancel_cgroup; - /* - * Allocate a default futex hash for the user process once the first - * thread spawns. - */ if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) From d66dc9505935c4c2c0b349407b37066dcbed48a8 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 18 May 2026 11:13:17 -0400 Subject: [PATCH 1040/1518] Revert "pseries/papr-hvpipe: Fix race with interrupt handler" This reverts commit 6542e180fa6e1c701aba446a555c65556e6fd1a5. Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/papr-hvpipe.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c index a238db095b4ec..3d8672642c251 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.c +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c @@ -449,14 +449,13 @@ static int papr_hvpipe_handle_release(struct inode *inode, struct file *file) { struct hvpipe_source_info *src_info; - unsigned long flags; /* * Hold the lock, remove source from src_list, reset the * hvpipe status and release the lock to prevent any race * with message event IRQ. */ - spin_lock_irqsave(&hvpipe_src_list_lock, flags); + spin_lock(&hvpipe_src_list_lock); src_info = file->private_data; list_del(&src_info->list); file->private_data = NULL; @@ -467,10 +466,10 @@ static int papr_hvpipe_handle_release(struct inode *inode, */ if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) { src_info->hvpipe_status = 0; - spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + spin_unlock(&hvpipe_src_list_lock); hvpipe_rtas_recv_msg(NULL, 0); } else - spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + spin_unlock(&hvpipe_src_list_lock); kfree(src_info); return 0; @@ -486,21 +485,20 @@ static const struct file_operations papr_hvpipe_handle_ops = { static int papr_hvpipe_dev_create_handle(u32 srcID) { struct hvpipe_source_info *src_info __free(kfree) = NULL; - unsigned long flags; - spin_lock_irqsave(&hvpipe_src_list_lock, flags); + spin_lock(&hvpipe_src_list_lock); /* * Do not allow more than one process communicates with * each source. */ src_info = hvpipe_find_source(srcID); if (src_info) { - spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + spin_unlock(&hvpipe_src_list_lock); pr_err("pid(%d) is already using the source(%d)\n", src_info->tsk->pid, srcID); return -EALREADY; } - spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + spin_unlock(&hvpipe_src_list_lock); src_info = kzalloc(sizeof(*src_info), GFP_KERNEL_ACCOUNT); if (!src_info) @@ -517,18 +515,18 @@ static int papr_hvpipe_dev_create_handle(u32 srcID) return fdf.err; retain_and_null_ptr(src_info); - spin_lock_irqsave(&hvpipe_src_list_lock, flags); + spin_lock(&hvpipe_src_list_lock); /* * If two processes are executing ioctl() for the same * source ID concurrently, prevent the second process to * acquire FD. */ if (hvpipe_find_source(srcID)) { - spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + spin_unlock(&hvpipe_src_list_lock); return -EALREADY; } list_add(&src_info->list, &hvpipe_src_list); - spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + spin_unlock(&hvpipe_src_list_lock); return fd_publish(fdf); } From 735439394dde8462f9b50566727fbe333beaadaf Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 18 May 2026 11:13:17 -0400 Subject: [PATCH 1041/1518] Revert "papr-hvpipe: convert papr_hvpipe_dev_create_handle() to FD_PREPARE()" This reverts commit 09c15bbbed533903e600660ea09098b3b0524f48. Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/papr-hvpipe.c | 39 +++++++++++++++----- 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c index 3d8672642c251..431f6a3da4c5a 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.c +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c @@ -484,7 +484,10 @@ static const struct file_operations papr_hvpipe_handle_ops = { static int papr_hvpipe_dev_create_handle(u32 srcID) { - struct hvpipe_source_info *src_info __free(kfree) = NULL; + struct hvpipe_source_info *src_info; + struct file *file; + long err; + int fd; spin_lock(&hvpipe_src_list_lock); /* @@ -508,13 +511,20 @@ static int papr_hvpipe_dev_create_handle(u32 srcID) src_info->tsk = current; init_waitqueue_head(&src_info->recv_wqh); - FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC, - anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops, - (void *)src_info, O_RDWR)); - if (fdf.err) - return fdf.err; + fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = fd; + goto free_buf; + } + + file = anon_inode_getfile("[papr-hvpipe]", + &papr_hvpipe_handle_ops, (void *)src_info, + O_RDWR); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto free_fd; + } - retain_and_null_ptr(src_info); spin_lock(&hvpipe_src_list_lock); /* * If two processes are executing ioctl() for the same @@ -523,11 +533,22 @@ static int papr_hvpipe_dev_create_handle(u32 srcID) */ if (hvpipe_find_source(srcID)) { spin_unlock(&hvpipe_src_list_lock); - return -EALREADY; + err = -EALREADY; + goto free_file; } list_add(&src_info->list, &hvpipe_src_list); spin_unlock(&hvpipe_src_list_lock); - return fd_publish(fdf); + + fd_install(fd, file); + return fd; + +free_file: + fput(file); +free_fd: + put_unused_fd(fd); +free_buf: + kfree(src_info); + return err; } /* From 22f72b1dccfe98e886cfddc5e6598d16d6613f39 Mon Sep 17 00:00:00 2001 From: Samiullah Khawaja Date: Tue, 5 May 2026 23:43:27 +0000 Subject: [PATCH 1042/1518] PCI: Initialize temporary device in new_id_store() [ Upstream commit f45a49a2380a47332817b7248c61a0ebbc6f0d00 ] When setting new_id of a PCI device driver using sysfs a lockdep splat occurs. This is because new_id_store() builds a temporary pci_dev for pci_match_device(), which calls device_match_driver_override(). That depends on the driver_override.lock added by cb3d1049f4ea ("driver core: generalize driver_override in struct device"). The new driver_override.lock was not initialized in the temporary pci_dev, resulting in this lockdep splat. Initialize the temporary pci_dev to fix this. Repro: Build with CONFIG_LOCKDEP=y, boot with QEMU, and add a new ID: # echo "8086 10f5" > /sys/bus/pci/drivers/e1000e/new_id INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator. CPU: 2 UID: 0 PID: 177 Comm: liveupdate-iomm Not tainted 7.0.0+ #9 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x5d/0x80 register_lock_class+0x77e/0x790 lock_acquire+0xbf/0x2e0 pci_match_device+0x24/0x180 new_id_store+0x189/0x1d0 kernfs_fop_write_iter+0x14f/0x210 vfs_write+0x263/0x5e0 ksys_write+0x79/0xf0 do_syscall_64+0x117/0xf80 Fixes: 10a4206a2401 ("PCI: use generic driver_override infrastructure") Fixes: 8895d3bcb8ba ("PCI: Fail new_id for vendor/device values already built into driver") Signed-off-by: Samiullah Khawaja [bhelgaas: add commit log details and repro, trim backtrace] Signed-off-by: Bjorn Helgaas Reviewed-by: Danilo Krummrich Link: https://patch.msgid.link/20260505234327.716630-1-skhawaja@google.com Signed-off-by: Sasha Levin --- drivers/pci/pci-driver.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index fba07a700508f..f9ead94d5ebb6 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -179,6 +179,11 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, return NULL; } +static void _pci_free_device(struct device *dev) +{ + kfree(to_pci_dev(dev)); +} + /** * new_id_store - sysfs frontend to pci_add_dynid() * @driver: target device driver @@ -214,11 +219,13 @@ static ssize_t new_id_store(struct device_driver *driver, const char *buf, pdev->subsystem_vendor = subvendor; pdev->subsystem_device = subdevice; pdev->class = class; + pdev->dev.release = _pci_free_device; + device_initialize(&pdev->dev); if (pci_match_device(pdrv, pdev)) retval = -EEXIST; - kfree(pdev); + put_device(&pdev->dev); if (retval) return retval; From dbbd60129f7908d49c6de3a29d2059defeb7f9ec Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 19 Mar 2026 22:15:06 +0100 Subject: [PATCH 1043/1518] bpf: Fix sync_linked_regs regarding BPF_ADD_CONST32 zext propagation [ Upstream commit bc308be380c136800e1e94c6ce49cb53141d6506 ] Jenny reported that in sync_linked_regs() the BPF_ADD_CONST32 flag is checked on known_reg (the register narrowed by a conditional branch) instead of reg (the linked target register created by an alu32 operation). Example case with reg: 1. r6 = bpf_get_prandom_u32() 2. r7 = r6 (linked, same id) 3. w7 += 5 (alu32 -- r7 gets BPF_ADD_CONST32, zero-extended by CPU) 4. if w6 < 0xFFFFFFFC goto safe (narrows r6 to [0xFFFFFFFC, 0xFFFFFFFF]) 5. sync_linked_regs() propagates to r7 but does NOT call zext_32_to_64() 6. Verifier thinks r7 is [0x100000001, 0x100000004] instead of [1, 4] Since known_reg above does not have BPF_ADD_CONST32 set above, zext_32_to_64() is never called on alu32-derived linked registers. This causes the verifier to track incorrect 64-bit bounds, while the CPU correctly zero-extends the 32-bit result. The code checking known_reg->id was correct however (see scalars_alu32_wrap selftest case), but the real fix needs to handle both directions - zext propagation should be done when either register has BPF_ADD_CONST32, since the linked relationship involves a 32-bit operation regardless of which side has the flag. Example case with known_reg (exercised also by scalars_alu32_wrap): 1. r1 = r0; w1 += 0x100 (alu32 -- r1 gets BPF_ADD_CONST32) 2. if r1 > 0x80 - known_reg = r1 (has BPF_ADD_CONST32), reg = r0 (doesn't) Hence, fix it by checking for (reg->id | known_reg->id) & BPF_ADD_CONST32. Moreover, sync_linked_regs() also has a soundness issue when two linked registers used different ALU widths: one with BPF_ADD_CONST32 and the other with BPF_ADD_CONST64. The delta relationship between linked registers assumes the same arithmetic width though. When one register went through alu32 (CPU zero-extends the 32-bit result) and the other went through alu64 (no zero-extension), the propagation produces incorrect bounds. Example: r6 = bpf_get_prandom_u32() // fully unknown if r6 >= 0x100000000 goto out // constrain r6 to [0, U32_MAX] r7 = r6 w7 += 1 // alu32: r7.id = N | BPF_ADD_CONST32 r8 = r6 r8 += 2 // alu64: r8.id = N | BPF_ADD_CONST64 if r7 < 0xFFFFFFFF goto out // narrows r7 to [0xFFFFFFFF, 0xFFFFFFFF] At the branch on r7, sync_linked_regs() runs with known_reg=r7 (BPF_ADD_CONST32) and reg=r8 (BPF_ADD_CONST64). The delta path computes: r8 = r7 + (delta_r8 - delta_r7) = 0xFFFFFFFF + (2 - 1) = 0x100000000 Then, because known_reg->id has BPF_ADD_CONST32, zext_32_to_64(r8) is called, truncating r8 to [0, 0]. But r8 used a 64-bit ALU op -- the CPU does NOT zero-extend it. The actual CPU value of r8 is 0xFFFFFFFE + 2 = 0x100000000, not 0. The verifier now underestimates r8's 64-bit bounds, which is a soundness violation. Fix sync_linked_regs() by skipping propagation when the two registers have mixed ALU widths (one BPF_ADD_CONST32, the other BPF_ADD_CONST64). Lastly, fix regsafe() used for path pruning: the existing checks used "& BPF_ADD_CONST" to test for offset linkage, which treated BPF_ADD_CONST32 and BPF_ADD_CONST64 as equivalent. Fixes: 7a433e519364 ("bpf: Support negative offsets, BPF_SUB, and alu32 for linked register tracking") Reported-by: Jenny Guanni Qu Co-developed-by: Puranjay Mohan Signed-off-by: Puranjay Mohan Signed-off-by: Daniel Borkmann Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260319211507.213816-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ebfa27d4002c5..3dcf591acd50d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16913,6 +16913,12 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s continue; if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST)) continue; + /* + * Skip mixed 32/64-bit links: the delta relationship doesn't + * hold across different ALU widths. + */ + if (((reg->id ^ known_reg->id) & BPF_ADD_CONST) == BPF_ADD_CONST) + continue; if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) || reg->off == known_reg->off) { s32 saved_subreg_def = reg->subreg_def; @@ -16940,7 +16946,7 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s scalar32_min_max_add(reg, &fake_reg); scalar_min_max_add(reg, &fake_reg); reg->var_off = tnum_add(reg->var_off, fake_reg.var_off); - if (known_reg->id & BPF_ADD_CONST32) + if ((reg->id | known_reg->id) & BPF_ADD_CONST32) zext_32_to_64(reg); reg_bounds_sync(reg); } @@ -19056,11 +19062,14 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, * Also verify that new value satisfies old value range knowledge. */ - /* ADD_CONST mismatch: different linking semantics */ - if ((rold->id & BPF_ADD_CONST) && !(rcur->id & BPF_ADD_CONST)) - return false; - - if (rold->id && !(rold->id & BPF_ADD_CONST) && (rcur->id & BPF_ADD_CONST)) + /* + * ADD_CONST flags must match exactly: BPF_ADD_CONST32 and + * BPF_ADD_CONST64 have different linking semantics in + * sync_linked_regs() (alu32 zero-extends, alu64 does not), + * so pruning across different flag types is unsafe. + */ + if (rold->id && + (rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST)) return false; /* Both have offset linkage: offsets must match */ From 26b4ea23f511e771a90efd394097c564360a5edc Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 24 Oct 2025 14:23:35 +0300 Subject: [PATCH 1044/1518] net: airoha: Fix a copy and paste bug in probe() [ Upstream commit 05e090620bacf317020f9591cfff8926093380bd ] This code has a copy and paste bug where it accidentally checks "if (err)" instead of checking if "xsi_rsts" is NULL. Also, as a free bonus, I changed the allocation from kzalloc() to kcalloc() which is a kernel hardening measure to protect against integer overflows. Fixes: 5863b4e065e2 ("net: airoha: Add airoha_eth_soc_data struct") Signed-off-by: Dan Carpenter Acked-by: Lorenzo Bianconi Link: https://patch.msgid.link/aPtht6y5DRokn9zv@stanley.mountain Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 81ecfc1a1094c..4364f4320428a 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -3097,11 +3097,11 @@ static int airoha_probe(struct platform_device *pdev) return err; } - xsi_rsts = devm_kzalloc(eth->dev, - eth->soc->num_xsi_rsts * sizeof(*xsi_rsts), + xsi_rsts = devm_kcalloc(eth->dev, + eth->soc->num_xsi_rsts, sizeof(*xsi_rsts), GFP_KERNEL); - if (err) - return err; + if (!xsi_rsts) + return -ENOMEM; eth->xsi_rsts = xsi_rsts; for (i = 0; i < eth->soc->num_xsi_rsts; i++) From 95fdee73c39c9f674e22eee4839e6698baa3ad28 Mon Sep 17 00:00:00 2001 From: Costa Shulyupin Date: Mon, 12 Jan 2026 21:26:41 +0200 Subject: [PATCH 1045/1518] rtla: Fix parse_cpu_set() bug introduced by strtoi() [ Upstream commit 6ea8a206108fe8b5940c2797afc54ae9f5a7bbdd ] The patch 'Replace atoi() with a robust strtoi()' introduced a bug in parse_cpu_set(), which relies on partial parsing of the input string. The function parses CPU specifications like '0-3,5' by incrementing a pointer through the string. strtoi() rejects strings with trailing characters, causing parse_cpu_set() to fail on any CPU list with multiple entries. Restore the original use of atoi() in parse_cpu_set(). Fixes: 7e9dfccf8f11 ("rtla: Replace atoi() with a robust strtoi()") Signed-off-by: Costa Shulyupin Reviewed-by: Masami Hiramatsu (Google) Link: https://lore.kernel.org/r/20260112192642.212848-2-costa.shul@redhat.com Signed-off-by: Tomas Glozar Signed-off-by: Sasha Levin --- tools/tracing/rtla/src/utils.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index bf20077cca742..b4cd93f784522 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -113,18 +113,16 @@ int parse_cpu_set(char *cpu_list, cpu_set_t *set) nr_cpus = sysconf(_SC_NPROCESSORS_CONF); for (p = cpu_list; *p; ) { - if (strtoi(p, &cpu)) - goto err; - if (cpu < 0 || cpu >= nr_cpus) + cpu = atoi(p); + if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus) goto err; while (isdigit(*p)) p++; if (*p == '-') { p++; - if (strtoi(p, &end_cpu)) - goto err; - if (end_cpu < cpu || end_cpu >= nr_cpus) + end_cpu = atoi(p); + if (end_cpu < cpu || (!end_cpu && *p != '0') || end_cpu >= nr_cpus) goto err; while (isdigit(*p)) p++; From 7645ead02939e0caa9d1655981a371c8fc06b7ab Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 29 Apr 2026 14:02:31 +0200 Subject: [PATCH 1046/1518] net: airoha: Move entries to queue head in case of DMA mapping failure in airoha_dev_xmit() [ Upstream commit 75df490c9e8457990c8b227650f6491218ce018b ] In order to respect the original descriptor order and avoid any potential IOMMU fault or memory corruption, move pending queue entries to the head of hw queue tx_list if the DMA mapping of current inflight packet fails in airoha_dev_xmit routine. Fixes: 3f47e67dff1f7 ("net: airoha: Add the capability to consume out-of-order DMA tx descriptors") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260429-airoha-xmit-unmap-error-path-v2-1-32e43b7c6d25@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 4364f4320428a..b4dfab2702cb9 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2136,14 +2136,12 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, return NETDEV_TX_OK; error_unmap: - while (!list_empty(&tx_list)) { - e = list_first_entry(&tx_list, struct airoha_queue_entry, - list); + list_for_each_entry(e, &tx_list, list) { dma_unmap_single(dev->dev.parent, e->dma_addr, e->dma_len, DMA_TO_DEVICE); e->dma_addr = 0; - list_move_tail(&e->list, &q->tx_list); } + list_splice(&tx_list, &q->tx_list); spin_unlock_bh(&q->lock); error: From 90619fdedfb9cc8a80f217d882ee7a84d3703e72 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 17 Apr 2026 08:36:31 +0200 Subject: [PATCH 1047/1518] net: airoha: Move ndesc initialization at end of airoha_qdma_init_tx() [ Upstream commit f329924bb49458c65297f1361f545816a5b90998 ] If queue entry list allocation fails in airoha_qdma_init_tx_queue routine, airoha_qdma_cleanup_tx_queue() will trigger a NULL pointer dereference accessing the queue entry array. The issue is due to the early ndesc initialization in airoha_qdma_init_tx_queue(). Fix the issue moving ndesc initialization at end of airoha_qdma_init_tx routine. Fixes: 3f47e67dff1f7 ("net: airoha: Add the capability to consume out-of-order DMA tx descriptors") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260417-airoha_qdma_cleanup_tx_queue-fix-net-v4-1-e04bcc2c9642@kernel.org Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index b4dfab2702cb9..3f97a0135f7f8 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1019,27 +1019,27 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, dma_addr_t dma_addr; spin_lock_init(&q->lock); - q->ndesc = size; q->qdma = qdma; q->free_thr = 1 + MAX_SKB_FRAGS; INIT_LIST_HEAD(&q->tx_list); - q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), + q->entry = devm_kzalloc(eth->dev, size * sizeof(*q->entry), GFP_KERNEL); if (!q->entry) return -ENOMEM; - q->desc = dmam_alloc_coherent(eth->dev, q->ndesc * sizeof(*q->desc), + q->desc = dmam_alloc_coherent(eth->dev, size * sizeof(*q->desc), &dma_addr, GFP_KERNEL); if (!q->desc) return -ENOMEM; - for (i = 0; i < q->ndesc; i++) { + for (i = 0; i < size; i++) { u32 val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1); list_add_tail(&q->entry[i].list, &q->tx_list); WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val)); } + q->ndesc = size; /* xmit ring drop default setting */ airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(qid), From db9af8a2efada5a4c5c2c6768a1706eb5d0f3106 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 30 Apr 2026 08:00:56 +0000 Subject: [PATCH 1048/1518] net/sched: sch_pie: annotate more data-races in pie_dump_stats() [ Upstream commit 6d4106e8df94c0c52cf3ca6a6a0d01567fb3844e ] My prior patch missed few READ_ONCE()/WRITE_ONCE() annotations. Fixes: 5154561d9b11 ("net/sched: sch_pie: annotate data-races in pie_dump_stats()") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20260430080056.35104-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_pie.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 73650200482f4..40149edecbd5a 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -219,16 +219,14 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, * packet timestamp. */ if (!params->dq_rate_estimator) { - vars->qdelay = now - pie_get_enqueue_time(skb); + WRITE_ONCE(vars->qdelay, + backlog ? now - pie_get_enqueue_time(skb) : 0); if (vars->dq_tstamp != DTIME_INVALID) dtime = now - vars->dq_tstamp; vars->dq_tstamp = now; - if (backlog == 0) - vars->qdelay = 0; - if (dtime == 0) return; @@ -376,7 +374,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) delta += MAX_PROB / (100 / 2); - vars->prob += delta; + WRITE_ONCE(vars->prob, vars->prob + delta); if (delta > 0) { /* prevent overflow */ @@ -401,7 +399,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, if (qdelay == 0 && qdelay_old == 0 && update_prob) /* Reduce drop probability to 98.4% */ - vars->prob -= vars->prob / 64; + WRITE_ONCE(vars->prob, vars->prob - vars->prob / 64); WRITE_ONCE(vars->qdelay, qdelay); vars->backlog_old = backlog; @@ -501,7 +499,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { - .prob = q->vars.prob << BITS_PER_BYTE, + .prob = READ_ONCE(q->vars.prob) << BITS_PER_BYTE, .delay = ((u32)PSCHED_TICKS2NS(READ_ONCE(q->vars.qdelay))) / NSEC_PER_USEC, .packets_in = READ_ONCE(q->stats.packets_in), @@ -512,7 +510,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) }; /* avg_dq_rate is only valid if dq_rate_estimator is enabled */ - st.dq_rate_estimating = q->params.dq_rate_estimator; + st.dq_rate_estimating = READ_ONCE(q->params.dq_rate_estimator); /* unscale and return dq_rate in bytes per sec */ if (st.dq_rate_estimating) From 106581064439cde70cf9e1accea8c76bcbbe20a1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 22 Oct 2025 09:11:12 +0200 Subject: [PATCH 1049/1518] net: airoha: Remove code duplication in airoha_regs.h [ Upstream commit 99ad2b6815f41acbec15ab051ccc79b11b05710a ] This patch does not introduce any logical change, it just removes duplicated code in airoha_regs.h. Fix naming conventions in airoha_regs.h. Reviewed-by: Simon Horman Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20251022-airoha-regs-cosmetics-v2-1-e0425b3f2c2c@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: 1acdfbdb516b ("net: airoha: Fix VIP configuration for AN7583 SoC") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 102 ++++++++++---------- drivers/net/ethernet/airoha/airoha_regs.h | 109 ++++++++++------------ 2 files changed, 100 insertions(+), 111 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 3f97a0135f7f8..269ed7179e6c9 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -137,11 +137,11 @@ static void airoha_fe_maccr_init(struct airoha_eth *eth) for (p = 1; p <= ARRAY_SIZE(eth->ports); p++) airoha_fe_set(eth, REG_GDM_FWD_CFG(p), - GDM_TCP_CKSUM | GDM_UDP_CKSUM | GDM_IP4_CKSUM | - GDM_DROP_CRC_ERR); + GDM_TCP_CKSUM_MASK | GDM_UDP_CKSUM_MASK | + GDM_IP4_CKSUM_MASK | GDM_DROP_CRC_ERR_MASK); - airoha_fe_rmw(eth, REG_CDM1_VLAN_CTRL, CDM1_VLAN_MASK, - FIELD_PREP(CDM1_VLAN_MASK, 0x8100)); + airoha_fe_rmw(eth, REG_CDM_VLAN_CTRL(1), CDM_VLAN_MASK, + FIELD_PREP(CDM_VLAN_MASK, 0x8100)); airoha_fe_set(eth, REG_FE_CPORT_CFG, FE_CPORT_PAD); } @@ -405,46 +405,46 @@ static int airoha_fe_mc_vlan_clear(struct airoha_eth *eth) static void airoha_fe_crsn_qsel_init(struct airoha_eth *eth) { /* CDM1_CRSN_QSEL */ - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_22 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_22), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_22), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_22 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_22), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_22), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_08 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_08), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_08), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_08 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_08), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_08), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_21 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_21), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_21), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_21 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_21), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_21), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_24 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_24), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_24), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_24 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_24), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_24), CDM_CRSN_QSEL_Q6)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_25 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_25), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_25), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_25 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_25), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_25), CDM_CRSN_QSEL_Q1)); /* CDM2_CRSN_QSEL */ - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_08 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_08), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_08), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_08 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_08), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_08), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_21 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_21), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_21), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_21 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_21), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_21), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_22 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_22), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_22), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_22 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_22), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_22), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_24 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_24), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_24), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_24 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_24), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_24), CDM_CRSN_QSEL_Q6)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_25 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_25), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_25), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_25 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_25), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_25), CDM_CRSN_QSEL_Q1)); } @@ -464,18 +464,18 @@ static int airoha_fe_init(struct airoha_eth *eth) airoha_fe_wr(eth, REG_FE_PCE_CFG, PCE_DPI_EN_MASK | PCE_KA_EN_MASK | PCE_MC_EN_MASK); /* set vip queue selection to ring 1 */ - airoha_fe_rmw(eth, REG_CDM1_FWD_CFG, CDM1_VIP_QSEL_MASK, - FIELD_PREP(CDM1_VIP_QSEL_MASK, 0x4)); - airoha_fe_rmw(eth, REG_CDM2_FWD_CFG, CDM2_VIP_QSEL_MASK, - FIELD_PREP(CDM2_VIP_QSEL_MASK, 0x4)); + airoha_fe_rmw(eth, REG_CDM_FWD_CFG(1), CDM_VIP_QSEL_MASK, + FIELD_PREP(CDM_VIP_QSEL_MASK, 0x4)); + airoha_fe_rmw(eth, REG_CDM_FWD_CFG(2), CDM_VIP_QSEL_MASK, + FIELD_PREP(CDM_VIP_QSEL_MASK, 0x4)); /* set GDM4 source interface offset to 8 */ - airoha_fe_rmw(eth, REG_GDM4_SRC_PORT_SET, - GDM4_SPORT_OFF2_MASK | - GDM4_SPORT_OFF1_MASK | - GDM4_SPORT_OFF0_MASK, - FIELD_PREP(GDM4_SPORT_OFF2_MASK, 8) | - FIELD_PREP(GDM4_SPORT_OFF1_MASK, 8) | - FIELD_PREP(GDM4_SPORT_OFF0_MASK, 8)); + airoha_fe_rmw(eth, REG_GDM_SRC_PORT_SET(4), + GDM_SPORT_OFF2_MASK | + GDM_SPORT_OFF1_MASK | + GDM_SPORT_OFF0_MASK, + FIELD_PREP(GDM_SPORT_OFF2_MASK, 8) | + FIELD_PREP(GDM_SPORT_OFF1_MASK, 8) | + FIELD_PREP(GDM_SPORT_OFF0_MASK, 8)); /* set PSE Page as 128B */ airoha_fe_rmw(eth, REG_FE_DMA_GLO_CFG, @@ -501,8 +501,8 @@ static int airoha_fe_init(struct airoha_eth *eth) airoha_fe_set(eth, REG_GDM_MISC_CFG, GDM2_RDM_ACK_WAIT_PREF_MASK | GDM2_CHN_VLD_MODE_MASK); - airoha_fe_rmw(eth, REG_CDM2_FWD_CFG, CDM2_OAM_QSEL_MASK, - FIELD_PREP(CDM2_OAM_QSEL_MASK, 15)); + airoha_fe_rmw(eth, REG_CDM_FWD_CFG(2), CDM_OAM_QSEL_MASK, + FIELD_PREP(CDM_OAM_QSEL_MASK, 15)); /* init fragment and assemble Force Port */ /* NPU Core-3, NPU Bridge Channel-3 */ @@ -516,8 +516,8 @@ static int airoha_fe_init(struct airoha_eth *eth) FIELD_PREP(IP_ASSEMBLE_PORT_MASK, 0) | FIELD_PREP(IP_ASSEMBLE_NBQ_MASK, 22)); - airoha_fe_set(eth, REG_GDM3_FWD_CFG, GDM3_PAD_EN_MASK); - airoha_fe_set(eth, REG_GDM4_FWD_CFG, GDM4_PAD_EN_MASK); + airoha_fe_set(eth, REG_GDM_FWD_CFG(3), GDM_PAD_EN_MASK); + airoha_fe_set(eth, REG_GDM_FWD_CFG(4), GDM_PAD_EN_MASK); airoha_fe_crsn_qsel_init(eth); @@ -525,7 +525,7 @@ static int airoha_fe_init(struct airoha_eth *eth) airoha_fe_set(eth, REG_FE_CPORT_CFG, FE_CPORT_PORT_XFC_MASK); /* default aging mode for mbi unlock issue */ - airoha_fe_rmw(eth, REG_GDM2_CHN_RLS, + airoha_fe_rmw(eth, REG_GDM_CHN_RLS(2), MBI_RX_AGE_SEL_MASK | MBI_TX_AGE_SEL_MASK, FIELD_PREP(MBI_RX_AGE_SEL_MASK, 3) | FIELD_PREP(MBI_TX_AGE_SEL_MASK, 3)); @@ -1816,7 +1816,7 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 : FE_PSE_PORT_GDM4; airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port); - airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC); + airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC_MASK); /* Enable GDM2 loopback */ airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff); diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h index ebcce00d9bc6f..ed4e3407f4a0e 100644 --- a/drivers/net/ethernet/airoha/airoha_regs.h +++ b/drivers/net/ethernet/airoha/airoha_regs.h @@ -23,6 +23,8 @@ #define GDM3_BASE 0x1100 #define GDM4_BASE 0x2500 +#define CDM_BASE(_n) \ + ((_n) == 2 ? CDM2_BASE : CDM1_BASE) #define GDM_BASE(_n) \ ((_n) == 4 ? GDM4_BASE : \ (_n) == 3 ? GDM3_BASE : \ @@ -109,30 +111,24 @@ #define PATN_DP_MASK GENMASK(31, 16) #define PATN_SP_MASK GENMASK(15, 0) -#define REG_CDM1_VLAN_CTRL CDM1_BASE -#define CDM1_VLAN_MASK GENMASK(31, 16) +#define REG_CDM_VLAN_CTRL(_n) CDM_BASE(_n) +#define CDM_VLAN_MASK GENMASK(31, 16) -#define REG_CDM1_FWD_CFG (CDM1_BASE + 0x08) -#define CDM1_VIP_QSEL_MASK GENMASK(24, 20) +#define REG_CDM_FWD_CFG(_n) (CDM_BASE(_n) + 0x08) +#define CDM_OAM_QSEL_MASK GENMASK(31, 27) +#define CDM_VIP_QSEL_MASK GENMASK(24, 20) -#define REG_CDM1_CRSN_QSEL(_n) (CDM1_BASE + 0x10 + ((_n) << 2)) -#define CDM1_CRSN_QSEL_REASON_MASK(_n) \ - GENMASK(4 + (((_n) % 4) << 3), (((_n) % 4) << 3)) - -#define REG_CDM2_FWD_CFG (CDM2_BASE + 0x08) -#define CDM2_OAM_QSEL_MASK GENMASK(31, 27) -#define CDM2_VIP_QSEL_MASK GENMASK(24, 20) - -#define REG_CDM2_CRSN_QSEL(_n) (CDM2_BASE + 0x10 + ((_n) << 2)) -#define CDM2_CRSN_QSEL_REASON_MASK(_n) \ +#define REG_CDM_CRSN_QSEL(_n, _m) (CDM_BASE(_n) + 0x10 + ((_m) << 2)) +#define CDM_CRSN_QSEL_REASON_MASK(_n) \ GENMASK(4 + (((_n) % 4) << 3), (((_n) % 4) << 3)) #define REG_GDM_FWD_CFG(_n) GDM_BASE(_n) -#define GDM_DROP_CRC_ERR BIT(23) -#define GDM_IP4_CKSUM BIT(22) -#define GDM_TCP_CKSUM BIT(21) -#define GDM_UDP_CKSUM BIT(20) -#define GDM_STRIP_CRC BIT(16) +#define GDM_PAD_EN_MASK BIT(28) +#define GDM_DROP_CRC_ERR_MASK BIT(23) +#define GDM_IP4_CKSUM_MASK BIT(22) +#define GDM_TCP_CKSUM_MASK BIT(21) +#define GDM_UDP_CKSUM_MASK BIT(20) +#define GDM_STRIP_CRC_MASK BIT(16) #define GDM_UCFQ_MASK GENMASK(15, 12) #define GDM_BCFQ_MASK GENMASK(11, 8) #define GDM_MCFQ_MASK GENMASK(7, 4) @@ -156,6 +152,10 @@ #define LBK_CHAN_MODE_MASK BIT(1) #define LPBK_EN_MASK BIT(0) +#define REG_GDM_CHN_RLS(_n) (GDM_BASE(_n) + 0x20) +#define MBI_RX_AGE_SEL_MASK GENMASK(26, 25) +#define MBI_TX_AGE_SEL_MASK GENMASK(18, 17) + #define REG_GDM_TXCHN_EN(_n) (GDM_BASE(_n) + 0x24) #define REG_GDM_RXCHN_EN(_n) (GDM_BASE(_n) + 0x28) @@ -168,10 +168,10 @@ #define FE_GDM_MIB_RX_CLEAR_MASK BIT(1) #define FE_GDM_MIB_TX_CLEAR_MASK BIT(0) -#define REG_FE_GDM1_MIB_CFG (GDM1_BASE + 0xf4) +#define REG_FE_GDM_MIB_CFG(_n) (GDM_BASE(_n) + 0xf4) #define FE_STRICT_RFC2819_MODE_MASK BIT(31) -#define FE_GDM1_TX_MIB_SPLIT_EN_MASK BIT(17) -#define FE_GDM1_RX_MIB_SPLIT_EN_MASK BIT(16) +#define FE_GDM_TX_MIB_SPLIT_EN_MASK BIT(17) +#define FE_GDM_RX_MIB_SPLIT_EN_MASK BIT(16) #define FE_TX_MIB_ID_MASK GENMASK(15, 8) #define FE_RX_MIB_ID_MASK GENMASK(7, 0) @@ -214,6 +214,33 @@ #define REG_FE_GDM_RX_ETH_L511_CNT_L(_n) (GDM_BASE(_n) + 0x198) #define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n) (GDM_BASE(_n) + 0x19c) +#define REG_GDM_SRC_PORT_SET(_n) (GDM_BASE(_n) + 0x23c) +#define GDM_SPORT_OFF2_MASK GENMASK(19, 16) +#define GDM_SPORT_OFF1_MASK GENMASK(15, 12) +#define GDM_SPORT_OFF0_MASK GENMASK(11, 8) + +#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x280) +#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x284) +#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x288) +#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x28c) + +#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x290) +#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x294) +#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x298) +#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x29c) +#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2b8) +#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2bc) +#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2c0) +#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2c4) +#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2c8) +#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2cc) +#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2e8) +#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2ec) +#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2f0) +#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2f4) +#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2f8) +#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2fc) + #define REG_PPE_GLO_CFG(_n) (((_n) ? PPE2_BASE : PPE1_BASE) + 0x200) #define PPE_GLO_CFG_BUSY_MASK BIT(31) #define PPE_GLO_CFG_FLOW_DROP_UPDATE_MASK BIT(9) @@ -326,44 +353,6 @@ #define REG_UPDMEM_DATA(_n) (((_n) ? PPE2_BASE : PPE1_BASE) + 0x374) -#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x280) -#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x284) -#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x288) -#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x28c) - -#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x290) -#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x294) -#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x298) -#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x29c) -#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2b8) -#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2bc) -#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2c0) -#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2c4) -#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2c8) -#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2cc) -#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2e8) -#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2ec) -#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2f0) -#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2f4) -#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2f8) -#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2fc) - -#define REG_GDM2_CHN_RLS (GDM2_BASE + 0x20) -#define MBI_RX_AGE_SEL_MASK GENMASK(26, 25) -#define MBI_TX_AGE_SEL_MASK GENMASK(18, 17) - -#define REG_GDM3_FWD_CFG GDM3_BASE -#define GDM3_PAD_EN_MASK BIT(28) - -#define REG_GDM4_FWD_CFG GDM4_BASE -#define GDM4_PAD_EN_MASK BIT(28) -#define GDM4_SPORT_OFFSET0_MASK GENMASK(11, 8) - -#define REG_GDM4_SRC_PORT_SET (GDM4_BASE + 0x23c) -#define GDM4_SPORT_OFF2_MASK GENMASK(19, 16) -#define GDM4_SPORT_OFF1_MASK GENMASK(15, 12) -#define GDM4_SPORT_OFF0_MASK GENMASK(11, 8) - #define REG_IP_FRAG_FP 0x2010 #define IP_ASSEMBLE_PORT_MASK GENMASK(24, 21) #define IP_ASSEMBLE_NBQ_MASK GENMASK(20, 16) From 81a2a3607866b713220bdc39243300673b1040af Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 5 Jan 2026 10:40:47 +0100 Subject: [PATCH 1050/1518] net: airoha: Use gdm port enum value whenever possible [ Upstream commit 4d513329b87c1bd0546d9f0288794e244322daa6 ] Use AIROHA_GDMx_IDX enum value whenever possible. This patch is just cosmetic changes and does not introduce any logic one. Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260105-airoha-use-port-idx-enum-v1-1-503ca5763858@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: 1acdfbdb516b ("net: airoha: Fix VIP configuration for AN7583 SoC") Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 40 +++++++++++++----------- 1 file changed, 21 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 269ed7179e6c9..c5f509cd52e63 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -108,11 +108,11 @@ static int airoha_set_vip_for_gdm_port(struct airoha_gdm_port *port, u32 vip_port; switch (port->id) { - case 3: + case AIROHA_GDM3_IDX: /* FIXME: handle XSI_PCIE1_PORT */ vip_port = XSI_PCIE0_VIP_PORT_MASK; break; - case 4: + case AIROHA_GDM4_IDX: /* FIXME: handle XSI_USB_PORT */ vip_port = XSI_ETH_VIP_PORT_MASK; break; @@ -516,8 +516,8 @@ static int airoha_fe_init(struct airoha_eth *eth) FIELD_PREP(IP_ASSEMBLE_PORT_MASK, 0) | FIELD_PREP(IP_ASSEMBLE_NBQ_MASK, 22)); - airoha_fe_set(eth, REG_GDM_FWD_CFG(3), GDM_PAD_EN_MASK); - airoha_fe_set(eth, REG_GDM_FWD_CFG(4), GDM_PAD_EN_MASK); + airoha_fe_set(eth, REG_GDM_FWD_CFG(AIROHA_GDM3_IDX), GDM_PAD_EN_MASK); + airoha_fe_set(eth, REG_GDM_FWD_CFG(AIROHA_GDM4_IDX), GDM_PAD_EN_MASK); airoha_fe_crsn_qsel_init(eth); @@ -1815,27 +1815,29 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) /* Forward the traffic to the proper GDM port */ pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 : FE_PSE_PORT_GDM4; - airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port); - airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC_MASK); + airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), + pse_port); + airoha_fe_clear(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), + GDM_STRIP_CRC_MASK); /* Enable GDM2 loopback */ - airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff); - airoha_fe_wr(eth, REG_GDM_RXCHN_EN(2), 0xffff); + airoha_fe_wr(eth, REG_GDM_TXCHN_EN(AIROHA_GDM2_IDX), 0xffffffff); + airoha_fe_wr(eth, REG_GDM_RXCHN_EN(AIROHA_GDM2_IDX), 0xffff); chan = port->id == AIROHA_GDM3_IDX ? airoha_is_7581(eth) ? 4 : 3 : 0; - airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(2), + airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(AIROHA_GDM2_IDX), LPBK_CHAN_MASK | LPBK_MODE_MASK | LPBK_EN_MASK, FIELD_PREP(LPBK_CHAN_MASK, chan) | LBK_GAP_MODE_MASK | LBK_LEN_MODE_MASK | LBK_CHAN_MODE_MASK | LPBK_EN_MASK); - airoha_fe_rmw(eth, REG_GDM_LEN_CFG(2), + airoha_fe_rmw(eth, REG_GDM_LEN_CFG(AIROHA_GDM2_IDX), GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK, FIELD_PREP(GDM_SHORT_LEN_MASK, 60) | FIELD_PREP(GDM_LONG_LEN_MASK, AIROHA_MAX_MTU)); /* Disable VIP and IFC for GDM2 */ - airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2)); - airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2)); + airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX)); + airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(AIROHA_GDM2_IDX)); /* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */ nbq = port->id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0; @@ -1869,8 +1871,8 @@ static int airoha_dev_init(struct net_device *dev) airoha_set_macaddr(port, dev->dev_addr); switch (port->id) { - case 3: - case 4: + case AIROHA_GDM3_IDX: + case AIROHA_GDM4_IDX: /* If GDM2 is active we can't enable loopback */ if (!eth->ports[1]) { int err; @@ -1880,7 +1882,7 @@ static int airoha_dev_init(struct net_device *dev) return err; } fallthrough; - case 2: + case AIROHA_GDM2_IDX: if (airoha_ppe_is_enabled(eth, 1)) { pse_port = FE_PSE_PORT_PPE2; break; @@ -3206,14 +3208,14 @@ static const char * const en7581_xsi_rsts_names[] = { static int airoha_en7581_get_src_port_id(struct airoha_gdm_port *port, int nbq) { switch (port->id) { - case 3: + case AIROHA_GDM3_IDX: /* 7581 SoC supports PCIe serdes on GDM3 port */ if (nbq == 4) return HSGMII_LAN_7581_PCIE0_SRCPORT; if (nbq == 5) return HSGMII_LAN_7581_PCIE1_SRCPORT; break; - case 4: + case AIROHA_GDM4_IDX: /* 7581 SoC supports eth and usb serdes on GDM4 port */ if (!nbq) return HSGMII_LAN_7581_ETH_SRCPORT; @@ -3237,12 +3239,12 @@ static const char * const an7583_xsi_rsts_names[] = { static int airoha_an7583_get_src_port_id(struct airoha_gdm_port *port, int nbq) { switch (port->id) { - case 3: + case AIROHA_GDM3_IDX: /* 7583 SoC supports eth serdes on GDM3 port */ if (!nbq) return HSGMII_LAN_7583_ETH_SRCPORT; break; - case 4: + case AIROHA_GDM4_IDX: /* 7583 SoC supports PCIe and USB serdes on GDM4 port */ if (!nbq) return HSGMII_LAN_7583_PCIE_SRCPORT; From 80c025618524d47907a1cd0b3783f874c78ef924 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 12 Apr 2026 09:57:29 +0200 Subject: [PATCH 1051/1518] net: airoha: Fix VIP configuration for AN7583 SoC [ Upstream commit 1acdfbdb516b32165a8ecd1d5f8c68e4eac64637 ] EN7581 and AN7583 SoCs have different VIP definitions. Introduce get_vip_port callback in airoha_eth_soc_data struct in order to take into account EN7581 and AN7583 VIP register layout and definition differences. Introduce nbq parameter in airoha_gdm_port struct. At the moment nbq is set statically to value previously used in airhoha_set_gdm2_loopback routine and it will be read from device tree in subsequent patches. Fixes: e4e5ce823bdd ("net: airoha: Add AN7583 SoC support") Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260412-airoha-7583-vip-fix-v1-1-c35e02b054bb@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 66 ++++++++++++++++++------ drivers/net/ethernet/airoha/airoha_eth.h | 2 + 2 files changed, 51 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index c5f509cd52e63..27d62acfcc39c 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -107,19 +107,7 @@ static int airoha_set_vip_for_gdm_port(struct airoha_gdm_port *port, struct airoha_eth *eth = port->qdma->eth; u32 vip_port; - switch (port->id) { - case AIROHA_GDM3_IDX: - /* FIXME: handle XSI_PCIE1_PORT */ - vip_port = XSI_PCIE0_VIP_PORT_MASK; - break; - case AIROHA_GDM4_IDX: - /* FIXME: handle XSI_USB_PORT */ - vip_port = XSI_ETH_VIP_PORT_MASK; - break; - default: - return 0; - } - + vip_port = eth->soc->ops.get_vip_port(port, port->nbq); if (enable) { airoha_fe_set(eth, REG_FE_VIP_PORT_EN, vip_port); airoha_fe_set(eth, REG_FE_IFC_PORT_EN, vip_port); @@ -1809,7 +1797,7 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) { struct airoha_eth *eth = port->qdma->eth; - u32 val, pse_port, chan, nbq; + u32 val, pse_port, chan; int src_port; /* Forward the traffic to the proper GDM port */ @@ -1839,9 +1827,7 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX)); airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(AIROHA_GDM2_IDX)); - /* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */ - nbq = port->id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0; - src_port = eth->soc->ops.get_src_port_id(port, nbq); + src_port = eth->soc->ops.get_src_port_id(port, port->nbq); if (src_port < 0) return src_port; @@ -3034,6 +3020,8 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, port->qdma = qdma; port->dev = dev; port->id = id; + /* XXX: Read nbq from DTS */ + port->nbq = id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0; eth->ports[p] = port; return airoha_metadata_dst_alloc(port); @@ -3229,6 +3217,28 @@ static int airoha_en7581_get_src_port_id(struct airoha_gdm_port *port, int nbq) return -EINVAL; } +static u32 airoha_en7581_get_vip_port(struct airoha_gdm_port *port, int nbq) +{ + switch (port->id) { + case AIROHA_GDM3_IDX: + if (nbq == 4) + return XSI_PCIE0_VIP_PORT_MASK; + if (nbq == 5) + return XSI_PCIE1_VIP_PORT_MASK; + break; + case AIROHA_GDM4_IDX: + if (!nbq) + return XSI_ETH_VIP_PORT_MASK; + if (nbq == 1) + return XSI_USB_VIP_PORT_MASK; + break; + default: + break; + } + + return 0; +} + static const char * const an7583_xsi_rsts_names[] = { "xsi-mac", "hsi0-mac", @@ -3258,6 +3268,26 @@ static int airoha_an7583_get_src_port_id(struct airoha_gdm_port *port, int nbq) return -EINVAL; } +static u32 airoha_an7583_get_vip_port(struct airoha_gdm_port *port, int nbq) +{ + switch (port->id) { + case AIROHA_GDM3_IDX: + if (!nbq) + return XSI_ETH_VIP_PORT_MASK; + break; + case AIROHA_GDM4_IDX: + if (!nbq) + return XSI_PCIE0_VIP_PORT_MASK; + if (nbq == 1) + return XSI_USB_VIP_PORT_MASK; + break; + default: + break; + } + + return 0; +} + static const struct airoha_eth_soc_data en7581_soc_data = { .version = 0x7581, .xsi_rsts_names = en7581_xsi_rsts_names, @@ -3265,6 +3295,7 @@ static const struct airoha_eth_soc_data en7581_soc_data = { .num_ppe = 2, .ops = { .get_src_port_id = airoha_en7581_get_src_port_id, + .get_vip_port = airoha_en7581_get_vip_port, }, }; @@ -3275,6 +3306,7 @@ static const struct airoha_eth_soc_data an7583_soc_data = { .num_ppe = 1, .ops = { .get_src_port_id = airoha_an7583_get_src_port_id, + .get_vip_port = airoha_an7583_get_vip_port, }, }; diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index 33277cc577990..57e8ddb30a9c5 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -536,6 +536,7 @@ struct airoha_gdm_port { struct airoha_qdma *qdma; struct net_device *dev; int id; + int nbq; struct airoha_hw_stats stats; @@ -576,6 +577,7 @@ struct airoha_eth_soc_data { int num_ppe; struct { int (*get_src_port_id)(struct airoha_gdm_port *port, int nbq); + u32 (*get_vip_port)(struct airoha_gdm_port *port, int nbq); } ops; }; From 45d6c6c10b8b3342cbb2e0b8d588d6d52039031b Mon Sep 17 00:00:00 2001 From: Dipayaan Roy Date: Thu, 18 Dec 2025 05:10:54 -0800 Subject: [PATCH 1052/1518] net: mana: Fix use-after-free in reset service rescan path [ Upstream commit 3387a7ad478b46970ae8254049167d166e398aeb ] When mana_serv_reset() encounters -ETIMEDOUT or -EPROTO from mana_gd_resume(), it performs a PCI rescan via mana_serv_rescan(). mana_serv_rescan() calls pci_stop_and_remove_bus_device(), which can invoke the driver's remove path and free the gdma_context associated with the device. After returning, mana_serv_reset() currently jumps to the out label and attempts to clear gc->in_service, dereferencing a freed gdma_context. The issue was observed with the following call logs: [ 698.942636] BUG: unable to handle page fault for address: ff6c2b638088508d [ 698.943121] #PF: supervisor write access in kernel mode [ 698.943423] #PF: error_code(0x0002) - not-present page [S[ 698.943793] Pat Dec 6 07:GD5 100000067 P4D 1002f7067 PUD 1002f8067 PMD 101bef067 PTE 0 0:56 2025] hv_[n e 698.944283] Oops: Oops: 0002 [#1] SMP NOPTI tvsc f8615163-00[ 698.944611] CPU: 28 UID: 0 PID: 249 Comm: kworker/28:1 ... [Sat Dec 6 07:50:56 2025] R10: [ 699.121594] mana 7870:00:00.0 enP30832s1: Configured vPort 0 PD 18 DB 16 000000000000001b R11: 0000000000000000 R12: ff44cf3f40270000 [Sat Dec 6 07:50:56 2025] R13: 0000000000000001 R14: ff44cf3f402700c8 R15: ff44cf3f4021b405 [Sat Dec 6 07:50:56 2025] FS: 0000000000000000(0000) GS:ff44cf7e9fcf9000(0000) knlGS:0000000000000000 [Sat Dec 6 07:50:56 2025] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Sat Dec 6 07:50:56 2025] CR2: ff6c2b638088508d CR3: 000000011fe43001 CR4: 0000000000b73ef0 [Sat Dec 6 07:50:56 2025] Call Trace: [Sat Dec 6 07:50:56 2025] [Sat Dec 6 07:50:56 2025] mana_serv_func+0x24/0x50 [mana] [Sat Dec 6 07:50:56 2025] process_one_work+0x190/0x350 [Sat Dec 6 07:50:56 2025] worker_thread+0x2b7/0x3d0 [Sat Dec 6 07:50:56 2025] kthread+0xf3/0x200 [Sat Dec 6 07:50:56 2025] ? __pfx_worker_thread+0x10/0x10 [Sat Dec 6 07:50:56 2025] ? __pfx_kthread+0x10/0x10 [Sat Dec 6 07:50:56 2025] ret_from_fork+0x21a/0x250 [Sat Dec 6 07:50:56 2025] ? __pfx_kthread+0x10/0x10 [Sat Dec 6 07:50:56 2025] ret_from_fork_asm+0x1a/0x30 [Sat Dec 6 07:50:56 2025] Fix this by returning immediately after mana_serv_rescan() to avoid accessing GC state that may no longer be valid. Fixes: 9bf66036d686 ("net: mana: Handle hardware recovery events when probing the device") Reviewed-by: Simon Horman Reviewed-by: Long Li Signed-off-by: Dipayaan Roy Link: https://patch.msgid.link/20251218131054.GA3173@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 0ad082b566f5e..45ee0774522a1 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -481,7 +481,7 @@ static void mana_serv_reset(struct pci_dev *pdev) /* Perform PCI rescan on device if we failed on HWC */ dev_err(&pdev->dev, "MANA service: resume failed, rescanning\n"); mana_serv_rescan(pdev); - goto out; + return; } if (ret) From ce8ac8432fd72ad48b8445378980dd1a760b41b4 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Mon, 20 Apr 2026 05:47:36 -0700 Subject: [PATCH 1053/1518] net: mana: Init gf_stats_work before potential error paths in probe [ Upstream commit 6e8bc03349fe4f09567fa76235abf52bdaf83082 ] Move INIT_DELAYED_WORK(gf_stats_work) to before mana_create_eq(), while keeping schedule_delayed_work() at its original location. Previously, if any function between mana_create_eq() and the INIT_DELAYED_WORK call failed, mana_probe() would call mana_remove() which unconditionally calls cancel_delayed_work_sync(gf_stats_work) in __flush_work() or debug object warnings with CONFIG_DEBUG_OBJECTS_WORK enabled. Fixes: be4f1d67ec56 ("net: mana: Add standard counter rx_missed_errors") Signed-off-by: Erni Sri Satya Vennela Link: https://patch.msgid.link/20260420124741.1056179-3-ernis@linux.microsoft.com Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/mana_en.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 4b7e5acba7f76..d1eb77d540427 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -3607,6 +3607,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) INIT_WORK(&ac->link_change_work, mana_link_state_handle); } + INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); + err = mana_create_eq(ac); if (err) { dev_err(dev, "Failed to create EQs: %d\n", err); @@ -3680,7 +3682,6 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!err) err = add_adev(gd, "eth"); - INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); out: From ec4f6da3373d21993229ef9f1e16a92045e5acee Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Sun, 3 May 2026 12:45:03 +0200 Subject: [PATCH 1054/1518] sched/fair: Fix wakeup_preempt_fair() for not waking up task [ Upstream commit 9f6d929ee2c6f0266edb564bcd2bd47fd6e884a8 ] Make sure to only call pick_next_entity() on an non-empty cfs_rq. The assumption that p is always enqueued and not delayed, is only true for wakeup. If p was moved while delayed, pick_next_entity() will dequeue it and the cfs might become empty. Test if there are still queued tasks before trying again to determine if p could be the next one to be picked. There are at least 2 cases: When cfs becomes idle, it tries to pull tasks but if those pulled tasks are delayed, they will be dequeued when attached to cfs. attach_tasks() -> attach_task() -> wakeup_preempt(rq, p, 0); A misfit task running on cfs A triggers a load balance to be pulled on a better cpu, the load balance on cfs B starts an active load balance to pulled the running misfit task. If there is a delayed dequeue task on cfs A, it can be pulled instead of the previously running misfit task. attach_one_task() -> attach_task() -> wakeup_preempt(rq, p, 0); Fixes: ac8e69e69363 ("sched/fair: Fix wakeup_preempt_fair() vs delayed dequeue") Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260503104503.1732682-1-vincent.guittot@linaro.org Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 565a96d6811e7..58f535cc64215 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8985,9 +8985,10 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int /* * Because p is enqueued, nse being null can only mean that we - * dequeued a delayed task. + * dequeued a delayed task. If there are still entities queued in + * cfs, check if the next one will be p. */ - if (!nse) + if (!nse && cfs_rq->nr_queued) goto pick; if (sched_feat(RUN_TO_PARITY)) From b4e1c03b876c71b8567b190e66beab8293480763 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 23 Jan 2026 11:28:58 +0100 Subject: [PATCH 1055/1518] sched/fair: Revert force wakeup preemption [ Upstream commit 15257cc2f905dbf5813c0bfdd3c15885f28093c4 ] This agressively bypasses run_to_parity and slice protection with the assumpiton that this is what waker wants but there is no garantee that the wakee will be the next to run. It is a better choice to use yield_to_task or WF_SYNC in such case. This increases the number of resched and preemption because a task becomes quickly "ineligible" when it runs; We update the task vruntime periodically and before the task exhausted its slice or at least quantum. Example: 2 tasks A and B wake up simultaneously with lag = 0. Both are eligible. Task A runs 1st and wakes up task C. Scheduler updates task A's vruntime which becomes greater than average runtime as all others have a lag == 0 and didn't run yet. Now task A is ineligible because it received more runtime than the other task but it has not yet exhausted its slice nor a min quantum. We force preemption, disable protection but Task B will run 1st not task C. Sidenote, DELAY_ZERO increases this effect by clearing positive lag at wake up. Fixes: e837456fdca8 ("sched/fair: Reimplement NEXT_BUDDY to align with EEVDF goals") Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260123102858.52428-1-vincent.guittot@linaro.org Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 58f535cc64215..7e0e2044d840b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8943,16 +8943,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if ((wake_flags & WF_FORK) || pse->sched_delayed) return; - /* - * If @p potentially is completing work required by current then - * consider preemption. - * - * Reschedule if waker is no longer eligible. */ - if (in_task() && !entity_eligible(cfs_rq, se)) { - preempt_action = PREEMPT_WAKEUP_RESCHED; - goto preempt; - } - /* Prefer picking wakee soon if appropriate. */ if (sched_feat(NEXT_BUDDY) && set_preempt_buddy(cfs_rq, wake_flags, pse, se)) { From a1c5672faf8e93e38c2deac3979cc767ca5cf918 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 5 May 2026 17:02:45 +0800 Subject: [PATCH 1056/1518] crypto: af_alg - Cap AEAD AD length to 0x80000000 commit e4c06479d7059888adf2f22bc1ebcf053bf691a2 upstream. In order to prevent arithmetic overflows when checking the TX buffer size, cap the associated data length to 0x80000000. Reported-by: Yiming Qian Fixes: 400c40cf78da ("crypto: algif - add AEAD support") Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/af_alg.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index b61c3ba126ed1..0111d07545931 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -586,6 +586,8 @@ static int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con) if (cmsg->cmsg_len < CMSG_LEN(sizeof(u32))) return -EINVAL; con->aead_assoclen = *(u32 *)CMSG_DATA(cmsg); + if (con->aead_assoclen >= 0x80000000u) + return -EINVAL; break; default: From f4324006879118b25b8e7d2bdb46c891d51b399d Mon Sep 17 00:00:00 2001 From: Matt Vollrath Date: Wed, 6 May 2026 14:48:11 -0700 Subject: [PATCH 1057/1518] i40e: Cleanup PTP pins on probe failure commit 678b713ece1e853f11e670a84cb887c35e1381b7 upstream. PTP pin structs are allocated early in probe, but never cleaned up. Fix this by calling i40e_ptp_free_pins in the error path. To support this, i40e_ptp_free_pins is added to the header and pin_config is correctly nullified after being freed. This has been an issue since i40e_ptp_alloc_pins was introduced. Fixes: 1050713026a08 ("i40e: add support for PTP external synchronization clock") Reported-by: Kohei Enju Cc: stable@vger.kernel.org Signed-off-by: Matt Vollrath Reviewed-by: Paul Menzel Reviewed-by: Aleksandr Loktionov Reviewed-by: Kohei Enju Tested-by: Sunitha Mekala Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260506-jk-iwl-net-2026-05-04-v2-2-a5ea4dc837a9@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_ptp.c | 3 ++- 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index feec9e1e13b36..0cf530a5298ec 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1314,6 +1314,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf); void i40e_ptp_init(struct i40e_pf *pf); void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); +void i40e_ptp_free_pins(struct i40e_pf *pf); int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); int i40e_get_partition_bw_setting(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 9f19370f1c87a..550b0dd58456a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16114,6 +16114,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_clear_interrupt_scheme(pf); kfree(pf->vsi); err_switch_setup: + i40e_ptp_free_pins(pf); i40e_reset_interrupt_capability(pf); timer_shutdown_sync(&pf->service_timer); err_mac_addr: diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 33535418178bd..178ac6e6d6a76 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -940,12 +940,13 @@ int i40e_ptp_hwtstamp_get(struct net_device *netdev, * * Release memory allocated for PTP pins. **/ -static void i40e_ptp_free_pins(struct i40e_pf *pf) +void i40e_ptp_free_pins(struct i40e_pf *pf) { if (i40e_is_ptp_pin_dev(&pf->hw)) { kfree(pf->ptp_pins); kfree(pf->ptp_caps.pin_config); pf->ptp_pins = NULL; + pf->ptp_caps.pin_config = NULL; } } From 10addc25fa17c3404d6e4cfe7db0019a43e774b2 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 8 May 2026 09:22:03 -0700 Subject: [PATCH 1058/1518] workqueue: Fix wq->cpu_pwq leak in alloc_and_link_pwqs() WQ_UNBOUND path commit 0143033dc22cdff912cfc13419f5db92fea3b4cb upstream. For WQ_UNBOUND workqueues, alloc_and_link_pwqs() allocates wq->cpu_pwq via alloc_percpu() and then calls apply_workqueue_attrs_locked(). On failure it returns the error directly, bypassing the enomem: label which holds the only free_percpu(wq->cpu_pwq) in this function. The caller's error path kfree()s wq without touching wq->cpu_pwq, leaking one percpu pointer table (nr_cpu_ids * sizeof(void *) bytes) per failed call. If kmemleak is enabled, we can see: unreferenced object (percpu) 0xc0fffa5b121048 (size 8): comm "insmod", pid 776, jiffies 4294682844 backtrace (crc 0): pcpu_alloc_noprof+0x665/0xac0 __alloc_workqueue+0x33f/0xa20 alloc_workqueue_noprof+0x60/0x100 Route the error through the existing enomem: cleanup and any error before this one. Cc: stable@kernel.org Fixes: 636b927eba5b ("workqueue: Make unbound workqueues to use per-cpu pool_workqueues") Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- kernel/workqueue.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 751b8cba52fc6..a7793c471cfd8 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5619,7 +5619,9 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } - return ret; + if (ret) + goto enomem; + return 0; enomem: if (wq->cpu_pwq) { From 95e8ae9af2a61b4e72f5c585bf4c7d8aaf2a2c98 Mon Sep 17 00:00:00 2001 From: Arthur Kiyanovski Date: Fri, 8 May 2026 06:21:21 +0000 Subject: [PATCH 1059/1518] net: ena: PHC: Fix potential use-after-free in get_timestamp commit e42c755582f0960e684298762f0ab927b3778376 upstream. Move the phc->active check and resp pointer assignment to after acquiring the spinlock. Previously, phc->active was checked without holding the lock, and resp was cached from ena_dev->phc.virt_addr before the lock was acquired. If ena_com_phc_destroy() runs between the lockless active check and the lock acquisition, it sets active=false, releases the lock, frees the DMA memory, and sets virt_addr=NULL. The get_timestamp path would then read a NULL virt_addr and dereference it. With both the active check and the pointer read under the lock, destroy cannot free the memory while get_timestamp is using it. Fixes: e0ea34158ee8 ("net: ena: Add PHC support in the ENA driver") Cc: stable@vger.kernel.org Signed-off-by: Arthur Kiyanovski Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20260508062126.7273-1-akiyano@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/amazon/ena/ena_com.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index e67b592e56976..8c86789d867a5 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -1782,20 +1782,23 @@ void ena_com_phc_destroy(struct ena_com_dev *ena_dev) int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp) { - volatile struct ena_admin_phc_resp *resp = ena_dev->phc.virt_addr; const ktime_t zero_system_time = ktime_set(0, 0); struct ena_com_phc_info *phc = &ena_dev->phc; + volatile struct ena_admin_phc_resp *resp; ktime_t expire_time; ktime_t block_time; unsigned long flags = 0; int ret = 0; + spin_lock_irqsave(&phc->lock, flags); + if (!phc->active) { + spin_unlock_irqrestore(&phc->lock, flags); netdev_err(ena_dev->net_device, "PHC feature is not active in the device\n"); return -EOPNOTSUPP; } - spin_lock_irqsave(&phc->lock, flags); + resp = ena_dev->phc.virt_addr; /* Check if PHC is in blocked state */ if (unlikely(ktime_compare(phc->system_time, zero_system_time))) { From 430b05f6c9183b7d5dc64b2250aaae86c73c61f6 Mon Sep 17 00:00:00 2001 From: Li Xiasong Date: Thu, 7 May 2026 22:04:22 +0800 Subject: [PATCH 1060/1518] netfilter: nf_conntrack_sip: get helper before allocating expectation commit eb6317739b1ea3ab28791e1f91b24781905fa815 upstream. process_register_request() allocates an expectation and then checks whether a conntrack helper is available. If helper lookup fails, the function returns early and the allocated expectation is left behind. Reorder the code to fetch and validate helper before calling nf_ct_expect_alloc(). This keeps the logic simpler and removes the leak path while preserving existing behavior. Fixes: e14575fa7529 ("netfilter: nf_conntrack: use rcu accessors where needed") Cc: stable@vger.kernel.org Signed-off-by: Li Xiasong Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conntrack_sip.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 6eb39285fbd6c..81534213f00f3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1367,6 +1367,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, goto store_cseq; } + helper = rcu_dereference(nfct_help(ct)->helper); + if (!helper) + return NF_DROP; + exp = nf_ct_expect_alloc(ct); if (!exp) { nf_ct_helper_log(skb, ct, "cannot alloc expectation"); @@ -1377,10 +1381,6 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, if (sip_direct_signalling) saddr = &ct->tuplehash[!dir].tuple.src.u3; - helper = rcu_dereference(nfct_help(ct)->helper); - if (!helper) - return NF_DROP; - nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; From e35f3550c5b4fab33103c18654c293cee9850b0a Mon Sep 17 00:00:00 2001 From: Sergio Correia Date: Tue, 12 May 2026 14:28:33 +0100 Subject: [PATCH 1061/1518] audit: fix incorrect inheritable capability in CAPSET records commit e4a640475e43f406fdfd56d370b1f34b0cbbc18d upstream. __audit_log_capset() records the effective capability set into the inheritable field due to a copy-paste error. Every CAPSET audit record therefore reports cap_pi (process inheritable) with the value of cap_effective instead of cap_inheritable. This silently corrupts audit data used for compliance and forensic analysis: an attacker who modifies inheritable capabilities to prepare for a privilege-escalating exec would have the change masked in the audit trail. The bug has been present since the original introduction of CAPSET audit records in 2008. Cc: stable@vger.kernel.org Fixes: e68b75a027bb ("When the capset syscall is used it is not possible for audit to record the actual capbilities being added/removed. This patch adds a new record type which emits the target pid and the eff, inh, and perm cap sets.") Reviewed-by: Ricardo Robaina Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Sergio Correia Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- kernel/auditsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d1966144bdfe7..3e42d32ebb285 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2814,7 +2814,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) context->capset.pid = task_tgid_nr(current); context->capset.cap.effective = new->cap_effective; - context->capset.cap.inheritable = new->cap_effective; + context->capset.cap.inheritable = new->cap_inheritable; context->capset.cap.permitted = new->cap_permitted; context->capset.cap.ambient = new->cap_ambient; context->type = AUDIT_CAPSET; From bddf59818ae5102e6d82a4dae5add6df8da38fb0 Mon Sep 17 00:00:00 2001 From: Arthur Kiyanovski Date: Thu, 7 May 2026 00:35:15 +0000 Subject: [PATCH 1062/1518] net: ena: PHC: Check return code before setting timestamp output commit 24a08d7d6218d60c033015cf4870b6096446e734 upstream. ena_phc_gettimex64() is setting the output parameter regardless of whether ena_com_phc_get_timestamp() succeeded or failed. When ena_com_phc_get_timestamp() returns an error, the timestamp parameter may contain uninitialized stack memory (e.g., when PHC is disabled or in blocked state) or invalid hardware values. Passing these to userspace via the PTP ioctl is both a security issue (information leak) and a correctness bug. Fix by checking the return code after releasing the lock and only setting the output timestamp on success. Fixes: e0ea34158ee8 ("net: ena: Add PHC support in the ENA driver") Cc: stable@vger.kernel.org Signed-off-by: Arthur Kiyanovski Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20260507003518.22554-1-akiyano@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/amazon/ena/ena_phc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.c b/drivers/net/ethernet/amazon/ena/ena_phc.c index 7867e893fd15f..c2a3ff1ef645c 100644 --- a/drivers/net/ethernet/amazon/ena/ena_phc.c +++ b/drivers/net/ethernet/amazon/ena/ena_phc.c @@ -46,9 +46,12 @@ static int ena_phc_gettimex64(struct ptp_clock_info *clock_info, spin_unlock_irqrestore(&phc_info->lock, flags); + if (rc) + return rc; + *ts = ns_to_timespec64(timestamp_nsec); - return rc; + return 0; } static int ena_phc_settime64(struct ptp_clock_info *clock_info, From c4a8998aafb87aeb2d3e0f00e01595e63126b4fb Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Mon, 11 May 2026 09:31:50 +0800 Subject: [PATCH 1063/1518] cgroup/dmem: Return -ENOMEM on failed pool preallocation commit 796ad622040f7f955ccc3973085e953415920496 upstream. get_cg_pool_unlocked() handles allocation failures under dmemcg_lock by dropping the lock, preallocating a pool with GFP_KERNEL, and retrying the locked lookup and creation path. If the fallback allocation fails too, pool remains NULL. Since the loop condition is while (!pool), the function can keep retrying instead of propagating the allocation failure to the caller. Set pool to ERR_PTR(-ENOMEM) when the fallback allocation fails so the loop exits through the existing common return path. The callers already handle ERR_PTR() from get_cg_pool_unlocked(), so this restores the expected error path. Fixes: b168ed458dde ("kernel/cgroup: Add "dmem" memory accounting cgroup") Cc: stable@vger.kernel.org # v6.14+ Signed-off-by: Guopeng Zhang Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/dmem.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index 1ea6afffa985c..250810f22525c 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -602,6 +602,7 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = NULL; continue; } + pool = ERR_PTR(-ENOMEM); } } From 722b91d5086a249318c9d0e2b36aeac80ba8c808 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 6 May 2026 14:48:13 -0700 Subject: [PATCH 1064/1518] idpf: fix double free and use-after-free in aux device error paths commit 6c77b9510829a424d1b74409b7db9456e3522871 upstream. When auxiliary_device_add() fails in idpf_plug_vport_aux_dev() or idpf_plug_core_aux_dev(), the err_aux_dev_add label calls auxiliary_device_uninit() and falls through to err_aux_dev_init. The uninit call will trigger put_device(), which invokes the release callback (idpf_vport_adev_release / idpf_core_adev_release) that frees iadev. The fall-through then reads adev->id from the freed iadev for ida_free() and double-frees iadev with kfree(). Free the IDA slot and clear the back-pointer before uninit, while adev is still valid, then return immediately. Commit 65637c3a1811 ("idpf: fix UAF in RDMA core aux dev deinitialization") fixed the same use-after-free in the matching unplug path in this file but missed both probe error paths. Cc: Tony Nguyen Cc: Przemek Kitszel Cc: Andrew Lunn Cc: stable@kernel.org Fixes: be91128c579c ("idpf: implement RDMA vport auxiliary dev create, init, and destroy") Fixes: f4312e6bfa2a ("idpf: implement core RDMA auxiliary dev create, init, and destroy") Signed-off-by: Greg Kroah-Hartman Reviewed-by: Aleksandr Loktionov Reviewed-by: Paul Menzel Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260506-jk-iwl-net-2026-05-04-v2-4-a5ea4dc837a9@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/idpf/idpf_idc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index 6dad0593f7f22..10a3ee2b8e0d5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -90,7 +90,10 @@ static int idpf_plug_vport_aux_dev(struct iidc_rdma_core_dev_info *cdev_info, return 0; err_aux_dev_add: + ida_free(&idpf_idc_ida, adev->id); + vdev_info->adev = NULL; auxiliary_device_uninit(adev); + return ret; err_aux_dev_init: ida_free(&idpf_idc_ida, adev->id); err_ida_alloc: @@ -228,7 +231,10 @@ static int idpf_plug_core_aux_dev(struct iidc_rdma_core_dev_info *cdev_info) return 0; err_aux_dev_add: + ida_free(&idpf_idc_ida, adev->id); + cdev_info->adev = NULL; auxiliary_device_uninit(adev); + return ret; err_aux_dev_init: ida_free(&idpf_idc_ida, adev->id); err_ida_alloc: From a9f76de38ba32389f8c2e3bc3b7fb1d62e2f8f77 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 4 May 2026 18:01:37 -0500 Subject: [PATCH 1065/1518] Revert "ACPI: CPPC: Adjust debug messages in amd_set_max_freq_ratio() to warn" commit db5dadb562cabb6da49959b473ed0d9645b6f2da upstream. Some older systems don't support CPPC in the firmware and this just makes noise for them when booting. Drop back to debug. This reverts commit 21fb59ab4b9767085f4fe1edbdbe3177fbb9ec97. Fixes: 21fb59ab4b976 ("ACPI: CPPC: Adjust debug messages in amd_set_max_freq_ratio() to warn") Suggested-by: Kim Phillips Signed-off-by: Mario Limonciello Tested-by: Kim Phillips Cc: All applicable Link: https://patch.msgid.link/20260504230141.484743-2-mario.limonciello@amd.com Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/acpi/cppc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index d7c8ef1e354d3..be4c5e9e5ff6f 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -88,19 +88,19 @@ static void amd_set_max_freq_ratio(void) rc = cppc_get_perf_caps(0, &perf_caps); if (rc) { - pr_warn("Could not retrieve perf counters (%d)\n", rc); + pr_debug("Could not retrieve perf counters (%d)\n", rc); return; } rc = amd_get_boost_ratio_numerator(0, &numerator); if (rc) { - pr_warn("Could not retrieve highest performance (%d)\n", rc); + pr_debug("Could not retrieve highest performance (%d)\n", rc); return; } nominal_perf = perf_caps.nominal_perf; if (!nominal_perf) { - pr_warn("Could not retrieve nominal performance\n"); + pr_debug("Could not retrieve nominal performance\n"); return; } From 1dced0725e2fae3ac3416274db20a7ff5a46931d Mon Sep 17 00:00:00 2001 From: Li Xiasong Date: Thu, 7 May 2026 22:04:23 +0800 Subject: [PATCH 1066/1518] netfilter: nft_ct: fix missing expect put in obj eval commit 19f94b6fee75b3ef7fbc06f3745b9a771a8a19a4 upstream. nft_ct_expect_obj_eval() allocates an expectation and may call nf_ct_expect_related(), but never drops its local reference. Add nf_ct_expect_put(exp) before return to balance allocation. Fixes: 857b46027d6f ("netfilter: nft_ct: add ct expectations support") Cc: stable@vger.kernel.org Signed-off-by: Li Xiasong Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nft_ct.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 4f52ca4c48d51..8dbf31e7ddcbe 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1382,6 +1382,8 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; + + nf_ct_expect_put(exp); } static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = { From e029cbd8c06d0698aceb2141b3dfd997c9805c38 Mon Sep 17 00:00:00 2001 From: Zoran Ilievski Date: Mon, 11 May 2026 08:40:02 +0200 Subject: [PATCH 1067/1518] net: atlantic: preserve PCI wake-from-D3 on shutdown when WOL enabled commit 2c308cf34284420963607d677d576a2b4124d8bd upstream. The shutdown handler aq_pci_shutdown() unconditionally calls pci_wake_from_d3(pdev, false), clearing the PCI PME_En bit even when wake-on-LAN has been configured. While aq_nic_shutdown() correctly programs the NIC firmware via aq_nic_set_power() to listen for magic packets, the PCI subsystem will not propagate the resulting PME wake event from D3, so the system never wakes after poweroff. WOL from suspend (S3) is unaffected because aq_suspend_common() does not touch pci_wake_from_d3() and relies on the PM core's wake configuration via device_may_wakeup(). This affects all atlantic-supported NICs (AQC107/108/111/112/113); users have reported that WOL works if the atlantic driver is never loaded, but breaks once it has run its shutdown path. Pass the configured WOL state to pci_wake_from_d3() instead of a literal false, so the PCI PME_En bit is preserved when the user has armed WOL via ethtool. Fixes: 90869ddfefeb ("net: aquantia: Implement pci shutdown callback") Cc: stable@vger.kernel.org Signed-off-by: Zoran Ilievski Reviewed-by: Sukhdeep Singh Link: https://patch.msgid.link/20260511064002.1857-1-goodboy@rexbytes.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index ed5231dece3f9..80bf71e1a9ce9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -371,7 +371,7 @@ static void aq_pci_shutdown(struct pci_dev *pdev) pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - pci_wake_from_d3(pdev, false); + pci_wake_from_d3(pdev, self->aq_hw->aq_nic_cfg->wol); pci_set_power_state(pdev, PCI_D3hot); } } From d9017d2332582dfd6357606f11d3347c902c3e3a Mon Sep 17 00:00:00 2001 From: Sergio Correia Date: Tue, 12 May 2026 14:28:59 +0100 Subject: [PATCH 1068/1518] audit: enforce AUDIT_LOCKED for AUDIT_TRIM and AUDIT_MAKE_EQUIV commit f9e1c1324b4d98d591a6f7568fdebf5cf456dfc2 upstream. AUDIT_ADD_RULE and AUDIT_DEL_RULE correctly check for AUDIT_LOCKED and return -EPERM, but AUDIT_TRIM and AUDIT_MAKE_EQUIV do not. This allows a process with CAP_AUDIT_CONTROL to modify directory tree watches and equivalence mappings even when the audit configuration has been locked, undermining the purpose of the lock. Add AUDIT_LOCKED checks to both commands. Cc: stable@vger.kernel.org Reviewed-by: Ricardo Robaina Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Sergio Correia Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- kernel/audit.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/audit.c b/kernel/audit.c index 26a332ffb1b8d..7bbd05cc3d6a5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1462,6 +1462,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: + if (audit_enabled == AUDIT_LOCKED) + return -EPERM; audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); @@ -1474,6 +1476,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, size_t msglen = data_len; char *old, *new; + if (audit_enabled == AUDIT_LOCKED) + return -EPERM; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; From 0d419c23bb11b5c9664de777c47c1f04a235882d Mon Sep 17 00:00:00 2001 From: Aaron Sacks Date: Tue, 12 May 2026 02:07:42 -0400 Subject: [PATCH 1069/1518] KVM: Reject wrapped offset in kvm_reset_dirty_gfn() commit 577a8d3bae0531f0e5ccfac919cd8192f920a804 upstream. kvm_reset_dirty_gfn() guards the gfn range with if (!memslot || (offset + __fls(mask)) >= memslot->npages) return; but offset is u64 and the addition is unchecked. The check can be silently bypassed by a u64 wrap. The dirty ring backing those entries is MAP_SHARED at KVM_DIRTY_LOG_PAGE_OFFSET of the vcpu fd, so the VMM can rewrite the slot and offset fields of any entry between when the kernel pushes them and when KVM_RESET_DIRTY_RINGS consumes them. On reset, kvm_dirty_ring_reset() re-reads the values via READ_ONCE() and feeds them straight back into this check; only the flags handshake is treated as the handover, the slot/offset payload is taken on trust. Crafting two entries entry[i].offset = 0xffffffffffffffc1 entry[i+1].offset = 0 makes the coalescing loop in kvm_dirty_ring_reset() compute delta = (s64)(0 - 0xffffffffffffffc1) = 63 which falls in [0, BITS_PER_LONG), so it folds entry[i+1] into the existing mask by setting bit 63. The trailing kvm_reset_dirty_gfn() call then sees offset = 0xffffffffffffffc1 and __fls(mask) = 63; the sum is 0 in u64 and the bounds check passes. That offset propagates into kvm_arch_mmu_enable_log_dirty_pt_masked() unchanged. On the legacy MMU path -- kvm_memslots_have_rmaps() == true, i.e. shadow paging, any VM that has allocated shadow roots, or a write-tracked slot -- it reaches gfn_to_rmap(), which indexes slot->arch.rmap[0][] with a near-U64_MAX gfn. That is an out-of-bounds load of a kvm_rmap_head, followed by a conditional clear of PT_WRITABLE_MASK in whatever the loaded pointer points at. The path is reachable from any process holding /dev/kvm. Range-check offset on its own first, so the addition cannot wrap. memslot->npages is bounded well below U64_MAX, so once offset < npages holds, offset + __fls(mask) (with __fls(mask) < BITS_PER_LONG) stays in range. Fixes: fb04a1eddb1a ("KVM: X86: Implement ring-based dirty memory tracking") Cc: stable@vger.kernel.org Signed-off-by: Aaron Sacks Link: https://patch.msgid.link/20260512060742.1628959-1-contact@xchglabs.com/ Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- virt/kvm/dirty_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 02bc6b00d76cb..572b854edf740 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -63,7 +63,8 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); - if (!memslot || (offset + __fls(mask)) >= memslot->npages) + if (!memslot || offset >= memslot->npages || + offset + __fls(mask) >= memslot->npages) return; KVM_MMU_LOCK(kvm); From b22a2da8792a7bfe743c1a922e77fa499ddedbe8 Mon Sep 17 00:00:00 2001 From: Junrui Luo Date: Wed, 15 Apr 2026 17:26:55 +0800 Subject: [PATCH 1070/1518] KVM: s390: pci: fix GAIT table indexing due to double-scaling pointer arithmetic commit 16d990a15491cf76cd6eef0846e1b4100e63261a upstream. kvm_s390_pci_aif_enable(), kvm_s390_pci_aif_disable(), and aen_host_forward() index the GAIT by manually multiplying the index with sizeof(struct zpci_gaite). Since aift->gait is already a struct zpci_gaite pointer, this double-scales the offset, accessing element aisb*16 instead of aisb. This causes out-of-bounds accesses when aisb >= 32 (with ZPCI_NR_DEVICES=512) Fix by removing the erroneous sizeof multiplication. Fixes: 3c5a1b6f0a18 ("KVM: s390: pci: provide routines for enabling/disabling interrupt forwarding") Fixes: 73f91b004321 ("KVM: s390: pci: enable host forwarding of Adapter Event Notifications") Reported-by: Yuhao Jiang Cc: stable@vger.kernel.org Signed-off-by: Junrui Luo Reviewed-by: Christian Borntraeger Reviewed-by: Matthew Rosato Tested-by: Matthew Rosato Signed-off-by: Christian Borntraeger Signed-off-by: Greg Kroah-Hartman --- arch/s390/kvm/interrupt.c | 3 +-- arch/s390/kvm/pci.c | 6 ++---- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c62a868cf2b6e..7b4e1deb07dbd 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3334,8 +3334,7 @@ static void aen_host_forward(unsigned long si) struct zpci_gaite *gaite; struct kvm *kvm; - gaite = (struct zpci_gaite *)aift->gait + - (si * sizeof(struct zpci_gaite)); + gaite = aift->gait + si; if (gaite->count == 0) return; if (gaite->aisb != 0) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 8c40154ff50ff..26cb4568732cd 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -291,8 +291,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, phys_to_virt(fib->fmt0.aibv)); spin_lock_irq(&aift->gait_lock); - gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * - sizeof(struct zpci_gaite)); + gaite = aift->gait + zdev->aisb; /* If assist not requested, host will get all alerts */ if (assist) @@ -358,8 +357,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) if (zdev->kzdev->fib.fmt0.aibv == 0) goto out; spin_lock_irq(&aift->gait_lock); - gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * - sizeof(struct zpci_gaite)); + gaite = aift->gait + zdev->aisb; isc = gaite->gisc; gaite->count--; if (gaite->count == 0) { From 8adc988e9f2061501340697d9ef581f09891253b Mon Sep 17 00:00:00 2001 From: Qiang Ma Date: Tue, 12 May 2026 09:53:13 +0800 Subject: [PATCH 1071/1518] KVM: x86: Fix Xen hypercall tracepoint argument assignment commit 2b72f1674e427c56e3772c5ccf785fdda2138820 upstream. TRACE_EVENT(kvm_xen_hypercall) stores a5 in __entry->a4 instead of __entry->a5. That overwrites the recorded a4 argument and leaves a5 unset in the trace entry. Fix the typo so both arguments are captured correctly. Signed-off-by: Qiang Ma Link: https://patch.msgid.link/20260512015313.1685784-1-maqianga@uniontech.com/ Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index e79bc9cb71623..3594bbe2cab2c 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -154,7 +154,7 @@ TRACE_EVENT(kvm_xen_hypercall, __entry->a2 = a2; __entry->a3 = a3; __entry->a4 = a4; - __entry->a4 = a5; + __entry->a5 = a5; ), TP_printk("cpl %d nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", From 509c2605065004fc4cd86ee50a9350d402785307 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Mon, 4 May 2026 10:47:22 +0200 Subject: [PATCH 1072/1518] HID: pass the buffer size to hid_report_raw_event [ Upstream commit 2c85c61d1332e1e16f020d76951baf167dcb6f7a ] commit 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing bogus memset()") enforced the provided data to be at least the size of the declared buffer in the report descriptor to prevent a buffer overflow. However, we can try to be smarter by providing both the buffer size and the data size, meaning that hid_report_raw_event() can make better decision whether we should plaining reject the buffer (buffer overflow attempt) or if we can safely memset it to 0 and pass it to the rest of the stack. Fixes: 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing bogus memset()") Cc: stable@vger.kernel.org Signed-off-by: Benjamin Tissoires Acked-by: Johan Hovold Reviewed-by: Greg Kroah-Hartman Signed-off-by: Jiri Kosina Stable-dep-of: 206342541fc8 ("HID: core: introduce hid_safe_input_report()") Signed-off-by: Sasha Levin --- drivers/hid/bpf/hid_bpf_dispatch.c | 6 +++-- drivers/hid/hid-core.c | 42 ++++++++++++++++++++---------- drivers/hid/hid-gfrm.c | 4 +-- drivers/hid/hid-logitech-hidpp.c | 2 +- drivers/hid/hid-multitouch.c | 2 +- drivers/hid/hid-primax.c | 2 +- drivers/hid/hid-vivaldi-common.c | 2 +- drivers/hid/wacom_sys.c | 6 ++--- drivers/staging/greybus/hid.c | 2 +- include/linux/hid.h | 4 +-- include/linux/hid_bpf.h | 14 ++++++---- 11 files changed, 53 insertions(+), 33 deletions(-) diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index cf465a5fe43af..eb9f40c988d02 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -24,7 +24,8 @@ EXPORT_SYMBOL(hid_ops); u8 * dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type, u8 *data, - u32 *size, int interrupt, u64 source, bool from_bpf) + size_t *buf_size, u32 *size, int interrupt, u64 source, + bool from_bpf) { struct hid_bpf_ctx_kern ctx_kern = { .ctx = { @@ -74,6 +75,7 @@ dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type *size = ret; } + *buf_size = ctx_kern.ctx.allocated_size; return ctx_kern.data; } EXPORT_SYMBOL_GPL(dispatch_hid_bpf_device_event); @@ -508,7 +510,7 @@ __hid_bpf_input_report(struct hid_bpf_ctx *ctx, enum hid_report_type type, u8 *b if (ret) return ret; - return hid_ops->hid_input_report(ctx->hid, type, buf, size, 0, (u64)(long)ctx, true, + return hid_ops->hid_input_report(ctx->hid, type, buf, size, size, 0, (u64)(long)ctx, true, lock_already_taken); } diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 8be4e06af4636..9e8eb727c6c98 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2029,24 +2029,32 @@ int __hid_request(struct hid_device *hid, struct hid_report *report, } EXPORT_SYMBOL_GPL(__hid_request); -int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, - int interrupt) +int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt) { struct hid_report_enum *report_enum = hid->report_enum + type; struct hid_report *report; struct hid_driver *hdrv; int max_buffer_size = HID_MAX_BUFFER_SIZE; u32 rsize, csize = size; + size_t bsize = bufsize; u8 *cdata = data; int ret = 0; report = hid_get_report(report_enum, data); if (!report) - goto out; + return 0; + + if (unlikely(bsize < csize)) { + hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n", + report->id, csize, bsize); + return -EINVAL; + } if (report_enum->numbered) { cdata++; csize--; + bsize--; } rsize = hid_compute_report_size(report); @@ -2059,11 +2067,16 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * else if (rsize > max_buffer_size) rsize = max_buffer_size; + if (bsize < rsize) { + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n", + report->id, rsize, bsize); + return -EINVAL; + } + if (csize < rsize) { - hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %d)\n", - report->id, rsize, csize); - ret = -EINVAL; - goto out; + dbg_hid("report %d is too short, (%d < %d)\n", report->id, + csize, rsize); + memset(cdata + csize, 0, rsize - csize); } if ((hid->claimed & HID_CLAIMED_HIDDEV) && hid->hiddev_report_event) @@ -2071,7 +2084,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * if (hid->claimed & HID_CLAIMED_HIDRAW) { ret = hidraw_report_event(hid, data, size); if (ret) - goto out; + return ret; } if (hid->claimed != HID_CLAIMED_HIDRAW && report->maxfield) { @@ -2083,15 +2096,15 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * if (hid->claimed & HID_CLAIMED_INPUT) hidinput_report_event(hid, report); -out: + return ret; } EXPORT_SYMBOL_GPL(hid_report_raw_event); static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, - bool lock_already_taken) + u8 *data, size_t bufsize, u32 size, int interrupt, u64 source, + bool from_bpf, bool lock_already_taken) { struct hid_report_enum *report_enum; struct hid_driver *hdrv; @@ -2116,7 +2129,8 @@ static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, report_enum = hid->report_enum + type; hdrv = hid->driver; - data = dispatch_hid_bpf_device_event(hid, type, data, &size, interrupt, source, from_bpf); + data = dispatch_hid_bpf_device_event(hid, type, data, &bufsize, &size, interrupt, + source, from_bpf); if (IS_ERR(data)) { ret = PTR_ERR(data); goto unlock; @@ -2145,7 +2159,7 @@ static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, goto unlock; } - ret = hid_report_raw_event(hid, type, data, size, interrupt); + ret = hid_report_raw_event(hid, type, data, bufsize, size, interrupt); unlock: if (!lock_already_taken) @@ -2167,7 +2181,7 @@ static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt) { - return __hid_input_report(hid, type, data, size, interrupt, 0, + return __hid_input_report(hid, type, data, size, size, interrupt, 0, false, /* from_bpf */ false /* lock_already_taken */); } diff --git a/drivers/hid/hid-gfrm.c b/drivers/hid/hid-gfrm.c index 699186ff2349e..d2a56bf92b416 100644 --- a/drivers/hid/hid-gfrm.c +++ b/drivers/hid/hid-gfrm.c @@ -66,7 +66,7 @@ static int gfrm_raw_event(struct hid_device *hdev, struct hid_report *report, switch (data[1]) { case GFRM100_SEARCH_KEY_DOWN: ret = hid_report_raw_event(hdev, HID_INPUT_REPORT, search_key_dn, - sizeof(search_key_dn), 1); + sizeof(search_key_dn), sizeof(search_key_dn), 1); break; case GFRM100_SEARCH_KEY_AUDIO_DATA: @@ -74,7 +74,7 @@ static int gfrm_raw_event(struct hid_device *hdev, struct hid_report *report, case GFRM100_SEARCH_KEY_UP: ret = hid_report_raw_event(hdev, HID_INPUT_REPORT, search_key_up, - sizeof(search_key_up), 1); + sizeof(search_key_up), sizeof(search_key_up), 1); break; default: diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index faef80cb2adbd..2eb67d0caebb2 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3664,7 +3664,7 @@ static int hidpp10_consumer_keys_raw_event(struct hidpp_device *hidpp, memcpy(&consumer_report[1], &data[3], 4); /* We are called from atomic context */ hid_report_raw_event(hidpp->hid_dev, HID_INPUT_REPORT, - consumer_report, 5, 1); + consumer_report, sizeof(consumer_report), 5, 1); return 1; } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 21bfaf9bbd733..a543d48221070 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -531,7 +531,7 @@ static void mt_get_feature(struct hid_device *hdev, struct hid_report *report) } ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf, - size, 0); + size, size, 0); if (ret) dev_warn(&hdev->dev, "failed to report feature\n"); } diff --git a/drivers/hid/hid-primax.c b/drivers/hid/hid-primax.c index e44d79dff8de6..8db054280afbc 100644 --- a/drivers/hid/hid-primax.c +++ b/drivers/hid/hid-primax.c @@ -44,7 +44,7 @@ static int px_raw_event(struct hid_device *hid, struct hid_report *report, data[0] |= (1 << (data[idx] - 0xE0)); data[idx] = 0; } - hid_report_raw_event(hid, HID_INPUT_REPORT, data, size, 0); + hid_report_raw_event(hid, HID_INPUT_REPORT, data, size, size, 0); return 1; default: /* unknown report */ diff --git a/drivers/hid/hid-vivaldi-common.c b/drivers/hid/hid-vivaldi-common.c index bf734055d4b69..b12bb5cc091aa 100644 --- a/drivers/hid/hid-vivaldi-common.c +++ b/drivers/hid/hid-vivaldi-common.c @@ -85,7 +85,7 @@ void vivaldi_feature_mapping(struct hid_device *hdev, } ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, report_data, - report_len, 0); + report_len, report_len, 0); if (ret) { dev_warn(&hdev->dev, "failed to report feature %d\n", field->report->id); diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 9a57504e51a19..a448cfcca4c47 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -90,7 +90,7 @@ static void wacom_wac_queue_flush(struct hid_device *hdev, kfree(buf); continue; } - err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, false); + err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, size, false); if (err) { hid_warn(hdev, "%s: unable to flush event due to error %d\n", __func__, err); @@ -334,7 +334,7 @@ static void wacom_feature_mapping(struct hid_device *hdev, data, n, WAC_CMD_RETRIES); if (ret == n && features->type == HID_GENERIC) { ret = hid_report_raw_event(hdev, - HID_FEATURE_REPORT, data, n, 0); + HID_FEATURE_REPORT, data, n, n, 0); } else if (ret == 2 && features->type != HID_GENERIC) { features->touch_max = data[1]; } else { @@ -395,7 +395,7 @@ static void wacom_feature_mapping(struct hid_device *hdev, data, n, WAC_CMD_RETRIES); if (ret == n) { ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, - data, n, 0); + data, n, n, 0); } else { hid_warn(hdev, "%s: could not retrieve sensor offsets\n", __func__); diff --git a/drivers/staging/greybus/hid.c b/drivers/staging/greybus/hid.c index 63c77a3df5911..afa78c96ede89 100644 --- a/drivers/staging/greybus/hid.c +++ b/drivers/staging/greybus/hid.c @@ -201,7 +201,7 @@ static void gb_hid_init_report(struct gb_hid *ghid, struct hid_report *report) * we just need to setup the input fields, so using * hid_report_raw_event is safe. */ - hid_report_raw_event(ghid->hid, report->type, ghid->inbuf, size, 1); + hid_report_raw_event(ghid->hid, report->type, ghid->inbuf, ghid->bufsize, size, 1); } static void gb_hid_init_reports(struct gb_hid *ghid) diff --git a/include/linux/hid.h b/include/linux/hid.h index a4ddb94e3ee56..d29efcf2e0789 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1258,8 +1258,8 @@ static inline u32 hid_report_len(struct hid_report *report) return DIV_ROUND_UP(report->size, 8) + (report->id > 0); } -int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, - int interrupt); +int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt); /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index a2e47dbcf82c8..19fffa4574a47 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -72,8 +72,8 @@ struct hid_ops { int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len, u64 source, bool from_bpf); int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, - bool lock_already_taken); + u8 *data, size_t bufsize, u32 size, int interrupt, u64 source, + bool from_bpf, bool lock_already_taken); struct module *owner; const struct bus_type *bus_type; }; @@ -200,7 +200,8 @@ struct hid_bpf { #ifdef CONFIG_HID_BPF u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data, - u32 *size, int interrupt, u64 source, bool from_bpf); + size_t *buf_size, u32 *size, int interrupt, u64 source, + bool from_bpf); int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, u32 size, enum hid_report_type rtype, @@ -215,8 +216,11 @@ int hid_bpf_device_init(struct hid_device *hid); const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size); #else /* CONFIG_HID_BPF */ static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 *size, int interrupt, - u64 source, bool from_bpf) { return data; } + u8 *data, size_t *buf_size, u32 *size, + int interrupt, u64 source, bool from_bpf) +{ + return data; +} static inline int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, unsigned char reportnum, u8 *buf, u32 size, enum hid_report_type rtype, From 301338b8edadc67a42b1c86add975091e66768d9 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Mon, 4 May 2026 10:47:23 +0200 Subject: [PATCH 1073/1518] HID: core: introduce hid_safe_input_report() [ Upstream commit 206342541fc887ae919774a43942dc883161fece ] hid_input_report() is used in too many places to have a commit that doesn't cross subsystem borders. Instead of changing the API, introduce a new one when things matters in the transport layers: - usbhid - i2chid This effectively revert to the old behavior for those two transport layers. Fixes: 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing bogus memset()") Cc: stable@vger.kernel.org Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-core.c | 25 +++++++++++++++++++++++++ drivers/hid/i2c-hid/i2c-hid-core.c | 7 ++++--- drivers/hid/usbhid/hid-core.c | 11 ++++++----- include/linux/hid.h | 2 ++ 4 files changed, 37 insertions(+), 8 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 9e8eb727c6c98..e67ea3a7d1395 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2177,6 +2177,7 @@ static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, * @interrupt: distinguish between interrupt and control transfers * * This is data entry for lower layers. + * Legacy, please use hid_safe_input_report() instead. */ int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt) @@ -2187,6 +2188,30 @@ int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data } EXPORT_SYMBOL_GPL(hid_input_report); +/** + * hid_safe_input_report - report data from lower layer (usb, bt...) + * + * @hid: hid device + * @type: HID report type (HID_*_REPORT) + * @data: report contents + * @bufsize: allocated size of the data buffer + * @size: useful size of data parameter + * @interrupt: distinguish between interrupt and control transfers + * + * This is data entry for lower layers. + * Please use this function instead of the non safe version because we provide + * here the size of the buffer, allowing hid-core to make smarter decisions + * regarding the incoming buffer. + */ +int hid_safe_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt) +{ + return __hid_input_report(hid, type, data, bufsize, size, interrupt, 0, + false, /* from_bpf */ + false /* lock_already_taken */); +} +EXPORT_SYMBOL_GPL(hid_safe_input_report); + bool hid_match_one_id(const struct hid_device *hdev, const struct hid_device_id *id) { diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 5a183af3d5c6a..e0a302544cef4 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -574,9 +574,10 @@ static void i2c_hid_get_input(struct i2c_hid *ihid) if (ihid->hid->group != HID_GROUP_RMI) pm_wakeup_event(&ihid->client->dev, 0); - hid_input_report(ihid->hid, HID_INPUT_REPORT, - ihid->inbuf + sizeof(__le16), - ret_size - sizeof(__le16), 1); + hid_safe_input_report(ihid->hid, HID_INPUT_REPORT, + ihid->inbuf + sizeof(__le16), + ihid->bufsize - sizeof(__le16), + ret_size - sizeof(__le16), 1); } return; diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index df3cc89dfb37f..4a493b46d9ee7 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -283,9 +283,9 @@ static void hid_irq_in(struct urb *urb) break; usbhid_mark_busy(usbhid); if (!test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { - hid_input_report(urb->context, HID_INPUT_REPORT, - urb->transfer_buffer, - urb->actual_length, 1); + hid_safe_input_report(urb->context, HID_INPUT_REPORT, + urb->transfer_buffer, urb->transfer_buffer_length, + urb->actual_length, 1); /* * autosuspend refused while keys are pressed * because most keyboards don't wake up when @@ -482,9 +482,10 @@ static void hid_ctrl(struct urb *urb) switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) - hid_input_report(urb->context, + hid_safe_input_report(urb->context, usbhid->ctrl[usbhid->ctrltail].report->type, - urb->transfer_buffer, urb->actual_length, 0); + urb->transfer_buffer, urb->transfer_buffer_length, + urb->actual_length, 0); break; case -ESHUTDOWN: /* unplug */ unplug = 1; diff --git a/include/linux/hid.h b/include/linux/hid.h index d29efcf2e0789..204ada8d12e5c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -990,6 +990,8 @@ struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_ty int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt); +int hid_safe_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); From 3ab135238832446399614e7a4bb796d620717806 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sun, 17 May 2026 13:51:01 +0900 Subject: [PATCH 1074/1518] HID: core: Fix size_t specifier in hid_report_raw_event() [ Upstream commit 4d3a2a466b8d68d852a1f3bbf11204b718428dc4 ] When building for 32-bit platforms, for which 'size_t' is 'unsigned int', there are warnings around using the incorrect format specifier to print bsize in hid_report_raw_event(): drivers/hid/hid-core.c:2054:29: error: format specifies type 'long' but the argument has type 'size_t' (aka 'unsigned int') [-Werror,-Wformat] 2053 | hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n", | ~~~ | %zu 2054 | report->id, csize, bsize); | ^~~~~ drivers/hid/hid-core.c:2076:29: error: format specifies type 'long' but the argument has type 'size_t' (aka 'unsigned int') [-Werror,-Wformat] 2075 | hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n", | ~~~ | %zu 2076 | report->id, rsize, bsize); | ^~~~~ Use the proper 'size_t' format specifier, '%zu', to clear up the warnings. Cc: stable@vger.kernel.org Fixes: 2c85c61d1332 ("HID: pass the buffer size to hid_report_raw_event") Reported-by: Miguel Ojeda Closes: https://lore.kernel.org/20260516020430.110135-1-ojeda@kernel.org/ Signed-off-by: Nathan Chancellor Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- drivers/hid/hid-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index e67ea3a7d1395..6a1600af30e20 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2046,7 +2046,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * return 0; if (unlikely(bsize < csize)) { - hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n", + hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n", report->id, csize, bsize); return -EINVAL; } @@ -2068,7 +2068,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * rsize = max_buffer_size; if (bsize < rsize) { - hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n", + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %zu)\n", report->id, rsize, bsize); return -EINVAL; } From d92229dfa3f9fdf91d9158a5854693511f1b1f2c Mon Sep 17 00:00:00 2001 From: Vlad Poenaru Date: Tue, 19 May 2026 10:48:16 -0700 Subject: [PATCH 1075/1518] fuse: avoid 0x10 fault in fuse_readahead when max_pages == 0 [ Upstream commit 4ea907108a5c ("fuse: use iomap for readahead") ] The upstream fix is the iomap conversion in commit 4ea907108a5c ("fuse: use iomap for readahead"), which rewrote fuse_readahead() entirely and removed the buggy loop along with it. That refactor is too invasive to backport to the pre-iomap readahead path still used by 6.18.y (and earlier stable branches), so this is a minimal, equivalent fix to the same bug on those branches. When fc->max_read is smaller than PAGE_SIZE (common on aarch64 with 64K base pages if the FUSE server advertises a small max_read in INIT), max_pages = min(fc->max_pages, fc->max_read / PAGE_SIZE) is 0, so cur_pages is 0 on every outer iteration. fuse_io_alloc(NULL, 0) then calls fuse_folios_alloc(0, ...), which calls kzalloc(0, ...) and gets back ZERO_SIZE_PTR == (void *)16. The "if (!ia->ap.folios)" guard in fuse_io_alloc does not catch ZERO_SIZE_PTR, so fuse_io_alloc happily returns an ia whose ap.folios is 0x10. The inner "while (pages < cur_pages)" loop runs zero times, then fuse_send_readpages(ia, ...) dereferences ap->folios[0] in folio_pos(), faulting at virtual address 0x10: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 fuse_readahead+0x14c/0x490 read_pages+0x80/0x318 page_cache_ra_unbounded+0x1c0/0x2b0 page_cache_ra_order+0xb8/0x368 page_cache_sync_ra+0x210/0x320 filemap_get_pages+0x290/0xdb0 generic_file_read_iter+0xd0/0x540 fuse_file_read_iter+0x8c/0x158 __arm64_sys_read+0x1a0/0x488 addr2line on the aarch64 vmlinux maps fuse_readahead+0x14c to fs/fuse/file.c:897 inlined into :999, i.e. "folio_pos(ap->folios[0])" inside fuse_send_readpages. The faulting instruction "ldr x8, [x8]" loads ap->folios[0]; ap->folios was previously loaded as 0x10 (ZERO_SIZE_PTR). Without this fix the function would also spin forever, since "nr_pages -= pages" makes no progress when pages stays 0; in practice the NULL deref masks the spin. Bail out of the outer loop if cur_pages is 0 -- there is no work we can issue via FUSE in this iteration, and remaining folios will be handled by read_pages() falling back to ->read_folio. Fixes: 3eab9d7bc2f4 ("fuse: convert readahead to use folios") Reported-by: Breno Leitao Reviewed-by: Joanne Koong Signed-off-by: Vlad Poenaru Signed-off-by: Sasha Levin --- fs/fuse/file.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 6014d588845cd..7821781245121 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -974,6 +974,16 @@ static void fuse_readahead(struct readahead_control *rac) unsigned cur_pages = min(max_pages, nr_pages); unsigned int pages = 0; + /* + * If max_pages == 0 (e.g. fc->max_read < PAGE_SIZE on a + * 64K-page kernel), cur_pages is 0 and we cannot make + * progress. Bailing here avoids passing 0 to fuse_io_alloc, + * which would return an ia whose ap.folios is ZERO_SIZE_PTR + * (0x10) -- later dereferenced by fuse_send_readpages. + */ + if (!cur_pages) + break; + if (fc->num_background >= fc->congestion_threshold && rac->ra->async_size >= readahead_count(rac)) /* From 7c96f2e5b6fbb870062c9cdde98a2dabefba6ad8 Mon Sep 17 00:00:00 2001 From: Igor Pylypiv Date: Sun, 12 Apr 2026 08:36:37 -0700 Subject: [PATCH 1076/1518] ata: libata-scsi: fix requeue of deferred ATA PASS-THROUGH commands [ Upstream commit 8ebf408e7d463eee02c348a3c8277b95587b710d ] Commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") introduced ata_scsi_requeue_deferred_qc() to handle commands deferred during resets or NCQ failures. This deferral logic completed commands with DID_SOFT_ERROR to trigger a retry in the SCSI mid-layer. However, DID_SOFT_ERROR is subject to scsi_cmd_retry_allowed() checks. ATA PASS-THROUGH commands sent via SG_IO ioctl have scmd->allowed set to zero. This causes the mid-layer to fail the command immediately instead of retrying, even though the command was never actually issued to the hardware. Switch to DID_REQUEUE to ensure these commands are inserted back into the request queue regardless of retry limits. Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Reviewed-by: Damien Le Moal Signed-off-by: Igor Pylypiv Signed-off-by: Niklas Cassel Signed-off-by: Sasha Levin --- drivers/ata/libata-scsi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 88689369db03d..e7c78b8d3c2c0 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1691,7 +1691,7 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap) /* * If we have a deferred qc when a reset occurs or NCQ commands fail, * do not try to be smart about what to do with this deferred command - * and simply retry it by completing it with DID_SOFT_ERROR. + * and simply requeue it by completing it with DID_REQUEUE. */ if (!qc) return; @@ -1700,7 +1700,7 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap) ap->deferred_qc = NULL; cancel_work(&ap->deferred_qc_work); ata_qc_free(qc); - scmd->result = (DID_SOFT_ERROR << 16); + scmd->result = (DID_REQUEUE << 16); scsi_done(scmd); } From 151cfe527f0a38d9ed3a1e53837a1c8d46a9a283 Mon Sep 17 00:00:00 2001 From: Michael Tretter Date: Tue, 19 May 2026 16:14:36 +0200 Subject: [PATCH 1077/1518] media: staging: imx: configure src_mux in csi_start [ Upstream commit ebeec2b000a90cd8aae86d1931ff5ef23af8284e ] After media_pipeline_start() was called, the media graph is assumed to be validated. It won't be validated again if a second stream starts. The imx-media-csi driver, however, changes hardware configuration in the link_validate() callback. This can result in started streams with misconfigured hardware. In the concrete example, the ipu2_csi1 is driven by a parallel video input. After the media pipeline has been started with this configuration, a second stream is configured to use ipu1_csi0 with MIPI-CSI input from imx6-mipi-csi2. This may require the reconfiguration of ipu1_csi0 with ipu_set_csi_src_mux(). Since the media pipeline is already running, link_validate won't be called, and the ipu1_csi0 won't be reconfigured. The resulting video is broken, because the ipu1_csi0 is misconfigured, but no error is reported. Move ipu_set_csi_src_mux from csi_link_validate to csi_start to ensure that input to ipu1_csi0 is configured correctly when starting the stream. This is a local reconfiguration in ipu1_csi0 and is possible while the media pipeline is running. Since csi_start() is called with priv->lock already locked, csi_set_src() must not lock priv->lock again. Thus, the mutex_lock() is dropped. Signed-off-by: Michael Tretter Fixes: 4a34ec8e470c ("[media] media: imx: Add CSI subdev driver") Cc: stable@vger.kernel.org Reviewed-by: Frank Li Reviewed-by: Philipp Zabel Signed-off-by: Frank Li Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/staging/media/imx/imx-media-csi.c | 44 ++++++++++++----------- 1 file changed, 24 insertions(+), 20 deletions(-) diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c index 55a7d8f38465b..1bc644f73a9d1 100644 --- a/drivers/staging/media/imx/imx-media-csi.c +++ b/drivers/staging/media/imx/imx-media-csi.c @@ -744,6 +744,28 @@ static int csi_setup(struct csi_priv *priv, return 0; } +static void csi_set_src(struct csi_priv *priv, + struct v4l2_mbus_config *mbus_cfg) +{ + bool is_csi2; + + is_csi2 = !is_parallel_bus(mbus_cfg); + if (is_csi2) { + /* + * NOTE! It seems the virtual channels from the mipi csi-2 + * receiver are used only for routing by the video mux's, + * or for hard-wired routing to the CSI's. Once the stream + * enters the CSI's however, they are treated internally + * in the IPU as virtual channel 0. + */ + ipu_csi_set_mipi_datatype(priv->csi, 0, + &priv->format_mbus[CSI_SINK_PAD]); + } + + /* select either parallel or MIPI-CSI2 as input to CSI */ + ipu_set_csi_src_mux(priv->ipu, priv->csi_id, is_csi2); +} + static int csi_start(struct csi_priv *priv) { struct v4l2_mbus_config mbus_cfg = { .type = 0 }; @@ -760,6 +782,8 @@ static int csi_start(struct csi_priv *priv) input_fi = &priv->frame_interval[CSI_SINK_PAD]; output_fi = &priv->frame_interval[priv->active_output_pad]; + csi_set_src(priv, &mbus_cfg); + /* start upstream */ ret = v4l2_subdev_call(priv->src_sd, video, s_stream, 1); ret = (ret && ret != -ENOIOCTLCMD) ? ret : 0; @@ -1130,7 +1154,6 @@ static int csi_link_validate(struct v4l2_subdev *sd, { struct csi_priv *priv = v4l2_get_subdevdata(sd); struct v4l2_mbus_config mbus_cfg = { .type = 0 }; - bool is_csi2; int ret; ret = v4l2_subdev_link_validate_default(sd, link, @@ -1145,25 +1168,6 @@ static int csi_link_validate(struct v4l2_subdev *sd, return ret; } - mutex_lock(&priv->lock); - - is_csi2 = !is_parallel_bus(&mbus_cfg); - if (is_csi2) { - /* - * NOTE! It seems the virtual channels from the mipi csi-2 - * receiver are used only for routing by the video mux's, - * or for hard-wired routing to the CSI's. Once the stream - * enters the CSI's however, they are treated internally - * in the IPU as virtual channel 0. - */ - ipu_csi_set_mipi_datatype(priv->csi, 0, - &priv->format_mbus[CSI_SINK_PAD]); - } - - /* select either parallel or MIPI-CSI2 as input to CSI */ - ipu_set_csi_src_mux(priv->ipu, priv->csi_id, is_csi2); - - mutex_unlock(&priv->lock); return ret; } From 527cb4a5515561ab8cc2b976396173fefbc85389 Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Fri, 24 Apr 2026 22:24:29 +0300 Subject: [PATCH 1078/1518] Bluetooth: btmtk: accept too short WMT FUNC_CTRL events commit e3ac0d9f1a205f33a43fba3b79ef74d2f604c78b upstream. MT7925 (USB ID 0e8d:e025) on fw version 20260106153314 sends WMT FUNC_CTRL events that are missing the status field. Prior to commit 006b9943b982 ("Bluetooth: btmtk: validate WMT event SKB length before struct access") the status was read from out-of-bounds of SKB data, which usually would result to success with BTMTK_WMT_ON_UNDONE, although I don't know the intent here. The bounds check added in that commit returns with error instead, producing "Bluetooth: hci0: Failed to send wmt func ctrl (-22)" and makes the device unusable. Fix the regression by interpreting too short packet as status BTMTK_WMT_ON_UNDONE, which makes the device work normally again. Fixes: 634a4408c061 ("Bluetooth: btmtk: validate WMT event SKB length before struct access") Signed-off-by: Pauli Virtanen Tested-by: Mikhail Gavrilov # MT7922 (0489:e0e2) Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btmtk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 7b4aa8e7a495b..cf05746e9db5a 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -678,8 +678,8 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev, case BTMTK_WMT_FUNC_CTRL: if (!skb_pull_data(data->evt_skb, sizeof(wmt_evt_funcc->status))) { - err = -EINVAL; - goto err_free_skb; + status = BTMTK_WMT_ON_UNDONE; + break; } wmt_evt_funcc = (struct btmtk_hci_wmt_evt_funcc *)wmt_evt; From 0ea9d6e036bee5c3bf1c8a820524b9a8a95c30eb Mon Sep 17 00:00:00 2001 From: Nick Chan Date: Thu, 14 May 2026 21:16:01 +0800 Subject: [PATCH 1079/1518] nvme-apple: Reset q->sq_tail during queue init commit a6ab75639e23169a741b0b2e12191fd8acb32c73 upstream. Fixes a "duplicate tag error for tag 0" firmware crash during controller reset while setting up a queue on Apple A11 / T8015 caused by stale entries in the submission queue due to an invalid sq_tail offset after reset. Fixes: 04d8ecf37b5e ("nvme: apple: Add Apple A11 support") Cc: stable@vger.kernel.org Suggested-by: Yuriy Havrylyuk Reviewed-by: Sven Peter Signed-off-by: Nick Chan Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/nvme/host/apple.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 86de41d0e7426..0a5b3903f9b9c 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1009,6 +1009,7 @@ static void apple_nvme_init_queue(struct apple_nvme_queue *q) unsigned int depth = apple_nvme_queue_depth(q); struct apple_nvme *anv = queue_to_apple_nvme(q); + q->sq_tail = 0; q->cq_head = 0; q->cq_phase = 1; if (anv->hw->has_lsq_nvmmu) From 97a05b0ae9ea5ec052be2eef0f9cc7ce03501bbb Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 14 May 2026 21:14:18 +0800 Subject: [PATCH 1080/1518] smb/client: fix possible infinite loop and oob read in symlink_data() commit 7d9a7f1f96cd617ee9e75bb22217c709038e26b8 upstream. On 32-bit architectures, the infinite loop is as follows: len = p->ErrorDataLength == 0xfffffff8 u8 *next = p->ErrorContextData + len next == p On 32-bit architectures, the out-of-bounds read is as follows: len = p->ErrorDataLength == 0xfffffff0 u8 *next = p->ErrorContextData + len next == (u8 *)p - 8 Reported-by: ChenXiaoSong Fixes: 76894f3e2f71 ("cifs: improve symlink handling for smb2+") Cc: stable@vger.kernel.org Signed-off-by: Ye Bin Reviewed-by: ChenXiaoSong Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/smb2file.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 30fff678c7456..cc1ff2461b003 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -49,6 +49,9 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) __func__, le32_to_cpu(p->ErrorId)); len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); + if (len > end - ((u8 *)p + sizeof(*p))) + return ERR_PTR(-EINVAL); + p = (struct smb2_error_context_rsp *)(p->ErrorContextData + len); } } else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) && From d31c6b3342158ebfcc92c17004e2095f27cc52ab Mon Sep 17 00:00:00 2001 From: Myeonghun Pak Date: Wed, 13 May 2026 15:57:00 +0900 Subject: [PATCH 1081/1518] drm/loongson: Use managed KMS polling commit 0a9c56dd387605d17dabeedd9fdd2c4c1d0bab7b upstream. lsdc_pci_probe() initializes KMS polling before setting up vblank support, requesting the IRQ and registering the DRM device. If any of those later steps fails, probe returns without finalizing polling. The driver also never finalizes polling on regular removal. Use drmm_kms_helper_poll_init() so polling is tied to the DRM device lifetime and automatically finalized on probe failure and device removal. This issue was identified during our ongoing static-analysis research while reviewing kernel code. Fixes: f39db26c5428 ("drm: Add kms driver for loongson display controller") Cc: stable@vger.kernel.org Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Reviewed-by: Thomas Zimmermann Acked-by: Jianmin Lv Reviewed-by: Huacai Chen Signed-off-by: Myeonghun Pak Signed-off-by: Thomas Zimmermann Link: https://patch.msgid.link/20260513065706.23803-1-mhun512@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/loongson/lsdc_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/loongson/lsdc_drv.c b/drivers/gpu/drm/loongson/lsdc_drv.c index 12193d2a301ac..65eb485efc627 100644 --- a/drivers/gpu/drm/loongson/lsdc_drv.c +++ b/drivers/gpu/drm/loongson/lsdc_drv.c @@ -291,7 +291,7 @@ static int lsdc_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) vga_client_register(pdev, lsdc_vga_set_decode); - drm_kms_helper_poll_init(ddev); + drmm_kms_helper_poll_init(ddev); if (loongson_vblank) { ret = drm_vblank_init(ddev, descp->num_of_crtc); From 318b995cffcfcaa69a234d28123a3f4ae186a9df Mon Sep 17 00:00:00 2001 From: Edward Adam Davis Date: Wed, 13 May 2026 12:30:50 +0800 Subject: [PATCH 1082/1518] drm: Replace old pointer to new idr commit dc366607c41c45fd0ae6f3db090f31dd611b644a upstream. Commit 5e28b7b94408 introduced a logical error by failing to replace the newly generated IDR pointer to old id's pointer at the correct location within the "change handle" logic; this resulted in the issue reported by syzbot [1]. Specifically, the new IDR object pointer is intended to replace the original id's pointer during the normal execution flow. Additionally, an unnecessary conditional check for the ret exit path has been removed. [1] !RB_EMPTY_ROOT(&prime_fpriv->dmabufs) WARNING: drivers/gpu/drm/drm_prime.c:224 at drm_prime_destroy_file_private+0x48/0x60 drivers/gpu/drm/drm_prime.c:224, CPU#0: syz.0.17/5833 Call Trace: drm_file_free.part.0+0x7e6/0xcc0 drivers/gpu/drm/drm_file.c:269 drm_file_free drivers/gpu/drm/drm_file.c:237 [inline] drm_close_helper.isra.0+0x186/0x200 drivers/gpu/drm/drm_file.c:290 drm_release+0x1ab/0x360 drivers/gpu/drm/drm_file.c:438 Fixes: 5e28b7b94408 ("drm: Set old handle to NULL before prime swap in change_handle") Reported-by: syzbot+d7c9eed171647e421013@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d7c9eed171647e421013 Cc: stable@vger.kernel.org Tested-by: syzbot+d7c9eed171647e421013@syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis Signed-off-by: Dave Airlie Link: https://patch.msgid.link/tencent_C267296443AAA4567771176886DFF364A305@qq.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gem.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 6d0d27aca518b..cc34ee8e1d483 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1017,17 +1017,12 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, spin_unlock(&file_priv->table_lock); - if (ret < 0) - goto out_unlock; - if (obj->dma_buf) { ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf, handle); if (ret < 0) { spin_lock(&file_priv->table_lock); idr_remove(&file_priv->object_idr, handle); - idrobj = idr_replace(&file_priv->object_idr, obj, handle); - WARN_ON(idrobj != NULL); spin_unlock(&file_priv->table_lock); goto out_unlock; } @@ -1039,7 +1034,9 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, spin_lock(&file_priv->table_lock); idr_remove(&file_priv->object_idr, args->handle); + idrobj = idr_replace(&file_priv->object_idr, obj, handle); spin_unlock(&file_priv->table_lock); + WARN_ON(idrobj != NULL); out_unlock: mutex_unlock(&file_priv->prime.lock); From d25b863e2dff42cf3533ca8d7e08c6eec910bc11 Mon Sep 17 00:00:00 2001 From: Chaitanya Kumar Borah Date: Tue, 5 May 2026 14:39:20 +0530 Subject: [PATCH 1083/1518] drm/i915/dp: Fix VSC dynamic range signaling for RGB formats commit 1ae15b6c7965d137eef21f2cc7d367b29cb88369 upstream. For RGB, set dynamic_range to CTA or VESA based on crtc_state->limited_color_range so sinks apply correct quantization. YCbCr remains limited (CTA) range. (DP v1.4, Table 5-1) v2: - Added Reported-by and Tested-by tags v3: - Add back YCbCr comment(Suraj) Cc: stable@vger.kernel.org #v5.8+ Reported-by: DeepChirp Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/15874 Tested-by: DeepChirp Fixes: 9799c4c3b76e ("drm/i915/dp: Add compute routine for DP VSC SDP") Assisted-by: GitHub-Copilot:GPT-5.4 Signed-off-by: Chaitanya Kumar Borah Reviewed-by: Suraj Kandpal Signed-off-by: Suraj Kandpal Link: https://patch.msgid.link/20260505090920.2479112-1-chaitanya.kumar.borah@intel.com (cherry picked from commit 38e10ddae6f8d42a2e8437fcd25a1cac51106c64) Signed-off-by: Tvrtko Ursulin Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_dp.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index be3d54729a440..61f22275403bf 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2869,8 +2869,13 @@ static void intel_dp_compute_vsc_colorimetry(const struct intel_crtc_state *crtc drm_WARN_ON(display->drm, vsc->bpc == 6 && vsc->pixelformat != DP_PIXELFORMAT_RGB); - /* all YCbCr are always limited range */ - vsc->dynamic_range = DP_DYNAMIC_RANGE_CTA; + /* All YCbCr formats are always limited range. */ + if (vsc->pixelformat == DP_PIXELFORMAT_RGB) + vsc->dynamic_range = crtc_state->limited_color_range ? + DP_DYNAMIC_RANGE_CTA : DP_DYNAMIC_RANGE_VESA; + else + vsc->dynamic_range = DP_DYNAMIC_RANGE_CTA; + vsc->content_type = DP_CONTENT_TYPE_NOT_DEFINED; } From 1b2dca1f9b5adc39bc976542262437aa408c245a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Thu, 30 Apr 2026 08:11:01 -0700 Subject: [PATCH 1084/1518] platform/x86: intel: Move debugfs register before creating devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ad3bff944c0f4f2e913298a9664391af32f87491 upstream. It is possible that the driver handling device is enumerated before registering debugfs. If the driver wants to access debugfs by calling tpmi_get_debugfs_dir(), this will return error in this case. Hence register debugfs before creating devices. Fixes: 811f67c51636 ("platform/x86/intel/tpmi: Add new auxiliary driver for performance limits") Signed-off-by: Srinivas Pandruvada Cc: Stable@vger.kernel.org Link: https://patch.msgid.link/20260430151103.1549733-2-srinivas.pandruvada@linux.intel.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/intel/vsec_tpmi.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/intel/vsec_tpmi.c b/drivers/platform/x86/intel/vsec_tpmi.c index 7748b5557a180..a8ccdd801ddd4 100644 --- a/drivers/platform/x86/intel/vsec_tpmi.c +++ b/drivers/platform/x86/intel/vsec_tpmi.c @@ -813,10 +813,6 @@ static int intel_vsec_tpmi_init(struct auxiliary_device *auxdev) auxiliary_set_drvdata(auxdev, tpmi_info); - ret = tpmi_create_devices(tpmi_info); - if (ret) - return ret; - /* * Allow debugfs when security policy allows. Everything this debugfs * interface provides, can also be done via /dev/mem access. If @@ -826,6 +822,12 @@ static int intel_vsec_tpmi_init(struct auxiliary_device *auxdev) if (!security_locked_down(LOCKDOWN_DEV_MEM) && capable(CAP_SYS_RAWIO)) tpmi_dbgfs_register(tpmi_info); + ret = tpmi_create_devices(tpmi_info); + if (ret) { + debugfs_remove_recursive(tpmi_info->dbgfs_dir); + return ret; + } + return 0; } From b6c0f545c8f94b447e554e57b66d28b163b48837 Mon Sep 17 00:00:00 2001 From: "Derek J. Clark" Date: Sun, 10 May 2026 04:25:37 +0000 Subject: [PATCH 1085/1518] platform/x86: lenovo-wmi-helpers: Move gamezone enums to wmi-helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 7e27896e16a1c450085c3fe020eeb1b223880f37 upstream. In a later patch in the series the thermal mode enum will be accessed across three separate drivers (wmi-capdata, wmi-gamezonem and wmi-other). An additional patch in the series will also add a function prototype that needs to reference this enum in wmi-helpers.h. To avoid having all these drivers begin to import each others headers, and to avoid declaring an opaque enum to hande the second case, move the thermal mode enum to helpers where it can be safely accessed by everything that needs it from a single import. While at it, since the gamezone_events_type enum is the only remaining item in the header, move that as well and remove the gamezone header entirely. Cc: stable@vger.kernel.org Reviewed-by: Mark Pearson Reviewed-by: Rong Zhang Tested-by: Rong Zhang Signed-off-by: Derek J. Clark Link: https://patch.msgid.link/20260510042546.436874-8-derekjohn.clark@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/lenovo/wmi-events.c | 2 +- drivers/platform/x86/lenovo/wmi-gamezone.c | 1 - drivers/platform/x86/lenovo/wmi-gamezone.h | 20 -------------------- drivers/platform/x86/lenovo/wmi-helpers.h | 13 +++++++++++++ drivers/platform/x86/lenovo/wmi-other.c | 1 - 5 files changed, 14 insertions(+), 23 deletions(-) delete mode 100644 drivers/platform/x86/lenovo/wmi-gamezone.h diff --git a/drivers/platform/x86/lenovo/wmi-events.c b/drivers/platform/x86/lenovo/wmi-events.c index 0994cd7dd504c..9e9f2e82e04dc 100644 --- a/drivers/platform/x86/lenovo/wmi-events.c +++ b/drivers/platform/x86/lenovo/wmi-events.c @@ -17,7 +17,7 @@ #include #include "wmi-events.h" -#include "wmi-gamezone.h" +#include "wmi-helpers.h" #define THERMAL_MODE_EVENT_GUID "D320289E-8FEA-41E0-86F9-911D83151B5F" diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.c b/drivers/platform/x86/lenovo/wmi-gamezone.c index baf1238b4d1d9..0f11b76af35dd 100644 --- a/drivers/platform/x86/lenovo/wmi-gamezone.c +++ b/drivers/platform/x86/lenovo/wmi-gamezone.c @@ -21,7 +21,6 @@ #include #include "wmi-events.h" -#include "wmi-gamezone.h" #include "wmi-helpers.h" #include "wmi-other.h" diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.h b/drivers/platform/x86/lenovo/wmi-gamezone.h deleted file mode 100644 index 6b163a5eeb959..0000000000000 --- a/drivers/platform/x86/lenovo/wmi-gamezone.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -/* Copyright (C) 2025 Derek J. Clark */ - -#ifndef _LENOVO_WMI_GAMEZONE_H_ -#define _LENOVO_WMI_GAMEZONE_H_ - -enum gamezone_events_type { - LWMI_GZ_GET_THERMAL_MODE = 1, -}; - -enum thermal_mode { - LWMI_GZ_THERMAL_MODE_QUIET = 0x01, - LWMI_GZ_THERMAL_MODE_BALANCED = 0x02, - LWMI_GZ_THERMAL_MODE_PERFORMANCE = 0x03, - LWMI_GZ_THERMAL_MODE_EXTREME = 0xE0, /* Ver 6+ */ - LWMI_GZ_THERMAL_MODE_CUSTOM = 0xFF, -}; - -#endif /* !_LENOVO_WMI_GAMEZONE_H_ */ diff --git a/drivers/platform/x86/lenovo/wmi-helpers.h b/drivers/platform/x86/lenovo/wmi-helpers.h index 20fd217498035..3364d8e152ca1 100644 --- a/drivers/platform/x86/lenovo/wmi-helpers.h +++ b/drivers/platform/x86/lenovo/wmi-helpers.h @@ -14,6 +14,19 @@ struct wmi_method_args_32 { u32 arg1; }; +enum lwmi_event_type { + LWMI_GZ_GET_THERMAL_MODE = 0x01, +}; + +enum thermal_mode { + LWMI_GZ_THERMAL_MODE_NONE = 0x00, + LWMI_GZ_THERMAL_MODE_QUIET = 0x01, + LWMI_GZ_THERMAL_MODE_BALANCED = 0x02, + LWMI_GZ_THERMAL_MODE_PERFORMANCE = 0x03, + LWMI_GZ_THERMAL_MODE_EXTREME = 0xE0, /* Ver 6+ */ + LWMI_GZ_THERMAL_MODE_CUSTOM = 0xFF, +}; + int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, unsigned char *buf, size_t size, u32 *retval); diff --git a/drivers/platform/x86/lenovo/wmi-other.c b/drivers/platform/x86/lenovo/wmi-other.c index 2a960b278f117..e379f65307b5b 100644 --- a/drivers/platform/x86/lenovo/wmi-other.c +++ b/drivers/platform/x86/lenovo/wmi-other.c @@ -36,7 +36,6 @@ #include "wmi-capdata01.h" #include "wmi-events.h" -#include "wmi-gamezone.h" #include "wmi-helpers.h" #include "wmi-other.h" #include "../firmware_attributes_class.h" From 9b718ebe0e9725e4040bda129a01d2dab86c15eb Mon Sep 17 00:00:00 2001 From: "Derek J. Clark" Date: Sun, 10 May 2026 04:25:35 +0000 Subject: [PATCH 1086/1518] platform/x86: lenovo-wmi-other: Fix tunable_attr_01 struct members MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 71f3843e0f81e3c097a088c1121154bb9a44da0a upstream. In struct tunable_attr_01 the capdata pointer is unused and the size of the id members is u32 when it should be u8. Fix these prior to adding additional members. No functional change intended. Reviewed-by: Mark Pearson Cc: stable@vger.kernel.org Reviewed-by: Rong Zhang Tested-by: Rong Zhang Signed-off-by: Derek J. Clark Link: https://patch.msgid.link/20260510042546.436874-6-derekjohn.clark@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/lenovo/wmi-other.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/lenovo/wmi-other.c b/drivers/platform/x86/lenovo/wmi-other.c index e379f65307b5b..dc7c60df7ad3b 100644 --- a/drivers/platform/x86/lenovo/wmi-other.c +++ b/drivers/platform/x86/lenovo/wmi-other.c @@ -82,11 +82,10 @@ struct lwmi_om_priv { }; struct tunable_attr_01 { - struct capdata01 *capdata; struct device *dev; - u32 feature_id; - u32 device_id; - u32 type_id; + u8 feature_id; + u8 device_id; + u8 type_id; }; static struct tunable_attr_01 ppt_pl1_spl = { From d3e03c25d520d717a65b82c52dd22ec662fe5580 Mon Sep 17 00:00:00 2001 From: Gyeyoung Baek Date: Sun, 19 Apr 2026 16:17:15 +0900 Subject: [PATCH 1087/1518] accel/rocket: Fix prep_bo ioctl leaking positive return from dma_resv_wait_timeout() commit 74570e12b4705ea11dcdfbfbd0a0b0fdaeff3059 upstream. dma_resv_wait_timeout() returns a positive 'remaining jiffies' value on success, 0 on timeout, and -errno on failure. rocket_ioctl_prep_bo() returns this 'long' result from an int-typed ioctl handler, so positive values reach userspace as bogus errors. Explicitly set ret to 0 on the success path. Fixes: 525ad89dd904 ("accel/rocket: Add IOCTLs for synchronizing memory accesses") Cc: stable@vger.kernel.org Signed-off-by: Gyeyoung Baek Reviewed-by: Tomeu Vizoso Link: https://patch.msgid.link/c0ebf83b345721701b22d8f5bc41c52c0ecf5e16.1776581974.git.gye976@gmail.com Signed-off-by: Steven Price Signed-off-by: Greg Kroah-Hartman --- drivers/accel/rocket/rocket_gem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/accel/rocket/rocket_gem.c b/drivers/accel/rocket/rocket_gem.c index 0551e11cc1841..c3c86e1abd25a 100644 --- a/drivers/accel/rocket/rocket_gem.c +++ b/drivers/accel/rocket/rocket_gem.c @@ -144,6 +144,8 @@ int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *fi ret = dma_resv_wait_timeout(gem_obj->resv, DMA_RESV_USAGE_WRITE, true, timeout); if (!ret) ret = timeout ? -ETIMEDOUT : -EBUSY; + else if (ret > 0) + ret = 0; shmem_obj = &to_rocket_bo(gem_obj)->base; From a424946e00f2e99d5a9fe6dadd095971a3f576b1 Mon Sep 17 00:00:00 2001 From: Adrien Burnett Date: Thu, 14 May 2026 18:59:05 +0200 Subject: [PATCH 1088/1518] ALSA: hda/realtek: Add mute LED quirk for HP Pavilion Laptop 16-ag0xxx commit 7d1051ad68df3d584b5f24bfa1fb19f3a24db278 upstream. Add a SND_PCI_QUIRK entry for the HP Pavilion Laptop 16-ag0xxx (subsystem 0x103c:0x8cbc, Realtek ALC245). The ALC245_FIXUP_HP_X360_MUTE_LEDS fixup is already used by the neighbouring HP Pavilion Aero Laptop 13-bg0xxx (0x103c:0x8cbd); it chains the master-mute COEF handler with the GPIO mic-mute LED handler, which is what this machine needs. Tested on the affected hardware: both the mute and mic-mute key LEDs respond correctly to the keyboard hotkeys after this change. Cc: Signed-off-by: Adrien Burnett Link: https://patch.msgid.link/20260514165905.21175-1-an.arctic.pigeon@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index e14caa040fc92..d9ef3fe4a21ca 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6960,6 +6960,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8caf, "HP Elite mt645 G8 Mobile Thin Client", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8cbc, "HP Pavilion Laptop 16-ag0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX), SND_PCI_QUIRK(0x103c, 0x8cde, "HP OmniBook Ultra Flip Laptop 14t", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX), From 651760f57fe0fce3c3c77e5099a8c81df31181af Mon Sep 17 00:00:00 2001 From: Markus Kramer Date: Thu, 14 May 2026 00:28:18 +0200 Subject: [PATCH 1089/1518] ALSA: hda/realtek: Add quirk for Samsung Galaxy Book5 360 headphone commit fd87b510f5f543125ecf51e7c706a9f4bc3352be upstream. The Samsung Galaxy Book5 360 (NP750QHA, PCI subsystem ID 0x144d:0xc902) has severe audio distortion on the 3.5mm headphone jack. Applying ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET corrects the output path configuration, consistent with fixes already applied to other Samsung Galaxy Book models using the same ALC256 codec. Cc: stable@vger.kernel.org Link: https://github.com/thesofproject/linux/issues/5648 Signed-off-by: Markus Kramer Link: https://patch.msgid.link/20260513222818.14351-1-linux@markus-kramer.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index d9ef3fe4a21ca..ea98cbc4310df 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7240,6 +7240,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc870, "Samsung Galaxy Book2 Pro (NP950XED)", ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS), SND_PCI_QUIRK(0x144d, 0xc872, "Samsung Galaxy Book2 Pro (NP950XEE)", ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS), SND_PCI_QUIRK(0x144d, 0xc886, "Samsung Galaxy Book3 Pro (NP964XFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), + SND_PCI_QUIRK(0x144d, 0xc902, "Samsung Galaxy Book5 360 (NP750QHA)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc1ca, "Samsung Galaxy Book3 Pro 360 (NP960QFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x144d, 0xc1cb, "Samsung Galaxy Book3 Pro 360 (NP965QFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x144d, 0xc1cc, "Samsung Galaxy Book3 Ultra (NT960XFH)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), From f9c184a83574549a36ea69b755f650e57d164c78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Thu, 7 May 2026 00:40:52 -0300 Subject: [PATCH 1090/1518] ALSA: usb-audio: Bound MIDI 2.0 endpoint descriptor scans MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 918be519c7876329e1b6e2ea1c59f0b75e792dca upstream. The USB MIDI 2.0 endpoint parser has the same descriptor walking pattern as the legacy MIDI parser. It validates bLength against bNumGrpTrmBlock before reading baAssoGrpTrmBlkID[], but not against the remaining bytes in the endpoint-extra scan. A malformed device can therefore make later baAssoGrpTrmBlkID[] reads consume bytes past the walked descriptor. Reject zero-length and overlong descriptors while walking endpoint extras. Fixes: ff49d1df79ae ("ALSA: usb-audio: USB MIDI 2.0 UMP support") Cc: stable@vger.kernel.org Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260507-usb-midi-endpoint-scan-bounds-v1-2-329d7348160e@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/midi2.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c index 0ca3819fc34b6..32a3102df15c5 100644 --- a/sound/usb/midi2.c +++ b/sound/usb/midi2.c @@ -496,15 +496,17 @@ static void *find_usb_ms_endpoint_descriptor(struct usb_host_endpoint *hostep, while (extralen > 3) { struct usb_ms_endpoint_descriptor *ms_ep = (struct usb_ms_endpoint_descriptor *)extra; + int length = ms_ep->bLength; - if (ms_ep->bLength > 3 && + if (!length || length > extralen) + break; + + if (length > 3 && ms_ep->bDescriptorType == USB_DT_CS_ENDPOINT && ms_ep->bDescriptorSubtype == subtype) return ms_ep; - if (!extra[0]) - break; - extralen -= extra[0]; - extra += extra[0]; + extralen -= length; + extra += length; } return NULL; } From 09141583bd97f4bbd7358e29fd138fe798467cdb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Thu, 7 May 2026 00:40:51 -0300 Subject: [PATCH 1091/1518] ALSA: usb-audio: Bound MIDI endpoint descriptor scans MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit d6854daa67be623860f4e1873fd3d3c275aba4ed upstream. snd_usbmidi_get_ms_info() validates the internal MIDIStreaming endpoint descriptor size before using baAssocJackID[], but the descriptor walker can still return a class-specific endpoint descriptor whose bLength exceeds the remaining bytes in the endpoint-extra scan. That leaves later flexible-array reads bounded by bLength, but not by the remaining bytes in the endpoint-extra scan. Stop walking when bLength is zero or extends past the remaining endpoint-extra scan. Fixes: 5c6cd7021a05 ("ALSA: usb-audio: Fix case when USB MIDI interface has more than one extra endpoint descriptor") Cc: stable@vger.kernel.org Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260507-usb-midi-endpoint-scan-bounds-v1-1-329d7348160e@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/midi.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/sound/usb/midi.c b/sound/usb/midi.c index dd8249e759700..e09761b6c91f3 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1947,15 +1947,17 @@ static struct usb_ms_endpoint_descriptor *find_usb_ms_endpoint_descriptor( while (extralen > 3) { struct usb_ms_endpoint_descriptor *ms_ep = (struct usb_ms_endpoint_descriptor *)extra; + int length = ms_ep->bLength; - if (ms_ep->bLength > 3 && + if (!length || length > extralen) + break; + + if (length > 3 && ms_ep->bDescriptorType == USB_DT_CS_ENDPOINT && ms_ep->bDescriptorSubtype == UAC_MS_GENERAL) return ms_ep; - if (!extra[0]) - break; - extralen -= extra[0]; - extra += extra[0]; + extralen -= length; + extra += length; } return NULL; } From d7b2de5d98628062426d618be509de611b433111 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Mon, 11 May 2026 01:36:37 -0300 Subject: [PATCH 1092/1518] ALSA: usb-audio: qcom: Check offload mapping failures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 814b2c9b30e56074e11fc0a6e5419b3fee0639bc upstream. uaudio_transfer_buffer_setup() calls dma_get_sgtable() and then passes the sg_table to uaudio_iommu_map_xfer_buf() without checking whether sg table construction succeeded. If dma_get_sgtable() fails, the sg_table contents are not valid. uaudio_iommu_map_pa() also ignores iommu_map() failures for the event and transfer rings and still returns the allocated IOVA to the QMI response. That can expose an unmapped IOVA to the audio DSP. For transfer rings, the failed mapping also leaves the IOVA allocator state marked in use. Check both operations. Free the coherent transfer buffer when sg table construction fails, free the sg table when transfer-buffer IOMMU mapping fails, and release the transfer-ring IOVA if iommu_map() fails. Also return the existing event-ring IOVA when the event ring is already mapped, matching the pre-split helper behavior. Fixes: 326bbc348298 ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support") Fixes: 44499ecb4f28 ("ALSA: usb: qcom: Fix false-positive address space check") Cc: stable@vger.kernel.org Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260511-alsa-usb-qcom-offload-map-errors-v1-1-6502695e58bc@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/qcom/qc_audio_offload.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index fc25e709ed4b2..e70649c4afcdc 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -565,6 +565,7 @@ static unsigned long uaudio_iommu_map_pa(enum mem_type mtype, bool dma_coherent, unsigned long iova = 0; bool map = true; int prot = uaudio_iommu_map_prot(dma_coherent); + int ret; switch (mtype) { case MEM_EVENT_RING: @@ -582,10 +583,24 @@ static unsigned long uaudio_iommu_map_pa(enum mem_type mtype, bool dma_coherent, dev_err(uaudio_qdev->data->dev, "unknown mem type %d\n", mtype); } - if (!iova || !map) + if (!iova) return 0; - iommu_map(uaudio_qdev->data->domain, iova, pa, size, prot, GFP_KERNEL); + if (!map) + return iova; + + ret = iommu_map(uaudio_qdev->data->domain, iova, pa, size, prot, + GFP_KERNEL); + if (ret) { + dev_err(uaudio_qdev->data->dev, + "failed to map %zu bytes at iova 0x%08lx: %d\n", + size, iova, ret); + if (mtype == MEM_XFER_RING) + uaudio_put_iova(iova, size, + &uaudio_qdev->xfer_ring_list, + &uaudio_qdev->xfer_ring_iova_size); + return 0; + } return iova; } @@ -1054,15 +1069,17 @@ static int uaudio_transfer_buffer_setup(struct snd_usb_substream *subs, if (!xfer_buf) return -ENOMEM; - dma_get_sgtable(subs->dev->bus->sysdev, &xfer_buf_sgt, xfer_buf, - xfer_buf_dma, len); + ret = dma_get_sgtable(subs->dev->bus->sysdev, &xfer_buf_sgt, xfer_buf, + xfer_buf_dma, len); + if (ret) + goto free_xfer_buf; /* map the physical buffer into sysdev as well */ xfer_buf_dma_sysdev = uaudio_iommu_map_xfer_buf(dma_coherent, len, &xfer_buf_sgt); if (!xfer_buf_dma_sysdev) { ret = -ENOMEM; - goto unmap_sync; + goto free_sgt; } mem_info->dma = xfer_buf_dma; @@ -1073,7 +1090,9 @@ static int uaudio_transfer_buffer_setup(struct snd_usb_substream *subs, return 0; -unmap_sync: +free_sgt: + sg_free_table(&xfer_buf_sgt); +free_xfer_buf: usb_free_coherent(subs->dev, len, xfer_buf, xfer_buf_dma); return ret; From 9ebb7eba1237dc198768b9c76506a79f924c82bb Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 30 Apr 2026 10:37:22 +0930 Subject: [PATCH 1093/1518] btrfs: only release the dirty pages io tree after successful writes commit 4066c55e109475a06d18a1f127c939d551211956 upstream. [WARNING] With extra warning on dirty extent buffers at umount (aka, the next patch in the series), test case generic/388 can trigger the following warning about dirty extent buffers at unmount time: BTRFS critical (device dm-2 state E): emergency shutdown BTRFS error (device dm-2 state E): error while writing out transaction: -30 BTRFS warning (device dm-2 state E): Skipping commit of aborted transaction. BTRFS error (device dm-2 state EA): Transaction 9 aborted (error -30) BTRFS: error (device dm-2 state EA) in cleanup_transaction:2068: errno=-30 Readonly filesystem BTRFS info (device dm-2 state EA): forced readonly BTRFS info (device dm-2 state EA): last unmount of filesystem 4fbf2e15-f941-49a0-bc7c-716315d2777c ------------[ cut here ]------------ WARNING: disk-io.c:3311 at invalidate_and_check_btree_folios+0xfd/0x1ca [btrfs], CPU#8: umount/914368 CPU: 8 UID: 0 PID: 914368 Comm: umount Tainted: G OE 7.1.0-rc1-custom+ #372 PREEMPT(full) 2de38db8d1deae71fde295430a0ff3ab98ccf596 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 02/02/2022 RIP: 0010:invalidate_and_check_btree_folios+0xfd/0x1ca [btrfs] Call Trace: close_ctree+0x52e/0x574 [btrfs d2f0b1cd330d1287e7a9919d112eadfc0e914efd] generic_shutdown_super+0x89/0x1a0 kill_anon_super+0x16/0x40 btrfs_kill_super+0x16/0x20 [btrfs d2f0b1cd330d1287e7a9919d112eadfc0e914efd] deactivate_locked_super+0x2d/0xb0 cleanup_mnt+0xdc/0x140 task_work_run+0x5a/0xa0 exit_to_user_mode_loop+0x123/0x4b0 do_syscall_64+0x243/0x7c0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ---[ end trace 0000000000000000 ]--- BTRFS warning (device dm-2 state EA): unable to release extent buffer 30539776 owner 9 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30621696 owner 257 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30638080 owner 258 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30654464 owner 7 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30703616 owner 2 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30720000 owner 10 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30736384 owner 4 gen 9 refs 2 flags 0x7 BTRFS warning (device dm-2 state EA): unable to release extent buffer 30752768 owner 11 gen 9 refs 2 flags 0x7 I'm using a stripped down version, which seems to trigger the warning more reliably: _fsstress_pid="" workload() { dmesg -C mkfs.btrfs -f -K $dev > /dev/null echo 1 > /sys/kernel/debug/clear_warn_once mount $dev $mnt $fsstress -w -n 1024 -p 4 -d $mnt & _fsstress_pid=$! sleep 0 $godown $mnt pkill --echo -PIPE fsstress > /dev/null wait $_fsstress_pid unset _fsstress_pid umount $mnt if dmesg | grep -q "WARNING"; then fail fi } for (( i = 0; i < $runtime; i++ )); do echo "=== $i/$runtime ===" workload done [CAUSE] Inside btrfs_write_and_wait_transaction(), we first try to write all dirty ebs, then wait for them to finish. After that we call btrfs_extent_io_tree_release() to free all extent states from dirty_pages io tree. However if we hit an error from btrfs_write_marked_extent(), then we still call btrfs_extent_io_tree_release() to clear that dirty_pages io tree, which may contain dirty records that we haven't yet submitted. Furthermore, the later transaction cleanup path will utilize that dirty_pages io tree to properly cleanup those dirty ebs, but since it's already empty, no dirty ebs are properly cleaned up, thus will later trigger the warnings inside invalidate_btree_folios(). [FIX] Normally such dirty ebs won't cause problems, as when the iput() is called on the btree inode, the dirty ebs will be forcibly written back, and since the fs is already in an error status, such writeback will not reach disk and finish immediately. But it's still better to get rid of such dirty ebs, if we ended up with dirty ebs but the fs is not in an error status, then such writeback at iput() time will be too late, as all workers are already stopped but writeback will utilize workers, which will lead to NULL pointer dereferences. Instead of unconditionally calling btrfs_extent_io_tree_release(), only call it if btrfs_write_and_wait_transaction() finished successfully, so that @dirty_pages extent io tree is kept untouched for transaction cleanup. CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 1 + fs/btrfs/transaction.c | 9 ++++----- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0f87f30c8dd27..655eed981078b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4646,6 +4646,7 @@ static void btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, free_extent_buffer_stale(eb); } } + btrfs_extent_io_tree_release(dirty_pages); } static void btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index fc3953136d23c..bd6cf479b3272 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1268,14 +1268,13 @@ static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans) blk_finish_plug(&plug); ret2 = btrfs_wait_extents(fs_info, dirty_pages); - btrfs_extent_io_tree_release(&trans->transaction->dirty_pages); - if (ret) return ret; - else if (ret2) + if (ret2) return ret2; - else - return 0; + + btrfs_extent_io_tree_release(&trans->transaction->dirty_pages); + return 0; } /* From 3fa13ceefbc5f36131110342743994cb3de80637 Mon Sep 17 00:00:00 2001 From: Viacheslav Dubeyko Date: Thu, 9 Apr 2026 12:26:02 -0700 Subject: [PATCH 1094/1518] ceph: fix a buffer leak in __ceph_setxattr() commit 5d3cc36b4e77a27ce7b686b7c59c7072bcb3fa8e upstream. The old_blob in __ceph_setxattr() can store ci->i_xattrs.prealloc_blob value during the retry. However, it is never called the ceph_buffer_put() for the old_blob object. This patch fixes the issue of the buffer leak. Cc: stable@vger.kernel.org Signed-off-by: Viacheslav Dubeyko Reviewed-by: Alex Markuze Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/xattr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 537165db45198..716cce1f95fe0 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1296,6 +1296,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, do_sync: spin_unlock(&ci->i_ceph_lock); + ceph_buffer_put(old_blob); do_sync_unlocked: if (lock_snap_rwsem) up_read(&mdsc->snap_rwsem); From d5bd8b4e39cfa8b087448adcd48088065cd629d5 Mon Sep 17 00:00:00 2001 From: Viacheslav Dubeyko Date: Thu, 9 Apr 2026 12:43:40 -0700 Subject: [PATCH 1095/1518] ceph: fix BUG_ON in __ceph_build_xattrs_blob() due to stale blob size commit 0c22d9511cbde746622f8e4c11aaa63fe76d45f9 upstream. The generic/642 test-case can reproduce the kernel crash: [40243.605254] ------------[ cut here ]------------ [40243.605956] kernel BUG at fs/ceph/xattr.c:918! [40243.607142] Oops: invalid opcode: 0000 [#1] SMP PTI [40243.608067] CPU: 7 UID: 0 PID: 498762 Comm: kworker/7:1 Not tainted 7.0.0-rc7+ #3 PREEMPT(full) [40243.609700] Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [40243.611820] Workqueue: ceph-msgr ceph_con_workfn [40243.612715] RIP: 0010:__ceph_build_xattrs_blob+0x1b8/0x1e0 [40243.613731] Code: 0f 84 82 fe ff ff e9 cf 8e 56 ff 48 8d 65 e8 31 c0 5b 41 5c 41 5d 5d 31 d2 31 c9 31 f6 31 ff 45 31 c0 45 31 c9 c3 cc cc cc cc <0f> 0b 4c 8b 62 08 41 8b 85 24 07 00 00 49 83 c4 04 41 89 44 24 fc [40243.616888] RSP: 0018:ffffcc80c4d4b688 EFLAGS: 00010287 [40243.617773] RAX: 0000000000010026 RBX: 0000000000000001 RCX: 0000000000000000 [40243.618928] RDX: ffff8a773798dee0 RSI: 0000000000000000 RDI: 0000000000000000 [40243.620158] RBP: ffffcc80c4d4b6a0 R08: 0000000000000000 R09: 0000000000000000 [40243.621573] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a75f3b58000 [40243.622907] R13: ffff8a75f3b58000 R14: 0000000000000080 R15: 000000000000bffd [40243.624054] FS: 0000000000000000(0000) GS:ffff8a787d1b4000(0000) knlGS:0000000000000000 [40243.625331] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [40243.626269] CR2: 000072f390b623c0 CR3: 000000011c02a003 CR4: 0000000000372ef0 [40243.627408] Call Trace: [40243.627839] [40243.628188] __prep_cap+0x3fd/0x4a0 [40243.628789] ? do_raw_spin_unlock+0x4e/0xe0 [40243.629474] ceph_check_caps+0x46a/0xc80 [40243.630094] ? __lock_acquire+0x4a2/0x2650 [40243.630773] ? find_held_lock+0x31/0x90 [40243.631347] ? handle_cap_grant+0x79f/0x1060 [40243.632068] ? lock_release+0xd9/0x300 [40243.632696] ? __mutex_unlock_slowpath+0x3e/0x340 [40243.633429] ? lock_release+0xd9/0x300 [40243.634052] handle_cap_grant+0xcf6/0x1060 [40243.634745] ceph_handle_caps+0x122b/0x2110 [40243.635415] mds_dispatch+0x5bd/0x2160 [40243.636034] ? ceph_con_process_message+0x65/0x190 [40243.636828] ? lock_release+0xd9/0x300 [40243.637431] ceph_con_process_message+0x7a/0x190 [40243.638184] ? kfree+0x311/0x4f0 [40243.638749] ? kfree+0x311/0x4f0 [40243.639268] process_message+0x16/0x1a0 [40243.639915] ? sg_free_table+0x39/0x90 [40243.640572] ceph_con_v2_try_read+0xf58/0x2120 [40243.641255] ? lock_acquire+0xc8/0x300 [40243.641863] ceph_con_workfn+0x151/0x820 [40243.642493] process_one_work+0x22f/0x630 [40243.643093] ? process_one_work+0x254/0x630 [40243.643770] worker_thread+0x1e2/0x400 [40243.644332] ? __pfx_worker_thread+0x10/0x10 [40243.645020] kthread+0x109/0x140 [40243.645560] ? __pfx_kthread+0x10/0x10 [40243.646125] ret_from_fork+0x3f8/0x480 [40243.646752] ? __pfx_kthread+0x10/0x10 [40243.647316] ? __pfx_kthread+0x10/0x10 [40243.647919] ret_from_fork_asm+0x1a/0x30 [40243.648556] [40243.648902] Modules linked in: overlay hctr2 libpolyval chacha libchacha adiantum libnh libpoly1305 essiv intel_rapl_msr intel_rapl_common intel_uncore_frequency_common skx_edac_common nfit kvm_intel kvm irqbypass joydev ghash_clmulni_intel aesni_intel rapl input_leds mac_hid psmouse vga16fb serio_raw vgastate floppy i2c_piix4 pata_acpi bochs qemu_fw_cfg i2c_smbus sch_fq_codel rbd dm_crypt msr parport_pc ppdev lp parport efi_pstore [40243.654766] ---[ end trace 0000000000000000 ]--- Commit d93231a6bc8a ("ceph: prevent a client from exceeding the MDS maximum xattr size") moved the required_blob_size computation to before the __build_xattrs() call, introducing a race. __build_xattrs() releases and reacquires i_ceph_lock during execution. In that window, handle_cap_grant() may update i_xattrs.blob with a newer MDS-provided blob and bump i_xattrs.version. When __build_xattrs() detects that index_version < version, it destroys and rebuilds the entire xattr rb-tree from the new blob, potentially increasing count, names_size, and vals_size. The prealloc_blob size check that follows still uses the stale required_blob_size computed before the rebuild, so it passes even when prealloc_blob is too small for the now-larger tree. After __set_xattr() adds one more xattr on top, __ceph_build_xattrs_blob() is called from the cap flush path and hits: BUG_ON(need > ci->i_xattrs.prealloc_blob->alloc_len); Fix this by recomputing required_blob_size after __build_xattrs() returns, using the current tree state. Also re-validate against m_max_xattr_size to fall back to the sync path if the rebuilt tree now exceeds the MDS limit. Cc: stable@vger.kernel.org Fixes: d93231a6bc8a ("ceph: prevent a client from exceeding the MDS maximum xattr size") Signed-off-by: Viacheslav Dubeyko Reviewed-by: Alex Markuze Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/xattr.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 716cce1f95fe0..caf0fe4d2b1b7 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1256,6 +1256,22 @@ int __ceph_setxattr(struct inode *inode, const char *name, ceph_vinop(inode), name, ceph_cap_string(issued)); __build_xattrs(inode); + /* + * __build_xattrs() may have released and reacquired i_ceph_lock, + * during which handle_cap_grant() could have replaced i_xattrs.blob + * with a newer MDS-provided blob and bumped i_xattrs.version. If that + * caused __build_xattrs() to rebuild the rb-tree from the new blob, + * count/names_size/vals_size may now be larger than when + * required_blob_size was computed above. Recompute it here so the + * prealloc_blob size check below reflects the current tree state. + */ + required_blob_size = __get_required_blob_size(ci, name_len, val_len); + if (required_blob_size > mdsc->mdsmap->m_max_xattr_size) { + doutc(cl, "sync (size too large): %d > %llu\n", + required_blob_size, mdsc->mdsmap->m_max_xattr_size); + goto do_sync; + } + if (!ci->i_xattrs.prealloc_blob || required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) { struct ceph_buffer *blob; From 252c5051dba9c709b6a72f2866f93e5e618b3f06 Mon Sep 17 00:00:00 2001 From: Nicholas Carlini Date: Mon, 11 May 2026 18:02:16 +0000 Subject: [PATCH 1096/1518] io-wq: check that the predecessor is hashed in io_wq_remove_pending() commit d6a2d7b04b5a093021a7a0e2e69e9d5237dfa8cc upstream. io_wq_remove_pending() needs to fix up wq->hash_tail[] if the cancelled work was the tail of its hash bucket. When doing this, it checks whether the preceding entry in acct->work_list has the same hash value, but never checks that the predecessor is hashed at all. io_get_work_hash() is simply atomic_read(&work->flags) >> IO_WQ_HASH_SHIFT, and the hash bits are never set for non-hashed work, so it returns 0. Thus, when a hashed bucket-0 work is cancelled while a non-hashed work is its list predecessor, the check spuriously passes and a pointer to the non-hashed io_kiocb is stored in wq->hash_tail[0]. Because non-hashed work is dequeued via the fast path in io_get_next_work(), which never touches hash_tail[], the stale pointer is never cleared. Therefore, after the non-hashed io_kiocb completes and is freed back to req_cachep, wq->hash_tail[0] is a dangling pointer. The io_wq is per-task (tctx->io_wq) and survives ring open/close, so the dangling pointer persists for the lifetime of the task; the next hashed bucket-0 enqueue dereferences it in io_wq_insert_work() and wq_list_add_after() writes through freed memory. Add the missing io_wq_is_hashed() check so a non-hashed predecessor never inherits a hash_tail[] slot. Cc: stable@vger.kernel.org Fixes: 204361a77f40 ("io-wq: fix hang after cancelling pending hashed work") Signed-off-by: Nicholas Carlini Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 49a9c914b4e97..bd47d32f71c25 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1125,7 +1125,8 @@ static inline void io_wq_remove_pending(struct io_wq *wq, if (io_wq_is_hashed(work) && work == wq->hash_tail[hash]) { if (prev) prev_work = container_of(prev, struct io_wq_work, list); - if (prev_work && io_get_work_hash(prev_work) == hash) + if (prev_work && io_wq_is_hashed(prev_work) && + io_get_work_hash(prev_work) == hash) wq->hash_tail[hash] = prev_work; else wq->hash_tail[hash] = NULL; From f0a0f01787ecece814414b0665df879b69849d09 Mon Sep 17 00:00:00 2001 From: "Jose Fernandez (Anthropic)" Date: Tue, 21 Apr 2026 19:26:13 +0000 Subject: [PATCH 1097/1518] iommu/amd: Bounds-check devid in __rlookup_amd_iommu() commit 07d0f496fe7ec5abe3bee7e38be709521567bb33 upstream. iommu_device_register() walks every device on the PCI bus via bus_for_each_dev() and calls amd_iommu_probe_device() for each. The inlined check_device() path computes the device's sbdf, calls rlookup_amd_iommu() to find the owning IOMMU, and only afterwards verifies devid <= pci_seg->last_bdf. __rlookup_amd_iommu() indexes rlookup_table[devid] with no bounds check of its own, so for a PCI device whose BDF is not described by the IVRS, the lookup reads past the end of the allocation before the caller's bounds check can run. This was harmless before commit e874c666b15b ("iommu/amd: Change rlookup, irq_lookup, and alias to use kvalloc()"): the table was a zeroed page-order allocation, so the over-read returned NULL and the caller's NULL check skipped the device. After that commit the table is a tight kvcalloc() and the over-read returns adjacent slab contents, which check_device() then dereferences as a struct amd_iommu *, causing a boot-time GPF. Seen on Google Compute Engine ct6e VMs, where the virtualized IVRS describes only the four TPU endpoints 00:04.0-07.0; the gVNIC at 00:08.0 (devid 0x40) indexes 56 bytes past the 456-byte allocation, into the adjacent kmalloc-512 slab object: pci 0000:00:04.0: Adding to iommu group 0 pci 0000:00:05.0: Adding to iommu group 1 pci 0000:00:06.0: Adding to iommu group 2 pci 0000:00:07.0: Adding to iommu group 3 Oops: general protection fault, probably for non-canonical address 0x3a64695f78746382: 0000 [#1] SMP NOPTI CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.18.22 #1 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 12/06/2025 RIP: 0010:amd_iommu_probe_device+0x54/0x3a0 Call Trace: __iommu_probe_device+0x107/0x520 probe_iommu_group+0x29/0x50 bus_for_each_dev+0x7e/0xe0 iommu_device_register+0xc9/0x240 iommu_go_to_state+0x9c0/0x1c60 amd_iommu_init+0x14/0x40 pci_iommu_init+0x16/0x60 do_one_initcall+0x47/0x2f0 Guard the array access in __rlookup_amd_iommu(). With the fix applied on 6.18.22, the gVNIC at 00:08.0 is skipped cleanly and the VM boots. Fixes: e874c666b15b ("iommu/amd: Change rlookup, irq_lookup, and alias to use kvalloc()") Cc: stable@vger.kernel.org Reported-by: Ziyuan Chen Tested-by: Ziyuan Chen Reviewed-by: Josef Bacik Assisted-by: Claude:unspecified Signed-off-by: Jose Fernandez (Anthropic) Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/amd/iommu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5afd1621d715e..dfbd09e2e0ca5 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -329,8 +329,12 @@ static struct amd_iommu *__rlookup_amd_iommu(u16 seg, u16 devid) struct amd_iommu_pci_seg *pci_seg; for_each_pci_segment(pci_seg) { - if (pci_seg->id == seg) - return pci_seg->rlookup_table[devid]; + if (pci_seg->id != seg) + continue; + /* IVRS may not describe every device on the bus */ + if (devid > pci_seg->last_bdf) + return NULL; + return pci_seg->rlookup_table[devid]; } return NULL; } From b0bd7a850e1f082560959707dbf57b0402071646 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 28 Apr 2026 21:59:52 +0100 Subject: [PATCH 1098/1518] x86/kexec: Push kjump return address even for non-kjump kexec commit 786a45757dcdf8f2beb9d4a6db605db16c18b2b4 upstream. The version of purgatory code shipped by kexec-tools attempts to look above the top of its stack to find a return address for a kjump, even in a non-kjump kexec. After the commit in Fixes: the word above the stack might not be there, leading to a fault (which is at least now caught by my exception-handling code in kexec). That commit fixed things for the actual kjump path, but no longer "gratuitously" pushes the unused return address to the stack in the non-kjump path. Put that *back* in the non-kjump path, to prevent purgatory from crashing when trying to access it. Fixes: 2cacf7f23a02 ("x86/kexec: Fix stack and handling of re-entry point for ::preserve_context") Reported-by: Rohan Kakulawaram Signed-off-by: David Woodhouse Signed-off-by: Borislav Petkov (AMD) Acked-by: Dave Hansen Tested-by: Rohan Kakulawaram Cc: Link: https://patch.msgid.link/32d627134143ffd957891cb697138e839c623211.camel@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/relocate_kernel_64.S | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 11e20bb13acaa..aa76d08b2d4b6 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -133,6 +133,14 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * %r13 original CR4 when relocate_kernel() was invoked */ + /* + * Set return address to 0 if not preserving context. The purgatory + * shipped in kexec-tools will unconditionally look for the return + * address on the stack and set a kexec_jump_back_entry= command + * line option if it's non-zero. There's no other way that it can + * tell a preserve-context (kjump) kexec from a normal one. + */ + pushq $0 /* store the start address on the stack */ pushq %rdx From 690b7ca1f9b343b505ff6d02226d40d1911a9d16 Mon Sep 17 00:00:00 2001 From: Wilfred Mallawa Date: Wed, 15 Apr 2026 09:45:14 +1000 Subject: [PATCH 1099/1518] xfs: fix memory leak on error in xfs_alloc_zone_info() commit 592975da8c3ca87b043077e6eafa37665eae7936 upstream. Currently, the 0th index of the zi_used_bucket_bitmap array is not freed on error due to the pre-decrement then evaluate semantic of the while loop used in xfs_alloc_zone_info(). Fix it by allowing for the i == 0 case to be covered. Fixes: 080d01c41d44 ("xfs: implement zoned garbage collection") Cc: stable@vger.kernel.org # v6.15 Reviewed-by: Damien Le Moal Reviewed-by: Carlos Maiolino Signed-off-by: Wilfred Mallawa Reviewed-by: Hans Holmberg Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_zone_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index ef7a931ebde5a..792bd389ebb71 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -1178,7 +1178,7 @@ xfs_alloc_zone_info( return zi; out_free_bitmaps: - while (--i > 0) + while (--i >= 0) kvfree(zi->zi_used_bucket_bitmap[i]); kfree(zi); return NULL; From 3f6fb0211b39aaa1b841260681dd02ca6b693ed5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Carlos=20L=C3=B3pez?= Date: Tue, 12 May 2026 12:00:41 +0200 Subject: [PATCH 1100/1518] virt: sev-guest: Do not use host-controlled page order in cleanup path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 23e6a1ca04ae44806439a5a446e62e4d42e80bb4 upstream. When issuing an extended guest request (SVM_VMGEXIT_EXT_GUEST_REQUEST), get_ext_report() allocates a buffer to retrieve a certificate blob from the host, keeping track of its size in report_req->certs_len. However, the host may return SNP_GUEST_VMM_ERR_INVALID_LEN, indicating an invalid buffer size, as well as the expected length of such buffer. get_ext_report() subsequently updates report_req->certs_len with the host-controlled value, and cleans up the buffer by computing a page order from such value. This is incorrect, as the host-provided length may not match the page order of the original allocation, potentially resulting in corruption in the page allocator. Fix this by using alloc_pages_exact() instead, and reusing @npages to compute the size passed to free_pages_exact(). For consistency, also use @npages to compute the size when allocating the pages, even though this last change has no functional effect. Fixes: 3e385c0d6ce8 ("virt: sev-guest: Move SNP Guest Request data pages handling under snp_cmd_mutex") Signed-off-by: Carlos López Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Roth Cc: stable@kernel.org Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/virt/coco/sev-guest/sev-guest.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index b01ec99106cdd..45b870b55feb4 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -176,7 +176,6 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques struct snp_guest_req req = {}; int ret, npages = 0, resp_len; sockptr_t certs_address; - struct page *page; if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data)) return -EINVAL; @@ -211,16 +210,15 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques * zeros to indicate that certificate data was not provided. */ npages = report_req->certs_len >> PAGE_SHIFT; - page = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, - get_order(report_req->certs_len)); - if (!page) + req.certs_data = alloc_pages_exact(npages << PAGE_SHIFT, + GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!req.certs_data) return -ENOMEM; - req.certs_data = page_address(page); ret = set_memory_decrypted((unsigned long)req.certs_data, npages); if (ret) { pr_err("failed to mark page shared, ret=%d\n", ret); - __free_pages(page, get_order(report_req->certs_len)); + free_pages_exact(req.certs_data, npages << PAGE_SHIFT); return -EFAULT; } @@ -277,7 +275,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques if (set_memory_encrypted((unsigned long)req.certs_data, npages)) WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); else - __free_pages(page, get_order(report_req->certs_len)); + free_pages_exact(req.certs_data, npages << PAGE_SHIFT); } return ret; } From 1a78bea6a5e9ecac37554648261d3f424b1dd3eb Mon Sep 17 00:00:00 2001 From: Ma Ke Date: Sun, 16 Nov 2025 10:44:11 +0800 Subject: [PATCH 1101/1518] powerpc/warp: Fix error handling in pika_dtm_thread commit 108d7f951271cbd36ca36efc5e5d106966f5180c upstream. pika_dtm_thread() acquires client through of_find_i2c_device_by_node() but fails to release it in error handling path. This could result in a reference count leak, preventing proper cleanup and potentially leading to resource exhaustion. Add put_device() to release the reference in the error handling path. Found by code review. Cc: stable@vger.kernel.org Fixes: 3984114f0562 ("powerpc/warp: Platform fix for i2c change") Signed-off-by: Ma Ke Reviewed-by: Christophe Leroy Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20251116024411.21968-1-make24@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/44x/warp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index a5001d32f978d..6f674f86dc853 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -293,6 +293,8 @@ static int pika_dtm_thread(void __iomem *fpga) schedule_timeout(HZ); } + put_device(&client->dev); + return 0; } From fc6db1e47c5551fd594511df69c3265fd6f71a80 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 12 May 2026 13:33:46 +0100 Subject: [PATCH 1102/1518] netfs: fix error handling in netfs_extract_user_iter() commit 0aad5704c6b4d14007d4eab15883e8524e4310f4 upstream. In netfs_extract_user_iter(), if iov_iter_extract_pages() failed to extract user pages, bail out on -ENOMEM, otherwise return the error code only if @npages == 0, allowing short DIO reads and writes to be issued. This fixes mmapstress02 from LTP tests against CIFS. Fixes: 85dd2c8ff368 ("netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator") Reported-by: Xiaoli Feng Signed-off-by: Paulo Alcantara (Red Hat) Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-10-dhowells@redhat.com Cc: netfs@lists.linux.dev Cc: stable@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/netfs/iterator.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 154a14bb2d7f7..adca78747f239 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -22,7 +22,7 @@ * * Extract the page fragments from the given amount of the source iterator and * build up a second iterator that refers to all of those bits. This allows - * the original iterator to disposed of. + * the original iterator to be disposed of. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be * allowed on the pages extracted. @@ -67,8 +67,8 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, ret = iov_iter_extract_pages(orig, &pages, count, max_pages - npages, extraction_flags, &offset); - if (ret < 0) { - pr_err("Couldn't get user pages (rc=%zd)\n", ret); + if (unlikely(ret <= 0)) { + ret = ret ?: -EIO; break; } @@ -97,6 +97,13 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, npages += cur_npages; } + if (ret < 0 && (ret == -ENOMEM || npages == 0)) { + for (i = 0; i < npages; i++) + unpin_user_page(bv[i].bv_page); + kvfree(bv); + return ret; + } + iov_iter_bvec(new, orig->data_source, bv, npages, orig_len - count); return npages; } From 42558732af4a4d814fce31f1fc1a90660ddc50d7 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Tue, 7 Apr 2026 18:08:57 -0400 Subject: [PATCH 1103/1518] nfsd: fix file change detection in CB_GETATTR commit 304d81a2fbf2b454def4debcb38ea173911b72cd upstream. RFC 8881, section 10.4.3 doesn't say anything about caching the file size in the delegation record, nor does it say anything about comparing a cached file size with the size reported by the client in the CB_GETATTR reply for the purpose of determining if the client holds modified data for the file. What section 10.4.3 of RFC 8881 does say is that the server should compare the *current* file size with the size reported by the client holding the delegation in the CB_GETATTR reply, and if they differ to treat it as a modification regardless of the change attribute retrieved via the CB_GETATTR. Doing otherwise would cause the server to believe the client holding the delegation has a modified version of the file, even if the client flushed the modifications to the server prior to the CB_GETATTR. This would have the added side effect of subsequent CB_GETATTRs causing updates to the mtime, ctime, and change attribute even if the client holding the delegation makes no further updates to the file. Modify nfsd4_deleg_getattr_conflict() to obtain the current file size via i_size_read(). Retain the ncf_cur_fsize field, since it's a convenient way to return the file size back to nfsd4_encode_fattr4(), but don't use it for the purpose of detecting file changes. Remove the unnecessary initialization of ncf_cur_fsize in nfs4_open_delegation(). Also, if we recall the delegation (because the client didn't respond to the CB_GETATTR), then skip the logic that checks the nfs4_cb_fattr fields. Fixes: c5967721e106 ("NFSD: handle GETATTR conflict with write delegation") Cc: stable@vger.kernel.org Signed-off-by: Scott Mayhew Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/nfs4state.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index adc33830438bb..cb8096e94f518 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -6350,7 +6350,6 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, } open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; - dp->dl_cb_fattr.ncf_cur_fsize = stat.size; dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); dp->dl_atime = stat.atime; dp->dl_ctime = stat.ctime; @@ -9396,11 +9395,15 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) goto out_status; + status = nfs_ok; + goto out_status; + } + if (!ncf->ncf_file_modified) { + if (ncf->ncf_initial_cinfo != ncf->ncf_cb_change) + ncf->ncf_file_modified = true; + else if (i_size_read(inode) != ncf->ncf_cb_fsize) + ncf->ncf_file_modified = true; } - if (!ncf->ncf_file_modified && - (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || - ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) - ncf->ncf_file_modified = true; if (ncf->ncf_file_modified) { int err; From 5b0756b6b757ba5952343df6b8b84d4c5b33c345 Mon Sep 17 00:00:00 2001 From: Yong-Xuan Wang Date: Fri, 8 May 2026 02:31:21 -0700 Subject: [PATCH 1104/1518] irqchip/riscv-imsic: Clear interrupt move state during CPU offlining commit cefafbd561402b0fe6447449364a30315b9b1570 upstream. Affinity changes of IMSIC interrupts have to be careful to not lose an interrupt in the process. Each vector keeps track of an affinity change in progress with two pointers in struct imsic_vector. imsic_vector::move_prev points to the previous CPU target data and imsic_vector::move_next to the designated new CPU target data. imsic_vector::move_prev on the new CPU can only be cleared after the previous CPU has cleared imsic_vector::move_next, which ususally happens in __imsic_remote_sync(). In case of CPU hot-unplug __imsic_remote_sync() is not invoked because the CPU is already marked offline. That means imsic_vector::move_prev becomes stale until the CPU is onlined again. The stale pointer prevents further affinity changes for the affected interrupts. Solve this by clearing the imsic_vector::move_prev pointers in the CPU hotplug offline path. [ tglx: Replace word salad in change log ] Fixes: 0f67911e821c ("irqchip/riscv-imsic: Separate next and previous pointers in IMSIC vector") Signed-off-by: Yong-Xuan Wang Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260508-imsic-v2-1-e9f08dd46cf5@sifive.com Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-riscv-imsic-early.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c index d1727c343c38f..12526b125bab0 100644 --- a/drivers/irqchip/irq-riscv-imsic-early.c +++ b/drivers/irqchip/irq-riscv-imsic-early.c @@ -163,6 +163,8 @@ static int imsic_dying_cpu(unsigned int cpu) /* Cleanup IPIs */ imsic_ipi_dying_cpu(); + imsic_local_sync_all(false); + /* Mark per-CPU IMSIC state as offline */ imsic_state_offline(); From 84ff9ae64d9b1ede5ed18b1d6bd979f270da92a8 Mon Sep 17 00:00:00 2001 From: Xianwei Zhao Date: Fri, 8 May 2026 07:36:54 +0000 Subject: [PATCH 1105/1518] irqchip/meson-gpio: Use the correct register in meson_s4_gpio_irq_set_type() commit 5363b67ac8ebcc3e227dbf59fc8061949109841d upstream. meson_s4_gpio_irq_set_type() uses the both-edge trigger register for configuring level type and single edge mode interrupts, which is not correct. Use REG_EDGE_POL instead. Fixes: bbd6fcc76b39 ("irqchip: Add support for Amlogic A4 and A5 SoCs") Signed-off-by: Xianwei Zhao Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260508-a9-gpio-irqchip-v1-1-9dc5f3e022e0@amlogic.com Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-meson-gpio.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index 09ebf1d9c21b0..a6663b36bc07f 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -404,8 +404,7 @@ static int meson_s4_gpio_irq_set_type(struct meson_gpio_irq_controller *ctl, if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING)) val |= BIT(ctl->params->edge_single_offset + idx); - meson_gpio_irq_update_bits(ctl, params->edge_pol_reg, - BIT(idx) | BIT(12 + idx), val); + meson_gpio_irq_update_bits(ctl, REG_EDGE_POL, BIT(idx) | BIT(12 + idx), val); return 0; }; From e6550b17cc0eed83e41bccff729a7402667d4f57 Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Wed, 6 May 2026 09:37:02 +0000 Subject: [PATCH 1106/1518] irqchip/gic-v5: Move LPI allocation into the LPI domain commit dec85d2fbd20de3711a71e65397dfdb40c3fa953 upstream. The IPI and ITS MSI domains currently allocate and release LPIs directly, then pass the selected LPI ID to the parent LPI domain. This leaks the LPI domain's allocation policy into its child domains and forces each child to duplicate part of the parent domain's teardown. Make the LPI domain allocate LPIs in its .alloc() callback and release them in a matching .free() callback. Child domains can then request a parent interrupt without passing an implementation-specific LPI ID, and the LPI lifetime is tied to the domain that owns the LPI namespace. Remove the gicv5_alloc_lpi() and gicv5_free_lpi() wrappers now that no external caller needs to manage LPIs directly. This is a preparatory change for an actual leakage problem in the allocation code and therefore tagged with the same Fixes tag. Fixes: 0f0101325876 ("irqchip/gic-v5: Add GICv5 LPI/IPI support") Signed-off-by: Sascha Bischoff Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Reviewed-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260506093634.382062-2-sascha.bischoff@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-gic-v5-its.c | 14 ++------ drivers/irqchip/irq-gic-v5.c | 53 +++++++++++++++--------------- include/linux/irqchip/arm-gic-v5.h | 3 -- 3 files changed, 28 insertions(+), 42 deletions(-) diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c index 8e22134b9f486..e21235b5079be 100644 --- a/drivers/irqchip/irq-gic-v5-its.c +++ b/drivers/irqchip/irq-gic-v5-its.c @@ -927,8 +927,8 @@ static void gicv5_its_free_eventid(struct gicv5_its_dev *its_dev, u32 event_id_b static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { - u32 device_id, event_id_base, lpi; struct gicv5_its_dev *its_dev; + u32 device_id, event_id_base; msi_alloc_info_t *info = arg; irq_hw_number_t hwirq; struct irq_data *irqd; @@ -947,16 +947,8 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi device_id = its_dev->device_id; for (i = 0; i < nr_irqs; i++) { - ret = gicv5_alloc_lpi(); - if (ret < 0) { - pr_debug("Failed to find free LPI!\n"); - goto out_free_irqs; - } - lpi = ret; - - ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, &lpi); + ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, NULL); if (ret) { - gicv5_free_lpi(lpi); goto out_free_irqs; } @@ -981,7 +973,6 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi out_free_irqs: while (--i >= 0) { irqd = irq_domain_get_irq_data(domain, virq + i); - gicv5_free_lpi(irqd->parent_data->hwirq); irq_domain_reset_irq_data(irqd); irq_domain_free_irqs_parent(domain, virq + i, 1); } @@ -1011,7 +1002,6 @@ static void gicv5_its_irq_domain_free(struct irq_domain *domain, unsigned int vi for (i = 0; i < nr_irqs; i++) { d = irq_domain_get_irq_data(domain, virq + i); - gicv5_free_lpi(d->parent_data->hwirq); irq_domain_reset_irq_data(d); irq_domain_free_irqs_parent(domain, virq + i, 1); } diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c index 41ef286c4d781..3e7c329b68fe3 100644 --- a/drivers/irqchip/irq-gic-v5.c +++ b/drivers/irqchip/irq-gic-v5.c @@ -58,16 +58,6 @@ static void release_lpi(u32 lpi) ida_free(&lpi_ida, lpi); } -int gicv5_alloc_lpi(void) -{ - return alloc_lpi(); -} - -void gicv5_free_lpi(u32 lpi) -{ - release_lpi(lpi); -} - static void gicv5_ppi_priority_init(void) { write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR0_EL1); @@ -751,18 +741,36 @@ static void gicv5_lpi_config_reset(struct irq_data *d) gicv5_lpi_irq_write_pending_state(d, false); } +static void gicv5_irq_lpi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d; + + if (WARN_ON_ONCE(nr_irqs != 1)) + return; + + d = irq_domain_get_irq_data(domain, virq); + + release_lpi(d->hwirq); + + irq_set_handler(virq, NULL); + irq_domain_reset_irq_data(d); +} + static int gicv5_irq_lpi_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { irq_hw_number_t hwirq; struct irq_data *irqd; - u32 *lpi = arg; int ret; if (WARN_ON_ONCE(nr_irqs != 1)) return -EINVAL; - hwirq = *lpi; + ret = alloc_lpi(); + if (ret < 0) + return ret; + hwirq = ret; irqd = irq_domain_get_irq_data(domain, virq); @@ -771,8 +779,10 @@ static int gicv5_irq_lpi_domain_alloc(struct irq_domain *domain, unsigned int vi irqd_set_single_target(irqd); ret = gicv5_irs_iste_alloc(hwirq); - if (ret < 0) + if (ret < 0) { + release_lpi(hwirq); return ret; + } gicv5_hwirq_init(hwirq, GICV5_IRQ_PRI_MI, GICV5_HWIRQ_TYPE_LPI); gicv5_lpi_config_reset(irqd); @@ -782,7 +792,7 @@ static int gicv5_irq_lpi_domain_alloc(struct irq_domain *domain, unsigned int vi static const struct irq_domain_ops gicv5_irq_lpi_domain_ops = { .alloc = gicv5_irq_lpi_domain_alloc, - .free = gicv5_irq_domain_free, + .free = gicv5_irq_lpi_domain_free, }; void __init gicv5_init_lpi_domain(void) @@ -804,21 +814,12 @@ static int gicv5_irq_ipi_domain_alloc(struct irq_domain *domain, unsigned int vi { struct irq_data *irqd; int ret, i; - u32 lpi; for (i = 0; i < nr_irqs; i++) { - ret = gicv5_alloc_lpi(); - if (ret < 0) + ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, NULL); + if (ret) return ret; - lpi = ret; - - ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, &lpi); - if (ret) { - gicv5_free_lpi(lpi); - return ret; - } - irqd = irq_domain_get_irq_data(domain, virq + i); irq_domain_set_hwirq_and_chip(domain, virq + i, i, @@ -844,8 +845,6 @@ static void gicv5_irq_ipi_domain_free(struct irq_domain *domain, unsigned int vi if (!d) return; - gicv5_free_lpi(d->parent_data->hwirq); - irq_set_handler(virq + i, NULL); irq_domain_reset_irq_data(d); irq_domain_free_irqs_parent(domain, virq + i, 1); diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h index 68ddcdb1cec5a..49994060f1529 100644 --- a/include/linux/irqchip/arm-gic-v5.h +++ b/include/linux/irqchip/arm-gic-v5.h @@ -387,8 +387,5 @@ struct gicv5_its_itt_cfg { void gicv5_init_lpis(u32 max); void gicv5_deinit_lpis(void); -int gicv5_alloc_lpi(void); -void gicv5_free_lpi(u32 lpi); - void __init gicv5_its_of_probe(struct device_node *parent); #endif From 2cbd4abe413e7444372f7fdf5af7046740e63329 Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Wed, 6 May 2026 09:37:23 +0000 Subject: [PATCH 1107/1518] irqchip/gic-v5: Support range allocation for LPIs commit eb6f6d523813ead9dc2799194a2839d42c049734 upstream. The per-IPI parent allocation loop returns immediately on failure and leaks any parent interrupts allocated by earlier iterations. The GICv5 LPI domain now owns LPI allocation and teardown internally, but its irq_domain callbacks still reject requests where nr_irqs is greater than one. This forces child domains to allocate and free LPIs one at a time even when the interrupt core requests a contiguous range. Handle multi-interrupt allocation and teardown in the LPI domain by iterating over the requested range and unwinding any partially allocated state on failure. Allocate the parent LPIs for the IPI domain with a single range request as well, which cures the leakage problem. Fixes: 0f0101325876 ("irqchip/gic-v5: Add GICv5 LPI/IPI support") Signed-off-by: Sascha Bischoff Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Reviewed-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260506093634.382062-3-sascha.bischoff@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-gic-v5.c | 77 ++++++++++++++++++++---------------- 1 file changed, 42 insertions(+), 35 deletions(-) diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c index 3e7c329b68fe3..fa86dd03e307c 100644 --- a/drivers/irqchip/irq-gic-v5.c +++ b/drivers/irqchip/irq-gic-v5.c @@ -746,15 +746,14 @@ static void gicv5_irq_lpi_domain_free(struct irq_domain *domain, unsigned int vi { struct irq_data *d; - if (WARN_ON_ONCE(nr_irqs != 1)) - return; - - d = irq_domain_get_irq_data(domain, virq); + for (unsigned int i = 0; i < nr_irqs; i++, virq++) { + d = irq_domain_get_irq_data(domain, virq); - release_lpi(d->hwirq); + release_lpi(d->hwirq); - irq_set_handler(virq, NULL); - irq_domain_reset_irq_data(d); + irq_set_handler(virq, NULL); + irq_domain_reset_irq_data(d); + } } static int gicv5_irq_lpi_domain_alloc(struct irq_domain *domain, unsigned int virq, @@ -762,32 +761,39 @@ static int gicv5_irq_lpi_domain_alloc(struct irq_domain *domain, unsigned int vi { irq_hw_number_t hwirq; struct irq_data *irqd; + unsigned int i; int ret; - if (WARN_ON_ONCE(nr_irqs != 1)) - return -EINVAL; - - ret = alloc_lpi(); - if (ret < 0) - return ret; - hwirq = ret; + for (i = 0; i < nr_irqs; i++) { + ret = alloc_lpi(); + if (ret < 0) + goto out_free_lpis; + hwirq = ret; + + ret = gicv5_irs_iste_alloc(hwirq); + if (ret < 0) { + /* Undo partial state first, then clean up the rest */ + release_lpi(hwirq); + goto out_free_lpis; + } - irqd = irq_domain_get_irq_data(domain, virq); + irqd = irq_domain_get_irq_data(domain, virq + i); - irq_domain_set_info(domain, virq, hwirq, &gicv5_lpi_irq_chip, NULL, - handle_fasteoi_irq, NULL, NULL); - irqd_set_single_target(irqd); + irq_domain_set_info(domain, virq + i, hwirq, &gicv5_lpi_irq_chip, + NULL, handle_fasteoi_irq, NULL, NULL); + irqd_set_single_target(irqd); - ret = gicv5_irs_iste_alloc(hwirq); - if (ret < 0) { - release_lpi(hwirq); - return ret; + gicv5_hwirq_init(hwirq, GICV5_IRQ_PRI_MI, GICV5_HWIRQ_TYPE_LPI); + gicv5_lpi_config_reset(irqd); } - gicv5_hwirq_init(hwirq, GICV5_IRQ_PRI_MI, GICV5_HWIRQ_TYPE_LPI); - gicv5_lpi_config_reset(irqd); - return 0; + +out_free_lpis: + if (i) + gicv5_irq_lpi_domain_free(domain, virq, i); + + return ret; } static const struct irq_domain_ops gicv5_irq_lpi_domain_ops = { @@ -813,21 +819,21 @@ static int gicv5_irq_ipi_domain_alloc(struct irq_domain *domain, unsigned int vi unsigned int nr_irqs, void *arg) { struct irq_data *irqd; - int ret, i; + int ret; - for (i = 0; i < nr_irqs; i++) { - ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, NULL); - if (ret) - return ret; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret) + return ret; - irqd = irq_domain_get_irq_data(domain, virq + i); + for (unsigned int i = 0; i < nr_irqs; i++, virq++) { + irqd = irq_domain_get_irq_data(domain, virq); - irq_domain_set_hwirq_and_chip(domain, virq + i, i, - &gicv5_ipi_irq_chip, NULL); + irq_domain_set_hwirq_and_chip(domain, virq, i, + &gicv5_ipi_irq_chip, NULL); irqd_set_single_target(irqd); - irq_set_handler(virq + i, handle_percpu_irq); + irq_set_handler(virq, handle_percpu_irq); } return 0; @@ -847,8 +853,9 @@ static void gicv5_irq_ipi_domain_free(struct irq_domain *domain, unsigned int vi irq_set_handler(virq + i, NULL); irq_domain_reset_irq_data(d); - irq_domain_free_irqs_parent(domain, virq + i, 1); } + + irq_domain_free_irqs_parent(domain, virq, nr_irqs); } static const struct irq_domain_ops gicv5_irq_ipi_domain_ops = { From 0de5cb2d61d053e34f416466c06fd9a5c3388f25 Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Wed, 6 May 2026 09:37:43 +0000 Subject: [PATCH 1108/1518] irqchip/gic-v5: Allocate ITS parent LPIs as a range commit a7c7e42654b6a8676610ee09d22901432c4851af upstream. The ITS MSI domain no longer manages LPI allocation directly. LPIs are allocated and freed by the parent LPI domain, which can now handle a full range of interrupts and unwind partial allocations internally. Make the ITS domain request and release the parent IRQs as a single range instead of iterating over each interrupt. The ITS allocation path then only needs to reserve EventIDs, allocate the parent range, and fill in the ITS irq_data for each MSI. Since no operation in the per-MSI loop can fail, the partial parent-free unwind becomes unnecessary. On teardown, reset the ITS irq_data for the range and then release the parent range in one call, leaving LPI teardown to the LPI domain. Fixes: 0f0101325876 ("irqchip/gic-v5: Add GICv5 LPI/IPI support") Signed-off-by: Sascha Bischoff Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Reviewed-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260506093634.382062-4-sascha.bischoff@arm.com Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-gic-v5-its.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c index e21235b5079be..1b6faca065dbb 100644 --- a/drivers/irqchip/irq-gic-v5-its.c +++ b/drivers/irqchip/irq-gic-v5-its.c @@ -935,6 +935,7 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi int ret, i; its_dev = info->scratchpad[0].ptr; + device_id = its_dev->device_id; ret = gicv5_its_alloc_eventid(its_dev, info, nr_irqs, &event_id_base); if (ret) @@ -944,14 +945,11 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi if (ret) goto out_eventid; - device_id = its_dev->device_id; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, NULL); + if (ret) + goto out_eventid; for (i = 0; i < nr_irqs; i++) { - ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, NULL); - if (ret) { - goto out_free_irqs; - } - /* * Store eventid and deviceid into the hwirq for later use. * @@ -970,12 +968,6 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi return 0; -out_free_irqs: - while (--i >= 0) { - irqd = irq_domain_get_irq_data(domain, virq + i); - irq_domain_reset_irq_data(irqd); - irq_domain_free_irqs_parent(domain, virq + i, 1); - } out_eventid: gicv5_its_free_eventid(its_dev, event_id_base, nr_irqs); return ret; @@ -998,14 +990,14 @@ static void gicv5_its_irq_domain_free(struct irq_domain *domain, unsigned int vi bitmap_release_region(its_dev->event_map, event_id_base, get_count_order(nr_irqs)); - /* Hierarchically free irq data */ for (i = 0; i < nr_irqs; i++) { d = irq_domain_get_irq_data(domain, virq + i); - irq_domain_reset_irq_data(d); - irq_domain_free_irqs_parent(domain, virq + i, 1); } + /* Hierarchically free irq data */ + irq_domain_free_irqs_parent(domain, virq, nr_irqs); + gicv5_its_syncr(its, its_dev); gicv5_irs_syncr(); } From 48df98d12b15360cd56af5c1f460307b340c1197 Mon Sep 17 00:00:00 2001 From: Raphael Zimmer Date: Tue, 5 May 2026 11:08:12 +0200 Subject: [PATCH 1109/1518] libceph: Fix potential out-of-bounds access in osdmap_decode() commit 35d0ed82d03e5ee77ea4f31f20e29562a7721649 upstream. When decoding osd_state and osd_weight from an incoming osdmap in osdmap_decode(), both are decoded for each osd, i.e., map->max_osd times. The ceph_decode_need() check only accounts for sizeof(*map->osd_weight) once. This can potentially result in an out-of-bounds memory access if the incoming message is corrupted such that the max_osd value exceeds the actual content of the osdmap message. This patch fixes the issue by changing the corresponding part in the ceph_decode_need() check to account for map->max_osd*sizeof(*map->osd_weight). Cc: stable@vger.kernel.org Fixes: dcbc919a5dc8 ("libceph: switch osdmap decoding to use ceph_decode_entity_addr") Signed-off-by: Raphael Zimmer Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- net/ceph/osdmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 7c76eb9d6ceec..34d2c246b2772 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1703,7 +1703,7 @@ static int osdmap_decode(void **p, void *end, bool msgr2, ceph_decode_need(p, end, 3*sizeof(u32) + map->max_osd*(struct_v >= 5 ? sizeof(u32) : sizeof(u8)) + - sizeof(*map->osd_weight), e_inval); + map->max_osd*sizeof(*map->osd_weight), e_inval); if (ceph_decode_32(p) != map->max_osd) goto e_inval; From f2f95e6d4b97e70bb876139b0583fc8079983f85 Mon Sep 17 00:00:00 2001 From: Raphael Zimmer Date: Tue, 12 May 2026 18:16:40 +0200 Subject: [PATCH 1110/1518] libceph: Fix potential null-ptr-deref in decode_choose_args() commit 28b0a2ab8c82d0bbdeb8013029c67c978ce6e4bf upstream. A message of type CEPH_MSG_OSD_MAP contains an OSD map that itself contains a CRUSH map. When decoding this CRUSH map in crush_decode(), an array of max_buckets CRUSH buckets is decoded, where some indices may not refer to actual buckets and are therefore set to NULL. The received CRUSH map may optionally contain choose_args that get decoded in decode_choose_args(). When decoding a crush_choose_arg_map, a series of choose_args for different buckets is decoded, with the bucket_index being read from the incoming message. It is only checked that the bucket index does not exceed max_buckets, but not that it doesn't point to an index with a NULL bucket. If a (potentially corrupted) message contains a crush_choose_arg_map including such a bucket_index, a null pointer dereference may occur in the subsequent processing when attempting to access the bucket with the given index. This patch fixes the issue by extending the affected check. Now, it is only attempted to access the bucket if it is not NULL. Cc: stable@vger.kernel.org Signed-off-by: Raphael Zimmer Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- net/ceph/osdmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 34d2c246b2772..99e16e5de0964 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -390,7 +390,8 @@ static int decode_choose_args(void **p, void *end, struct crush_map *c) goto fail; if (arg->ids_size && - arg->ids_size != c->buckets[bucket_index]->size) + (!c->buckets[bucket_index] || + arg->ids_size != c->buckets[bucket_index]->size)) goto e_inval; } From 0f3604cbe4df14c5e58288ac9f57511e726a222d Mon Sep 17 00:00:00 2001 From: Raphael Zimmer Date: Wed, 22 Apr 2026 10:47:13 +0200 Subject: [PATCH 1111/1518] libceph: Fix potential out-of-bounds access in crush_decode() commit 4c79fc2d598694bda845b46229c9d48b65042970 upstream. A message of type CEPH_MSG_OSD_MAP containing a crush map with at least one bucket has two fields holding the bucket algorithm. If the values in these two fields differ, an out-of-bounds access can occur. This is the case because the first algorithm field (alg) is used to allocate the correct amount of memory for a bucket of this type, while the second algorithm field inside the bucket (b->alg) is used in the subsequent processing. This patch fixes the issue by adding a check that compares alg and b->alg and aborts the processing in case they differ. Furthermore, b->alg is set to 0 in this case, because the destruction of the crush map also uses this field to determine the bucket type, which can again result in an out-of-bounds access when trying to free the memory pointed to by the fields of the bucket. To correctly free the memory allocated for the bucket in such a case, the corresponding call to kfree is moved from the algorithm-specific crush_destroy_bucket functions to the generic crush_destroy_bucket(). Cc: stable@vger.kernel.org Signed-off-by: Raphael Zimmer Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- net/ceph/crush/crush.c | 6 +----- net/ceph/osdmap.c | 4 ++++ 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c index 254ded0b05f6a..521aec1d5fc06 100644 --- a/net/ceph/crush/crush.c +++ b/net/ceph/crush/crush.c @@ -47,7 +47,6 @@ int crush_get_bucket_item_weight(const struct crush_bucket *b, int p) void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b) { kfree(b->h.items); - kfree(b); } void crush_destroy_bucket_list(struct crush_bucket_list *b) @@ -55,14 +54,12 @@ void crush_destroy_bucket_list(struct crush_bucket_list *b) kfree(b->item_weights); kfree(b->sum_weights); kfree(b->h.items); - kfree(b); } void crush_destroy_bucket_tree(struct crush_bucket_tree *b) { kfree(b->h.items); kfree(b->node_weights); - kfree(b); } void crush_destroy_bucket_straw(struct crush_bucket_straw *b) @@ -70,14 +67,12 @@ void crush_destroy_bucket_straw(struct crush_bucket_straw *b) kfree(b->straws); kfree(b->item_weights); kfree(b->h.items); - kfree(b); } void crush_destroy_bucket_straw2(struct crush_bucket_straw2 *b) { kfree(b->item_weights); kfree(b->h.items); - kfree(b); } void crush_destroy_bucket(struct crush_bucket *b) @@ -99,6 +94,7 @@ void crush_destroy_bucket(struct crush_bucket *b) crush_destroy_bucket_straw2((struct crush_bucket_straw2 *)b); break; } + kfree(b); } /** diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 99e16e5de0964..d09a2e7741e64 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -518,6 +518,10 @@ static struct crush_map *crush_decode(void *pbyval, void *end) b->id = ceph_decode_32(p); b->type = ceph_decode_16(p); b->alg = ceph_decode_8(p); + if (b->alg != alg) { + b->alg = 0; + goto bad; + } b->hash = ceph_decode_8(p); b->weight = ceph_decode_32(p); b->size = ceph_decode_32(p); From 4d2b37abda9536808655830d683dc491d31741a8 Mon Sep 17 00:00:00 2001 From: Raphael Zimmer Date: Tue, 12 May 2026 09:29:30 +0200 Subject: [PATCH 1112/1518] libceph: handle rbtree insertion error in decode_choose_args() commit d289478cfc0bcf81c7914200d6abdcb78bd04ded upstream. A message of type CEPH_MSG_OSD_MAP contains an OSD map that itself contains a CRUSH map. The received CRUSH map may optionally contain choose_args that get decoded in decode_choose_args(). In this function, num_choose_arg_maps is read from the message, and a corresponding number of crush_choose_arg_maps gets decoded afterwards. Each crush_choose_arg_map has a choose_args_index, which serves as the key when inserting it into the choose_args rbtree of the decoded crush_map. If a (potentially corrupted) message contains two crush_choose_arg_maps with the same index, the assertion in insert_choose_arg_map() triggers a kernel BUG when trying to insert the second crush_choose_arg_map. This patch fixes the issue by switching to the non-asserting rbtree insertion function and rejecting the message if the insertion fails. [ idryomov: changelog ] Cc: stable@vger.kernel.org Signed-off-by: Raphael Zimmer Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- net/ceph/osdmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index d09a2e7741e64..c34a5bf86831b 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -395,7 +395,10 @@ static int decode_choose_args(void **p, void *end, struct crush_map *c) goto e_inval; } - insert_choose_arg_map(&c->choose_args, arg_map); + if (!__insert_choose_arg_map(&c->choose_args, arg_map)) { + ret = -EEXIST; + goto fail; + } } return 0; From 637b7ce89e543284857c68ef66d04dd1f34008cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Naval=20Alcal=C3=A1?= Date: Sat, 9 May 2026 10:43:44 +0800 Subject: [PATCH 1113/1518] iommu/vt-d: Disable DMAR for Intel Q35 IGFX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2cda2e10dc8343ae01eae9e999a876b7e7d37861 upstream. Intel Q35 integrated graphics (8086:29b2) exhibits broken DMAR behaviour similar to other G4x/GM45 devices for which DMAR is already disabled via quirks. When DMAR is enabled, the system may hard lock up during boot or early device initialization, requiring a reset. Add the missing PCI ID to the existing quirk list to disable DMAR for this device. Fixes: 1f76249cc3be ("iommu/vt-d: Declare Broadwell igfx dmar support snafu") Cc: stable@vger.kernel.org Closes: https://bugzilla.kernel.org/show_bug.cgi?id=201185 Closes: https://bugzilla.kernel.org/show_bug.cgi?id=216064 Signed-off-by: Naval Alcalá Link: https://lore.kernel.org/r/20260410161622.13549-1-ari@naval.cat Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel/iommu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 49e83c8566a32..8e72dc63fd995 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4517,6 +4517,9 @@ static void quirk_iommu_igfx(struct pci_dev *dev) disable_igfx_iommu = 1; } +/* Q35 integrated gfx dmar support is totally busted. */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x29b2, quirk_iommu_igfx); + /* G4x/GM45 integrated gfx dmar support is totally busted. */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx); From 88397fad7914ee74a7880fa5ce01f9eb6bfe0743 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Sat, 9 May 2026 10:43:45 +0800 Subject: [PATCH 1114/1518] iommu/vt-d: Fix oops due to out of scope access commit a6dea58d8625c06b9654c0555f101742481335c3 upstream. Below oops triggers when kill QEMU process: Oops: general protection fault, probably for non-canonical address 0x7fffffff844eaaa7: 0000 [#1] SMP NOPTI Call Trace: do_raw_spin_lock+0xaa/0xc0 _raw_spin_lock_irqsave+0x21/0x40 domain_remove_dev_pasid+0x52/0x160 intel_nested_set_dev_pasid+0x1b9/0x1e0 __iommu_set_group_pasid+0x56/0x120 pci_dev_reset_iommu_done+0xe3/0x180 pcie_flr+0x65/0x160 __pci_reset_function_locked+0x5b/0x120 vfio_pci_core_close_device+0x63/0xe0 [vfio_pci_core] vfio_df_close+0x4f/0xa0 vfio_df_unbind_iommufd+0x2d/0x60 vfio_device_fops_release+0x3e/0x40 __fput+0xe5/0x2c0 task_work_run+0x58/0xa0 do_exit+0x2c8/0x600 do_group_exit+0x2f/0xa0 get_signal+0x863/0x8c0 arch_do_signal_or_restart+0x24/0x100 exit_to_user_mode_loop+0x87/0x380 do_syscall_64+0x2ff/0x11e0 entry_SYSCALL_64_after_hwframe+0x76/0x7e The global static blocked domain is a dummy domain without corresponding dmar_domain structure, accessing beyond iommu_domain structure triggers oops easily. Fix it by return early in domain_remove_dev_pasid() like identity domain. Fixes: 7d0c9da6c150 ("iommu/vt-d: Add set_dev_pasid callback for dma domain") Cc: stable@vger.kernel.org Signed-off-by: Zhenzhong Duan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20260421031347.1408890-1-zhenzhong.duan@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel/iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 8e72dc63fd995..59583428f2492 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4068,8 +4068,8 @@ void domain_remove_dev_pasid(struct iommu_domain *domain, if (!domain) return; - /* Identity domain has no meta data for pasid. */ - if (domain->type == IOMMU_DOMAIN_IDENTITY) + /* Identity domain and blocked domain have no meta data for pasid. */ + if (domain->type == IOMMU_DOMAIN_IDENTITY || domain->type == IOMMU_DOMAIN_BLOCKED) return; dmar_domain = to_dmar_domain(domain); From 9022cb9ac0c2a72a57fa8ebf92ac74f953ca0153 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Sat, 9 May 2026 10:43:46 +0800 Subject: [PATCH 1115/1518] iommu/vt-d: Avoid NULL pointer dereference or refcount corruption commit 79ea2feb917b05366b49d85573c9c5331f043b2c upstream. Commit 60f030f7418d ("iommu/vt-d: Avoid use of NULL after WARN_ON_ONCE") fixed a NULL pointer dereference in an unlikely situation partly. If dev_pasid is not found in the dev_pasids list, it remains NULL. However, the teardown operations are executed unconditionally, this lead to a NULL pointer dereference or refcount corruption. If the domain was never attached to this IOMMU, info will be NULL, which would cause an immediate dereference when checking --info->refcnt. Even if info is not NULL, decrementing the refcount without having removed a valid PASID might unbalance the count. This could lead to premature dropping of the refcount to 0, potentially causing a use-after-free for the remaining active devices sharing the domain. Fix it by returning early if dev_pasid is NULL, before executing the teardown operations. Issue found by AI review and suggested by Kevin Tian. https://sashiko.dev/#/patchset/20260421031347.1408890-1-zhenzhong.duan%40intel.com Fixes: 60f030f7418d ("iommu/vt-d: Avoid use of NULL after WARN_ON_ONCE") Cc: stable@vger.kernel.org Suggested-by: Kevin Tian Signed-off-by: Zhenzhong Duan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20260422033538.95000-1-zhenzhong.duan@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel/iommu.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 59583428f2492..79676188f60f3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4083,12 +4083,13 @@ void domain_remove_dev_pasid(struct iommu_domain *domain, } spin_unlock_irqrestore(&dmar_domain->lock, flags); + if (WARN_ON_ONCE(!dev_pasid)) + return; + cache_tag_unassign_domain(dmar_domain, dev, pasid); domain_detach_iommu(dmar_domain, iommu); - if (!WARN_ON_ONCE(!dev_pasid)) { - intel_iommu_debugfs_remove_dev_pasid(dev_pasid); - kfree(dev_pasid); - } + intel_iommu_debugfs_remove_dev_pasid(dev_pasid); + kfree(dev_pasid); } static int blocking_domain_set_dev_pasid(struct iommu_domain *domain, From 65a3a1cf29ebe143a989bc1e96519a393e68ab65 Mon Sep 17 00:00:00 2001 From: Sebastian Brzezinka Date: Thu, 16 Apr 2026 13:31:18 +0200 Subject: [PATCH 1116/1518] drm/i915: skip __i915_request_skip() for already signaled requests commit 4cfe4c0efbdcde742a47813180cc69b132d7598e upstream. After a GPU reset the HWSP is zeroed, so previously completed requests appear incomplete. If such a request is picked up during reset_rewind() and marked guilty, i915_request_set_error_once() returns early (fence already signaled), leaving fence.error without a fatal error code. The subsequent __i915_request_skip() then hits: ``` GEM_BUG_ON(!fatal_error(rq->fence.error)) ``` Fixes a kernel BUG observed on Sandy Bridge (Gen6) during heartbeat-triggered engine resets. ``` kernel BUG at drivers/gpu/drm/i915/i915_request.c:556! RIP: __i915_request_skip+0x15e/0x1d0 [i915] ... __i915_request_reset+0x212/0xa70 [i915] reset_rewind+0xe4/0x280 [i915] intel_gt_reset+0x30d/0x5b0 [i915] heartbeat+0x516/0x530 [i915] ``` Guard __i915_request_skip() with i915_request_signaled(), if the fence is already signaled, the ring content is committed and there is nothing left to skip. Fixes: 36e191f0644b ("drm/i915: Apply i915_request_skip() on submission") Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/13729 Signed-off-by: Sebastian Brzezinka Cc: stable@vger.kernel.org # v5.7+ Reviewed-by: Krzysztof Karas Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/fe76921d35b6ae85aa651822726d0d9815aa5362.1776339012.git.sebastian.brzezinka@intel.com (cherry picked from commit 5ba54393dcd7adf75a9f39f5a933b1538349cad5) Signed-off-by: Tvrtko Ursulin Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/intel_reset.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 41b5036dc5385..64ef68e6ac625 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -132,7 +132,8 @@ void __i915_request_reset(struct i915_request *rq, bool guilty) rcu_read_lock(); /* protect the GEM context */ if (guilty) { i915_request_set_error_once(rq, -EIO); - __i915_request_skip(rq); + if (!i915_request_signaled(rq)) + __i915_request_skip(rq); banned = mark_guilty(rq); } else { i915_request_set_error_once(rq, -EAGAIN); From c76273c3eba934f241e03056b9a9531dc92e4d7c Mon Sep 17 00:00:00 2001 From: Gyeyoung Baek Date: Sun, 19 Apr 2026 16:17:16 +0900 Subject: [PATCH 1117/1518] drm/panfrost: Fix wait_bo ioctl leaking positive return from dma_resv_wait_timeout() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 459d75523b71c0ec254d153d8850d0b7008af396 upstream. dma_resv_wait_timeout() returns a positive 'remaining jiffies' value on success, 0 on timeout, and -errno on failure. panfrost_ioctl_wait_bo() returns this 'long' result from an int-typed ioctl handler, so positive values reach userspace as bogus errors. Explicitly set ret to 0 on the success path. Fixes: f3ba91228e8e ("drm/panfrost: Add initial panfrost driver") Cc: stable@vger.kernel.org Signed-off-by: Gyeyoung Baek Reviewed-by: Adrián Larumbe Reviewed-by: Boris Brezillon Reviewed-by: Steven Price Link: https://patch.msgid.link/fe33f82fded7be1c18e2e0eb2db451d5a738cf39.1776581974.git.gye976@gmail.com Signed-off-by: Steven Price Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/panfrost/panfrost_drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 1ea6c509a5d59..a31c5395de18c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -365,6 +365,8 @@ panfrost_ioctl_wait_bo(struct drm_device *dev, void *data, true, timeout); if (!ret) ret = timeout ? -ETIMEDOUT : -EBUSY; + else if (ret > 0) + ret = 0; drm_gem_object_put(gem_obj); From 20a99ea1e2fd720856d6ba497ff26b82c604751f Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Fri, 8 May 2026 11:26:36 +0100 Subject: [PATCH 1118/1518] drm/xe/dma-buf: handle empty bo and UAF races MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 981bedbbe61364fcc3a3b87ebaf648a66cd07108 upstream. There look to be some nasty races here when triggering the invalidate_mappings hook: 1) We do xe_bo_alloc() followed by the attach, before the actual full bo init step in xe_dma_buf_init_obj(). However the bo is visible on the attachments list after the attach. This is bad since exporter driver, say amdgpu, can at any time call back into our invalidate_mappings hook, with an empty/bogus bo, leading to potential bugs/crashes. 2) Similar to 1) but here we get a UAF, when the invalidate_mappings hook is triggered. For example, we get as far as xe_bo_init_locked() but this fails in some way. But here the bo will be freed on error, but we still have it attached from dma-buf pov, so if the invalidate_mappings is now triggered then the bo we access is gone and we trigger UAF and more bugs/crashes. To fix this, move the attach step until after we actually have a fully set up buffer object. Note that the bo is not published to userspace until later, so not sure what the comment "Don't publish the bo until we have a valid attachment", is referring to. We have at least two different customers reporting hitting a NULL ptr deref in evict_flags when importing something from amdgpu, followed by triggering the evict flow. Hit rate is also pretty low, which would hint at some kind of race, so something like 1) or 2) might explain this. v2: - Shuffle the order of the ops slightly (no functional change) - Improve the comment to better explain the ordering (Matt B) Assisted-by: Gemini:gemini-3 #debug Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/7903 Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/4055 Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Matthew Brost Cc: # v6.8+ Reviewed-by: Matthew Brost Acked-by: Thomas Hellström Link: https://patch.msgid.link/20260508102635.149172-3-matthew.auld@intel.com (cherry picked from commit af1f2ad0c59fe4e2f924c526f66e968289d77971) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_dma_buf.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 4cef02ff14518..683088592c1be 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -326,15 +326,25 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, } } - /* - * Don't publish the bo until we have a valid attachment, and a - * valid attachment needs the bo address. So pre-create a bo before - * creating the attachment and publish. - */ bo = xe_bo_alloc(); if (IS_ERR(bo)) return ERR_CAST(bo); + /* + * xe_dma_buf_init_obj() takes ownership of the raw bo, so do not touch + * on fail, since it will already take care of cleanup. On success we + * still need to drop the ref, if something later fails. + * + * In addition this needs to happen before the attach, since + * it will create a new attachment for this, and add it to the list of + * attachments, at which point it is globally visible, and at any point + * the export side can call into on invalidate_mappings callback, which + * require a working object. + */ + obj = xe_dma_buf_init_obj(dev, bo, dma_buf); + if (IS_ERR(obj)) + return obj; + attach_ops = &xe_dma_buf_attach_ops; #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) if (test) @@ -347,21 +357,12 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, goto out_err; } - /* - * xe_dma_buf_init_obj() takes ownership of bo on both success - * and failure, so we must not touch bo after this call. - */ - obj = xe_dma_buf_init_obj(dev, bo, dma_buf); - if (IS_ERR(obj)) { - dma_buf_detach(dma_buf, attach); - return obj; - } get_dma_buf(dma_buf); obj->import_attach = attach; return obj; out_err: - xe_bo_free(bo); + xe_bo_put(bo); return obj; } From 39fdac6be02eb7c3460518c1c4085f75f935c4ce Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Fri, 8 May 2026 11:26:37 +0100 Subject: [PATCH 1119/1518] drm/xe/dma-buf: fix UAF with retry loop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 155a372a1cc50fa93387c5d3cdfd614a61e1afd1 upstream. Retry doesn't work here, since bo will be freed on error, leading to UAF. However, now that we do the alloc & init before the attach, we can now combine this as one unit and have the init do the alloc for us. This should make the retry safe. Reported by Sashiko. v2: Fix up the error unwind (CI) Closes: https://sashiko.dev/#/patchset/20260506184332.86743-2-matthew.auld%40intel.com Fixes: eb289a5f6cc6 ("drm/xe: Convert xe_dma_buf.c for exhaustive eviction") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Matthew Brost Cc: # v6.18+ Reviewed-by: Thomas Hellström Link: https://patch.msgid.link/20260508102635.149172-4-matthew.auld@intel.com (cherry picked from commit 479669418253e0f27f8cf5db01a731352ea592e7) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/xe/xe_dma_buf.c | 49 ++++++++------------------------- 1 file changed, 12 insertions(+), 37 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 683088592c1be..eeea2a6e15b5c 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -227,16 +227,8 @@ struct dma_buf *xe_gem_prime_export(struct drm_gem_object *obj, int flags) return buf; } -/* - * Takes ownership of @storage: on success it is transferred to the returned - * drm_gem_object; on failure it is freed before returning the error. - * This matches the contract of xe_bo_init_locked() which frees @storage on - * its error paths, so callers need not (and must not) free @storage after - * this call. - */ static struct drm_gem_object * -xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, - struct dma_buf *dma_buf) +xe_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) { struct dma_resv *resv = dma_buf->resv; struct xe_device *xe = to_xe_device(dev); @@ -247,10 +239,8 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, int ret = 0; dummy_obj = drm_gpuvm_resv_object_alloc(&xe->drm); - if (!dummy_obj) { - xe_bo_free(storage); + if (!dummy_obj) return ERR_PTR(-ENOMEM); - } dummy_obj->resv = resv; xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, ret) { @@ -259,8 +249,7 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, if (ret) break; - /* xe_bo_init_locked() frees storage on error */ - bo = xe_bo_init_locked(xe, storage, NULL, resv, NULL, dma_buf->size, + bo = xe_bo_init_locked(xe, NULL, NULL, resv, NULL, dma_buf->size, 0, /* Will require 1way or 2way for vm_bind */ ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, &exec); drm_exec_retry_on_contention(&exec); @@ -311,7 +300,6 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, const struct dma_buf_attach_ops *attach_ops; struct dma_buf_attachment *attach; struct drm_gem_object *obj; - struct xe_bo *bo; if (dma_buf->ops == &xe_dmabuf_ops) { obj = dma_buf->priv; @@ -326,22 +314,14 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, } } - bo = xe_bo_alloc(); - if (IS_ERR(bo)) - return ERR_CAST(bo); - /* - * xe_dma_buf_init_obj() takes ownership of the raw bo, so do not touch - * on fail, since it will already take care of cleanup. On success we - * still need to drop the ref, if something later fails. - * - * In addition this needs to happen before the attach, since - * it will create a new attachment for this, and add it to the list of - * attachments, at which point it is globally visible, and at any point - * the export side can call into on invalidate_mappings callback, which - * require a working object. + * This needs to happen before the attach, since it will create a new + * attachment for this, and add it to the list of attachments, at which + * point it is globally visible, and at any point the export side can + * call into on invalidate_mappings callback, which require a working + * object. */ - obj = xe_dma_buf_init_obj(dev, bo, dma_buf); + obj = xe_dma_buf_create_obj(dev, dma_buf); if (IS_ERR(obj)) return obj; @@ -351,20 +331,15 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, attach_ops = test->attach_ops; #endif - attach = dma_buf_dynamic_attach(dma_buf, dev->dev, attach_ops, &bo->ttm.base); + attach = dma_buf_dynamic_attach(dma_buf, dev->dev, attach_ops, obj); if (IS_ERR(attach)) { - obj = ERR_CAST(attach); - goto out_err; + xe_bo_put(gem_to_xe_bo(obj)); + return ERR_CAST(attach); } get_dma_buf(dma_buf); obj->import_attach = attach; return obj; - -out_err: - xe_bo_put(bo); - - return obj; } #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) From 9a34b94832c374543ce553d4cec6eda6955397d1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= Date: Fri, 8 May 2026 18:09:20 +0200 Subject: [PATCH 1120/1518] drm/ttm: Convert -EAGAIN from dmem_cgroup_try_charge to -ENOSPC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 591711b32681a04b57d00c2a404658f8419a081c upstream. dmem_cgroup_try_charge() returns -EAGAIN when the cgroup limit is hit and the charge fails. TTM has no concept of -EAGAIN from resource allocation; -ENOSPC is the canonical error meaning "no space, try eviction". Convert at the source in ttm_resource_alloc() so no caller needs to handle an unexpected error code, and clean up the now-redundant -EAGAIN check in ttm_bo_alloc_resource(). Without this, -EAGAIN escaping ttm_resource_alloc() during an eviction walk causes the walk to terminate early instead of continuing to the next candidate. Cc: Friedrich Vock Cc: Maarten Lankhorst Cc: Tejun Heo Cc: Maxime Ripard Cc: Christian Koenig Cc: dri-devel@lists.freedesktop.org Cc: # v6.14+ Fixes: 2b624a2c1865 ("drm/ttm: Handle cgroup based eviction in TTM") Assisted-by: GitHub_Copilot:claude-sonnet-4.6 Signed-off-by: Thomas Hellström Reviewed-by: Maarten Lankhorst Link: https://patch.msgid.link/20260508160920.230339-1-thomas.hellstrom@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ttm/ttm_bo.c | 2 +- drivers/gpu/drm/ttm/ttm_resource.c | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 29423ceeec5c7..cf0e785aa9d3c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -739,7 +739,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo, may_evict = (force_space && place->mem_type != TTM_PL_SYSTEM); ret = ttm_resource_alloc(bo, place, res, force_space ? &limit_pool : NULL); if (ret) { - if (ret != -ENOSPC && ret != -EAGAIN) { + if (ret != -ENOSPC) { dmem_cgroup_pool_state_put(limit_pool); return ret; } diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index e2c82ad07eb44..2a05fbd075465 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -384,8 +384,11 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo, if (man->cg) { ret = dmem_cgroup_try_charge(man->cg, bo->base.size, &pool, ret_limit_pool); - if (ret) + if (ret) { + if (ret == -EAGAIN) + ret = -ENOSPC; return ret; + } } ret = man->func->alloc(man, bo, place, res_ptr); From 6d835a99474cd7a6a9f3f94e8b66b188b2a64b95 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 8 May 2026 16:44:44 +0200 Subject: [PATCH 1121/1518] drm/gma500/oaktrail_hdmi: fix i2c adapter leak on setup commit 950953f774b3f69da6f413e045ef075e1f3da2df upstream. Make sure to drop the reference taken to the I2C adapter (and its module) when setting up HDMI to allow the adapter to be deregistered. Fixes: 1b082ccf5901 ("gma500: Add Oaktrail support") Cc: stable@vger.kernel.org # 3.3 Signed-off-by: Johan Hovold Signed-off-by: Patrik Jakobsson Link: https://patch.msgid.link/20260508144446.59722-2-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/gma500/oaktrail_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c index c0feca58511df..4366c01bf5d05 100644 --- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c +++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c @@ -579,6 +579,7 @@ static int oaktrail_hdmi_get_modes(struct drm_connector *connector) } else { edid = (struct edid *)raw_edid; /* FIXME ? edid = drm_get_edid(connector, i2c_adap); */ + i2c_put_adapter(i2c_adap); } if (edid) { From ab9256936b58eb178caddcf5b5b1638f079909d2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 8 May 2026 16:44:45 +0200 Subject: [PATCH 1122/1518] drm/gma500/oaktrail_lvds: fix hang on init failure commit 657a091ab6d01d0091b77660c75cfed573c9a53e upstream. The LVDS init code looks up an I2C adapter using i2c_get_adapter() and tries to read the EDID before falling back to allocating and registering its own adapter. The error handling does not separate these cases so on a late init failure it will try to deregister and free also an adapter that had previously been registered. Since i2c_get_adapter() takes another reference to the adapter, deregistration hangs indefinitely while waiting for the reference to be released. Fix this by only destroying adapters allocated during LVDS init on errors. Fixes: a57ebfc0b4da ("drm/gma500: Make oaktrail lvds use ddc adapter from drm_connector") Cc: stable@vger.kernel.org # 6.0 Cc: Patrik Jakobsson Signed-off-by: Johan Hovold Signed-off-by: Patrik Jakobsson Link: https://patch.msgid.link/20260508144446.59722-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/gma500/oaktrail_lvds.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c index 72191d6f0d06f..e2d5837fe54cd 100644 --- a/drivers/gpu/drm/gma500/oaktrail_lvds.c +++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c @@ -292,7 +292,7 @@ void oaktrail_lvds_init(struct drm_device *dev, { struct gma_encoder *gma_encoder; struct gma_connector *gma_connector; - struct gma_i2c_chan *ddc_bus; + struct gma_i2c_chan *ddc_bus = NULL; struct drm_connector *connector; struct drm_encoder *encoder; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); @@ -420,7 +420,8 @@ void oaktrail_lvds_init(struct drm_device *dev, err_unlock: mutex_unlock(&dev->mode_config.mutex); - gma_i2c_destroy(to_gma_i2c_chan(connector->ddc)); + if (!IS_ERR_OR_NULL(ddc_bus)) + gma_i2c_destroy(ddc_bus); drm_encoder_cleanup(encoder); err_connector_cleanup: drm_connector_cleanup(connector); From 4e003e2fb6d3f814a535d8fd44b17146e1c701a5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 8 May 2026 16:44:46 +0200 Subject: [PATCH 1123/1518] drm/gma500/oaktrail_lvds: fix i2c adapter leaks on init commit 84d1c9b416d54afe760ca4c378bd95c89261254c upstream. The LVDS init code looks up an I2C adapter using i2c_get_adapter() and tries to read the EDID before falling back to allocating and registering its own adapter. Make sure to drop the references taken by i2c_get_adapter() when falling back to allocating an adapter as well as on late errors to allow the looked up adapter to be deregistered. Fixes: 1b082ccf5901 ("gma500: Add Oaktrail support") Cc: stable@vger.kernel.org # 3.3 Signed-off-by: Johan Hovold Signed-off-by: Patrik Jakobsson Link: https://patch.msgid.link/20260508144446.59722-4-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/gma500/oaktrail_lvds.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c index e2d5837fe54cd..cdaa9b5b78cb8 100644 --- a/drivers/gpu/drm/gma500/oaktrail_lvds.c +++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c @@ -366,6 +366,8 @@ void oaktrail_lvds_init(struct drm_device *dev, if (edid == NULL && dev_priv->lpc_gpio_base) { ddc_bus = oaktrail_lvds_i2c_init(dev); if (!IS_ERR(ddc_bus)) { + if (i2c_adap) + i2c_put_adapter(i2c_adap); i2c_adap = &ddc_bus->base; edid = drm_get_edid(connector, i2c_adap); } @@ -422,6 +424,8 @@ void oaktrail_lvds_init(struct drm_device *dev, mutex_unlock(&dev->mode_config.mutex); if (!IS_ERR_OR_NULL(ddc_bus)) gma_i2c_destroy(ddc_bus); + else if (i2c_adap) + i2c_put_adapter(i2c_adap); drm_encoder_cleanup(encoder); err_connector_cleanup: drm_connector_cleanup(connector); From 4fa42a249e8cd6ed17aea04e5695b6e9001f2433 Mon Sep 17 00:00:00 2001 From: Ashutosh Desai Date: Wed, 15 Apr 2026 05:00:00 +0000 Subject: [PATCH 1124/1518] drm/v3d: Reject empty multisync extension to prevent infinite loop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit fb44d589bf3148e13452185a6e772a7efbf2d684 upstream. v3d_get_extensions() walks a userspace-provided singly-linked list of ioctl extensions without any bound on the chain length. A local user can craft a self-referential extension (ext->next == &ext) with zero in_sync_count and out_sync_count, which bypasses the existing duplicate- extension guard: if (se->in_sync_count || se->out_sync_count) return -EINVAL; The guard never fires because v3d_get_multisync_post_deps() returns immediately when count is zero, leaving both fields at zero on every iteration. The result is an infinite loop in kernel context, blocking the calling thread and pegging a CPU core indefinitely. Fix this by rejecting a multisync extension where both in_sync_count and out_sync_count are zero in v3d_get_multisync_submit_deps(). An empty multisync carries no synchronization information and serves no useful purpose, so returning -EINVAL for such an extension is the correct defense against this attack vector. Fixes: e4165ae8304e ("drm/v3d: add multiple syncobjs support") Cc: stable@vger.kernel.org Signed-off-by: Ashutosh Desai Link: https://patch.msgid.link/20260415050000.3816128-1-ashutoshdesai993@gmail.com Signed-off-by: Maíra Canal Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/v3d/v3d_submit.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index f3652e90683c3..23fa18e5e65c8 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -390,6 +390,11 @@ v3d_get_multisync_submit_deps(struct drm_file *file_priv, if (multisync.pad) return -EINVAL; + if (!multisync.in_sync_count && !multisync.out_sync_count) { + DRM_DEBUG("Empty multisync extension\n"); + return -EINVAL; + } + ret = v3d_get_multisync_post_deps(file_priv, se, multisync.out_sync_count, multisync.out_syncs); if (ret) From 244575d0c695862bfd59ea3b1754c1e7f88ed454 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 15 May 2026 11:36:49 -0400 Subject: [PATCH 1125/1518] eventfs: Use list_add_tail_rcu() for SRCU-protected children list [ Upstream commit f67950b2887fa10df50c4317a1fe98a65bc6875b ] Commit d2603279c7d6 ("eventfs: Use list_del_rcu() for SRCU protected list variable") converted the removal side to pair with the list_for_each_entry_srcu() walker in eventfs_iterate(). The insertion in eventfs_create_dir() was left as a plain list_add_tail(), which on weakly-ordered architectures can expose a new entry to the SRCU reader before its list pointers and fields are observable. Use list_add_tail_rcu() so the publication pairs with the existing list_del_rcu() and list_for_each_entry_srcu(). Fixes: 43aa6f97c2d0 ("eventfs: Get rid of dentry pointers without refcounts") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260418152251.199343-1-devnexen@gmail.com Signed-off-by: David Carlier Signed-off-by: Steven Rostedt [ adapted scoped_guard(mutex, &eventfs_mutex) block to explicit mutex_lock()/mutex_unlock() pair ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/tracefs/event_inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 0d2bc92b760f3..02d56ed6ad20e 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -732,7 +732,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode mutex_lock(&eventfs_mutex); if (!parent->is_freed) - list_add_tail(&ei->list, &parent->children); + list_add_tail_rcu(&ei->list, &parent->children); mutex_unlock(&eventfs_mutex); /* Was the parent freed? */ From 2647b8fe2f1f85194092a94d7ca0c4679795da87 Mon Sep 17 00:00:00 2001 From: Piyush Sachdeva Date: Fri, 15 May 2026 17:35:02 -0400 Subject: [PATCH 1126/1518] smb: client: Use FullSessionKey for AES-256 encryption key derivation [ Upstream commit 5be7a0cef3229fb3b63a07c0d289daf752545424 ] When Kerberos authentication is used with AES-256 encryption (AES-256-CCM or AES-256-GCM), the SMB3 encryption and decryption keys must be derived using the full session key (Session.FullSessionKey) rather than just the first 16 bytes (Session.SessionKey). Per MS-SMB2 section 3.2.5.3.1, when Connection.Dialect is "3.1.1" and Connection.CipherId is AES-256-CCM or AES-256-GCM, Session.FullSessionKey must be set to the full cryptographic key from the GSS authentication context. The encryption and decryption key derivation (SMBC2SCipherKey, SMBS2CCipherKey) must use this FullSessionKey as the KDF input. The signing key derivation continues to use Session.SessionKey (first 16 bytes) in all cases. Previously, generate_key() hardcoded SMB2_NTLMV2_SESSKEY_SIZE (16) as the HMAC-SHA256 key input length for all derivations. When Kerberos with AES-256 provides a 32-byte session key, the KDF for encryption/decryption was using only the first 16 bytes, producing keys that did not match the server's, causing mount failures with sec=krb5 and require_gcm_256=1. Add a full_key_size parameter to generate_key() and pass the appropriate size from generate_smb3signingkey(): - Signing: always SMB2_NTLMV2_SESSKEY_SIZE (16 bytes) - Encryption/Decryption: ses->auth_key.len when AES-256, otherwise 16 Also fix cifs_dump_full_key() to report the actual session key length for AES-256 instead of hardcoded CIFS_SESS_KEY_SIZE, so that userspace tools like Wireshark receive the correct key for decryption. Cc: Reviewed-by: Bharath SM Signed-off-by: Piyush Sachdeva Signed-off-by: Piyush Sachdeva Signed-off-by: Steve French Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/ioctl.c | 2 +- fs/smb/client/smb2transport.c | 32 +++++++++++++++++++++++++------- 2 files changed, 26 insertions(+), 8 deletions(-) diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 0a9935ce05a5a..1a6ce837e26af 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -297,7 +297,7 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug break; case SMB2_ENCRYPTION_AES256_CCM: case SMB2_ENCRYPTION_AES256_GCM: - out.session_key_length = CIFS_SESS_KEY_SIZE; + out.session_key_length = ses->auth_key.len; out.server_in_key_length = out.server_out_key_length = SMB3_GCM256_CRYPTKEY_SIZE; break; default: diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 211305d43f8d4..db98ced541baa 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -259,7 +259,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, } static int generate_key(struct cifs_ses *ses, struct kvec label, - struct kvec context, __u8 *key, unsigned int key_size) + struct kvec context, __u8 *key, unsigned int key_size, + unsigned int full_key_size) { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; @@ -280,7 +281,7 @@ static int generate_key(struct cifs_ses *ses, struct kvec label, } hmac_sha256_init_usingrawkey(&hmac_ctx, ses->auth_key.response, - SMB2_NTLMV2_SESSKEY_SIZE); + full_key_size); hmac_sha256_update(&hmac_ctx, i, 4); hmac_sha256_update(&hmac_ctx, label.iov_base, label.iov_len); hmac_sha256_update(&hmac_ctx, &zero, 1); @@ -314,6 +315,7 @@ generate_smb3signingkey(struct cifs_ses *ses, struct TCP_Server_Info *server, const struct derivation_triplet *ptriplet) { + unsigned int full_key_size = SMB2_NTLMV2_SESSKEY_SIZE; int rc; bool is_binding = false; int chan_index = 0; @@ -348,17 +350,31 @@ generate_smb3signingkey(struct cifs_ses *ses, rc = generate_key(ses, ptriplet->signing.label, ptriplet->signing.context, ses->chans[chan_index].signkey, - SMB3_SIGN_KEY_SIZE); + SMB3_SIGN_KEY_SIZE, + SMB2_NTLMV2_SESSKEY_SIZE); if (rc) return rc; } else { rc = generate_key(ses, ptriplet->signing.label, ptriplet->signing.context, ses->smb3signingkey, - SMB3_SIGN_KEY_SIZE); + SMB3_SIGN_KEY_SIZE, + SMB2_NTLMV2_SESSKEY_SIZE); if (rc) return rc; + /* + * Per MS-SMB2 3.2.5.3.1, signing key always uses Session.SessionKey + * (first 16 bytes). Encryption/decryption keys use + * Session.FullSessionKey when dialect is 3.1.1 and cipher is + * AES-256-CCM or AES-256-GCM, otherwise Session.SessionKey. + */ + + if (server->dialect == SMB311_PROT_ID && + (server->cipher_type == SMB2_ENCRYPTION_AES256_CCM || + server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) + full_key_size = ses->auth_key.len; + /* safe to access primary channel, since it will never go away */ spin_lock(&ses->chan_lock); memcpy(ses->chans[chan_index].signkey, ses->smb3signingkey, @@ -368,13 +384,15 @@ generate_smb3signingkey(struct cifs_ses *ses, rc = generate_key(ses, ptriplet->encryption.label, ptriplet->encryption.context, ses->smb3encryptionkey, - SMB3_ENC_DEC_KEY_SIZE); + SMB3_ENC_DEC_KEY_SIZE, + full_key_size); if (rc) return rc; rc = generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, ses->smb3decryptionkey, - SMB3_ENC_DEC_KEY_SIZE); + SMB3_ENC_DEC_KEY_SIZE, + full_key_size); if (rc) return rc; } @@ -389,7 +407,7 @@ generate_smb3signingkey(struct cifs_ses *ses, &ses->Suid); cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type); cifs_dbg(VFS, "Session Key %*ph\n", - SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); + (int)ses->auth_key.len, ses->auth_key.response); cifs_dbg(VFS, "Signing Key %*ph\n", SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || From b6437e6f8f3df87b3fea6d808775d88ee4b5b437 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sat, 16 May 2026 15:09:07 -0400 Subject: [PATCH 1127/1518] btrfs: do not mark inode incompressible after inline attempt fails [ Upstream commit 2e0e3716c7b6f8d71df2fbe709b922e54700f71b ] [BUG] The following sequence will set the file with nocompress flag: # mkfs.btrfs -f $dev # mount $dev $mnt -o max_inline=4,compress # xfs_io -f -c "pwrite 0 2k" -c sync $mnt/foobar The inode will have NOCOMPRESS flag, even if the content itself (all 0xcd) can still be compressed very well: item 4 key (257 INODE_ITEM 0) itemoff 15879 itemsize 160 generation 9 transid 10 size 2097152 nbytes 1052672 block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0 sequence 257 flags 0x8(NOCOMPRESS) Please note that, this behavior is there even before commit 59615e2c1f63 ("btrfs: reject single block sized compression early"). [CAUSE] At compress_file_range(), after btrfs_compress_folios() call, we try making an inlined extent by calling cow_file_range_inline(). But cow_file_range_inline() calls can_cow_file_range_inline() which has more accurate checks on if the range can be inlined. One of the user configurable conditions is the "max_inline=" mount option. If that value is set low (like the example, 4 bytes, which cannot store any header), or the compressed content is just slightly larger than 2K (the default value, meaning a 50% compression ratio), cow_file_range_inline() will return 1 immediately. And since we're here only to try inline the compressed data, the range is no larger than a single fs block. Thus compression is never going to make it a win, we fall back to marking the inode incompressible unavoidably. [FIX] Just add an extra check after inline attempt, so that if the inline attempt failed, do not set the nocompress flag. As there is no way to remove that flag, and the default 50% compression ratio is way too strict for the whole inode. CC: stable@vger.kernel.org # 6.12+ Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5b99f2941f577..2c361e0691fc5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1006,6 +1006,12 @@ static void compress_file_range(struct btrfs_work *work) mapping_set_error(mapping, -EIO); goto free_pages; } + /* + * If a single block at file offset 0 cannot be inlined, fall back to + * regular writes without marking the file incompressible. + */ + if (start == 0 && end <= blocksize) + goto cleanup_and_bail_uncompressed; /* * We aren't doing an inline extent. Round the compressed size up to a From a3c44e77f3796f62b890c8a72eb1161efd525a8b Mon Sep 17 00:00:00 2001 From: Dapeng Mi Date: Sun, 17 May 2026 21:23:15 -0400 Subject: [PATCH 1128/1518] perf/x86/intel: Disable PMI for self-reloaded ACR events [ Upstream commit 1271aeccc307066315b2d3b0d5af2510e27018b5 ] On platforms with Auto Counter Reload (ACR) support, such as NVL, a "NMI received for unknown reason 30" warning is observed when running multiple events in a group with ACR enabled: $ perf record -e '{instructions/period=20000,acr_mask=0x2/u,\ cycles/period=40000,acr_mask=0x3/u}' ./test The warning occurs because the Performance Monitoring Interrupt (PMI) is enabled for the self-reloaded event (the cycles event in this case). According to the Intel SDM, the overflow bit (IA32_PERF_GLOBAL_STATUS.PMCn_OVF) is never set for self-reloaded events. Since the bit is not set, the perf NMI handler cannot identify the source of the interrupt, leading to the "unknown reason" message. Furthermore, enabling PMI for self-reloaded events is unnecessary and can lead to extraneous records that pollute the user's requested data. Disable the interrupt bit for all events configured with ACR self-reload. Fixes: ec980e4facef ("perf/x86/intel: Support auto counter reload") Reported-by: Andi Kleen Signed-off-by: Dapeng Mi Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260430002558.712334-4-dapeng1.mi@linux.intel.com Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/core.c | 17 +++++++++++++---- arch/x86/events/perf_event.h | 10 ++++++++++ 2 files changed, 23 insertions(+), 4 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7d8c7eb7838da..7d9f6a58f3f26 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2866,11 +2866,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event) intel_set_masks(event, idx); /* - * Enable IRQ generation (0x8), if not PEBS, - * and enable ring-3 counting (0x2) and ring-0 counting (0x1) - * if requested: + * Enable IRQ generation (0x8), if not PEBS or self-reloaded + * ACR event, and enable ring-3 counting (0x2) and ring-0 + * counting (0x1) if requested: */ - if (!event->attr.precise_ip) + if (!event->attr.precise_ip && !is_acr_self_reload_event(event)) bits |= INTEL_FIXED_0_ENABLE_PMI; if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) bits |= INTEL_FIXED_0_USER; @@ -2955,6 +2955,15 @@ static void intel_pmu_enable_event(struct perf_event *event) enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR; intel_set_masks(event, idx); static_call_cond(intel_pmu_enable_acr_event)(event); + /* + * For self-reloaded ACR event, don't enable PMI since + * HW won't set overflow bit in GLOBAL_STATUS. Otherwise, + * the PMI would be recognized as a suspicious NMI. + */ + if (is_acr_self_reload_event(event)) + hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + else if (!event->attr.precise_ip) + hwc->config |= ARCH_PERFMON_EVENTSEL_INT; __x86_pmu_enable_event(hwc, enable_mask); break; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 493e6ba51e06d..2bafb8f0f9077 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -133,6 +133,16 @@ static inline bool is_acr_event_group(struct perf_event *event) return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR); } +static inline bool is_acr_self_reload_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < 0) + return false; + + return test_bit(hwc->idx, (unsigned long *)&hwc->config1); +} + struct amd_nb { int nb_id; /* NorthBridge id */ int refcnt; /* reference count */ From 255c3998dae8c492ec3cc6ac550f27b233161e02 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 17 May 2026 22:11:00 -0400 Subject: [PATCH 1129/1518] sched_ext: Guard scx_dsq_move() against NULL kit->dsq after failed iter_new [ Upstream commit 4fda9f0e7c950da4fe03cedeb2ac818edf5d03e9 ] bpf_iter_scx_dsq_new() clears kit->dsq on failure and bpf_iter_scx_dsq_{next,destroy}() guard against that. scx_dsq_move() doesn't - it dereferences kit->dsq immediately, so a BPF program that calls scx_bpf_dsq_move[_vtime]() after a failed iter_new oopses the kernel. Return false if kit->dsq is NULL. Fixes: 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()") Cc: stable@vger.kernel.org # v6.12+ Reported-by: Chris Mason Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi [ dropped upstream `sch = src_dsq->sched` reordering since stable initializes `sch` from `scx_root` instead ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/sched/ext.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 32bb89559716e..5aba87198dc1c 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -5650,6 +5650,14 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, bool in_balance; unsigned long flags; + /* + * The verifier considers an iterator slot initialized on any + * KF_ITER_NEW return, so a BPF program may legally reach here after + * bpf_iter_scx_dsq_new() failed and left @kit->dsq NULL. + */ + if (unlikely(!src_dsq)) + return false; + if (!scx_kf_allowed_if_unlocked() && !scx_kf_allowed(sch, SCX_KF_DISPATCH)) return false; From a4a0340d20abe7c2b9c5c310db221045acef2652 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 18 May 2026 07:48:25 -0400 Subject: [PATCH 1130/1518] sched_ext: Pass held rq to SCX_CALL_OP() for core_sched_before [ Upstream commit 4155fb489fa175ec74eedde7d02219cf2fe74303 ] scx_prio_less() runs from core-sched's pick_next_task() path with rq locked but invokes ops.core_sched_before() with NULL locked_rq, leaving scx_locked_rq_state NULL. If the BPF callback calls a kfunc that re-acquires rq based on scx_locked_rq() - e.g. scx_bpf_cpuperf_set(cpu) - it re-acquires the already-held rq. Pass task_rq(a). Fixes: 7b0888b7cc19 ("sched_ext: Implement core-sched support") Cc: stable@vger.kernel.org # v6.12+ Reported-by: Chris Mason Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi [ adapted call to use stable's single `sch`/`SCX_KF_REST` mask and `scx_rq_bypassing(task_rq(a))` signature ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 5aba87198dc1c..35c0b31924d37 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2522,7 +2522,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, if (SCX_HAS_OP(sch, core_sched_before) && !scx_rq_bypassing(task_rq(a))) return SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, core_sched_before, - NULL, + task_rq(a), (struct task_struct *)a, (struct task_struct *)b); else From fac9cfad2f90fa21d81327028c7125889442c005 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 19 May 2026 07:53:09 -0400 Subject: [PATCH 1131/1518] f2fs: fix false alarm of lockdep on cp_global_sem lock [ Upstream commit 6a5e3de9c2bb0b691d16789a5d19e9276a09b308 ] lockdep reported a potential deadlock: a) TCMU device removal context: - call del_gendisk() to get q->q_usage_counter - call start_flush_work() to get work_completion of wb->dwork b) f2fs writeback context: - in wb_workfn(), which holds work_completion of wb->dwork - call f2fs_balance_fs() to get sbi->gc_lock c) f2fs vfs_write context: - call f2fs_gc() to get sbi->gc_lock - call f2fs_write_checkpoint() to get sbi->cp_global_sem d) f2fs mount context: - call recover_fsync_data() to get sbi->cp_global_sem - call f2fs_check_and_fix_write_pointer() to call blkdev_report_zones() that goes down to blk_mq_alloc_request and get q->q_usage_counter Original callstack is in Closes tag. However, I think this is a false alarm due to before mount returns successfully (context d), we can not access file therein via vfs_write (context c). Let's introduce per-sb cp_global_sem_key, and assign the key for cp_global_sem, so that lockdep can recognize cp_global_sem from different super block correctly. A lot of work are done by Shin'ichiro Kawasaki, thanks a lot for the work. Fixes: c426d99127b1 ("f2fs: Check write pointer consistency of open zones") Cc: stable@kernel.org Reported-and-tested-by: Shin'ichiro Kawasaki Closes: https://lore.kernel.org/linux-f2fs-devel/20260218125237.3340441-1-shinichiro.kawasaki@wdc.com Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim [ adapted context to use plain `init_f2fs_rwsem` instead of mainline's `init_f2fs_rwsem_trace` macro ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/f2fs.h | 3 +++ fs/f2fs/super.c | 11 +++++++++++ 2 files changed, 14 insertions(+) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b3731ba46f571..a77858bd38779 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1967,6 +1967,9 @@ struct f2fs_sb_info { spinlock_t iostat_lat_lock; struct iostat_lat_info *iostat_io_lat; #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key cp_global_sem_key; +#endif }; /* Definitions to access f2fs_sb_info */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index cb8e8a587ba9e..9154f702e1706 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -4889,6 +4889,11 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) init_f2fs_rwsem(&sbi->gc_lock); mutex_init(&sbi->writepages); init_f2fs_rwsem(&sbi->cp_global_sem); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + lockdep_register_key(&sbi->cp_global_sem_key); + lockdep_set_class(&sbi->cp_global_sem.internal_rwsem, + &sbi->cp_global_sem_key); +#endif init_f2fs_rwsem(&sbi->node_write); init_f2fs_rwsem(&sbi->node_change); spin_lock_init(&sbi->stat_lock); @@ -5360,6 +5365,9 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) free_sb_buf: kfree(raw_super); free_sbi: +#ifdef CONFIG_DEBUG_LOCK_ALLOC + lockdep_unregister_key(&sbi->cp_global_sem_key); +#endif kfree(sbi); sb->s_fs_info = NULL; @@ -5441,6 +5449,9 @@ static void kill_f2fs_super(struct super_block *sb) /* Release block devices last, after fscrypt_destroy_keyring(). */ if (sbi) { destroy_device_list(sbi); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + lockdep_unregister_key(&sbi->cp_global_sem_key); +#endif kfree(sbi); sb->s_fs_info = NULL; } From 27fcf3dd04df2defeff4c00ff3d2a2ae4b3d4831 Mon Sep 17 00:00:00 2001 From: Pei Xiao Date: Wed, 20 May 2026 09:11:27 -0400 Subject: [PATCH 1132/1518] spi: sifive: Simplify clock handling with devm_clk_get_enabled() [ Upstream commit 140039c23aca067b9ff0242e3c0ce96276bb95f3 ] Replace devm_clk_get() followed by clk_prepare_enable() with devm_clk_get_enabled() for the bus clock. This reduces boilerplate code and error handling, as the managed API automatically disables the clock when the device is removed or if probe fails. Remove the now-unnecessary clk_disable_unprepare() calls from the probe error path and the remove callback. Adjust the error handling to use the existing put_host label. Signed-off-by: Pei Xiao Link: https://patch.msgid.link/73d0d8ecb4e1af5a558d6a7866c0f886d94fe3d1.1773885292.git.xiaopei01@kylinos.cn Signed-off-by: Mark Brown Stable-dep-of: 0f25236694a2 ("spi: sifive: fix controller deregistration") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-sifive.c | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/drivers/spi/spi-sifive.c b/drivers/spi/spi-sifive.c index 87bde2a207a3e..90be9fbab7071 100644 --- a/drivers/spi/spi-sifive.c +++ b/drivers/spi/spi-sifive.c @@ -312,7 +312,8 @@ static int sifive_spi_probe(struct platform_device *pdev) goto put_host; } - spi->clk = devm_clk_get(&pdev->dev, NULL); + /* Spin up the bus clock before hitting registers */ + spi->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(spi->clk)) { dev_err(&pdev->dev, "Unable to find bus clock\n"); ret = PTR_ERR(spi->clk); @@ -342,13 +343,6 @@ static int sifive_spi_probe(struct platform_device *pdev) goto put_host; } - /* Spin up the bus clock before hitting registers */ - ret = clk_prepare_enable(spi->clk); - if (ret) { - dev_err(&pdev->dev, "Unable to enable bus clock\n"); - goto put_host; - } - /* probe the number of CS lines */ spi->cs_inactive = sifive_spi_read(spi, SIFIVE_SPI_REG_CSDEF); sifive_spi_write(spi, SIFIVE_SPI_REG_CSDEF, 0xffffffffU); @@ -357,14 +351,14 @@ static int sifive_spi_probe(struct platform_device *pdev) if (!cs_bits) { dev_err(&pdev->dev, "Could not auto probe CS lines\n"); ret = -EINVAL; - goto disable_clk; + goto put_host; } num_cs = ilog2(cs_bits) + 1; if (num_cs > SIFIVE_SPI_MAX_CS) { dev_err(&pdev->dev, "Invalid number of spi targets\n"); ret = -EINVAL; - goto disable_clk; + goto put_host; } /* Define our host */ @@ -393,7 +387,7 @@ static int sifive_spi_probe(struct platform_device *pdev) dev_name(&pdev->dev), spi); if (ret) { dev_err(&pdev->dev, "Unable to bind to interrupt\n"); - goto disable_clk; + goto put_host; } dev_info(&pdev->dev, "mapped; irq=%d, cs=%d\n", @@ -402,13 +396,11 @@ static int sifive_spi_probe(struct platform_device *pdev) ret = devm_spi_register_controller(&pdev->dev, host); if (ret < 0) { dev_err(&pdev->dev, "spi_register_host failed\n"); - goto disable_clk; + goto put_host; } return 0; -disable_clk: - clk_disable_unprepare(spi->clk); put_host: spi_controller_put(host); @@ -422,7 +414,6 @@ static void sifive_spi_remove(struct platform_device *pdev) /* Disable all the interrupts just in case */ sifive_spi_write(spi, SIFIVE_SPI_REG_IE, 0); - clk_disable_unprepare(spi->clk); } static int sifive_spi_suspend(struct device *dev) From 6bf4253af8142a47aa66cb1ffbe5e8ad7065a32a Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 20 May 2026 09:11:28 -0400 Subject: [PATCH 1133/1518] spi: sifive: fix controller deregistration [ Upstream commit 0f25236694a2854627c1597465a071e6bb6fe572 ] Make sure to deregister the controller before disabling underlying resources like interrupts during driver unbind. Note that clocks were also disabled before the recent commit 140039c23aca ("spi: sifive: Simplify clock handling with devm_clk_get_enabled()"). Fixes: 484a9a68d669 ("spi: sifive: Add driver for the SiFive SPI controller") Cc: stable@vger.kernel.org # 5.1 Cc: Yash Shah Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260410081757.503099-15-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-sifive.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-sifive.c b/drivers/spi/spi-sifive.c index 90be9fbab7071..d6e0f12e86b82 100644 --- a/drivers/spi/spi-sifive.c +++ b/drivers/spi/spi-sifive.c @@ -393,7 +393,7 @@ static int sifive_spi_probe(struct platform_device *pdev) dev_info(&pdev->dev, "mapped; irq=%d, cs=%d\n", irq, host->num_chipselect); - ret = devm_spi_register_controller(&pdev->dev, host); + ret = spi_register_controller(host); if (ret < 0) { dev_err(&pdev->dev, "spi_register_host failed\n"); goto put_host; @@ -412,8 +412,14 @@ static void sifive_spi_remove(struct platform_device *pdev) struct spi_controller *host = platform_get_drvdata(pdev); struct sifive_spi *spi = spi_controller_get_devdata(host); + spi_controller_get(host); + + spi_unregister_controller(host); + /* Disable all the interrupts just in case */ sifive_spi_write(spi, SIFIVE_SPI_REG_IE, 0); + + spi_controller_put(host); } static int sifive_spi_suspend(struct device *dev) From 640e37f58f991546a87540d067279c2c1fa9fe51 Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Tue, 5 May 2026 16:43:36 -0700 Subject: [PATCH 1134/1518] net/rds: reset op_nents when zerocopy page pin fails commit e174929793195e0cd6a4adb0cad731b39f9019b4 upstream. When iov_iter_get_pages2() fails in rds_message_zcopy_from_user(), the pinned pages are released with put_page(), and rm->data.op_mmp_znotifier is cleared. But we fail to properly clear rm->data.op_nents. Later when rds_message_purge() is called from rds_sendmsg() the cleanup loop iterates over the incorrectly non zero number of op_nents and frees them again. Fix this by properly resetting op_nents when it should be in rds_message_zcopy_from_user(). Fixes: 0cebaccef3ac ("rds: zerocopy Tx support.") Signed-off-by: Allison Henderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260505234336.2132721-1-achender@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/rds/message.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rds/message.c b/net/rds/message.c index bdf5af2547577..064e507f0ccf2 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -408,6 +408,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter * for (i = 0; i < rm->data.op_nents; i++) put_page(sg_page(&rm->data.op_sg[i])); + rm->data.op_nents = 0; mmp = &rm->data.op_mmp_znotifier->z_mmp; mm_unaccount_pinned_pages(mmp); ret = -EFAULT; From 3bd9e113d50034db99d7ef69fd8e5242d15e414a Mon Sep 17 00:00:00 2001 From: William Bowling Date: Wed, 13 May 2026 04:16:35 +0000 Subject: [PATCH 1135/1518] net: skbuff: preserve shared-frag marker during coalescing commit f84eca5817390257cef78013d0112481c503b4a3 upstream. skb_try_coalesce() can attach paged frags from @from to @to. If @from has SKBFL_SHARED_FRAG set, the resulting @to skb can contain the same externally-owned or page-cache-backed frags, but the shared-frag marker is currently lost. That breaks the invariant relied on by later in-place writers. In particular, ESP input checks skb_has_shared_frag() before deciding whether an uncloned nonlinear skb can skip skb_cow_data(). If TCP receive coalescing has moved shared frags into an unmarked skb, ESP can see skb_has_shared_frag() as false and decrypt in place over page-cache backed frags. Propagate SKBFL_SHARED_FRAG when skb_try_coalesce() transfers paged frags. The tailroom copy path does not need the marker because it copies bytes into @to's linear data rather than transferring frag descriptors. Fixes: cef401de7be8 ("net: fix possible wrong checksum generation") Fixes: f4c50a4034e6 ("xfrm: esp: avoid in-place decrypt on shared skb frags") Signed-off-by: William Bowling Reviewed-by: Eric Dumazet Tested-by: Jiayuan Chen Link: https://patch.msgid.link/20260513041635.1289541-1-vakzz@zellic.io Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a4695882d1c4c..3e8f0b8226caf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6149,6 +6149,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; + if (from_shinfo->nr_frags) + to_shinfo->flags |= from_shinfo->flags & SKBFL_SHARED_FRAG; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; From ff375cc75f9167168db38e0464a482d5fbc8d81d Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Sat, 16 May 2026 07:28:53 +0900 Subject: [PATCH 1136/1518] net: skbuff: propagate shared-frag marker through frag-transfer helpers commit 48f6a5356a33dd78e7144ae1faef95ffc990aae0 upstream. Two frag-transfer helpers (__pskb_copy_fclone() and skb_shift()) fail to propagate the SKBFL_SHARED_FRAG bit in skb_shinfo()->flags when moving frags from source to destination. __pskb_copy_fclone() defers the rest of the shinfo metadata to skb_copy_header() after copying frag descriptors, but that helper only carries over gso_{size,segs, type} and never touches skb_shinfo()->flags; skb_shift() moves frag descriptors directly and leaves flags untouched. As a result, the destination skb keeps a reference to the same externally-owned or page-cache-backed pages while reporting skb_has_shared_frag() as false. The mismatch is harmful in any in-place writer that uses skb_has_shared_frag() to decide whether shared pages must be detoured through skb_cow_data(). ESP input is one such writer (esp4.c, esp6.c), and a single nft 'dup to ' rule -- or any other nf_dup_ipv4() / xt_TEE caller -- is enough to land a pskb_copy()'d skb in esp_input() with the marker stripped, letting an unprivileged user write into the page cache of a root-owned read-only file via authencesn-ESN stray writes. Set SKBFL_SHARED_FRAG on the destination whenever frag descriptors were actually moved from the source. skb_copy() and skb_copy_expand() share skb_copy_header() too but linearize all paged data into freshly allocated head storage and emerge with nr_frags == 0, so skb_has_shared_frag() returns false on its own; they need no change. The same omission exists in skb_gro_receive() and skb_gro_receive_list(). The former moves the incoming skb's frag descriptors into the accumulator's last sub-skb via two paths (a direct frag-move loop and the head_frag + memcpy path); the latter chains the incoming skb whole onto p's frag_list. Downstream skb_segment() reads only skb_shinfo(p)->flags, and skb_segment_list() reuses each sub-skb's shinfo as the nskb -- both p and lp must carry the marker. The same omission also exists in tcp_clone_payload(), which builds an MTU probe skb by moving frag descriptors from skbs on sk_write_queue into a freshly allocated nskb. The helper falls into the same family and warrants the same fix for consistency; no TCP TX-side in-place writer is currently known to reach a user page through this gap, but a future consumer depending on the marker would regress silently. The same omission exists in skb_segment(): the per-iteration flag merge takes only head_skb's flag, and the inner switch that rebinds frag_skb to list_skb on head_skb-frags exhaustion does not fold the new frag_skb's flag into nskb. Fold frag_skb's flag at both sites so segments drawing frags from frag_list members carry the marker. Fixes: cef401de7be8 ("net: fix possible wrong checksum generation") Fixes: f4c50a4034e6 ("xfrm: esp: avoid in-place decrypt on shared skb frags") Suggested-by: Sabrina Dubroca Suggested-by: Sultan Alsawaf Suggested-by: Ben Hutchings Suggested-by: Lin Ma Suggested-by: Jingguo Tan Suggested-by: Aaron Esau Cc: stable@vger.kernel.org Signed-off-by: Hyunwoo Kim Tested-by: Rajat Gupta Link: https://patch.msgid.link/ageeJfJHwgzmKXbh@v4bel Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- net/core/gro.c | 4 ++++ net/core/skbuff.c | 9 ++++++++- net/ipv4/tcp_output.c | 1 + 3 files changed, 13 insertions(+), 1 deletion(-) diff --git a/net/core/gro.c b/net/core/gro.c index ef61695fbdbb6..867611d171dbb 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -215,10 +215,12 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) p->data_len += len; p->truesize += delta_truesize; p->len += len; + skb_shinfo(p)->flags |= skbinfo->flags & SKBFL_SHARED_FRAG; if (lp != p) { lp->data_len += len; lp->truesize += delta_truesize; lp->len += len; + skb_shinfo(lp)->flags |= skbinfo->flags & SKBFL_SHARED_FRAG; } NAPI_GRO_CB(skb)->same_flow = 1; return 0; @@ -246,6 +248,8 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) p->truesize += skb->truesize; p->len += skb->len; + skb_shinfo(p)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + NAPI_GRO_CB(skb)->same_flow = 1; return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3e8f0b8226caf..a8911f1b90c15 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2188,6 +2188,7 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; + skb_shinfo(n)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } if (skb_has_frag_list(skb)) { @@ -4301,6 +4302,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; + skb_shinfo(tgt)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + skb_len_add(skb, -shiftlen); skb_len_add(tgt, shiftlen); @@ -4911,7 +4914,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & + skb_shinfo(nskb)->flags |= (skb_shinfo(head_skb)->flags | + skb_shinfo(frag_skb)->flags) & SKBFL_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) @@ -4928,6 +4932,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; + + skb_shinfo(nskb)->flags |= skb_shinfo(frag_skb)->flags & SKBFL_SHARED_FRAG; + if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5a443fb14a973..6937b2b03ef93 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2543,6 +2543,7 @@ static int tcp_clone_payload(struct sock *sk, struct sk_buff *to, todo = min_t(int, skb_frag_size(fragfrom), probe_size - len); len += todo; + skb_shinfo(to)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; if (lastfrag && skb_frag_page(fragfrom) == skb_frag_page(lastfrag) && skb_frag_off(fragfrom) == skb_frag_off(lastfrag) + From e9a23ec9461e9e76f0f8e02821627478a576b5ee Mon Sep 17 00:00:00 2001 From: Venkat Rao Bagalkote Date: Fri, 10 Apr 2026 16:24:04 +0530 Subject: [PATCH 1137/1518] selftests/bpf: Remove test_access_variable_array commit aacee214d57636fa1f63007c65f333b5ea75a7a0 upstream. test_access_variable_array relied on accessing struct sched_domain::span to validate variable-length array handling via BTF. Recent scheduler refactoring removed or hid this field, causing the test to fail to build. Given that this test depends on internal scheduler structures that are subject to refactoring, and equivalent variable-length array coverage already exists via bpf_testmod-based tests, remove test_access_variable_array entirely. Link: https://lore.kernel.org/all/177434340048.1647592.8586759362906719839.tip-bot2@tip-bot2/ Signed-off-by: Venkat Rao Bagalkote Tested-by: Naveen Kumar Thummalapenta Link: https://lore.kernel.org/r/20260410105404.91126-1-venkat88@linux.ibm.com Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- .../bpf/prog_tests/access_variable_array.c | 16 ---------------- .../bpf/progs/test_access_variable_array.c | 19 ------------------- 2 files changed, 35 deletions(-) delete mode 100644 tools/testing/selftests/bpf/prog_tests/access_variable_array.c delete mode 100644 tools/testing/selftests/bpf/progs/test_access_variable_array.c diff --git a/tools/testing/selftests/bpf/prog_tests/access_variable_array.c b/tools/testing/selftests/bpf/prog_tests/access_variable_array.c deleted file mode 100644 index 08131782437c6..0000000000000 --- a/tools/testing/selftests/bpf/prog_tests/access_variable_array.c +++ /dev/null @@ -1,16 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2022 Bytedance */ - -#include -#include "test_access_variable_array.skel.h" - -void test_access_variable_array(void) -{ - struct test_access_variable_array *skel; - - skel = test_access_variable_array__open_and_load(); - if (!ASSERT_OK_PTR(skel, "test_access_variable_array__open_and_load")) - return; - - test_access_variable_array__destroy(skel); -} diff --git a/tools/testing/selftests/bpf/progs/test_access_variable_array.c b/tools/testing/selftests/bpf/progs/test_access_variable_array.c deleted file mode 100644 index 326b7d1f496ab..0000000000000 --- a/tools/testing/selftests/bpf/progs/test_access_variable_array.c +++ /dev/null @@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2023 Bytedance */ - -#include "vmlinux.h" -#include -#include - -unsigned long span = 0; - -SEC("fentry/sched_balance_rq") -int BPF_PROG(fentry_fentry, int this_cpu, struct rq *this_rq, - struct sched_domain *sd) -{ - span = sd->span[0]; - - return 0; -} - -char _license[] SEC("license") = "GPL"; From 664736cc1f95198438aa69ae82df9f42c64d0e1c Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:45 +0100 Subject: [PATCH 1138/1518] netfs: Fix potential uninitialised var in netfs_extract_user_iter() commit 7e3d8db899d54af39fafb2eb3392b0cdae9973b5 upstream. In netfs_extract_user_iter(), if it's given a zero-length iterator, it will fall through the loop without setting ret, and so the error handling behaviour will be undefined, depending on whether ret happens to be negative. The value of ret then propagates back up the callstack. Fix this by presetting ret to 0. Fixes: 85dd2c8ff368 ("netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-9-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/netfs/iterator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index adca78747f239..429e4396e1b00 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -43,7 +43,7 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, unsigned int max_pages; unsigned int npages = 0; unsigned int i; - ssize_t ret; + ssize_t ret = 0; size_t count = orig_len, offset, len; size_t bv_size, pg_size; From 83657f4189612e5cbcabc3058acd36c0bd120729 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 23 May 2026 13:07:21 +0200 Subject: [PATCH 1139/1518] Linux 6.18.33 Link: https://lore.kernel.org/r/20260520162134.554764788@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Wentao Guan Tested-by: Pavel Machek (CIP) Tested-by: Jon Hunter Tested-by: Peter Schneider Tested-by: Mark Brown Tested-by: Brett A C Sheffield Tested-by: Ron Economos Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 70e10b29b3859..dc63a98489a54 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 32 +SUBLEVEL = 33 EXTRAVERSION = NAME = Baby Opossum Posse From 814326e86e929b865020ff44f4576dbdfe3f7ff3 Mon Sep 17 00:00:00 2001 From: Gustavo Sousa Date: Fri, 22 May 2026 15:47:22 -0300 Subject: [PATCH 1140/1518] drm/xe/hdcp: Add NULL check for media_gt in intel_hdcp_gsc_check_status() commit 60a1e131a811b68703da58fd805ab359b704ab03 upstream. When media GT is disabled via configfs, there is no allocation for media_gt, which is kept as NULL. In such scenario, intel_hdcp_gsc_check_status() results in a kernel pagefault error due to >->uc.gsc being evaluated as an invalid memory address. Fix that by introducing a NULL check on media_gt and bailing out early if so. While at it, also drop the NULL check for gsc, since it can't be NULL if media_gt is not NULL. v2: - Get address for gsc only after checking that gt is not NULL. (Shuicheng) - Drop the NULL check for gsc. (Shuicheng) v3: - Add "Fixes" and "Cc: " tags. (Matt) Fixes: 4af50beb4e0f ("drm/xe: Use gsc_proxy_init_done to check proxy status") Cc: # v6.10+ Reviewed-by: Matt Roper Reviewed-by: Shuicheng Lin Link: https://patch.msgid.link/20260416-check-for-null-media_gt-in-intel_hdcp_gsc_check_status-v2-1-9adb9fd3b621@intel.com Signed-off-by: Gustavo Sousa (cherry picked from commit bfaf87e84ca3ca3f6e275f9ae56da47a8b55ffd1) Signed-off-by: Matthew Brost Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/display/xe_hdcp_gsc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c index 4ae847b628e23..6324f526dcfab 100644 --- a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c +++ b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c @@ -35,11 +35,19 @@ bool intel_hdcp_gsc_check_status(struct drm_device *drm) struct xe_device *xe = to_xe_device(drm); struct xe_tile *tile = xe_device_get_root_tile(xe); struct xe_gt *gt = tile->media_gt; - struct xe_gsc *gsc = >->uc.gsc; + struct xe_gsc *gsc; bool ret = true; unsigned int fw_ref; - if (!gsc || !xe_uc_fw_is_enabled(&gsc->fw)) { + if (!gt) { + drm_dbg_kms(&xe->drm, + "not checking GSC status for HDCP2.x: media GT not present or disabled\n"); + return false; + } + + gsc = >->uc.gsc; + + if (!xe_uc_fw_is_enabled(&gsc->fw)) { drm_dbg_kms(&xe->drm, "GSC Components not ready for HDCP2.x\n"); return false; From b9a4184271b9c10144b3490a18f59a756a73542c Mon Sep 17 00:00:00 2001 From: Guanghui Feng Date: Thu, 19 Mar 2026 15:37:54 +0800 Subject: [PATCH 1141/1518] iommu/amd: Fix illegal cap/mmio access in IOMMU debugfs [ Upstream commit 0e59645683b7b6fa20eceb21a6f420e4f7412943 ] In the current AMD IOMMU debugfs, when multiple processes simultaneously access the IOMMU mmio/cap registers using the IOMMU debugfs, illegal access issues can occur in the following execution flow: 1. CPU1: Sets a valid access address using iommu_mmio/capability_write, and verifies the access address's validity in iommu_mmio/capability_show 2. CPU2: Sets an invalid address using iommu_mmio/capability_write 3. CPU1: accesses the IOMMU mmio/cap registers based on the invalid address, resulting in an illegal access. This patch modifies the execution process to first verify the address's validity and then access it based on the same address, ensuring correctness and robustness. Signed-off-by: Guanghui Feng Signed-off-by: Joerg Roedel Stable-dep-of: 8dfd3d8d7443 ("iommu/amd: Remove latent out-of-bounds access in IOMMU debugfs") Signed-off-by: Sasha Levin --- drivers/iommu/amd/debugfs.c | 42 +++++++++++++++++-------------------- 1 file changed, 19 insertions(+), 23 deletions(-) diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c index 20b04996441d6..0584ca2f859d9 100644 --- a/drivers/iommu/amd/debugfs.c +++ b/drivers/iommu/amd/debugfs.c @@ -26,22 +26,19 @@ static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf, { struct seq_file *m = filp->private_data; struct amd_iommu *iommu = m->private; - int ret; - - iommu->dbg_mmio_offset = -1; + int ret, dbg_mmio_offset = iommu->dbg_mmio_offset = -1; if (cnt > OFS_IN_SZ) return -EINVAL; - ret = kstrtou32_from_user(ubuf, cnt, 0, &iommu->dbg_mmio_offset); + ret = kstrtou32_from_user(ubuf, cnt, 0, &dbg_mmio_offset); if (ret) return ret; - if (iommu->dbg_mmio_offset > iommu->mmio_phys_end - sizeof(u64)) { - iommu->dbg_mmio_offset = -1; - return -EINVAL; - } + if (dbg_mmio_offset > iommu->mmio_phys_end - sizeof(u64)) + return -EINVAL; + iommu->dbg_mmio_offset = dbg_mmio_offset; return cnt; } @@ -49,14 +46,16 @@ static int iommu_mmio_show(struct seq_file *m, void *unused) { struct amd_iommu *iommu = m->private; u64 value; + int dbg_mmio_offset = iommu->dbg_mmio_offset; - if (iommu->dbg_mmio_offset < 0) { + if (dbg_mmio_offset < 0 || dbg_mmio_offset > + iommu->mmio_phys_end - sizeof(u64)) { seq_puts(m, "Please provide mmio register's offset\n"); return 0; } - value = readq(iommu->mmio_base + iommu->dbg_mmio_offset); - seq_printf(m, "Offset:0x%x Value:0x%016llx\n", iommu->dbg_mmio_offset, value); + value = readq(iommu->mmio_base + dbg_mmio_offset); + seq_printf(m, "Offset:0x%x Value:0x%016llx\n", dbg_mmio_offset, value); return 0; } @@ -67,23 +66,20 @@ static ssize_t iommu_capability_write(struct file *filp, const char __user *ubuf { struct seq_file *m = filp->private_data; struct amd_iommu *iommu = m->private; - int ret; - - iommu->dbg_cap_offset = -1; + int ret, dbg_cap_offset = iommu->dbg_cap_offset = -1; if (cnt > OFS_IN_SZ) return -EINVAL; - ret = kstrtou32_from_user(ubuf, cnt, 0, &iommu->dbg_cap_offset); + ret = kstrtou32_from_user(ubuf, cnt, 0, &dbg_cap_offset); if (ret) return ret; /* Capability register at offset 0x14 is the last IOMMU capability register. */ - if (iommu->dbg_cap_offset > 0x14) { - iommu->dbg_cap_offset = -1; + if (dbg_cap_offset > 0x14) return -EINVAL; - } + iommu->dbg_cap_offset = dbg_cap_offset; return cnt; } @@ -91,21 +87,21 @@ static int iommu_capability_show(struct seq_file *m, void *unused) { struct amd_iommu *iommu = m->private; u32 value; - int err; + int err, dbg_cap_offset = iommu->dbg_cap_offset; - if (iommu->dbg_cap_offset < 0) { + if (dbg_cap_offset < 0 || dbg_cap_offset > 0x14) { seq_puts(m, "Please provide capability register's offset in the range [0x00 - 0x14]\n"); return 0; } - err = pci_read_config_dword(iommu->dev, iommu->cap_ptr + iommu->dbg_cap_offset, &value); + err = pci_read_config_dword(iommu->dev, iommu->cap_ptr + dbg_cap_offset, &value); if (err) { seq_printf(m, "Not able to read capability register at 0x%x\n", - iommu->dbg_cap_offset); + dbg_cap_offset); return 0; } - seq_printf(m, "Offset:0x%x Value:0x%08x\n", iommu->dbg_cap_offset, value); + seq_printf(m, "Offset:0x%x Value:0x%08x\n", dbg_cap_offset, value); return 0; } From 488d2c76bd9f78433a70690d1054bfae3d39a407 Mon Sep 17 00:00:00 2001 From: Eder Zulian Date: Fri, 10 Apr 2026 14:55:50 +0200 Subject: [PATCH 1142/1518] iommu/amd: Remove latent out-of-bounds access in IOMMU debugfs [ Upstream commit 8dfd3d8d74435344ee8dc9237596959c8b2a6cbe ] In iommu_mmio_write() and iommu_capability_write(), the variables dbg_mmio_offset and dbg_cap_offset are declared as int. However, they are populated using kstrtou32_from_user(). If a user provides a sufficiently large value, it can become a negative integer. Prior to this patch, the AMD IOMMU debugfs implementation was already protected by different mechanisms. 1. #define OFS_IN_SZ 8 ensures the user string <= 8 bytes, so e.g. 0xffffffff isn't a valid input. if (cnt > OFS_IN_SZ) return -EINVAL; 2. Implicit type promotion in iommu_mmio_write(), dbg_mmio_offset is int and iommu->mmio_phys_end is u64 if (dbg_mmio_offset > iommu->mmio_phys_end - sizeof(u64)) return -EINVAL; 3. The show handlers would currently catch the negative number and refuse to perform the read. Replace kstrtou32_from_user() with kstrtos32_from_user() to parse the input, and check for negative values to explicitly prevent out-of-bounds memory accesses directly in iommu_mmio_write() and iommu_capability_write(). Signed-off-by: Eder Zulian Fixes: 7a4ee419e8c1 ("iommu/amd: Add debugfs support to dump IOMMU MMIO registers") Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd/debugfs.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c index 0584ca2f859d9..3909a1fb218e9 100644 --- a/drivers/iommu/amd/debugfs.c +++ b/drivers/iommu/amd/debugfs.c @@ -31,11 +31,12 @@ static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf, if (cnt > OFS_IN_SZ) return -EINVAL; - ret = kstrtou32_from_user(ubuf, cnt, 0, &dbg_mmio_offset); + ret = kstrtos32_from_user(ubuf, cnt, 0, &dbg_mmio_offset); if (ret) return ret; - if (dbg_mmio_offset > iommu->mmio_phys_end - sizeof(u64)) + if (dbg_mmio_offset < 0 || dbg_mmio_offset > + iommu->mmio_phys_end - sizeof(u64)) return -EINVAL; iommu->dbg_mmio_offset = dbg_mmio_offset; @@ -71,12 +72,12 @@ static ssize_t iommu_capability_write(struct file *filp, const char __user *ubuf if (cnt > OFS_IN_SZ) return -EINVAL; - ret = kstrtou32_from_user(ubuf, cnt, 0, &dbg_cap_offset); + ret = kstrtos32_from_user(ubuf, cnt, 0, &dbg_cap_offset); if (ret) return ret; /* Capability register at offset 0x14 is the last IOMMU capability register. */ - if (dbg_cap_offset > 0x14) + if (dbg_cap_offset < 0 || dbg_cap_offset > 0x14) return -EINVAL; iommu->dbg_cap_offset = dbg_cap_offset; From da3d241c5b925f17a9d8051d7a9e0d454d8e01f6 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Mon, 16 Feb 2026 14:48:30 +0000 Subject: [PATCH 1143/1518] fuse: fix uninit-value in fuse_dentry_revalidate() commit 5a6baf204610589f8a5b5a1cd69d1fe661d9d3cd upstream. fuse_dentry_revalidate() may be called with a dentry that didn't had ->d_time initialised. The issue was found with KMSAN, where lookup_open() calls __d_alloc(), followed by d_revalidate(), as shown below: ===================================================== BUG: KMSAN: uninit-value in fuse_dentry_revalidate+0x150/0x13d0 fs/fuse/dir.c:394 fuse_dentry_revalidate+0x150/0x13d0 fs/fuse/dir.c:394 d_revalidate fs/namei.c:1030 [inline] lookup_open fs/namei.c:4405 [inline] open_last_lookups fs/namei.c:4583 [inline] path_openat+0x1614/0x64c0 fs/namei.c:4827 do_file_open+0x2aa/0x680 fs/namei.c:4859 [...] Uninit was created at: slab_post_alloc_hook mm/slub.c:4466 [inline] slab_alloc_node mm/slub.c:4788 [inline] kmem_cache_alloc_lru_noprof+0x382/0x1280 mm/slub.c:4807 __d_alloc+0x55/0xa00 fs/dcache.c:1740 d_alloc_parallel+0x99/0x2740 fs/dcache.c:2604 lookup_open fs/namei.c:4398 [inline] open_last_lookups fs/namei.c:4583 [inline] path_openat+0x135f/0x64c0 fs/namei.c:4827 do_file_open+0x2aa/0x680 fs/namei.c:4859 [...] ===================================================== Reported-by: syzbot+fdebb2dc960aa56c600a@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/69917e0d.050a0220.340abe.02e2.GAE@google.com Fixes: 2396356a945b ("fuse: add more control over cache invalidation behaviour") Signed-off-by: Luis Henriques Signed-off-by: Miklos Szeredi Signed-off-by: Sasha Levin --- fs/fuse/dir.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index ecaec0fea3a13..1bc6982b5d6aa 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -283,21 +283,33 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name, goto out; } -#if BITS_PER_LONG < 64 static int fuse_dentry_init(struct dentry *dentry) { + int ret = 0; + + /* + * Initialising d_time (epoch) to '0' ensures the dentry is invalid + * if compared to fc->epoch, which is initialized to '1'. + */ + dentry->d_time = 0; + +#if BITS_PER_LONG < 64 dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry), GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); - return dentry->d_fsdata ? 0 : -ENOMEM; + ret = dentry->d_fsdata ? 0 : -ENOMEM; +#endif + + return ret; } static void fuse_dentry_release(struct dentry *dentry) { +#if BITS_PER_LONG < 64 union fuse_dentry *fd = dentry->d_fsdata; kfree_rcu(fd, rcu); -} #endif +} static int fuse_dentry_delete(const struct dentry *dentry) { @@ -331,10 +343,8 @@ static struct vfsmount *fuse_dentry_automount(struct path *path) const struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, .d_delete = fuse_dentry_delete, -#if BITS_PER_LONG < 64 .d_init = fuse_dentry_init, .d_release = fuse_dentry_release, -#endif .d_automount = fuse_dentry_automount, }; From dc184ac2f0ba77ae19725ee06ad3ab36bb9d1f61 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 19 Feb 2026 16:16:17 -0800 Subject: [PATCH 1144/1518] cxl/mbox: validate payload size before accessing contents in cxl_payload_from_user_allowed() [ Upstream commit 60b5d1f68338aff2c5af0113f04aefa7169c50c2 ] cxl_payload_from_user_allowed() casts and dereferences the input payload without first verifying its size. When a raw mailbox command is sent with an undersized payload (ie: 1 byte for CXL_MBOX_OP_CLEAR_LOG, which expects a 16-byte UUID), uuid_equal() reads past the allocated buffer, triggering a KASAN splat: BUG: KASAN: slab-out-of-bounds in memcmp+0x176/0x1d0 lib/string.c:683 Read of size 8 at addr ffff88810130f5c0 by task syz.1.62/2258 CPU: 2 UID: 0 PID: 2258 Comm: syz.1.62 Not tainted 6.19.0-dirty #3 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xab/0xe0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xce/0x650 mm/kasan/report.c:482 kasan_report+0xce/0x100 mm/kasan/report.c:595 memcmp+0x176/0x1d0 lib/string.c:683 uuid_equal include/linux/uuid.h:73 [inline] cxl_payload_from_user_allowed drivers/cxl/core/mbox.c:345 [inline] cxl_mbox_cmd_ctor drivers/cxl/core/mbox.c:368 [inline] cxl_validate_cmd_from_user drivers/cxl/core/mbox.c:522 [inline] cxl_send_cmd+0x9c0/0xb50 drivers/cxl/core/mbox.c:643 __cxl_memdev_ioctl drivers/cxl/core/memdev.c:698 [inline] cxl_memdev_ioctl+0x14f/0x190 drivers/cxl/core/memdev.c:713 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:583 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xa8/0x330 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fdaf331ba79 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fdaf1d77038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fdaf3585fa0 RCX: 00007fdaf331ba79 RDX: 00002000000001c0 RSI: 00000000c030ce02 RDI: 0000000000000003 RBP: 00007fdaf33749df R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fdaf3586038 R14: 00007fdaf3585fa0 R15: 00007ffced2af768 Add 'in_size' parameter to cxl_payload_from_user_allowed() and validate the payload is large enough. Fixes: 6179045ccc0c ("cxl/mbox: Block immediate mode in SET_PARTITION_INFO command") Fixes: 206f9fa9d555 ("cxl/mbox: Add Clear Log mailbox command") Signed-off-by: Davidlohr Bueso Reviewed-by: Alison Schofield Reviewed-by: Dave Jiang Link: https://patch.msgid.link/20260220001618.963490-2-dave@stgolabs.net Signed-off-by: Dave Jiang Signed-off-by: Sasha Levin --- drivers/cxl/core/mbox.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index fa6dd0c94656f..e7a6452bf5445 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -311,6 +311,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) * cxl_payload_from_user_allowed() - Check contents of in_payload. * @opcode: The mailbox command opcode. * @payload_in: Pointer to the input payload passed in from user space. + * @in_size: Size of @payload_in in bytes. * * Return: * * true - payload_in passes check for @opcode. @@ -325,12 +326,15 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) * * The specific checks are determined by the opcode. */ -static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in) +static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in, + size_t in_size) { switch (opcode) { case CXL_MBOX_OP_SET_PARTITION_INFO: { struct cxl_mbox_set_partition_info *pi = payload_in; + if (in_size < sizeof(*pi)) + return false; if (pi->flags & CXL_SET_PARTITION_IMMEDIATE_FLAG) return false; break; @@ -338,6 +342,8 @@ static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in) case CXL_MBOX_OP_CLEAR_LOG: { const uuid_t *uuid = (uuid_t *)payload_in; + if (in_size < sizeof(uuid_t)) + return false; /* * Restrict the ‘Clear log’ action to only apply to * Vendor debug logs. @@ -365,7 +371,8 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox_cmd, if (IS_ERR(mbox_cmd->payload_in)) return PTR_ERR(mbox_cmd->payload_in); - if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in)) { + if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in, + in_size)) { dev_dbg(cxl_mbox->host, "%s: input payload not allowed\n", cxl_mem_opcode_to_name(opcode)); kvfree(mbox_cmd->payload_in); From 3f0543bdf446a62b7293c445377a1e5741817dfd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Oct 2024 13:43:43 +0100 Subject: [PATCH 1145/1518] sched: Employ sched_change guards [ Upstream commit e9139f765ac7048cadc9981e962acdf8b08eabf3 ] As proposed a long while ago -- and half done by scx -- wrap the scheduler's 'change' pattern in a guard helper. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Juri Lelli Acked-by: Tejun Heo Acked-by: Vincent Guittot Stable-dep-of: d658686a1331 ("sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting") Signed-off-by: Sasha Levin --- include/linux/cleanup.h | 5 ++ kernel/sched/core.c | 159 +++++++++++++++------------------------- kernel/sched/ext.c | 39 +++++----- kernel/sched/sched.h | 33 ++++++--- kernel/sched/syscalls.c | 65 ++++++---------- 5 files changed, 131 insertions(+), 170 deletions(-) diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 19c7e475d3a4d..a1194e44b5276 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -341,6 +341,11 @@ _label: \ #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond +#define DEFINE_CLASS_IS_UNCONDITIONAL(_name) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ + static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ + { return (void *)1; } + #define __GUARD_IS_ERR(_ptr) \ ({ \ unsigned long _rc = (__force unsigned long)(_ptr); \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0d93f60fed20a..46fc94f2338e8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7332,7 +7332,7 @@ void rt_mutex_post_schedule(void) */ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) { - int prio, oldprio, queued, running, queue_flag = + int prio, oldprio, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; const struct sched_class *prev_class, *next_class; struct rq_flags rf; @@ -7397,52 +7397,42 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (prev_class != next_class && p->se.sched_delayed) dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK); - queued = task_on_rq_queued(p); - running = task_current_donor(rq, p); - if (queued) - dequeue_task(rq, p, queue_flag); - if (running) - put_prev_task(rq, p); - - /* - * Boosting condition are: - * 1. -rt task is running and holds mutex A - * --> -dl task blocks on mutex A - * - * 2. -dl task is running and holds mutex A - * --> -dl task blocks on mutex A and could preempt the - * running task - */ - if (dl_prio(prio)) { - if (!dl_prio(p->normal_prio) || - (pi_task && dl_prio(pi_task->prio) && - dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.pi_se = pi_task->dl.pi_se; - queue_flag |= ENQUEUE_REPLENISH; + scoped_guard (sched_change, p, queue_flag) { + /* + * Boosting condition are: + * 1. -rt task is running and holds mutex A + * --> -dl task blocks on mutex A + * + * 2. -dl task is running and holds mutex A + * --> -dl task blocks on mutex A and could preempt the + * running task + */ + if (dl_prio(prio)) { + if (!dl_prio(p->normal_prio) || + (pi_task && dl_prio(pi_task->prio) && + dl_entity_preempt(&pi_task->dl, &p->dl))) { + p->dl.pi_se = pi_task->dl.pi_se; + scope->flags |= ENQUEUE_REPLENISH; + } else { + p->dl.pi_se = &p->dl; + } + } else if (rt_prio(prio)) { + if (dl_prio(oldprio)) + p->dl.pi_se = &p->dl; + if (oldprio < prio) + scope->flags |= ENQUEUE_HEAD; } else { - p->dl.pi_se = &p->dl; + if (dl_prio(oldprio)) + p->dl.pi_se = &p->dl; + if (rt_prio(oldprio)) + p->rt.timeout = 0; } - } else if (rt_prio(prio)) { - if (dl_prio(oldprio)) - p->dl.pi_se = &p->dl; - if (oldprio < prio) - queue_flag |= ENQUEUE_HEAD; - } else { - if (dl_prio(oldprio)) - p->dl.pi_se = &p->dl; - if (rt_prio(oldprio)) - p->rt.timeout = 0; - } - p->sched_class = next_class; - p->prio = prio; + p->sched_class = next_class; + p->prio = prio; - check_class_changing(rq, p, prev_class); - - if (queued) - enqueue_task(rq, p, queue_flag); - if (running) - set_next_task(rq, p); + check_class_changing(rq, p, prev_class); + } check_class_changed(rq, p, prev_class, oldprio); out_unlock: @@ -8090,26 +8080,9 @@ int migrate_task_to(struct task_struct *p, int target_cpu) */ void sched_setnuma(struct task_struct *p, int nid) { - bool queued, running; - struct rq_flags rf; - struct rq *rq; - - rq = task_rq_lock(p, &rf); - queued = task_on_rq_queued(p); - running = task_current_donor(rq, p); - - if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); - if (running) - put_prev_task(rq, p); - - p->numa_preferred_nid = nid; - - if (queued) - enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - if (running) - set_next_task(rq, p); - task_rq_unlock(rq, p, &rf); + guard(task_rq_lock)(p); + scoped_guard (sched_change, p, DEQUEUE_SAVE) + p->numa_preferred_nid = nid; } #endif /* CONFIG_NUMA_BALANCING */ @@ -9215,8 +9188,9 @@ static void sched_change_group(struct task_struct *tsk) */ void sched_move_task(struct task_struct *tsk, bool for_autogroup) { - int queued, running, queue_flags = + unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; + bool resched = false; struct rq *rq; CLASS(task_rq_lock, rq_guard)(tsk); @@ -9224,29 +9198,16 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup) update_rq_clock(rq); - running = task_current_donor(rq, tsk); - queued = task_on_rq_queued(tsk); - - if (queued) - dequeue_task(rq, tsk, queue_flags); - if (running) - put_prev_task(rq, tsk); - - sched_change_group(tsk); - if (!for_autogroup) - scx_cgroup_move_task(tsk); + scoped_guard (sched_change, tsk, queue_flags) { + sched_change_group(tsk); + if (!for_autogroup) + scx_cgroup_move_task(tsk); + if (scope->running) + resched = true; + } - if (queued) - enqueue_task(rq, tsk, queue_flags); - if (running) { - set_next_task(rq, tsk); - /* - * After changing group, the running task may have joined a - * throttled one but it's still the running task. Trigger a - * resched to make sure that task can still run. - */ + if (resched) resched_curr(rq); - } } static struct cgroup_subsys_state * @@ -10902,37 +10863,39 @@ void sched_mm_cid_fork(struct task_struct *t) } #endif /* CONFIG_SCHED_MM_CID */ -#ifdef CONFIG_SCHED_CLASS_EXT -void sched_deq_and_put_task(struct task_struct *p, int queue_flags, - struct sched_enq_and_set_ctx *ctx) +static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx); + +struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags) { + struct sched_change_ctx *ctx = this_cpu_ptr(&sched_change_ctx); struct rq *rq = task_rq(p); lockdep_assert_rq_held(rq); - *ctx = (struct sched_enq_and_set_ctx){ + *ctx = (struct sched_change_ctx){ .p = p, - .queue_flags = queue_flags, + .flags = flags, .queued = task_on_rq_queued(p), - .running = task_current(rq, p), + .running = task_current_donor(rq, p), }; - update_rq_clock(rq); if (ctx->queued) - dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK); + dequeue_task(rq, p, flags); if (ctx->running) put_prev_task(rq, p); + + return ctx; } -void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx) +void sched_change_end(struct sched_change_ctx *ctx) { - struct rq *rq = task_rq(ctx->p); + struct task_struct *p = ctx->p; + struct rq *rq = task_rq(p); lockdep_assert_rq_held(rq); if (ctx->queued) - enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK); + enqueue_task(rq, p, ctx->flags | ENQUEUE_NOCLOCK); if (ctx->running) - set_next_task(rq, ctx->p); + set_next_task(rq, p); } -#endif /* CONFIG_SCHED_CLASS_EXT */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 35c0b31924d37..3029e5b8f9a57 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3866,11 +3866,10 @@ static void scx_bypass(bool bypass) */ list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list, scx.runnable_node) { - struct sched_enq_and_set_ctx ctx; - /* cycling deq/enq is enough, see the function comment */ - sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); - sched_enq_and_set_task(&ctx); + scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) { + /* nothing */ ; + } } /* resched to restore ticks and idle state */ @@ -4021,17 +4020,16 @@ static void scx_disable_workfn(struct kthread_work *work) while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; const struct sched_class *new_class = scx_setscheduler_class(p); - struct sched_enq_and_set_ctx ctx; - if (old_class != new_class && p->se.sched_delayed) - dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); + update_rq_clock(task_rq(p)); - sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); - - p->sched_class = new_class; - check_class_changing(task_rq(p), p, old_class); + if (old_class != new_class && p->se.sched_delayed) + dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK); - sched_enq_and_set_task(&ctx); + scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) { + p->sched_class = new_class; + check_class_changing(task_rq(p), p, old_class); + } check_class_changed(task_rq(p), p, old_class, p->prio); scx_exit_task(p); @@ -4845,21 +4843,20 @@ static void scx_enable_workfn(struct kthread_work *work) while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; const struct sched_class *new_class = scx_setscheduler_class(p); - struct sched_enq_and_set_ctx ctx; if (!tryget_task_struct(p)) continue; - if (old_class != new_class && p->se.sched_delayed) - dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); - - sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); + update_rq_clock(task_rq(p)); - p->scx.slice = SCX_SLICE_DFL; - p->sched_class = new_class; - check_class_changing(task_rq(p), p, old_class); + if (old_class != new_class && p->se.sched_delayed) + dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK); - sched_enq_and_set_task(&ctx); + scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) { + p->scx.slice = SCX_SLICE_DFL; + p->sched_class = new_class; + check_class_changing(task_rq(p), p, old_class); + } check_class_changed(task_rq(p), p, old_class, p->prio); put_task_struct(p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f750dea7b7876..668841022dbf2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3891,23 +3891,38 @@ extern void check_class_changed(struct rq *rq, struct task_struct *p, extern struct balance_callback *splice_balance_callbacks(struct rq *rq); extern void balance_callbacks(struct rq *rq, struct balance_callback *head); -#ifdef CONFIG_SCHED_CLASS_EXT /* - * Used by SCX in the enable/disable paths to move tasks between sched_classes - * and establish invariants. + * The 'sched_change' pattern is the safe, easy and slow way of changing a + * task's scheduling properties. It dequeues a task, such that the scheduler + * is fully unaware of it; at which point its properties can be modified; + * after which it is enqueued again. + * + * Typically this must be called while holding task_rq_lock, since most/all + * properties are serialized under those locks. There is currently one + * exception to this rule in sched/ext which only holds rq->lock. + */ + +/* + * This structure is a temporary, used to preserve/convey the queueing state + * of the task between sched_change_begin() and sched_change_end(). Ensuring + * the task's queueing state is idempotent across the operation. */ -struct sched_enq_and_set_ctx { +struct sched_change_ctx { struct task_struct *p; - int queue_flags; + int flags; bool queued; bool running; }; -void sched_deq_and_put_task(struct task_struct *p, int queue_flags, - struct sched_enq_and_set_ctx *ctx); -void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx); +struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags); +void sched_change_end(struct sched_change_ctx *ctx); -#endif /* CONFIG_SCHED_CLASS_EXT */ +DEFINE_CLASS(sched_change, struct sched_change_ctx *, + sched_change_end(_T), + sched_change_begin(p, flags), + struct task_struct *p, unsigned int flags) + +DEFINE_CLASS_IS_UNCONDITIONAL(sched_change) #include "ext.h" diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 6805a63d47af7..d2bcedc10152f 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -64,7 +64,6 @@ static int effective_prio(struct task_struct *p) void set_user_nice(struct task_struct *p, long nice) { - bool queued, running; struct rq *rq; int old_prio; @@ -90,22 +89,12 @@ void set_user_nice(struct task_struct *p, long nice) return; } - queued = task_on_rq_queued(p); - running = task_current_donor(rq, p); - if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK); - if (running) - put_prev_task(rq, p); - - p->static_prio = NICE_TO_PRIO(nice); - set_load_weight(p, true); - old_prio = p->prio; - p->prio = effective_prio(p); - - if (queued) - enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - if (running) - set_next_task(rq, p); + scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK) { + p->static_prio = NICE_TO_PRIO(nice); + set_load_weight(p, true); + old_prio = p->prio; + p->prio = effective_prio(p); + } /* * If the task increased its priority or is running and @@ -515,7 +504,7 @@ int __sched_setscheduler(struct task_struct *p, bool user, bool pi) { int oldpolicy = -1, policy = attr->sched_policy; - int retval, oldprio, newprio, queued, running; + int retval, oldprio, newprio; const struct sched_class *prev_class, *next_class; struct balance_callback *head; struct rq_flags rf; @@ -698,33 +687,25 @@ int __sched_setscheduler(struct task_struct *p, if (prev_class != next_class && p->se.sched_delayed) dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK); - queued = task_on_rq_queued(p); - running = task_current_donor(rq, p); - if (queued) - dequeue_task(rq, p, queue_flags); - if (running) - put_prev_task(rq, p); - - if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { - __setscheduler_params(p, attr); - p->sched_class = next_class; - p->prio = newprio; - } - __setscheduler_uclamp(p, attr); - check_class_changing(rq, p, prev_class); + scoped_guard (sched_change, p, queue_flags) { - if (queued) { - /* - * We enqueue to tail when the priority of a task is - * increased (user space view). - */ - if (oldprio < p->prio) - queue_flags |= ENQUEUE_HEAD; + if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { + __setscheduler_params(p, attr); + p->sched_class = next_class; + p->prio = newprio; + } + __setscheduler_uclamp(p, attr); + check_class_changing(rq, p, prev_class); - enqueue_task(rq, p, queue_flags); + if (scope->queued) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + if (oldprio < p->prio) + scope->flags |= ENQUEUE_HEAD; + } } - if (running) - set_next_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); From 0638bf16b7a73a2fe63624bd0d16d9fd904805c3 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Mon, 2 Mar 2026 16:45:40 +0100 Subject: [PATCH 1146/1518] sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting [ Upstream commit d658686a1331db3bb108ca079d76deb3208ed949 ] Running stress-ng --schedpolicy 0 on an RT kernel on a big machine might lead to the following WARNINGs (edited). sched: DL de-boosted task PID 22725: REPLENISH flag missing WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8 ... (running_bw underflow) Call trace: dequeue_task_dl+0x15c/0x1f8 (P) dequeue_task+0x80/0x168 deactivate_task+0x24/0x50 push_dl_task+0x264/0x2e0 dl_task_timer+0x1b0/0x228 __hrtimer_run_queues+0x188/0x378 hrtimer_interrupt+0xfc/0x260 ... The problem is that when a SCHED_DEADLINE task (lock holder) is changed to a lower priority class via sched_setscheduler(), it may fail to properly inherit the parameters of potential DEADLINE donors if it didn't already inherit them in the past (shorter deadline than donor's at that time). This might lead to bandwidth accounting corruption, as enqueue_task_dl() won't recognize the lock holder as boosted. The scenario occurs when: 1. A DEADLINE task (donor) blocks on a PI mutex held by another DEADLINE task (holder), but the holder doesn't inherit parameters (e.g., it already has a shorter deadline) 2. sched_setscheduler() changes the holder from DEADLINE to a lower class while still holding the mutex 3. The holder should now inherit DEADLINE parameters from the donor and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen Fix the issue by introducing __setscheduler_dl_pi(), which detects when a DEADLINE (proper or boosted) task gets setscheduled to a lower priority class. In case, the function makes the task inherit DEADLINE parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to ensure proper bandwidth accounting during the next enqueue operation. Fixes: 2279f540ea7d ("sched/deadline: Fix priority inheritance with multiple scheduling classes") Reported-by: Bruno Goncalves Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260302-upstream-fix-deadline-piboost-b4-v3-1-6ba32184a9e0@redhat.com Signed-off-by: Sasha Levin --- kernel/sched/syscalls.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index d2bcedc10152f..77b663a5dfb2b 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -322,6 +322,35 @@ static bool check_same_owner(struct task_struct *p) uid_eq(cred->euid, pcred->uid)); } +#ifdef CONFIG_RT_MUTEXES +static inline void __setscheduler_dl_pi(int newprio, int policy, + struct task_struct *p, + struct sched_change_ctx *scope) +{ + /* + * In case a DEADLINE task (either proper or boosted) gets + * setscheduled to a lower priority class, check if it neeeds to + * inherit parameters from a potential pi_task. In that case make + * sure replenishment happens with the next enqueue. + */ + + if (dl_prio(newprio) && !dl_policy(policy)) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + + if (pi_task) { + p->dl.pi_se = pi_task->dl.pi_se; + scope->flags |= ENQUEUE_REPLENISH; + } + } +} +#else /* !CONFIG_RT_MUTEXES */ +static inline void __setscheduler_dl_pi(int newprio, int policy, + struct task_struct *p, + struct sched_change_ctx *scope) +{ +} +#endif /* !CONFIG_RT_MUTEXES */ + #ifdef CONFIG_UCLAMP_TASK static int uclamp_validate(struct task_struct *p, @@ -693,6 +722,7 @@ int __sched_setscheduler(struct task_struct *p, __setscheduler_params(p, attr); p->sched_class = next_class; p->prio = newprio; + __setscheduler_dl_pi(newprio, policy, p, scope); } __setscheduler_uclamp(p, attr); check_class_changing(rq, p, prev_class); From e8ec80430bfa520e7352155d6ac632e527cba7aa Mon Sep 17 00:00:00 2001 From: Xiang Mei Date: Fri, 27 Mar 2026 23:30:00 -0700 Subject: [PATCH 1147/1518] bridge: mrp: reject zero test interval to avoid OOM panic [ Upstream commit fa6e24963342de4370e3a3c9af41e38277b74cf3 ] br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied interval value from netlink without validation. When interval is 0, usecs_to_jiffies(0) yields 0, causing the delayed work (br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule itself with zero delay. This creates a tight loop on system_percpu_wq that allocates and transmits MRP test frames at maximum rate, exhausting all system memory and causing a kernel panic via OOM deadlock. The same zero-interval issue applies to br_mrp_start_in_test_parse() for interconnect test frames. Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both IFLA_BRIDGE_MRP_START_TEST_INTERVAL and IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the netlink attribute parsing layer before the value ever reaches the workqueue scheduling code. This is consistent with how other bridge subsystems (br_fdb, br_mst) enforce range constraints on netlink attributes. Fixes: 20f6a05ef635 ("bridge: mrp: Rework the MRP netlink interface") Fixes: 7ab1748e4ce6 ("bridge: mrp: Extend MRP netlink interface for configuring MRP interconnect") Reported-by: Weiming Shi Signed-off-by: Xiang Mei Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260328063000.1845376-1-xmei5@asu.edu Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/bridge/br_mrp_netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c index ce6f63c77cc0a..86f0e75d6e345 100644 --- a/net/bridge/br_mrp_netlink.c +++ b/net/bridge/br_mrp_netlink.c @@ -196,7 +196,7 @@ static const struct nla_policy br_mrp_start_test_policy[IFLA_BRIDGE_MRP_START_TEST_MAX + 1] = { [IFLA_BRIDGE_MRP_START_TEST_UNSPEC] = { .type = NLA_REJECT }, [IFLA_BRIDGE_MRP_START_TEST_RING_ID] = { .type = NLA_U32 }, - [IFLA_BRIDGE_MRP_START_TEST_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_TEST_INTERVAL] = NLA_POLICY_MIN(NLA_U32, 1), [IFLA_BRIDGE_MRP_START_TEST_MAX_MISS] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_TEST_PERIOD] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_TEST_MONITOR] = { .type = NLA_U32 }, @@ -316,7 +316,7 @@ static const struct nla_policy br_mrp_start_in_test_policy[IFLA_BRIDGE_MRP_START_IN_TEST_MAX + 1] = { [IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC] = { .type = NLA_REJECT }, [IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID] = { .type = NLA_U32 }, - [IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL] = NLA_POLICY_MIN(NLA_U32, 1), [IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS] = { .type = NLA_U32 }, [IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD] = { .type = NLA_U32 }, }; From aae4a47073b12c23eb1d2c5401bda442fbe27bd1 Mon Sep 17 00:00:00 2001 From: Vladimir Yakovlev Date: Tue, 3 Mar 2026 01:20:17 +0300 Subject: [PATCH 1148/1518] spi: spi-dw-dma: fix print error log when wait finish transaction [ Upstream commit 3b46d61890632c8f8b117147b6923bff4b42ccb7 ] If an error occurs, the device may not have a current message. In this case, the system will crash. In this case, it's better to use dev from the struct ctlr (struct spi_controller*). Signed-off-by: Vladimir Yakovlev Link: https://patch.msgid.link/20260302222017.992228-2-vovchkir@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-dw-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c index b5bed02b7e500..31063f9270924 100644 --- a/drivers/spi/spi-dw-dma.c +++ b/drivers/spi/spi-dw-dma.c @@ -271,7 +271,7 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed) msecs_to_jiffies(ms)); if (ms == 0) { - dev_err(&dws->host->cur_msg->spi->dev, + dev_err(&dws->host->dev, "DMA transaction timed out\n"); return -ETIMEDOUT; } From 5da69a65b282d2276de22e5194ba0f88c836170c Mon Sep 17 00:00:00 2001 From: DaeMyung Kang Date: Tue, 28 Apr 2026 23:08:56 +0900 Subject: [PATCH 1149/1518] ksmbd: close durable scavenger races against m_fp_list lookups [ Upstream commit bf736184d063da1a552ffeff0481813599a182cc ] ksmbd_durable_scavenger() has two related races against any walker that iterates f_ci->m_fp_list, including ksmbd_lookup_fd_inode() (used by ksmbd_vfs_rename) and the share-mode checks in fs/smb/server/smb_common.c. (1) fp->node list-head reuse. Durable-preserved handles can remain linked on f_ci->m_fp_list after session teardown so share-mode checks still see them while the handle is reconnectable. The scavenger collected expired handles by adding fp->node to a local scavenger_list after removing them from the global durable idr. Because fp->node is the same list_head used by m_fp_list, list_add(&fp->node, &scavenger_list) overwrites the m_fp_list links and corrupts both lists. CONFIG_DEBUG_LIST can report this on the share-mode walk path. (2) Refcount race against m_fp_list walkers. The scavenger qualifies an expired durable handle with atomic_read(&fp->refcount) > 1 and fp->conn under global_ft.lock, removes fp from global_ft, then drops global_ft.lock before unlinking fp from m_fp_list and freeing it. During that gap fp is still linked on m_fp_list with f_state == FP_INITED. ksmbd_lookup_fd_inode() under m_lock read calls ksmbd_fp_get() (atomic_inc_not_zero on refcount that is still 1) and takes a live reference; the scavenger then unlinks and frees fp while the holder owns a reference, leading to UAF on the holder's subsequent ksmbd_fd_put() and on any field reads performed by a concurrent share-mode walker that iterates m_fp_list without taking ksmbd_fp_get() (smb_check_perm_dleases-like paths). Fix both: * Stop reusing fp->node as a scavenger-private list node. Remove one expired handle from global_ft under global_ft.lock, take an explicit transient reference, drop the lock, unlink fp->node from m_fp_list under f_ci->m_lock, then drop both the durable lifetime and transient references with atomic_sub_and_test(2, &fp->refcount). If the scavenger is the last putter the close runs there; otherwise an in-flight holder that already raced through the m_fp_list lookup owns the final close via its ksmbd_fd_put() path. The one-at-a-time disposal can rescan the durable idr when multiple handles expire in the same pass, but durable scavenging is a background expiration path and the final full scan recomputes min_timeout before the next wait. * Clear fp->persistent_id inside __ksmbd_remove_durable_fd() right after idr_remove(), so a delayed final close from a holder that snatched fp does not re-issue idr_remove() on a persistent id that idr_alloc_cyclic() in ksmbd_open_durable_fd() may have already handed out to a brand-new durable handle. * Bypass the per-conn open_files_count decrement in __put_fd_final() when fp is detached from any session table (fp->conn cleared by session_fd_check() at durable preserve -- paired with the volatile_id clear at unpublish, so checking fp->conn alone is sufficient). The walker that owns the final close runs from an unrelated work->conn whose stats.open_files_count never tracked this durable fp; without this guard the holder would underflow that unrelated counter. The two races are folded into one patch because patch (1) alone cleans up the corrupted list but leaves a deterministic UAF window for m_fp_list walkers that the transient-reference and persistent_id discipline in (2) close; bisecting onto an intermediate state would land on a UAF that pre-patch chaos merely made less reproducible. Validation: * CONFIG_DEBUG_LIST coverage for the list_head reuse path. * KASAN-enabled direct SMB2 durable-handle coverage that exercised ksmbd_durable_scavenger() and non-NULL ksmbd_lookup_fd_inode() returns while durable handles expired under concurrent rename lookups, with no KASAN, UAF, list-corruption, ODEBUG, or WARNING reports. * checkpatch --strict * make -j$(nproc) M=fs/smb/server Fixes: d484d621d40f ("ksmbd: add durable scavenger timer") Signed-off-by: DaeMyung Kang Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/vfs_cache.c | 104 ++++++++++++++++++++++++++++---------- 1 file changed, 77 insertions(+), 27 deletions(-) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index d29cc1d01bd2c..a8fed467e9b69 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -325,6 +325,14 @@ static void __ksmbd_remove_durable_fd(struct ksmbd_file *fp) return; idr_remove(global_ft.idr, fp->persistent_id); + /* + * Clear persistent_id so a later __ksmbd_close_fd() that runs from a + * delayed putter (e.g. when a concurrent ksmbd_lookup_fd_inode() + * walker held the final reference) does not re-issue idr_remove() on + * an id that idr_alloc_cyclic() may have already handed out to a new + * durable handle. + */ + fp->persistent_id = KSMBD_NO_FID; } static void ksmbd_remove_durable_fd(struct ksmbd_file *fp) @@ -417,6 +425,20 @@ static struct ksmbd_file *__ksmbd_lookup_fd(struct ksmbd_file_table *ft, static void __put_fd_final(struct ksmbd_work *work, struct ksmbd_file *fp) { + /* + * Detached durable fp -- session_fd_check() cleared fp->conn at + * preserve, so this fp is no longer tracked by any conn's + * stats.open_files_count. This happens when + * ksmbd_scavenger_dispose_dh() hands the final close off to an + * m_fp_list walker (e.g. ksmbd_lookup_fd_inode()) whose work->conn + * is unrelated to the conn that originally opened the handle; close + * via the NULL-ft path so we do not underflow that unrelated + * counter. + */ + if (!fp->conn) { + __ksmbd_close_fd(NULL, fp); + return; + } __ksmbd_close_fd(&work->sess->file_table, fp); atomic_dec(&work->conn->stats.open_files_count); } @@ -788,24 +810,37 @@ static bool ksmbd_durable_scavenger_alive(void) return true; } -static void ksmbd_scavenger_dispose_dh(struct list_head *head) +static void ksmbd_scavenger_dispose_dh(struct ksmbd_file *fp) { - while (!list_empty(head)) { - struct ksmbd_file *fp; + /* + * Durable-preserved fp can remain linked on f_ci->m_fp_list for + * share-mode checks. Unlink it before final close; fp->node is not + * available as a scavenger-private list node because re-adding it to + * another list corrupts m_fp_list. + */ + down_write(&fp->f_ci->m_lock); + list_del_init(&fp->node); + up_write(&fp->f_ci->m_lock); - fp = list_first_entry(head, struct ksmbd_file, node); - list_del_init(&fp->node); + /* + * Drop both the durable lifetime reference and the transient reference + * taken by the scavenger under global_ft.lock. If a concurrent + * ksmbd_lookup_fd_inode() (or any other m_fp_list walker) snatched fp + * before the unlink above, that holder owns the final close via + * ksmbd_fd_put() -> __ksmbd_close_fd(). Otherwise the scavenger is + * the last putter and finalises fp here. + */ + if (atomic_sub_and_test(2, &fp->refcount)) __ksmbd_close_fd(NULL, fp); - } } static int ksmbd_durable_scavenger(void *dummy) { struct ksmbd_file *fp = NULL; + struct ksmbd_file *expired_fp; unsigned int id; unsigned int min_timeout = 1; bool found_fp_timeout; - LIST_HEAD(scavenger_list); unsigned long remaining_jiffies; __module_get(THIS_MODULE); @@ -815,8 +850,6 @@ static int ksmbd_durable_scavenger(void *dummy) if (try_to_freeze()) continue; - found_fp_timeout = false; - remaining_jiffies = wait_event_timeout(dh_wq, ksmbd_durable_scavenger_alive() == false, __msecs_to_jiffies(min_timeout)); @@ -825,23 +858,39 @@ static int ksmbd_durable_scavenger(void *dummy) else min_timeout = DURABLE_HANDLE_MAX_TIMEOUT; - write_lock(&global_ft.lock); - idr_for_each_entry(global_ft.idr, fp, id) { - if (!fp->durable_timeout) - continue; - - if (atomic_read(&fp->refcount) > 1 || - fp->conn) - continue; - - found_fp_timeout = true; - if (fp->durable_scavenger_timeout <= - jiffies_to_msecs(jiffies)) { - __ksmbd_remove_durable_fd(fp); - list_add(&fp->node, &scavenger_list); - } else { + do { + expired_fp = NULL; + found_fp_timeout = false; + + write_lock(&global_ft.lock); + idr_for_each_entry(global_ft.idr, fp, id) { unsigned long durable_timeout; + if (!fp->durable_timeout) + continue; + + if (atomic_read(&fp->refcount) > 1 || + fp->conn) + continue; + + found_fp_timeout = true; + if (fp->durable_scavenger_timeout <= + jiffies_to_msecs(jiffies)) { + __ksmbd_remove_durable_fd(fp); + /* + * Take a transient reference so fp + * cannot be freed by an in-flight + * ksmbd_lookup_fd_inode() that found + * it through f_ci->m_fp_list while we + * drop global_ft.lock and reach the + * m_fp_list unlink in + * ksmbd_scavenger_dispose_dh(). + */ + atomic_inc(&fp->refcount); + expired_fp = fp; + break; + } + durable_timeout = fp->durable_scavenger_timeout - jiffies_to_msecs(jiffies); @@ -849,10 +898,11 @@ static int ksmbd_durable_scavenger(void *dummy) if (min_timeout > durable_timeout) min_timeout = durable_timeout; } - } - write_unlock(&global_ft.lock); + write_unlock(&global_ft.lock); - ksmbd_scavenger_dispose_dh(&scavenger_list); + if (expired_fp) + ksmbd_scavenger_dispose_dh(expired_fp); + } while (expired_fp); if (found_fp_timeout == false) break; From 91f89c1d83e80417629791fcef6af8140d7d01c8 Mon Sep 17 00:00:00 2001 From: Asim Viladi Oglu Manizada Date: Sat, 16 May 2026 21:15:39 +0000 Subject: [PATCH 1150/1518] smb: client: reject userspace cifs.spnego descriptions commit 3da1fdf4efbc490041eb4f836bf596201203f8f2 upstream. cifs.spnego key descriptions contain authority-bearing fields such as pid, uid, creduid, and upcall_target that cifs.upcall treats as kernel-originating inputs. However, userspace can also create keys of this type through request_key(2) or add_key(2), allowing those fields to be supplied without CIFS origin. Only accept cifs.spnego descriptions while CIFS is using its private spnego_cred to request the key. Fixes: f1d662a7d5e5 ("[CIFS] Add upcall files for cifs to use spnego/kerberos") Assisted-by: avom-custom-harness:gpt-5.5-qwen3.6-mod-mix Reviewed-by: David Howells Signed-off-by: Asim Viladi Oglu Manizada Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/cifs_spnego.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 9891f55bac1e2..60b4147d0eea0 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -40,12 +41,27 @@ cifs_spnego_key_destroy(struct key *key) kfree(key->payload.data[0]); } +static int +cifs_spnego_key_vet_description(const char *description) +{ + /* + * cifs.spnego descriptions are authority-bearing inputs to cifs.upcall. + * They are only valid when produced by CIFS while using the private + * spnego_cred installed below. Do not let userspace create this type + * of key through request_key(2)/add_key(2), since the helper treats + * pid/uid/creduid/upcall_target as kernel-originating fields. + */ + if (current_cred() != spnego_cred) + return -EPERM; + return 0; +} /* * keytype for CIFS spnego keys */ struct key_type cifs_spnego_key_type = { .name = "cifs.spnego", + .vet_description = cifs_spnego_key_vet_description, .instantiate = cifs_spnego_key_instantiate, .destroy = cifs_spnego_key_destroy, .describe = user_describe, From 375d5a17dc8d7668c2479dc4cd329838c58d8e4f Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Fri, 31 Oct 2025 20:33:07 +0200 Subject: [PATCH 1151/1518] dt-bindings: soc: bcm: Add bcm2712 compatible commit 34194cb385033656d347ebe45c241e4739a58125 upstream. Add bcm2712-pm compatible and update the bindings to satisfy it's requirements. The PM hardware block inside bcm2712 lacks the "asb" and "rpivid_asb" register ranges and also does not have clocks, update the bindings accordingly. Signed-off-by: Stanimir Varbanov Reviewed-by: Florian Fainelli Acked-by: Conor Dooley Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- .../bindings/soc/bcm/brcm,bcm2835-pm.yaml | 38 ++++++++++++++++--- 1 file changed, 32 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/soc/bcm/brcm,bcm2835-pm.yaml b/Documentation/devicetree/bindings/soc/bcm/brcm,bcm2835-pm.yaml index e28ef198a801c..039c8e4a4c51b 100644 --- a/Documentation/devicetree/bindings/soc/bcm/brcm,bcm2835-pm.yaml +++ b/Documentation/devicetree/bindings/soc/bcm/brcm,bcm2835-pm.yaml @@ -13,23 +13,21 @@ description: | maintainers: - Nicolas Saenz Julienne -allOf: - - $ref: /schemas/watchdog/watchdog.yaml# - properties: compatible: items: - enum: - brcm,bcm2835-pm - brcm,bcm2711-pm + - brcm,bcm2712-pm - const: brcm,bcm2835-pm-wdt reg: - minItems: 2 + minItems: 1 maxItems: 3 reg-names: - minItems: 2 + minItems: 1 items: - const: pm - const: asb @@ -62,7 +60,35 @@ required: - reg - "#power-domain-cells" - "#reset-cells" - - clocks + +allOf: + - $ref: /schemas/watchdog/watchdog.yaml# + + - if: + properties: + compatible: + contains: + enum: + - brcm,bcm2835-pm + - brcm,bcm2711-pm + then: + required: + - clocks + + properties: + reg: + minItems: 2 + + reg-names: + minItems: 2 + + else: + properties: + reg: + maxItems: 1 + + reg-names: + maxItems: 1 additionalProperties: false From ed915823d4692aa4fc9d8ece4746ea1a7269cfde Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Fri, 31 Oct 2025 20:33:09 +0200 Subject: [PATCH 1152/1518] arm64: dts: broadcom: bcm2712: Add watchdog DT node commit 37c3a91e9730e274fe2eca9703033ae0f154cb62 upstream. Add watchdog device-tree node for bcm2712 SoC. Signed-off-by: Stanimir Varbanov Link: https://lore.kernel.org/r/20251031183309.1163384-5-svarbanov@suse.de Signed-off-by: Florian Fainelli Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/broadcom/bcm2712.dtsi | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 205b87f557d6d..d771694787b28 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -250,6 +250,15 @@ status = "disabled"; }; + pm: watchdog@7d200000 { + compatible = "brcm,bcm2712-pm", "brcm,bcm2835-pm-wdt"; + reg = <0x7d200000 0x604>; + reg-names = "pm"; + #power-domain-cells = <1>; + #reset-cells = <1>; + system-power-controller; + }; + pinctrl: pinctrl@7d504100 { compatible = "brcm,bcm2712c0-pinctrl"; reg = <0x7d504100 0x30>; From 9d11e4b1db1ce4057251d90ea1a670f2339ab664 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Wed, 17 Sep 2025 09:32:32 +0300 Subject: [PATCH 1153/1518] mfd: bcm2835-pm: Add support for BCM2712 commit 30ed024fb0768e9353f21d1d9e6960b7028acdfa upstream. The BCM2712 SoC has PM block but lacks the "asb" and "rpivid_asb" register spaces, and doesn't need clock(s). Add a compatible string for bcm2712 to allow probe of bcm2835-wdt and bcm2835-power drivers. Signed-off-by: Stanimir Varbanov Reviewed-by: Florian Fainelli Link: https://patch.msgid.link/20250917063233.1270-4-svarbanov@suse.de Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- drivers/mfd/bcm2835-pm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/bcm2835-pm.c b/drivers/mfd/bcm2835-pm.c index 3cb2b94231211..8bed59816e82e 100644 --- a/drivers/mfd/bcm2835-pm.c +++ b/drivers/mfd/bcm2835-pm.c @@ -108,6 +108,7 @@ static const struct of_device_id bcm2835_pm_of_match[] = { { .compatible = "brcm,bcm2835-pm-wdt", }, { .compatible = "brcm,bcm2835-pm", }, { .compatible = "brcm,bcm2711-pm", }, + { .compatible = "brcm,bcm2712-pm", }, {}, }; MODULE_DEVICE_TABLE(of, bcm2835_pm_of_match); From 62ee00c1042ca9e0c4c1f9587d49197a6c1c6bac Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 May 2026 09:38:59 +0200 Subject: [PATCH 1154/1518] ata: libata-scsi: improve readability of ata_scsi_qc_issue() commit 360190bd965f93794d5f5685a6de22ce6da2b672 upstream. Improve readability of ata_scsi_qc_issue(). No functional changes. Tested-by: Tommy Kelly Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-scsi.c | 43 +++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 22 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e7c78b8d3c2c0..73903f5997cab 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1767,7 +1767,7 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) int ret; if (!ap->ops->qc_defer) - goto issue; + goto issue_qc; /* * If we already have a deferred qc, then rely on the SCSI layer to @@ -1786,38 +1786,37 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) break; case ATA_DEFER_LINK: ret = SCSI_MLQUEUE_DEVICE_BUSY; - break; + goto defer_qc; case ATA_DEFER_PORT: ret = SCSI_MLQUEUE_HOST_BUSY; - break; + goto defer_qc; default: WARN_ON_ONCE(1); ret = SCSI_MLQUEUE_HOST_BUSY; - break; + goto defer_qc; } - if (ret) { - /* - * We must defer this qc: if this is not an NCQ command, keep - * this qc as a deferred one and report to the SCSI layer that - * we issued it so that it is not requeued. The deferred qc will - * be issued with the port deferred_qc_work once all on-going - * commands complete. - */ - if (!ata_is_ncq(qc->tf.protocol)) { - ap->deferred_qc = qc; - return 0; - } +issue_qc: + ata_qc_issue(qc); + return 0; - /* Force a requeue of the command to defer its execution. */ - ata_qc_free(qc); - return ret; +defer_qc: + /* + * We must defer this qc: if this is not an NCQ command, keep + * this qc as a deferred one and report to the SCSI layer that + * we issued it so that it is not requeued. The deferred qc will + * be issued with the port deferred_qc_work once all on-going + * commands complete. + */ + if (!ata_is_ncq(qc->tf.protocol)) { + ap->deferred_qc = qc; + return 0; } -issue: - ata_qc_issue(qc); + /* Force a requeue of the command to defer its execution. */ + ata_qc_free(qc); - return 0; + return ret; } /** From f207ebd5656e7eadb6b17e23ed763f4c3ac8637c Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 May 2026 09:39:00 +0200 Subject: [PATCH 1155/1518] ata: libata-scsi: do not use the deferred QC feature for ATA_DEFER_PORT commit ce4548807d2e4ae48fd0dbe38865467369877913 upstream. The deferred QC feature was meant to handle mixed NCQ and non-NCQ commands, i.e. for return value ATA_DEFER_LINK. ATA_DEFER_PORT is returned by PATA drivers, but also certain SATA drivers like sata_mv and sata_sil24 that uses ap->excl_link to workaround hardware bugs in these HBAs. Regardless of the reason, using the deferred QC feature for ATA_DEFER_PORT is always wrong, and will break the ap->excl_link usage of the SATA drivers that rely on that feature. Modify ata_scsi_qc_issue() to only use the deferred QC feature when mixing NCQ and non-NCQ commands, i.e. ATA_DEFER_LINK. Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Tested-by: Tommy Kelly Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-scsi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 73903f5997cab..d837389f40f7d 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1789,11 +1789,11 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) goto defer_qc; case ATA_DEFER_PORT: ret = SCSI_MLQUEUE_HOST_BUSY; - goto defer_qc; + goto free_qc; default: WARN_ON_ONCE(1); ret = SCSI_MLQUEUE_HOST_BUSY; - goto defer_qc; + goto free_qc; } issue_qc: @@ -1813,6 +1813,7 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) return 0; } +free_qc: /* Force a requeue of the command to defer its execution. */ ata_qc_free(qc); From 4e6eada8de381aaa7c8d8abc724327a48e2205de Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 May 2026 09:39:01 +0200 Subject: [PATCH 1156/1518] ata: libata-scsi: do not use the deferred QC feature on PMPs with CBS commit f233124fb36cd57ef09f96d517a38ab4b902e15e upstream. When using Port Multipliers (PMPs) with Command-Based Switching (CBS), you can only issue commands to one link at a time. For PMPs with CBS, there is already code to handle commands being sent to different links in sata_pmp_qc_defer_cmd_switch() using ap->excl_link. sata_sil24 also makes use of ap->excl_link. A user on the list reported that commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") broke PMPs with CBS. The commit introduced code that stores a deferred qc in ap->deferred_qc, to later be issued via a workqueue. It turns out that this change is incompatible with the existing ap->excl_link handling used by PMPs with CBS. Thus, modify sata_pmp_qc_defer_cmd_switch() and sil24_qc_defer() to return ATA_DEFER_LINK_EXCL, and make sure that the deferred QC handling via workqueue is not used for this return value. This way, PMPs with CBS will work once again. Note that the starvation referenced in commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") can only happen on libsas ports, and libsas does not support Port Multipliers, thus there is no harm of reverting back to the previous way of deferring commands for PMPs with CBS. Non-libsas ports connected to anything but a PMP with CBS (e.g. a normal drive or a PMP with FBS) will continue using the deferred workqueue, since it does result in lower completion latencies for non-NCQ commands, even though the workqueue is not strictly needed to avoid starvation for non-libsas ports. If we want to modify the scope of the workqueue issuing to also handle PMPs with CBS, then we should ensure that we can save both NCQ and non-NCQ commands in ap->deferred_qc, while also removing the existing PMP CBS handling using ap->excl_link, such that we don't duplicate features. While at it, also add a comment explaining how the ap->excl_link mechanism works. Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Tested-by: Tommy Kelly Reported-by: Tommy Kelly Closes: https://lore.kernel.org/linux-ide/ce09cc21-a8e9-4845-b205-35411e22fba9@tkel.ly/ Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-pmp.c | 13 ++++++++++++- drivers/ata/libata-scsi.c | 8 ++++++++ drivers/ata/sata_sil24.c | 6 +++++- include/linux/libata.h | 1 + 4 files changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index 57023324a56f0..b4adf0eb2ed51 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -110,13 +110,24 @@ int sata_pmp_qc_defer_cmd_switch(struct ata_queued_cmd *qc) { struct ata_link *link = qc->dev->link; struct ata_port *ap = link->ap; + int ret; if (ap->excl_link == NULL || ap->excl_link == link) { if (ap->nr_active_links == 0 || ata_link_active(link)) { qc->flags |= ATA_QCFLAG_CLEAR_EXCL; - return ata_std_qc_defer(qc); + ret = ata_std_qc_defer(qc); + if (ret == ATA_DEFER_LINK) + return ATA_DEFER_LINK_EXCL; + return ret; } + /* + * Note: ap->excl_link contains the link that is next in line, + * i.e. implicit round robin. If there is only one link + * dispatching, ap->excl_link will be left unclaimed, allowing + * other links to set ap->excl_link, ensuring that the currently + * active link cannot queue any more. + */ ap->excl_link = link; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d837389f40f7d..bbedbee6b85e9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1787,6 +1787,14 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) case ATA_DEFER_LINK: ret = SCSI_MLQUEUE_DEVICE_BUSY; goto defer_qc; + case ATA_DEFER_LINK_EXCL: + /* + * Drivers making use of ap->excl_link cannot store the QC in + * ap->deferred_qc, because the ap->excl_link handling is + * incompatible with the ap->deferred_qc workqueue handling. + */ + ret = SCSI_MLQUEUE_DEVICE_BUSY; + goto free_qc; case ATA_DEFER_PORT: ret = SCSI_MLQUEUE_HOST_BUSY; goto free_qc; diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index d642ece9f07a1..57f1081b86db3 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -789,6 +789,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) struct ata_link *link = qc->dev->link; struct ata_port *ap = link->ap; u8 prot = qc->tf.protocol; + int ret; /* * There is a bug in the chip: @@ -826,7 +827,10 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) qc->flags |= ATA_QCFLAG_CLEAR_EXCL; } - return ata_std_qc_defer(qc); + ret = ata_std_qc_defer(qc); + if (ret == ATA_DEFER_LINK) + return ATA_DEFER_LINK_EXCL; + return ret; } static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) diff --git a/include/linux/libata.h b/include/linux/libata.h index 3b8bdea8516d0..03cd68a4da66e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -335,6 +335,7 @@ enum { /* return values for ->qc_defer */ ATA_DEFER_LINK = 1, ATA_DEFER_PORT = 2, + ATA_DEFER_LINK_EXCL = 3, /* desc_len for ata_eh_info and context */ ATA_EH_DESC_LEN = 80, From 515de0a3b6c12577dcd7ed7c7b2875b18a316935 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 May 2026 09:39:02 +0200 Subject: [PATCH 1157/1518] ata: libata-scsi: do not needlessly defer commands when using PMP with FBS commit 759e8756da00aa115d504a18155b1d1ee1cc12e8 upstream. The ACS specification does not allow a non-NCQ command to be issued while an NCQ command is outstanding. Commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") introduced a feature where a deferred non-NCQ command gets issued from a workqueue. The design stores a single non-NCQ command per port. However, when using Port Multipliers (PMPs), specifically PMPs that support FIS-Based Switching (FBS), non-NCQ and NCQ commands can be mixed on the same port, just not for the same link, see e.g. ata_std_qc_defer() which is, and always has operated on a per-link basis. Therefore, move the deferred_qc from struct ata_port to struct ata_link. This way, when using a PMP with FBS, we will not needlessly defer commands to all other links, just because one link issued a non-NCQ command while having an NCQ command outstanding. Only commands for that specific link will be deferred. This is in line with how PMPs with FBS worked before commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation"). Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Tested-by: Tommy Kelly Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-core.c | 9 ++++--- drivers/ata/libata-eh.c | 8 +++--- drivers/ata/libata-pmp.c | 5 +++- drivers/ata/libata-scsi.c | 54 ++++++++++++++++++++++----------------- include/linux/libata.h | 6 ++--- 5 files changed, 47 insertions(+), 35 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 4fb8990d22d55..5ee4adc623427 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5499,6 +5499,7 @@ void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp) link->pmp = pmp; link->active_tag = ATA_TAG_POISON; link->hw_sata_spd_limit = UINT_MAX; + INIT_WORK(&link->deferred_qc_work, ata_scsi_deferred_qc_work); /* can't use iterator, ap isn't initialized yet */ for (i = 0; i < ATA_MAX_DEVICES; i++) { @@ -5581,7 +5582,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host) mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); - INIT_WORK(&ap->deferred_qc_work, ata_scsi_deferred_qc_work); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -6204,12 +6204,15 @@ static void ata_port_detach(struct ata_port *ap) /* It better be dead now and not have any remaining deferred qc. */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); - WARN_ON(ap->deferred_qc); - cancel_work_sync(&ap->deferred_qc_work); cancel_delayed_work_sync(&ap->hotplug_task); cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_for_each_link(link, ap, PMP_FIRST) { + WARN_ON(link->deferred_qc); + cancel_work_sync(&link->deferred_qc_work); + } + /* Delete port multiplier link transport devices */ if (ap->pmp_link) { int i; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 23be85418b3b1..5e8a63206108e 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -643,11 +643,11 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, if (qc->scsicmd != scmd) continue; if ((qc->flags & ATA_QCFLAG_ACTIVE) || - qc == ap->deferred_qc) + qc == qc->dev->link->deferred_qc) break; } - if (i < ATA_MAX_QUEUE && qc == ap->deferred_qc) { + if (i < ATA_MAX_QUEUE && qc == qc->dev->link->deferred_qc) { /* * This is a deferred command that timed out while * waiting for the command queue to drain. Since the qc @@ -658,8 +658,8 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, * deferred qc work from issuing this qc. */ WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); - ap->deferred_qc = NULL; - cancel_work(&ap->deferred_qc_work); + qc->dev->link->deferred_qc = NULL; + cancel_work(&qc->dev->link->deferred_qc_work); set_host_byte(scmd, DID_TIME_OUT); scsi_eh_finish_cmd(scmd, &ap->eh_done_q); } else if (i < ATA_MAX_QUEUE) { diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index b4adf0eb2ed51..48ac09d9031e6 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -582,8 +582,11 @@ static void sata_pmp_detach(struct ata_device *dev) if (ap->ops->pmp_detach) ap->ops->pmp_detach(ap); - ata_for_each_link(tlink, ap, EDGE) + ata_for_each_link(tlink, ap, EDGE) { + WARN_ON(tlink->deferred_qc); + cancel_work_sync(&tlink->deferred_qc_work); ata_eh_detach_dev(tlink->device); + } spin_lock_irqsave(ap->lock, flags); ap->nr_pmp_links = 0; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index bbedbee6b85e9..c7d2addf34874 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1659,8 +1659,9 @@ static void ata_qc_done(struct ata_queued_cmd *qc) void ata_scsi_deferred_qc_work(struct work_struct *work) { - struct ata_port *ap = - container_of(work, struct ata_port, deferred_qc_work); + struct ata_link *link = + container_of(work, struct ata_link, deferred_qc_work); + struct ata_port *ap = link->ap; struct ata_queued_cmd *qc; unsigned long flags; @@ -1671,10 +1672,10 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) * such case, we should not need any more deferring the qc, so warn if * qc_defer() says otherwise. */ - qc = ap->deferred_qc; + qc = link->deferred_qc; if (qc && !ata_port_eh_scheduled(ap)) { WARN_ON_ONCE(ap->ops->qc_defer(qc)); - ap->deferred_qc = NULL; + link->deferred_qc = NULL; ata_qc_issue(qc); } @@ -1683,8 +1684,7 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) void ata_scsi_requeue_deferred_qc(struct ata_port *ap) { - struct ata_queued_cmd *qc = ap->deferred_qc; - struct scsi_cmnd *scmd; + struct ata_link *link; lockdep_assert_held(ap->lock); @@ -1693,20 +1693,25 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap) * do not try to be smart about what to do with this deferred command * and simply requeue it by completing it with DID_REQUEUE. */ - if (!qc) - return; - - scmd = qc->scsicmd; - ap->deferred_qc = NULL; - cancel_work(&ap->deferred_qc_work); - ata_qc_free(qc); - scmd->result = (DID_REQUEUE << 16); - scsi_done(scmd); + ata_for_each_link(link, ap, PMP_FIRST) { + struct ata_queued_cmd *qc = link->deferred_qc; + struct scsi_cmnd *scmd; + + if (qc) { + scmd = qc->scsicmd; + link->deferred_qc = NULL; + cancel_work(&link->deferred_qc_work); + ata_qc_free(qc); + scmd->result = (DID_REQUEUE << 16); + scsi_done(scmd); + } + } } -static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) +static void ata_scsi_schedule_deferred_qc(struct ata_link *link) { - struct ata_queued_cmd *qc = ap->deferred_qc; + struct ata_queued_cmd *qc = link->deferred_qc; + struct ata_port *ap = link->ap; lockdep_assert_held(ap->lock); @@ -1723,12 +1728,12 @@ static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) return; } if (!ap->ops->qc_defer(qc)) - queue_work(system_highpri_wq, &ap->deferred_qc_work); + queue_work(system_highpri_wq, &link->deferred_qc_work); } static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { - struct ata_port *ap = qc->ap; + struct ata_link *link = qc->dev->link; struct scsi_cmnd *cmd = qc->scsicmd; u8 *cdb = cmd->cmnd; bool have_sense = qc->flags & ATA_QCFLAG_SENSE_VALID; @@ -1759,11 +1764,12 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) ata_qc_done(qc); - ata_scsi_schedule_deferred_qc(ap); + ata_scsi_schedule_deferred_qc(link); } static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) { + struct ata_link *link = qc->dev->link; int ret; if (!ap->ops->qc_defer) @@ -1774,7 +1780,7 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) * requeue and defer all incoming commands until the deferred qc is * processed, once all on-going commands complete. */ - if (ap->deferred_qc) { + if (link->deferred_qc) { ata_qc_free(qc); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1790,8 +1796,8 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) case ATA_DEFER_LINK_EXCL: /* * Drivers making use of ap->excl_link cannot store the QC in - * ap->deferred_qc, because the ap->excl_link handling is - * incompatible with the ap->deferred_qc workqueue handling. + * link->deferred_qc, because the ap->excl_link handling is + * incompatible with the link->deferred_qc workqueue handling. */ ret = SCSI_MLQUEUE_DEVICE_BUSY; goto free_qc; @@ -1817,7 +1823,7 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) * commands complete. */ if (!ata_is_ncq(qc->tf.protocol)) { - ap->deferred_qc = qc; + link->deferred_qc = qc; return 0; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 03cd68a4da66e..5c3f98a418c38 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -855,6 +855,9 @@ struct ata_link { unsigned int sata_spd; /* current SATA PHY speed */ enum ata_lpm_policy lpm_policy; + struct work_struct deferred_qc_work; + struct ata_queued_cmd *deferred_qc; + /* record runtime error info, protected by host_set lock */ struct ata_eh_info eh_info; /* EH context */ @@ -900,9 +903,6 @@ struct ata_port { u64 qc_active; int nr_active_links; /* #links with active qcs */ - struct work_struct deferred_qc_work; - struct ata_queued_cmd *deferred_qc; - struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ From 523cd0ea0324202704f24bd27eacd742916c8b8b Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 27 May 2026 12:43:10 -0400 Subject: [PATCH 1158/1518] Revert "ice: fix double-free of tx_buf skb" This reverts commit 7cb19ec8ac087f33bee60f5d6054b284a5b9bb6f. Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_txrx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index e0774a640955d..90dbe5266ce78 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2594,9 +2594,6 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) ice_trace(xmit_frame_ring, tx_ring, skb); - /* record the location of the first descriptor for this packet */ - first = &tx_ring->tx_buf[tx_ring->next_to_use]; - count = ice_xmit_desc_count(skb); if (ice_chk_linearize(skb, count)) { if (__skb_linearize(skb)) @@ -2622,6 +2619,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.tx_ring = tx_ring; + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buf[tx_ring->next_to_use]; first->skb = skb; first->type = ICE_TX_BUF_SKB; first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN); @@ -2686,7 +2685,6 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) out_drop: ice_trace(xmit_frame_ring_drop, tx_ring, skb); dev_kfree_skb_any(skb); - first->type = ICE_TX_BUF_EMPTY; return NETDEV_TX_OK; } From 18a08b87db713d50b4fb0ff3e971c36f6610c666 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 27 May 2026 12:43:10 -0400 Subject: [PATCH 1159/1518] Revert "ice: Remove jumbo_remove step from TX path" This reverts commit 55500245ec0420df96b2a89444aabf0cff2c60bc. Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_txrx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 90dbe5266ce78..73f08d02f9c76 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2594,6 +2594,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) ice_trace(xmit_frame_ring, tx_ring, skb); + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto out_drop; + count = ice_xmit_desc_count(skb); if (ice_chk_linearize(skb, count)) { if (__skb_linearize(skb)) From fa4b91eea4331e7c24aa2d7855583d062a73e4ea Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 26 May 2026 21:31:19 +0800 Subject: [PATCH 1160/1518] drm/vblank: Add vblank timer [ Upstream commit 74afeb8128502a529041a2566febd26053a7be11 ] The vblank timer simulates a vblank interrupt for hardware without support. Rate-limits the display update frequency. DRM drivers for hardware without vblank support apply display updates ASAP. A vblank event informs DRM clients of the completed update. Userspace compositors immediately schedule the next update, which creates significant load on virtualization outputs. Display updates are usually fast on virtualization outputs, as their framebuffers are in regular system memory and there's no hardware vblank interrupt to throttle the update rate. The vblank timer is a HR timer that signals the vblank in software. It limits the update frequency of a DRM driver similar to a hardware vblank interrupt. The timer is not synchronized to the actual vblank interval of the display. The code has been adopted from vkms, which added the funtionality in commit 3a0709928b17 ("drm/vkms: Add vblank events simulated by hrtimers"). The new implementation is part of the existing vblank support, which sets up the timer automatically. Drivers only have to start and cancel the vblank timer as part of enabling and disabling the CRTC. The new vblank helper library provides callbacks for struct drm_crtc_funcs. The standard way for handling vblank is to call drm_crtc_handle_vblank(). Drivers that require additional processing, such as vkms, can init handle_vblank_timeout in struct drm_crtc_helper_funcs to refer to their timeout handler. There's a possible deadlock between drm_crtc_handle_vblank() and hrtimer_cancel(). [1] The implementation avoids to call hrtimer_cancel() directly and instead signals to the timer function to not restart itself. v4: - fix possible race condition between timeout and atomic commit (Michael) v3: - avoid deadlock when cancelling timer (Ville, Lyude) v2: - implement vblank timer entirely in vblank helpers - downgrade overrun warning to debug - fix docs Signed-off-by: Thomas Zimmermann Tested-by: Louis Chauvet Reviewed-by: Louis Chauvet Reviewed-by: Javier Martinez Canillas Tested-by: Michael Kelley Link: https://lore.kernel.org/all/20250510094757.4174662-1-zengheng4@huawei.com/ # [1] Link: https://lore.kernel.org/r/20250916083816.30275-2-tzimmermann@suse.de Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Signed-off-by: Sasha Levin --- Documentation/gpu/drm-kms-helpers.rst | 12 ++ drivers/gpu/drm/Makefile | 3 +- drivers/gpu/drm/drm_vblank.c | 172 ++++++++++++++++++++++- drivers/gpu/drm/drm_vblank_helper.c | 96 +++++++++++++ include/drm/drm_modeset_helper_vtables.h | 12 ++ include/drm/drm_vblank.h | 32 +++++ include/drm/drm_vblank_helper.h | 33 +++++ 7 files changed, 357 insertions(+), 3 deletions(-) create mode 100644 drivers/gpu/drm/drm_vblank_helper.c create mode 100644 include/drm/drm_vblank_helper.h diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst index 5139705089f20..781129f78b06b 100644 --- a/Documentation/gpu/drm-kms-helpers.rst +++ b/Documentation/gpu/drm-kms-helpers.rst @@ -92,6 +92,18 @@ GEM Atomic Helper Reference .. kernel-doc:: drivers/gpu/drm/drm_gem_atomic_helper.c :export: +VBLANK Helper Reference +----------------------- + +.. kernel-doc:: drivers/gpu/drm/drm_vblank_helper.c + :doc: overview + +.. kernel-doc:: include/drm/drm_vblank_helper.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_vblank_helper.c + :export: + Simple KMS Helper Reference =========================== diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 742f0d590c5af..b248e64587ed4 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -152,7 +152,8 @@ drm_kms_helper-y := \ drm_plane_helper.o \ drm_probe_helper.o \ drm_self_refresh_helper.o \ - drm_simple_kms_helper.o + drm_simple_kms_helper.o \ + drm_vblank_helper.o drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 46f59883183d9..61e211fd3c9c8 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -136,8 +136,17 @@ * vblanks after a timer has expired, which can be configured through the * ``vblankoffdelay`` module parameter. * - * Drivers for hardware without support for vertical-blanking interrupts - * must not call drm_vblank_init(). For such drivers, atomic helpers will + * Drivers for hardware without support for vertical-blanking interrupts can + * use DRM vblank timers to send vblank events at the rate of the current + * display mode's refresh. While not synchronized to the hardware's + * vertical-blanking regions, the timer helps DRM clients and compositors to + * adapt their update cycle to the display output. Drivers should set up + * vblanking as usual, but call drm_crtc_vblank_start_timer() and + * drm_crtc_vblank_cancel_timer() as part of their atomic mode setting. + * See also DRM vblank helpers for more information. + * + * Drivers without support for vertical-blanking interrupts nor timers must + * not call drm_vblank_init(). For these drivers, atomic helpers will * automatically generate fake vblank events as part of the display update. * This functionality also can be controlled by the driver by enabling and * disabling struct drm_crtc_state.no_vblank. @@ -508,6 +517,9 @@ static void drm_vblank_init_release(struct drm_device *dev, void *ptr) drm_WARN_ON(dev, READ_ONCE(vblank->enabled) && drm_core_check_feature(dev, DRIVER_MODESET)); + if (vblank->vblank_timer.crtc) + hrtimer_cancel(&vblank->vblank_timer.timer); + drm_vblank_destroy_worker(vblank); timer_delete_sync(&vblank->disable_timer); } @@ -2162,3 +2174,159 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data, return ret; } +/* + * VBLANK timer + */ + +static enum hrtimer_restart drm_vblank_timer_function(struct hrtimer *timer) +{ + struct drm_vblank_crtc_timer *vtimer = + container_of(timer, struct drm_vblank_crtc_timer, timer); + struct drm_crtc *crtc = vtimer->crtc; + const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private; + struct drm_device *dev = crtc->dev; + unsigned long flags; + ktime_t interval; + u64 ret_overrun; + bool succ; + + spin_lock_irqsave(&vtimer->interval_lock, flags); + interval = vtimer->interval; + spin_unlock_irqrestore(&vtimer->interval_lock, flags); + + if (!interval) + return HRTIMER_NORESTART; + + ret_overrun = hrtimer_forward_now(&vtimer->timer, interval); + if (ret_overrun != 1) + drm_dbg_vbl(dev, "vblank timer overrun\n"); + + if (crtc_funcs->handle_vblank_timeout) + succ = crtc_funcs->handle_vblank_timeout(crtc); + else + succ = drm_crtc_handle_vblank(crtc); + if (!succ) + return HRTIMER_NORESTART; + + return HRTIMER_RESTART; +} + +/** + * drm_crtc_vblank_start_timer - Starts the vblank timer on the given CRTC + * @crtc: the CRTC + * + * Drivers should call this function from their CRTC's enable_vblank + * function to start a vblank timer. The timer will fire after the duration + * of a full frame. drm_crtc_vblank_cancel_timer() disables a running timer. + * + * Returns: + * 0 on success, or a negative errno code otherwise. + */ +int drm_crtc_vblank_start_timer(struct drm_crtc *crtc) +{ + struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc); + struct drm_vblank_crtc_timer *vtimer = &vblank->vblank_timer; + unsigned long flags; + + if (!vtimer->crtc) { + /* + * Set up the data structures on the first invocation. + */ + vtimer->crtc = crtc; + spin_lock_init(&vtimer->interval_lock); + hrtimer_setup(&vtimer->timer, drm_vblank_timer_function, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); + } else { + /* + * Timer should not be active. If it is, wait for the + * previous cancel operations to finish. + */ + while (hrtimer_active(&vtimer->timer)) + hrtimer_try_to_cancel(&vtimer->timer); + } + + drm_calc_timestamping_constants(crtc, &crtc->mode); + + spin_lock_irqsave(&vtimer->interval_lock, flags); + vtimer->interval = ns_to_ktime(vblank->framedur_ns); + spin_unlock_irqrestore(&vtimer->interval_lock, flags); + + hrtimer_start(&vtimer->timer, vtimer->interval, HRTIMER_MODE_REL); + + return 0; +} +EXPORT_SYMBOL(drm_crtc_vblank_start_timer); + +/** + * drm_crtc_vblank_start_timer - Cancels the given CRTC's vblank timer + * @crtc: the CRTC + * + * Drivers should call this function from their CRTC's disable_vblank + * function to stop a vblank timer. + */ +void drm_crtc_vblank_cancel_timer(struct drm_crtc *crtc) +{ + struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc); + struct drm_vblank_crtc_timer *vtimer = &vblank->vblank_timer; + unsigned long flags; + + /* + * Calling hrtimer_cancel() can result in a deadlock with DRM's + * vblank_time_lime_lock and hrtimers' softirq_expiry_lock. So + * clear interval and indicate cancellation. The timer function + * will cancel itself on the next invocation. + */ + + spin_lock_irqsave(&vtimer->interval_lock, flags); + vtimer->interval = 0; + spin_unlock_irqrestore(&vtimer->interval_lock, flags); + + hrtimer_try_to_cancel(&vtimer->timer); +} +EXPORT_SYMBOL(drm_crtc_vblank_cancel_timer); + +/** + * drm_crtc_vblank_get_vblank_timeout - Returns the vblank timeout + * @crtc: The CRTC + * @vblank_time: Returns the next vblank timestamp + * + * The helper drm_crtc_vblank_get_vblank_timeout() returns the next vblank + * timestamp of the CRTC's vblank timer according to the timer's expiry + * time. + */ +void drm_crtc_vblank_get_vblank_timeout(struct drm_crtc *crtc, ktime_t *vblank_time) +{ + struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc); + struct drm_vblank_crtc_timer *vtimer = &vblank->vblank_timer; + u64 cur_count; + ktime_t cur_time; + + if (!READ_ONCE(vblank->enabled)) { + *vblank_time = ktime_get(); + return; + } + + /* + * A concurrent vblank timeout could update the expires field before + * we compare it with the vblank time. Hence we'd compare the old + * expiry time to the new vblank time; deducing the timer had already + * expired. Reread until we get consistent values from both fields. + */ + do { + cur_count = drm_crtc_vblank_count_and_time(crtc, &cur_time); + *vblank_time = READ_ONCE(vtimer->timer.node.expires); + } while (cur_count != drm_crtc_vblank_count_and_time(crtc, &cur_time)); + + if (drm_WARN_ON(crtc->dev, !ktime_compare(*vblank_time, cur_time))) + return; /* Already expired */ + + /* + * To prevent races we roll the hrtimer forward before we do any + * interrupt processing - this is how real hw works (the interrupt + * is only generated after all the vblank registers are updated) + * and what the vblank core expects. Therefore we need to always + * correct the timestamp by one frame. + */ + *vblank_time = ktime_sub(*vblank_time, vtimer->interval); +} +EXPORT_SYMBOL(drm_crtc_vblank_get_vblank_timeout); diff --git a/drivers/gpu/drm/drm_vblank_helper.c b/drivers/gpu/drm/drm_vblank_helper.c new file mode 100644 index 0000000000000..f94d1e706191b --- /dev/null +++ b/drivers/gpu/drm/drm_vblank_helper.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: MIT + +#include +#include +#include +#include +#include +#include + +/** + * DOC: overview + * + * The vblank helper library provides functions for supporting vertical + * blanking in DRM drivers. + * + * For vblank timers, several callback implementations are available. + * Drivers enable support for vblank timers by setting the vblank callbacks + * in struct &drm_crtc_funcs to the helpers provided by this library. The + * initializer macro DRM_CRTC_VBLANK_TIMER_FUNCS does this conveniently. + * + * Once the driver enables vblank support with drm_vblank_init(), each + * CRTC's vblank timer fires according to the programmed display mode. By + * default, the vblank timer invokes drm_crtc_handle_vblank(). Drivers with + * more specific requirements can set their own handler function in + * struct &drm_crtc_helper_funcs.handle_vblank_timeout. + */ + +/* + * VBLANK timer + */ + +/** + * drm_crtc_vblank_helper_enable_vblank_timer - Implements struct &drm_crtc_funcs.enable_vblank + * @crtc: The CRTC + * + * The helper drm_crtc_vblank_helper_enable_vblank_timer() implements + * enable_vblank of struct drm_crtc_helper_funcs for CRTCs that require + * a VBLANK timer. It sets up the timer on the first invocation. The + * started timer expires after the current frame duration. See struct + * &drm_vblank_crtc.framedur_ns. + * + * See also struct &drm_crtc_helper_funcs.enable_vblank. + * + * Returns: + * 0 on success, or a negative errno code otherwise. + */ +int drm_crtc_vblank_helper_enable_vblank_timer(struct drm_crtc *crtc) +{ + return drm_crtc_vblank_start_timer(crtc); +} +EXPORT_SYMBOL(drm_crtc_vblank_helper_enable_vblank_timer); + +/** + * drm_crtc_vblank_helper_disable_vblank_timer - Implements struct &drm_crtc_funcs.disable_vblank + * @crtc: The CRTC + * + * The helper drm_crtc_vblank_helper_disable_vblank_timer() implements + * disable_vblank of struct drm_crtc_funcs for CRTCs that require a + * VBLANK timer. + * + * See also struct &drm_crtc_helper_funcs.disable_vblank. + */ +void drm_crtc_vblank_helper_disable_vblank_timer(struct drm_crtc *crtc) +{ + drm_crtc_vblank_cancel_timer(crtc); +} +EXPORT_SYMBOL(drm_crtc_vblank_helper_disable_vblank_timer); + +/** + * drm_crtc_vblank_helper_get_vblank_timestamp_from_timer - + * Implements struct &drm_crtc_funcs.get_vblank_timestamp + * @crtc: The CRTC + * @max_error: Maximum acceptable error + * @vblank_time: Returns the next vblank timestamp + * @in_vblank_irq: True is called from drm_crtc_handle_vblank() + * + * The helper drm_crtc_helper_get_vblank_timestamp_from_timer() implements + * get_vblank_timestamp of struct drm_crtc_funcs for CRTCs that require a + * VBLANK timer. It returns the timestamp according to the timer's expiry + * time. + * + * See also struct &drm_crtc_funcs.get_vblank_timestamp. + * + * Returns: + * True on success, or false otherwise. + */ +bool drm_crtc_vblank_helper_get_vblank_timestamp_from_timer(struct drm_crtc *crtc, + int *max_error, + ktime_t *vblank_time, + bool in_vblank_irq) +{ + drm_crtc_vblank_get_vblank_timeout(crtc, vblank_time); + + return true; +} +EXPORT_SYMBOL(drm_crtc_vblank_helper_get_vblank_timestamp_from_timer); diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index ce7c7aeac887b..fe32854b7ffec 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -490,6 +490,18 @@ struct drm_crtc_helper_funcs { bool in_vblank_irq, int *vpos, int *hpos, ktime_t *stime, ktime_t *etime, const struct drm_display_mode *mode); + + /** + * @handle_vblank_timeout: Handles timeouts of the vblank timer. + * + * Called by CRTC's the vblank timer on each timeout. Semantics is + * equivalient to drm_crtc_handle_vblank(). Implementations should + * invoke drm_crtc_handle_vblank() as part of processing the timeout. + * + * This callback is optional. If unset, the vblank timer invokes + * drm_crtc_handle_vblank() directly. + */ + bool (*handle_vblank_timeout)(struct drm_crtc *crtc); }; /** diff --git a/include/drm/drm_vblank.h b/include/drm/drm_vblank.h index 151ab1e85b1b7..ffa564d796384 100644 --- a/include/drm/drm_vblank.h +++ b/include/drm/drm_vblank.h @@ -25,6 +25,7 @@ #define _DRM_VBLANK_H_ #include +#include #include #include #include @@ -103,6 +104,28 @@ struct drm_vblank_crtc_config { bool disable_immediate; }; +/** + * struct drm_vblank_crtc_timer - vblank timer for a CRTC + */ +struct drm_vblank_crtc_timer { + /** + * @timer: The vblank's high-resolution timer + */ + struct hrtimer timer; + /** + * @interval_lock: Protects @interval + */ + spinlock_t interval_lock; + /** + * @interval: Duration between two vblanks + */ + ktime_t interval; + /** + * @crtc: The timer's CRTC + */ + struct drm_crtc *crtc; +}; + /** * struct drm_vblank_crtc - vblank tracking for a CRTC * @@ -254,6 +277,11 @@ struct drm_vblank_crtc { * cancelled. */ wait_queue_head_t work_wait_queue; + + /** + * @vblank_timer: Holds the state of the vblank timer + */ + struct drm_vblank_crtc_timer vblank_timer; }; struct drm_vblank_crtc *drm_crtc_vblank_crtc(struct drm_crtc *crtc); @@ -290,6 +318,10 @@ wait_queue_head_t *drm_crtc_vblank_waitqueue(struct drm_crtc *crtc); void drm_crtc_set_max_vblank_count(struct drm_crtc *crtc, u32 max_vblank_count); +int drm_crtc_vblank_start_timer(struct drm_crtc *crtc); +void drm_crtc_vblank_cancel_timer(struct drm_crtc *crtc); +void drm_crtc_vblank_get_vblank_timeout(struct drm_crtc *crtc, ktime_t *vblank_time); + /* * Helpers for struct drm_crtc_funcs */ diff --git a/include/drm/drm_vblank_helper.h b/include/drm/drm_vblank_helper.h new file mode 100644 index 0000000000000..74a971d0cfba0 --- /dev/null +++ b/include/drm/drm_vblank_helper.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _DRM_VBLANK_HELPER_H_ +#define _DRM_VBLANK_HELPER_H_ + +#include +#include + +struct drm_crtc; + +/* + * VBLANK timer + */ + +int drm_crtc_vblank_helper_enable_vblank_timer(struct drm_crtc *crtc); +void drm_crtc_vblank_helper_disable_vblank_timer(struct drm_crtc *crtc); +bool drm_crtc_vblank_helper_get_vblank_timestamp_from_timer(struct drm_crtc *crtc, + int *max_error, + ktime_t *vblank_time, + bool in_vblank_irq); + +/** + * DRM_CRTC_VBLANK_TIMER_FUNCS - Default implementation for VBLANK timers + * + * This macro initializes struct &drm_crtc_funcs to default helpers for + * VBLANK timers. + */ +#define DRM_CRTC_VBLANK_TIMER_FUNCS \ + .enable_vblank = drm_crtc_vblank_helper_enable_vblank_timer, \ + .disable_vblank = drm_crtc_vblank_helper_disable_vblank_timer, \ + .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp_from_timer + +#endif From 60918357456d39f640de25845890614caa44a30a Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 26 May 2026 21:31:20 +0800 Subject: [PATCH 1161/1518] drm/vblank: Add CRTC helpers for simple use cases [ Upstream commit d54dbb5963bdbdf8559903fe2b2343e871adcb30 ] Implement atomic_flush, atomic_enable and atomic_disable of struct drm_crtc_helper_funcs for vblank handling. Driver with no further requirements can use these functions instead of adding their own. Also simplifies the use of vblank timers. The code has been adopted from vkms, which added the funtionality in commit 3a0709928b17 ("drm/vkms: Add vblank events simulated by hrtimers"). v3: - mention vkms (Javier) v2: - fix docs Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20250916083816.30275-3-tzimmermann@suse.de Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_vblank_helper.c | 80 +++++++++++++++++++++++++++++ include/drm/drm_vblank_helper.h | 23 +++++++++ 2 files changed, 103 insertions(+) diff --git a/drivers/gpu/drm/drm_vblank_helper.c b/drivers/gpu/drm/drm_vblank_helper.c index f94d1e706191b..a04a6ba1b0ca0 100644 --- a/drivers/gpu/drm/drm_vblank_helper.c +++ b/drivers/gpu/drm/drm_vblank_helper.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: MIT +#include #include #include #include @@ -17,6 +18,12 @@ * Drivers enable support for vblank timers by setting the vblank callbacks * in struct &drm_crtc_funcs to the helpers provided by this library. The * initializer macro DRM_CRTC_VBLANK_TIMER_FUNCS does this conveniently. + * The driver further has to send the VBLANK event from its atomic_flush + * callback and control vblank from the CRTC's atomic_enable and atomic_disable + * callbacks. The callbacks are located in struct &drm_crtc_helper_funcs. + * The vblank helper library provides implementations of these callbacks + * for drivers without further requirements. The initializer macro + * DRM_CRTC_HELPER_VBLANK_FUNCS sets them coveniently. * * Once the driver enables vblank support with drm_vblank_init(), each * CRTC's vblank timer fires according to the programmed display mode. By @@ -25,6 +32,79 @@ * struct &drm_crtc_helper_funcs.handle_vblank_timeout. */ +/* + * VBLANK helpers + */ + +/** + * drm_crtc_vblank_atomic_flush - + * Implements struct &drm_crtc_helper_funcs.atomic_flush + * @crtc: The CRTC + * @state: The atomic state to apply + * + * The helper drm_crtc_vblank_atomic_flush() implements atomic_flush of + * struct drm_crtc_helper_funcs for CRTCs that only need to send out a + * VBLANK event. + * + * See also struct &drm_crtc_helper_funcs.atomic_flush. + */ +void drm_crtc_vblank_atomic_flush(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_device *dev = crtc->dev; + struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + struct drm_pending_vblank_event *event; + + spin_lock_irq(&dev->event_lock); + + event = crtc_state->event; + crtc_state->event = NULL; + + if (event) { + if (drm_crtc_vblank_get(crtc) == 0) + drm_crtc_arm_vblank_event(crtc, event); + else + drm_crtc_send_vblank_event(crtc, event); + } + + spin_unlock_irq(&dev->event_lock); +} +EXPORT_SYMBOL(drm_crtc_vblank_atomic_flush); + +/** + * drm_crtc_vblank_atomic_enable - Implements struct &drm_crtc_helper_funcs.atomic_enable + * @crtc: The CRTC + * @state: The atomic state + * + * The helper drm_crtc_vblank_atomic_enable() implements atomic_enable + * of struct drm_crtc_helper_funcs for CRTCs the only need to enable VBLANKs. + * + * See also struct &drm_crtc_helper_funcs.atomic_enable. + */ +void drm_crtc_vblank_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + drm_crtc_vblank_on(crtc); +} +EXPORT_SYMBOL(drm_crtc_vblank_atomic_enable); + +/** + * drm_crtc_vblank_atomic_disable - Implements struct &drm_crtc_helper_funcs.atomic_disable + * @crtc: The CRTC + * @state: The atomic state + * + * The helper drm_crtc_vblank_atomic_disable() implements atomic_disable + * of struct drm_crtc_helper_funcs for CRTCs the only need to disable VBLANKs. + * + * See also struct &drm_crtc_funcs.atomic_disable. + */ +void drm_crtc_vblank_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + drm_crtc_vblank_off(crtc); +} +EXPORT_SYMBOL(drm_crtc_vblank_atomic_disable); + /* * VBLANK timer */ diff --git a/include/drm/drm_vblank_helper.h b/include/drm/drm_vblank_helper.h index 74a971d0cfba0..fcd8a9b358463 100644 --- a/include/drm/drm_vblank_helper.h +++ b/include/drm/drm_vblank_helper.h @@ -6,8 +6,31 @@ #include #include +struct drm_atomic_state; struct drm_crtc; +/* + * VBLANK helpers + */ + +void drm_crtc_vblank_atomic_flush(struct drm_crtc *crtc, + struct drm_atomic_state *state); +void drm_crtc_vblank_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state); +void drm_crtc_vblank_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *crtc_state); + +/** + * DRM_CRTC_HELPER_VBLANK_FUNCS - Default implementation for VBLANK helpers + * + * This macro initializes struct &drm_crtc_helper_funcs to default helpers + * for VBLANK handling. + */ +#define DRM_CRTC_HELPER_VBLANK_FUNCS \ + .atomic_flush = drm_crtc_vblank_atomic_flush, \ + .atomic_enable = drm_crtc_vblank_atomic_enable, \ + .atomic_disable = drm_crtc_vblank_atomic_disable + /* * VBLANK timer */ From a0582cc923985c6b72fe871b5f7aa7c682bfc230 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 26 May 2026 21:31:21 +0800 Subject: [PATCH 1162/1518] drm/vkms: Convert to DRM's vblank timer [ Upstream commit 02e2681ffe1addde1fc8c35d05657b16bfa79613 ] Replace vkms' vblank timer with the DRM implementation. The DRM code is identical in concept, but differs in implementation. Vblank timers are covered in vblank helpers and initializer macros, so remove the corresponding hrtimer in struct vkms_output. The vblank timer calls vkms' custom timeout code via handle_vblank_timeout in struct drm_crtc_helper_funcs. Signed-off-by: Thomas Zimmermann Tested-by: Louis Chauvet Reviewed-by: Louis Chauvet Reviewed-by: Javier Martinez Canillas Link: https://lore.kernel.org/r/20250916083816.30275-4-tzimmermann@suse.de Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Signed-off-by: Sasha Levin --- drivers/gpu/drm/vkms/vkms_crtc.c | 83 +++----------------------------- drivers/gpu/drm/vkms/vkms_drv.h | 2 - 2 files changed, 7 insertions(+), 78 deletions(-) diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c index e60573e0f3e95..bd79f24686dce 100644 --- a/drivers/gpu/drm/vkms/vkms_crtc.c +++ b/drivers/gpu/drm/vkms/vkms_crtc.c @@ -7,25 +7,18 @@ #include #include #include +#include #include "vkms_drv.h" -static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer) +static bool vkms_crtc_handle_vblank_timeout(struct drm_crtc *crtc) { - struct vkms_output *output = container_of(timer, struct vkms_output, - vblank_hrtimer); - struct drm_crtc *crtc = &output->crtc; + struct vkms_output *output = drm_crtc_to_vkms_output(crtc); struct vkms_crtc_state *state; - u64 ret_overrun; bool ret, fence_cookie; fence_cookie = dma_fence_begin_signalling(); - ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer, - output->period_ns); - if (ret_overrun != 1) - pr_warn("%s: vblank timer overrun\n", __func__); - spin_lock(&output->lock); ret = drm_crtc_handle_vblank(crtc); if (!ret) @@ -57,55 +50,6 @@ static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer) dma_fence_end_signalling(fence_cookie); - return HRTIMER_RESTART; -} - -static int vkms_enable_vblank(struct drm_crtc *crtc) -{ - struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc); - struct vkms_output *out = drm_crtc_to_vkms_output(crtc); - - hrtimer_setup(&out->vblank_hrtimer, &vkms_vblank_simulate, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); - out->period_ns = ktime_set(0, vblank->framedur_ns); - hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL); - - return 0; -} - -static void vkms_disable_vblank(struct drm_crtc *crtc) -{ - struct vkms_output *out = drm_crtc_to_vkms_output(crtc); - - hrtimer_cancel(&out->vblank_hrtimer); -} - -static bool vkms_get_vblank_timestamp(struct drm_crtc *crtc, - int *max_error, ktime_t *vblank_time, - bool in_vblank_irq) -{ - struct vkms_output *output = drm_crtc_to_vkms_output(crtc); - struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc); - - if (!READ_ONCE(vblank->enabled)) { - *vblank_time = ktime_get(); - return true; - } - - *vblank_time = READ_ONCE(output->vblank_hrtimer.node.expires); - - if (WARN_ON(*vblank_time == vblank->time)) - return true; - - /* - * To prevent races we roll the hrtimer forward before we do any - * interrupt processing - this is how real hw works (the interrupt is - * only generated after all the vblank registers are updated) and what - * the vblank core expects. Therefore we need to always correct the - * timestampe by one frame. - */ - *vblank_time -= output->period_ns; - return true; } @@ -159,9 +103,7 @@ static const struct drm_crtc_funcs vkms_crtc_funcs = { .reset = vkms_atomic_crtc_reset, .atomic_duplicate_state = vkms_atomic_crtc_duplicate_state, .atomic_destroy_state = vkms_atomic_crtc_destroy_state, - .enable_vblank = vkms_enable_vblank, - .disable_vblank = vkms_disable_vblank, - .get_vblank_timestamp = vkms_get_vblank_timestamp, + DRM_CRTC_VBLANK_TIMER_FUNCS, .get_crc_sources = vkms_get_crc_sources, .set_crc_source = vkms_set_crc_source, .verify_crc_source = vkms_verify_crc_source, @@ -213,18 +155,6 @@ static int vkms_crtc_atomic_check(struct drm_crtc *crtc, return 0; } -static void vkms_crtc_atomic_enable(struct drm_crtc *crtc, - struct drm_atomic_state *state) -{ - drm_crtc_vblank_on(crtc); -} - -static void vkms_crtc_atomic_disable(struct drm_crtc *crtc, - struct drm_atomic_state *state) -{ - drm_crtc_vblank_off(crtc); -} - static void vkms_crtc_atomic_begin(struct drm_crtc *crtc, struct drm_atomic_state *state) __acquires(&vkms_output->lock) @@ -265,8 +195,9 @@ static const struct drm_crtc_helper_funcs vkms_crtc_helper_funcs = { .atomic_check = vkms_crtc_atomic_check, .atomic_begin = vkms_crtc_atomic_begin, .atomic_flush = vkms_crtc_atomic_flush, - .atomic_enable = vkms_crtc_atomic_enable, - .atomic_disable = vkms_crtc_atomic_disable, + .atomic_enable = drm_crtc_vblank_atomic_enable, + .atomic_disable = drm_crtc_vblank_atomic_disable, + .handle_vblank_timeout = vkms_crtc_handle_vblank_timeout, }; struct vkms_output *vkms_crtc_init(struct drm_device *dev, struct drm_plane *primary, diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h index 8013c31efe3b1..fb9711e1c6fbd 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.h +++ b/drivers/gpu/drm/vkms/vkms_drv.h @@ -215,8 +215,6 @@ struct vkms_output { struct drm_crtc crtc; struct drm_writeback_connector wb_connector; struct drm_encoder wb_encoder; - struct hrtimer vblank_hrtimer; - ktime_t period_ns; struct workqueue_struct *composer_workq; spinlock_t lock; From ed39ecd3a96cdf94589aef46f2f711cf93baa0d3 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 26 May 2026 21:31:22 +0800 Subject: [PATCH 1163/1518] drm/atomic: Increase timeout in drm_atomic_helper_wait_for_vblanks() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 79ae8510b5b81b9500370f89c619b50ca9c0990f ] Increase the timeout for vblank events from 100 ms to 1000 ms. This is the same fix as in commit f050da08a4ed ("drm/vblank: Increase timeout in drm_wait_one_vblank()") for another vblank timeout. After merging generic DRM vblank timers [1] and converting several DRM drivers for virtual hardware, these drivers synchronize their vblank events to the display refresh rate. This can trigger timeouts within the DRM framework. Signed-off-by: Thomas Zimmermann Link: https://lore.kernel.org/dri-devel/20250904145806.430568-1-tzimmermann@suse.de/ # [1] Reported-by: syzbot+fcede535e7eb57cf5b43@syzkaller.appspotmail.com Closes: https://lore.kernel.org/dri-devel/69381d6c.050a0220.4004e.0017.GAE@google.com/ Reviewed-by: Ville Syrjälä Fixes: 74afeb812850 ("drm/vblank: Add vblank timer") Link: https://patch.msgid.link/20251209143325.102056-1-tzimmermann@suse.de Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_atomic_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index bbec1c184f652..b06a5cba52958 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1913,7 +1913,7 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, ret = wait_event_timeout(dev->vblank[i].queue, state->crtcs[i].last_vblank_count != drm_crtc_vblank_count(crtc), - msecs_to_jiffies(100)); + msecs_to_jiffies(1000)); WARN(!ret, "[CRTC:%d:%s] vblank wait timed out\n", crtc->base.id, crtc->name); From 141ffb83abe97db88df8822c82cd53ae5e38221a Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 26 May 2026 21:31:23 +0800 Subject: [PATCH 1164/1518] drm/vblank: Fix kernel docs for vblank timer [ Upstream commit 3946d3ba99342f3b9996e621f05e7003d4308171 ] Fix documentation for drm_crtc_vblank_start_timer(), which referred to drm_crtc_vblank_cancel_timer(). Signed-off-by: Thomas Zimmermann Reported-by: Stephen Rothwell Closes: https://lore.kernel.org/dri-devel/20251106152201.6f248c09@canb.auug.org.au/ Fixes: 74afeb812850 ("drm/vblank: Add vblank timer") Cc: Thomas Zimmermann Cc: Louis Chauvet Cc: Javier Martinez Canillas Cc: David Airlie Cc: Simona Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: dri-devel@lists.freedesktop.org Reviewed-by: Louis Chauvet Link: https://patch.msgid.link/20251106073207.11192-1-tzimmermann@suse.de Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_vblank.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 61e211fd3c9c8..451ec96202266 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -2258,7 +2258,7 @@ int drm_crtc_vblank_start_timer(struct drm_crtc *crtc) EXPORT_SYMBOL(drm_crtc_vblank_start_timer); /** - * drm_crtc_vblank_start_timer - Cancels the given CRTC's vblank timer + * drm_crtc_vblank_cancel_timer - Cancels the given CRTC's vblank timer * @crtc: the CRTC * * Drivers should call this function from their CRTC's disable_vblank From 48fa96538bd2868034d33429e4565fda384d0736 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 20 May 2026 15:05:04 +0200 Subject: [PATCH 1165/1518] sysfs: don't remove existing directory on update failure commit 237557b8a81ab948e8332f7c0058e758f081c0a3 upstream. When sysfs_update_group() is called for a named group and create_files() fails (e.g. -ENOMEM), internal_create_group() calls kernfs_remove(kn) on the group directory. In the update path, kn was obtained via kernfs_find_and_get() and refers to a directory that already existed before this call. Removing it silently destroys a sysfs group that the caller did not create. Only remove the directory if we created it ourselves. On update failure the directory remains as it is left empty by remove_files() inside create_files(), but can be repopulated by a retry. Cc: Rajat Jain Fixes: c855cf2759d2 ("sysfs: Fix internal_create_group() for named group updates") Cc: stable Assisted-by: gkh_clanker_t1000 Reviewed-by: Rafael J. Wysocki (Intel) Reviewed-by: Danilo Krummrich Link: https://patch.msgid.link/2026052003-uniquely-hastily-c093@gregkh Signed-off-by: Greg Kroah-Hartman --- fs/sysfs/group.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index e142bac4f9f80..68c75913c9783 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -182,7 +182,7 @@ static int internal_create_group(struct kobject *kobj, int update, kernfs_get(kn); error = create_files(kn, kobj, uid, gid, grp, update); if (error) { - if (grp->name) + if (grp->name && !update) kernfs_remove(kn); } kernfs_put(kn); From 302e02f9ba49f81418ec2a749ae6f5cac1d424e9 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Sun, 26 Apr 2026 10:36:12 -0700 Subject: [PATCH 1166/1518] mm/damon/sysfs-schemes: call missing mem_cgroup_iter_break() commit d4e7b5c4cc353f154d5ab8bb2e1ce7714d77a6e9 upstream. damon_sysfs_memcg_path_to_id() breaks mem_cgroup_iter() loop without calling mem_cgroup_iter_break(). This leaks the cgroup reference. Fix the issue by calling mem_cgroup_iter_break() before the break. The issue was discovered [1] by Sashiko. Link: https://lore.kernel.org/20260426173625.86521-1-sj@kernel.org Link: https://lore.kernel.org/20260423004148.74722-1-sj@kernel.org [1] Fixes: 29cbb9a13f05 ("mm/damon/sysfs-schemes: implement scheme filters") Signed-off-by: SeongJae Park Cc: # 6.3.x Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/damon/sysfs-schemes.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index ca82dc78f0b98..a7be6ea812e47 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2444,6 +2444,7 @@ static int damon_sysfs_memcg_path_to_id(char *memcg_path, unsigned short *id) if (damon_sysfs_memcg_path_eq(memcg, path, memcg_path)) { *id = mem_cgroup_id(memcg); found = true; + mem_cgroup_iter_break(NULL, memcg); break; } } From cd5c1b75d2f454f625d7dc55bd3ae21d0855f6ad Mon Sep 17 00:00:00 2001 From: Jeremy Laratro Date: Wed, 13 May 2026 08:26:16 +0900 Subject: [PATCH 1167/1518] ksmbd: fix null pointer dereference in compare_guid_key() commit 4b83cbc4c15f09b000cc06f033f64b0824b6dc87 upstream. session_fd_check() walks the per-inode m_op_list during durable-handle session teardown and sets op->conn = NULL for every opinfo whose conn matched the closing session's connection. The matching opinfo, however, stays linked in its per-ClientGuid lease_table_list entry's lb->lease_list because destroy_lease_table() only runs on full TCP-connection teardown, not on SESSION_LOGOFF. If the same TCP connection then negotiates a fresh session with the same ClientGuid (ClientGuid is bound to NEGOTIATE, not the session, and is unchanged across LOGOFF + SETUP) and issues a SMB2 CREATE with a lease context on a different inode, find_same_lease_key() walks lb->lease_list, reaches the stale opinfo, and calls compare_guid_key(), which unconditionally dereferences opinfo->conn->ClientGUID. The conn pointer is NULL and the kernel panics. Reproducer requires only a successful SMB2 SESSION_SETUP and a share configured with 'durable handles = yes'. KASAN report on mainline 70390501d194: general protection fault, probably for non-canonical address 0xdffffc0000000069: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000348-0x000000000000034f] Workqueue: ksmbd-io handle_ksmbd_work RIP: 0010:bcmp+0x5b/0x230 Call Trace: compare_guid_key+0x4b/0xd0 find_same_lease_key+0x324/0x690 smb2_open+0x6aea/0x8e60 handle_ksmbd_work+0x796/0xee0 ... Faulting address 0x348 is the offset of ClientGUID within struct ksmbd_conn, confirming opinfo->conn was NULL. Read opinfo->conn once and bail out if it has been cleared by a concurrent session_fd_check(). A half-detached opinfo cannot be the owner of an active lease, so returning 0 is the correct match result. Fixes: c8efcc786146 ("ksmbd: add support for durable handles v1/v2") Cc: stable@vger.kernel.org Signed-off-by: Jeremy Laratro Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/oplock.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index bbb2cb3782d0c..a84c01bceb8ba 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -484,8 +484,12 @@ static inline int compare_guid_key(struct oplock_info *opinfo, const char *guid1, const char *key1) { const char *guid2, *key2; + struct ksmbd_conn *conn; - guid2 = opinfo->conn->ClientGUID; + conn = READ_ONCE(opinfo->conn); + if (!conn) + return 0; + guid2 = conn->ClientGUID; key2 = opinfo->o_lease->lease_key; if (!memcmp(guid1, guid2, SMB2_CLIENT_GUID_SIZE) && !memcmp(key1, key2, SMB2_LEASE_KEY_SIZE)) From 0e198f09cb2a554c04de0fea4e790f1250a943ca Mon Sep 17 00:00:00 2001 From: Ferry Meng Date: Mon, 11 May 2026 21:18:16 +0800 Subject: [PATCH 1168/1518] ksmbd: fix SID memory leak in set_posix_acl_entries_dacl() on overflow commit af92ee994cc7f7e83a41c2025f32257a2f82a7ef upstream. Commit 299f962c0b02 ("ksmbd: use check_add_overflow() to prevent u16 DACL size overflow") added check_add_overflow() guards that break out of the ACE-building loops in set_posix_acl_entries_dacl() when the accumulated DACL size would wrap past 65535. However, each iteration allocates a struct smb_sid via kmalloc_obj() at the top of the loop and relies on the kfree(sid) call at the end of the loop body (the 'pass_same_sid' label in the first loop, and the explicit kfree at the tail of the second loop) to release it. The newly introduced 'break' statements bypass those kfree() calls, leaking the sid buffer every time an overflow is detected. A malicious or malformed file with enough POSIX ACL entries to trip the overflow check will leak one or more struct smb_sid allocations on every request that touches the file's DACL, providing a trivial kernel memory exhaustion vector. Free sid before breaking out of the loops to plug the leak. Fixes: 299f962c0b02 ("ksmbd: use check_add_overflow() to prevent u16 DACL size overflow") Cc: stable@vger.kernel.org Signed-off-by: Ferry Meng Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/smbacl.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index a0e0dc56c7300..4ea489a79afa8 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -643,8 +643,10 @@ static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, ntace = (struct smb_ace *)((char *)pndace + *size); ace_sz = fill_ace_for_sid(ntace, sid, ACCESS_ALLOWED, flags, pace->e_perm, 0777); - if (check_add_overflow(*size, ace_sz, size)) + if (check_add_overflow(*size, ace_sz, size)) { + kfree(sid); break; + } (*num_aces)++; if (pace->e_tag == ACL_USER) ntace->access_req |= @@ -655,8 +657,10 @@ static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, ntace = (struct smb_ace *)((char *)pndace + *size); ace_sz = fill_ace_for_sid(ntace, sid, ACCESS_ALLOWED, 0x03, pace->e_perm, 0777); - if (check_add_overflow(*size, ace_sz, size)) + if (check_add_overflow(*size, ace_sz, size)) { + kfree(sid); break; + } (*num_aces)++; if (pace->e_tag == ACL_USER) ntace->access_req |= @@ -698,8 +702,10 @@ static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, ntace = (struct smb_ace *)((char *)pndace + *size); ace_sz = fill_ace_for_sid(ntace, sid, ACCESS_ALLOWED, 0x0b, pace->e_perm, 0777); - if (check_add_overflow(*size, ace_sz, size)) + if (check_add_overflow(*size, ace_sz, size)) { + kfree(sid); break; + } (*num_aces)++; if (pace->e_tag == ACL_USER) ntace->access_req |= From 18d8db24b0a5b7be4829238dd4022236df02d421 Mon Sep 17 00:00:00 2001 From: Junyi Liu Date: Tue, 19 May 2026 16:12:04 +0900 Subject: [PATCH 1169/1518] ksmbd: validate SID in parent security descriptor during ACL inheritance commit 69f030cf95488ae1186c72ac8c66fd279664ea7f upstream. Introduce smb_validate_ntsd_sid() helper to safely validate Owner SID and Group SID inside the NT Security Descriptor (smb_ntsd) retrieved from the parent directory. Cc: stable@vger.kernel.org Signed-off-by: Junyi Liu Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/smbacl.c | 66 ++++++++++++++++++++++++++++++++---------- 1 file changed, 50 insertions(+), 16 deletions(-) diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 4ea489a79afa8..6c4f9c8c7f130 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1096,6 +1096,40 @@ static int smb_append_inherited_ace(struct smb_ace **ace, int *nt_size, return 0; } +static int smb_validate_ntsd_sid(struct smb_ntsd *pntsd, size_t pntsd_size, + unsigned int sid_offset, struct smb_sid **sid, + size_t *sid_size) +{ + size_t sid_end; + + *sid = NULL; + *sid_size = 0; + + if (!sid_offset) + return 0; + + if (sid_offset < sizeof(struct smb_ntsd) || + check_add_overflow(sid_offset, (size_t)CIFS_SID_BASE_SIZE, + &sid_end) || + sid_end > pntsd_size) + return -EINVAL; + + *sid = (struct smb_sid *)((char *)pntsd + sid_offset); + if ((*sid)->num_subauth > SID_MAX_SUB_AUTHORITIES) + return -EINVAL; + + if (check_add_overflow((size_t)CIFS_SID_BASE_SIZE, + sizeof(__le32) * (size_t)(*sid)->num_subauth, + &sid_end)) + return -EINVAL; + + if (sid_offset > pntsd_size || sid_end > pntsd_size - sid_offset) + return -EINVAL; + + *sid_size = sid_end; + return 0; +} + int smb_inherit_dacl(struct ksmbd_conn *conn, const struct path *path, unsigned int uid, unsigned int gid) @@ -1108,28 +1142,28 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, struct dentry *parent = path->dentry->d_parent; struct mnt_idmap *idmap = mnt_idmap(path->mnt); int inherited_flags = 0, flags = 0, i, nt_size = 0, pdacl_size; - int rc = 0, pntsd_type, pntsd_size, acl_len, aces_size; + int rc = 0, pntsd_type, ppntsd_size, acl_len, aces_size; unsigned int dacloffset; size_t dacl_struct_end; u16 num_aces, ace_cnt = 0; char *aces_base; bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode); - pntsd_size = ksmbd_vfs_get_sd_xattr(conn, idmap, + ppntsd_size = ksmbd_vfs_get_sd_xattr(conn, idmap, parent, &parent_pntsd); - if (pntsd_size <= 0) + if (ppntsd_size <= 0) return -ENOENT; dacloffset = le32_to_cpu(parent_pntsd->dacloffset); if (!dacloffset || check_add_overflow(dacloffset, sizeof(struct smb_acl), &dacl_struct_end) || - dacl_struct_end > (size_t)pntsd_size) { + dacl_struct_end > (size_t)ppntsd_size) { rc = -EINVAL; goto free_parent_pntsd; } parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset); - acl_len = pntsd_size - dacloffset; + acl_len = ppntsd_size - dacloffset; num_aces = le16_to_cpu(parent_pdacl->num_aces); pntsd_type = le16_to_cpu(parent_pntsd->type); pdacl_size = le16_to_cpu(parent_pdacl->size); @@ -1243,19 +1277,19 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, struct smb_ntsd *pntsd; struct smb_acl *pdacl; struct smb_sid *powner_sid = NULL, *pgroup_sid = NULL; - int powner_sid_size = 0, pgroup_sid_size = 0, pntsd_size; + size_t powner_sid_size = 0, pgroup_sid_size = 0, pntsd_size; size_t pntsd_alloc_size; - if (parent_pntsd->osidoffset) { - powner_sid = (struct smb_sid *)((char *)parent_pntsd + - le32_to_cpu(parent_pntsd->osidoffset)); - powner_sid_size = 1 + 1 + 6 + (powner_sid->num_subauth * 4); - } - if (parent_pntsd->gsidoffset) { - pgroup_sid = (struct smb_sid *)((char *)parent_pntsd + - le32_to_cpu(parent_pntsd->gsidoffset)); - pgroup_sid_size = 1 + 1 + 6 + (pgroup_sid->num_subauth * 4); - } + rc = smb_validate_ntsd_sid(parent_pntsd, ppntsd_size, + le32_to_cpu(parent_pntsd->osidoffset), + &powner_sid, &powner_sid_size); + if (rc) + goto free_aces_base; + rc = smb_validate_ntsd_sid(parent_pntsd, ppntsd_size, + le32_to_cpu(parent_pntsd->gsidoffset), + &pgroup_sid, &pgroup_sid_size); + if (rc) + goto free_aces_base; if (check_add_overflow(sizeof(struct smb_ntsd), (size_t)powner_sid_size, From 6827647fd2dcf4e7f355478a42e82f51e0b5344c Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Mon, 18 May 2026 10:31:11 +0200 Subject: [PATCH 1170/1518] regulator: tps65219: fix irq_data.rdev not being assigned commit f9b2d3b703d13df50c630997dfdc25648e96db0d upstream. Commit 64a6b577490c ("regulator: tps65219: Remove debugging helper function") removed the tps65219_get_rdev_by_name() helper along with the irq_data.rdev assignment that depended on it. This left irq_data.rdev uninitialized for all IRQs, causing undefined behavior when regulator_notifier_call_chain() is called from the IRQ handler: Internal error: Oops: 0000000096000004 pc : regulator_notifier_call_chain lr : tps65219_regulator_irq_handler Call trace: regulator_notifier_call_chain tps65219_regulator_irq_handler handle_nested_irq regmap_irq_thread irq_thread_fn irq_thread kthread ret_from_fork Instead of restoring a dedicated lookup array, restructure the probe function to combine regulator registration with IRQ registration in the same loop. This way the rdev returned by devm_regulator_register() is naturally available for assigning to irq_data.rdev without any auxiliary data structure. Non-regulator IRQs (SENSOR, TIMEOUT) that don't correspond to any registered regulator are registered with rdev=NULL, and the IRQ handler is protected with a NULL check to avoid crashing. Cc: stable@vger.kernel.org Closes: https://lore.kernel.org/all/aBDSTxALaOc-PD7X@gaggiata.pivistrello.it/ Reported-by: Francesco Dolcini Fixes: 64a6b577490c ("regulator: tps65219: Remove debugging helper function") Signed-off-by: Alexander Sverdlin Link: https://patch.msgid.link/20260518083113.2063368-1-alexander.sverdlin@siemens.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/tps65219-regulator.c | 135 +++++++++++++++++-------- 1 file changed, 95 insertions(+), 40 deletions(-) diff --git a/drivers/regulator/tps65219-regulator.c b/drivers/regulator/tps65219-regulator.c index d77ca486879fd..324c3a33af8a4 100644 --- a/drivers/regulator/tps65219-regulator.c +++ b/drivers/regulator/tps65219-regulator.c @@ -346,8 +346,9 @@ static irqreturn_t tps65219_regulator_irq_handler(int irq, void *data) return IRQ_HANDLED; } - regulator_notifier_call_chain(irq_data->rdev, - irq_data->type->event, NULL); + if (irq_data->rdev) + regulator_notifier_call_chain(irq_data->rdev, + irq_data->type->event, NULL); dev_err(irq_data->dev, "Error IRQ trap %s for %s\n", irq_data->type->event_name, irq_data->type->regulator_name); @@ -398,14 +399,65 @@ static struct tps65219_chip_data chip_info_table[] = { }, }; -static int tps65219_regulator_probe(struct platform_device *pdev) +static bool tps65219_is_regulator_name(const struct tps65219_chip_data *pmic, + const char *name) +{ + int i; + + for (i = 0; i < pmic->common_rdesc_size; i++) + if (!strcmp(pmic->common_rdesc[i].name, name)) + return true; + for (i = 0; i < pmic->rdesc_size; i++) + if (!strcmp(pmic->rdesc[i].name, name)) + return true; + return false; +} + +static int tps65219_register_irqs(struct platform_device *pdev, + struct tps65219 *tps, + struct regulator_dev *rdev, + struct tps65219_regulator_irq_type *irq_types, + int nirqs, + const char *regulator_name) { struct tps65219_regulator_irq_data *irq_data; + int i, irq, error; + + for (i = 0; i < nirqs; i++) { + if (strcmp(irq_types[i].regulator_name, regulator_name)) + continue; + + irq = platform_get_irq_byname(pdev, irq_types[i].irq_name); + if (irq < 0) + return -EINVAL; + + irq_data = devm_kmalloc(tps->dev, sizeof(*irq_data), GFP_KERNEL); + if (!irq_data) + return -ENOMEM; + + irq_data->dev = tps->dev; + irq_data->type = &irq_types[i]; + irq_data->rdev = rdev; + + error = devm_request_threaded_irq(tps->dev, irq, NULL, + tps65219_regulator_irq_handler, + IRQF_ONESHOT, + irq_types[i].irq_name, + irq_data); + if (error) + return dev_err_probe(tps->dev, error, + "Failed to request %s IRQ %d\n", + irq_types[i].irq_name, irq); + } + return 0; +} + +static int tps65219_regulator_probe(struct platform_device *pdev) +{ struct tps65219_regulator_irq_type *irq_type; struct tps65219_chip_data *pmic; struct regulator_dev *rdev; int error; - int irq; int i; struct tps65219 *tps = dev_get_drvdata(pdev->dev.parent); @@ -425,6 +477,19 @@ static int tps65219_regulator_probe(struct platform_device *pdev) return dev_err_probe(tps->dev, PTR_ERR(rdev), "Failed to register %s regulator\n", pmic->common_rdesc[i].name); + + error = tps65219_register_irqs(pdev, tps, rdev, + pmic->common_irq_types, + pmic->common_irq_size, + pmic->common_rdesc[i].name); + if (error) + return error; + error = tps65219_register_irqs(pdev, tps, rdev, + pmic->irq_types, + pmic->dev_irq_size, + pmic->common_rdesc[i].name); + if (error) + return error; } for (i = 0; i < pmic->rdesc_size; i++) { @@ -434,52 +499,42 @@ static int tps65219_regulator_probe(struct platform_device *pdev) return dev_err_probe(tps->dev, PTR_ERR(rdev), "Failed to register %s regulator\n", pmic->rdesc[i].name); + + error = tps65219_register_irqs(pdev, tps, rdev, + pmic->common_irq_types, + pmic->common_irq_size, + pmic->rdesc[i].name); + if (error) + return error; + error = tps65219_register_irqs(pdev, tps, rdev, + pmic->irq_types, + pmic->dev_irq_size, + pmic->rdesc[i].name); + if (error) + return error; } + /* Register non-regulator IRQs (TIMEOUT, SENSOR) with rdev=NULL */ for (i = 0; i < pmic->common_irq_size; ++i) { irq_type = &pmic->common_irq_types[i]; - irq = platform_get_irq_byname(pdev, irq_type->irq_name); - if (irq < 0) - return -EINVAL; - - irq_data = devm_kmalloc(tps->dev, sizeof(*irq_data), GFP_KERNEL); - if (!irq_data) - return -ENOMEM; - - irq_data->dev = tps->dev; - irq_data->type = irq_type; - error = devm_request_threaded_irq(tps->dev, irq, NULL, - tps65219_regulator_irq_handler, - IRQF_ONESHOT, - irq_type->irq_name, - irq_data); + if (tps65219_is_regulator_name(pmic, irq_type->regulator_name)) + continue; + error = tps65219_register_irqs(pdev, tps, NULL, + irq_type, 1, + irq_type->regulator_name); if (error) - return dev_err_probe(tps->dev, error, - "Failed to request %s IRQ %d\n", - irq_type->irq_name, irq); + return error; } for (i = 0; i < pmic->dev_irq_size; ++i) { irq_type = &pmic->irq_types[i]; - irq = platform_get_irq_byname(pdev, irq_type->irq_name); - if (irq < 0) - return -EINVAL; - - irq_data = devm_kmalloc(tps->dev, sizeof(*irq_data), GFP_KERNEL); - if (!irq_data) - return -ENOMEM; - - irq_data->dev = tps->dev; - irq_data->type = irq_type; - error = devm_request_threaded_irq(tps->dev, irq, NULL, - tps65219_regulator_irq_handler, - IRQF_ONESHOT, - irq_type->irq_name, - irq_data); + if (tps65219_is_regulator_name(pmic, irq_type->regulator_name)) + continue; + error = tps65219_register_irqs(pdev, tps, NULL, + irq_type, 1, + irq_type->regulator_name); if (error) - return dev_err_probe(tps->dev, error, - "Failed to request %s IRQ %d\n", - irq_type->irq_name, irq); + return error; } return 0; From a8d17d22db591099519a89f14dd24810daba74c3 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Sun, 17 May 2026 20:11:50 -0400 Subject: [PATCH 1171/1518] smb: client: require net admin for CIFS SWN netlink commit d1ebfce2c1d161186a82e77590bf7da2ea1bce91 upstream. CIFS_GENL_CMD_SWN_NOTIFY is the userspace witness-notify command. The intended sender is the cifs.witness helper, but the generic-netlink operation currently has no capability flag, so any local process can send RESOURCE_CHANGE or CLIENT_MOVE notifications to the in-kernel witness handler. The same family exposes CIFS_GENL_MCGRP_SWN without multicast-group capability flags. Register messages sent to that group include the witness registration id and, for NTLM-authenticated mounts, the username, domain, and password attributes copied from the CIFS session. An unprivileged local process should not be able to join that group and receive those messages. Require CAP_NET_ADMIN for incoming SWN_NOTIFY commands with GENL_ADMIN_PERM, and require CAP_NET_ADMIN over the network namespace for joining the SWN multicast group with GENL_MCAST_CAP_NET_ADMIN. The cifs.witness service runs with the privileges needed for both operations. Fixes: fed979a7e082 ("cifs: Set witness notification handler for messages from userspace daemon") Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/netlink.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/netlink.c b/fs/smb/client/netlink.c index 147d9409252cd..0dd10913c37a0 100644 --- a/fs/smb/client/netlink.c +++ b/fs/smb/client/netlink.c @@ -33,13 +33,17 @@ static const struct nla_policy cifs_genl_policy[CIFS_GENL_ATTR_MAX + 1] = { static const struct genl_ops cifs_genl_ops[] = { { .cmd = CIFS_GENL_CMD_SWN_NOTIFY, + .flags = GENL_ADMIN_PERM, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = cifs_swn_notify, }, }; static const struct genl_multicast_group cifs_genl_mcgrps[] = { - [CIFS_GENL_MCGRP_SWN] = { .name = CIFS_GENL_MCGRP_SWN_NAME }, + [CIFS_GENL_MCGRP_SWN] = { + .name = CIFS_GENL_MCGRP_SWN_NAME, + .flags = GENL_MCAST_CAP_NET_ADMIN, + }, }; struct genl_family cifs_genl_family = { From bf4ebdb19ff9b3cdf992b50715fe61633327416a Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 14 May 2026 20:18:25 -0300 Subject: [PATCH 1172/1518] smb: client: protect tc_count increment in smb2_find_smb_sess_tcon_unlocked() commit 4d8690dace005a38e6dbde9ecce2da3ad85c7c41 upstream. Commit 96c4af418586 ("cifs: Fix locking usage for tcon fields") refactored cifs code to change cifs_tcp_ses_lock for tc_lock around tc_count changes. There was missing lock around tc_count increment inside smb2_find_smb_sess_tcon_unlocked(). Cc: stable@vger.kernel.org Fixes: 96c4af418586 ("cifs: Fix locking usage for tcon fields") Reviewed-by: Shyam Prasad N Signed-off-by: Henrique Carvalho Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/smb2transport.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index db98ced541baa..7483b29367d5a 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -176,7 +176,9 @@ smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid) list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != tid) continue; + spin_lock(&tcon->tc_lock); ++tcon->tc_count; + spin_unlock(&tcon->tc_lock); trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, netfs_trace_tcon_ref_get_find_sess_tcon); return tcon; From d65104a4a81573994be43718f10e1c18110b9e07 Mon Sep 17 00:00:00 2001 From: Jeremy Erazo Date: Fri, 15 May 2026 19:31:41 +0000 Subject: [PATCH 1173/1518] smb: client: use data_len for SMB2 READ encrypted folioq copy commit d4d76c9ee1997cc8c977a63f6c43551c253c1066 upstream. In handle_read_data() the encrypted/folioq branch (buf_len <= data_offset, reached via receive_encrypted_read for transform PDUs > CIFSMaxBufSize + MAX_HEADER_SIZE) copies the READ payload using buffer_len rather than data_len: rdata->result = cifs_copy_folioq_to_iter(buffer, buffer_len, cur_off, &rdata->subreq.io_iter); ... rdata->got_bytes = buffer_len; buffer_len comes from the SMB3 transform header OriginalMessageSize field (OriginalMessageSize - read_rsp_size); it represents the size of the decrypted message after the SMB2 header. data_len comes from the SMB2 READ response DataLength field; it represents the actual READ payload size and may be smaller than buffer_len when the decrypted message contains padding or other trailing bytes after the READ payload. The existing check `data_len > buffer_len - pad_len` only enforces an upper bound, so a server that emits OriginalMessageSize larger than read_rsp_size + pad_len + data_len passes the check and the kernel copies buffer_len bytes per response, ignoring the server-asserted DataLength. Two observable failures with a crafted server (DataLength=4, buffer_len=20000): - the kernel returns 20000 bytes per sub-request to userspace and sets got_bytes = buffer_len, even though the response claimed only 4 bytes of payload; - on a partial netfs sub-request whose iterator is sized to data_len, the over-large copy_folio_to_iter() short-reads, cifs_copy_folioq_to_iter() returns -EIO via the n != len path, and the entire netfs read collapses to -EIO even though the leading sub-requests succeeded. Use data_len for the copy length and for got_bytes so the kernel honours the server-asserted READ payload size. For well-formed servers (where buffer_len == pad_len + data_len) the change is behaviour-equivalent. Cc: stable@vger.kernel.org Signed-off-by: Jeremy Erazo Acked-by: David Howells Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/smb2ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index eed3a71171c0b..e1a9e89cb85fe 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4842,7 +4842,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, } /* Copy the data to the output I/O iterator. */ - rdata->result = cifs_copy_folioq_to_iter(buffer, buffer_len, + rdata->result = cifs_copy_folioq_to_iter(buffer, data_len, cur_off, &rdata->subreq.io_iter); if (rdata->result != 0) { if (is_offloaded) @@ -4851,7 +4851,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, dequeue_mid(mid, rdata->result); return 0; } - rdata->got_bytes = buffer_len; + rdata->got_bytes = data_len; } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ From 9803e75c9813a7cbebb258e47719ed9055b708ef Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Mon, 18 May 2026 15:23:22 +0000 Subject: [PATCH 1174/1518] smb/server: promote S_DEL_ON_CLS to S_DEL_PENDING when close commit 4ec9c8e023c79f613fe4d5ad8cc737112efb2e44 upstream. Reproducer: 1. server: systemctl start ksmbd 2. client: mount -t cifs //${server_ip}/export /mnt 3. client: C program: openat(AT_FDCWD, "/mnt", O_RDWR | O_TMPFILE, 0600) Do not treat `FILE_DELETE_ON_CLOSE_LE` as delete pending while files remain open. This patch fixes xfstests generic/004. Cc: stable@vger.kernel.org Link: https://chenxiaosong.com/en/smb-xfstests-generic-004.html Co-developed-by: Huiwen He Signed-off-by: Huiwen He Signed-off-by: ChenXiaoSong Tested-by: Steve French Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/vfs_cache.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index a8fed467e9b69..7293b7effbc14 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -118,7 +118,7 @@ int ksmbd_query_inode_status(struct dentry *dentry) return ret; down_read(&ci->m_lock); - if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) + if (ci->m_flags & S_DEL_PENDING) ret = KSMBD_INODE_STATUS_PENDING_DELETE; else ret = KSMBD_INODE_STATUS_OK; @@ -134,7 +134,7 @@ bool ksmbd_inode_pending_delete(struct ksmbd_file *fp) int ret; down_read(&ci->m_lock); - ret = (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)); + ret = (ci->m_flags & S_DEL_PENDING); up_read(&ci->m_lock); return ret; @@ -302,12 +302,20 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) } } + down_write(&ci->m_lock); + /* Promote S_DEL_ON_CLS to S_DEL_PENDING when close */ + if (ci->m_flags & S_DEL_ON_CLS) { + ci->m_flags &= ~S_DEL_ON_CLS; + ci->m_flags |= S_DEL_PENDING; + } + up_write(&ci->m_lock); + if (atomic_dec_and_test(&ci->m_count)) { bool do_unlink = false; down_write(&ci->m_lock); - if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { - ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); + if (ci->m_flags & S_DEL_PENDING) { + ci->m_flags &= ~S_DEL_PENDING; do_unlink = true; } up_write(&ci->m_lock); From ca560f7566df7e2826c2999e959e6b94eb938f76 Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Fri, 15 May 2026 15:11:48 -0700 Subject: [PATCH 1175/1518] hwmon: (pmbus/adm1266) widen blackbox-info buffer to I2C_SMBUS_BLOCK_MAX commit eee213daa1e1b402eb631bcd1b8c5aa340a6b081 upstream. adm1266_nvmem_read_blackbox() declares a 5-byte stack buffer and passes it to i2c_smbus_read_block_data() to retrieve the 4-byte BLACKBOX_INFO response. i2c_smbus_read_block_data() does not honour caller buffer sizes -- it memcpy()s data.block[0] bytes from the SMBus transaction (where data.block[0] is the length byte returned by the slave device, up to I2C_SMBUS_BLOCK_MAX = 32): memcpy(values, &data.block[1], data.block[0]); If the device returns any block length above 5, the call overflows the caller's 5-byte stack buffer before the post-call if (ret != 4) return -EIO; check has a chance to reject the response. Widen the local buffer to I2C_SMBUS_BLOCK_MAX so the helper has room for any well-formed SMBus block response, matching the convention used by the other i2c_smbus_read_block_data() callers in this driver. Fixes: 15609d189302 ("hwmon: (pmbus/adm1266) read blackbox") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Link: https://lore.kernel.org/r/20260515-adm1266-fixes-v1-2-1c1ea1349cfe@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index d90f8f80be8e0..5348feefd1e64 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -349,7 +349,7 @@ static int adm1266_nvmem_read_blackbox(struct adm1266_data *data, u8 *read_buff) { int record_count; char index; - u8 buf[5]; + u8 buf[I2C_SMBUS_BLOCK_MAX]; int ret; ret = i2c_smbus_read_block_data(data->client, ADM1266_BLACKBOX_INFO, buf); From cba8dab72e9b480f6bc07d83974afb1648c6573f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Tue, 19 May 2026 00:32:15 -0300 Subject: [PATCH 1176/1518] ALSA: ua101: Reject too-short USB descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b59d5c51bb328a60749b4dd5fe7e649bfb4089b4 upstream. find_format_descriptor() walks the class-specific interface extras by advancing with bLength. It rejects descriptors that extend past the remaining buffer, but it does not reject descriptor lengths smaller than a USB descriptor header. Reject too-short descriptors before using bLength to advance the local scan. This keeps the UA-101 parser robust against malformed descriptor data and matches the usual USB descriptor walking rules. Fixes: 63978ab3e3e9 ("sound: add Edirol UA-101 support") Cc: stable@vger.kernel.org Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260519-alsa-ua101-desc-len-v1-1-4307d1a5e054@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/misc/ua101.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c index 99e98b5e3241f..586ef13097a31 100644 --- a/sound/usb/misc/ua101.c +++ b/sound/usb/misc/ua101.c @@ -894,8 +894,9 @@ find_format_descriptor(struct usb_interface *interface) struct uac_format_type_i_discrete_descriptor *desc; desc = (struct uac_format_type_i_discrete_descriptor *)extra; - if (desc->bLength > extralen) { - dev_err(&interface->dev, "descriptor overflow\n"); + if (desc->bLength < sizeof(struct usb_descriptor_header) || + desc->bLength > extralen) { + dev_err(&interface->dev, "invalid descriptor length\n"); return NULL; } if (desc->bLength == UAC_FORMAT_TYPE_I_DISCRETE_DESC_SIZE(1) && From feff0251386aa6bb180a0a1cf7c1f91ba868113d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 17 May 2026 18:51:20 +0200 Subject: [PATCH 1177/1518] ALSA: pcm: Don't setup bogus iov_iter for silencing commit e4d3386b74fba8e01280484b67ee481ece00201e upstream. At transition to the iov_iter for PCM data transfer, we blindly applied the iov_iter setup also for silencing (i.e. data = NULL), and it leads to a calculation of bogus iov_iter. Fortunately this didn't cause troubles on most of architectures but it goes wrong on RISC-V now, causing a NULL dereference. Handle the NULL data case to treat the silencing in interleaved_copy() for addressing the bug above. noninterleaved_copy() has already the NULL data handling, so it doesn't need changes. Reported-by: Jiakai Xu Closes: https://lore.kernel.org/20260515051516.3103036-1-xujiakai24@mails.ucas.ac.cn Fixes: cf393babb37a ("ALSA: pcm: Add copy ops with iov_iter") Cc: Link: https://patch.msgid.link/20260517165121.31399-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_lib.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6eaa950504cfc..932b9337c93ee 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2138,6 +2138,9 @@ static int interleaved_copy(struct snd_pcm_substream *substream, off = frames_to_bytes(runtime, off); frames = frames_to_bytes(runtime, frames); + if (!data) + return fill_silence(substream, 0, hwoff, NULL, frames); + return do_transfer(substream, 0, hwoff, data + off, frames, transfer, in_kernel); } From 61c5017c64e2ac9e10b70b14b17a079dbc0a805f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 15 May 2026 10:55:58 +0200 Subject: [PATCH 1178/1518] ALSA: asihpi: Fix potential OOB array access at reading cache commit 7b7d6572145c1dab2dd9bfb550b188e5f0ff3c3f upstream. find_control() to retrieve a cached info accesses the array with the given index blindly, which may lead to an OOB array access. Add a sanity check for avoiding it. Link: https://sashiko.dev/#/patchset/20260511230121.28606-1-rosenp%40gmail.com Cc: Link: https://patch.msgid.link/20260515085606.242284-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/asihpi/hpicmn.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sound/pci/asihpi/hpicmn.c b/sound/pci/asihpi/hpicmn.c index 7d1abaedb46ac..f06f44b13d3d2 100644 --- a/sound/pci/asihpi/hpicmn.c +++ b/sound/pci/asihpi/hpicmn.c @@ -276,6 +276,12 @@ static short find_control(u16 control_index, return 0; } + if (control_index >= p_cache->control_count) { + HPI_DEBUG_LOG(VERBOSE, "control_index out of bounce %d\n", + control_index); + return 0; + } + *pI = p_cache->p_info[control_index]; if (!*pI) { HPI_DEBUG_LOG(VERBOSE, "Uncached Control %d\n", From fcbd0a5fd812e9c19733de1a3c271e5b4aa8b06f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Tue, 19 May 2026 11:46:19 -0300 Subject: [PATCH 1179/1518] ALSA: scarlett2: Allow flash writes ending at segment boundary MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a69b677e47a80319ce148d61cc29a2b57006e78d upstream. scarlett2_hwdep_write() rejects writes when offset + count is greater than or equal to the selected flash segment size. That incorrectly treats a write ending exactly at the end of the segment as out of space, although the last byte written is still within the segment. Split invalid argument checks from the segment-space check, keep zero-length writes as no-ops, and compare count against the remaining segment size. This permits exact-end writes and avoids relying on offset + count before deciding whether the request is in bounds. Fixes: 1abfbd3c9527 ("ALSA: scarlett2: Add support for uploading new firmware") Cc: stable@vger.kernel.org Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260519-alsa-scarlett2-flash-write-boundary-v1-1-b550480e92da@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/mixer_scarlett2.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index a75a4610663e9..d0cad1d1efa35 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -9186,12 +9186,15 @@ static long scarlett2_hwdep_write(struct snd_hwdep *hw, flash_size = private->flash_segment_blocks[segment_id] * SCARLETT2_FLASH_BLOCK_SIZE; - if (count < 0 || *offset < 0 || *offset + count >= flash_size) - return -ENOSPC; + if (count < 0 || *offset < 0) + return -EINVAL; if (!count) return 0; + if (*offset >= flash_size || count > flash_size - *offset) + return -ENOSPC; + /* Limit the *req size to SCARLETT2_FLASH_RW_MAX */ if (count > max_data_size) count = max_data_size; From c32a1fbe0f9a48453a552bb315cc4f1e7a74084e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 19 May 2026 10:03:00 +0200 Subject: [PATCH 1180/1518] efi: Allocate runtime workqueue before ACPI init commit 13c6da02e767152c9ac4330962247a5e47011035 upstream. Since commit 5894cf571e14 ("acpi/prmt: Use EFI runtime sandbox to invoke PRM handlers") ACPI PRM calls are delegated to a workqueue which runs in a kernel thread, making it easier to detect and mitigate faulting memory accesses performed by the firmware. Rafael reports that such PRM accesses may occur before efisubsys_init() executes, which is where the workqueue is allocated, leading to NULL pointer dereferences. Since acpi_init() [which triggers the early PRM accesses] executes as a subsys_initcall() as well, and has its own dependencies that may be sensitive to initcall ordering, deferring acpi_init() is not an option. So instead, split off the workqueue allocation into its own postcore initcall, as this is the only missing piece to allow EFI runtime calls to be made. This ensures that EFI runtime call (including PRM calls) are accessible to all code running at subsys_initcall() level. Cc: Fixes: 5894cf571e14 ("acpi/prmt: Use EFI runtime sandbox to invoke PRM handlers") Reviewed-by: Rafael J. Wysocki (Intel) Signed-off-by: Ard Biesheuvel Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/efi/efi.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index c3cf5541ed682..c27fe836c8aec 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -401,21 +401,11 @@ static void __init efi_debugfs_init(void) static inline void efi_debugfs_init(void) {} #endif -/* - * We register the efi subsystem with the firmware subsystem and the - * efivars subsystem with the efi subsystem, if the system was booted with - * EFI. - */ -static int __init efisubsys_init(void) +static int __init efipostcore_init(void) { - int error; - if (!efi_enabled(EFI_RUNTIME_SERVICES)) efi.runtime_supported_mask = 0; - if (!efi_enabled(EFI_BOOT)) - return 0; - if (efi.runtime_supported_mask) { /* * Since we process only one efi_runtime_service() at a time, an @@ -427,9 +417,23 @@ static int __init efisubsys_init(void) pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n"); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); efi.runtime_supported_mask = 0; - return 0; } } + return 0; +} +postcore_initcall(efipostcore_init); + +/* + * We register the efi subsystem with the firmware subsystem and the + * efivars subsystem with the efi subsystem, if the system was booted with + * EFI. + */ +static int __init efisubsys_init(void) +{ + int error; + + if (!efi_enabled(EFI_BOOT)) + return 0; if (efi_rt_services_supported(EFI_RT_SUPPORTED_TIME_SERVICES)) platform_device_register_simple("rtc-efi", 0, NULL, 0); From 5fb947ddae55f82358967aa620679f572572f844 Mon Sep 17 00:00:00 2001 From: Krishnamoorthi M Date: Thu, 7 May 2026 23:30:51 +0530 Subject: [PATCH 1181/1518] spi: amd: Set correct bus number in ACPI probe path commit 422bd00b71ab42163aa3b8f8370276fe4c1581e7 upstream. On platforms where the HID2 SPI controller (AMDI0063) is enumerated via ACPI instead of PCI, amd_spi_probe() unconditionally sets bus_num to 0, while the PCI probe path assigns bus_num 2 for HID2 controller. Align the ACPI probe path to use the same bus number so that userspace and SPI client drivers see a consistent bus assignment regardless of the enumeration method. Fixes: b644c2776652 ("spi: spi_amd: Add PCI-based driver for AMD HID2 SPI controller") Cc: stable@vger.kernel.org # v6.16+ Signed-off-by: Krishnamoorthi M Link: https://patch.msgid.link/20260507180051.4158674-1-krishnamoorthi.m@amd.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c index 4d1dce4f49740..71a6e5c475b03 100644 --- a/drivers/spi/spi-amd.c +++ b/drivers/spi/spi-amd.c @@ -868,7 +868,7 @@ static int amd_spi_probe(struct platform_device *pdev) dev_dbg(dev, "io_remap_address: %p\n", amd_spi->io_remap_addr); amd_spi->version = (uintptr_t)device_get_match_data(dev); - host->bus_num = 0; + host->bus_num = (amd_spi->version == AMD_HID2_SPI) ? 2 : 0; return amd_spi_probe_common(dev, host); } From b737c6612c60c23b40a9f31749b99e6f61943847 Mon Sep 17 00:00:00 2001 From: Heechan Kang Date: Sun, 17 May 2026 03:47:09 +0900 Subject: [PATCH 1182/1518] io_uring/waitid: clear waitid info before copying it to userspace commit 93d93f5f8da791e98159795c6ef683f45bd95d13 upstream. IORING_OP_WAITID stores its result fields in struct io_waitid::info and later copies them to userspace siginfo. The prep path initializes the request arguments, but it does not initialize info itself. If the wait operation completes without reporting a child event, the common wait code can return without writing wo_info. In that case io_waitid_finish() still copies iw->info to userspace, exposing stale bytes from the reused io_kiocb command storage. Clear the result storage during prep so the io_uring path matches the regular waitid syscall, which uses a zero-initialized struct waitid_info. Fixes: f31ecf671ddc ("io_uring: add IORING_OP_WAITID support") Cc: stable@vger.kernel.org # 6.7+ Signed-off-by: Heechan Kang Link: https://patch.msgid.link/20260516184709.852814-1-gganji11@naver.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/waitid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 53532ae6256ca..921b4de3a31cb 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -258,6 +258,7 @@ int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) iw->upid = READ_ONCE(sqe->fd); iw->options = READ_ONCE(sqe->file_index); iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + memset(&iw->info, 0, sizeof(iw->info)); return 0; } From 24840b3139d7415144b81e4f9f4c44670d15bed9 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 28 Apr 2026 16:52:18 +0800 Subject: [PATCH 1183/1518] drivers/base/memory: fix memory block reference leak in poison accounting commit 03a2cc1756a0570f887d624cd6c535ea0cbd4951 upstream. memblk_nr_poison_inc() and memblk_nr_poison_sub() look up a memory block via find_memory_block_by_id(), which acquires a reference to the memory block device. Both helpers use the returned memory block without dropping that reference, leaking the device reference on each successful lookup. Drop the reference after updating nr_hwpoison. Link: https://lore.kernel.org/20260428085219.1316047-3-songmuchun@bytedance.com Fixes: 5033091de814 ("mm/hwpoison: introduce per-memory_block hwpoison counter") Signed-off-by: Muchun Song Reviewed-by: Miaohe Lin Acked-by: Oscar Salvador Acked-by: David Hildenbrand (Arm) Cc: Danilo Krummrich Cc: Greg Kroah-Hartman Cc: "Huang, Ying" Cc: Naoya Horiguchi Cc: "Rafael J. Wysocki" Cc: Vishal Verma Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/base/memory.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 6d84a02cfa5dc..0ecb43556736b 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -1251,8 +1251,10 @@ void memblk_nr_poison_inc(unsigned long pfn) const unsigned long block_id = pfn_to_block_id(pfn); struct memory_block *mem = find_memory_block_by_id(block_id); - if (mem) + if (mem) { atomic_long_inc(&mem->nr_hwpoison); + put_device(&mem->dev); + } } void memblk_nr_poison_sub(unsigned long pfn, long i) @@ -1260,8 +1262,10 @@ void memblk_nr_poison_sub(unsigned long pfn, long i) const unsigned long block_id = pfn_to_block_id(pfn); struct memory_block *mem = find_memory_block_by_id(block_id); - if (mem) + if (mem) { atomic_long_sub(i, &mem->nr_hwpoison); + put_device(&mem->dev); + } } static unsigned long memblk_nr_poison(struct memory_block *mem) From 24de676da63c1122d2c13b0d546238b66d1b4e62 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Wed, 20 May 2026 14:42:42 +0200 Subject: [PATCH 1184/1518] ipv6: ioam: refresh hdr pointer before ioam6_event() commit e46e6bc97fb1f339730ff1ba74267fbf48e7a422 upstream. Reported by Sashiko: In ipv6_hop_ioam(), the hdr pointer is initialized to point into the skb's linear data buffer. Later, the code calls skb_ensure_writable(), which might reallocate the buffer: if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) goto drop; /* Trace pointer may have changed */ trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + optoff + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); ioam6_event(IOAM6_EVENT_TRACE, dev_net(skb->dev), GFP_ATOMIC, (void *)trace, hdr->opt_len - 2); If the skb is cloned or lacks sufficient linear headroom, skb_ensure_writable() will invoke pskb_expand_head(), which reallocates the skb's data buffer and frees the old one, invalidating pointers to it. While the code recalculates the trace pointer immediately after the call to skb_ensure_writable(), it fails to recalculate the hdr pointer. This patch fixes the above by recalculating the hdr pointer before passing hdr->opt_len to ioam6_event(), so that we avoid any UaF. Fixes: f655c78d6225 ("net: exthdrs: ioam6: send trace event") Cc: stable@vger.kernel.org Signed-off-by: Justin Iurman Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260520124242.32320-1-justin.iurman@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/exthdrs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index ec03bcff6b65e..9b4ea568b8d7b 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -955,9 +955,9 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) goto drop; - /* Trace pointer may have changed */ - trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) - + optoff + sizeof(*hdr)); + /* Trace and hdr pointers may have changed */ + hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); + trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); From 2fff0cdd942261497fb8922a194b4da3315ae864 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Fri, 1 May 2026 16:51:16 +1000 Subject: [PATCH 1185/1518] mm/memory: fix spurious warning when unmapping device-private/exclusive pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit be3f38d05cc5a7c3f13e51994c5dd043ab604d28 upstream. Device private and exclusive entries are only supported for anonymous folios. This condition is tested in __migrate_device_pages() and make_device_exclusive() using folio_test_anon(). However the unmap path tests this assumption using vma_is_anonymous(). This is wrong because whilst anonymous VMAs can only contain folios where folio_test_anon() is true the opposite relation does not hold. A folio for which folio_test_anon() is true does not imply vma_is_anonymous() is true. Such a condition can occur if for example a folio is part of a private filebacked mapping. In this case vma_is_anonymous() is false as the mapping is filebacked, but folio_test_anon() may be true, thus permitting devices to migrate the folio to device private memory. This can lead to the following spurious warnings during process teardown: [ 772.737706] ------------[ cut here ]------------ [ 772.739201] WARNING: mm/memory.c:1754 at unmap_page_range.cold+0x26/0x18a, CPU#17: hmm-tests/2041 [ 772.742050] Modules linked in: test_hmm nvidia_uvm(O) nvidia(O) [ 772.743959] CPU: 17 UID: 0 PID: 2041 Comm: hmm-tests Tainted: G W O 7.0.0+ #387 PREEMPT(full) [ 772.747104] Tainted: [W]=WARN, [O]=OOT_MODULE [ 772.748509] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 772.752117] RIP: 0010:unmap_page_range.cold+0x26/0x18a [ 772.753780] Code: 7e fe ff ff 48 89 4c 24 78 4c 89 44 24 38 e8 f2 ff b1 00 48 8b 4c 24 78 4c 8b 44 24 38 48 8b 44 24 18 48 83 78 48 00 74 04 90 <0f> 0b 90 48 89 ca b8 ff ff 37 00 48 c1 ea 03 48 c1 e0 2a 80 3c 02 [ 772.759602] RSP: 0018:ffff888112607550 EFLAGS: 00010286 [ 772.761310] RAX: ffff88811bbf4dc0 RBX: dffffc0000000000 RCX: ffffea03e9bfffd8 [ 772.763583] RDX: 1ffff1102377e9c1 RSI: 0000000000000008 RDI: ffff88811bbf4e08 [ 772.765914] RBP: 0000000000000006 R08: ffff8881059f7448 R09: ffffed10224c0e68 [ 772.768184] R10: ffff888112607347 R11: 0000000000000001 R12: 0000000000000001 [ 772.770461] R13: ffffea03e9bfffc0 R14: ffff888112607908 R15: ffffea03e9bfffc0 [ 772.772782] FS: 00007f327caa2780(0000) GS:ffff888427b7d000(0000) knlGS:0000000000000000 [ 772.775328] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 772.777187] CR2: 00007f327ca89000 CR3: 00000001994d5000 CR4: 00000000000006f0 [ 772.779135] Call Trace: [ 772.779792] [ 772.780317] ? dmirror_interval_invalidate+0x1a3/0x290 [test_hmm] [ 772.781873] ? vm_normal_page_pud+0x2b0/0x2b0 [ 772.782992] ? __rwlock_init+0x150/0x150 [ 772.784006] ? lock_release+0x216/0x2b0 [ 772.785008] ? __mmu_notifier_invalidate_range_start+0x505/0x6e0 [ 772.786522] ? lock_release+0x216/0x2b0 [ 772.787498] ? unmap_single_vma+0xb6/0x210 [ 772.788573] unmap_vmas+0x27d/0x520 [ 772.789506] ? unmap_single_vma+0x210/0x210 [ 772.790607] ? mas_update_gap.part.0+0x620/0x620 [ 772.791834] unmap_region+0x19e/0x350 [ 772.792769] ? remove_vma+0x130/0x130 [ 772.793684] ? mas_alloc_nodes+0x1f2/0x300 [ 772.794730] vms_complete_munmap_vmas+0x8c1/0xe20 [ 772.795926] ? unmap_region+0x350/0x350 [ 772.796917] do_vmi_align_munmap+0x36a/0x4e0 [ 772.798018] ? lock_release+0x216/0x2b0 [ 772.799024] ? vma_shrink+0x620/0x620 [ 772.799983] do_vmi_munmap+0x150/0x2c0 [ 772.800939] __vm_munmap+0x161/0x2c0 [ 772.801872] ? expand_downwards+0xd60/0xd60 [ 772.802948] ? clockevents_program_event+0x1ef/0x540 [ 772.804217] ? lock_release+0x216/0x2b0 [ 772.805158] __x64_sys_munmap+0x59/0x80 [ 772.805776] do_syscall_64+0xfc/0x670 [ 772.806336] ? irqentry_exit+0xda/0x580 [ 772.806976] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 772.807772] RIP: 0033:0x7f327cbb2717 [ 772.808323] Code: 73 01 c3 48 8b 0d f9 76 0d 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 b8 0b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c9 76 0d 00 f7 d8 64 89 01 48 [ 772.811337] RSP: 002b:00007ffde7f57d38 EFLAGS: 00000202 ORIG_RAX: 000000000000000b [ 772.812564] RAX: ffffffffffffffda RBX: 00007f327cc9c000 RCX: 00007f327cbb2717 [ 772.813733] RDX: 0000000000000000 RSI: 0000000000400000 RDI: 00007f327c289000 [ 772.814867] RBP: 0000000000421360 R08: 000000000000001a R09: 0000000000000000 [ 772.815991] R10: 0000000000000003 R11: 0000000000000202 R12: 00007ffde7f57d74 [ 772.817121] R13: 00007f327c689010 R14: 0000000000100000 R15: 00007f327c289000 [ 772.818272] [ 772.818614] irq event stamp: 0 [ 772.819159] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [ 772.820174] hardirqs last disabled at (0): [] copy_process+0x19f3/0x6440 [ 772.821511] softirqs last enabled at (0): [] copy_process+0x1a40/0x6440 [ 772.822869] softirqs last disabled at (0): [<0000000000000000>] 0x0 [ 772.823871] ---[ end trace 0000000000000000 ]--- Fix this by using the same check for folio_test_anon() in zap_nonpresent_ptes(). Also add a hmm-test case for this. Link: https://lore.kernel.org/20260501065116.2057242-1-apopple@nvidia.com Fixes: 999dad824c39 ("mm/shmem: persist uffd-wp bit across zapping for file-backed") Signed-off-by: Alistair Popple Reported-by: Arsen Arsenović Reviewed-by: Balbir Singh Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: John Hubbard Cc: Leon Romanovsky Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Peter Xu Cc: Matthew Brost Cc: Michal Hocko Cc: Mike Rapoport Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Thomas Hellström Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/memory.c | 2 +- tools/testing/selftests/mm/hmm-tests.c | 50 ++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 94bf107a47caf..bc6e483fc6a60 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1735,7 +1735,7 @@ static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, * consider uffd-wp bit when zap. For more information, * see zap_install_uffd_wp_if_needed(). */ - WARN_ON_ONCE(!vma_is_anonymous(vma)); + WARN_ON_ONCE(!folio_test_anon(folio)); rss[mm_counter(folio)]--; folio_remove_rmap_pte(folio, page, vma); folio_put(folio); diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 15aadaf24a667..c13b779bf1184 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -998,6 +998,56 @@ TEST_F(hmm, migrate) hmm_buffer_free(buffer); } +/* + * Migrate private file memory to device private memory. + */ +TEST_F(hmm, migrate_file_private) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + int fd; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + fd = hmm_create_file(size); + ASSERT_GE(fd, 0); + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = fd; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + hmm_buffer_free(buffer); +} + /* * Migrate anonymous memory to device private memory and fault some of it back * to system memory, then try migrating the resulting mix of system and device From 62153767e8fc3889bc6508e9ffe927aaf64c4334 Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Thu, 30 Apr 2026 13:31:22 +0200 Subject: [PATCH 1186/1518] mm: fix __vm_normal_page() to handle missing support for pmd_special()/pud_special() commit c0c6ccd9828c3a1950623b546fa57292a77b5c73 upstream. On x86 32-bit with THP enabled, zap_huge_pmd() is seen to generate a "WARNING: mm/memory.c:735 at __vm_normal_page+0x6a/0x7d", from the VM_WARN_ON_ONCE(is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)); followed by "BUG: Bad rss-counter state"s, then later "BUG: Bad page state"s when reclaim gets to call shrink_huge_zero_folio_scan(). It's as if the _PAGE_SPECIAL bit never got set in the huge_zero pmd: and indeed, whereas pte_special() and pte_mkspecial() are subject to a dedicated CONFIG_ARCH_HAS_PTE_SPECIAL, pmd_special() and pmd_mkspecial() are subject to CONFIG_ARCH_SUPPORTS_PMD_PFNMAP, which is never enabled on any 32-bit architecture. While the problem was exposed through commit d80a9cb1a64a ("mm/huge_memory: add and use normal_or_softleaf_folio_pmd()"), it was an oversight in commit af38538801c6 ("mm/memory: factor out common code from vm_normal_page_*()") and would result in other problems: * huge zero folio accounted in smaps, pagemap (PAGE_IS_FILE) and numamaps as file-backed THP * folio_walk_start() returning the folio even without FW_ZEROPAGE set. Callers seem to tolerate that, though. ... and triggering the VM_WARN_ON_ONE(), although never reported so far. To fix it, teach vm_normal_page_pmd()/vm_normal_page_pud() to consider whether pmd_special/pud_special is actually implemented. Link: https://lore.kernel.org/20260430-pmd_special-v1-1-dbcbcfd72c20@kernel.org Fixes: af38538801c6 ("mm/memory: factor out common code from vm_normal_page_*()") Signed-off-by: David Hildenbrand (Arm) Reported-by: Hugh Dickins Closes: https://lore.kernel.org/r/74a75b59-2e13-3985-ee99-d5521f39df2a@google.com Reported-by: Bibo Mao Closes: https://lore.kernel.org/r/20260430041121.2839350-1-maobibo@loongson.cn Debugged-by: Hugh Dickins Reviewed-by: Lance Yang Tested-by: Bibo Mao Reviewed-by: Baolin Wang Reviewed-by: Oscar Salvador Reviewed-by: Lorenzo Stoakes Cc: Liam R. Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/memory.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index bc6e483fc6a60..42b733b785236 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -612,6 +612,21 @@ static void print_bad_page_map(struct vm_area_struct *vma, dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } + +static inline bool pgtable_level_has_pxx_special(enum pgtable_level level) +{ + switch (level) { + case PGTABLE_LEVEL_PTE: + return IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL); + case PGTABLE_LEVEL_PMD: + return IS_ENABLED(CONFIG_ARCH_SUPPORTS_PMD_PFNMAP); + case PGTABLE_LEVEL_PUD: + return IS_ENABLED(CONFIG_ARCH_SUPPORTS_PUD_PFNMAP); + default: + return false; + } +} + #define print_bad_pte(vma, addr, pte, page) \ print_bad_page_map(vma, addr, pte_val(pte), page, PGTABLE_LEVEL_PTE) @@ -684,7 +699,7 @@ static inline struct page *__vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, bool special, unsigned long long entry, enum pgtable_level level) { - if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { + if (pgtable_level_has_pxx_special(level)) { if (unlikely(special)) { #ifdef CONFIG_FIND_NORMAL_PAGE if (vma->vm_ops && vma->vm_ops->find_normal_page) @@ -699,8 +714,9 @@ static inline struct page *__vm_normal_page(struct vm_area_struct *vma, return NULL; } /* - * With CONFIG_ARCH_HAS_PTE_SPECIAL, any special page table - * mappings (incl. shared zero folios) are marked accordingly. + * With working pte_special()/pmd_special()..., any special page + * table mappings (incl. shared zero folios) are marked + * accordingly. */ } else { if (unlikely(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) { From 09ce923071e7852ece60d7368e05249bf32c7967 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 28 Apr 2026 16:52:17 +0800 Subject: [PATCH 1187/1518] mm/memory_hotplug: fix memory block reference leak on remove commit 93866f55f7e292fe3d47d36c9efe5ee10213a06b upstream. Patch series "mm: Fix memory block leaks and locking", v2. This series fixes two memory block device reference leaks and one locking issue around the per-memory_block hwpoison counter. This patch (of 2): remove_memory_blocks_and_altmaps() looks up each memory block with find_memory_block(), which acquires a reference to the memory block device. That reference is never dropped on this path, resulting in a leaked device reference when removing memory blocks and their altmaps. Drop the reference after retrieving mem->altmap and clearing mem->altmap, before removing the memory block device. Link: https://lore.kernel.org/20260428085219.1316047-1-songmuchun@bytedance.com Link: https://lore.kernel.org/20260428085219.1316047-2-songmuchun@bytedance.com Fixes: 6b8f0798b85a ("mm/memory_hotplug: split memmap_on_memory requests across memblocks") Signed-off-by: Muchun Song Acked-by: Oscar Salvador Acked-by: David Hildenbrand (Arm) Cc: Danilo Krummrich Cc: Greg Kroah-Hartman Cc: "Huang, Ying" Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: "Rafael J. Wysocki" Cc: Vishal Verma Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/memory_hotplug.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index aa1f744143077..6a7714179c205 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1439,6 +1439,8 @@ static void remove_memory_blocks_and_altmaps(u64 start, u64 size) altmap = mem->altmap; mem->altmap = NULL; + /* drop the ref. we got via find_memory_block() */ + put_device(&mem->dev); remove_memory_block_devices(cur_start, memblock_size); From 738d18f1da3513d17b6f7bf30146cc4ac2480ffd Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Tue, 21 Apr 2026 17:39:07 +0200 Subject: [PATCH 1188/1518] mm/page_alloc: fix initialization of tags of the huge zero folio with init_on_free commit 6a288a4ddb4a994490505ab5f41c445f8e6b6467 upstream. __GFP_ZEROTAGS semantics are currently a bit weird, but effectively this flag is only ever set alongside __GFP_ZERO and __GFP_SKIP_KASAN. If we run with init_on_free, we will zero out pages during __free_pages_prepare(), to skip zeroing on the allocation path. However, when allocating with __GFP_ZEROTAG set, post_alloc_hook() will consequently not only skip clearing page content, but also skip clearing tag memory. Not clearing tags through __GFP_ZEROTAGS is irrelevant for most pages that will get mapped to user space through set_pte_at() later: set_pte_at() and friends will detect that the tags have not been initialized yet (PG_mte_tagged not set), and initialize them. However, for the huge zero folio, which will be mapped through a PMD marked as special, this initialization will not be performed, ending up exposing whatever tags were still set for the pages. The docs (Documentation/arch/arm64/memory-tagging-extension.rst) state that allocation tags are set to 0 when a page is first mapped to user space. That no longer holds with the huge zero folio when init_on_free is enabled. Fix it by decoupling __GFP_ZEROTAGS from __GFP_ZERO, passing to tag_clear_highpages() whether we want to also clear page content. Invert the meaning of the tag_clear_highpages() return value to have clearer semantics. Reproduced with the huge zero folio by modifying the check_buffer_fill arm64/mte selftest to use a 2 MiB area, after making sure that pages have a non-0 tag set when freeing (note that, during boot, we will not actually initialize tags, but only set KASAN_TAG_KERNEL in the page flags). $ ./check_buffer_fill 1..20 ... not ok 17 Check initial tags with private mapping, sync error mode and mmap memory not ok 18 Check initial tags with private mapping, sync error mode and mmap/mprotect memory ... This code needs more cleanups; we'll tackle that next, like decoupling __GFP_ZEROTAGS from __GFP_SKIP_KASAN. [akpm@linux-foundation.org: s/__GPF_ZERO/__GFP_ZERO/, per David] Link: https://lore.kernel.org/20260421-zerotags-v2-1-05cb1035482e@kernel.org Fixes: adfb6609c680 ("mm/huge_memory: initialise the tags of the huge zero folio") Signed-off-by: David Hildenbrand (Arm) Reviewed-by: Catalin Marinas Tested-by: Lance Yang Cc: Brendan Jackman Cc: Dev Jain Cc: Johannes Weiner Cc: Liam Howlett Cc: Lorenzo Stoakes (Oracle) Cc: Mark Brown Cc: Michal Hocko Cc: Mike Rapoport Cc: Ryan Roberts Cc: Suren Baghdasaryan Cc: Will Deacon Cc: Zi Yan Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/page.h | 2 +- arch/arm64/mm/fault.c | 11 +++++++---- include/linux/gfp_types.h | 10 +++++----- include/linux/highmem.h | 7 ++++--- mm/page_alloc.c | 8 ++++---- 5 files changed, 21 insertions(+), 17 deletions(-) diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index 258cca4b48734..5062d8725fda1 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -33,7 +33,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr); #define vma_alloc_zeroed_movable_folio vma_alloc_zeroed_movable_folio -bool tag_clear_highpages(struct page *to, int numpages); +bool tag_clear_highpages(struct page *to, int numpages, bool clear_pages); #define __HAVE_ARCH_TAG_CLEAR_HIGHPAGES #define clear_user_page(page, vaddr, pg) clear_page(page) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index a193b6a5d1e65..4c62082b9a3bd 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -967,7 +967,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, return vma_alloc_folio(flags, 0, vma, vaddr); } -bool tag_clear_highpages(struct page *page, int numpages) +bool tag_clear_highpages(struct page *page, int numpages, bool clear_pages) { /* * Check if MTE is supported and fall back to clear_highpage(). @@ -975,13 +975,16 @@ bool tag_clear_highpages(struct page *page, int numpages) * post_alloc_hook() will invoke tag_clear_highpages(). */ if (!system_supports_mte()) - return false; + return clear_pages; /* Newly allocated pages, shouldn't have been tagged yet */ for (int i = 0; i < numpages; i++, page++) { WARN_ON_ONCE(!try_page_mte_tagging(page)); - mte_zero_clear_page_tags(page_address(page)); + if (clear_pages) + mte_zero_clear_page_tags(page_address(page)); + else + mte_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } - return true; + return false; } diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 65db9349f9053..63bee08c6f31c 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -277,11 +277,11 @@ enum { * * %__GFP_ZERO returns a zeroed page on success. * - * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself - * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that - * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting - * memory tags at the same time as zeroing memory has minimal additional - * performance impact. + * %__GFP_ZEROTAGS zeroes memory tags at allocation time. Setting memory tags at + * the same time as zeroing memory (e.g., with __GFP_ZERO) has minimal + * additional performance impact. However, __GFP_ZEROTAGS also zeroes the tags + * even if memory is not getting zeroed at allocation time (e.g., + * with init_on_free). * * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. * Used for userspace and vmalloc pages; the latter are unpoisoned by diff --git a/include/linux/highmem.h b/include/linux/highmem.h index abc20f9810fd4..029172383b769 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -251,10 +251,11 @@ static inline void clear_highpage_kasan_tagged(struct page *page) #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES -/* Return false to let people know we did not initialize the pages */ -static inline bool tag_clear_highpages(struct page *page, int numpages) +/* Returns true if the caller has to initialize the pages */ +static inline bool tag_clear_highpages(struct page *page, int numpages, + bool clear_pages) { - return false; + return clear_pages; } #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f676966180035..775e02b797a3b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1847,9 +1847,9 @@ static inline bool should_skip_init(gfp_t flags) inline void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags) { + const bool zero_tags = gfp_flags & __GFP_ZEROTAGS; bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); - bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); int i; set_page_private(page, 0); @@ -1871,11 +1871,11 @@ inline void post_alloc_hook(struct page *page, unsigned int order, */ /* - * If memory tags should be zeroed - * (which happens only when memory should be initialized as well). + * Clearing tags can efficiently clear the memory for us as well, if + * required. */ if (zero_tags) - init = !tag_clear_highpages(page, 1 << order); + init = tag_clear_highpages(page, 1 << order, /* clear_pages= */init); if (!should_skip_kasan_unpoison(gfp_flags) && kasan_unpoison_pages(page, order, init)) { From 0fa24311bd42df98296ec2ae94d602e55ff0eb2a Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Mon, 27 Apr 2026 12:03:51 -0400 Subject: [PATCH 1189/1518] selftests/mm: run_vmtests.sh: fix destructive tests invocation commit 3432cbb291aabf85f8af4b9d1ec37179168ff999 upstream. Destructive tests should be invoked with -d command-line option, but this won't work today since 'd' is missing in getopts command-line. This commit fixes it. Link: https://lore.kernel.org/214fd9e4-5398-4c26-859e-c982c2e277c3@redhat.com Fixes: f16ff3b692ad ("selftests/mm: run_vmtests.sh: add missing tests") Signed-off-by: Luiz Capitulino Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: SeongJae Park Cc: David Hildenbrand Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/mm/run_vmtests.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index d9173f2312b7b..1edb2d785d936 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -97,7 +97,7 @@ RUN_ALL=false RUN_DESTRUCTIVE=false TAP_PREFIX="# " -while getopts "aht:n" OPT; do +while getopts "aht:nd" OPT; do case ${OPT} in "a") RUN_ALL=true ;; "h") usage ;; From ffb6dbb49c96be82f07c7b112e3ebc3e6fdd8dd5 Mon Sep 17 00:00:00 2001 From: Abdun Nihaal Date: Tue, 19 May 2026 11:57:39 +0530 Subject: [PATCH 1190/1518] net: wwan: iosm: fix potential memory leaks in ipc_imem_init() commit c5d93b2c40355e999715262a824965aac025a427 upstream. The memory allocated in ipc_protocol_init() is not freed on the error paths that follow in ipc_imem_init(). Fix that by calling the corresponding release function ipc_protocol_deinit() in the error path. Fixes: 3670970dd8c6 ("net: iosm: shared memory IPC interface") Cc: stable@vger.kernel.org Signed-off-by: Abdun Nihaal Link: https://patch.msgid.link/20260519062815.55545-1-nihaal@cse.iitm.ac.in Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/wwan/iosm/iosm_ipc_imem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index 530a3ea47a1a7..ce76045004867 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -1426,6 +1426,8 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, protocol_init_fail: cancel_work_sync(&ipc_imem->run_state_worker); ipc_task_deinit(ipc_imem->ipc_task); + if (ipc_imem->ipc_protocol) + ipc_protocol_deinit(ipc_imem->ipc_protocol); ipc_task_init_fail: kfree(ipc_imem->ipc_task); ipc_task_fail: From added1213395071470a900cc845a042fb51882a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Safa=20Karaku=C5=9F?= Date: Sat, 16 May 2026 21:15:04 +0300 Subject: [PATCH 1191/1518] Bluetooth: fix UAF in l2cap_sock_cleanup_listen() vs l2cap_conn_del() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ab1513597c6cf17cd1ad2a21e3b045421b48e022 upstream. bt_accept_dequeue() unlinks a not-yet-accepted child from the parent accept queue and release_sock()s it before returning, so the returned sk has no caller reference and is unlocked. l2cap_sock_cleanup_listen() walks these children on listening-socket close. A concurrent HCI disconnect drives hci_rx_work -> l2cap_conn_del() which runs l2cap_chan_del() + l2cap_sock_kill() and frees the child sk and its l2cap_chan; cleanup_listen() then uses both: BUG: KASAN: slab-use-after-free in l2cap_sock_kill l2cap_sock_kill / l2cap_sock_cleanup_listen / __x64_sys_close Freed by: l2cap_conn_del -> l2cap_sock_close_cb -> l2cap_sock_kill This is distinct from the two fixes already in this area: commit e83f5e24da741 ("Bluetooth: serialize accept_q access") serialises the accept_q list/poll and takes temporary refs inside bt_accept_dequeue(), and CVE-2025-39860 serialises the userspace close()/accept() race by calling cleanup_listen() under lock_sock() in l2cap_sock_release(). Neither covers l2cap_conn_del() running from hci_rx_work, so this UAF still reproduces on current bluetooth/master. Take the reference at the source: bt_accept_dequeue() does sock_hold() while sk is still locked, before release_sock(); callers sock_put(). cleanup_listen() pins the chan with l2cap_chan_hold_unless_zero() under a brief child sk lock (serialising vs l2cap_sock_teardown_cb()), drops it before l2cap_chan_lock(), and skips a duplicate l2cap_sock_kill() on SOCK_DEAD. conn->lock is not taken here: cleanup_listen() runs under the parent sk lock and that would invert conn->lock -> chan->lock -> sk_lock (lockdep). KASAN/SMP: an unprivileged listen/close vs HCI-disconnect race produced 12 use-after-free reports per run before this change; 0, and no lockdep report, over 1600+ raced iterations after it on bluetooth/master. Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode") Cc: stable@vger.kernel.org Reported-by: Siwei Zhang Reviewed-by: Siwei Zhang Signed-off-by: Safa Karakuş Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/af_bluetooth.c | 10 +++++++ net/bluetooth/iso.c | 9 ++++++- net/bluetooth/l2cap_sock.c | 51 +++++++++++++++++++++++++++++++----- net/bluetooth/rfcomm/sock.c | 9 ++++++- net/bluetooth/sco.c | 9 ++++++- 5 files changed, 78 insertions(+), 10 deletions(-) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 2b94e20772038..bcdf086b8ca54 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -309,6 +309,16 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) if (newsock) sock_graft(sk, newsock); + /* Hand the caller a reference taken while sk is + * still locked. bt_accept_unlink() just dropped + * the accept-queue reference; without this hold a + * concurrent teardown (e.g. l2cap_conn_del() -> + * l2cap_sock_kill()) could free sk between + * release_sock() and the caller using it. Every + * caller drops this with sock_put() when done. + */ + sock_hold(sk); + release_sock(sk); return sk; } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 46ebd69026fe2..3b0385071bb4f 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -741,6 +741,8 @@ static void iso_sock_cleanup_listen(struct sock *parent) while ((sk = bt_accept_dequeue(parent, NULL))) { iso_sock_close(sk); iso_sock_kill(sk); + /* Drop the reference handed back by bt_accept_dequeue(). */ + sock_put(sk); } /* If listening socket has a hcon, properly disconnect it */ @@ -1282,8 +1284,13 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, } ch = bt_accept_dequeue(sk, newsock); - if (ch) + if (ch) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps ch alive from here. + */ + sock_put(ch); break; + } if (!timeo) { err = -EAGAIN; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 15637402a39de..898ee21d7e4fd 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -349,8 +349,13 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, } nsk = bt_accept_dequeue(sk, newsock); - if (nsk) + if (nsk) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps nsk alive from here. + */ + sock_put(nsk); break; + } if (!timeo) { err = -EAGAIN; @@ -1457,22 +1462,54 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) BT_DBG("parent %p state %s", parent, state_to_string(parent->sk_state)); - /* Close not yet accepted channels */ + /* Close not yet accepted channels. + * + * bt_accept_dequeue() now returns sk with an extra reference held + * (taken while sk was still locked) so a concurrent l2cap_conn_del() + * -> l2cap_sock_kill() cannot free sk under us. + * + * cleanup_listen() runs under the parent sk lock, so unlike + * l2cap_sock_shutdown() we must NOT take conn->lock here: that would + * establish sk_lock -> conn->lock and invert the established + * conn->lock -> chan->lock -> sk_lock order (lockdep deadlock). + * + * Instead, briefly take the child sk lock to fetch and pin its chan. + * l2cap_conn_del() reaches the chan free only via + * l2cap_chan_del() -> l2cap_sock_teardown_cb(), which itself takes + * the child sk lock; holding it across l2cap_chan_hold_unless_zero() + * therefore guarantees the chan cannot be freed while we read and + * pin it (hold_unless_zero() additionally skips a chan already past + * its last reference). We then drop the sk lock before taking + * chan->lock, so sk and chan locks are never held together. + */ while ((sk = bt_accept_dequeue(parent, NULL))) { - struct l2cap_chan *chan = l2cap_pi(sk)->chan; + struct l2cap_chan *chan; + + lock_sock_nested(sk, L2CAP_NESTING_NORMAL); + chan = l2cap_chan_hold_unless_zero(l2cap_pi(sk)->chan); + release_sock(sk); + if (!chan) { + /* l2cap_conn_del() already tearing this child down */ + sock_put(sk); + continue; + } BT_DBG("child chan %p state %s", chan, state_to_string(chan->state)); - l2cap_chan_hold(chan); l2cap_chan_lock(chan); - __clear_chan_timer(chan); l2cap_chan_close(chan, ECONNRESET); - l2cap_sock_kill(sk); - + /* l2cap_conn_del() may already have killed this socket + * (it sets SOCK_DEAD); skip the duplicate to avoid a + * double sock_put()/l2cap_chan_put(). + */ + if (!sock_flag(sk, SOCK_DEAD)) + l2cap_sock_kill(sk); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); + sock_put(sk); } } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 913402806fa0d..3052436e9c6de 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -180,6 +180,8 @@ static void rfcomm_sock_cleanup_listen(struct sock *parent) while ((sk = bt_accept_dequeue(parent, NULL))) { rfcomm_sock_close(sk); rfcomm_sock_kill(sk); + /* Drop the reference handed back by bt_accept_dequeue(). */ + sock_put(sk); } parent->sk_state = BT_CLOSED; @@ -496,8 +498,13 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, } nsk = bt_accept_dequeue(sk, newsock); - if (nsk) + if (nsk) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps nsk alive from here. + */ + sock_put(nsk); break; + } if (!timeo) { err = -EAGAIN; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 9404fdb10ea63..a536c2edd14f2 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -498,6 +498,8 @@ static void sco_sock_cleanup_listen(struct sock *parent) while ((sk = bt_accept_dequeue(parent, NULL))) { sco_sock_close(sk); sco_sock_kill(sk); + /* Drop the reference handed back by bt_accept_dequeue(). */ + sock_put(sk); } parent->sk_state = BT_CLOSED; @@ -759,8 +761,13 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, } ch = bt_accept_dequeue(sk, newsock); - if (ch) + if (ch) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps ch alive from here. + */ + sock_put(ch); break; + } if (!timeo) { err = -EAGAIN; From 61f2410a96dee808029e2ae4d6ef2dd635f3477f Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 15 May 2026 07:25:25 +0100 Subject: [PATCH 1192/1518] Bluetooth: ISO: drop ISO_END frames received without prior ISO_START commit 84c24fb151fc1179355296d7ff29129ac7c42129 upstream. ISO data PDUs carry a packet-boundary flag indicating START, CONT, END or SINGLE. The ISO_CONT branch of iso_recv() guards against a missing ISO_START by checking conn->rx_len before touching conn->rx_skb, but ISO_END does not. If a peer sends an ISO_END as the first packet on a fresh ISO connection, conn->rx_skb is still NULL and conn->rx_len is zero, so skb_put(conn->rx_skb, ...) dereferences NULL and oopses. For BIS, where receivers sync to a broadcaster without pairing, any broadcaster on the air can trigger this. Mirror the ISO_CONT check at the top of ISO_END so a stray end fragment is logged and dropped instead of crashing the host. Fixes: ccf74f2390d6 ("Bluetooth: Add BTPROTO_ISO socket type") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-7 Signed-off-by: David Carlier Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/iso.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 3b0385071bb4f..038e292fb194f 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -2461,6 +2461,11 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) break; case ISO_END: + if (!conn->rx_len) { + BT_ERR("Unexpected end frame (len %d)", skb->len); + goto drop; + } + skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; From 5506aec795135cdd4cbf4e845929155663b25055 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 12 May 2026 22:15:39 +0200 Subject: [PATCH 1193/1518] Bluetooth: bnep: Fix UAF read of dev->name commit 59e932ded949fa6f0340bf7c6d7818f962fa4fd2 upstream. bnep_add_connection() needs to keep holding the bnep_session_sem while reading dev->name (just like bnep_get_connlist() does); otherwise the bnep_session() thread can concurrently free the net_device, which can for example be triggered by a concurrent bnep_del_connection(). (This UAF is fairly uninteresting from a security perspective; calling bnep_add_connection() requires passing a capable(CAP_NET_ADMIN) check. It also requires completely tearing down a netdev during a fairly tight race window.) Cc: stable@vger.kernel.org Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jann Horn Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/bnep/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index d44987d4515c0..b3cef7a4db541 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -638,8 +638,8 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) goto failed; } - up_write(&bnep_session_sem); strcpy(req->device, dev->name); + up_write(&bnep_session_sem); return 0; failed: From 192cb0f1ca706d9a1bc36ae0ad5f666d1e4fd894 Mon Sep 17 00:00:00 2001 From: Mingyu Wang <25181214217@stu.xidian.edu.cn> Date: Mon, 18 May 2026 10:49:49 +0800 Subject: [PATCH 1194/1518] Bluetooth: hci_uart: fix UAFs and race conditions in close and init paths commit c1bb9336ae6b54a5f6a353c4bd4ed9a4307e429b upstream. Vulnerabilities leading to Use-After-Free (UAF) and Null Pointer Dereference (NPD) conditions were observed in the lifecycle management of hci_uart. The primary issue arises because the workqueues (init_ready and write_work) are only flushed/cancelled if the HCI_UART_PROTO_READY flag is set during TTY close. If a hangup occurs before setup completes, hci_uart_tty_close() skips the teardown of these workqueues and proceeds to free the `hu` struct. When the scheduled work executes later, it blindly dereferences the freed `hu` struct. Furthermore, several data races and UAFs were identified in the teardown sequence: 1. Calling hci_uart_flush() from hci_uart_close() without effectively disabling write_work causes a race condition where both can concurrently double-free hu->tx_skb. This happens because protocol timers can concurrently invoke hci_uart_tx_wakeup() and requeue write_work. 2. Calling hci_free_dev(hdev) before hu->proto->close(hu) causes a UAF when vendor specific protocol close callbacks dereference hu->hdev. 3. In the initialization error paths, failing to take the proto_lock write lock before clearing PROTO_READY leads to races with active readers. Additionally, hci_uart_tty_receive() accesses hu->hdev outside the read lock, leading to UAFs if the initialization error path frees hdev concurrently. Fix these synchronization and lifecycle issues by: 1. Re-ordering hci_uart_tty_close() to clear HCI_UART_PROTO_READY first, followed immediately by a cancel_work_sync(&hu->write_work). Clearing the flag locks out concurrent protocol timers from successfully invoking hci_uart_tx_wakeup(), effectively rendering the cancellation permanent and preventing the tx_skb double-free. 2. Note: Clearing PROTO_READY early causes hci_uart_close() to skip hu->proto->flush(). This is perfectly safe in the tty_close path because hu->proto->close() executes shortly after, which intrinsically purges all protocol SKB queues and tears down the state. 3. Relocating hu->proto->close(hu) strictly prior to hci_free_dev(hdev) across all close and error paths to prevent vendor-level UAFs. 4. Moving the hdev->stat.byte_rx increment in hci_uart_tty_receive() inside the proto_lock read-side critical section to safely synchronize with device unregistration. 5. Adding cancel_work_sync(&hu->write_work) to hci_uart_close() to safely flush the workqueue before hci_uart_flush() is invoked via the HCI core. 6. Utilizing cancel_work_sync() instead of disable_work_sync() across all paths to prevent permanently breaking user-space retry capabilities. Fixes: 3b799254cf6f ("Bluetooth: hci_uart: Cancel init work before unregistering") Cc: stable@vger.kernel.org Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_ldisc.c | 48 +++++++++++++++++++++++++++++------ 1 file changed, 40 insertions(+), 8 deletions(-) diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 5455990ab211e..10e936b87cc8e 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -194,7 +194,15 @@ void hci_uart_init_work(struct work_struct *work) err = hci_register_dev(hu->hdev); if (err < 0) { BT_ERR("Can't register HCI device"); + + percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_READY, &hu->flags); + percpu_up_write(&hu->proto_lock); + + /* Safely cancel work after clearing flags */ + cancel_work_sync(&hu->write_work); + + /* Close protocol before freeing hdev */ hu->proto->close(hu); hdev = hu->hdev; hu->hdev = NULL; @@ -263,8 +271,12 @@ static int hci_uart_open(struct hci_dev *hdev) /* Close device */ static int hci_uart_close(struct hci_dev *hdev) { + struct hci_uart *hu = hci_get_drvdata(hdev); + BT_DBG("hdev %p", hdev); + cancel_work_sync(&hu->write_work); + hci_uart_flush(hdev); hdev->flush = NULL; return 0; @@ -531,6 +543,7 @@ static void hci_uart_tty_close(struct tty_struct *tty) { struct hci_uart *hu = tty->disc_data; struct hci_dev *hdev; + bool proto_ready; BT_DBG("tty %p", tty); @@ -540,24 +553,38 @@ static void hci_uart_tty_close(struct tty_struct *tty) if (!hu) return; - hdev = hu->hdev; - if (hdev) - hci_uart_close(hdev); + /* Wait for init_ready to finish to prevent registration races */ + cancel_work_sync(&hu->init_ready); - if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) { + proto_ready = test_bit(HCI_UART_PROTO_READY, &hu->flags); + if (proto_ready) { percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_READY, &hu->flags); percpu_up_write(&hu->proto_lock); + } - cancel_work_sync(&hu->init_ready); - cancel_work_sync(&hu->write_work); + /* + * Unconditionally cancel write_work AFTER clearing PROTO_READY. + * This ensures that concurrent protocol timers cannot requeue + * write_work via hci_uart_tx_wakeup(), permanently preventing + * double-free races and UAFs. + */ + cancel_work_sync(&hu->write_work); + + hdev = hu->hdev; + if (hdev) + hci_uart_close(hdev); /* proto->flush is safely skipped */ + if (proto_ready) { if (hdev) { if (test_bit(HCI_UART_REGISTERED, &hu->flags)) hci_unregister_dev(hdev); - hci_free_dev(hdev); } + /* Close protocol before freeing hdev (intrinsically purges queues) */ hu->proto->close(hu); + + if (hdev) + hci_free_dev(hdev); } clear_bit(HCI_UART_PROTO_SET, &hu->flags); @@ -625,11 +652,12 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, * tty caller */ hu->proto->recv(hu, data, count); - percpu_up_read(&hu->proto_lock); if (hu->hdev) hu->hdev->stat.byte_rx += count; + percpu_up_read(&hu->proto_lock); + tty_unthrottle(tty); } @@ -695,6 +723,10 @@ static int hci_uart_register_dev(struct hci_uart *hu) percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_INIT, &hu->flags); percpu_up_write(&hu->proto_lock); + /* Cancel work after clearing flags */ + cancel_work_sync(&hu->write_work); + + /* Close protocol before freeing hdev */ hu->proto->close(hu); hu->hdev = NULL; hci_free_dev(hdev); From 051922ab709c0a6917eae765c22481dfc68379e5 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Mon, 11 May 2026 08:26:41 -0400 Subject: [PATCH 1195/1518] Bluetooth: L2CAP: ecred_reconfigure: send packed pdu, not stack pointer commit 3374ef8cf99368a40f7efd51a2a375a4c5dc6f0d upstream. Commit 1c08108f3014 ("Bluetooth: L2CAP: Avoid -Wflex-array-member-not-at-end warnings") converted the on-stack request PDU in l2cap_ecred_reconfigure() from an explicit packed struct to DEFINE_RAW_FLEX(), but did not adjust the size and source-pointer arguments to l2cap_send_cmd(): - struct { - struct l2cap_ecred_reconf_req req; - __le16 scid; - } pdu; + DEFINE_RAW_FLEX(struct l2cap_ecred_reconf_req, pdu, scid, 1); ... l2cap_send_cmd(conn, chan->ident, L2CAP_ECRED_RECONF_REQ, sizeof(pdu), &pdu); After the conversion, DEFINE_RAW_FLEX() expands to declare an anonymous union pdu_u plus a local pointer "pdu" pointing at it. Therefore: - sizeof(pdu) is now sizeof(struct l2cap_ecred_reconf_req *) = 8 on 64-bit (4 on 32-bit), not the 6 bytes of (mtu, mps, scid[1]). - &pdu is the address of the local pointer's stack storage, not the address of the request payload. l2cap_send_cmd() forwards (data, count) to l2cap_build_cmd(), which calls skb_put_data(skb, data, count). The L2CAP_ECRED_RECONFIGURE_REQ packet body therefore contains 8 bytes copied from the kernel stack starting at &pdu -- the 8 bytes overlap the pdu pointer's value, leaking a kernel stack address to the paired Bluetooth peer. The intended (mtu, mps, scid) fields are not transmitted at all, so the peer rejects the request as malformed and the L2CAP_ECRED_RECONFIGURE feature itself has been broken for the local-side initiator since the introducing commit landed. The sibling site l2cap_ecred_conn_req() in the same commit was converted correctly (sizeof(*pdu) + len, pdu); only this site was missed. Restore the original semantics: pass the full flex-struct size via struct_size(pdu, scid, 1) and the pdu pointer (the struct address) as the source. Validated on a stock 7.0-based host kernel via the real call path: setsockopt(SOL_BLUETOOTH, BT_RCVMTU, ...) on a BT_CONNECTED L2CAP_MODE_EXT_FLOWCTL socket emits an L2CAP_ECRED_RECONFIGURE_REQ whose body is 8 bytes (the on-stack pdu local's value) rather than the expected 6. Three captures from fresh socket / fresh hciemu peer on the same host -- low bytes vary per call, high 0xffff confirms a kernel virtual address (KASLR-randomised stack slot, not a fixed string): RECONF_REQ body (ident=0x02 len=8): 42 fb 54 af 0e ca ff ff RECONF_REQ body (ident=0x02 len=8): 52 3d 2e af 0e ca ff ff RECONF_REQ body (ident=0x02 len=8): b2 fc 5b af 0e ca ff ff After this patch the body is 6 bytes carrying the expected little-endian (mtu, mps, scid). Cc: stable@vger.kernel.org Fixes: 1c08108f3014 ("Bluetooth: L2CAP: Avoid -Wflex-array-member-not-at-end warnings") Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Michael Bommarito Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/l2cap_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index bcb13ce531099..87ebe81277c51 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7275,7 +7275,7 @@ static void l2cap_ecred_reconfigure(struct l2cap_chan *chan) chan->ident = l2cap_get_ident(conn); l2cap_send_cmd(conn, chan->ident, L2CAP_ECRED_RECONF_REQ, - sizeof(pdu), &pdu); + struct_size(pdu, scid, 1), pdu); } int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu) From f1febe93ef075314615f970a87681d9ab86691d1 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Fri, 15 May 2026 10:38:19 -0400 Subject: [PATCH 1196/1518] Bluetooth: MGMT: validate Add Extended Advertising Data length commit d3f7d17960ed50df3a6709c5158caff989c8c905 upstream. MGMT_OP_ADD_EXT_ADV_DATA is registered as a variable-length command, with MGMT_ADD_EXT_ADV_DATA_SIZE as the fixed header size. The handler then uses cp->adv_data_len and cp->scan_rsp_len to validate and copy cp->data, but it never checks that those bytes are part of the mgmt command payload. A short command can therefore make add_ext_adv_data() pass an out-of-bounds pointer into tlv_data_is_valid(). If the bytes beyond the command buffer are addressable, they can also be copied into the advertising instance as scan response data, where the caller can read them back via MGMT_OP_GET_ADV_INSTANCE. The trigger requires CAP_NET_ADMIN in the initial user namespace; KASAN reports an 8-byte slab-out-of-bounds read. Reject commands whose length does not match the fixed header plus both advertising data lengths before parsing cp->data. Fixes: 12410572833a ("Bluetooth: Break add adv into two mgmt commands") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Michael Bommarito Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/mgmt.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 9065a864bc65d..91d1c0d132f9e 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -9094,9 +9094,15 @@ static int add_ext_adv_data(struct sock *sk, struct hci_dev *hdev, void *data, struct adv_info *adv_instance; int err = 0; struct mgmt_pending_cmd *cmd; + u16 expected_len; BT_DBG("%s", hdev->name); + expected_len = struct_size(cp, data, cp->adv_data_len + cp->scan_rsp_len); + if (expected_len != data_len) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA, + MGMT_STATUS_INVALID_PARAMS); + hci_dev_lock(hdev); adv_instance = hci_find_adv_instance(hdev, cp->instance); From 8b4c412e001b0c670eb937beab491af974da55b3 Mon Sep 17 00:00:00 2001 From: Jiexun Wang Date: Wed, 6 May 2026 19:43:30 +0800 Subject: [PATCH 1197/1518] Bluetooth: serialize accept_q access commit e83f5e24da741fa9405aeeff00b08c5ee7c37b88 upstream. bt_sock_poll() walks the accept queue without synchronization, while child teardown can unlink the same socket and drop its last reference. The unsynchronized accept queue walk has existed since the initial Bluetooth import. Protect accept_q with a dedicated lock for queue updates and polling. Also rework bt_accept_dequeue() to take temporary child references under the queue lock before dropping it and locking the child socket. Fixes: 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Reported-by: Jann Horn Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Jiexun Wang Signed-off-by: Ren Wei Signed-off-by: Jiexun Wang Reviewed-by: Jann Horn Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- include/net/bluetooth/bluetooth.h | 1 + net/bluetooth/af_bluetooth.c | 87 +++++++++++++++++++++++-------- 2 files changed, 66 insertions(+), 22 deletions(-) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index d46ed9011ee5d..3791915e4a0ac 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -389,6 +389,7 @@ void baswap(bdaddr_t *dst, const bdaddr_t *src); struct bt_sock { struct sock sk; struct list_head accept_q; + spinlock_t accept_q_lock; /* protects accept_q */ struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index bcdf086b8ca54..70e35e1980753 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -154,6 +154,7 @@ struct sock *bt_sock_alloc(struct net *net, struct socket *sock, sock_init_data(sock, sk); INIT_LIST_HEAD(&bt_sk(sk)->accept_q); + spin_lock_init(&bt_sk(sk)->accept_q_lock); sock_reset_flag(sk, SOCK_ZAPPED); @@ -214,6 +215,7 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { const struct cred *old_cred; struct pid *old_pid; + struct bt_sock *par = bt_sk(parent); BT_DBG("parent %p, sk %p", parent, sk); @@ -224,9 +226,13 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) else lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; + spin_lock_bh(&par->accept_q_lock); + list_add_tail(&bt_sk(sk)->accept_q, &par->accept_q); + sk_acceptq_added(parent); + spin_unlock_bh(&par->accept_q_lock); + /* Copy credentials from parent since for incoming connections the * socket is allocated by the kernel. */ @@ -244,8 +250,6 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) bh_unlock_sock(sk); else release_sock(sk); - - sk_acceptq_added(parent); } EXPORT_SYMBOL(bt_accept_enqueue); @@ -254,45 +258,72 @@ EXPORT_SYMBOL(bt_accept_enqueue); */ void bt_accept_unlink(struct sock *sk) { + struct sock *parent = bt_sk(sk)->parent; + BT_DBG("sk %p state %d", sk, sk->sk_state); + spin_lock_bh(&bt_sk(parent)->accept_q_lock); list_del_init(&bt_sk(sk)->accept_q); - sk_acceptq_removed(bt_sk(sk)->parent); + sk_acceptq_removed(parent); + spin_unlock_bh(&bt_sk(parent)->accept_q_lock); bt_sk(sk)->parent = NULL; sock_put(sk); } EXPORT_SYMBOL(bt_accept_unlink); +static struct sock *bt_accept_get(struct sock *parent, struct sock *sk) +{ + struct bt_sock *bt = bt_sk(parent); + struct sock *next = NULL; + + /* accept_q is modified from child teardown paths too, so take a + * temporary reference before dropping the queue lock. + */ + spin_lock_bh(&bt->accept_q_lock); + + if (sk) { + if (bt_sk(sk)->parent != parent) + goto out; + + if (!list_is_last(&bt_sk(sk)->accept_q, &bt->accept_q)) { + next = &list_next_entry(bt_sk(sk), accept_q)->sk; + sock_hold(next); + } + } else if (!list_empty(&bt->accept_q)) { + next = &list_first_entry(&bt->accept_q, + struct bt_sock, accept_q)->sk; + sock_hold(next); + } + +out: + spin_unlock_bh(&bt->accept_q_lock); + return next; +} + struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) { - struct bt_sock *s, *n; - struct sock *sk; + struct sock *sk, *next; BT_DBG("parent %p", parent); restart: - list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { - sk = (struct sock *)s; - + for (sk = bt_accept_get(parent, NULL); sk; sk = next) { /* Prevent early freeing of sk due to unlink and sock_kill */ - sock_hold(sk); lock_sock(sk); /* Check sk has not already been unlinked via * bt_accept_unlink() due to serialisation caused by sk locking */ - if (!bt_sk(sk)->parent) { + if (bt_sk(sk)->parent != parent) { BT_DBG("sk %p, already unlinked", sk); release_sock(sk); sock_put(sk); - /* Restart the loop as sk is no longer in the list - * and also avoid a potential infinite loop because - * list_for_each_entry_safe() is not thread safe. - */ goto restart; } + next = bt_accept_get(parent, sk); + /* sk is safely in the parent list so reduce reference count */ sock_put(sk); @@ -320,6 +351,8 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) sock_hold(sk); release_sock(sk); + if (next) + sock_put(next); return sk; } @@ -528,18 +561,28 @@ EXPORT_SYMBOL(bt_sock_stream_recvmsg); static inline __poll_t bt_accept_poll(struct sock *parent) { - struct bt_sock *s, *n; + struct bt_sock *bt = bt_sk(parent); + struct bt_sock *s; struct sock *sk; + __poll_t mask = 0; + + spin_lock_bh(&bt->accept_q_lock); + list_for_each_entry(s, &bt->accept_q, accept_q) { + int state; - list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; - if (sk->sk_state == BT_CONNECTED || - (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && - sk->sk_state == BT_CONNECT2)) - return EPOLLIN | EPOLLRDNORM; + state = READ_ONCE(sk->sk_state); + + if (state == BT_CONNECTED || + (test_bit(BT_SK_DEFER_SETUP, &bt->flags) && + state == BT_CONNECT2)) { + mask = EPOLLIN | EPOLLRDNORM; + break; + } } + spin_unlock_bh(&bt->accept_q_lock); - return 0; + return mask; } __poll_t bt_sock_poll(struct file *file, struct socket *sock, From 84bc87beb4cd77670939b446326788e4c9b3db37 Mon Sep 17 00:00:00 2001 From: Zijing Yin Date: Tue, 19 May 2026 10:26:33 -0700 Subject: [PATCH 1198/1518] phonet/pep: disable BH around forwarded sk_receive_skb() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit dbc81608e3a653dea6cf403f20cae35468b8ab9c upstream. The networking receive path is usually run from softirq context, but protocols that take the socket lock may have packets stored in the backlog and processed later from process context. In that case release_sock() -> __release_sock() drops the slock with spin_unlock_bh() and then calls sk->sk_backlog_rcv() with bottom halves enabled. Typical sk_backlog_rcv handlers process the socket whose backlog is being drained, so the BH state at entry is irrelevant for the slocks they touch. pep_do_rcv() is different: when the inbound skb targets an existing PEP pipe, it forwards the skb to a different *child* socket via sk_receive_skb(). That helper takes the child slock with bh_lock_sock_nested(), which is just spin_lock_nested() and assumes BH is already off. The same child slock therefore ends up acquired with BH on (process path) and with BH off (softirq path): process context softirq context --------------- --------------- release_sock(listener) __netif_receive_skb() __release_sock() phonet_rcv() spin_unlock_bh() __sk_receive_skb(listener) [BH now ENABLED] [BH already disabled] sk_backlog_rcv: sk_backlog_rcv: pep_do_rcv() pep_do_rcv() sk_receive_skb(child) sk_receive_skb(child) bh_lock_sock_nested(child) bh_lock_sock_nested(child) => SOFTIRQ-ON-W => IN-SOFTIRQ-W Lockdep flags this as inconsistent lock state, and it can become a real self-deadlock if a softirq on the same CPU tries to receive to the same child socket while its slock is held in the BH-enabled path: WARNING: inconsistent lock state inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. (slock-AF_PHONET/1){+.?.}-{3:3}, at: __sk_receive_skb+0x1cf/0x900 __sk_receive_skb net/core/sock.c:563 sk_receive_skb include/net/sock.h:2022 [inline] pep_do_rcv net/phonet/pep.c:675 sk_backlog_rcv include/net/sock.h:1190 __release_sock net/core/sock.c:3216 release_sock net/core/sock.c:3815 pep_sock_accept net/phonet/pep.c:879 Wrap the forwarded sk_receive_skb() in local_bh_disable() / local_bh_enable() so the child slock is always acquired with BH off. local_bh_disable() nests safely on the softirq path. Discovered via in-house syzkaller fuzzing; the same root cause also on the linux-6.1.y syzbot dashboard as extid 44f0626dd6284f02663c. Reproduced under KASAN + LOCKDEP + PROVE_LOCKING, reproducer: https://pastebin.com/A3t8xzCR Fixes: 9641458d3ec4 ("Phonet: Pipe End Point for Phonet Pipes protocol") Link: https://syzkaller.appspot.com/bug?extid=44f0626dd6284f02663c Cc: stable@vger.kernel.org Signed-off-by: Zijing Yin Acked-by: Rémi Denis-Courmont Reported-by: syzbot+9f4a135646b66c509935@syzkaller.appspotmail.com Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260519172635.86304-1-yzjaurora@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/phonet/pep.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 4db564d9d522b..058a16c423aef 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -671,8 +671,23 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb) /* Look for an existing pipe handle */ sknode = pep_find_pipe(&pn->hlist, &dst, pipe_handle); - if (sknode) - return sk_receive_skb(sknode, skb, 1); + if (sknode) { + int rc; + + /* pep_do_rcv() runs from two contexts: from softirq via + * phonet_rcv() -> __sk_receive_skb() with BH disabled, + * and from process context via + * release_sock() -> __release_sock(), which drops + * the listener slock with spin_unlock_bh() before draining + * the backlog. The child pipe slock is taken below via + * bh_lock_sock_nested(), which does not itself disable BH, so + * disable BH here to keep both acquire contexts consistent. + */ + local_bh_disable(); + rc = sk_receive_skb(sknode, skb, 1); + local_bh_enable(); + return rc; + } switch (hdr->message_id) { case PNS_PEP_CONNECT_REQ: From 3d4ef05266ab16d8ef7dd21658a557801eb78704 Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Wed, 20 May 2026 20:43:20 +0200 Subject: [PATCH 1199/1518] net: bcmgenet: keep RBUF EEE/PM disabled commit 9a1730245e416d11ad5c0f2c100061d61cc43f60 upstream. Setting RBUF_EEE_EN | RBUF_PM_EN in RBUF_ENERGY_CTRL breaks the RX path on GENET hardware once MAC EEE becomes active. RX traffic stops flowing while the link stays up and the usual descriptor/RX error counters remain quiet. In that state the MAC still accepts frames (rbuf_ovflow_cnt keeps climbing) but RBUF no longer forwards them to DMA, so rx_packets is no longer incremented at the netdev level. On some boards the corruption ends up as a paging fault in skb_release_data via bcmgenet_rx_poll on an LPI exit. Reproduced on Pi 4B (BCM2711 + BCM54213PE) and confirmed by Florian Fainelli on an internal Broadcom 4908-family board with the same crash signature. RBUF_PM_EN is not publicly documented. This shows up more often now that phy_support_eee() enables EEE by default, but it also affects older kernels as soon as TX LPI is turned on via ethtool, so it is not specific to recent changes. Always clear RBUF_EEE_EN | RBUF_PM_EN in bcmgenet_eee_enable_set so the bits stay off across resets. UMAC and TBUF setup is left alone so TX-side EEE keeps working. Link: https://github.com/raspberrypi/linux/issues/7304 Fixes: 6ef398ea60d9 ("net: bcmgenet: add EEE support") Cc: stable@vger.kernel.org Signed-off-by: Nicolai Buchwitz Reviewed-by: Florian Fainelli Link: https://patch.msgid.link/20260520184320.652053-1-nb@tipi-net.de Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 63cdf6d9d0772..abf6a6451cb1c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1369,13 +1369,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); bcmgenet_writel(reg, priv->base + off); - /* Do the same for thing for RBUF */ + /* RBUF EEE/PM can break the RX path on GENET. Keep it disabled. */ reg = bcmgenet_rbuf_readl(priv, RBUF_ENERGY_CTRL); - if (enable) - reg |= RBUF_EEE_EN | RBUF_PM_EN; - else + if (reg & (RBUF_EEE_EN | RBUF_PM_EN)) { reg &= ~(RBUF_EEE_EN | RBUF_PM_EN); - bcmgenet_rbuf_writel(priv, reg, RBUF_ENERGY_CTRL); + bcmgenet_rbuf_writel(priv, reg, RBUF_ENERGY_CTRL); + } if (!enable && priv->clk_eee_enabled) { clk_disable_unprepare(priv->clk_eee); From 49eff79967fd6ea45a9d028710bb852c950baef9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nerijus=20Bend=C5=BEi=C5=ABnas?= Date: Sat, 16 May 2026 18:02:51 +0300 Subject: [PATCH 1200/1518] net: phy: skip EEE advertisement write when autoneg is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 960e77ce14a83ef7f226e8e4b4d75765633ba48b upstream. genphy_c45_an_config_eee_aneg() writes the EEE advertisement to the auto-negotiation device's MMD register space (MDIO_MMD_AN, register MDIO_AN_EEE_ADV). These registers are read by the link partner only during auto-negotiation, so writing them while autoneg is disabled cannot influence the link. On some PHYs (e.g. Broadcom BCM54213PE) the write nevertheless reaches the chip and disturbs the receive datapath. Concretely, running ethtool -s eth0 speed 100 duplex full autoneg off ethtool --set-eee eth0 eee off leaves eth0 with TX working and RX completely silent on a Raspberry Pi 4 / CM4 board (bcmgenet + BCM54213PE in rgmii-rxid). Switching back to autoneg recovers the link. Prior to commit f26a29a038ee ("net: phy: ensure that genphy_c45_an_config_eee_aneg() sees new value of phydev->eee_cfg.eee_enabled"), the disable path was effectively a no-op because the helper read the stale eee_cfg.eee_enabled, so the underlying PHY behavior never surfaced. Bisected on rpi-6.12.y between commits 83943264 (good) and effcbc88 (bad) to f26a29a038ee. Fixes: f26a29a038ee ("net: phy: ensure that genphy_c45_an_config_eee_aneg() sees new value of phydev->eee_cfg.eee_enabled") Cc: stable@vger.kernel.org Signed-off-by: Nerijus Bendžiūnas Reviewed-by: Nicolai Buchwitz Tested-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260516150251.879680-1-nerijus.bendziunas@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/phy-c45.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 61670be0f0957..d2e36e460cc7f 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -939,6 +939,14 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_eee_abilities); */ int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) { + /* Writing MMD AN advertisements while autoneg is disabled has no + * effect on link-partner negotiation, but on some PHYs (e.g. the + * Broadcom BCM54213PE) the write itself disturbs the receive + * datapath. Skip it. + */ + if (phydev->autoneg == AUTONEG_DISABLE) + return 0; + if (!phydev->eee_cfg.eee_enabled) { __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; From 1604a2d68414aa4cc34faac0b7faa9c14455e8d3 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Wed, 13 May 2026 12:22:26 +0100 Subject: [PATCH 1201/1518] net/mlx5e: Fix use-after-free in mlx5e_tx_reporter_timeout_recover commit 7d260c5d2d89eb2c8c528d54b576b3aae3e20231 upstream. mlx5e_tx_reporter_timeout_recover() accesses sq->netdev after mlx5e_safe_reopen_channels() has torn down and freed the channel (and its embedded SQs). Replace the three sq->netdev references with priv->netdev which is safe because priv outlives channel teardown. The netdev_err() call already used priv->netdev for this reason; make the trylock/unlock and health_channel_eq_recover calls consistent. This fixes the following KASAN splat: BUG: KASAN: use-after-free in mlx5e_tx_reporter_timeout_recover+0x1dd/0x360 [mlx5_core] Read of size 8 at addr ffff889860ed0b28 by task kworker/u113:2/5277 Call Trace: mlx5e_tx_reporter_timeout_recover+0x1dd/0x360 [mlx5_core] devlink_health_reporter_recover+0xa2/0x150 devlink_health_report+0x254/0x7c0 mlx5e_reporter_tx_timeout+0x297/0x380 [mlx5_core] mlx5e_tx_timeout_work+0x109/0x170 [mlx5_core] process_one_work+0x677/0xf20 worker_thread+0x51f/0xd90 kthread+0x3a5/0x810 ret_from_fork+0x208/0x400 ret_from_fork_asm+0x1a/0x30 Fixes: 83ac0304a2d7 ("net/mlx5e: Fix deadlocks between devlink and netdev instance locks") Cc: stable@vger.kernel.org Reviewed-by: Cosmin Ratiu Reviewed-by: Tariq Toukan Signed-off-by: Matt Fleming Link: https://patch.msgid.link/20260513112226.140512-1-matt@readmodwrite.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index d6ace2b6fc1df..198033620c830 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -159,13 +159,13 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) * channels are being closed for other reason and this work is not * relevant anymore. */ - while (!netdev_trylock(sq->netdev)) { + while (!netdev_trylock(priv->netdev)) { if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) return 0; msleep(20); } - err = mlx5e_health_channel_eq_recover(sq->netdev, eq, sq->cq.ch_stats); + err = mlx5e_health_channel_eq_recover(priv->netdev, eq, sq->cq.ch_stats); if (!err) { to_ctx->status = 0; /* this sq recovered */ goto out; @@ -185,7 +185,7 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n", err); out: - netdev_unlock(sq->netdev); + netdev_unlock(priv->netdev); return err; } From f8a5a76b4a683043c6eff2a060bcaa17f9316ad5 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Wed, 13 May 2026 21:37:39 -0400 Subject: [PATCH 1202/1518] net: ifb: report ethtool stats over num_tx_queues commit 5db89c99566fc4728cc92e941d8e1975711e24b5 upstream. ifb_dev_init() allocates dp->tx_private to dev->num_tx_queues entries via kzalloc_objs(*txp, dev->num_tx_queues). Both IFB per-queue RX and TX stats live in those entries: ifb_xmit() updates txp->rx_stats using the skb queue mapping, ifb_ri_tasklet() updates txp->tx_stats, and ifb_stats64() aggregates both over dev->num_tx_queues. The ethtool stats callbacks instead size and walk the per-queue stats with dev->real_num_rx_queues and dev->real_num_tx_queues. With an asymmetric device where the RX queue count exceeds the TX queue count, for example: ip link add name ifb10 numtxqueues 1 numrxqueues 8 type ifb ethtool -S ifb10 ifb_get_ethtool_stats() indexes past the tx_private allocation and copies adjacent slab data through ETHTOOL_GSTATS. Use dev->num_tx_queues consistently for the stats strings, the stats count, and the stats data walks. This reports one RX stats group and one TX stats group for each backing ifb_q_private entry, which is the queue set IFB can actually populate. Reproduced under UML+KASAN at v7.1-rc2: BUG: KASAN: slab-out-of-bounds in ifb_fill_stats_data+0x3c/0xae Read of size 8 at addr 0000000062dbd228 by task ethtool/36 ifb_fill_stats_data+0x3c/0xae ifb_get_ethtool_stats+0xc0/0x129 __dev_ethtool+0x1ca5/0x363c dev_ethtool+0x123/0x1b3 dev_ioctl+0x56c/0x744 sock_do_ioctl+0x15f/0x1b2 sock_ioctl+0x4d5/0x50a sys_ioctl+0xd8b/0xde9 With the patch applied, the same UML+KASAN repro is silent and ethtool -S ifb10 reports only the stats backed by the single allocated tx_private entry. Fixes: a21ee5b2fcb8 ("net: ifb: support ethtools stats") Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/20260514013739.3549624-1-michael.bommarito@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ifb.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index d3dc0914450a8..0534d2471e617 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -211,12 +211,12 @@ static void ifb_get_strings(struct net_device *dev, u32 stringset, u8 *buf) switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < dev->real_num_rx_queues; i++) + for (i = 0; i < dev->num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "rx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); - for (i = 0; i < dev->real_num_tx_queues; i++) + for (i = 0; i < dev->num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "tx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); @@ -229,8 +229,7 @@ static int ifb_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: - return IFB_Q_STATS_LEN * (dev->real_num_rx_queues + - dev->real_num_tx_queues); + return IFB_Q_STATS_LEN * dev->num_tx_queues * 2; default: return -EOPNOTSUPP; } @@ -262,12 +261,12 @@ static void ifb_get_ethtool_stats(struct net_device *dev, struct ifb_q_private *txp; int i; - for (i = 0; i < dev->real_num_rx_queues; i++) { + for (i = 0; i < dev->num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->rx_stats); } - for (i = 0; i < dev->real_num_tx_queues; i++) { + for (i = 0; i < dev->num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->tx_stats); } From dac025c4e8f9c5cf9467eeac8be4639469aa5ac5 Mon Sep 17 00:00:00 2001 From: Jonas Jelonek Date: Fri, 15 May 2026 14:31:03 +0000 Subject: [PATCH 1203/1518] net: pse-pd: fix sign on -ENOENT check in of_load_pse_pis() commit 33d35975cbead3fa6b738ee57e5e45e14fbe0886 upstream. of_count_phandle_with_args() returns the count on success and a negative errno on failure, including -ENOENT when the "pairsets" property is absent. The existing comparison in of_load_pse_pis() checks against ENOENT (positive 2) instead of -ENOENT, so the branch is taken for any error return: legitimate DTs that omit "pairsets" trigger a spurious "wrong number of pairsets" error and probe fails with -EINVAL. Compare against -ENOENT so a missing "pairsets" property is correctly treated as "this PI has no pairsets, continue". Fixes: 9be9567a7c59 ("net: pse-pd: Add support for PSE PIs") Cc: stable@vger.kernel.org Signed-off-by: Jonas Jelonek Acked-by: Oleksij Rempel Link: https://patch.msgid.link/20260515143103.1721888-1-jelonek.jonas@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/pse-pd/pse_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 23eb3c9d0bcd3..af354483d1910 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -210,7 +210,7 @@ static int of_load_pse_pis(struct pse_controller_dev *pcdev) ret = of_load_pse_pi_pairsets(node, &pi, ret); if (ret) goto out; - } else if (ret != ENOENT) { + } else if (ret != -ENOENT) { dev_err(pcdev->dev, "error: wrong number of pairsets. Should be 1 or 2, got %d (%pOF)\n", ret, node); From 57b0ac5e1b46f1f0338dff392ef2092e2871b412 Mon Sep 17 00:00:00 2001 From: Zhengchuan Liang Date: Wed, 13 May 2026 15:57:17 +0800 Subject: [PATCH 1204/1518] netfilter: ip6t_hbh: reject oversized option lists commit 4322dcde6b4173c2d8e8e6118ed290794263bcc8 upstream. struct ip6t_opts stores at most IP6T_OPTS_OPTSNR option descriptors, but hbh_mt6_check() does not reject larger optsnr values supplied from userspace. Validate optsnr in the rule setup path so only match data that fits the fixed-size opts array can be installed. This follows the existing xtables pattern of rejecting invalid user-provided counts in checkentry() and keeps the packet matching path unchanged. `struct ip6t_opts` has a fixed `opts[IP6T_OPTS_OPTSNR]` array, where `IP6T_OPTS_OPTSNR` is 16, then off-by-one array access is possible: [ 137.924693][ T8692] UBSAN: array-index-out-of-bounds in ../net/ipv6/netfilter/ip6t_hbh.c:110:29 [ 137.926167][ T8692] index 16 is out of range for type '__u16 [16]' Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Zhengchuan Liang Signed-off-by: Ren Wei Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/ipv6/netfilter/ip6t_hbh.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index e7a3fb9355ee3..450dd53846a2f 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -168,6 +168,10 @@ static int hbh_mt6_check(const struct xt_mtchk_param *par) pr_debug("unknown flags %X\n", optsinfo->invflags); return -EINVAL; } + if (optsinfo->optsnr > IP6T_OPTS_OPTSNR) { + pr_debug("too many supported opts specified\n"); + return -EINVAL; + } if (optsinfo->flags & IP6T_OPTS_NSTRICT) { pr_debug("Not strict - not implemented"); From 15d464265120ab9818bd673af301deee09bedab2 Mon Sep 17 00:00:00 2001 From: Haoze Xie Date: Fri, 15 May 2026 11:19:02 +0800 Subject: [PATCH 1205/1518] netfilter: nf_queue: hold bridge skb->dev while queued commit e196115ec330a18de415bdb9f5071aa9f08e53ce upstream. br_pass_frame_up() rewrites skb->dev from the ingress port to the bridge master before queueing bridge LOCAL_IN packets. NFQUEUE only holds references on state.in/out and bridge physdevs, so a queued bridge packet can retain a freed bridge master in skb->dev until reinjection. When the verdict is reinjected later, br_netif_receive_skb() re-enters the receive path with skb->dev still pointing at the freed bridge master, triggering a use-after-free. Store skb->dev in the queue entry, hold a reference on it for the queue lifetime, and use the saved device when dropping queued packets during NETDEV_DOWN handling. Fixes: ac2863445686 ("netfilter: bridge: add nf_afinfo to enable queuing to userspace") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Haoze Xie Signed-off-by: Ren Wei Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_queue.h | 1 + net/netfilter/nf_queue.c | 4 +++- net/netfilter/nfnetlink_queue.c | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index d17035d14d96c..3978c3174cdbe 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -14,6 +14,7 @@ struct nf_queue_entry { struct list_head list; struct rhash_head hash_node; struct sk_buff *skb; + struct net_device *skb_dev; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 7f12e56e6e526..dd416c8532c55 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -60,6 +60,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) struct nf_hook_state *state = &entry->state; /* Release those devices we held, or Alexey will kill me. */ + dev_put(entry->skb_dev); dev_put(state->in); dev_put(state->out); if (state->sk) @@ -101,6 +102,7 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) return false; + dev_hold(entry->skb_dev); dev_hold(state->in); dev_hold(state->out); @@ -201,11 +203,11 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, *entry = (struct nf_queue_entry) { .skb = skb, + .skb_dev = skb->dev, .state = *state, .hook_index = index, .size = sizeof(*entry) + route_key_size, }; - __nf_queue_entry_init_physdevs(entry); if (!nf_queue_entry_get_refs(entry)) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index fe5942535245d..d42e8ac3062fb 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1198,6 +1198,8 @@ dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) if (physinif == ifindex || physoutif == ifindex) return 1; #endif + if (entry->skb_dev && entry->skb_dev->ifindex == ifindex) + return 1; if (entry->state.in) if (entry->state.in->ifindex == ifindex) return 1; From 952e988163c2ab9939c3db9f0f8e77af6a1bb436 Mon Sep 17 00:00:00 2001 From: Nan Li Date: Tue, 12 May 2026 16:50:01 +0800 Subject: [PATCH 1206/1518] netfilter: ipset: stop hash:* range iteration at end commit 0d3a282ab5f165fc207ff49ea5b6ad8f54616bd6 upstream. The following hash set variants: hash:ip,mark hash:ip,port hash:ip,port,ip hash:ip,port,net iterate IPv4 ranges with a 32-bit iterator. The iterator must stop once the last address in the requested range has been processed. Advancing it once more can move the traversal state past the end of the request, so a later retry may continue from an unintended position. Handle the iterator increment explicitly at the end of the loop and stop once the upper bound has been processed. This keeps the existing retry behaviour intact for valid ranges while preventing traversal from continuing past the original boundary. Fixes: 48596a8ddc46 ("netfilter: ipset: Fix adding an IPv4 range containing more than 2^31 addresses") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Nan Li Signed-off-by: Ren Wei Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/ipset/ip_set_hash_ipmark.c | 6 +++++- net/netfilter/ipset/ip_set_hash_ipport.c | 5 ++++- net/netfilter/ipset/ip_set_hash_ipportip.c | 5 ++++- net/netfilter/ipset/ip_set_hash_ipportnet.c | 5 ++++- 4 files changed, 17 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index a22ec1a6f6ec8..e26ca2a370e34 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -150,7 +150,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++, i++) { + for (; ip <= ip_to; i++) { e.ip = htonl(ip); if (i > IPSET_MAX_RANGE) { hash_ipmark4_data_next(&h->next, &e); @@ -162,6 +162,10 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; ret = 0; + + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e977b5a9c48dc..41ca24a22a026 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -186,7 +186,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to;) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { @@ -203,6 +203,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], ret = 0; } + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 39a01934b1536..b9ac2efaa15c7 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -182,7 +182,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to;) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { @@ -199,6 +199,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = 0; } + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5c6de605a9fb7..2d6652d43199a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -274,7 +274,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], p = port; ip2 = ip2_from; } - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to;) { e.ip = htonl(ip); for (; p <= port_to; p++) { e.port = htons(p); @@ -298,6 +298,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip2 = ip2_from; } p = port; + if (ip == ip_to) + break; + ip++; } return ret; } From 689bbf48c1f45130086ae1c46ab83ea4c753c601 Mon Sep 17 00:00:00 2001 From: Yizhou Zhao Date: Tue, 12 May 2026 01:30:41 +0800 Subject: [PATCH 1207/1518] netfilter: nft_inner: Fix IPv6 inner_thoff desync MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b6a91f68ebfed9c38e0e9150f58a9b85da07181c upstream. In nft_inner_parse_l2l3(), when processing inner IPv6 packets, ipv6_find_hdr() correctly computes the transport header offset traversing all extension headers, but the result is immediately overwritten with nhoff + sizeof(_ip6h) (40 bytes), which only accounts for the IPv6 base header. This creates a desync between inner_thoff (wrong — points to extension header start) and l4proto (correct — e.g., IPPROTO_TCP), enabling transport header forgery and potential firewall bypass. This issue affects stable versions from Linux 6.2. For comparison, the normal (non-inner) IPv6 path correctly preserves ipv6_find_hdr()'s result. Removing the incorrect overwrite ensures that ipv6_find_hdr()'s calculated transport header offset is preserved, thereby fixing the desynchronization. Fixes: 3a07327d10a0 ("netfilter: nft_inner: support for inner tunnel header matching") Cc: stable@vger.kernel.org Reported-by: Yizhou Zhao Reported-by: Yuxiang Yang Reported-by: Xuewei Feng Reported-by: Qi Li Reported-by: Ke Xu Assisted-by: GLM:5.1 Z.ai Signed-off-by: Yizhou Zhao Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nft_inner.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index c4569d4b92285..1b3e7a976f560 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -163,7 +163,6 @@ static int nft_inner_parse_l2l3(const struct nft_inner *priv, return -1; if (fragoff == 0) { - thoff = nhoff + sizeof(_ip6h); ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; ctx->inner_thoff = thoff; ctx->l4proto = l4proto; From 6e73ec10b2a32b1126423a71f2c4247041048d81 Mon Sep 17 00:00:00 2001 From: Samuele Mariotti Date: Thu, 21 May 2026 09:53:57 -0400 Subject: [PATCH 1208/1518] sched_ext: Fix missing warning in scx_set_task_state() default case [ Upstream commit b905ee77d5f557a83a485b4146210f54f13365fc ] In scx_set_task_state(), the default case was setting the warn flag, but then returning immediately. This is problematic because the only purpose of the warn flag is to trigger WARN_ONCE, but the early return prevented it from ever firing, leaving invalid task states undetected and untraced. To fix this, a WARN_ONCE call is now added directly in the default case. The fix addresses two aspects: - Guarantees the invalid task states are properly logged and traced. - Provides a distinct warning message ("sched_ext: Invalid task state") specifically for states outside the defined scx_task_state enum values, making it easier to distinguish from other transition warnings. This ensures proper detection and reporting of invalid states. Signed-off-by: Samuele Mariotti Signed-off-by: Paolo Valente Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo Stable-dep-of: 9a415cc53711 ("sched_ext: Avoid UAF in scx_root_enable_workfn() init failure path") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/sched/ext.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 3029e5b8f9a57..2cfd321d92367 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2800,7 +2800,8 @@ static void scx_set_task_state(struct task_struct *p, enum scx_task_state state) warn = prev_state != SCX_TASK_READY; break; default: - warn = true; + WARN_ONCE(1, "sched_ext: Invalid task state %d -> %d for %s[%d]", + prev_state, state, p->comm, p->pid); return; } From 45c7c4e3db8b700307313c035ea08be829a7f21b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 21 May 2026 09:53:58 -0400 Subject: [PATCH 1209/1518] sched_ext: Avoid UAF in scx_root_enable_workfn() init failure path [ Upstream commit 9a415cc53711f2238e0f0ca8a6bcc796c003b127 ] In scx_root_enable_workfn(), put_task_struct(p) is called before scx_error() dereferences p->comm and p->pid. If the iterator's reference is the last drop, the task is freed synchronously and the deref becomes a UAF. Move put_task_struct() past scx_error(). Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260511214031.AF5E9C2BCB0@smtp.kernel.org/ Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class") Cc: stable@vger.kernel.org # v6.12+ Signed-off-by: Tejun Heo [ kept `scx_init_task()` call site instead of `__scx_init_task()`/`task_rq_lock` ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 2cfd321d92367..7b750bf42698c 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4812,10 +4812,10 @@ static void scx_enable_workfn(struct kthread_work *work) ret = scx_init_task(p, task_group(p), false); if (ret) { - put_task_struct(p); scx_task_iter_stop(&sti); scx_error(sch, "ops.init_task() failed (%d) for %s[%d]", ret, p->comm, p->pid); + put_task_struct(p); goto err_disable_unlock_all; } From 52cc572c95655ad71cdde4e494abf770efe9e233 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 21 May 2026 08:58:10 -0400 Subject: [PATCH 1210/1518] tracing: fprobe: Remove unused local variable [ Upstream commit 90e69d291d195d35215b578d210fd3ce0e5a3f42 ] The 'ret' local variable in fprobe_remove_node_in_module() was used for checking the error state in the loop, but commit dfe0d675df82 ("tracing: fprobe: use rhltable for fprobe_ip_table") removed the loop. So we don't need it anymore. Link: https://lore.kernel.org/all/175867358989.600222.6175459620045800878.stgit@devnote2/ Fixes: e5a4cc28a052 ("tracing: fprobe: use rhltable for fprobe_ip_table") Signed-off-by: Masami Hiramatsu (Google) Acked-by: Menglong Dong Stable-dep-of: 0ac0058a74ac ("tracing/fprobe: Check the same type fprobe on table as the unregistered one") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 8fa5bff2c26fa..51003d85933d9 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -561,8 +561,6 @@ static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long ad static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, struct fprobe_addr_list *alist) { - int ret = 0; - if (!within_module(node->addr, mod)) return; if (delete_fprobe_node(node)) @@ -571,8 +569,7 @@ static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist * If failed to update alist, just continue to update hlist. * Therefore, at list user handler will not hit anymore. */ - if (!ret) - ret = fprobe_addr_list_add(alist, node->addr); + fprobe_addr_list_add(alist, node->addr); } /* Handle module unloading to manage fprobe_ip_table. */ From bb92f356d2b73bc65ea20919a0e39efdf538f5cd Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 21 May 2026 08:58:11 -0400 Subject: [PATCH 1211/1518] tracing: fprobe: use ftrace if CONFIG_DYNAMIC_FTRACE_WITH_ARGS [ Upstream commit cd06078a38aaedfebbf8fa0c009da0f99f4473fb ] For now, we will use ftrace for the fprobe if fp->exit_handler not exists and CONFIG_DYNAMIC_FTRACE_WITH_REGS is enabled. However, CONFIG_DYNAMIC_FTRACE_WITH_REGS is not supported by some arch, such as arm. What we need in the fprobe is the function arguments, so we can use ftrace for fprobe if CONFIG_DYNAMIC_FTRACE_WITH_ARGS is enabled. Therefore, use ftrace if CONFIG_DYNAMIC_FTRACE_WITH_REGS or CONFIG_DYNAMIC_FTRACE_WITH_ARGS enabled. Link: https://lore.kernel.org/all/20251103063434.47388-1-dongml2@chinatelecom.cn/ Signed-off-by: Menglong Dong Signed-off-by: Masami Hiramatsu (Google) Stable-dep-of: 0ac0058a74ac ("tracing/fprobe: Check the same type fprobe on table as the unregistered one") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 51003d85933d9..574f2886cc9e3 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -45,6 +45,7 @@ static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE]; static struct rhltable fprobe_ip_table; static DEFINE_MUTEX(fprobe_mutex); +static struct fgraph_ops fprobe_graph_ops; static u32 fprobe_node_hashfn(const void *data, u32 len, u32 seed) { @@ -259,7 +260,7 @@ static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent return ret; } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#if defined(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) || defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) /* ftrace_ops callback, this processes fprobes which have only entry_handler. */ static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) @@ -300,7 +301,7 @@ NOKPROBE_SYMBOL(fprobe_ftrace_entry); static struct ftrace_ops fprobe_ftrace_ops = { .func = fprobe_ftrace_entry, - .flags = FTRACE_OPS_FL_SAVE_REGS, + .flags = FTRACE_OPS_FL_SAVE_ARGS, }; static int fprobe_ftrace_active; @@ -341,6 +342,15 @@ static bool fprobe_is_ftrace(struct fprobe *fp) { return !fp->exit_handler; } + +#ifdef CONFIG_MODULES +static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove, + int reset) +{ + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset); + ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset); +} +#endif #else static int fprobe_ftrace_add_ips(unsigned long *addrs, int num) { @@ -355,7 +365,15 @@ static bool fprobe_is_ftrace(struct fprobe *fp) { return false; } + +#ifdef CONFIG_MODULES +static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove, + int reset) +{ + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset); +} #endif +#endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ /* fgraph_ops callback, this processes fprobes which have exit_handler. */ static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, @@ -601,14 +619,8 @@ static int fprobe_module_callback(struct notifier_block *nb, } while (node == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); - if (alist.index > 0) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, - alist.addrs, alist.index, 1, 0); -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - ftrace_set_filter_ips(&fprobe_ftrace_ops, - alist.addrs, alist.index, 1, 0); -#endif - } + if (alist.index > 0) + fprobe_set_ips(alist.addrs, alist.index, 1, 0); mutex_unlock(&fprobe_mutex); kfree(alist.addrs); From f0ad68d2f0adbeae50140c944d5676a58bf92aa6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 21 May 2026 08:58:12 -0400 Subject: [PATCH 1212/1518] tracing/fprobe: Avoid kcalloc() in rcu_read_lock section [ Upstream commit aa72812b49104bb5a38272fc9541feb62ca6fd32 ] fprobe_remove_node_in_module() is called under RCU read locked, but this invokes kcalloc() if there are more than 8 fprobes installed on the module. Sashiko warns it because kcalloc() can sleep [1]. [1] https://sashiko.dev/#/patchset/177552432201.853249.5125045538812833325.stgit%40mhiramat.tok.corp.google.com To fix this issue, expand the batch size to 128 and do not expand the fprobe_addr_list, but just cancel walking on fprobe_ip_table, update fgraph/ftrace_ops and retry the loop again. Link: https://lore.kernel.org/all/177669367206.132053.1493637946869032744.stgit@mhiramat.tok.corp.google.com/ Fixes: 0de4c70d04a4 ("tracing: fprobe: use rhltable for fprobe_ip_table") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Stable-dep-of: 0ac0058a74ac ("tracing/fprobe: Check the same type fprobe on table as the unregistered one") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 92 +++++++++++++++++++++---------------------- 1 file changed, 45 insertions(+), 47 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 574f2886cc9e3..37a4352efb4da 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -344,11 +344,10 @@ static bool fprobe_is_ftrace(struct fprobe *fp) } #ifdef CONFIG_MODULES -static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove, - int reset) +static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset); - ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset); + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); + ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0); } #endif #else @@ -367,10 +366,9 @@ static bool fprobe_is_ftrace(struct fprobe *fp) } #ifdef CONFIG_MODULES -static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove, - int reset) +static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset); + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); } #endif #endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ @@ -543,7 +541,7 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) #ifdef CONFIG_MODULES -#define FPROBE_IPS_BATCH_INIT 8 +#define FPROBE_IPS_BATCH_INIT 128 /* instruction pointer address list */ struct fprobe_addr_list { int index; @@ -551,45 +549,24 @@ struct fprobe_addr_list { unsigned long *addrs; }; -static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long addr) +static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, + struct fprobe_addr_list *alist) { - unsigned long *addrs; - - /* Previously we failed to expand the list. */ - if (alist->index == alist->size) - return -ENOSPC; - - alist->addrs[alist->index++] = addr; - if (alist->index < alist->size) + if (!within_module(node->addr, mod)) return 0; - /* Expand the address list */ - addrs = kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL); - if (!addrs) - return -ENOMEM; - - memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs)); - alist->size *= 2; - kfree(alist->addrs); - alist->addrs = addrs; + if (delete_fprobe_node(node)) + return 0; + /* If no address list is available, we can't track this address. */ + if (!alist->addrs) + return 0; + alist->addrs[alist->index++] = node->addr; + if (alist->index == alist->size) + return -ENOSPC; return 0; } -static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, - struct fprobe_addr_list *alist) -{ - if (!within_module(node->addr, mod)) - return; - if (delete_fprobe_node(node)) - return; - /* - * If failed to update alist, just continue to update hlist. - * Therefore, at list user handler will not hit anymore. - */ - fprobe_addr_list_add(alist, node->addr); -} - /* Handle module unloading to manage fprobe_ip_table. */ static int fprobe_module_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -598,29 +575,50 @@ static int fprobe_module_callback(struct notifier_block *nb, struct fprobe_hlist_node *node; struct rhashtable_iter iter; struct module *mod = data; + bool retry; if (val != MODULE_STATE_GOING) return NOTIFY_DONE; alist.addrs = kcalloc(alist.size, sizeof(*alist.addrs), GFP_KERNEL); - /* If failed to alloc memory, we can not remove ips from hash. */ - if (!alist.addrs) - return NOTIFY_DONE; + /* + * If failed to alloc memory, ftrace_ops will not be able to remove ips from + * hash, but we can still remove nodes from fprobe_ip_table, so we can avoid + * the potential wrong callback. So just print a warning here and try to + * continue without address list. + */ + WARN_ONCE(!alist.addrs, + "Failed to allocate memory for fprobe_addr_list, ftrace_ops will not be updated"); mutex_lock(&fprobe_mutex); +again: + retry = false; + alist.index = 0; rhltable_walk_enter(&fprobe_ip_table, &iter); do { rhashtable_walk_start(&iter); while ((node = rhashtable_walk_next(&iter)) && !IS_ERR(node)) - fprobe_remove_node_in_module(mod, node, &alist); + if (fprobe_remove_node_in_module(mod, node, &alist) < 0) { + retry = true; + break; + } rhashtable_walk_stop(&iter); - } while (node == ERR_PTR(-EAGAIN)); + } while (node == ERR_PTR(-EAGAIN) && !retry); rhashtable_walk_exit(&iter); + /* Remove any ips from hash table(s) */ + if (alist.index > 0) { + fprobe_remove_ips(alist.addrs, alist.index); + /* + * If we break rhashtable walk loop except for -EAGAIN, we need + * to restart looping from start for safety. Anyway, this is + * not a hotpath. + */ + if (retry) + goto again; + } - if (alist.index > 0) - fprobe_set_ips(alist.addrs, alist.index, 1, 0); mutex_unlock(&fprobe_mutex); kfree(alist.addrs); From 1aed73795392d64193a4d8f30bbe355bca7d92fd Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 21 May 2026 08:58:13 -0400 Subject: [PATCH 1213/1518] tracing/fprobe: Check the same type fprobe on table as the unregistered one [ Upstream commit 0ac0058a74ac5765c7ce09ea630f4fdeaf4d80fa ] Commit 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case") introduced a different ftrace_ops for entry-only fprobes. However, when unregistering an fprobe, the kernel only checks if another fprobe exists at the same address, without checking which type of fprobe it is. If different fprobes are registered at the same address, the same address will be registered in both fgraph_ops and ftrace_ops, but only one of them will be deleted when unregistering. (the one removed first will not be deleted from the ops). This results in junk entries remaining in either fgraph_ops or ftrace_ops. For example: ======= cd /sys/kernel/tracing # 'Add entry and exit events on the same place' echo 'f:event1 vfs_read' >> dynamic_events echo 'f:event2 vfs_read%return' >> dynamic_events # 'Enable both of them' echo 1 > events/fprobes/enable cat enabled_functions vfs_read (2) ->arch_ftrace_ops_list_func+0x0/0x210 # 'Disable and remove exit event' echo 0 > events/fprobes/event2/enable echo -:event2 >> dynamic_events # 'Disable and remove all events' echo 0 > events/fprobes/enable echo > dynamic_events # 'Add another event' echo 'f:event3 vfs_open%return' > dynamic_events cat dynamic_events f:fprobes/event3 vfs_open%return echo 1 > events/fprobes/enable cat enabled_functions vfs_open (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150} vfs_read (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150} ======= As you can see, an entry for the vfs_read remains. To fix this issue, when unregistering, the kernel should also check if there is the same type of fprobes still exist at the same address, and if not, delete its entry from either fgraph_ops or ftrace_ops. Link: https://lore.kernel.org/all/177669367993.132053.10553046138528674802.stgit@mhiramat.tok.corp.google.com/ Fixes: 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/trace/fprobe.c | 82 ++++++++++++++++++++++++++++++++++--------- 1 file changed, 65 insertions(+), 17 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 37a4352efb4da..6419c8d772731 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -92,11 +92,8 @@ static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) return ret; } -/* Return true if there are synonims */ -static bool delete_fprobe_node(struct fprobe_hlist_node *node) +static void delete_fprobe_node(struct fprobe_hlist_node *node) { - bool ret; - lockdep_assert_held(&fprobe_mutex); /* Avoid double deleting and non-inserted nodes */ @@ -105,13 +102,6 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node) rhltable_remove(&fprobe_ip_table, &node->hlist, fprobe_rht_params); } - - rcu_read_lock(); - ret = !!rhltable_lookup(&fprobe_ip_table, &node->addr, - fprobe_rht_params); - rcu_read_unlock(); - - return ret; } /* Check existence of the fprobe */ @@ -343,6 +333,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return !fp->exit_handler; } +static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace) +{ + struct rhlist_head *head, *pos; + struct fprobe_hlist_node *node; + struct fprobe *fp; + + guard(rcu)(); + head = rhltable_lookup(&fprobe_ip_table, &ip, + fprobe_rht_params); + if (!head) + return false; + /* We have to check the same type on the list. */ + rhl_for_each_entry_rcu(node, pos, head, hlist) { + if (node->addr != ip) + break; + fp = READ_ONCE(node->fp); + if (likely(fp)) { + if ((!ftrace && fp->exit_handler) || + (ftrace && !fp->exit_handler)) + return true; + } + } + + return false; +} + #ifdef CONFIG_MODULES static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { @@ -365,6 +381,29 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return false; } +static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused) +{ + struct rhlist_head *head, *pos; + struct fprobe_hlist_node *node; + struct fprobe *fp; + + guard(rcu)(); + head = rhltable_lookup(&fprobe_ip_table, &ip, + fprobe_rht_params); + if (!head) + return false; + /* We only need to check fp is there. */ + rhl_for_each_entry_rcu(node, pos, head, hlist) { + if (node->addr != ip) + break; + fp = READ_ONCE(node->fp); + if (likely(fp)) + return true; + } + + return false; +} + #ifdef CONFIG_MODULES static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { @@ -552,18 +591,25 @@ struct fprobe_addr_list { static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, struct fprobe_addr_list *alist) { + lockdep_assert_in_rcu_read_lock(); + if (!within_module(node->addr, mod)) return 0; - if (delete_fprobe_node(node)) - return 0; + delete_fprobe_node(node); /* If no address list is available, we can't track this address. */ if (!alist->addrs) return 0; + /* + * Don't care the type here, because all fprobes on the same + * address must be removed eventually. + */ + if (!rhltable_lookup(&fprobe_ip_table, &node->addr, fprobe_rht_params)) { + alist->addrs[alist->index++] = node->addr; + if (alist->index == alist->size) + return -ENOSPC; + } - alist->addrs[alist->index++] = node->addr; - if (alist->index == alist->size) - return -ENOSPC; return 0; } @@ -934,7 +980,9 @@ static int unregister_fprobe_nolock(struct fprobe *fp) /* Remove non-synonim ips from table and hash */ count = 0; for (i = 0; i < hlist_array->size; i++) { - if (!delete_fprobe_node(&hlist_array->array[i]) && addrs) + delete_fprobe_node(&hlist_array->array[i]); + if (addrs && !fprobe_exists_on_hash(hlist_array->array[i].addr, + fprobe_is_ftrace(fp))) addrs[count++] = hlist_array->array[i].addr; } del_fprobe_hash(fp); From 752ea4a105e6f42cabbb70e335baab3b5b2ddafd Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Fri, 22 May 2026 08:54:20 -0400 Subject: [PATCH 1214/1518] cgroup/cpuset: Reset DL migration state on can_attach() failure [ Upstream commit 4a39eda5fdd867fc39f3c039714dd432cee00268 ] cpuset_can_attach() accumulates temporary SCHED_DEADLINE migration state in the destination cpuset while walking the taskset. If a later task_can_attach() or security_task_setscheduler() check fails, cgroup_migrate_execute() treats cpuset as the failing subsystem and does not call cpuset_cancel_attach() for it. The partially accumulated state is then left behind and can be consumed by a later attach, corrupting cpuset DL task accounting and pending DL bandwidth accounting. Reset the pending DL migration state from the common error exit when ret is non-zero. Successful can_attach() keeps the state for cpuset_attach() or cpuset_cancel_attach(). Fixes: 2ef269ef1ac0 ("cgroup/cpuset: Free DL BW in case can_attach() fails") Cc: stable@vger.kernel.org # v6.10+ Signed-off-by: Guopeng Zhang Signed-off-by: Tejun Heo Reviewed-by: Chen Ridong Reviewed-by: Waiman Long [ omitted upstream context line `cs->dl_bw_cpu = cpu;` ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/cpuset.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 08b0c264bd268..5057cf44342b5 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3163,16 +3163,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) { - reset_migrate_dl_data(cs); ret = -EINVAL; goto out_unlock; } ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); - if (ret) { - reset_migrate_dl_data(cs); + if (ret) goto out_unlock; - } } out_success: @@ -3181,7 +3178,10 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; + out_unlock: + if (ret) + reset_migrate_dl_data(cs); mutex_unlock(&cpuset_mutex); return ret; } From 61f53c1e58d68723bc1db10912a53f1991f08719 Mon Sep 17 00:00:00 2001 From: Quan Sun <2022090917019@std.uestc.edu.cn> Date: Fri, 22 May 2026 09:02:59 -0400 Subject: [PATCH 1215/1518] net: ethtool: fix NULL pointer dereference in phy_reply_size [ Upstream commit 4908f1395fb1b832ceec11584af649874a2732ea ] In phy_prepare_data(), several strings such as 'name', 'drvname', 'upstream_sfp_name', and 'downstream_sfp_name' are allocated using kstrdup(). However, these allocations were not checked for failure. If kstrdup() fails for 'name', it returns NULL while the function continues. This leads to a kernel NULL pointer dereference and panic later in phy_reply_size() when it unconditionally calls strlen() on the NULL pointer. While other strings like 'upstream_sfp_name' might be checked before access in certain code paths, failing to handle these allocations consistently can lead to incomplete data reporting or hidden bugs. Fix this by adding proper NULL checks for all kstrdup() calls in phy_prepare_data() and implement a centralized error handling path using goto labels to ensure all previously allocated resources are freed on failure. Fixes: 9dd2ad5e92b9 ("net: ethtool: phy: Convert the PHY_GET command to generic phy dump") Signed-off-by: Quan Sun <2022090917019@std.uestc.edu.cn> Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20260507131738.1173835-1-2022090917019@std.uestc.edu.cn Signed-off-by: Jakub Kicinski Stable-dep-of: e3adf69f8eb1 ("net: ethtool: phy: avoid NULL deref when PHY driver is unbound") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/ethtool/phy.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c index 68372bef4b2fe..cb1e0aea450f9 100644 --- a/net/ethtool/phy.c +++ b/net/ethtool/phy.c @@ -76,6 +76,7 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, struct nlattr **tb = info->attrs; struct phy_device_node *pdn; struct phy_device *phydev; + int ret; /* RTNL is held by the caller */ phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER, @@ -88,8 +89,17 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, return -EOPNOTSUPP; rep_data->phyindex = phydev->phyindex; + rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL); + if (!rep_data->name) + return -ENOMEM; + rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); + if (!rep_data->drvname) { + ret = -ENOMEM; + goto err_free_name; + } + rep_data->upstream_type = pdn->upstream_type; if (pdn->upstream_type == PHY_UPSTREAM_PHY) { @@ -97,15 +107,33 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, rep_data->upstream_index = upstream->phyindex; } - if (pdn->parent_sfp_bus) + if (pdn->parent_sfp_bus) { rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus), GFP_KERNEL); + if (!rep_data->upstream_sfp_name) { + ret = -ENOMEM; + goto err_free_drvname; + } + } - if (phydev->sfp_bus) + if (phydev->sfp_bus) { rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus), GFP_KERNEL); + if (!rep_data->downstream_sfp_name) { + ret = -ENOMEM; + goto err_free_upstream_sfp; + } + } return 0; + +err_free_upstream_sfp: + kfree(rep_data->upstream_sfp_name); +err_free_drvname: + kfree(rep_data->drvname); +err_free_name: + kfree(rep_data->name); + return ret; } static int phy_fill_reply(struct sk_buff *skb, From 3586924625559e6f9876d726c80ff0a75f0d5849 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 22 May 2026 09:03:00 -0400 Subject: [PATCH 1216/1518] net: ethtool: phy: avoid NULL deref when PHY driver is unbound [ Upstream commit e3adf69f8eb121a9128c2b0029efd050d3649153 ] phydev->drv can become NULL while the phy_device is still attached to its net_device, namely after the PHY driver is unbound via sysfs: echo > /sys/bus/mdio_bus/drivers//unbind phy_remove() clears phydev->drv but doesn't call phy_detach(), so the phy_device stays in the link topology xarray and ethnl_req_get_phydev() still hands it back. ETHTOOL_MSG_PHY_GET then oopses on: rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); drvname is already treated as optional by phy_reply_size(), phy_fill_reply() and phy_cleanup_data(), so just skip the allocation when there is no driver bound. Fixes: 9dd2ad5e92b9 ("net: ethtool: phy: Convert the PHY_GET command to generic phy dump") Cc: stable@vger.kernel.org # 6.13.x Signed-off-by: David Carlier Reviewed-by: Maxime Chevallier Tested-by: Maxime Chevallier Link: https://patch.msgid.link/20260509215046.107157-1-devnexen@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/ethtool/phy.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c index cb1e0aea450f9..98392a3c34b5b 100644 --- a/net/ethtool/phy.c +++ b/net/ethtool/phy.c @@ -94,10 +94,12 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, if (!rep_data->name) return -ENOMEM; - rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); - if (!rep_data->drvname) { - ret = -ENOMEM; - goto err_free_name; + if (phydev->drv) { + rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); + if (!rep_data->drvname) { + ret = -ENOMEM; + goto err_free_name; + } } rep_data->upstream_type = pdn->upstream_type; From d73dcd1520d65a34420761641a36b951b14c8c53 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Thu, 28 May 2026 11:20:28 +0800 Subject: [PATCH 1217/1518] fs/ntfs3: handle attr_set_size() errors when truncating files [ Upstream commit 576248a34b927e93b2fd3fff7df735ba73ad7d01 ] If attr_set_size() fails while truncating down, the error is silently ignored and the inode may be left in an inconsistent state. Signed-off-by: Konstantin Komarov [ Minor context conflict resolved. ] Signed-off-by: Bin Lan Signed-off-by: Greg Kroah-Hartman --- fs/ntfs3/file.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index cd7aaeef45fe9..5042eb321eb89 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -458,8 +458,8 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) { struct super_block *sb = inode->i_sb; struct ntfs_inode *ni = ntfs_i(inode); - int err, dirty = 0; u64 new_valid; + int err; if (!S_ISREG(inode->i_mode)) return 0; @@ -475,7 +475,6 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) } new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size)); - truncate_setsize(inode, new_size); ni_lock(ni); @@ -489,22 +488,19 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) ni->i_valid = new_valid; ni_unlock(ni); + if (unlikely(err)) + return err; ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE; inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (!IS_DIRSYNC(inode)) { - dirty = 1; + mark_inode_dirty(inode); } else { err = ntfs_sync_inode(inode); if (err) return err; } - if (dirty) - mark_inode_dirty(inode); - - /*ntfs_flush_inodes(inode->i_sb, inode, NULL);*/ - return 0; } From e0c3dd7b30cc5ee42ab502da140cda93d794a20b Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Mon, 18 May 2026 14:34:47 -0400 Subject: [PATCH 1218/1518] l2tp: use list_del_rcu in l2tp_session_unhash commit 979c017803c40829b03acd9e5236e354b7622360 upstream. An unprivileged local user can pin a host CPU indefinitely in l2tp_session_get_by_ifname() by issuing L2TP_CMD_SESSION_GET on L2TP_ATTR_IFNAME concurrently with L2TP_CMD_SESSION_CREATE and L2TP_CMD_SESSION_DELETE on the same tunnel. All three commands take GENL_UNS_ADMIN_PERM, so CAP_NET_ADMIN in the netns user namespace suffices; on any host that has l2tp_core loaded the trigger is reachable from a standard `unshare -Urn` sandbox. l2tp_session_unhash() removes a session from tunnel->session_list with list_del_init(), but that list is walked by l2tp_session_get_by_ifname() with list_for_each_entry_rcu() under rcu_read_lock_bh(). list_del_init() leaves the deleted entry's next/prev self-pointing; a reader that has loaded the entry and then advances pos->list.next reads &session->list, container_of()s back to the same session, and list_for_each_entry_rcu() never reaches the list head. The CPU stays in strcmp() inside the walker, with BH and preemption disabled, so RCU grace periods on the host stall behind it and the wedged thread cannot be killed (SIGKILL is delivered on syscall return). Use list_del_rcu() to match the existing list_add_rcu() in l2tp_session_register(); the deleted session remains visible to in-flight walkers with consistent next/prev pointers until kfree_rcu() in l2tp_session_free() releases it. tunnel->session_list has exactly one list_del_init() call site; the list_del_init (&session->clist) at l2tp_core.c:533 operates on the per-collision list, which is not walked under RCU. list_empty(&session->list) is not used anywhere in net/l2tp/ after the unhash point, so dropping the post-delete self-init is safe; the fix has no userspace-visible behavior change. Fixes: 89b768ec2dfef ("l2tp: use rcu list add/del when updating lists") Cc: stable@vger.kernel.org # 6.11+ Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/20260518183447.64078-1-michael.bommarito@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 9156a937334ae..be32bf45d5831 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1360,7 +1360,7 @@ static void l2tp_session_unhash(struct l2tp_session *session) spin_lock_bh(&pn->l2tp_session_idr_lock); /* Remove from the per-tunnel list */ - list_del_init(&session->list); + list_del_rcu(&session->list); /* Remove from per-net IDR */ if (tunnel->version == L2TP_HDR_VER_3) { From 0e47fc1c9181ae029e0e35a865cbf2adcbae626c Mon Sep 17 00:00:00 2001 From: Dawei Feng Date: Wed, 20 May 2026 15:03:23 +0800 Subject: [PATCH 1219/1518] qed: fix double free in qed_cxt_tables_alloc() commit 2bccfb8476ca5f3548afbd623dc7a6980d4e77de upstream. If one of the later PF or VF CID bitmap allocations fails, qed_cid_map_alloc() jumps to cid_map_fail and frees the previously allocated CID bitmaps before returning an error. qed_cxt_tables_alloc() then calls qed_cxt_mngr_free(), which invokes qed_cid_map_free() again. Fix this by setting each CID bitmap pointer to NULL after bitmap_free() to avoid double free. The bug was first flagged by an experimental analysis tool we are developing for kernel memory-management bugs while analyzing v6.13-rc1. The tool is still under development and is not yet publicly available. Manual inspection confirms that the bug is still present in v7.1-rc3. Runtime reproduction was not attempted because exercising the failing allocation path requires device-specific setup. Fixes: fe56b9e6a8d9 ("qed: Add module with basic common support") Cc: stable@vger.kernel.org Signed-off-by: Zilin Guan Signed-off-by: Dawei Feng Link: https://patch.msgid.link/20260520070323.2762379-1-dawei.feng@seu.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 33f4f58ee51c6..1fb09372c25a3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -1038,11 +1038,13 @@ static void qed_cid_map_free(struct qed_hwfn *p_hwfn) for (type = 0; type < MAX_CONN_TYPES; type++) { bitmap_free(p_mngr->acquired[type].cid_map); + p_mngr->acquired[type].cid_map = NULL; p_mngr->acquired[type].max_count = 0; p_mngr->acquired[type].start_cid = 0; for (vf = 0; vf < MAX_NUM_VFS; vf++) { bitmap_free(p_mngr->acquired_vf[type][vf].cid_map); + p_mngr->acquired_vf[type][vf].cid_map = NULL; p_mngr->acquired_vf[type][vf].max_count = 0; p_mngr->acquired_vf[type][vf].start_cid = 0; } From 610ff6bc2f44b8beb70ab7913e1da305a1ebfa13 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 20 May 2026 22:08:01 -0400 Subject: [PATCH 1220/1518] ring-buffer: Fix reporting of missed events in iterator commit a254b6d13b0edd6272926674d2afc46d46e496b7 upstream. When tracing is active while reading the trace file, if the iterator reading the buffer detects that the writer has passed the iterator head, it will reset and set a "missed events" flag. This flag is passed to the output processing to show the user that events were missed: CPU:4 [LOST EVENTS] The problem is that the flag is reset after it is checked in ring_buffer_iter_dropped(). But the "trace" file iterates over all the CPU ring buffers and it will check if they are dropped when figuring out which buffer to print next. This prematurely clears the missed_events flag if the CPU buffer with the missed events is not the one that is printed next. On the iteration where the CPU buffer with the missed events is printed, the check if it had missed events would return false and the output does not show that events were missed. Do not reset the missed_events flag when checking if there were missed events, but instead clear it when moving the iterator head to the next event. Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260520220801.4fd09d13@fedora Fixes: c9b7a4a72ff64 ("ring-buffer/tracing: Have iterator acknowledge dropped events") Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ring_buffer.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a31fb4b7a52ea..fdce9101c0b13 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5249,6 +5249,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->head_page = cpu_buffer->reader_page; iter->head = cpu_buffer->reader_page->read; iter->next_event = iter->head; + iter->missed_events = 0; iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; @@ -5863,10 +5864,7 @@ ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, */ bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter) { - bool ret = iter->missed_events != 0; - - iter->missed_events = 0; - return ret; + return iter->missed_events != 0; } EXPORT_SYMBOL_GPL(ring_buffer_iter_dropped); @@ -6028,7 +6026,7 @@ void ring_buffer_iter_advance(struct ring_buffer_iter *iter) unsigned long flags; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - + iter->missed_events = 0; rb_advance_iter(iter); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); From 2bc60c175568ecf0e8b7803dcbf54bd61f3cf76e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 30 Apr 2026 12:28:16 +0900 Subject: [PATCH 1221/1518] ring-buffer: Flush and stop persistent ring buffer on panic commit a494d3c8d5392bcdff83c2a593df0c160ff9f322 upstream. On real hardware, panic and machine reboot may not flush hardware cache to memory. This means the persistent ring buffer, which relies on a coherent state of memory, may not have its events written to the buffer and they may be lost. Moreover, there may be inconsistency with the counters which are used for validation of the integrity of the persistent ring buffer which may cause all data to be discarded. To avoid this issue, stop recording of the ring buffer on panic and flush the cache of the ring buffer's memory. Fixes: e645535a954a ("tracing: Add option to use memmapped memory for trace boot instance") Cc: stable@vger.kernel.org Cc: Will Deacon Cc: Mathieu Desnoyers Cc: Ian Rogers Link: https://patch.msgid.link/177751969602.2136606.12031934362587643488.stgit@mhiramat.tok.corp.google.com Signed-off-by: Masami Hiramatsu (Google) Acked-by: Catalin Marinas Acked-by: Geert Uytterhoeven Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/Kbuild | 1 + arch/arc/include/asm/Kbuild | 1 + arch/arm/include/asm/Kbuild | 1 + arch/arm64/include/asm/ring_buffer.h | 10 ++++++++++ arch/csky/include/asm/Kbuild | 1 + arch/hexagon/include/asm/Kbuild | 1 + arch/loongarch/include/asm/Kbuild | 1 + arch/m68k/include/asm/Kbuild | 1 + arch/microblaze/include/asm/Kbuild | 1 + arch/mips/include/asm/Kbuild | 1 + arch/nios2/include/asm/Kbuild | 1 + arch/openrisc/include/asm/Kbuild | 1 + arch/parisc/include/asm/Kbuild | 1 + arch/powerpc/include/asm/Kbuild | 1 + arch/riscv/include/asm/Kbuild | 1 + arch/s390/include/asm/Kbuild | 1 + arch/sh/include/asm/Kbuild | 1 + arch/sparc/include/asm/Kbuild | 1 + arch/um/include/asm/Kbuild | 1 + arch/x86/include/asm/Kbuild | 1 + arch/xtensa/include/asm/Kbuild | 1 + include/asm-generic/ring_buffer.h | 13 +++++++++++++ kernel/trace/ring_buffer.c | 22 ++++++++++++++++++++++ 23 files changed, 65 insertions(+) create mode 100644 arch/arm64/include/asm/ring_buffer.h create mode 100644 include/asm-generic/ring_buffer.h diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index 483965c5a4de2..b154b4e3dfa86 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -5,4 +5,5 @@ generic-y += agp.h generic-y += asm-offsets.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 4c69522e0328e..483caacc69884 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -5,5 +5,6 @@ generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += user.h generic-y += text-patching.h diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 03657ff8fbe3d..decad5f2c826f 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h generic-y += parport.h +generic-y += ring_buffer.h generated-y += mach-types.h generated-y += unistd-nr.h diff --git a/arch/arm64/include/asm/ring_buffer.h b/arch/arm64/include/asm/ring_buffer.h new file mode 100644 index 0000000000000..62316c4068881 --- /dev/null +++ b/arch/arm64/include/asm/ring_buffer.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_ARM64_RING_BUFFER_H +#define _ASM_ARM64_RING_BUFFER_H + +#include + +/* Flush D-cache on persistent ring buffer */ +#define arch_ring_buffer_flush_range(start, end) dcache_clean_pop(start, end) + +#endif /* _ASM_ARM64_RING_BUFFER_H */ diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index 3a5c7f6e5aacb..7dca0c6cdc848 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -9,6 +9,7 @@ generic-y += qrwlock.h generic-y += qrwlock_types.h generic-y += qspinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += user.h generic-y += vmlinux.lds.h generic-y += text-patching.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 1efa1e993d4b9..0f887d4238edd 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -5,4 +5,5 @@ generic-y += extable.h generic-y += iomap.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index b04d2cef935f6..bdd9f0aa8f71a 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -9,5 +9,6 @@ generic-y += qrwlock.h generic-y += user.h generic-y += ioctl.h generic-y += mmzone.h +generic-y += ring_buffer.h generic-y += statfs.h generic-y += text-patching.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index b282e0dd8dc10..62543bf305ff1 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -3,5 +3,6 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += spinlock.h generic-y += text-patching.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 7178f990e8b3d..0030309b47ad8 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -5,6 +5,7 @@ generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += syscalls.h generic-y += tlb.h generic-y += user.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 684569b2ecd6b..9771c3d85074c 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -12,5 +12,6 @@ generic-y += mcs_spinlock.h generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h +generic-y += ring_buffer.h generic-y += user.h generic-y += text-patching.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 28004301c236f..0a25309644133 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -5,6 +5,7 @@ generic-y += cmpxchg.h generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += spinlock.h generic-y += user.h generic-y += text-patching.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index cef49d60d74c0..8aa34621702de 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -8,4 +8,5 @@ generic-y += spinlock_types.h generic-y += spinlock.h generic-y += qrwlock_types.h generic-y += qrwlock.h +generic-y += ring_buffer.h generic-y += user.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 4fb596d94c893..d48d158f72412 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -4,4 +4,5 @@ generated-y += syscall_table_64.h generic-y += agp.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += user.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 2e23533b67e30..805b5aeebb6f3 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -5,4 +5,5 @@ generated-y += syscall_table_spu.h generic-y += agp.h generic-y += mcs_spinlock.h generic-y += qrwlock.h +generic-y += ring_buffer.h generic-y += early_ioremap.h diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index bd5fc94032953..7721b63642f41 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -14,5 +14,6 @@ generic-y += ticket_spinlock.h generic-y += qrwlock.h generic-y += qrwlock_types.h generic-y += qspinlock.h +generic-y += ring_buffer.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 297bf71579689..2b367fa4de8e4 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -8,3 +8,4 @@ generic-y += asm-offsets.h generic-y += kvm_types.h generic-y += mcs_spinlock.h generic-y += mmzone.h +generic-y += ring_buffer.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 4d3f10ed82758..f0403d3ee8ab8 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -3,4 +3,5 @@ generated-y += syscall_table.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 17ee8a273aa6b..49c6bb326b75b 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -4,4 +4,5 @@ generated-y += syscall_table_64.h generic-y += agp.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index b6810db24ca4d..9be3ee2e37013 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -18,6 +18,7 @@ generic-y += module.lds.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h +generic-y += ring_buffer.h generic-y += runtime-const.h generic-y += softirq_stack.h generic-y += switch_to.h diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4566000e15c44..078fd2c0d69df 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -14,3 +14,4 @@ generic-y += early_ioremap.h generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h +generic-y += ring_buffer.h diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 13fe45dea2961..e57af619263a1 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -6,5 +6,6 @@ generic-y += mcs_spinlock.h generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h +generic-y += ring_buffer.h generic-y += user.h generic-y += text-patching.h diff --git a/include/asm-generic/ring_buffer.h b/include/asm-generic/ring_buffer.h new file mode 100644 index 0000000000000..201d2aee10054 --- /dev/null +++ b/include/asm-generic/ring_buffer.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Generic arch dependent ring_buffer macros. + */ +#ifndef __ASM_GENERIC_RING_BUFFER_H__ +#define __ASM_GENERIC_RING_BUFFER_H__ + +#include + +/* Flush cache on ring buffer range if needed. Do nothing by default. */ +#define arch_ring_buffer_flush_range(start, end) do { } while (0) + +#endif /* __ASM_GENERIC_RING_BUFFER_H__ */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fdce9101c0b13..bef1c05b9b715 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5,6 +5,7 @@ * Copyright (C) 2008 Steven Rostedt */ #include +#include #include #include #include @@ -29,6 +30,7 @@ #include #include +#include #include #include #include @@ -553,6 +555,7 @@ struct trace_buffer { unsigned long range_addr_start; unsigned long range_addr_end; + struct notifier_block flush_nb; struct ring_buffer_meta *meta; @@ -2455,6 +2458,16 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) kfree(cpu_buffer); } +/* Stop recording on a persistent buffer and flush cache if needed. */ +static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data) +{ + struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb); + + ring_buffer_record_off(buffer); + arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end); + return NOTIFY_DONE; +} + static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, int order, unsigned long start, unsigned long end, @@ -2574,6 +2587,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, mutex_init(&buffer->mutex); + /* Persistent ring buffer needs to flush cache before reboot. */ + if (start && end) { + buffer->flush_nb.notifier_call = rb_flush_buffer_cb; + atomic_notifier_chain_register(&panic_notifier_list, &buffer->flush_nb); + } + return_ptr(buffer); fail_free_buffers: @@ -2661,6 +2680,9 @@ ring_buffer_free(struct trace_buffer *buffer) { int cpu; + if (buffer->range_addr_start && buffer->range_addr_end) + atomic_notifier_chain_unregister(&panic_notifier_list, &buffer->flush_nb); + cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); irq_work_sync(&buffer->irq_work.work); From abdd03229414b5a52943b65a60f34b84cea5ac59 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Sun, 17 May 2026 20:30:59 +0200 Subject: [PATCH 1222/1518] ipv6: ioam: add NULL check for idev in ipv6_hop_ioam() commit d4ea0dfd75011b78cebf3808f98ac4c4f51a6fb9 upstream. Reported by Sashiko: The function ipv6_hop_ioam() accesses __in6_dev_get(skb->dev)->cnf.ioam6_enabled without validating the returned idev pointer. Because addrconf_ifdown() can concurrently clear dev->ip6_ptr via RCU, __in6_dev_get() can return NULL during interface teardown, which could cause a NULL pointer dereference when processing an IOAM Hop-by-Hop option. Let's add a check and use SKB_DROP_REASON_IPV6DISABLED accordingly. Fixes: 9ee11f0fff20 ("ipv6: ioam: Data plane support for Pre-allocated Trace") Cc: stable@vger.kernel.org Signed-off-by: Justin Iurman Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260517183059.29140-1-justin.iurman@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/exthdrs.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 9b4ea568b8d7b..d15e609438209 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -910,16 +910,27 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) { + enum skb_drop_reason drop_reason; struct ioam6_trace_hdr *trace; struct ioam6_namespace *ns; + struct inet6_dev *idev; struct ioam6_hdr *hdr; + drop_reason = SKB_DROP_REASON_IP_INHDR; + /* Bad alignment (must be 4n-aligned) */ if (optoff & 3) goto drop; + /* Does the device still have IPv6 configuration? */ + idev = __in6_dev_get(skb->dev); + if (!idev) { + drop_reason = SKB_DROP_REASON_IPV6DISABLED; + goto drop; + } + /* Ignore if IOAM is not enabled on ingress */ - if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) + if (!READ_ONCE(idev->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ @@ -972,7 +983,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) return true; drop: - kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); + kfree_skb_reason(skb, drop_reason); return false; } From 29b6433510127e19f67378f92af6c0cb2ec1c4d4 Mon Sep 17 00:00:00 2001 From: Li Xiasong Date: Fri, 15 May 2026 06:27:33 +0200 Subject: [PATCH 1223/1518] mptcp: pm: fix ADD_ADDR timer infinite retry on option space insufficient commit 51e398a3b8961b26a8c0a4ba9a777c5339791707 upstream. When TCP option space is insufficient (e.g., when sending ADD_ADDR with an IPv6 address and port while tcp_timestamps is enabled), the original code jumped to out_unlock without clearing the addr_signal flag. This caused mptcp_pm_add_timer to keep rescheduling indefinitely, not sending ADD_ADDR, preventing subsequent addresses in the endpoint list from being announced. Handle this case by clearing the ADD_ADDR signal and skipping the matching ADD_ADDR retransmission entry. The skip path cancels the matching timer (with id check) and advances PM state progression, preserving forward progress to subsequent PM work. This cancellation is inherently best-effort. A concurrent add_timer callback may already be running and may acquire pm.lock before the cancel path updates entry state. In that case, one final ADD_ADDR transmit attempt can still be executed. Once the cancel path sets entry->retrans_times to ADD_ADDR_RETRANS_MAX, the callback-side retrans_times check suppresses further ADD_ADDR retransmissions. Note that when an ADD_ADDR is being prepared, a pure-ACK is queued. On the output side, it means that it is fine to skip non-pure-ACK packets, when drop_other_suboptions is set: a pure-ACK will be processed soon after. Fixes: 00cfd77b9063 ("mptcp: retransmit ADD_ADDR when timeout") Cc: stable@vger.kernel.org Signed-off-by: Li Xiasong Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260515-net-mptcp-misc-fixes-7-1-rc4-v2-2-701e96419f2f@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- net/mptcp/pm.c | 56 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 46 insertions(+), 10 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 8523d3af3ca70..6c995cc38a002 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -364,7 +364,13 @@ static void mptcp_pm_add_timer(struct timer_list *timer) spin_lock_bh(&msk->pm.lock); - if (!mptcp_pm_should_add_signal_addr(msk)) { + /* The cancel path (mptcp_pm_del_add_timer()) can race with this + * callback. Once cancel updates retrans_times to MAX, suppress further + * retransmissions here. If this callback acquires pm.lock first, one + * final transmit attempt is still possible. + */ + if (entry->retrans_times < ADD_ADDR_RETRANS_MAX && + !mptcp_pm_should_add_signal_addr(msk)) { pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); @@ -414,8 +420,12 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, /* Note: entry might have been removed by another thread. * We hold rcu_read_lock() to ensure it is not freed under us. */ - if (stop_timer) - sk_stop_timer_sync(sk, &entry->add_timer); + if (stop_timer) { + if (check_id) + sk_stop_timer(sk, &entry->add_timer); + else + sk_stop_timer_sync(sk, &entry->add_timer); + } rcu_read_unlock(); return entry; @@ -880,6 +890,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, struct mptcp_addr_info *addr, bool *echo, bool *drop_other_suboptions) { + bool skip_add_addr = false; int ret = false; u8 add_addr; u8 family; @@ -901,24 +912,49 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, } *echo = mptcp_pm_should_add_signal_echo(msk); - port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); - - family = *echo ? msk->pm.remote.family : msk->pm.local.family; - if (remaining < mptcp_add_addr_len(family, *echo, port)) - goto out_unlock; - if (*echo) { *addr = msk->pm.remote; add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_ECHO); + port = !!msk->pm.remote.port; + family = msk->pm.remote.family; } else { *addr = msk->pm.local; add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_SIGNAL); + port = !!msk->pm.local.port; + family = msk->pm.local.family; } - WRITE_ONCE(msk->pm.addr_signal, add_addr); + + if (remaining < mptcp_add_addr_len(family, *echo, port)) { + struct net *net = sock_net((struct sock *)msk); + + if (!*drop_other_suboptions) + goto out_unlock; + + if (*echo) { + MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP); + } else { + skip_add_addr = true; + MPTCP_INC_STATS(net, MPTCP_MIB_ADDADDRTXDROP); + } + goto drop_signal_mark; + } + ret = true; +drop_signal_mark: + WRITE_ONCE(msk->pm.addr_signal, add_addr); + out_unlock: spin_unlock_bh(&msk->pm.lock); + + /* On pure-ACK option-space exhaustion, stop retrying this ADD_ADDR: + * clear the signal bit, cancel the matching retransmission timer, and + * let the PM state machine progress. + */ + if (skip_add_addr) { + mptcp_pm_del_add_timer(msk, addr, true); + mptcp_pm_subflow_established(msk); + } return ret; } From 440447699c681e26ed58e9c309cad718270a18b4 Mon Sep 17 00:00:00 2001 From: Minh Nguyen Date: Tue, 19 May 2026 17:23:10 +0700 Subject: [PATCH 1224/1518] vsock/vmci: fix UAF when peer resets connection during handshake commit 99e22ddf4edb63dc8382bc028af928056d3450cf upstream. vmci_transport_recv_connecting_server() returned err = 0 for a peer RST in its default switch arm: err = pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST ? 0 : -EINVAL; That made vmci_transport_recv_listen() skip vsock_remove_pending(), leaving the pending socket on the listener's pending_links with sk_state = TCP_CLOSE while destroy: still dropped the explicit reference taken before schedule_delayed_work(). One second later vsock_pending_work() observed is_pending=true and performed full cleanup: vsock_remove_pending() then the two trailing sock_put(sk) calls -- the first reached refcount 0 and __sk_freed the socket, and the second wrote into the freed object: BUG: KASAN: slab-use-after-free in refcount_warn_saturate Write of size 4 at addr ffff88800b1cac80 by task kworker Workqueue: events vsock_pending_work Treat peer RST like any other unexpected packet type (err = -EINVAL). All destroy: arms now return err < 0, so vmci_transport_recv_listen() removes pending from pending_links synchronously and vsock_pending_work() takes the is_pending=false / !rejected branch, dropping only its own work reference. This also closes the multi-packet race Sashiko reported on v2: pending is removed from the list before any subsequent packet can find it. The pre-existing sk_acceptq_removed() gap on the err < 0 path of vmci_transport_recv_listen() that Sashiko also noted is not introduced or changed by this patch. Tested on lts-6.12.79 with KASAN: 52/100 unpatched -> 0/100 patched. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Cc: stable@vger.kernel.org Signed-off-by: Minh Nguyen Acked-by: Bryan Tan Link: https://patch.msgid.link/20260519102310.237181-1-minhnguyen.080505@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/vmci_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index aca3132689cf1..4cd11f355e9d6 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1156,7 +1156,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, /* Close and cleanup the connection. */ vmci_transport_send_reset(pending, pkt); skerr = EPROTO; - err = pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST ? 0 : -EINVAL; + err = -EINVAL; goto destroy; } From c618cf8926c0574c32649c56331f6ecee674928e Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 18 May 2026 11:06:55 +0200 Subject: [PATCH 1225/1518] vsock/virtio: reset connection on receiving queue overflow commit a4f0b001782b21663d10df983b4b208195bec66c upstream. When there is no more space to queue an incoming packet, the packet is silently dropped. This causes data loss without any notification to either peer, since there is no retransmission. Under normal circumstances, this should never happen. However, it could happen if the other peer doesn't respect the credit, or if the skb overhead, which we recently began to take into account with commit 059b7dbd20a6 ("vsock/virtio: fix potential unbounded skb queue"), is too high. Fix this by resetting the connection and setting the local socket error to ENOBUFS when virtio_transport_recv_enqueue() can no longer queue a packet, so both peers are explicitly notified of the failure rather than silently losing data. Fixes: ae6fcfbf5f03 ("vsock/virtio: discard packets if credit is not respected") Cc: stable@vger.kernel.org Signed-off-by: Stefano Garzarella Link: https://patch.msgid.link/20260518090656.134588-2-sgarzare@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- net/vmw_vsock/virtio_transport_common.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 495c93cddcdc0..65e2b24892346 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1335,7 +1335,7 @@ virtio_transport_recv_connecting(struct sock *sk, return err; } -static void +static bool virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct sk_buff *skb) { @@ -1350,10 +1350,8 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, spin_lock_bh(&vvs->rx_lock); can_enqueue = virtio_transport_inc_rx_pkt(vvs, len); - if (!can_enqueue) { - free_pkt = true; + if (!can_enqueue) goto out; - } if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) vvs->msg_count++; @@ -1393,6 +1391,8 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, spin_unlock_bh(&vvs->rx_lock); if (free_pkt) kfree_skb(skb); + + return can_enqueue; } static int @@ -1405,7 +1405,17 @@ virtio_transport_recv_connected(struct sock *sk, switch (le16_to_cpu(hdr->op)) { case VIRTIO_VSOCK_OP_RW: - virtio_transport_recv_enqueue(vsk, skb); + if (!virtio_transport_recv_enqueue(vsk, skb)) { + /* There is no more space to queue the packet, so let's + * close the connection; otherwise, we'll lose data. + */ + (void)virtio_transport_reset(vsk, skb); + virtio_transport_do_close(vsk, true); + sk->sk_err = ENOBUFS; + sk_error_report(sk); + vsock_remove_sock(vsk); + break; + } vsock_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_REQUEST: From a3529032afe2253117dcda3920af7cb2b40ed272 Mon Sep 17 00:00:00 2001 From: Jose Ignacio Tornos Martinez Date: Fri, 15 May 2026 11:24:09 -0700 Subject: [PATCH 1226/1518] ice: fix VF queue configuration with low MTU values commit 3ba4dd024d26372733d1c02e13e076c6016e3320 upstream. The ice driver's VF queue configuration validation rejects databuffer_size values below 1024 bytes, which prevents VFs from using MTU values below 871 bytes. The iavf driver calculates databuffer_size based on the MTU using: databuffer_size = ALIGN(MTU + LIBETH_RX_LL_LEN, 128) where LIBETH_RX_LL_LEN = 26 (ETH_HLEN + 2*VLAN_HLEN + ETH_FCS_LEN). For MTU values below 871: MTU 870: 870 + 26 = 896, aligned to 128 = 896 (< 1024, rejected) MTU 871: 871 + 26 = 897, aligned to 128 = 1024 (>= 1024, accepted) The 1024-byte minimum seems unnecessarily restrictive, because the hardware supports databuffer_size as low as 128 bytes (the alignment boundary), which should allow MTU values down to the standard minimum of 68 bytes. I haven't found the reason why the limit was configured in the commit 9c7dd7566d18 ("ice: add validation in OP_CONFIG_VSI_QUEUES VF message"), so with no more information and since it is working, change the minimum databuffer_size validation from 1024 to 128 bytes to allow standard low MTU values while still preventing invalid configurations. Fixes: 9c7dd7566d18 ("ice: add validation in OP_CONFIG_VSI_QUEUES VF message") cc: stable@vger.kernel.org Signed-off-by: Jose Ignacio Tornos Martinez Reviewed-by: Jacob Keller Reviewed-by: Michal Swiatkowski Reviewed-by: Paul Menzel Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-3-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ice/virt/queues.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c index 370f6ec2a374c..a82024bf388bf 100644 --- a/drivers/net/ethernet/intel/ice/virt/queues.c +++ b/drivers/net/ethernet/intel/ice/virt/queues.c @@ -840,7 +840,7 @@ int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) if (qpi->rxq.databuffer_size != 0 && (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || - qpi->rxq.databuffer_size < 1024)) + qpi->rxq.databuffer_size < 128)) goto error_param; ring->rx_buf_len = qpi->rxq.databuffer_size; if (qpi->rxq.max_pkt_size > max_frame_size || From 614cacec60fe92d50abe532f011a7549a1c94169 Mon Sep 17 00:00:00 2001 From: Kyle Farnung Date: Wed, 13 May 2026 21:52:12 -0700 Subject: [PATCH 1227/1518] wifi: ath11k: clear shared SRNG pointer state on restart commit f51e4b3b5574ad8cb5b16b11f8a1452147ece87a upstream. LMAC rings reuse the shared rdp/wrp pointer buffers without going through the normal SRNG hw-init path that zeros non-LMAC ring pointers. After restart, ath11k_hal_srng_clear() can therefore hand stale hp/tp state from the previous firmware instance back to the new one. Clear the shared pointer buffers while keeping the allocations in place so restart still avoids reallocating SRNG DMA memory, but starts with fresh ring-pointer state. Fixes: 32be3ca4cf78b ("wifi: ath11k: HAL SRNG: don't deinitialize and re-initialize again") Cc: stable@vger.kernel.org Closes: https://lore.kernel.org/all/CAOPSVF04q6uvVdq8GTRLHBrVMdpt9=o9wVcFMc6f-yhmSBcZqQ@mail.gmail.com/ Signed-off-by: Kyle Farnung Reviewed-by: Rameshkumar Sundaram Reviewed-by: Baochen Qiang Link: https://patch.msgid.link/20260513-kfarnung-ath11k-srng-clear-pointer-state-v1-1-bc700dd8b333@gmail.com Signed-off-by: Jeff Johnson Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath11k/hal.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c index 0c797b8d0a276..8330c9e7ac7d4 100644 --- a/drivers/net/wireless/ath/ath11k/hal.c +++ b/drivers/net/wireless/ath/ath11k/hal.c @@ -1388,14 +1388,22 @@ EXPORT_SYMBOL(ath11k_hal_srng_deinit); void ath11k_hal_srng_clear(struct ath11k_base *ab) { - /* No need to memset rdp and wrp memory since each individual - * segment would get cleared in ath11k_hal_srng_src_hw_init() - * and ath11k_hal_srng_dst_hw_init(). + /* + * Preserve the shared pointer buffers, but clear the previous + * firmware instance's hp/tp state before handing them back to FW. + * LMAC rings reuse this shared memory without going through the + * normal SRNG hw-init path that zeros non-LMAC ring pointers. */ memset(ab->hal.srng_list, 0, sizeof(ab->hal.srng_list)); memset(ab->hal.shadow_reg_addr, 0, sizeof(ab->hal.shadow_reg_addr)); + if (ab->hal.rdp.vaddr) + memset(ab->hal.rdp.vaddr, 0, + sizeof(*ab->hal.rdp.vaddr) * HAL_SRNG_RING_ID_MAX); + if (ab->hal.wrp.vaddr) + memset(ab->hal.wrp.vaddr, 0, + sizeof(*ab->hal.wrp.vaddr) * HAL_SRNG_NUM_LMAC_RINGS); ab->hal.avail_blk_resource = 0; ab->hal.current_blk_index = 0; ab->hal.num_shadow_reg_configured = 0; From 6fe92651b44fd3cfc8dcfdaad0e82885c384dada Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 15 May 2026 15:14:57 +0300 Subject: [PATCH 1228/1518] wifi: iwlwifi: mvm: fix driver-set TX rates on old devices commit fb84b5cbcaab3ca0f4e961d92a40ed7f3aac483b upstream. On old devices such as 7265D, rates are still encoded in version 1 format, which doesn't use the CCK/OFDM rate index (0-3/0-7) but rather their PLCP value (e.g. 10 for 1 Mbps CCK rate.) While introducing v3 rates, I changed the driver from internally handling v1 rates and converting to v2, to internally handling v3 and converting to v1 or v2 according to the firmware. I accordingly changed the code in iwl_mvm_mac80211_idx_to_hwrate() to no longer have different values for different APIs. This was correct. However, I later reverted this part of the change, because it was reported that I had broken beacon rates, causing a FW assert/crash. This caused TX_CMD rates to be set incorrectly, potentially causing a warning when reported back from the device as having been used. Fix this (hopefully correctly now) by handling beacon rates in the TX_CMD that's embedded in the beacon template command separately. Restore iwl_mvm_mac80211_idx_to_hwrate() to return only the rate index, not PLCP value, fixing the real TX_CMD. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg Link: https://patch.msgid.link/20260515151351.7407e293dff7.I4ea1a17f8fe99c933d3f3e30d077cf4246125c3e@changeid Signed-off-by: Miri Korenblit Signed-off-by: Greg Kroah-Hartman --- .../net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 27 ++++++++++++------- .../net/wireless/intel/iwlwifi/mvm/utils.c | 14 +++------- 2 files changed, 22 insertions(+), 19 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 49ffc4ecee855..44380ebfe09d0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -938,13 +938,18 @@ u8 iwl_mvm_mac_ctxt_get_lowest_rate(struct iwl_mvm *mvm, u16 iwl_mvm_mac_ctxt_get_beacon_flags(const struct iwl_fw *fw, u8 rate_idx) { - u16 flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); bool is_new_rate = iwl_fw_lookup_cmd_ver(fw, BEACON_TEMPLATE_CMD, 0) > 10; + u16 flags = 0; if (rate_idx <= IWL_LAST_CCK_RATE) flags |= is_new_rate ? IWL_MAC_BEACON_CCK : IWL_MAC_BEACON_CCK_V1; + if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8) + flags |= iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); + else + flags |= iwl_fw_rate_idx_to_plcp(rate_idx); + return flags; } @@ -973,6 +978,7 @@ static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm, { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct ieee80211_tx_info *info; + u32 rate_n_flags = 0; u8 rate; u32 tx_flags; @@ -992,18 +998,21 @@ static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm, IWL_UCODE_TLV_CAPA_BEACON_ANT_SELECTION)) { iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx); - tx_params->rate_n_flags = - cpu_to_le32(BIT(mvm->mgmt_last_antenna_idx) << - RATE_MCS_ANT_POS); + rate_n_flags |= BIT(mvm->mgmt_last_antenna_idx) << + RATE_MCS_ANT_POS; } rate = iwl_mvm_mac_ctxt_get_beacon_rate(mvm, info, vif); - tx_params->rate_n_flags |= - cpu_to_le32(iwl_mvm_mac80211_idx_to_hwrate(mvm->fw, rate)); - if (rate == IWL_FIRST_CCK_RATE) - tx_params->rate_n_flags |= cpu_to_le32(RATE_MCS_CCK_MSK_V1); + if (rate < IWL_FIRST_OFDM_RATE) + rate_n_flags |= RATE_MCS_MOD_TYPE_CCK; + else + rate_n_flags |= RATE_MCS_MOD_TYPE_LEGACY_OFDM; + + rate_n_flags |= iwl_mvm_mac80211_idx_to_hwrate(mvm->fw, rate); + tx_params->rate_n_flags = iwl_mvm_v3_rate_to_fw(rate_n_flags, + mvm->fw_rates_ver); } int iwl_mvm_mac_ctxt_send_beacon_cmd(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index fa995e235d9b4..63e84efdaa46c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -159,15 +159,9 @@ int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags, u8 iwl_mvm_mac80211_idx_to_hwrate(const struct iwl_fw *fw, int rate_idx) { - if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8) - /* In the new rate legacy rates are indexed: - * 0 - 3 for CCK and 0 - 7 for OFDM. - */ - return (rate_idx >= IWL_FIRST_OFDM_RATE ? - rate_idx - IWL_FIRST_OFDM_RATE : - rate_idx); - - return iwl_fw_rate_idx_to_plcp(rate_idx); + return rate_idx >= IWL_FIRST_OFDM_RATE ? + rate_idx - IWL_FIRST_OFDM_RATE : + rate_idx; } u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac) From dc31c69476520bb4c2a208211a8d3c310a62c4d0 Mon Sep 17 00:00:00 2001 From: Sheroz Juraev Date: Sun, 15 Mar 2026 13:12:21 +0500 Subject: [PATCH 1229/1518] wifi: iwlwifi: mld: stop TX during firmware restart commit 2becb38a3e217ef2b2f42fddd7db7a25905ec291 upstream. When iwlwifi firmware crashes (e.g., NMI_INTERRUPT_UNKNOWN on Intel BE201/Wi-Fi 7), iwl_mld_nic_error() sets mld->fw_status.in_hw_restart to true. However, iwl_mld_tx_from_txq() does not check this flag before dequeuing frames from mac80211 and pushing them to the transport layer. Since the firmware is dead, iwl_trans_tx() returns -EIO for each frame, which then gets freed immediately. Under high-throughput conditions (e.g., Tailscale UDP traffic or active SSH sessions), this creates a tight dequeue-send-fail-free loop that wastes CPU cycles and generates rapid skb allocation churn, leading to memory pressure from slab fragmentation. The RX path already has this guard (iwl_mld_rx_mpdu checks in_hw_restart at rx.c:1906), and so does the TXQ allocation worker (iwl_mld_add_txqs_wk at tx.c:156). Add the same guard to iwl_mld_tx_from_txq() to stop all TX during firmware restart. Frames left in mac80211's TXQs are naturally drained after restart completes, when queue reallocation triggers iwl_mld_tx_from_txq() via iwl_mld_add_txq_list(), or when new upper-layer traffic invokes wake_tx_queue. Tested on ASUS Zenbook 14 UX3405CA with Intel BE201 (Wi-Fi 7) on kernel 6.19.5 where the firmware crashes approximately every 10-15 minutes under Tailscale traffic. Fixes: d1e879ec600f ("wifi: iwlwifi: add iwlmld sub-driver") Cc: stable@vger.kernel.org Signed-off-by: Sheroz Juraev Link: https://patch.msgid.link/20260315081221.2678478-1-goodmartiandev@gmail.com Signed-off-by: Miri Korenblit Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/intel/iwlwifi/mld/tx.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.c b/drivers/net/wireless/intel/iwlwifi/mld/tx.c index e3fb4fc4f452e..c54ea3a91b667 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.c @@ -964,6 +964,16 @@ void iwl_mld_tx_from_txq(struct iwl_mld *mld, struct ieee80211_txq *txq) struct sk_buff *skb = NULL; u8 zero_addr[ETH_ALEN] = {}; + /* + * Don't transmit during firmware restart. The firmware is dead, + * so iwl_trans_tx() would return -EIO for each frame. Avoid the + * overhead of dequeuing from mac80211 only to immediately free + * the skbs, and the potential memory pressure from rapid skb + * allocation churn during high-throughput restart scenarios. + */ + if (unlikely(mld->fw_status.in_hw_restart)) + return; + /* * No need for threads to be pending here, they can leave the first * taker all the work. From 7725cd3b471740fd23d25ed1da722c671fb2a5d3 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 12 May 2026 16:51:14 -0400 Subject: [PATCH 1230/1518] ipv4: raw: reject IP_HDRINCL packets with ihl < 5 commit 915fab69823a14c170dbaa3b41978768e0fe62fc upstream. raw_send_hdrinc() validates that the caller-supplied IPv4 header fits within the message length: iphlen = iph->ihl * 4; err = -EINVAL; if (iphlen > length) goto error_free; if (iphlen >= sizeof(*iph)) { /* fix up saddr, tot_len, id, csum, transport_header */ } It does not, however, reject ihl < 5. For such a packet the "if (iphlen >= sizeof(*iph))" branch is skipped, leaving the crafted iphdr untouched, but the packet is still handed to __ip_local_out() and onward. Downstream consumers that read iph->ihl assume a sane value: net/ipv4/ah4.c:ah_output() in particular subtracts sizeof(struct iphdr) from top_iph->ihl * 4 and passes the (signed-int-negative, then cast to size_t) result to memcpy(), producing an OOB access of length close to SIZE_MAX and a host kernel panic. An IPv4 header with ihl < 5 is malformed by definition (RFC 791: "Internet Header Length is the length of the internet header in 32 bit words ... Note that the minimum value for a correct header is 5."). The kernel should not be willing to inject such a packet into its own output path. Reject "iphlen < sizeof(*iph)" alongside the existing "iphlen > length" check. This matches the principle that locally constructed packets that re-enter the IP stack must pass the same basic sanity tests that a foreign packet would be subjected to. Once this lands, the "if (iphlen >= sizeof(*iph))" wrapper around the fixup branch becomes redundant; left in place to keep the patch minimal and backport-friendly. A follow-up can unwrap it. Note that commit 86f4c90a1c5c ("ipv4, ipv6: ensure raw socket message is big enough to hold an IP header") ensures the message buffer is large enough to hold an iphdr, but does not constrain the self-reported iph->ihl. Reachability: the malformed packet source is any caller with CAP_NET_RAW, including an unprivileged process in a user+net namespace on a kernel with CONFIG_USER_NS=y. The reproduced AH crash also requires a matching xfrm AH policy on the outgoing route; a container granted CAP_NET_ADMIN can install that state and policy in its netns. Loopback bypasses xfrm_output, so the trigger uses a real netdev. Reproduced on UML + KASAN: kernel-mode fault at addr 0x0 with memcpy_orig at the crash site. Same shape reproduces inside a rootless Docker container with --cap-add NET_ADMIN on a stock distro kernel. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Suggested-by: Herbert Xu Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/77ec2b5e8111961c2c39883c92e8aa2709039c17.1778614451.git.michael.bommarito@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/raw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index d54ebb7df966d..f79f4c29a0433 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -390,7 +390,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, * in, reject the frame as invalid */ err = -EINVAL; - if (iphlen > length) + if (iphlen > length || iphlen < sizeof(*iph)) goto error_free; if (iphlen >= sizeof(*iph)) { From dfef79e09ed2f5df975c98547f97f5d7f8982a24 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Fri, 15 May 2026 11:24:14 -0700 Subject: [PATCH 1231/1518] ixgbevf: fix use-after-free in VEPA multicast source pruning commit 5d49b568c188dc77199d8d2b959c91da8cc27cf1 upstream. ixgbevf_clean_rx_irq() prunes frames whose source MAC matches the VF's own address (VEPA multicast workaround) by freeing the skb and continuing to the next descriptor: dev_kfree_skb_irq(skb); continue; The skb pointer is declared outside the while loop and persists across iterations. Because the continue skips the "skb = NULL" reset at the bottom of the loop, the next iteration enters the "else if (skb)" path and calls ixgbevf_add_rx_frag() on the freed skb, dereferencing skb_shinfo(skb)->nr_frags - a use-after-free in NAPI softirq context. The sibling driver iavf already handles this correctly by nulling the pointer before continuing. Apply the same pattern here. I do not have ixgbevf hardware; the bug was found by static analysis (scan_drop_continue_loops.py + semgrep drop_continue_in_loop, multi-tool corroboration with the highest score in the scan). The UAF was confirmed under KASAN by loading a test module that reproduces the exact code pattern (alloc skb, kfree_skb, then read skb_shinfo(skb)->nr_frags): BUG: KASAN: slab-use-after-free in ixgbevf_uaf_test_init+0x100/0x1000 Read of size 8 at addr 000000006163ae78 by task insmod/30 freed 208-byte region [000000006163adc0, 000000006163ae90) QEMU emulates igb (82576) but not ixgbe (82599), and the igbvf VF driver does not include the VEPA source pruning path, so a full end-to-end reproduction with emulated hardware was not possible. Fixes: bad17234ba70 ("ixgbevf: Change receive model to use double buffered page based receives") Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-8-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index d5ce20f47def1..c999abd784819 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1221,6 +1221,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, ether_addr_equal(rx_ring->netdev->dev_addr, eth_hdr(skb)->h_source)) { dev_kfree_skb_irq(skb); + skb = NULL; continue; } From 9dcd4f5c99b491c37be90b0bd9988db48225fb75 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2026 23:07:26 +0200 Subject: [PATCH 1232/1518] rbd: eliminate a race in lock_dwork draining on unmap commit 9fc75b71fdd38465c76c6f6a884cdd4ae3c72d90 upstream. Given how rbd_lock_add_request() and rbd_img_exclusive_lock() are written, lock_dwork may be (re)queued more than it's actually needed: for example in case a new I/O request comes in while we are in the middle of rbd_acquire_lock() on behalf of another I/O request. This is expected and with rbd_release_lock() preemptively canceling lock_dwork is benign under normal operation. A more problematic example is maybe_kick_acquire(): if (have_requests || delayed_work_pending(&rbd_dev->lock_dwork)) { dout("%s rbd_dev %p kicking lock_dwork\n", __func__, rbd_dev); mod_delayed_work(rbd_dev->task_wq, &rbd_dev->lock_dwork, 0); } It's not unrealistic for lock_dwork to get canceled right after delayed_work_pending() returns true and for mod_delayed_work() to requeue it right there anyway. This is a classic TOCTOU race. When it comes to unmapping the image, there is an implicit assumption of no self-initiated exclusive lock activity past the point of return from rbd_dev_image_unlock() which unlocks the lock if it happens to be held. This unlock is assumed to be final and lock_dwork (as well as all other exclusive lock tasks, really) isn't expected to get queued again. However, lock_dwork is canceled only in cancel_tasks_sync() (i.e. later in the unmap sequence) and on top of that the cancellation can get in effect nullified by maybe_kick_acquire(). This may result in rbd_acquire_lock() executing after rbd_dev_device_release() and rbd_dev_image_release() run and free and/or reset a bunch of things. One of the possible failure modes then is a violated rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); in rbd_dev_header_info() which is called via rbd_dev_refresh() from rbd_post_acquire_action(). Redo exclusive lock task draining to provide saner semantics and try to meet the assumptions around rbd_dev_image_unlock(). Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Viacheslav Dubeyko Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 9236b5184bce3..97cd8cf7bad30 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4565,24 +4565,12 @@ static int rbd_register_watch(struct rbd_device *rbd_dev) return ret; } -static void cancel_tasks_sync(struct rbd_device *rbd_dev) -{ - dout("%s rbd_dev %p\n", __func__, rbd_dev); - - cancel_work_sync(&rbd_dev->acquired_lock_work); - cancel_work_sync(&rbd_dev->released_lock_work); - cancel_delayed_work_sync(&rbd_dev->lock_dwork); - cancel_work_sync(&rbd_dev->unlock_work); -} - /* * header_rwsem must not be held to avoid a deadlock with * rbd_dev_refresh() when flushing notifies. */ static void rbd_unregister_watch(struct rbd_device *rbd_dev) { - cancel_tasks_sync(rbd_dev); - mutex_lock(&rbd_dev->watch_mutex); if (rbd_dev->watch_state == RBD_WATCH_STATE_REGISTERED) __rbd_unregister_watch(rbd_dev); @@ -6548,10 +6536,18 @@ static int rbd_add_parse_args(const char *buf, static void rbd_dev_image_unlock(struct rbd_device *rbd_dev) { + dout("%s rbd_dev %p\n", __func__, rbd_dev); + + disable_delayed_work_sync(&rbd_dev->lock_dwork); + disable_work_sync(&rbd_dev->unlock_work); + down_write(&rbd_dev->lock_rwsem); if (__rbd_is_lock_owner(rbd_dev)) __rbd_release_lock(rbd_dev); up_write(&rbd_dev->lock_rwsem); + + flush_work(&rbd_dev->acquired_lock_work); + flush_work(&rbd_dev->released_lock_work); } /* From 5b906f31e977286888a9e31282589b545b249139 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Wed, 13 May 2026 14:05:06 -0400 Subject: [PATCH 1233/1518] lsm: hold cred_guard_mutex for lsm_set_self_attr() commit 4a9b16541ad3faf8bccb398532bf3f8b6bbf1188 upstream. Just as proc_pid_attr_write() already does before calling the LSM hook. This only matters for SELinux and AppArmor which check whether the process is being ptraced and if so, whether to allow the transition. Cc: stable@vger.kernel.org Signed-off-by: Stephen Smalley Acked-by: Casey Schaufler Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/lsm_syscalls.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c index 8440948a690c9..b3887c85a2ba1 100644 --- a/security/lsm_syscalls.c +++ b/security/lsm_syscalls.c @@ -55,7 +55,14 @@ u64 lsm_name_to_attr(const char *name) SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, ctx, u32, size, u32, flags) { - return security_setselfattr(attr, ctx, size, flags); + int rc; + + rc = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); + if (rc < 0) + return rc; + rc = security_setselfattr(attr, ctx, size, flags); + mutex_unlock(¤t->signal->cred_guard_mutex); + return rc; } /** From 47a4cf2229be379cf88f92e32e1240337cd6273f Mon Sep 17 00:00:00 2001 From: Sam Daly Date: Wed, 13 May 2026 18:42:53 +0200 Subject: [PATCH 1234/1518] octeontx2-af: CGX: add bounds check to cgx_speed_mbps index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit c0bf0a4f3f1f5f57aa83e1400ba4f56f0abfd542 upstream. cgx_speed_mbps has 13 elements but RESP_LINKSTAT_SPEED can yield values 0-15. If it returns a value >= 13, this causes an out-of-bounds array access. Add a bounds check and default to speed 0 if the index is out of range. Fixes: 61071a871ea6 ("octeontx2-af: Forward CGX link notifications to PFs") Cc: Sunil Goutham Cc: Linu Cherian Cc: Geetha sowjanya Cc: hariprasad Cc: Subbaraya Sundeep Cc: Andrew Lunn Cc: stable Signed-off-by: Sam Daly Signed-off-by: Greg Kroah-Hartman Link: https://patch.msgid.link/2026051352-refined-demise-e88d@gregkh Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 81b55f1416e0d..c6b5f6564ed05 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1294,13 +1294,18 @@ static inline void link_status_user_format(u64 lstat, struct cgx_link_user_info *linfo, struct cgx *cgx, u8 lmac_id) { + unsigned int speed; + linfo->link_up = FIELD_GET(RESP_LINKSTAT_UP, lstat); linfo->full_duplex = FIELD_GET(RESP_LINKSTAT_FDUPLEX, lstat); - linfo->speed = cgx_speed_mbps[FIELD_GET(RESP_LINKSTAT_SPEED, lstat)]; linfo->an = FIELD_GET(RESP_LINKSTAT_AN, lstat); linfo->fec = FIELD_GET(RESP_LINKSTAT_FEC, lstat); linfo->lmac_type_id = FIELD_GET(RESP_LINKSTAT_LMAC_TYPE, lstat); + speed = FIELD_GET(RESP_LINKSTAT_SPEED, lstat); + linfo->speed = speed < ARRAY_SIZE(cgx_speed_mbps) ? + cgx_speed_mbps[speed] : 0; + if (linfo->lmac_type_id >= LMAC_MODE_MAX) { dev_err(&cgx->pdev->dev, "Unknown lmac_type_id %d reported by firmware on cgx port%d:%d", linfo->lmac_type_id, cgx->cgx_id, lmac_id); From 8864b664d0443ecb8e56690e5546fcda5fe5e81b Mon Sep 17 00:00:00 2001 From: Dawei Feng Date: Wed, 13 May 2026 23:13:20 +0800 Subject: [PATCH 1235/1518] octeontx2-pf: fix double free in rvu_rep_rsrc_init() commit e8fb3de2a8effcaf62bec2c56b93d8bb480371d1 upstream. rvu_rep_rsrc_init() allocates queue memory before calling otx2_init_hw_resources(). When hardware resource setup fails, otx2_init_hw_resources() already unwinds the partially initialized SQ, CQ, and aura state before returning an error. The representor error path then calls otx2_free_hw_resources() again and can free the same resources a second time. Fix this by splitting the cleanup labels so that a failure from otx2_init_hw_resources() only releases queue memory. Keep the otx2_free_hw_resources() call for failures that happen after hardware resource initialization completed successfully. The bug was first flagged by an experimental analysis tool we are developing for kernel memory-management bugs while analyzing v6.13-rc1. The tool is still under development and is not yet publicly available. Manual inspection confirms that the bug is still present in v7.1-rc3. Runtime validation was not performed because reproducing this path requires OcteonTX2 representor hardware. Fixes: 3937b7308d4f ("octeontx2-pf: Create representor netdev") Cc: stable@vger.kernel.org # v6.13+ Signed-off-by: Zilin Guan Signed-off-by: Dawei Feng Reviewed-by: Geetha sowjanya Link: https://patch.msgid.link/20260513151320.213260-1-dawei.feng@seu.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/marvell/octeontx2/nic/rep.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index b476733a02345..3271ab5539a58 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -609,7 +609,7 @@ static int rvu_rep_rsrc_init(struct otx2_nic *priv) err = otx2_init_hw_resources(priv); if (err) - goto err_free_rsrc; + goto err_free_mem; /* Set maximum frame size allowed in HW */ err = otx2_hw_set_mtu(priv, priv->hw.max_mtu); @@ -621,6 +621,7 @@ static int rvu_rep_rsrc_init(struct otx2_nic *priv) err_free_rsrc: otx2_free_hw_resources(priv); +err_free_mem: otx2_free_queue_mem(qset); return err; } From f1bafd35f11b3aca1c7bb38da173b8787364a04c Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Fri, 15 May 2026 11:24:16 -0700 Subject: [PATCH 1236/1518] igc: fix potential skb leak in igc_fpe_xmit_smd_frame() commit e935c37b8a94bb256fada6395a5d05e1c0c6bdaf upstream. When igc_fpe_init_tx_descriptor() fails, no one takes care of an allocated skb, leaking it. [1] Use dev_kfree_skb_any() on failure. Tested on an I226 adapter with the following command, while injecting faults in igc_fpe_init_tx_descriptor() to trigger the error path. # ethtool --set-mm $DEV verify-enabled on tx-enabled on pmac-enabled on [1] unreferenced object 0xffff888113c6cdc0 (size 224): ... backtrace (crc be3d3fda): kmem_cache_alloc_node_noprof+0x3b1/0x410 __alloc_skb+0xde/0x830 igc_fpe_xmit_smd_frame.isra.0+0xad/0x1b0 igc_fpe_send_mpacket+0x37/0x90 ethtool_mmsv_verify_timer+0x15e/0x300 Cc: stable@vger.kernel.org Fixes: 5422570c0010 ("igc: add support for frame preemption verification") Signed-off-by: Kohei Enju Reviewed-by: Simon Horman Reviewed-by: Faizal Rahim Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-10-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/igc/igc_tsn.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 8a110145bfee7..02dd9f0290a34 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -109,10 +109,16 @@ static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter, __netif_tx_lock(nq, cpu); err = igc_fpe_init_tx_descriptor(ring, skb, type); - igc_flush_tx_descriptors(ring); + if (err) + goto err_free_skb_any; + igc_flush_tx_descriptors(ring); __netif_tx_unlock(nq); + return 0; +err_free_skb_any: + __netif_tx_unlock(nq); + dev_kfree_skb_any(skb); return err; } From 9c9d00d81b41cb637dd0440e4d995861d052e5c8 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 15 May 2026 11:24:08 -0700 Subject: [PATCH 1237/1518] ice: fix locking around wait_event_interruptible_locked_irq commit 89bbff099bfc94888eb942d5b981592bbbe0c856 upstream. Commit 50327223a8bb ("ice: add lock to protect low latency interface") introduced a wait queue used to protect the low latency timer interface. The queue is used with the wait_event_interruptible_locked_irq macro, which unlocks the wait queue lock while sleeping. The irq variant uses spin_lock_irq and spin_unlock_irq to manage this. The wait queue lock was previously locked using spin_lock_irqsave. This difference in lock variants could lead to issues, since wait_event would unlock the wait queue and restore interrupts while sleeping. The ice_read_phy_tstamp_ll_e810() function is ultimately called through ice_read_phy_tstamp, which is called from ice_ptp_process_tx_tstamp or ice_ptp_clear_unexpected_tx_ready. The former is called through the miscellaneous IRQ thread function, while the latter is called from the service task work queue thread. Neither of these functions has interrupts disabled, so use spin_lock_irq instead of spin_lock_irqsave. Fixes: 50327223a8bb ("ice: add lock to protect low latency interface") Cc: stable@vger.kernel.org Reported-by: Jakub Kicinski Closes: https://lore.kernel.org/netdev/20250109181823.77f44c69@kernel.org/ Signed-off-by: Jacob Keller Signed-off-by: Aleksandr Loktionov Reviewed-by: Simon Horman Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-2-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index d461e00d15e9e..30b7839398165 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -4503,18 +4503,17 @@ static int ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) { struct ice_e810_params *params = &hw->ptp.phy.e810; - unsigned long flags; u32 val; int err; - spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + spin_lock_irq(¶ms->atqbal_wq.lock); /* Wait for any pending in-progress low latency interrupt */ err = wait_event_interruptible_locked_irq(params->atqbal_wq, !(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS)); if (err) { - spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + spin_unlock_irq(¶ms->atqbal_wq.lock); return err; } @@ -4529,7 +4528,7 @@ ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) REG_LL_PROXY_H); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); - spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + spin_unlock_irq(¶ms->atqbal_wq.lock); return err; } @@ -4539,7 +4538,7 @@ ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) /* Read the low 32 bit value and set the TS valid bit */ *lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID; - spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + spin_unlock_irq(¶ms->atqbal_wq.lock); return 0; } From 0b9431b972a0d0933b5b2f31079a037fe17d01dc Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Fri, 15 May 2026 11:24:10 -0700 Subject: [PATCH 1238/1518] ice: fix setting promisc mode while adding VID filter commit ebc8de716c9ec2be384abdc2dd866da26c6580d1 upstream. There are at least two paths through which VSI promiscuous mode can be independently configured via ice_fltr_set_vsi_promisc(): - ice_vlan_rx_add_vid() (netdev op) - ice_service_task() -> ... -> ice_set_promisc() Both paths may try to program promiscuous mode concurrently. One such scenario is: 1. Add ice netdev to bond 2. Add the bond netdev to bridge 3. ice netdev enters allmulticast mode (IFF_ALLMULTI) 4. Service task programs promisc mode filter 5. Bridge -> bond calls ice_vlan_rx_add_vid() Crucially, ice_vlan_rx_add_vid() fails if ice_fltr_set_vsi_promisc() returns any error, including -EEXIST. This causes VLAN filtering setup to fail on the bond interface. ice_set_promisc() already handles -EEXIST correctly. Fix by adding the same -EEXIST check to ice_vlan_rx_add_vid(): if the promisc filter is already programmed, continue without returning error. Fixes: 1273f89578f2 ("ice: Fix broken IFF_ALLMULTI handling") Cc: stable@vger.kernel.org Signed-off-by: Marcin Szycik Signed-off-by: Aleksandr Loktionov Reviewed-by: Simon Horman Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-4-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index c064c3653c540..2d78d9838518b 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3764,7 +3764,7 @@ int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, ICE_MCAST_VLAN_PROMISC_BITS, vid); - if (ret) + if (ret && ret != -EEXIST) goto finish; } From 50884c2afd7a016ef56667c4079c2d27a261bbb3 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Fri, 15 May 2026 11:24:13 -0700 Subject: [PATCH 1239/1518] ice: restore PTP Rx timestamp config after ethtool set-channels commit 975b564d195b13ca6ee1ef5e6a9561734898eb17 upstream. When ethtool -L changes queue counts, ice_vsi_recfg_qs() closes and rebuilds the VSI, reallocating Rx rings. The newly allocated rings have ptp_rx cleared, so RX hardware timestamps are no longer attached to skb until hwtstamp configuration is applied again. Restore timestamp mode after ice_vsi_open() in the queue reconfiguration path, matching reset/rebuild behavior and ensuring newly rebuilt Rx rings have PTP RX timestamping re-enabled. Testing hints: - run ptp4l application in client synchronization mode: ptp4l -i ethX -m -s - run PTP traffic - change queue number on ethX netdev interface: ethtool -L ethX combined new_queue_size - observe ptp4l output - expected result: no "received DELAY_REQ without timestamp" messages Fixes: 77a781155a65 ("ice: enable receive hardware timestamping") Cc: stable@vger.kernel.org Reviewed-by: Aleksandr Loktionov Signed-off-by: Grzegorz Nitka Reviewed-by: Simon Horman Tested-by: Alexander Nowlin Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-7-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ice/ice_main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 2d78d9838518b..d42b65e29e485 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4186,6 +4186,12 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) } ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); + /* Rx rings are reallocated during VSI rebuild and lose their ptp_rx + * flag. Restore timestamp mode so newly allocated rings are set up + * for hardware Rx timestamping. + */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_restore_timestamp_mode(pf); goto done; rebuild_err: From 6cfae4914439878b8acb35c7e3b40096eeb2ad9c Mon Sep 17 00:00:00 2001 From: John Walker Date: Thu, 7 May 2026 17:07:20 -0600 Subject: [PATCH 1240/1518] wifi: cfg80211: advance loop vars in cfg80211_merge_profile() commit 7666dbb1bacc4ba522b96740cba7283d243d16e1 upstream. cfg80211_merge_profile() reassembles a Multi-BSSID non-transmitted BSS profile that has been split across multiple consecutive MBSSID elements. Its while-loop calls cfg80211_get_profile_continuation(ie, ielen, mbssid_elem, sub_elem) but never advances mbssid_elem or sub_elem inside the body. Each iteration therefore searches for a continuation that follows the same fixed pair; the helper returns the same next_mbssid; and the same next_sub bytes are memcpy()'d into merged_ie at a growing offset until the buffer fills. Advance both mbssid_elem and sub_elem to the just-consumed continuation so the next call to cfg80211_get_profile_continuation() searches for a further continuation beyond it (or returns NULL when none exists). A specially-crafted malicious beacon can take advantage of this bug to cause the kernel to spend an excessive amount of time in cfg80211_merge_profile (up to as much as 2ms per beacon received), which could theoretically be abused in some way. Cc: stable@vger.kernel.org Fixes: fe806e4992c9 ("cfg80211: support profile split between elements") Signed-off-by: John Walker Link: https://patch.msgid.link/20260507230720.64783-1-johnwalker0@gmail.com Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/wireless/scan.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 9a0c02c23dc56..4a1cdfc3221ca 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2475,6 +2475,9 @@ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen, memcpy(merged_ie + copied_len, next_sub->data, next_sub->datalen); copied_len += next_sub->datalen; + + mbssid_elem = next_mbssid; + sub_elem = next_sub; } return copied_len; From acdff9907478e82208475b1151700d0b71dcdc63 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 18 May 2026 18:51:30 +0200 Subject: [PATCH 1241/1518] af_unix: Fix UAF read of tail->len in unix_stream_data_wait() commit be309f8eae8b474a4a617eaae01324da996fc719 upstream. unix_stream_data_wait() does skb_peek_tail(&sk->sk_receive_queue) without holding any lock that prevents SKBs on that queue from being dequeued and freed. This has been the case since commit 79f632c71bea ("unix/stream: fix peeking with an offset larger than data in queue"). The first consequence of this is that the pointer comparison `tail != last` can be false even if `last` semantically refers to an already-freed SKB while `tail` is a new SKB allocated at the same address; which can cause unix_stream_data_wait() to wrongly keep blocking after new data has arrived, but only in a weird scenario where a peeking recv() and a normal recv() on the same socket are racing, which is probably not a real problem. But since commit 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets"), `tail` is actually dereferenced, which can cause UAF in the following race scenario (where test_setup() runs single-threaded, and afterwards, test_thread1() and test_thread2() run concurrently in two threads: ``` static int socks[2]; void test_setup(void) { socketpair(AF_UNIX, SOCK_STREAM, 0, socks); send(socks[1], "A", 1, 0); int peekoff = 1; setsockopt(socks[0], SOL_SOCKET, SO_PEEK_OFF, &peekoff, sizeof(peekoff)); } void test_thread1(void) { char dummy; recv(socks[0], &dummy, 1, MSG_PEEK); } void test_thread2(void) { char dummy; recv(socks[0], &dummy, 1, 0); shutdown(socks[1], SHUT_WR); } ``` when racing like this: ``` thread1 thread2 unix_stream_read_generic mutex_lock(&u->iolock) skb_peek(&sk->sk_receive_queue) skb_peek_next(skb, &sk->sk_receive_queue) mutex_unlock(&u->iolock) unix_stream_read_generic unix_state_lock(sk) skb_peek(&sk->sk_receive_queue) unix_state_unlock(sk) unix_stream_data_wait unix_state_lock(sk) tail = skb_peek_tail(&sk->sk_receive_queue) spin_lock(&sk->sk_receive_queue.lock) __skb_unlink(skb, &sk->sk_receive_queue) spin_unlock(&sk->sk_receive_queue.lock) consume_skb(skb) [frees the SKB] `tail != last`: false `tail`: true `tail->len != last_len` ***UAF*** ``` Fix the UAF by removing the read of tail->len; checking tail->len would only make sense if SKBs in the receive queue of a UNIX socket could grow, which can no longer happen. Kuniyuki explained: > When commit 869e7c62486e ("net: af_unix: implement stream sendpage > support") added sendpage() support, data could be appended to the last > skb in the receiver's queue. > > That's why we needed to check if the length of the last skb was changed > while waiting for new data in unix_stream_data_wait(). > > However, commit a0dbf5f818f9 ("af_unix: Support MSG_SPLICE_PAGES") and > commit 57d44a354a43 ("unix: Convert unix_stream_sendpage() to use > MSG_SPLICE_PAGES") refactored sendmsg(), and now data is always added > to a new skb. That means this fix is not suitable for kernels before 6.5. Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets") Cc: stable@vger.kernel.org # 6.5.x Signed-off-by: Jann Horn Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260518-b4-unix-recv-wait-hotfix-v2-1-83e29ce8ad31@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/unix/af_unix.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 33ed8ecb556dd..faf04d1b6c013 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2716,8 +2716,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last, unsigned int last_len, - bool freezable) + struct sk_buff *last, bool freezable) { unsigned int state = TASK_INTERRUPTIBLE | freezable * TASK_FREEZABLE; struct sk_buff *tail; @@ -2730,7 +2729,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, tail = skb_peek_tail(&sk->sk_receive_queue); if (tail != last || - (tail && tail->len != last_len) || sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current) || @@ -2923,7 +2921,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, int flags = state->flags; bool check_creds = false; struct scm_cookie scm; - unsigned int last_len; struct unix_sock *u; int copied = 0; int err = 0; @@ -2969,7 +2966,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, goto unlock; } last = skb = skb_peek(&sk->sk_receive_queue); - last_len = last ? last->len : 0; again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) @@ -3003,8 +2999,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, mutex_unlock(&u->iolock); - timeo = unix_stream_data_wait(sk, timeo, last, - last_len, freezable); + timeo = unix_stream_data_wait(sk, timeo, last, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -3021,7 +3016,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, while (skip >= unix_skb_len(skb)) { skip -= unix_skb_len(skb); last = skb; - last_len = skb->len; skb = skb_peek_next(skb, &sk->sk_receive_queue); if (!skb) goto again; @@ -3096,7 +3090,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, skip = 0; last = skb; - last_len = skb->len; unix_state_lock(sk); skb = skb_peek_next(skb, &sk->sk_receive_queue); if (skb) From 2dd9304727c7041df0a599595910bdbe02ad03c5 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Fri, 15 May 2026 11:17:18 -0400 Subject: [PATCH 1242/1518] wifi: mac80211: consume only present negotiated TTLM maps commit a6e6ccd5bd07155c2add6c74ce1a5e68ad3b95ea upstream. ieee80211_tid_to_link_map_size_ok() validates negotiated TTLM elements against the number of link-map entries indicated by link_map_presence. ieee80211_parse_neg_ttlm() must consume the same layout. The parser advanced its cursor for every TID, including TIDs whose presence bit is clear and therefore have no map bytes in the element. A sparse map can then make a later present TID read past the validated element. The bad bytes land in neg_ttlm->{up,down}link[tid] but are gated by valid_links before being applied to driver state, so a peer cannot turn the read into a policy change. Under KUnit + KASAN with an exact-sized element allocation the OOB read is reported as a slab-out-of-bounds; whether the same trigger fires under the production RX path depends on surrounding allocator state. Advance the cursor only when the current TID has a map present. Fixes: 8f500fbc6c65 ("wifi: mac80211: process and save negotiated TID to Link mapping request") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/20260515151719.1317659-2-michael.bommarito@gmail.com Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/mlme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index bcc4090ddc1a5..ce247dde048c0 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7959,6 +7959,7 @@ ieee80211_parse_neg_ttlm(struct ieee80211_sub_if_data *sdata, "No active links for TID %d", tid); return -EINVAL; } + pos += map_size; } else { map = 0; } @@ -7977,7 +7978,6 @@ ieee80211_parse_neg_ttlm(struct ieee80211_sub_if_data *sdata, default: return -EINVAL; } - pos += map_size; } return 0; } From 5e7d9d0805e58fa3760894e73115b7a74024fd07 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 19 May 2026 17:18:05 +0800 Subject: [PATCH 1243/1518] cifs: Fix busy dentry used after unmounting commit c68337442f03953237a94577beb468ab2662a851 upstream. Since commit 340cea84f691c ("cifs: open files should not hold ref on superblock"), cifs file only holds the dentry ref_cnt, the cifs file close work(cfile->deferred) could be executed after unmounting, which will trigger a warning in generic_shutdown_super: BUG: Dentry 00000000a14a6845{i=c,n=file} still in use (1) [unmount of cifs cifs] The detailed processs is: process A process B kworker fd = open(PATH) vfs_open file->__f_path = *path // dentry->d_lockref.count = 1 cifs_open cifs_new_fileinfo cfile->dentry = dget(dentry) // dentry->d_lockref.count = 2 close(fd) __fput cifs_close queue_delayed_work(deferredclose_wq, cfile->deferred) dput(dentry) // dentry->d_lockref.count = 1 smb2_deferred_work_close _cifsFileInfo_put list_del(&cifs_file->flist) umount cleanup_mnt deactivate_super cifs_kill_sb cifs_close_all_deferred_files_sb cifs_close_all_deferred_files // cannot find cfile, skip _cifsFileInfo_put kill_anon_super generic_shutdown_super shrink_dcache_for_umount umount_check WARN ! // dentry->d_lockref.count = 1 cifsFileInfo_put_final dput(cifs_file->dentry) // dentry->d_lockref.count = 0 Fix it by flushing 'deferredclose_wq' before calling kill_anon_super. Fetch a reproducer in https://bugzilla.kernel.org/show_bug.cgi?id=221548. Fixes: 340cea84f691c ("cifs: open files should not hold ref on superblock") Cc: stable@vger.kernel.org Reviewed-by: Shyam Prasad N Signed-off-by: Zhihao Cheng Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/cifsfs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 4b34a4304edb7..9059c2efbcc05 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -338,6 +338,8 @@ static void cifs_kill_sb(struct super_block *sb) /* Wait for all pending oplock breaks to complete */ flush_workqueue(cifsoplockd_wq); + /* Wait for all opened files to release */ + flush_workqueue(deferredclose_wq); /* finally release root dentry */ dput(cifs_sb->root); From 798183376d9d3e278a270ea0e75a5769c8f145d9 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 21 May 2026 13:49:14 +0900 Subject: [PATCH 1244/1518] tracing: Do not call map->ops->elt_free() if elt_alloc() fails commit 8f0f5c4fb9df0e19a341e0c6ed8dc4fda9124f03 upstream. In paths where tracing_map_elt_alloc() failed to allocate objects, the map->ops->elt_alloc() call was never successful. In this case, map->ops->elt_free() should not be called. Link: https://sashiko.dev/#/patchset/20260520223101.34710-1-rosenp%40gmail.com Cc: stable@vger.kernel.org Cc: Tom Zanussi Cc: Mathieu Desnoyers Cc: Rosen Penev Reported-by: Sashiko Fixes: 2734b629525a ("tracing: Add per-element variable support to tracing_map") Link: https://patch.msgid.link/177933895460.108746.5396070821443932634.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- kernel/trace/tracing_map.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 7f8da4dab69d5..ba52813ce51bd 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -386,13 +386,11 @@ static void tracing_map_elt_init_fields(struct tracing_map_elt *elt) } } -static void tracing_map_elt_free(struct tracing_map_elt *elt) +static void __tracing_map_elt_free(struct tracing_map_elt *elt) { if (!elt) return; - if (elt->map->ops && elt->map->ops->elt_free) - elt->map->ops->elt_free(elt); kfree(elt->fields); kfree(elt->vars); kfree(elt->var_set); @@ -400,6 +398,17 @@ static void tracing_map_elt_free(struct tracing_map_elt *elt) kfree(elt); } +static void tracing_map_elt_free(struct tracing_map_elt *elt) +{ + if (!elt) + return; + + /* Only objects initialized with alloc_elt() should be passed to free_elt().*/ + if (elt->map->ops && elt->map->ops->elt_free) + elt->map->ops->elt_free(elt); + __tracing_map_elt_free(elt); +} + static struct tracing_map_elt *tracing_map_elt_alloc(struct tracing_map *map) { struct tracing_map_elt *elt; @@ -444,7 +453,7 @@ static struct tracing_map_elt *tracing_map_elt_alloc(struct tracing_map *map) } return elt; free: - tracing_map_elt_free(elt); + __tracing_map_elt_free(elt); return ERR_PTR(err); } From 240373425e2d09928af534089f5c569ae2084a7b Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Fri, 15 May 2026 14:37:29 +0100 Subject: [PATCH 1245/1518] arm64: probes: Handle probes on hinted conditional branch instructions commit 2ccd8ff980b50e842481bae71102fa3883fc4377 upstream. BC.cond instructions introduced by FEAT_HBC cannot be executed out-of-line, like other branch instructions. However, they can be simulated in the same way as B.cond instructions. Extend the B.cond decoder mask to match BC.cond instructions as well, and handle them using the existing B.cond simulation path. Fixes: 7f86d128e437 ("arm64: add HWCAP for FEAT_HBC (hinted conditional branches)") Cc: Signed-off-by: Vladimir Murzin Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/insn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 18c7811774d30..032cd7b76b484 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -409,7 +409,7 @@ __AARCH64_INSN_FUNCS(cbz, 0x7F000000, 0x34000000) __AARCH64_INSN_FUNCS(cbnz, 0x7F000000, 0x35000000) __AARCH64_INSN_FUNCS(tbz, 0x7F000000, 0x36000000) __AARCH64_INSN_FUNCS(tbnz, 0x7F000000, 0x37000000) -__AARCH64_INSN_FUNCS(bcond, 0xFF000010, 0x54000000) +__AARCH64_INSN_FUNCS(bcond, 0xFF000000, 0x54000000) __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001) __AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002) __AARCH64_INSN_FUNCS(smc, 0xFFE0001F, 0xD4000003) From 0680f511926589206f81f57f76ce131d7741a316 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 19 May 2026 09:25:19 -0400 Subject: [PATCH 1246/1518] KVM: arm64: vgic-its: Reject restored DTE with out-of-range num_eventid_bits commit 9ce754ed8e7ab4e3999767ce1505f85c449ccb07 upstream. Userspace can restore an ITS Device Table Entry whose Size field encodes more EventID bits than the virtual ITS supports. The live MAPD path rejects that state, but vgic_its_restore_dte() accepts it and stores the out-of-range value in dev->num_eventid_bits. Reject restored DTEs with num_eventid_bits > VITS_TYPER_IDBITS before allocating the device. This mirrors the MAPD check and prevents the restored state from reaching vgic_its_restore_itt(), where the unchecked value can be converted into an oversized scan_its_table() range. Fixes: 57a9a117154c ("KVM: arm64: vgic-its: Device table save/restore") Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Michael Bommarito Link: https://lore.kernel.org/r/20260519132519.2142458-1-michael.bommarito@gmail.com Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/vgic/vgic-its.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 3f1c4b10fed90..a4c0fb7f02ea8 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2307,6 +2307,10 @@ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, /* dte entry is valid */ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; + /* Mimic the MAPD behaviour and reject invalid EID bits. */ + if (num_eventid_bits > VITS_TYPER_IDBITS) + return -EINVAL; + if (!vgic_its_check_id(its, baser, id, NULL)) return -EINVAL; From 7023900b4988fb6f4a59d304d878003ff562e98d Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Tue, 19 May 2026 09:50:42 -0400 Subject: [PATCH 1247/1518] KVM: arm64: vgic: Free private_irqs when init fails after allocation commit f19c354dbd457759dfcf1195ab4bdba2bb568323 upstream. Companion to commit 250f25367b58 ("KVM: arm64: Tear down vGIC on failed vCPU creation"), which added the missing kvm_vgic_vcpu_destroy() call to the kvm_share_hyp() failure path in kvm_arch_vcpu_create(). The kvm_vgic_vcpu_init() failure path immediately above it has the same shape and still needs the same cleanup. Call kvm_vgic_vcpu_destroy() when kvm_vgic_vcpu_init() fails so private IRQs allocated before a redistributor iodev registration failure are released before the failed vCPU is freed. Fixes: 03b3d00a70b5 ("KVM: arm64: vgic: Allocate private interrupts on demand") Cc: stable@vger.kernel.org Cc: Will Deacon Reviewed-by: Yuan Yao Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Michael Bommarito Link: https://lore.kernel.org/r/20260519135042.2219239-1-michael.bommarito@gmail.com Signed-off-by: Marc Zyngier Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/arm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index afc77977d4b94..e59cb36b5f36f 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -490,8 +490,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_destroy_mpidr_data(vcpu->kvm); err = kvm_vgic_vcpu_init(vcpu); - if (err) + if (err) { + kvm_vgic_vcpu_destroy(vcpu); return err; + } err = kvm_share_hyp(vcpu, vcpu + 1); if (err) From 94ade38f317ea086a181db0e6b69c574b3b70a5e Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Fri, 22 May 2026 12:00:14 +0800 Subject: [PATCH 1248/1518] KVM: SVM: Disable AVIC IPI virtualization on Hygon Family 18h (erratum #1235) commit 9a12fa5213cfc391e0eed63902d3be98f0913765 upstream. Hygon Family 18h CPUs are derived from AMD Family 17h (Zen1) silicon and share the same erratum #1235: hardware may read a stale IsRunning=1 bit during ICR write emulation and silently fail to generate an AVIC_IPI_FAILURE_TARGET_NOT_RUNNING VM-Exit on the sending vCPU. The absence of the VM-Exit causes KVM to miss the required wakeup of blocking target vCPUs, leading to hung vCPUs and unbounded delays in guest execution. Extend the existing AMD Family 17h erratum #1235 workaround to also cover Hygon Family 18h. With IPI virtualization disabled, KVM never sets IsRunning=1 in the Physical ID table, so every non-self IPI generates a VM-Exit and is correctly emulated. Fixes: 8de4a1c8164e ("KVM: SVM: Disable (x2)AVIC IPI virtualization if CPU has erratum #1235") Cc: Signed-off-by: Tina Zhang Message-ID: <20260522040014.3380201-1-zhang_wei@open-hieco.net> Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/avic.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index ba6e9485e8247..ba844088581fe 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1252,12 +1252,14 @@ bool __init avic_hardware_setup(void) svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true; /* - * Disable IPI virtualization for AMD Family 17h CPUs (Zen1 and Zen2) - * due to erratum 1235, which results in missed VM-Exits on the sender - * and thus missed wake events for blocking vCPUs due to the CPU - * failing to see a software update to clear IsRunning. + * Disable IPI virtualization for AMD Family 17h (Zen1 and Zen2) and + * Hygon Family 18h (derived from AMD Zen1) CPUs due to erratum 1235, + * which results in missed VM-Exits on the sender and thus missed wake + * events for blocking vCPUs due to the CPU failing to see a software + * update to clear IsRunning. */ - enable_ipiv = enable_ipiv && boot_cpu_data.x86 != 0x17; + if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) + enable_ipiv = false; amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); From 77071943c752e2133dd6ea1f9933368246a49358 Mon Sep 17 00:00:00 2001 From: Osama Abdelkader Date: Thu, 14 May 2026 19:36:40 +0200 Subject: [PATCH 1249/1518] riscv: kvm: return SBI_ERR_FAILURE for pmu_snapshot_set_shmem() when OOM commit 0835ee26938e15eccd70f7d33da386b6490f9449 upstream. kvm_riscv_vcpu_pmu_snapshot_set_shmem() returned -ENOMEM from the SBI extension handler, which caused kvm_riscv_vcpu_sbi_ecall() to abort KVM_RUN and surface the error to userspace instead of ompleting the ECALL with a negative SBI error in a0. Use SBI_ERR_FAILURE and the normal retdata path, matching other PMU handlers and kvm_sbi_ext_pmu_handler comment. Fixes: c2f41ddbcdd7 ("RISC-V: KVM: Implement SBI PMU Snapshot feature") Cc: stable@vger.kernel.org Signed-off-by: Osama Abdelkader Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260514173642.41448-1-osama.abdelkader@gmail.com Signed-off-by: Anup Patel Signed-off-by: Greg Kroah-Hartman --- arch/riscv/kvm/vcpu_pmu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index a2fae70ee174c..aeb16dd780351 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -431,8 +431,10 @@ int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long s } kvpmu->sdata = kzalloc(snapshot_area_size, GFP_ATOMIC); - if (!kvpmu->sdata) - return -ENOMEM; + if (!kvpmu->sdata) { + sbiret = SBI_ERR_FAILURE; + goto out; + } /* No need to check writable slot explicitly as kvm_vcpu_write_guest does it internally */ if (kvm_vcpu_write_guest(vcpu, saddr, kvpmu->sdata, snapshot_area_size)) { From 4f087193b5ff0211ce5fa567db3184fb31a53f65 Mon Sep 17 00:00:00 2001 From: Osama Abdelkader Date: Thu, 14 May 2026 19:36:41 +0200 Subject: [PATCH 1250/1518] riscv: kvm: return SBI_ERR_FAILURE for pmu_event_info() when OOM commit 0e9d0e7a7c78db7aa1c13796c65cfe0aefa54a5b upstream. kvm_riscv_vcpu_pmu_event_info() returned -ENOMEM from the SBI extension handler, which caused kvm_riscv_vcpu_sbi_ecall() to abort KVM_RUN and surface the error to userspace instead of completing the ECALL with a negative SBI error in a0. Use SBI_ERR_FAILURE and the normal retdata path, matching other PMU handlers and kvm_sbi_ext_pmu_handler comment. Fixes: e309fd113b9f ("RISC-V: KVM: Implement get event info function") Cc: stable@vger.kernel.org Signed-off-by: Osama Abdelkader Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20260514173642.41448-2-osama.abdelkader@gmail.com Signed-off-by: Anup Patel Signed-off-by: Greg Kroah-Hartman --- arch/riscv/kvm/vcpu_pmu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index aeb16dd780351..ef55089c0c1a6 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -478,8 +478,10 @@ int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low } einfo = kzalloc(shmem_size, GFP_KERNEL); - if (!einfo) - return -ENOMEM; + if (!einfo) { + ret = SBI_ERR_FAILURE; + goto out; + } ret = kvm_vcpu_read_guest(vcpu, shmem, einfo, shmem_size); if (ret) { From bee400ad4f4259c9c0758e4f1960a1eed6f6f9f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Carlos=20L=C3=B3pez?= Date: Tue, 12 May 2026 12:00:42 +0200 Subject: [PATCH 1251/1518] virt: sev-guest: Explicitly leak pages in unknown state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit fd948c3f96b18ff9ba7d3e8eae13d196593e1aaf upstream. When set_memory_{encrypted,decrypted}() fail, the user cannot know at which point the function failed, meaning that the pages are left in an unknown state from the point of view of the caller. Since the pages may be left in an unencrypted state, they are not suitable for general use, and cannot be returned safely to the buddy allocator. Avoid the issue by never freeing the pages, and then do the proper accounting by calling snp_leak_pages(). Fixes: 3e385c0d6ce8 ("virt: sev-guest: Move SNP Guest Request data pages handling under snp_cmd_mutex") Signed-off-by: Carlos López Signed-off-by: Borislav Petkov (AMD) Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/virt/coco/sev-guest/sev-guest.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index 45b870b55feb4..b6315cfe52bc1 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -176,6 +176,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques struct snp_guest_req req = {}; int ret, npages = 0, resp_len; sockptr_t certs_address; + u64 pfn; if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data)) return -EINVAL; @@ -215,10 +216,11 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques if (!req.certs_data) return -ENOMEM; + pfn = PHYS_PFN(virt_to_phys(req.certs_data)); ret = set_memory_decrypted((unsigned long)req.certs_data, npages); if (ret) { pr_err("failed to mark page shared, ret=%d\n", ret); - free_pages_exact(req.certs_data, npages << PAGE_SHIFT); + snp_leak_pages(pfn, npages); return -EFAULT; } @@ -272,10 +274,12 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques kfree(report_resp); e_free_data: if (npages) { - if (set_memory_encrypted((unsigned long)req.certs_data, npages)) + if (set_memory_encrypted((unsigned long)req.certs_data, npages)) { WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); - else + snp_leak_pages(pfn, npages); + } else { free_pages_exact(req.certs_data, npages << PAGE_SHIFT); + } } return ret; } From ecdf21536c6d8ad079700fd3312225cd6b1e52bd Mon Sep 17 00:00:00 2001 From: Osama Abdelkader Date: Thu, 30 Apr 2026 21:49:42 +0200 Subject: [PATCH 1252/1518] drm/bridge: chipone-icn6211: use devm_drm_bridge_add in i2c probe commit 73d01051e8040c0b1de7fd26b3b8d0c2ffa6895c upstream. Use devm_drm_bridge_add() so the bridge is released if probe fails after registration, and drop drm_bridge_remove() in chipone_i2c_probe. Signed-off-by: Osama Abdelkader Fixes: 8dde6f7452a1 ("drm: bridge: icn6211: Add I2C configuration support") Cc: stable@vger.kernel.org Reviewed-by: Luca Ceresoli Link: https://patch.msgid.link/20260430194944.78119-1-osama.abdelkader@gmail.com Signed-off-by: Luca Ceresoli Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/bridge/chipone-icn6211.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/chipone-icn6211.c b/drivers/gpu/drm/bridge/chipone-icn6211.c index 814713c5bea97..553a1df4688d0 100644 --- a/drivers/gpu/drm/bridge/chipone-icn6211.c +++ b/drivers/gpu/drm/bridge/chipone-icn6211.c @@ -758,7 +758,9 @@ static int chipone_i2c_probe(struct i2c_client *client) dev_set_drvdata(dev, icn); i2c_set_clientdata(client, icn); - drm_bridge_add(&icn->bridge); + ret = devm_drm_bridge_add(dev, &icn->bridge); + if (ret) + return ret; return chipone_dsi_host_attach(icn); } From 4bb4764f2c51f03f657a28029eb0595d8223aab5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 12 May 2026 09:43:34 +0200 Subject: [PATCH 1253/1518] spi: qup: fix error pointer deref after DMA setup failure commit a7e8f3efd50a165ba0189f6dc57f7e51a7d149db upstream. The driver falls back to PIO mode if DMA setup fails during probe. Make sure to the clear the DMA channel pointers on setup failure to avoid dereferencing an error pointer (or attempting to release a channel a second time) on later probe errors or driver unbind. This issue was flagged by Sashiko when reviewing a devres allocation conversion patch. Fixes: 612762e82ae6 ("spi: qup: Add DMA capabilities") Link: https://sashiko.dev/#/patchset/20260505072909.618363-1-johan%40kernel.org?part=4 Cc: stable@vger.kernel.org # 4.1 Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260512074334.914735-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-qup.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index a5c549479c7d1..3134b9c1480aa 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -996,8 +996,11 @@ static int spi_qup_init_dma(struct spi_controller *host, resource_size_t base) err: dma_release_channel(host->dma_tx); + host->dma_tx = NULL; err_tx: dma_release_channel(host->dma_rx); + host->dma_rx = NULL; + return ret; } From a1f50f5aaa695417c0bc45636020e9310cc4ecc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C5=81ukasz=20Lebiedzi=C5=84ski?= Date: Mon, 6 Apr 2026 15:56:27 +0200 Subject: [PATCH 1254/1518] phy: exynos5-usbdrd: fix USB 2.0 HS PHY tuning values for Exynos7870 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 5a759b120e31aa3ed914d98b51eb1755235250f2 upstream. The existing PHYPARAM0 tuning values for Exynos7870 are incorrect, causing the USB 2.0 PHY to fail high-speed negotiation and fall back to full-speed (12Mbps) operation. Fix TXVREFTUNE (transmitter voltage reference) from 14 to 3, TXRESTUNE (transmitter impedance) from 3 to 2, and SQRXTUNE (squelch threshold) from 6 to 5. Also explicitly set TXPREEMPPULSETUNE to 0, which was previously missing from the tuning table despite being included in the register mask. All values are derived from the vendor kernel for the Samsung Galaxy A6 (SM-A600FN), as no public hardware documentation is available for the Exynos7870 USB DRD PHY. With these corrections, the PHY successfully negotiates high-speed (480Mbps) operation. Fixes: 588d5d20ca8d ("phy: exynos5-usbdrd: add exynos7870 USBDRD support") Cc: stable@vger.kernel.org Tested-by: Kaustabh Chakraborty Reviewed-by: Krzysztof Kozlowski Signed-off-by: Łukasz Lebiedziński Link: https://patch.msgid.link/20260406135627.234835-1-kernel@lvkasz.us Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/phy/samsung/phy-exynos5-usbdrd.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c index 1c8bf80119f11..93ac302de1eb0 100644 --- a/drivers/phy/samsung/phy-exynos5-usbdrd.c +++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c @@ -1905,13 +1905,14 @@ const struct exynos5_usbdrd_phy_tuning exynos7870_tunes_utmi_postinit[] = { PHYPARAM0_TXPREEMPAMPTUNE | PHYPARAM0_TXHSXVTUNE | PHYPARAM0_TXFSLSTUNE | PHYPARAM0_SQRXTUNE | PHYPARAM0_OTGTUNE | PHYPARAM0_COMPDISTUNE), - (FIELD_PREP_CONST(PHYPARAM0_TXVREFTUNE, 14) | + (FIELD_PREP_CONST(PHYPARAM0_TXVREFTUNE, 3) | FIELD_PREP_CONST(PHYPARAM0_TXRISETUNE, 1) | - FIELD_PREP_CONST(PHYPARAM0_TXRESTUNE, 3) | + FIELD_PREP_CONST(PHYPARAM0_TXRESTUNE, 2) | + FIELD_PREP_CONST(PHYPARAM0_TXPREEMPPULSETUNE, 0) | FIELD_PREP_CONST(PHYPARAM0_TXPREEMPAMPTUNE, 0) | FIELD_PREP_CONST(PHYPARAM0_TXHSXVTUNE, 0) | FIELD_PREP_CONST(PHYPARAM0_TXFSLSTUNE, 3) | - FIELD_PREP_CONST(PHYPARAM0_SQRXTUNE, 6) | + FIELD_PREP_CONST(PHYPARAM0_SQRXTUNE, 5) | FIELD_PREP_CONST(PHYPARAM0_OTGTUNE, 2) | FIELD_PREP_CONST(PHYPARAM0_COMPDISTUNE, 3))), PHY_TUNING_ENTRY_LAST From 58f4a7bd8d73d3c27d7d3e88cc0b309fede40eb0 Mon Sep 17 00:00:00 2001 From: Wayne Chang Date: Mon, 4 May 2026 11:33:05 +0800 Subject: [PATCH 1255/1518] phy: tegra: xusb: Fix per-pad high-speed termination calibration commit da110228b54f2e2143d97ea7151e0dc22e539d67 upstream. The existing code reads a single hs_term_range_adj value from bit field [10:7] of FUSE_SKU_CALIB_0 and applies it to all USB2 pads uniformly. However, on SoCs that support per-pad termination, each pad has its own hs_term_range_adj field: pad 0 in FUSE_SKU_CALIB_0[10:7], and pads 1-3 in FUSE_USB_CALIB_EXT_0 at bit offsets [8:5], [12:9], and [16:13] respectively. Fix the calibration by reading per-pad values from the appropriate fuse registers. For SoCs that do not support per-pad termination, replicate pad 0's value to all pads to maintain existing behavior. Add a has_per_pad_term flag to the SoC data to indicate whether per-pad termination values are available in FUSE_USB_CALIB_EXT_0. Fixes: 1ef535c6ba8e ("phy: tegra: xusb: Add Tegra194 support") Cc: stable@vger.kernel.org Signed-off-by: Wayne Chang Signed-off-by: Wei-Cheng Chen Reviewed-by: Jon Hunter Tested-by: Jon Hunter Link: https://patch.msgid.link/20260504033305.2283145-1-weichengc@nvidia.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/phy/tegra/xusb-tegra186.c | 33 ++++++++++++++++++++++++------- drivers/phy/tegra/xusb.h | 1 + 2 files changed, 27 insertions(+), 7 deletions(-) diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index bec9616c4a2e0..4452e73fb82a6 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -20,8 +20,8 @@ /* FUSE USB_CALIB registers */ #define HS_CURR_LEVEL_PADX_SHIFT(x) ((x) ? (11 + (x - 1) * 6) : 0) #define HS_CURR_LEVEL_PAD_MASK 0x3f -#define HS_TERM_RANGE_ADJ_SHIFT 7 -#define HS_TERM_RANGE_ADJ_MASK 0xf +#define HS_TERM_RANGE_ADJ_PADX_SHIFT(x) ((x) ? (5 + (x - 1) * 4) : 7) +#define HS_TERM_RANGE_ADJ_PAD_MASK 0xf #define HS_SQUELCH_SHIFT 29 #define HS_SQUELCH_MASK 0x7 @@ -253,7 +253,7 @@ struct tegra_xusb_fuse_calibration { u32 *hs_curr_level; u32 hs_squelch; - u32 hs_term_range_adj; + u32 *hs_term_range_adj; u32 rpd_ctrl; }; @@ -930,7 +930,7 @@ static int tegra186_utmi_phy_power_on(struct phy *phy) value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index)); value &= ~TERM_RANGE_ADJ(~0); - value |= TERM_RANGE_ADJ(priv->calib.hs_term_range_adj); + value |= TERM_RANGE_ADJ(priv->calib.hs_term_range_adj[index]); value &= ~RPD_CTRL(~0); value |= RPD_CTRL(priv->calib.rpd_ctrl); padctl_writel(padctl, value, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index)); @@ -1464,17 +1464,23 @@ static const char * const tegra186_usb3_functions[] = { static int tegra186_xusb_read_fuse_calibration(struct tegra186_xusb_padctl *padctl) { + const struct tegra_xusb_padctl_soc *soc = padctl->base.soc; struct device *dev = padctl->base.dev; unsigned int i, count; u32 value, *level; + u32 *hs_term_range_adj; int err; - count = padctl->base.soc->ports.usb2.count; + count = soc->ports.usb2.count; level = devm_kcalloc(dev, count, sizeof(u32), GFP_KERNEL); if (!level) return -ENOMEM; + hs_term_range_adj = devm_kcalloc(dev, count, sizeof(u32), GFP_KERNEL); + if (!hs_term_range_adj) + return -ENOMEM; + err = tegra_fuse_readl(TEGRA_FUSE_SKU_CALIB_0, &value); if (err) return dev_err_probe(dev, err, @@ -1490,8 +1496,8 @@ tegra186_xusb_read_fuse_calibration(struct tegra186_xusb_padctl *padctl) padctl->calib.hs_squelch = (value >> HS_SQUELCH_SHIFT) & HS_SQUELCH_MASK; - padctl->calib.hs_term_range_adj = (value >> HS_TERM_RANGE_ADJ_SHIFT) & - HS_TERM_RANGE_ADJ_MASK; + hs_term_range_adj[0] = (value >> HS_TERM_RANGE_ADJ_PADX_SHIFT(0)) & + HS_TERM_RANGE_ADJ_PAD_MASK; err = tegra_fuse_readl(TEGRA_FUSE_USB_CALIB_EXT_0, &value); if (err) { @@ -1503,6 +1509,17 @@ tegra186_xusb_read_fuse_calibration(struct tegra186_xusb_padctl *padctl) padctl->calib.rpd_ctrl = (value >> RPD_CTRL_SHIFT) & RPD_CTRL_MASK; + for (i = 1; i < count; i++) { + if (soc->has_per_pad_term) + hs_term_range_adj[i] = + (value >> HS_TERM_RANGE_ADJ_PADX_SHIFT(i)) & + HS_TERM_RANGE_ADJ_PAD_MASK; + else + hs_term_range_adj[i] = hs_term_range_adj[0]; + } + + padctl->calib.hs_term_range_adj = hs_term_range_adj; + return 0; } @@ -1708,6 +1725,7 @@ const struct tegra_xusb_padctl_soc tegra194_xusb_padctl_soc = { .num_supplies = ARRAY_SIZE(tegra194_xusb_padctl_supply_names), .supports_gen2 = true, .poll_trk_completed = true, + .has_per_pad_term = true, }; EXPORT_SYMBOL_GPL(tegra194_xusb_padctl_soc); @@ -1732,6 +1750,7 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = { .trk_hw_mode = false, .trk_update_on_idle = true, .supports_lp_cfg_en = true, + .has_per_pad_term = true, }; EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc); #endif diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h index d2b5f95651324..810b410672f37 100644 --- a/drivers/phy/tegra/xusb.h +++ b/drivers/phy/tegra/xusb.h @@ -436,6 +436,7 @@ struct tegra_xusb_padctl_soc { bool trk_hw_mode; bool trk_update_on_idle; bool supports_lp_cfg_en; + bool has_per_pad_term; }; struct tegra_xusb_padctl { From 78a369a065f1fa821b50730877d88aeaf9459974 Mon Sep 17 00:00:00 2001 From: Nitin Rawat Date: Wed, 15 Apr 2026 16:18:51 +0530 Subject: [PATCH 1256/1518] phy: qcom-qmp-ufs: Fix kaanapali PHY PLL lock failure after SM8650 G4 fix commit 80305760d7a55b884fb9023c490b75568d1ea0b1 upstream. Commit 81af9e40e2e4 ("phy: qcom: qmp-ufs: Fix SM8650 PCS table for Gear 4") moved QPHY_V6_PCS_UFS_PLL_CNTL register configuration from the shared sm8650_ufsphy_g5_pcs table to the SM8650-specific sm8650_ufsphy_pcs base table to fix Gear 4 operation on SM8650. However, this change inadvertently broke kaanapali and SM8750 SoCs which also rely on the shared sm8650_ufsphy_g5_pcs table for Gear 5 configuration but use their own sm8750_ufsphy_pcs base table. After the change, kaanapali PHYs are left without the required PLL_CNTL = 0x33 setting, causing the PHY PLL to remain at its hardware reset default value, preventing PLL lock and resulting in DME_LINKSTARTUP timeouts. Fix this by adding the missing QPHY_V6_PCS_UFS_PLL_CNTL = 0x33 entry to the sm8750_ufsphy_pcs table, mirroring what the original commit already did for sm8650_ufsphy_pcs. Cc: stable@vger.kernel.org # v6.19.12 Fixes: 81af9e40e2e4 ("phy: qcom: qmp-ufs: Fix SM8650 PCS table for Gear 4") Signed-off-by: Nitin Rawat Reviewed-by: Abel Vesa Reviewed-by: Konrad Dybcio Reviewed-by: Manivannan Sadhasivam Link: https://patch.msgid.link/20260415104851.2763238-1-nitin.rawat@oss.qualcomm.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/phy/qualcomm/phy-qcom-qmp-ufs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c index dda877561f8ca..8af777f7ddd03 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c @@ -1050,6 +1050,7 @@ static const struct qmp_phy_init_tbl sm8750_ufsphy_pcs[] = { QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0x40), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x68), QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_POST_EMP_LVL_S4, 0x0e), From b9ff8631006233ba246828ac70409d2cb2da38d3 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Sun, 19 Apr 2026 17:04:20 -0400 Subject: [PATCH 1257/1518] scsi: isci: Fix use-after-free in device removal path commit b52a8d52c3125ec9a93106ed816582368de34426 upstream. The ISCI completion tasklet is initialized in isci_host_alloc() (drivers/scsi/isci/init.c:496) and scheduled from both MSI-X and legacy interrupt handlers (drivers/scsi/isci/host.c:223,613). isci_host_deinit() stops the controller and waits for stop completion, but it never kills completion_tasklet before teardown continues. A top-of-function tasklet_kill() is not sufficient here: interrupts are only disabled when isci_host_stop_complete() runs, so until wait_for_stop() returns the IRQ handlers can still requeue the tasklet. The tasklet callback also re-enables interrupts after draining completions, so killing the tasklet before the source is quiesced leaves the same race open. Once wait_for_stop() returns, no further IRQ-driven scheduling can occur. Kill completion_tasklet there so teardown cannot race a queued tasklet running on a dead ihost. On remove or unload, the stale callback can otherwise dereference ihost and touch ihost->smu_registers after the host lifetime ends. A UML + KASAN analogue reproduced the failure class both with no tasklet_kill() and with tasklet_kill() placed before source quiesce, and stayed clean once the kill happened after quiescing the scheduling source. This mirrors commit f6ab594672d4 ("scsi: aic94xx: fix use-after-free in device removal path"), but ISCI needs the kill after wait_for_stop(). Fixes: 6f231dda6808 ("isci: Intel(R) C600 Series Chipset Storage Control Unit Driver") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-7 Assisted-by: Codex:gpt-5-4 Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/20260419210420.2134639-1-michael.bommarito@gmail.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/isci/host.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index 6d2f4c831df74..ff199bab5d1a8 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -1252,6 +1252,9 @@ void isci_host_deinit(struct isci_host *ihost) wait_for_stop(ihost); + /* No further IRQ-driven scheduling can happen past wait_for_stop(). */ + tasklet_kill(&ihost->completion_tasklet); + /* phy stop is after controller stop to allow port and device to * go idle before shutting down the phys, but the expectation is * that i/o has been shut off well before we reach this From 8e027db9fa310b1d5e7ad928510be800c4f004d9 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 12 May 2026 09:48:49 +0200 Subject: [PATCH 1258/1518] spi: ep93xx: fix error pointer deref after DMA setup failure commit 5e121a81667a83e9a01d62b429e340f5a4a84abc upstream. The driver falls back to PIO mode if DMA setup fails during probe. Make sure to the clear the DMA channel pointers on setup failure to avoid dereferencing an error pointer on later probe errors or driver unbind. This issue was flagged by Sashiko when reviewing a devres allocation conversion patch. Fixes: e79e7c2df627 ("spi: ep93xx: add DT support for Cirrus EP93xx") Link: https://sashiko.dev/#/patchset/20260429091333.165363-1-johan%40kernel.org?part=10 Cc: stable@vger.kernel.org # 6.12 Cc: Nikita Shubin Signed-off-by: Johan Hovold Acked-by: Nikita Shubin Link: https://patch.msgid.link/20260512074849.915143-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-ep93xx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c index e1d097091925c..52d2f8920cd75 100644 --- a/drivers/spi/spi-ep93xx.c +++ b/drivers/spi/spi-ep93xx.c @@ -582,12 +582,14 @@ static int ep93xx_spi_setup_dma(struct device *dev, struct ep93xx_spi *espi) espi->dma_rx = dma_request_chan(dev, "rx"); if (IS_ERR(espi->dma_rx)) { ret = dev_err_probe(dev, PTR_ERR(espi->dma_rx), "rx DMA setup failed"); + espi->dma_rx = NULL; goto fail_free_page; } espi->dma_tx = dma_request_chan(dev, "tx"); if (IS_ERR(espi->dma_tx)) { ret = dev_err_probe(dev, PTR_ERR(espi->dma_tx), "tx DMA setup failed"); + espi->dma_tx = NULL; goto fail_release_rx; } From be409d2bbe9ca7da7b05cc7dde7499bc481f0766 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 12 May 2026 09:47:33 +0200 Subject: [PATCH 1259/1518] spi: sprd: fix error pointer deref after DMA setup failure commit 3d67fffb74267772d461c02c67f1eff893ad547d upstream. The driver falls back to PIO mode if DMA setup fails during probe. Make sure to check the dma.enabled flag before trying to release the DMA channels also on late probe errors to avoid dereferencing an error pointer (or attempting to release a channel a second time). This issue was flagged by Sashiko when reviewing a devres allocation conversion patch. Fixes: 386119bc7be9 ("spi: sprd: spi: sprd: Add DMA mode support") Link: https://sashiko.dev/#/patchset/20260505072909.618363-1-johan%40kernel.org?part=10 Cc: stable@vger.kernel.org # 5.1 Cc: Lanqing Liu Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260512074733.915029-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-sprd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index 218c38841f05f..827a307c7c823 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -992,7 +992,8 @@ static int sprd_spi_probe(struct platform_device *pdev) disable_clk: clk_disable_unprepare(ss->clk); release_dma: - sprd_spi_dma_release(ss); + if (ss->dma.enable) + sprd_spi_dma_release(ss); free_controller: spi_controller_put(sctlr); From d7a076fb596c7b408ed6df74793a597990a6d860 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 12 May 2026 09:48:09 +0200 Subject: [PATCH 1260/1518] spi: ti-qspi: fix use-after-free after DMA setup failure commit ea6ec3343e05f7937a53eb6d7617b3abdb4abc19 upstream. The driver falls back to PIO mode if DMA setup fails during probe. Make sure to clear the DMA channel pointer also if buffer allocation fails to avoid passing a pointer to the released channel to the DMA engine (or trying to free the channel a second time on late probe errors or driver unbind). This issue was flagged by Sashiko when reviewing a devres allocation conversion patch. Fixes: c687c46e9e45 ("spi: spi-ti-qspi: Use bounce buffer if read buffer is not DMA'ble") Link: https://sashiko.dev/#/patchset/20260505072909.618363-1-johan%40kernel.org?part=17 Cc: stable@vger.kernel.org # 4.12 Cc: Vignesh R Signed-off-by: Johan Hovold Link: https://patch.msgid.link/20260512074809.915084-1-johan@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-ti-qspi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index ba54d222d0e0b..28a867c164c42 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -868,6 +868,7 @@ static int ti_qspi_probe(struct platform_device *pdev) dev_err(qspi->dev, "dma_alloc_coherent failed, using PIO mode\n"); dma_release_channel(qspi->rx_chan); + qspi->rx_chan = NULL; goto no_dma; } host->dma_rx = qspi->rx_chan; From 1012896f4225e8f801ff3c1648023845b66dfb11 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Wed, 13 May 2026 13:53:24 -0400 Subject: [PATCH 1261/1518] RDMA/siw: Reject MPA FPDU length underflow before signed receive math commit 0ce1bc9e46ecabe84772bb561e373c0d9876d6f2 upstream. A malicious connected siw peer can send an iWARP FPDU whose MPA length field (c_hdr->mpa_len, 16 bit big-endian, peer-controlled) is smaller than the fixed DDP/RDMAP header for the announced opcode. Soft-iWARP parses the full header in siw_get_hdr() based on iwarp_pktinfo[opcode] .hdr_len, but never compares mpa_len against that header length. siw_tcp_rx_data() then derives srx->fpdu_part_rem = be16_to_cpu(mpa_len) - fpdu_part_rcvd + MPA_HDR_SIZE; where fpdu_part_rcvd equals iwarp_pktinfo[opcode].hdr_len at this point. For a tagged WRITE (hdr_len 16, MPA_HDR_SIZE 2) the smallest on-wire mpa_len of 0 yields fpdu_part_rem = -14, and any mpa_len below hdr_len - MPA_HDR_SIZE underflows to a negative int. The signed value then flows into siw_proc_write()/siw_proc_rresp() as bytes = min(srx->fpdu_part_rem, srx->skb_new); is handed to siw_check_mem() as an int len (whose interval check addr + len > mem->va + mem->len is satisfied for a valid base when len is negative), and reaches siw_rx_data() -> siw_rx_kva() / siw_rx_umem() -> skb_copy_bits() as a signed copy length. The header copy branch in skb_copy_bits() promotes that to size_t, producing a multi-gigabyte read. KASAN under a KUnit harness that drives the real kernel TCP receive path -- a loopback AF_INET socketpair, the malformed FPDU written via kernel_sendmsg, sk_data_ready firing in softirq, tcp_read_sock dispatching to siw_tcp_rx_data -- reports: BUG: KASAN: use-after-free in skb_copy_bits+0x284/0x480 Read of size 4294967295 at addr ffff888... Call Trace: skb_copy_bits siw_rx_kva siw_rx_data siw_check_mem siw_proc_write siw_tcp_rx_data __tcp_read_sock siw_qp_llp_data_ready tcp_data_ready tcp_data_queue Add the missing invariant at the earliest point where the peer header is fully assembled. iwarp_pktinfo[*].hdr_len - MPA_HDR_SIZE is exactly the value the siw transmitter uses as the minimum mpa_len for each opcode (drivers/infiniband/sw/siw/siw_qp.c:33), so this matches the protocol contract. Out-of-range FPDUs terminate the connection with TERM_ERROR_LAYER_LLP / LLP_ETYPE_MPA / LLP_ECODE_FPDU_START -- which is RFC 5044 Section 8 error code 3 ("Marker and ULPDU Length fields do not agree on the start of an FPDU"), the correct framing-error class for this inconsistency. Fixes: 8b6a361b8c48 ("rdma/siw: receive path") Link: https://patch.msgid.link/r/20260513175325.2042630-2-michael.bommarito@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Michael Bommarito Assisted-by: Claude:claude-opus-4-7 Acked-by: Bernard Metzler Signed-off-by: Jason Gunthorpe Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/sw/siw/siw_qp_rx.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index e8a88b378d51d..34d03584160c2 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -1081,6 +1081,21 @@ static int siw_get_hdr(struct siw_rx_stream *srx) return -EAGAIN; } + /* + * Peer-controlled mpa_len must not underflow srx->fpdu_part_rem + * in siw_tcp_rx_data(); a negative value flows as a signed copy + * length into siw_check_mem() and skb_copy_bits(). + */ + if (unlikely(be16_to_cpu(c_hdr->mpa_len) + MPA_HDR_SIZE < + iwarp_pktinfo[opcode].hdr_len)) { + pr_warn_ratelimited("siw: short mpa_len %u for opcode %u (hdr_len %u)\n", + be16_to_cpu(c_hdr->mpa_len), opcode, + iwarp_pktinfo[opcode].hdr_len); + siw_init_terminate(rx_qp(srx), TERM_ERROR_LAYER_LLP, + LLP_ETYPE_MPA, LLP_ECODE_FPDU_START, 0); + return -EINVAL; + } + /* * DDP/RDMAP header receive completed. Check if the current * DDP segment starts a new RDMAP message or continues a previously From 9e3f18883a98420a3b8873c6f894bc57e9b98e41 Mon Sep 17 00:00:00 2001 From: Heechan Kang Date: Sun, 17 May 2026 15:22:32 +0900 Subject: [PATCH 1262/1518] fwctl: pds: Validate RPC input size before parsing commit e7537735028c3ad4b0bfc02ff8fa2a1a28aa04fe upstream. The fwctl core allocates the device-specific RPC input buffer with fwctl_rpc.in_len and passes that buffer to the driver callback. pdsfc_fw_rpc() casts the buffer to struct fwctl_rpc_pds and then calls pdsfc_validate_rpc(), which reads fields from that structure before checking that the input buffer is large enough to contain it. A short in_len can make pds_fwctl read beyond the allocation. Reject pds RPC buffers that are smaller than struct fwctl_rpc_pds before parsing any pds-specific fields. Fixes: 92c66ee829b9 ("pds_fwctl: add rpc and query support") Link: https://patch.msgid.link/r/20260517062232.1858747-1-gganji11@naver.com Cc: stable@vger.kernel.org # v6.15+ Signed-off-by: Heechan Kang Reviewed-by: Dave Jiang Signed-off-by: Jason Gunthorpe Signed-off-by: Greg Kroah-Hartman --- drivers/fwctl/pds/main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/fwctl/pds/main.c b/drivers/fwctl/pds/main.c index 1809853f63538..ccc5654d3ae74 100644 --- a/drivers/fwctl/pds/main.c +++ b/drivers/fwctl/pds/main.c @@ -362,6 +362,9 @@ static void *pdsfc_fw_rpc(struct fwctl_uctx *uctx, enum fwctl_rpc_scope scope, void *out = NULL; int err; + if (in_len < sizeof(*rpc)) + return ERR_PTR(-EINVAL); + err = pdsfc_validate_rpc(pdsfc, rpc, scope); if (err) return ERR_PTR(err); From f27a3b9aadfb53150a1b033f1d463f63ad800cf6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 22 May 2026 15:05:07 +0800 Subject: [PATCH 1263/1518] LoongArch: kprobes: Use larch_insn_text_copy() to patch instructions commit e3ef9a28f558d1cbf0b42d6dcd16c60da557562b upstream. On SMP systems, kprobe handlers would occasionally fail to execute on certain CPU cores. The issue is hard to reproduce and typically occurs randomly under high system load. The root cause is a software-side instruction hazard. According to the LoongArch Reference Manual, while the cache coherency is maintained by hardware, software must explicitly use the "IBAR" instruction to ensure the instruction fetch unit (IFU) observes the effects of recent stores. The current arch_arm_kprobe() and arch_disarm_kprobe() only execute the "IBAR" barrier (via flush_insn_slot -> local_flush_icache_range) on the local CPU. This leaves a vulnerable window where remote CPU cores may continue executing stale instructions from their pipelines or prefetch buffers, as they have not executed an "IBAR" since the code modification. Switch to larch_insn_text_copy() to fix this: 1. Synchronization: It uses stop_machine_cpuslocked() to synchronize all online CPUs, ensuring no CPU is executing the target code area during modification. 2. Visibility: By passing cpu_online_mask to stop_machine_cpuslocked(), the callback text_copy_cb() is executed on all online cores. Each CPU core invokes local_flush_icache_range() to execute "IBAR", clearing instruction hazards system-wide and ensuring the "break" instruction is visible to the fetch units of all cores. 3. Robustness: It properly manages memory write permissions (ROX/RW) for the kernel text segment during patching, ensuring compatibility with CONFIG_STRICT_KERNEL_RWX. Cc: # 6.18+ Fixes: 6d4cc40fb5f5 ("LoongArch: Add kprobes support") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/kernel/kprobes.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c index 8ba391cfabb00..04b5b05715cdc 100644 --- a/arch/loongarch/kernel/kprobes.c +++ b/arch/loongarch/kernel/kprobes.c @@ -60,16 +60,18 @@ NOKPROBE_SYMBOL(arch_prepare_kprobe); /* Install breakpoint in text */ void arch_arm_kprobe(struct kprobe *p) { - *p->addr = KPROBE_BP_INSN; - flush_insn_slot(p); + u32 insn = KPROBE_BP_INSN; + + larch_insn_text_copy(p->addr, &insn, LOONGARCH_INSN_SIZE); } NOKPROBE_SYMBOL(arch_arm_kprobe); /* Remove breakpoint from text */ void arch_disarm_kprobe(struct kprobe *p) { - *p->addr = p->opcode; - flush_insn_slot(p); + u32 insn = p->opcode; + + larch_insn_text_copy(p->addr, &insn, LOONGARCH_INSN_SIZE); } NOKPROBE_SYMBOL(arch_disarm_kprobe); From 22d9b9739b8ead1445ad4b3aa514b181b29b6893 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 21 May 2026 20:58:40 +0800 Subject: [PATCH 1264/1518] LoongArch: Remove unused code to avoid build warning commit 0ccc9d47cf020994097ff51827cebd04aa2b0bf4 upstream. After commit feee6b2989165631b1 ("mm/memory_hotplug: shrink zones when offlining memory"), __remove_pages() doesn't need the "zone" parameter so the "page" variable is also unused. Remove the unused code to avoid such build warning: arch/loongarch/mm/init.c: In function 'arch_remove_memory': arch/loongarch/mm/init.c:134:22: warning: variable 'page' set but not used [-Wunused-but-set-variable=] 134 | struct page *page = pfn_to_page(start_pfn); Cc: Reviewed-by: Guo Ren Signed-off-by: Huacai Chen Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/mm/init.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 6bfd4b8dad1b6..900ce1da75a43 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -97,11 +97,7 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn); - /* With altmap the first mapped page is offset from @start */ - if (altmap) - page += vmem_altmap_offset(altmap); __remove_pages(start_pfn, nr_pages, altmap); } #endif From 508fd8ab158abd04b7f7d0f707cd6d6c405df4ea Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 6 May 2026 13:57:00 +0200 Subject: [PATCH 1265/1518] device property: set fwnode->secondary to NULL in fwnode_init() commit 215c90ee656114f5e8c32408228d97082f8e0eef upstream. If a firmware node is allocated on the stack (for instance: temporary software node whose life-time we control) or on the heap - but using a non-zeroing allocation function - and initialized using fwnode_init(), its secondary pointer will contain uninitalized memory which likely will be neither NULL nor IS_ERR() and so may end up being dereferenced (for example: in dev_to_swnode()). Set fwnode->secondary to NULL on initialization. Cc: stable Fixes: 01bb86b380a3 ("driver core: Add fwnode_init()") Signed-off-by: Bartosz Golaszewski Reviewed-by: Rafael J. Wysocki (Intel) Reviewed-by: Andy Shevchenko Reviewed-by: Sakari Ailus Link: https://patch.msgid.link/20260506115701.23035-1-bartosz.golaszewski@oss.qualcomm.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 80b38fbf2121c..31df7608737e7 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -208,6 +208,7 @@ struct fwnode_operations { static inline void fwnode_init(struct fwnode_handle *fwnode, const struct fwnode_operations *ops) { + fwnode->secondary = NULL; fwnode->ops = ops; INIT_LIST_HEAD(&fwnode->consumers); INIT_LIST_HEAD(&fwnode->suppliers); From 942968260e61d4a5d7552b20814b6277f9c553df Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Fri, 8 May 2026 14:57:21 +0800 Subject: [PATCH 1266/1518] drm/msm: Fix shrinker deadlock commit 3392291fc509d8ad6e4ad90f15b0a193f721cbc9 upstream. With PROVE_LOCKING on an Snapdragon X1 and VM reclaim pressure, we see: ====================================================== WARNING: possible circular locking dependency detected 7.0.0-debug+ #43 Tainted: G W ------------------------------------------------------ kswapd0/82 is trying to acquire lock: ffff800080ec3870 (reservation_ww_class_acquire){+.+.}-{0:0}, at: msm_gem_shrinker_scan+0x17c/0x400 [msm] but task is already holding lock: ffffc31709b263b8 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x88/0x988 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (fs_reclaim){+.+.}-{0:0}: __lock_acquire+0x4d0/0xad0 lock_acquire.part.0+0xc4/0x248 lock_acquire+0x8c/0x248 fs_reclaim_acquire+0xd0/0xf0 dma_resv_lockdep+0x224/0x348 do_one_initcall+0x84/0x5d0 do_initcalls+0x194/0x1d8 kernel_init_freeable+0x128/0x180 kernel_init+0x2c/0x160 ret_from_fork+0x10/0x20 -> #1 (reservation_ww_class_mutex){+.+.}-{4:4}: __lock_acquire+0x4d0/0xad0 lock_acquire.part.0+0xc4/0x248 lock_acquire+0x8c/0x248 dma_resv_lockdep+0x1a8/0x348 do_one_initcall+0x84/0x5d0 do_initcalls+0x194/0x1d8 kernel_init_freeable+0x128/0x180 kernel_init+0x2c/0x160 ret_from_fork+0x10/0x20 -> #0 (reservation_ww_class_acquire){+.+.}-{0:0}: check_prev_add+0x114/0x790 validate_chain+0x594/0x6f0 __lock_acquire+0x4d0/0xad0 lock_acquire.part.0+0xc4/0x248 lock_acquire+0x8c/0x248 drm_gem_lru_scan+0x1ac/0x440 msm_gem_shrinker_scan+0x17c/0x400 [msm] do_shrink_slab+0x150/0x4a0 shrink_slab+0x144/0x460 shrink_one+0x9c/0x1b0 shrink_many+0x27c/0x5c0 shrink_node+0x344/0x550 balance_pgdat+0x2c0/0x988 kswapd+0x11c/0x318 kthread+0x10c/0x128 ret_from_fork+0x10/0x20 other info that might help us debug this: Chain exists of: reservation_ww_class_acquire --> reservation_ww_class_mutex --> fs_reclaim Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(reservation_ww_class_mutex); lock(fs_reclaim); lock(reservation_ww_class_acquire); *** DEADLOCK *** 1 lock held by kswapd0/82: #0: ffffc31709b263b8 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x88/0x988 stack backtrace: CPU: 4 UID: 0 PID: 82 Comm: kswapd0 Tainted: G W 7.0.0-debug+ #43 PREEMPT(full) Tainted: [W]=WARN Hardware name: LENOVO 21BX0016US/21BX0016US, BIOS N3HET94W (1.66 ) 09/15/2025 Call trace: show_stack+0x20/0x40 (C) dump_stack_lvl+0x9c/0xd0 dump_stack+0x18/0x30 print_circular_bug+0x114/0x120 check_noncircular+0x178/0x198 check_prev_add+0x114/0x790 validate_chain+0x594/0x6f0 __lock_acquire+0x4d0/0xad0 lock_acquire.part.0+0xc4/0x248 lock_acquire+0x8c/0x248 drm_gem_lru_scan+0x1ac/0x440 msm_gem_shrinker_scan+0x17c/0x400 [msm] do_shrink_slab+0x150/0x4a0 shrink_slab+0x144/0x460 shrink_one+0x9c/0x1b0 shrink_many+0x27c/0x5c0 shrink_node+0x344/0x550 balance_pgdat+0x2c0/0x988 kswapd+0x11c/0x318 kthread+0x10c/0x128 ret_from_fork+0x10/0x20 kswapd0 holding fs_reclaim calls the MSM shrinker, which calls dma_resv_lock. This in turn acquires fs_reclaim. Fix this deadlock by using dma_resv_trylock() instead, dropping the subsequently unused passed wait-wound lock 'ticket'. Cc: stable@vger.kernel.org Signed-off-by: Daniel J Blueman Fixes: fe4952b5f27c ("drm/msm: Convert vm locking") Patchwork: https://patchwork.freedesktop.org/patch/723564/ Message-ID: <20260508065722.18785-1-daniel@quora.org> [rob: fixup compile errors, replace lockdep splat with something legible] Signed-off-by: Rob Clark Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/msm/msm_gem_shrinker.c | 40 +++++++++++--------------- 1 file changed, 16 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 31fa51a44f86e..6e39e4e578bba 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -43,8 +43,7 @@ msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) } static bool -with_vm_locks(struct ww_acquire_ctx *ticket, - void (*fn)(struct drm_gem_object *obj), +with_vm_locks(void (*fn)(struct drm_gem_object *obj), struct drm_gem_object *obj) { /* @@ -52,7 +51,7 @@ with_vm_locks(struct ww_acquire_ctx *ticket, * success paths */ struct drm_gpuvm_bo *vm_bo, *last_locked = NULL; - int ret = 0; + bool locked = true; drm_gem_for_each_gpuvm_bo (vm_bo, obj) { struct dma_resv *resv = drm_gpuvm_resv(vm_bo->vm); @@ -60,23 +59,14 @@ with_vm_locks(struct ww_acquire_ctx *ticket, if (resv == obj->resv) continue; - ret = dma_resv_lock(resv, ticket); - - /* - * Since we already skip the case when the VM and obj - * share a resv (ie. _NO_SHARE objs), we don't expect - * to hit a double-locking scenario... which the lock - * unwinding cannot really cope with. - */ - WARN_ON(ret == -EALREADY); - /* - * Don't bother with slow-lock / backoff / retry sequence, - * if we can't get the lock just give up and move on to - * the next object. + * dma_resv_lock can't be used due to acquiring 'ticket' before the + * fs_reclaim lock, which is held in shrinker context */ - if (ret) + if (!dma_resv_trylock(resv)) { + locked = false; goto out_unlock; + } /* * Hold a ref to prevent the vm_bo from being freed @@ -108,11 +98,11 @@ with_vm_locks(struct ww_acquire_ctx *ticket, } } - return ret == 0; + return locked; } static bool -purge(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) +purge(struct drm_gem_object *obj, struct ww_acquire_ctx *) { if (!is_purgeable(to_msm_bo(obj))) return false; @@ -120,11 +110,11 @@ purge(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) if (msm_gem_active(obj)) return false; - return with_vm_locks(ticket, msm_gem_purge, obj); + return with_vm_locks(msm_gem_purge, obj); } static bool -evict(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) +evict(struct drm_gem_object *obj, struct ww_acquire_ctx *) { if (is_unevictable(to_msm_bo(obj))) return false; @@ -132,7 +122,7 @@ evict(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) if (msm_gem_active(obj)) return false; - return with_vm_locks(ticket, msm_gem_evict, obj); + return with_vm_locks(msm_gem_evict, obj); } static bool @@ -164,7 +154,6 @@ static unsigned long msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { struct msm_drm_private *priv = shrinker->private_data; - struct ww_acquire_ctx ticket; struct { struct drm_gem_lru *lru; bool (*shrink)(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket); @@ -185,11 +174,14 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) for (unsigned i = 0; (nr > 0) && (i < ARRAY_SIZE(stages)); i++) { if (!stages[i].cond) continue; + /* + * 'ticket' not needed on trylock paths + */ stages[i].freed = drm_gem_lru_scan(stages[i].lru, nr, &stages[i].remaining, stages[i].shrink, - &ticket); + NULL); nr -= stages[i].freed; freed += stages[i].freed; remaining += stages[i].remaining; From 0f8efc45740b0628a787d1b0be8a0ddabd700625 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Fri, 15 May 2026 12:07:14 -0300 Subject: [PATCH 1267/1518] drm/v3d: Fix use-after-free of CPU job query arrays on error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b0fe80c0b9250b35e2211bf3117e7aca814a21b0 upstream. The CPU job ioctl's fail label calls kvfree() on cpu_job's timestamp and performance query arrays after v3d_job_cleanup(), which drops the job's last reference and frees cpu_job. Reading cpu_job at that point is a use-after-free. Also, on the early v3d_job_init() failure path, it is a NULL dereference, since v3d_job_deallocate() zeroes the local pointer. In the success path, the arrays are released from the scheduler's .free_job callback, but on the error path, they are freed manually, as the job was never pushed to the scheduler. While the success path deals with this correctly, the fail path doesn't. On top of that, the manual kvfree() calls only free the array storage; they don't drm_syncobj_put() the per-query syncobjs that v3d_timestamp_query_info_free() and v3d_performance_query_info_free() release on the success path. So the same fail path that triggers the use-after-free also leaks one syncobj reference per query. Unify the CPU job teardown into the CPU job's kref destructor, mirroring v3d_render_job_free(). The scheduler's .free_job slot reverts to the generic v3d_sched_job_free() and the fail label drops the manual kvfree() calls, leaving a single teardown path that is reached from both the scheduler and the ioctl error path. That removes the use-after-free, the NULL dereference, and the syncobj leak by construction. Cc: stable@vger.kernel.org Fixes: 9ba0ff3e083f ("drm/v3d: Create a CPU job extension for the timestamp query job") Assisted-by: Claude:claude-opus-4.7 Reviewed-by: Iago Toral Quiroga Link: https://patch.msgid.link/20260515-v3d-cpu-job-leaks-v1-1-7f147cbbf935@igalia.com Signed-off-by: Maíra Canal Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/v3d/v3d_sched.c | 16 +--------------- drivers/gpu/drm/v3d/v3d_submit.c | 19 ++++++++++++++++--- 2 files changed, 17 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 0ec06bfbbebb5..e0cbd12c51c93 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -103,20 +103,6 @@ v3d_performance_query_info_free(struct v3d_performance_query_info *query_info, } } -static void -v3d_cpu_job_free(struct drm_sched_job *sched_job) -{ - struct v3d_cpu_job *job = to_cpu_job(sched_job); - - v3d_timestamp_query_info_free(&job->timestamp_query, - job->timestamp_query.count); - - v3d_performance_query_info_free(&job->performance_query, - job->performance_query.count); - - v3d_job_cleanup(&job->base); -} - static void v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job) { @@ -860,7 +846,7 @@ static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = { static const struct drm_sched_backend_ops v3d_cpu_sched_ops = { .run_job = v3d_cpu_job_run, - .free_job = v3d_cpu_job_free + .free_job = v3d_sched_job_free }; static int diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 23fa18e5e65c8..acb1dd7458a39 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -119,6 +119,21 @@ v3d_render_job_free(struct kref *ref) v3d_job_free(ref); } +static void +v3d_cpu_job_free(struct kref *ref) +{ + struct v3d_cpu_job *job = container_of(ref, struct v3d_cpu_job, + base.refcount); + + v3d_timestamp_query_info_free(&job->timestamp_query, + job->timestamp_query.count); + + v3d_performance_query_info_free(&job->performance_query, + job->performance_query.count); + + v3d_job_free(ref); +} + void v3d_job_cleanup(struct v3d_job *job) { if (!job) @@ -1321,7 +1336,7 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_cpu_ioctl(&v3d->drm, cpu_job->job_type); ret = v3d_job_init(v3d, file_priv, &cpu_job->base, - v3d_job_free, 0, &se, V3D_CPU); + v3d_cpu_job_free, 0, &se, V3D_CPU); if (ret) { v3d_job_deallocate((void *)&cpu_job); goto fail; @@ -1404,8 +1419,6 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data, v3d_job_cleanup((void *)csd_job); v3d_job_cleanup(clean_job); v3d_put_multisync_post_deps(&se); - kvfree(cpu_job->timestamp_query.queries); - kvfree(cpu_job->performance_query.queries); return ret; } From 35671087a272cd236ff2785eff16970b0ee9b112 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Fri, 15 May 2026 12:07:15 -0300 Subject: [PATCH 1268/1518] drm/v3d: Release indirect CSD GEM reference on CPU job free MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6eb6e5acafa46854d4363e6c34981289995f3ace upstream. v3d_get_cpu_indirect_csd_params() takes a reference to the indirect BO via drm_gem_object_lookup() and stashes it in cpu_job->indirect_csd.indirect, but nothing on the CPU job teardown path ever drops that reference. Drop the extra reference in v3d_cpu_job_free(). The NULL check covers ioctl errors before the lookup ran and CPU job types other than V3D_CPU_JOB_TYPE_INDIRECT_CSD, which leave the field zero-initialised. Cc: stable@vger.kernel.org Fixes: 18b8413b25b7 ("drm/v3d: Create a CPU job extension for a indirect CSD job") Assisted-by: Claude:claude-opus-4.7 Reviewed-by: Iago Toral Quiroga Link: https://patch.msgid.link/20260515-v3d-cpu-job-leaks-v1-2-7f147cbbf935@igalia.com Signed-off-by: Maíra Canal Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/v3d/v3d_submit.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index acb1dd7458a39..95b9e68b0dfe5 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -131,6 +131,9 @@ v3d_cpu_job_free(struct kref *ref) v3d_performance_query_info_free(&job->performance_query, job->performance_query.count); + if (job->indirect_csd.indirect) + drm_gem_object_put(job->indirect_csd.indirect); + v3d_job_free(ref); } From 8fadd01cf461fee5bb11506621339c548447e5c7 Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Tue, 19 May 2026 13:52:47 +0530 Subject: [PATCH 1269/1518] drm/virtio: use uninterruptible resv lock for plane updates commit 9af1b6e175c82daf4b423da339a722d8e67a735a upstream. virtio_gpu_cursor_plane_update() and virtio_gpu_resource_flush() lock the framebuffer BO's dma_resv via virtio_gpu_array_lock_resv() and ignore its return value. The function can fail with -EINTR from dma_resv_lock_interruptible() (signal during lock wait) or with -ENOMEM from dma_resv_reserve_fences() (fence slot allocation), leaving the resv lock not held. The queue path then walks the object array and calls dma_resv_add_fence(), which requires the lock held; with lockdep enabled this trips dma_resv_assert_held(): WARNING: drivers/dma-buf/dma-resv.c:296 at dma_resv_add_fence+0x71e/0x840 Call Trace: virtio_gpu_array_add_fence virtio_gpu_queue_ctrl_sgs virtio_gpu_queue_fenced_ctrl_buffer virtio_gpu_cursor_plane_update drm_atomic_helper_commit_planes drm_atomic_helper_commit_tail commit_tail drm_atomic_helper_commit drm_atomic_commit drm_atomic_helper_update_plane __setplane_atomic drm_mode_cursor_universal drm_mode_cursor_common drm_mode_cursor_ioctl drm_ioctl __x64_sys_ioctl Beyond the WARN, mutating the dma_resv fence list without the lock races with concurrent readers/writers and can corrupt the list. Both call sites run inside the .atomic_update plane callback, which DRM atomic helpers do not allow to fail (by the time it runs, the commit has been signed off to userspace and there is no clean rollback path). Moving the lock acquisition to .prepare_fb was rejected because the broader lock scope deadlocks against other BO locking paths in the same atomic commit. Introduce virtio_gpu_lock_one_resv_uninterruptible() that uses dma_resv_lock() instead of dma_resv_lock_interruptible(). This eliminates the -EINTR failure mode -- the realistic syzbot trigger -- without extending the lock hold across the commit. The helper locks a single BO and rejects nents > 1 with -EINVAL; both fix sites lock exactly one BO. Use it from virtio_gpu_cursor_plane_update() and virtio_gpu_resource_flush(); check the return value to handle the remaining -ENOMEM case from dma_resv_reserve_fences() by freeing the objs and skipping the plane update for that frame. The framebuffer BOs touched here are not shared with other contexts and lock contention is expected to be brief, so the loss of signal-interruptibility is acceptable. Other callers of virtio_gpu_array_lock_resv() (the ioctl paths) continue to use the interruptible variant. The bug was reported by syzbot, triggered via fault injection (fail_nth) on the DRM_IOCTL_MODE_CURSOR path, which forces the -ENOMEM branch in dma_resv_reserve_fences(). Reported-by: syzbot+72bd3dd3a5d5f39a0271@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=72bd3dd3a5d5f39a0271 Fixes: 5cfd31c5b3a3 ("drm/virtio: fix virtio_gpu_cursor_plane_update().") Cc: stable@vger.kernel.org Signed-off-by: Deepanshu Kartikey Signed-off-by: Dmitry Osipenko Link: https://patch.msgid.link/20260519082247.34470-1-kartikey406@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/virtio/virtgpu_drv.h | 1 + drivers/gpu/drm/virtio/virtgpu_gem.c | 17 +++++++++++++++++ drivers/gpu/drm/virtio/virtgpu_plane.c | 10 ++++++++-- 3 files changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index f17660a71a3e7..2f3531950aa4d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -317,6 +317,7 @@ virtio_gpu_array_from_handles(struct drm_file *drm_file, u32 *handles, u32 nents void virtio_gpu_array_add_obj(struct virtio_gpu_object_array *objs, struct drm_gem_object *obj); int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs); +int virtio_gpu_lock_one_resv_uninterruptible(struct virtio_gpu_object_array *objs); void virtio_gpu_array_unlock_resv(struct virtio_gpu_object_array *objs); void virtio_gpu_array_add_fence(struct virtio_gpu_object_array *objs, struct dma_fence *fence); diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 90c99d83c4cfd..015b5debd7451 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -238,6 +238,23 @@ int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs) return ret; } +int virtio_gpu_lock_one_resv_uninterruptible(struct virtio_gpu_object_array *objs) +{ + int ret; + + if (objs->nents != 1) + return -EINVAL; + + dma_resv_lock(objs->objs[0]->resv, NULL); + + ret = dma_resv_reserve_fences(objs->objs[0]->resv, 1); + if (ret) { + virtio_gpu_array_unlock_resv(objs); + return ret; + } + return 0; +} + void virtio_gpu_array_unlock_resv(struct virtio_gpu_object_array *objs) { if (objs->nents == 1) { diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 29e4b458ae573..192327723bb9a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -214,7 +214,10 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, if (!objs) return; virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); - virtio_gpu_array_lock_resv(objs); + if (virtio_gpu_lock_one_resv_uninterruptible(objs)) { + virtio_gpu_array_put_free(objs); + return; + } virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, width, height, objs, vgplane_st->fence); @@ -458,7 +461,10 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, if (!objs) return; virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); - virtio_gpu_array_lock_resv(objs); + if (virtio_gpu_lock_one_resv_uninterruptible(objs)) { + virtio_gpu_array_put_free(objs); + return; + } virtio_gpu_cmd_transfer_to_host_2d (vgdev, 0, plane->state->crtc_w, From 3ed448c1dc78ddbf2e1f29dc00788c028ccdbb82 Mon Sep 17 00:00:00 2001 From: Alan Liu Date: Fri, 1 May 2026 12:35:48 +0800 Subject: [PATCH 1270/1518] drm/amdgpu/vpe: Force collaborate sync after TRAP commit b6074630a461b1322a814988779005cbc43612ea upstream. VPE1 could possibly hang and fail to power off at the end of commands in collaboration mode. This workaround adds a COLLAB_SYNC after TRAP to force instances synchronized to avoid VPE1 fail to power off. Reviewed-by: Mario Limonciello (AMD) Signed-off-by: Alan liu Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5171 Signed-off-by: Alex Deucher (cherry picked from commit a8b749c5c5afb7e5daa2bfb95d958fb3c6b8f055) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c index aa78c2ee9e21c..bd5eff4bafe79 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c @@ -562,6 +562,11 @@ static void vpe_ring_emit_fence(struct amdgpu_ring *ring, uint64_t addr, amdgpu_ring_write(ring, 0); } + /* WA: Force sync after TRAP to avoid VPE1 fail to power off */ + if (ring->adev->vpe.collaborate_mode) { + amdgpu_ring_write(ring, VPE_CMD_HEADER(VPE_CMD_OPCODE_COLLAB_SYNC, 0)); + amdgpu_ring_write(ring, 0xabcd); + } } static void vpe_ring_emit_pipeline_sync(struct amdgpu_ring *ring) @@ -968,7 +973,7 @@ static const struct amdgpu_ring_funcs vpe_ring_funcs = { .emit_frame_size = 5 + /* vpe_ring_init_cond_exec */ 6 + /* vpe_ring_emit_pipeline_sync */ - 10 + 10 + 10 + /* vpe_ring_emit_fence */ + 12 + 12 + 12 + /* vpe_ring_emit_fence */ /* vpe_ring_emit_vm_flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6, From 95306db11956dd8d82f56a20452c13008519388a Mon Sep 17 00:00:00 2001 From: Julien Chauveau Date: Tue, 24 Mar 2026 20:30:11 +0100 Subject: [PATCH 1271/1518] drm/bridge: it66121: acquire reset GPIO in probe commit e02b5262fd288cc235f14e12233ea54e78c04611 upstream. The it66121_ctx structure has a gpio_reset field, and it66121_hw_reset() calls gpiod_set_value() on it. However, the GPIO descriptor is never acquired via devm_gpiod_get(), leaving gpio_reset as NULL throughout the driver lifetime. gpiod_set_value() silently returns when passed a NULL descriptor, so the hardware reset sequence in it66121_hw_reset() is a no-op. This leaves the chip in an undefined state at probe time, which can prevent it from responding on the I2C bus. The DT binding marks reset-gpios as a required property, so all compliant device trees provide this GPIO. Add the missing devm_gpiod_get() call after enabling power supplies and before the hardware reset, so the chip is properly reset with power applied. Fixes: 988156dc2fc9 ("drm: bridge: add it66121 driver") Cc: stable@vger.kernel.org Signed-off-by: Julien Chauveau Reviewed-by: Javier Martinez Canillas Tested-by: Javier Martinez Canillas Link: https://patch.msgid.link/20260324193011.16583-1-chauveau.julien@gmail.com Signed-off-by: Javier Martinez Canillas Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/bridge/ite-it66121.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index aa7b1dcc5d70e..f9aff56dd5032 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -1559,6 +1559,11 @@ static int it66121_probe(struct i2c_client *client) return ret; } + ctx->gpio_reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(ctx->gpio_reset)) + return dev_err_probe(dev, PTR_ERR(ctx->gpio_reset), + "Failed to get reset GPIO\n"); + it66121_hw_reset(ctx); ctx->regmap = devm_regmap_init_i2c(client, &it66121_regmap_config); From d35563813296ec7e965ad87415a0f82944bc41a2 Mon Sep 17 00:00:00 2001 From: Osama Abdelkader Date: Thu, 30 Apr 2026 21:56:59 +0200 Subject: [PATCH 1272/1518] drm/bridge: megachips: remove bridge when irq request fails commit d45d5c819f2cd0b6b5d76a194a537a5f4aeefecb upstream. If devm_request_threaded_irq() fails after drm_bridge_add(), remove the bridge before returning. Keep drm_bridge_add() rather than devm_drm_bridge_add(): registration is tied to the STDP4028 device while ge_b850v3_register() may complete from either I2C probe; devm would not unwind the bridge if the other client's probe fails. Signed-off-by: Osama Abdelkader Fixes: fcfa0ddc18ed ("drm/bridge: Drivers for megachips-stdpxxxx-ge-b850v3-fw (LVDS-DP++)") Cc: stable@vger.kernel.org Reviewed-by: Luca Ceresoli Tested-by: Ian Ray Link: https://patch.msgid.link/20260430195700.80317-1-osama.abdelkader@gmail.com Signed-off-by: Luca Ceresoli Signed-off-by: Greg Kroah-Hartman --- .../drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index c9e6505cbd882..2d02cc69f2374 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -251,7 +251,6 @@ static void ge_b850v3_lvds_remove(void) goto out; drm_bridge_remove(&ge_b850v3_lvds_ptr->bridge); - ge_b850v3_lvds_ptr = NULL; out: mutex_unlock(&ge_b850v3_lvds_dev_mutex); @@ -261,6 +260,7 @@ static int ge_b850v3_register(void) { struct i2c_client *stdp4028_i2c = ge_b850v3_lvds_ptr->stdp4028_i2c; struct device *dev = &stdp4028_i2c->dev; + int ret; /* drm bridge initialization */ ge_b850v3_lvds_ptr->bridge.ops = DRM_BRIDGE_OP_DETECT | @@ -277,11 +277,15 @@ static int ge_b850v3_register(void) if (!stdp4028_i2c->irq) return 0; - return devm_request_threaded_irq(&stdp4028_i2c->dev, - stdp4028_i2c->irq, NULL, - ge_b850v3_lvds_irq_handler, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, - "ge-b850v3-lvds-dp", ge_b850v3_lvds_ptr); + ret = devm_request_threaded_irq(&stdp4028_i2c->dev, + stdp4028_i2c->irq, NULL, + ge_b850v3_lvds_irq_handler, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "ge-b850v3-lvds-dp", ge_b850v3_lvds_ptr); + if (ret) + drm_bridge_remove(&ge_b850v3_lvds_ptr->bridge); + + return ret; } static int stdp4028_ge_b850v3_fw_probe(struct i2c_client *stdp4028_i2c) From 6bbd703ea1c141d7ac0e7f7e82ff5fd237b67a17 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Mon, 4 May 2026 11:14:45 -0400 Subject: [PATCH 1273/1518] drm/amd/display: Fix integer overflow in bios_get_image() commit cd86529ec61474a38c3837fb7823790a7c3f8cce upstream. [Why&How] The bounds check in bios_get_image() computes 'offset + size' using unsigned 32-bit arithmetic before comparing against bios_size. If a VBIOS image contains a near-UINT32_MAX offset the addition wraps to a small value, the comparison passes, and the function returns a wild pointer past the VBIOS mapping. Additionally, the comparison uses '<' (strict), which incorrectly rejects the valid exact-fit case where offset + size == bios_size. Fix both issues by restructuring the check to avoid the addition entirely: first reject if offset alone exceeds bios_size, then check size against the remaining space (bios_size - offset). This eliminates the overflow and correctly permits exact-fit accesses. Assisted-by: GitHub Copilot:claude-opus-4.6 Reviewed-by: Alex Hung Signed-off-by: Harry Wentland Signed-off-by: Ivan Lipski Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit d40fb392af659c4a02b560319f226842f6ec1a95) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.c index 8d2cf95ae7393..e00dc05c2d9d9 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser_helper.c @@ -37,10 +37,13 @@ uint8_t *bios_get_image(struct dc_bios *bp, uint32_t offset, uint32_t size) { - if (bp->bios && offset + size < bp->bios_size) - return bp->bios + offset; - else + if (!bp->bios) return NULL; + + if (offset > bp->bios_size || size > bp->bios_size - offset) + return NULL; + + return bp->bios + offset; } #include "reg_helper.h" From 7ca695b3122297b06a3ed605bbe1cd32c85d9f5a Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Mon, 4 May 2026 16:14:11 -0400 Subject: [PATCH 1274/1518] drm/amd/display: Validate GPIO pin LUT table size before iterating commit 86d2b20644b11d21fe52c596e6e922b4590a3e3f upstream. [Why&How] The GPIO pin table parsers in get_gpio_i2c_info() and bios_parser_get_gpio_pin_info() derive an element count from the VBIOS table_header.structuresize field, then iterate over gpio_pin[] entries. However, GET_IMAGE() only validates that the table header itself fits within the BIOS image. If the VBIOS reports a structuresize larger than the actual mapped data, the loop reads past the end of the BIOS image, causing an out-of-bounds read. Fix this by calling bios_get_image() to validate that the full claimed structuresize is accessible within the BIOS image before entering the loop in both functions. Assisted-by: GitHub Copilot:claude-opus-4-6 Reviewed-by: Alex Hung Signed-off-by: Harry Wentland Signed-off-by: Ivan Lipski Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit ba5e95b43b773ae1bf1f66ee6b31eb774e65afe3) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 550a9f1d03f82..e004458f0e43d 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -492,6 +492,10 @@ static enum bp_result get_gpio_i2c_info( - sizeof(struct atom_common_table_header)) / sizeof(struct atom_gpio_pin_assignment); + if (!bios_get_image(&bp->base, DATA_TABLES(gpio_pin_lut), + le16_to_cpu(header->table_header.structuresize))) + return BP_RESULT_BADBIOSTABLE; + pin = (struct atom_gpio_pin_assignment *) header->gpio_pin; for (table_index = 0; table_index < count; table_index++) { @@ -680,6 +684,11 @@ static enum bp_result bios_parser_get_gpio_pin_info( count = (le16_to_cpu(header->table_header.structuresize) - sizeof(struct atom_common_table_header)) / sizeof(struct atom_gpio_pin_assignment); + + if (!bios_get_image(&bp->base, DATA_TABLES(gpio_pin_lut), + le16_to_cpu(header->table_header.structuresize))) + return BP_RESULT_BADBIOSTABLE; + for (i = 0; i < count; ++i) { if (header->gpio_pin[i].gpio_id != gpio_id) continue; From 1ecde19bfce6535bffddad1139ff466b6d401b8e Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Thu, 7 May 2026 16:26:31 -0400 Subject: [PATCH 1275/1518] drm/amd/display: Validate payload length and link_index in dc_process_dmub_aux_transfer_async commit 6c92f6d9600efa3ef0d9e560a2b52776d9803c29 upstream. [Why&How] dc_process_dmub_aux_transfer_async() copies payload->length bytes into a 16-byte stack buffer (dpaux.data[16]) guarded only by an ASSERT(), which is a no-op in release builds. If a caller ever passes length > 16 this results in a stack buffer overflow via memcpy. Additionally, link_index is used to dereference dc->links[] without bounds checking against dc->link_count, risking an out-of-bounds access. Replace the ASSERT with a hard runtime check that returns false when payload->length exceeds the destination buffer size, and add a bounds check for link_index before it is used. Assisted-by: GitHub Copilot:Claude claude-4-opus Reviewed-by: Alex Hung Signed-off-by: Harry Wentland Signed-off-by: Ivan Lipski Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit ba4caa9fecdf7a38f98c878ad05a8a64148b6881) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 5f2d5638c8191..0347174173f34 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -5884,7 +5884,11 @@ bool dc_process_dmub_aux_transfer_async(struct dc *dc, uint8_t action; union dmub_rb_cmd cmd = {0}; - ASSERT(payload->length <= 16); + if (link_index >= dc->link_count || !dc->links[link_index]) + return false; + + if (payload->length > sizeof(cmd.dp_aux_access.aux_control.dpaux.data)) + return false; cmd.dp_aux_access.header.type = DMUB_CMD__DP_AUX_ACCESS; cmd.dp_aux_access.header.payload_bytes = 0; From 1be1e99cbd5b74a69d3f92200ca87cf1bce852db Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 9 May 2026 22:44:12 +0200 Subject: [PATCH 1276/1518] batman-adv: v: stop OGMv2 on disabled interface commit f8ce8b8331a1bc44ad4905886a482214d428b253 upstream. When a batadv_hard_iface is disabled, its mesh_iface pointer is set to NULL. However, batadv_v_ogm_send_meshif() may still dispatch OGMs via batadv_v_ogm_queue_on_if() for interfaces that have since lost their mesh_iface association. This results in a NULL pointer dereference when batadv_v_ogm_queue_on_if() unconditionally calls netdev_priv() on the now NULL hard_iface->mesh_iface to retrieve the batadv_priv. It is necessary to ensure that the batadv_v_ogm_queue_on_if() checks that it is using the same mesh_iface for which batadv_v_ogm_send_meshif() was called. Cc: stable@kernel.org Fixes: 0da0035942d4 ("batman-adv: OGMv2 - add basic infrastructure") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Reviewed-by: Yuan Tan Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_v_ogm.c | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index e3870492dab77..e955b4940c728 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -113,14 +113,14 @@ static void batadv_v_ogm_start_timer(struct batadv_priv *bat_priv) /** * batadv_v_ogm_send_to_if() - send a batman ogm using a given interface + * @bat_priv: the bat priv with all the mesh interface information * @skb: the OGM to send * @hard_iface: the interface to use to send the OGM */ -static void batadv_v_ogm_send_to_if(struct sk_buff *skb, +static void batadv_v_ogm_send_to_if(struct batadv_priv *bat_priv, + struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { - struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); - if (hard_iface->if_status != BATADV_IF_ACTIVE) { kfree_skb(skb); return; @@ -187,6 +187,7 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) /** * batadv_v_ogm_aggr_send() - flush & send aggregation queue + * @bat_priv: the bat priv with all the mesh interface information * @hard_iface: the interface with the aggregation queue to flush * * Aggregates all OGMv2 packets currently in the aggregation queue into a @@ -196,7 +197,8 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) * * Caller needs to hold the hard_iface->bat_v.aggr_list.lock. */ -static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) +static void batadv_v_ogm_aggr_send(struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface) { unsigned int aggr_len = hard_iface->bat_v.aggr_len; struct sk_buff *skb_aggr; @@ -226,27 +228,32 @@ static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) consume_skb(skb); } - batadv_v_ogm_send_to_if(skb_aggr, hard_iface); + batadv_v_ogm_send_to_if(bat_priv, skb_aggr, hard_iface); } /** * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface + * @bat_priv: the bat priv with all the mesh interface information * @skb: the OGM to queue * @hard_iface: the interface to queue the OGM on */ -static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, +static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv, + struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { - struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); + if (hard_iface->mesh_iface != bat_priv->mesh_iface) { + kfree_skb(skb); + return; + } if (!atomic_read(&bat_priv->aggregated_ogms)) { - batadv_v_ogm_send_to_if(skb, hard_iface); + batadv_v_ogm_send_to_if(bat_priv, skb, hard_iface); return; } spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); if (!batadv_v_ogm_queue_left(skb, hard_iface)) - batadv_v_ogm_aggr_send(hard_iface); + batadv_v_ogm_aggr_send(bat_priv, hard_iface); hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); __skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); @@ -343,7 +350,7 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) break; } - batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); + batadv_v_ogm_queue_on_if(bat_priv, skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); @@ -383,12 +390,14 @@ void batadv_v_ogm_aggr_work(struct work_struct *work) { struct batadv_hard_iface_bat_v *batv; struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); + bat_priv = netdev_priv(hard_iface->mesh_iface); spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); - batadv_v_ogm_aggr_send(hard_iface); + batadv_v_ogm_aggr_send(bat_priv, hard_iface); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); batadv_v_ogm_start_queue_timer(hard_iface); @@ -578,7 +587,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); - batadv_v_ogm_queue_on_if(skb, if_outgoing); + batadv_v_ogm_queue_on_if(bat_priv, skb, if_outgoing); out: batadv_orig_ifinfo_put(orig_ifinfo); From 23d4ce84df4d614f39ec3244f2a5a731d185d08d Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 14 May 2026 16:33:12 +0200 Subject: [PATCH 1277/1518] batman-adv: tvlv: abort OGM send on tvlv append failure commit 501368506563e151b322c8c3f228b796e615b90d upstream. batadv_tvlv_container_ogm_append() could fail in two ways: a memory allocation failure when resizing the packet buffer, or the tvlv data exceeding U16_MAX bytes. In both cases the function previously returned the old (now stale) tvlv_value_len rather than signalling an error, causing the OGM/OGM2 send path to transmit a packet whose TVLV length field no longer matched the actual buffer contents. And because it also didn't fill in the new TVLV data, sending either uninitialized or corrupted data on the wire. All errors in batadv_tvlv_container_ogm_append() must be forwarded to the caller. And the caller must abort the send of the OGM2. For B.A.T.M.A.N. IV, it is currently not allowed to abort the send. The non-TVLV part of the OGM must be queued up instead. Cc: stable@kernel.org Fixes: ef26157747d4 ("batman-adv: tvlv - basic infrastructure") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_iv_ogm.c | 16 +++++++++++++--- net/batman-adv/bat_v_ogm.c | 26 ++++++++++++++------------ net/batman-adv/tvlv.c | 17 ++++++++++++----- net/batman-adv/tvlv.h | 2 +- 4 files changed, 40 insertions(+), 21 deletions(-) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 74ef7dc2b2f98..7ad26128b5f7c 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -790,6 +790,7 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) u32 seqno; u16 tvlv_len = 0; unsigned long send_time; + int ret; lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); @@ -813,9 +814,18 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) * appended as it may alter the tt tvlv container */ batadv_tt_local_commit_changes(bat_priv); - tvlv_len = batadv_tvlv_container_ogm_append(bat_priv, ogm_buff, - ogm_buff_len, - BATADV_OGM_HLEN); + ret = batadv_tvlv_container_ogm_append(bat_priv, ogm_buff, + ogm_buff_len, + BATADV_OGM_HLEN); + if (ret < 0) { + /* OGMs must be queued even when the buffer allocation for + * TVLVs failed. just fall back to the non-TVLV version + */ + ret = 0; + *ogm_buff_len = BATADV_OGM_HLEN; + } + + tvlv_len = ret; } batadv_ogm_packet = (struct batadv_ogm_packet *)(*ogm_buff); diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index e955b4940c728..d66ca77b1aaa3 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -269,10 +269,10 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) struct batadv_hard_iface *hard_iface; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; - unsigned char *ogm_buff; + unsigned char **ogm_buff; struct list_head *iter; - int ogm_buff_len; - u16 tvlv_len = 0; + int *ogm_buff_len; + u16 tvlv_len; int ret; lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex); @@ -280,25 +280,27 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; - ogm_buff = bat_priv->bat_v.ogm_buff; - ogm_buff_len = bat_priv->bat_v.ogm_buff_len; + ogm_buff = &bat_priv->bat_v.ogm_buff; + ogm_buff_len = &bat_priv->bat_v.ogm_buff_len; + /* tt changes have to be committed before the tvlv data is * appended as it may alter the tt tvlv container */ batadv_tt_local_commit_changes(bat_priv); - tvlv_len = batadv_tvlv_container_ogm_append(bat_priv, &ogm_buff, - &ogm_buff_len, - BATADV_OGM2_HLEN); + ret = batadv_tvlv_container_ogm_append(bat_priv, ogm_buff, + ogm_buff_len, + BATADV_OGM2_HLEN); + if (ret < 0) + goto reschedule; - bat_priv->bat_v.ogm_buff = ogm_buff; - bat_priv->bat_v.ogm_buff_len = ogm_buff_len; + tvlv_len = ret; - skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + ogm_buff_len); + skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + *ogm_buff_len); if (!skb) goto reschedule; skb_reserve(skb, ETH_HLEN); - skb_put_data(skb, ogm_buff, ogm_buff_len); + skb_put_data(skb, *ogm_buff, *ogm_buff_len); ogm_packet = (struct batadv_ogm2_packet *)skb->data; ogm_packet->seqno = htonl(atomic_read(&bat_priv->bat_v.ogm_seqno)); diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 76dff1f9c559a..ce158d6b68567 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -306,9 +307,10 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff, * The ogm packet might be enlarged or shrunk depending on the current size * and the size of the to-be-appended tvlv containers. * - * Return: size of all appended tvlv containers in bytes. + * Return: size of all appended tvlv containers in bytes (max U16_MAX), negative + * if operation failed */ -u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, +int batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, unsigned char **packet_buff, int *packet_buff_len, int packet_min_len) { @@ -316,6 +318,7 @@ u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, struct batadv_tvlv_hdr *tvlv_hdr; u16 tvlv_value_len; void *tvlv_value; + int tvlv_len_ret; bool ret; spin_lock_bh(&bat_priv->tvlv.container_list_lock); @@ -323,9 +326,12 @@ u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len, packet_min_len, tvlv_value_len); - - if (!ret) + if (!ret) { + tvlv_len_ret = -ENOMEM; goto end; + } + + tvlv_len_ret = tvlv_value_len; if (!tvlv_value_len) goto end; @@ -344,7 +350,8 @@ u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, end: spin_unlock_bh(&bat_priv->tvlv.container_list_lock); - return tvlv_value_len; + + return tvlv_len_ret; } /** diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index e5697230d9917..f96f6b3f44a00 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -16,7 +16,7 @@ void batadv_tvlv_container_register(struct batadv_priv *bat_priv, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len); -u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, +int batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, unsigned char **packet_buff, int *packet_buff_len, int packet_min_len); void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, From ede47988ac5687793745b17c1634a496a2299919 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 9 May 2026 21:55:29 +0200 Subject: [PATCH 1278/1518] batman-adv: tvlv: reject oversized TVLV packets commit f50487e3566358b2b982b7801945e858c78ad9ab upstream. batadv_tvlv_container_ogm_append() builds a TVLV packet section from the tvlv.container_list. The total size of this section is computed by batadv_tvlv_container_list_size(), which sums the sizes of all registered containers. The return type and accumulator in batadv_tvlv_container_list_size() were u16. If the accumulated size exceeds U16_MAX, the value wraps around, causing the subsequent allocation in batadv_tvlv_container_ogm_append() to be undersized. The memcpy-style copy that follows would then write beyond the end of the allocated buffer, corrupting kernel memory. Fix this by widening the return type of batadv_tvlv_container_list_size() to size_t. In batadv_tvlv_container_ogm_append(), check the computed length against U16_MAX before proceeding, and bail out as if the allocation had failed when the limit is exceeded. Cc: stable@kernel.org Fixes: ef26157747d4 ("batman-adv: tvlv - basic infrastructure") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Reviewed-by: Yuan Tan Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tvlv.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index ce158d6b68567..cde798c82dcf1 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -160,10 +161,10 @@ batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version) * * Return: size of all currently registered tvlv containers in bytes. */ -static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) +static size_t batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) { struct batadv_tvlv_container *tvlv; - u16 tvlv_len = 0; + size_t tvlv_len = 0; lockdep_assert_held(&bat_priv->tvlv.container_list_lock); @@ -316,13 +317,17 @@ int batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, { struct batadv_tvlv_container *tvlv; struct batadv_tvlv_hdr *tvlv_hdr; - u16 tvlv_value_len; + size_t tvlv_value_len; void *tvlv_value; int tvlv_len_ret; bool ret; spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv_value_len = batadv_tvlv_container_list_size(bat_priv); + if (tvlv_value_len > U16_MAX) { + tvlv_len_ret = -E2BIG; + goto end; + } ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len, packet_min_len, tvlv_value_len); From ca3ff3d2a0af42a1636f4c01087bc50923ce50d4 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Fri, 15 May 2026 22:00:40 +0200 Subject: [PATCH 1279/1518] batman-adv: iv: recover OGM scheduling after forward packet error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit aa3153bd139a6c48667dcd02608d3b2c80bff02c upstream. When batadv_iv_ogm_schedule_buff() fails to allocate and queue a forward packet for OGM transmission, the work item that drives periodic OGM scheduling is never re-armed. This silently halts transmission of the node's own OGMs on the affected interface — only OGMs from other peers continue to be aggregated and forwarded. Fix this by tracking whether batadv_iv_ogm_queue_add() (and transitively batadv_iv_ogm_aggregate_new()) successfully scheduled a forward packet. When scheduling fails, batadv_iv_ogm_schedule_buff() falls back to queuing a dedicated recovery work item (reschedule_work) that fires after one originator interval and calls batadv_iv_ogm_schedule() again. Cc: stable@kernel.org Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_iv_ogm.c | 76 +++++++++++++++++++++++++++---------- net/batman-adv/types.h | 3 ++ 2 files changed, 60 insertions(+), 19 deletions(-) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 7ad26128b5f7c..b8b1b997960a9 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -224,6 +224,8 @@ static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) hard_iface->bat_iv.ogm_buff = NULL; mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); + + cancel_delayed_work_sync(&hard_iface->bat_iv.reschedule_work); } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) @@ -536,8 +538,10 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, * @if_incoming: interface where the packet was received * @if_outgoing: interface for which the retransmission should be considered * @own_packet: true if it is a self-generated ogm + * + * Return: whether forward packet was scheduled */ -static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, +static bool batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, int packet_len, unsigned long send_time, bool direct_link, struct batadv_hard_iface *if_incoming, @@ -561,13 +565,13 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, skb = netdev_alloc_skb_ip_align(NULL, skb_size); if (!skb) - return; + return false; forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing, queue_left, bat_priv, skb); if (!forw_packet_aggr) { kfree_skb(skb); - return; + return false; } forw_packet_aggr->skb->priority = TC_PRIO_CONTROL; @@ -590,6 +594,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, batadv_iv_send_outstanding_bat_ogm_packet); batadv_forw_packet_ogmv1_queue(bat_priv, forw_packet_aggr, send_time); + + return true; } /* aggregate a new packet into the existing ogm packet */ @@ -617,8 +623,10 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, * @if_outgoing: interface for which the retransmission should be considered * @own_packet: true if it is a self-generated ogm * @send_time: timestamp (jiffies) when the packet is to be sent + * + * Return: whether forward packet was scheduled */ -static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, +static bool batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, unsigned char *packet_buff, int packet_len, struct batadv_hard_iface *if_incoming, @@ -670,14 +678,16 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, if (!own_packet && atomic_read(&bat_priv->aggregated_ogms)) send_time += max_aggregation_jiffies; - batadv_iv_ogm_aggregate_new(packet_buff, packet_len, - send_time, direct_link, - if_incoming, if_outgoing, - own_packet); + return batadv_iv_ogm_aggregate_new(packet_buff, packet_len, + send_time, direct_link, + if_incoming, if_outgoing, + own_packet); } else { batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff, packet_len, direct_link); spin_unlock_bh(&bat_priv->forw_bat_list_lock); + + return true; } } @@ -790,6 +800,8 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) u32 seqno; u16 tvlv_len = 0; unsigned long send_time; + bool reschedule = false; + bool scheduled; int ret; lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); @@ -818,11 +830,8 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) ogm_buff_len, BATADV_OGM_HLEN); if (ret < 0) { - /* OGMs must be queued even when the buffer allocation for - * TVLVs failed. just fall back to the non-TVLV version - */ - ret = 0; - *ogm_buff_len = BATADV_OGM_HLEN; + reschedule = true; + goto out; } tvlv_len = ret; @@ -844,8 +853,11 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) /* OGMs from secondary interfaces are only scheduled on their * respective interfaces. */ - batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, - hard_iface, hard_iface, 1, send_time); + scheduled = batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, + hard_iface, hard_iface, 1, send_time); + if (!scheduled) + reschedule = true; + goto out; } @@ -857,15 +869,28 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) if (!kref_get_unless_zero(&tmp_hard_iface->refcount)) continue; - batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, - *ogm_buff_len, hard_iface, - tmp_hard_iface, 1, send_time); - + scheduled = batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, + *ogm_buff_len, hard_iface, + tmp_hard_iface, 1, send_time); batadv_hardif_put(tmp_hard_iface); + + if (!scheduled && tmp_hard_iface == hard_iface) + reschedule = true; } rcu_read_unlock(); out: + if (reschedule) { + /* there was a failure scheduling the own forward packet. + * as result, the batadv_iv_send_outstanding_bat_ogm_packet() + * work item is no longer scheduled. it is therefore necessary + * to reschedule it manually + */ + queue_delayed_work(batadv_event_workqueue, + &hard_iface->bat_iv.reschedule_work, + msecs_to_jiffies(atomic_read(&bat_priv->orig_interval))); + } + batadv_hardif_put(primary_if); } @@ -880,6 +905,17 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } +static void batadv_iv_ogm_reschedule(struct work_struct *work) +{ + struct delayed_work *delayed_work = to_delayed_work(work); + struct batadv_hard_iface *hard_iface; + + hard_iface = container_of(delayed_work, + struct batadv_hard_iface, + bat_iv.reschedule_work); + batadv_iv_ogm_schedule(hard_iface); +} + /** * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over interface * @orig_node: originator which reproadcasted the OGMs directly @@ -2272,6 +2308,8 @@ batadv_iv_ogm_neigh_is_sob(struct batadv_neigh_node *neigh1, static void batadv_iv_iface_enabled(struct batadv_hard_iface *hard_iface) { + INIT_DELAYED_WORK(&hard_iface->bat_iv.reschedule_work, batadv_iv_ogm_reschedule); + /* begin scheduling originator messages on that interface */ batadv_iv_ogm_schedule(hard_iface); } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 41c1d19f786bb..83ca23a317b3e 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -83,6 +83,9 @@ struct batadv_hard_iface_bat_iv { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + /** @reschedule_work: recover OGM schedule after schedule error */ + struct delayed_work reschedule_work; + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ struct mutex ogm_buff_mutex; }; From 8a3707653ab658e082ccd992e92594e01b09a3fc Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 14 May 2026 19:22:02 +0200 Subject: [PATCH 1280/1518] batman-adv: mcast: fix use-after-free in orig_node RCU release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 20c2d6a20ca936f5aaa6dd40f73f262ac45c87cc upstream. batadv_mcast_purge_orig() removes entries from RCU-protected hlists but does not wait for an RCU grace period before returning. Concurrent RCU readers may still accesses references to those entries at the point of removal. RCU-protected readers trying to operate on entries like orig->mcast_want_all_ipv6_node will then access already freed memory. Fix this by moving batadv_mcast_purge_orig() to batadv_orig_node_release(), just before the call_rcu() invocation. This ensures RCU readers that were active at purge time have drained before the orig_node memory is reclaimed. Cc: stable@kernel.org Fixes: ab49886e3da7 ("batman-adv: Add IPv4 link-local/IPv6-ll-all-nodes multicast support") Acked-by: Linus Lüssing Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/originator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index a662408ad8673..ae195053e0605 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -835,8 +835,6 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) orig_node = container_of(rcu, struct batadv_orig_node, rcu); - batadv_mcast_purge_orig(orig_node); - batadv_frag_purge_orig(orig_node, NULL); kfree(orig_node->tt_buff); @@ -887,6 +885,8 @@ void batadv_orig_node_release(struct kref *ref) } spin_unlock_bh(&orig_node->vlan_list_lock); + batadv_mcast_purge_orig(orig_node); + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } From ae7aeb0ce3c0ebbe357ed525779acac197a18086 Mon Sep 17 00:00:00 2001 From: Ruijie Li Date: Thu, 14 May 2026 16:13:25 +0800 Subject: [PATCH 1281/1518] batman-adv: clear current gateway during teardown commit a340a51ed801eab7bb454150c226323b865263cc upstream. batadv_gw_node_free() removes the gateway list entries during mesh teardown, but it does not clear the currently selected gateway. This leaves stale gateway state behind across cleanup and can break a later mesh recreation. Clear bat_priv->gw.curr_gw before walking the gateway list so the selected gateway reference is dropped as part of teardown. Fixes: 2265c1410864 ("batman-adv: gateway election code refactoring") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Ruijie Li Signed-off-by: Zhanpeng Li Signed-off-by: Ren Wei Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/gateway_client.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 7a11b245e9f40..ff341c270d915 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -478,10 +478,14 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, */ void batadv_gw_node_free(struct batadv_priv *bat_priv) { + struct batadv_gw_node *curr_gw; struct batadv_gw_node *gw_node; struct hlist_node *node_tmp; spin_lock_bh(&bat_priv->gw.list_lock); + curr_gw = rcu_replace_pointer(bat_priv->gw.curr_gw, NULL, true); + batadv_gw_node_put(curr_gw); + hlist_for_each_entry_safe(gw_node, node_tmp, &bat_priv->gw.gateway_list, list) { hlist_del_init_rcu(&gw_node->list); From 9cceea8eeba710def2a5707ee00f00c74a9a1cac Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 13 May 2026 09:01:34 +0200 Subject: [PATCH 1282/1518] batman-adv: dat: handle forward allocation error commit 2d8826a2d3657cea66fb0370f9e521575a673871 upstream. batadv_dat_forward_data() calls pskb_copy_for_clone() to duplicate an skb for each DHT candidate, but does not check the return value before passing it to batadv_send_skb_prepare_unicast_4addr(). That function dereferences the skb unconditionally, so a failed allocation triggers a NULL pointer dereference. Skip forwarding to the current DHT candidate on allocation failure. Cc: stable@kernel.org Fixes: 785ea1144182 ("batman-adv: Distributed ARP Table - create DHT helper functions") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Reviewed-by: Yuan Tan Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/distributed-arp-table.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 8b8132eb0a79f..031c295fff1b1 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -697,6 +697,9 @@ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv, goto free_orig; tmp_skb = pskb_copy_for_clone(skb, GFP_ATOMIC); + if (!tmp_skb) + goto free_neigh; + if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, tmp_skb, cand[i].orig_node, packet_subtype)) { From 3eb8bcb823391bd58997831b3c9c152a4ba8e255 Mon Sep 17 00:00:00 2001 From: Ruide Cao Date: Wed, 13 May 2026 11:58:15 +0800 Subject: [PATCH 1283/1518] batman-adv: fix fragment reassembly length accounting commit 9cd3f16c320bfdadd4509358122368deb56a5741 upstream. batman-adv keeps a running payload length for queued fragments and uses it to validate a fragment chain before reassembly. That accounting currently allows the accumulated fragment length to be truncated during updates. As a result, malformed fragment chains can bypass the intended validation and drive reassembly with inconsistent length state, leading to a local denial of service. Fix the accounting by storing the accumulated length in a length-typed field and rejecting update overflows before the existing validation logic runs. The fix was verified against the original reproducer and against valid fragment reassembly paths. Fixes: 610bfc6bc99b ("batman-adv: Receive fragmented packets and merge") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Ruide Cao Tested-by: Ren Wei Signed-off-by: Ren Wei Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/fragmentation.c | 23 +++++++++++++++++------ net/batman-adv/types.h | 2 +- 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index cc14bc41381e0..d462d5501d550 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -80,9 +81,9 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig_node, * * Return: the maximum size of payload that can be fragmented. */ -static int batadv_frag_size_limit(void) +static size_t batadv_frag_size_limit(void) { - int limit = BATADV_FRAG_MAX_FRAG_SIZE; + size_t limit = BATADV_FRAG_MAX_FRAG_SIZE; limit -= sizeof(struct batadv_frag_packet); limit *= BATADV_FRAG_MAX_FRAGMENTS; @@ -143,7 +144,9 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, struct batadv_frag_packet *frag_packet; u8 bucket; u16 seqno, hdr_size = sizeof(struct batadv_frag_packet); + bool overflow = false; bool ret = false; + size_t data_len; /* Linearize packet to avoid linearizing 16 packets in a row when doing * the later merge. Non-linear merge should be added to remove this @@ -153,6 +156,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, goto err; frag_packet = (struct batadv_frag_packet *)skb->data; + data_len = skb->len - hdr_size; seqno = ntohs(frag_packet->seqno); bucket = seqno % BATADV_FRAG_BUFFER_COUNT; @@ -171,7 +175,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, spin_lock_bh(&chain->lock); if (batadv_frag_init_chain(chain, seqno)) { hlist_add_head(&frag_entry_new->list, &chain->fragment_list); - chain->size = skb->len - hdr_size; + chain->size = data_len; chain->timestamp = jiffies; chain->total_size = ntohs(frag_packet->total_size); ret = true; @@ -188,7 +192,11 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, if (frag_entry_curr->no < frag_entry_new->no) { hlist_add_before(&frag_entry_new->list, &frag_entry_curr->list); - chain->size += skb->len - hdr_size; + + if (check_add_overflow(chain->size, data_len, + &chain->size)) + overflow = true; + chain->timestamp = jiffies; ret = true; goto out; @@ -201,13 +209,16 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, /* Reached the end of the list, so insert after 'frag_entry_last'. */ if (likely(frag_entry_last)) { hlist_add_behind(&frag_entry_new->list, &frag_entry_last->list); - chain->size += skb->len - hdr_size; + + if (check_add_overflow(chain->size, data_len, &chain->size)) + overflow = true; + chain->timestamp = jiffies; ret = true; } out: - if (chain->size > batadv_frag_size_limit() || + if (overflow || chain->size > batadv_frag_size_limit() || chain->total_size != ntohs(frag_packet->total_size) || chain->total_size > batadv_frag_size_limit()) { /* Clear chain if total size of either the list or the packet diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 83ca23a317b3e..aca82693ccff0 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -304,7 +304,7 @@ struct batadv_frag_table_entry { u16 seqno; /** @size: accumulated size of packets in list */ - u16 size; + size_t size; /** @total_size: expected size of the assembled packet */ u16 total_size; From 90ae3eae06b7b8ab9f6250b9497c860915b4c17b Mon Sep 17 00:00:00 2001 From: Luxiao Xu Date: Mon, 11 May 2026 18:52:09 +0200 Subject: [PATCH 1284/1518] batman-adv: fix tp_meter counter underflow during shutdown commit 94f3b133168d1c49895e7cc6afbcf1cc0b354602 upstream. batadv_tp_sender_shutdown() unconditionally decrements the "sending" atomic counter. If multiple paths (e.g. timeout, user cancel, and normal finish) call this function, the counter can underflow to -1. Since the sender logic treats any non-zero value as "still sending", a negative value causes the sender kthread to loop indefinitely. This leads to a use-after-free when the interface is removed while the zombie thread is still active. Fix this by using atomic_xchg() to ensure the counter only transitions from 1 to 0 once. Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Luxiao Xu Signed-off-by: Ren Wei [sven: added missing change in batadv_tp_send] Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 76ece40143840..e279d42fe0827 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -451,7 +451,7 @@ static void batadv_tp_sender_end(struct batadv_priv *bat_priv, static void batadv_tp_sender_shutdown(struct batadv_tp_vars *tp_vars, enum batadv_tp_meter_reason reason) { - if (!atomic_dec_and_test(&tp_vars->sending)) + if (atomic_xchg(&tp_vars->sending, 0) != 1) return; tp_vars->reason = reason; @@ -885,7 +885,7 @@ static int batadv_tp_send(void *arg) "Meter: %s() cannot send packets (%d)\n", __func__, err); /* ensure nobody else tries to stop the thread now */ - if (atomic_dec_and_test(&tp_vars->sending)) + if (atomic_xchg(&tp_vars->sending, 0) == 1) tp_vars->reason = err; break; } From 5895ad21c7059a652da83fb817510f7a1e962abf Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 13 May 2026 09:01:36 +0200 Subject: [PATCH 1285/1518] batman-adv: frag: disallow unicast fragment in fragment commit bc62216dc8e221e3781afa14430f45208bfa9af9 upstream. batadv_frag_skb_buffer() is called by batadv_batman_skb_recv() when a BATADV_UNICAST_FRAG packet is received. Once all fragments are collected and the packet is reassembled, batadv_recv_frag_packet() calls batadv_batman_skb_recv() again to process the defragmented payload. A malicious sender can craft a BATADV_UNICAST_FRAG packet whose reassembled payload is itself a BATADV_UNICAST_FRAG packet (matryoshka-style nesting). Each nesting level recurses through batadv_batman_skb_recv() without bound, growing the kernel stack until it is exhausted. Since refragmentation or fragments in fragments are not actually allowed, discard all packets which are still BATADV_UNICAST_FRAG packets after the defragmentation process. Cc: stable@kernel.org Fixes: 610bfc6bc99b ("batman-adv: Receive fragmented packets and merge") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Reviewed-by: Yuan Tan Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/fragmentation.c | 35 ++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index d462d5501d550..31395281692cb 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -304,6 +304,31 @@ batadv_frag_merge_packets(struct hlist_head *chain) return skb_out; } +/** + * batadv_skb_is_frag() - check if newly merged skb is gain a unicast packet + * @skb: newly merged skb + * + * Return: if newly skb is of type BATADV_UNICAST_FRAG + */ +static bool batadv_skb_is_frag(struct sk_buff *skb) +{ + struct batadv_ogm_packet *batadv_ogm_packet; + + /* packet should hold at least type and version */ + if (unlikely(!pskb_may_pull(skb, 2))) + return false; + + batadv_ogm_packet = (struct batadv_ogm_packet *)skb->data; + + if (batadv_ogm_packet->version != BATADV_COMPAT_VERSION) + return false; + + if (batadv_ogm_packet->packet_type != BATADV_UNICAST_FRAG) + return false; + + return true; +} + /** * batadv_frag_skb_buffer() - buffer fragment for later merge * @skb: skb to buffer @@ -337,6 +362,16 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb, if (!skb_out) goto out_err; + /* fragment in fragment is not allowed. otherwise it is possible + * to exhaust the stack when receiving a matryoshka-style + * "fragments in a fragment packet" + */ + if (batadv_skb_is_frag(skb_out)) { + kfree_skb(skb_out); + skb_out = NULL; + goto out_err; + } + out: ret = true; out_err: From c6de1a5a9c406e30b91f1515a6ce05cc84023baa Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 10 May 2026 11:43:20 +0200 Subject: [PATCH 1286/1518] batman-adv: bla: fix report_work leak on backbone_gw purge commit 0459430add32ea41f3e2ef9351610e6d33627a6b upstream. batadv_bla_purge_backbone_gw() removes stale backbone gateway entries, but fails to properly handle their associated report_work: - If report_work is running, the purge must wait for it to finish before freeing the backbone_gw, otherwise the worker may access freed memory (e.g. bat_priv). - If report_work is pending, the purge must cancel it and release the reference held for that pending work item. The previous implementation called hlist_for_each_entry_safe() inside a spin_lock_bh() section, but cancel_work_sync() may sleep and therefore cannot be called from within a spinlock-protected region. Restructure the loop to handle one entry per spinlock critical section: acquire the lock, find the next entry to purge, remove it from the hash list, then release the lock before calling cancel_work_sync() and dropping the hash_entry reference. Repeat until no more entries require purging. Cc: stable@kernel.org Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Reviewed-by: Simon Wunderlich Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 54 +++++++++++++++++--------- 1 file changed, 35 insertions(+), 19 deletions(-) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 2d7971424aa0e..33b1275fdf83b 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1225,6 +1225,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) struct hlist_head *head; struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ + bool purged; int i; hash = bat_priv->bla.backbone_hash; @@ -1235,30 +1236,45 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) head = &hash->table[i]; list_lock = &hash->list_locks[i]; - spin_lock_bh(list_lock); - hlist_for_each_entry_safe(backbone_gw, node_tmp, - head, hash_entry) { - if (now) - goto purge_now; - if (!batadv_has_timed_out(backbone_gw->lasttime, - BATADV_BLA_BACKBONE_TIMEOUT)) - continue; + do { + purged = false; - batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, - "%s(): backbone gw %pM timed out\n", - __func__, backbone_gw->orig); + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(backbone_gw, node_tmp, + head, hash_entry) { + if (now) + goto purge_now; + if (!batadv_has_timed_out(backbone_gw->lasttime, + BATADV_BLA_BACKBONE_TIMEOUT)) + continue; + + batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, + "%s(): backbone gw %pM timed out\n", + __func__, backbone_gw->orig); purge_now: - /* don't wait for the pending request anymore */ - if (atomic_read(&backbone_gw->request_sent)) - atomic_dec(&bat_priv->bla.num_requests); + purged = true; - batadv_bla_del_backbone_claims(backbone_gw); + /* don't wait for the pending request anymore */ + if (atomic_read(&backbone_gw->request_sent)) + atomic_dec(&bat_priv->bla.num_requests); - hlist_del_rcu(&backbone_gw->hash_entry); - batadv_backbone_gw_put(backbone_gw); - } - spin_unlock_bh(list_lock); + batadv_bla_del_backbone_claims(backbone_gw); + + hlist_del_rcu(&backbone_gw->hash_entry); + break; + } + spin_unlock_bh(list_lock); + + if (purged) { + /* reference for pending report_work */ + if (cancel_work_sync(&backbone_gw->report_work)) + batadv_backbone_gw_put(backbone_gw); + + /* reference for hash_entry */ + batadv_backbone_gw_put(backbone_gw); + } + } while (purged); } } From 45384612f29692fbf0c770200361a7acff90125c Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 12 May 2026 09:13:31 +0200 Subject: [PATCH 1287/1518] batman-adv: bla: avoid double decrement of bla.num_requests commit 83ab69bd12b80f6ea169c8bea6977701b53a043d upstream. The bla.num_requests is increased when no request_sent was in progress. And it is decremented in various places (announcement was received, backbone is purged, periodic work). But the check if the request_sent is actually set to a specific state and the atomic_dec/_inc are not safe because they are not atomic (TOCTOU) and multiple such code portions can run concurrently. At the same time, it is necessary to modify request_sent (state) and bla.num_requests atomically. Otherwise batadv_bla_send_request() might set request_sent to 1 and is interrupted. batadv_handle_announce() can then set request_sent back to 0 and decrement num_requests before batadv_bla_send_request() incremented it. The two operations must therefore be locked. And since state (request_sent) and wait_periods are only accessed inside this lock, they can be converted to simpler datatypes. And to avoid that the bla.num_requests is touched by a parallel running context with a valid backbone_gw reference after batadv_bla_purge_backbone_gw() ran, a third state "stopped" is required to correctly signal that a backbone_gw is in the state of being cleaned up. Cc: stable@kernel.org Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 51 ++++++++++++++++++-------- net/batman-adv/mesh-interface.c | 1 + net/batman-adv/types.h | 39 ++++++++++++++++---- 3 files changed, 67 insertions(+), 24 deletions(-) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 33b1275fdf83b..42ee7efc3d79d 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -515,8 +515,8 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; spin_lock_init(&entry->crc_lock); - atomic_set(&entry->request_sent, 0); - atomic_set(&entry->wait_periods, 0); + entry->state = BATADV_BLA_BACKBONE_GW_SYNCED; + entry->wait_periods = 0; ether_addr_copy(entry->orig, orig); INIT_WORK(&entry->report_work, batadv_bla_loopdetect_report); kref_init(&entry->refcount); @@ -545,9 +545,13 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, batadv_bla_send_announce(bat_priv, entry); /* this will be decreased in the worker thread */ - atomic_inc(&entry->request_sent); - atomic_set(&entry->wait_periods, BATADV_BLA_WAIT_PERIODS); - atomic_inc(&bat_priv->bla.num_requests); + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (entry->state == BATADV_BLA_BACKBONE_GW_SYNCED) { + entry->state = BATADV_BLA_BACKBONE_GW_UNSYNCED; + entry->wait_periods = BATADV_BLA_WAIT_PERIODS; + atomic_inc(&bat_priv->bla.num_requests); + } + spin_unlock_bh(&bat_priv->bla.num_requests_lock); } return entry; @@ -650,10 +654,12 @@ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) backbone_gw->vid, BATADV_CLAIM_TYPE_REQUEST); /* no local broadcasts should be sent or received, for now. */ - if (!atomic_read(&backbone_gw->request_sent)) { + spin_lock_bh(&backbone_gw->bat_priv->bla.num_requests_lock); + if (backbone_gw->state == BATADV_BLA_BACKBONE_GW_SYNCED) { + backbone_gw->state = BATADV_BLA_BACKBONE_GW_UNSYNCED; atomic_inc(&backbone_gw->bat_priv->bla.num_requests); - atomic_set(&backbone_gw->request_sent, 1); } + spin_unlock_bh(&backbone_gw->bat_priv->bla.num_requests_lock); } /** @@ -874,10 +880,12 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, /* if we have sent a request and the crc was OK, * we can allow traffic again. */ - if (atomic_read(&backbone_gw->request_sent)) { + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (backbone_gw->state == BATADV_BLA_BACKBONE_GW_UNSYNCED) { + backbone_gw->state = BATADV_BLA_BACKBONE_GW_SYNCED; atomic_dec(&backbone_gw->bat_priv->bla.num_requests); - atomic_set(&backbone_gw->request_sent, 0); } + spin_unlock_bh(&bat_priv->bla.num_requests_lock); } batadv_backbone_gw_put(backbone_gw); @@ -1256,9 +1264,13 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) purged = true; /* don't wait for the pending request anymore */ - if (atomic_read(&backbone_gw->request_sent)) + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (backbone_gw->state == BATADV_BLA_BACKBONE_GW_UNSYNCED) atomic_dec(&bat_priv->bla.num_requests); + backbone_gw->state = BATADV_BLA_BACKBONE_GW_STOPPED; + spin_unlock_bh(&bat_priv->bla.num_requests_lock); + batadv_bla_del_backbone_claims(backbone_gw); hlist_del_rcu(&backbone_gw->hash_entry); @@ -1509,7 +1521,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) batadv_bla_send_loopdetect(bat_priv, backbone_gw); - /* request_sent is only set after creation to avoid + /* state is only set to unsynced after creation to avoid * problems when we are not yet known as backbone gw * in the backbone. * @@ -1518,14 +1530,21 @@ static void batadv_bla_periodic_work(struct work_struct *work) * some grace time. */ - if (atomic_read(&backbone_gw->request_sent) == 0) - continue; + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (backbone_gw->state != BATADV_BLA_BACKBONE_GW_UNSYNCED) + goto unlock_next; - if (!atomic_dec_and_test(&backbone_gw->wait_periods)) - continue; + if (backbone_gw->wait_periods > 0) + backbone_gw->wait_periods--; + + if (backbone_gw->wait_periods > 0) + goto unlock_next; + backbone_gw->state = BATADV_BLA_BACKBONE_GW_SYNCED; atomic_dec(&backbone_gw->bat_priv->bla.num_requests); - atomic_set(&backbone_gw->request_sent, 0); + +unlock_next: + spin_unlock_bh(&bat_priv->bla.num_requests_lock); } rcu_read_unlock(); } diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c index df7e95811ef56..dcdc82f6af8cf 100644 --- a/net/batman-adv/mesh-interface.c +++ b/net/batman-adv/mesh-interface.c @@ -787,6 +787,7 @@ static int batadv_meshif_init_late(struct net_device *dev) atomic_set(&bat_priv->tt.ogm_append_cnt, 0); #ifdef CONFIG_BATMAN_ADV_BLA atomic_set(&bat_priv->bla.num_requests, 0); + spin_lock_init(&bat_priv->bla.num_requests_lock); #endif atomic_set(&bat_priv->tp_num, 0); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index aca82693ccff0..d9518d73c257c 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1026,6 +1026,12 @@ struct batadv_priv_bla { /** @num_requests: number of bla requests in flight */ atomic_t num_requests; + /** + * @num_requests_lock: locks update num_requests + + * batadv_backbone_gw::state + batadv_backbone_gw::wait_periods update + */ + spinlock_t num_requests_lock; + /** * @claim_hash: hash table containing mesh nodes this host has claimed */ @@ -1669,6 +1675,27 @@ struct batadv_priv { #ifdef CONFIG_BATMAN_ADV_BLA +enum batadv_bla_backbone_gw_state { + /** + * @BATADV_BLA_BACKBONE_GW_STOPPED: backbone gw is being removed + * and it must not longer work on requests + */ + BATADV_BLA_BACKBONE_GW_STOPPED, + + /** + * @BATADV_BLA_BACKBONE_GW_UNSYNCED: backbone was detected out + * of sync and a request was send. No traffic is forwarded until the + * situation is resolved + */ + BATADV_BLA_BACKBONE_GW_UNSYNCED, + + /** + * @BATADV_BLA_BACKBONE_GW_SYNCED: backbone is consider to be in + * sync. traffic can be forwarded + */ + BATADV_BLA_BACKBONE_GW_SYNCED, +}; + /** * struct batadv_bla_backbone_gw - batman-adv gateway bridged into the LAN */ @@ -1694,16 +1721,12 @@ struct batadv_bla_backbone_gw { /** * @wait_periods: grace time for bridge forward delays and bla group * forming at bootup phase - no bcast traffic is formwared until it has - * elapsed + * elapsed. Must only be access with num_requests_lock. */ - atomic_t wait_periods; + u8 wait_periods; - /** - * @request_sent: if this bool is set to true we are out of sync with - * this backbone gateway - no bcast traffic is formwared until the - * situation was resolved - */ - atomic_t request_sent; + /** @state: sync state. Must only be access with num_requests_lock. */ + enum batadv_bla_backbone_gw_state state; /** @crc: crc16 checksum over all claims */ u16 crc; From 6921a7683ae9ad0208d829e71f725a9e25ccff49 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 19 May 2026 09:23:49 +0200 Subject: [PATCH 1288/1518] batman-adv: bla: avoid NULL-ptr deref for claim via dropped interface commit f80d3d98d2ff78d9e2fe5d68b1f45948c4f7bd24 upstream. Without rtnl_lock held, a hardif might be retrieved as primary interface of a meshif, but then (while operating on this interface) getting decoupled from the mesh interface. In this case, the meshif still exists but the pointer from the primary hardif to the meshif is set to NULL. The mesh_iface must be checked first to be non-NULL before continuing to send an ARP request using meshif. Cc: stable@kernel.org Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Reported-by: Ido Schimmel Reported-by: syzbot+9fdcc9f05a98a540b816@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=9fdcc9f05a98a540b816 Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 42ee7efc3d79d..3072f94275ac6 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -357,12 +357,14 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, sizeof(local_claim_dest)); local_claim_dest.type = claimtype; - mesh_iface = primary_if->mesh_iface; + mesh_iface = READ_ONCE(primary_if->mesh_iface); + if (!mesh_iface) + goto out; skb = arp_create(ARPOP_REPLY, ETH_P_ARP, /* IP DST: 0.0.0.0 */ zeroip, - primary_if->mesh_iface, + mesh_iface, /* IP SRC: 0.0.0.0 */ zeroip, /* Ethernet DST: Broadcast */ From dc2ae5fbd2dadc26735092f140b246841d969a11 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 13 May 2026 09:01:35 +0200 Subject: [PATCH 1289/1518] batman-adv: tp_meter: avoid use of uninit sender vars commit 6c65cf23d4c6170fcf5714c32aa64689718cb142 upstream. batadv_tp_recv_ack() and batadv_tp_stop() are only valid for tp_vars in the BATADV_TP_SENDER role. When called with a BATADV_TP_RECEIVER role, it proceeds to read sender-only members that were never initialized, leading to undefined behavior. This can be triggered when a node that is currently acting as a receiver in an ongoing tp_meter session receives a malicious ACK packet. Guard against this by checking tp_vars->role immediately after the lookup and bailing out if it is not BATADV_TP_SENDER, before any of those members are accessed. Cc: stable@kernel.org Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Reviewed-by: Yuan Tan Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index e279d42fe0827..341d6d5083e17 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -663,6 +663,9 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv, if (unlikely(!tp_vars)) return; + if (unlikely(tp_vars->role != BATADV_TP_SENDER)) + goto out; + if (unlikely(atomic_read(&tp_vars->sending) == 0)) goto out; @@ -1100,12 +1103,16 @@ void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst, if (!tp_vars) { batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: trying to interrupt an already over connection\n"); - goto out; + goto out_put_orig_node; } + if (unlikely(tp_vars->role != BATADV_TP_SENDER)) + goto out_put_tp_vars; + batadv_tp_sender_shutdown(tp_vars, return_value); +out_put_tp_vars: batadv_tp_vars_put(tp_vars); -out: +out_put_orig_node: batadv_orig_node_put(orig_node); } From 770bf0a35f0620b526fd4193889d1e77084e4c43 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 13 May 2026 10:43:54 +0200 Subject: [PATCH 1290/1518] batman-adv: tp_meter: directly shut down timer on cleanup commit d5487249a81ea658717614009c8f46acc5b7101a upstream. batadv_tp_sender_cleanup() was calling timer_delete_sync() followed by timer_delete() to guard against the timer handler re-arming itself between the two calls. This double-deletion hack relied on the sending status being set to 0 to suppress re-arming. Replace both calls with a single timer_shutdown_sync(). This function both waits for any running timer callback to complete (like timer_delete_sync()) and permanently disarms the timer so it cannot be re-armed afterwards, making re-arming prevention unconditional and self-documenting. The re-arming property is also required because otherwise: 1. context 0 (batadv_tp_recv_ack()) checks in batadv_tp_reset_sender_timer() if sending is still 1 -> it is 2. context 1 changes in batadv_tp_sender_shutdown() sending to 0 and in this process forces the kthread to stop timer in batadv_tp_sender_cleanup() 3. context 0 continues in batadv_tp_reset_sender_timer() and rearms the timer -> but the reference for it is already gone Cc: stable@kernel.org Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 341d6d5083e17..e0d7f98e5b9d9 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -400,13 +400,7 @@ static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) batadv_tp_list_detach(tp_vars); /* kill the timer and remove its reference */ - timer_delete_sync(&tp_vars->timer); - /* the worker might have rearmed itself therefore we kill it again. Note - * that if the worker should run again before invoking the following - * timer_delete(), it would not re-arm itself once again because the status - * is OFF now - */ - timer_delete(&tp_vars->timer); + timer_shutdown_sync(&tp_vars->timer); batadv_tp_vars_put(tp_vars); } From b285bc0a97f43823a4967fb6d286de4c7f53d541 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 10 May 2026 11:31:03 +0200 Subject: [PATCH 1291/1518] batman-adv: tp_meter: fix tp_vars reference leak in receiver shutdown commit 77098e4bea37af51d3962efa88a5af2ea5e1ac57 upstream. The receiver shutdown timer handler, batadv_tp_receiver_shutdown(), is responsible for releasing the tp_vars reference it holds. However, the existing logic for coordinating this release with batadv_tp_stop_all() was flawed. timer_shutdown_sync() guarantees the timer will not fire again after it returns, but it returns non-zero only when the timer was pending at the time of the call. If the timer had already expired (and batadv_tp_stop_all() would unsucessfully try to rearm itself), batadv_tp_stop_all() skips its batadv_tp_vars_put(), and batadv_tp_receiver_shutdown() fails to put its own reference as well. Fix this by introducing a new atomic variable receiving that is set to 1 when the receiver is initialized and cleared atomically with atomic_xchg() by whichever side claims it first. Only the side that observes the transition from 1 to 0 is responsible for releasing the tp_vars timer reference, eliminating the uncertainty. Cc: stable@kernel.org Fixes: 3d3cf6a7314a ("batman-adv: stop tp_meter sessions during mesh teardown") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 13 +++++++++++-- net/batman-adv/types.h | 3 +++ 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index e0d7f98e5b9d9..6a6fcf2d2f008 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -8,6 +8,7 @@ #include "main.h" #include +#include #include #include #include @@ -1157,6 +1158,9 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) spin_unlock_bh(&tp_vars->unacked_lock); /* drop reference of timer */ + if (WARN_ON(atomic_xchg(&tp_vars->receiving, 0) != 1)) + return; + batadv_tp_vars_put(tp_vars); } @@ -1375,6 +1379,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, ether_addr_copy(tp_vars->other_end, icmp->orig); tp_vars->role = BATADV_TP_RECEIVER; + atomic_set(&tp_vars->receiving, 1); memcpy(tp_vars->session, icmp->session, sizeof(tp_vars->session)); tp_vars->last_recv = BATADV_TP_FIRST_SEQ; tp_vars->bat_priv = bat_priv; @@ -1547,8 +1552,12 @@ void batadv_tp_stop_all(struct batadv_priv *bat_priv) break; case BATADV_TP_RECEIVER: batadv_tp_list_detach(tp_var); - if (timer_shutdown_sync(&tp_var->timer)) - batadv_tp_vars_put(tp_var); + timer_shutdown_sync(&tp_var->timer); + + if (atomic_xchg(&tp_var->receiving, 0) != 1) + break; + + batadv_tp_vars_put(tp_var); break; } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index d9518d73c257c..c886d86cba63e 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1332,6 +1332,9 @@ struct batadv_tp_vars { /** @sending: sending binary semaphore: 1 if sending, 0 is not */ atomic_t sending; + /** @receiving: receiving binary semaphore: 1 if receiving, 0 is not */ + atomic_t receiving; + /** @reason: reason for a stopped session */ enum batadv_tp_meter_reason reason; From 72d670d7a4928003dd2e8c1dfedd424a8d4f9804 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 13 May 2026 23:38:54 +0200 Subject: [PATCH 1292/1518] batman-adv: tp_meter: fix race condition in send error reporting commit 71dce47f0758537fff78fddb5fb0d4632d29b29f upstream. batadv_tp_sender_shutdown() previously used two separate variables to track session state: sending (an atomic flag indicating whether the session was active) and reason (a plain enum storing the stop reason). This introduced a race window between the two writes: after sending was cleared to 0, batadv_tp_send() could observe the stopped state and call batadv_tp_sender_end() before reason was written, causing the wrong stop reason to be reported to the caller. Fix this by consolidating both variables into a single atomic send_result, which holds 0 while the session is running and the stop reason once it ends. Cc: stable@kernel.org Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 40 ++++++++++++++++++++++++--------------- net/batman-adv/types.h | 10 +++++----- 2 files changed, 30 insertions(+), 20 deletions(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 6a6fcf2d2f008..e5342760b49f3 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -413,11 +413,14 @@ static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) static void batadv_tp_sender_end(struct batadv_priv *bat_priv, struct batadv_tp_vars *tp_vars) { + enum batadv_tp_meter_reason reason; u32 session_cookie; + reason = atomic_read(&tp_vars->send_result); + batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Test towards %pM finished..shutting down (reason=%d)\n", - tp_vars->other_end, tp_vars->reason); + tp_vars->other_end, reason); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Last timing stats: SRTT=%ums RTTVAR=%ums RTO=%ums\n", @@ -430,7 +433,7 @@ static void batadv_tp_sender_end(struct batadv_priv *bat_priv, session_cookie = batadv_tp_session_cookie(tp_vars->session, tp_vars->icmp_uid); - batadv_tp_batctl_notify(tp_vars->reason, + batadv_tp_batctl_notify(reason, tp_vars->other_end, bat_priv, tp_vars->start_time, @@ -446,10 +449,18 @@ static void batadv_tp_sender_end(struct batadv_priv *bat_priv, static void batadv_tp_sender_shutdown(struct batadv_tp_vars *tp_vars, enum batadv_tp_meter_reason reason) { - if (atomic_xchg(&tp_vars->sending, 0) != 1) - return; + atomic_cmpxchg(&tp_vars->send_result, 0, reason); +} - tp_vars->reason = reason; +/** + * batadv_tp_sender_stopped() - check if tp session was stopped with reason + * @tp_vars: the private data of the current TP meter session + * + * Return: whether stop reason was found + */ +static bool batadv_tp_sender_stopped(struct batadv_tp_vars *tp_vars) +{ + return atomic_read(&tp_vars->send_result) != 0; } /** @@ -479,7 +490,7 @@ static void batadv_tp_reset_sender_timer(struct batadv_tp_vars *tp_vars) /* most of the time this function is invoked while normal packet * reception... */ - if (unlikely(atomic_read(&tp_vars->sending) == 0)) + if (unlikely(batadv_tp_sender_stopped(tp_vars))) /* timer ref will be dropped in batadv_tp_sender_cleanup */ return; @@ -499,7 +510,7 @@ static void batadv_tp_sender_timeout(struct timer_list *t) struct batadv_tp_vars *tp_vars = timer_container_of(tp_vars, t, timer); struct batadv_priv *bat_priv = tp_vars->bat_priv; - if (atomic_read(&tp_vars->sending) == 0) + if (batadv_tp_sender_stopped(tp_vars)) return; /* if the user waited long enough...shutdown the test */ @@ -661,7 +672,7 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv, if (unlikely(tp_vars->role != BATADV_TP_SENDER)) goto out; - if (unlikely(atomic_read(&tp_vars->sending) == 0)) + if (unlikely(batadv_tp_sender_stopped(tp_vars))) goto out; /* old ACK? silently drop it.. */ @@ -827,21 +838,21 @@ static int batadv_tp_send(void *arg) if (unlikely(tp_vars->role != BATADV_TP_SENDER)) { err = BATADV_TP_REASON_DST_UNREACHABLE; - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); goto out; } orig_node = batadv_orig_hash_find(bat_priv, tp_vars->other_end); if (unlikely(!orig_node)) { err = BATADV_TP_REASON_DST_UNREACHABLE; - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); goto out; } primary_if = batadv_primary_if_get_selected(bat_priv); if (unlikely(!primary_if)) { err = BATADV_TP_REASON_DST_UNREACHABLE; - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); goto out; } @@ -860,7 +871,7 @@ static int batadv_tp_send(void *arg) queue_delayed_work(batadv_event_workqueue, &tp_vars->finish_work, msecs_to_jiffies(tp_vars->test_length)); - while (atomic_read(&tp_vars->sending) != 0) { + while (!batadv_tp_sender_stopped(tp_vars)) { if (unlikely(!batadv_tp_avail(tp_vars, payload_len))) { batadv_tp_wait_available(tp_vars, payload_len); continue; @@ -883,8 +894,7 @@ static int batadv_tp_send(void *arg) "Meter: %s() cannot send packets (%d)\n", __func__, err); /* ensure nobody else tries to stop the thread now */ - if (atomic_xchg(&tp_vars->sending, 0) == 1) - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); break; } @@ -1006,7 +1016,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, ether_addr_copy(tp_vars->other_end, dst); kref_init(&tp_vars->refcount); tp_vars->role = BATADV_TP_SENDER; - atomic_set(&tp_vars->sending, 1); + atomic_set(&tp_vars->send_result, 0); memcpy(tp_vars->session, session_id, sizeof(session_id)); tp_vars->icmp_uid = icmp_uid; diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index c886d86cba63e..6b4c48bff561a 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1329,15 +1329,15 @@ struct batadv_tp_vars { /** @role: receiver/sender modi */ enum batadv_tp_meter_role role; - /** @sending: sending binary semaphore: 1 if sending, 0 is not */ - atomic_t sending; + /** + * @send_result: 0 when sending is ongoing and otherwise + * enum batadv_tp_meter_reason + */ + atomic_t send_result; /** @receiving: receiving binary semaphore: 1 if receiving, 0 is not */ atomic_t receiving; - /** @reason: reason for a stopped session */ - enum batadv_tp_meter_reason reason; - /** @finish_work: work item for the finishing procedure */ struct delayed_work finish_work; From 2d2d365d0b9d0987e37c6172f8c4b9f7a2ba569f Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 16 May 2026 12:33:41 +0200 Subject: [PATCH 1293/1518] batman-adv: tp_meter: avoid role confusion in tp_list commit ff24f2ecfd94c07a2b89bac497433e3b23271cac upstream. Session lookups in tp_list matched only on destination address (and optionally session ID), leaving role validation to the caller. If two sessions with the same other_end coexisted (one as sender, one as receiver) a lookup could silently return the wrong one, causing the caller's role to bail out early, potentially skipping necessary cleanup. Move the role check into the lookup functions themselves so the correct entry is always returned, or none at all. Since batadv_tp_start() legitimately needs to detect any active session to a destination regardless of role, introduce a dedicated helper for that case rather than bending the existing lookup semantics. Cc: stable@kernel.org Fixes: 33a3bb4a3345 ("batman-adv: throughput meter implementation") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/tp_meter.c | 59 ++++++++++++++++++++++++--------------- 1 file changed, 36 insertions(+), 23 deletions(-) diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index e5342760b49f3..b1629e0ac8268 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -255,6 +255,7 @@ static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason, * batadv_tp_list_find() - find a tp_vars object in the global list * @bat_priv: the bat priv with all the mesh interface information * @dst: the other endpoint MAC address to look for + * @role: role of the session * * Look for a tp_vars object matching dst as end_point and return it after * having increment the refcounter. Return NULL is not found @@ -262,7 +263,8 @@ static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason, * Return: matching tp_vars or NULL when no tp_vars with @dst was found */ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, - const u8 *dst) + const u8 *dst, + enum batadv_tp_meter_role role) { struct batadv_tp_vars *pos, *tp_vars = NULL; @@ -271,6 +273,9 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, if (!batadv_compare_eth(pos->other_end, dst)) continue; + if (pos->role != role) + continue; + /* most of the time this function is invoked during the normal * process..it makes sens to pay more when the session is * finished and to speed the process up during the measurement @@ -286,12 +291,33 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, return tp_vars; } +/** + * batadv_tp_list_active() - check if session from/to destination is ongoing + * @bat_priv: the bat priv with all the mesh interface information + * @dst: the other endpoint MAC address to look for + * + * Return: if matching session with @dst was found + */ +static bool batadv_tp_list_active(struct batadv_priv *bat_priv, const u8 *dst) + __must_hold(&bat_priv->tp_list_lock) +{ + struct batadv_tp_vars *tp_vars; + + hlist_for_each_entry_rcu(tp_vars, &bat_priv->tp_list, list) { + if (batadv_compare_eth(tp_vars->other_end, dst)) + return true; + } + + return false; +} + /** * batadv_tp_list_find_session() - find tp_vars session object in the global * list * @bat_priv: the bat priv with all the mesh interface information * @dst: the other endpoint MAC address to look for * @session: session identifier + * @role: role of the session * * Look for a tp_vars object matching dst as end_point, session as tp meter * session and return it after having increment the refcounter. Return NULL @@ -301,7 +327,7 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, */ static struct batadv_tp_vars * batadv_tp_list_find_session(struct batadv_priv *bat_priv, const u8 *dst, - const u8 *session) + const u8 *session, enum batadv_tp_meter_role role) { struct batadv_tp_vars *pos, *tp_vars = NULL; @@ -313,6 +339,9 @@ batadv_tp_list_find_session(struct batadv_priv *bat_priv, const u8 *dst, if (memcmp(pos->session, session, sizeof(pos->session)) != 0) continue; + if (pos->role != role) + continue; + /* most of the time this function is invoked during the normal * process..it makes sense to pay more when the session is * finished and to speed the process up during the measurement @@ -665,13 +694,10 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv, /* find the tp_vars */ tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, - icmp->session); + icmp->session, BATADV_TP_SENDER); if (unlikely(!tp_vars)) return; - if (unlikely(tp_vars->role != BATADV_TP_SENDER)) - goto out; - if (unlikely(batadv_tp_sender_stopped(tp_vars))) goto out; @@ -980,10 +1006,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, return; } - tp_vars = batadv_tp_list_find(bat_priv, dst); - if (tp_vars) { + if (batadv_tp_list_active(bat_priv, dst)) { spin_unlock_bh(&bat_priv->tp_list_lock); - batadv_tp_vars_put(tp_vars); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: test to or from the same node already ongoing, aborting\n"); batadv_tp_batctl_error_notify(BATADV_TP_REASON_ALREADY_ONGOING, @@ -1104,18 +1128,14 @@ void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst, if (!orig_node) return; - tp_vars = batadv_tp_list_find(bat_priv, orig_node->orig); + tp_vars = batadv_tp_list_find(bat_priv, orig_node->orig, BATADV_TP_SENDER); if (!tp_vars) { batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: trying to interrupt an already over connection\n"); goto out_put_orig_node; } - if (unlikely(tp_vars->role != BATADV_TP_SENDER)) - goto out_put_tp_vars; - batadv_tp_sender_shutdown(tp_vars, return_value); -out_put_tp_vars: batadv_tp_vars_put(tp_vars); out_put_orig_node: batadv_orig_node_put(orig_node); @@ -1371,7 +1391,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, goto out_unlock; tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, - icmp->session); + icmp->session, BATADV_TP_RECEIVER); if (tp_vars) goto out_unlock; @@ -1442,7 +1462,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, } } else { tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, - icmp->session); + icmp->session, BATADV_TP_RECEIVER); if (!tp_vars) { batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Unexpected packet from %pM!\n", @@ -1451,13 +1471,6 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, } } - if (unlikely(tp_vars->role != BATADV_TP_RECEIVER)) { - batadv_dbg(BATADV_DBG_TP_METER, bat_priv, - "Meter: dropping packet: not expected (role=%u)\n", - tp_vars->role); - goto out; - } - tp_vars->last_recv_time = jiffies; /* if the packet is a duplicate, it may be the case that an ACK has been From 4cc85aec8d3c9ab4dc716dc9f1ed36fca16b227f Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 2 May 2026 19:47:11 +0200 Subject: [PATCH 1294/1518] batman-adv: tt: fix TOCTOU race for reported vlans commit 94d27005016be15ffc638b2ecbc4d58805ad7b48 upstream. The local TT based TVLV is generated by first checking the number of VLANs which have at least one TT entry. A new buffer with the correct size for the VLANs is then allocated. Only then, the list of VLANs s used to fill the VLAN entries in the buffer. During this time, the meshif_vlan_list_lock is held. But the actual number of TT entries of each VLAN can still increase during this time - just not the number of VLANs in the list. But the prefilter used in the buffer size calculation might still cause an increase of the number of VLANs which need to be stored. Simply because a VLAN might now suddenly have at least one entry when it had none in the pre-alloc check - and then needs to occupy space which was not allocated. It is better to overestimate the buffer size at the beginning and then fill the buffer only with the VLANs which are not empty. Cc: stable@kernel.org Fixes: 16116dac2339 ("batman-adv: prevent TT request storms by not sending inconsistent TT TLVLs") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/translation-table.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 05cddcf994f65..bf5f35a3c9ba6 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -887,11 +887,8 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->meshif_vlan_list_lock); hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); - if (vlan_entries < 1) - continue; - - num_vlan++; total_entries += vlan_entries; + num_vlan++; } change_offset = struct_size(*tt_data, vlan_data, num_vlan); @@ -914,6 +911,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (*tt_data)->vlan_data; + num_vlan = 0; hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); if (vlan_entries < 1) @@ -924,8 +922,15 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan->reserved = 0; tt_vlan++; + num_vlan++; } + /* recalculate in case number of VLANs reduced */ + change_offset = struct_size(*tt_data, vlan_data, num_vlan); + tvlv_len = *tt_len + change_offset; + + (*tt_data)->num_vlan = htons(num_vlan); + tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; From 7cac9c9ef4b7fa3e4959098b9801723fa9f25908 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 2 May 2026 19:08:37 +0200 Subject: [PATCH 1295/1518] batman-adv: tt: reject oversized local TVLV buffers commit 1e9fab756f8395096d5bba7be0c373c4c8f5d165 upstream. The commit 3a359bf5c61d ("batman-adv: reject oversized global TT response buffers") added a check to ensure that a global return buffer size can be stored in an u16. The same buffer handling also exists for the local data buffer but was not touched. A similar check should be also be in place for the local TVLV buffer. It doesn't have the similar attack surface because it is only generated from locally discovered MAC addresses but the dynamic nature could still cause temporarily to large buffers. Cc: stable@kernel.org Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/translation-table.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index bf5f35a3c9ba6..f009cbf8a2768 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -877,12 +877,12 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, { struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_meshif_vlan *vlan; + size_t change_offset; u16 num_vlan = 0; u16 vlan_entries = 0; u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; - int change_offset; spin_lock_bh(&bat_priv->meshif_vlan_list_lock); hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) { @@ -897,8 +897,10 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, if (*tt_len < 0) *tt_len = batadv_tt_len(total_entries); - tvlv_len = *tt_len; - tvlv_len += change_offset; + if (check_add_overflow(*tt_len, change_offset, &tvlv_len)) { + tvlv_len = 0; + goto out; + } *tt_data = kmalloc(tvlv_len, GFP_ATOMIC); if (!*tt_data) { From b93ca6012712ecab2b551e120d7c95038d6a89e5 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 2 May 2026 20:47:34 +0200 Subject: [PATCH 1296/1518] batman-adv: tt: avoid empty VLAN responses commit fa1bd704940b5bcbc32c0b28db9167405c8ee5e0 upstream. The commit 16116dac2339 ("batman-adv: prevent TT request storms by not sending inconsistent TT TLVLs") added checks to the local (direct) TT response code. But the response can also be done indirectly by another node using the global TT state. To avoid such inconsistency states reported in the original fix, also avoid sending empty VLANs for replies from the global TT state. Cc: stable@kernel.org Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/translation-table.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index f009cbf8a2768..2259b241e0b56 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -797,24 +797,26 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, s32 *tt_len) { u16 num_vlan = 0; - u16 num_entries = 0; u16 tvlv_len = 0; unsigned int change_offset; struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_orig_node_vlan *vlan; + u16 total_entries = 0; u8 *tt_change_ptr; + int vlan_entries; spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + total_entries += vlan_entries; num_vlan++; - num_entries += atomic_read(&vlan->tt.num_entries); } change_offset = struct_size(*tt_data, vlan_data, num_vlan); /* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) - *tt_len = batadv_tt_len(num_entries); + *tt_len = batadv_tt_len(total_entries); if (change_offset > U16_MAX || *tt_len > U16_MAX - change_offset) { *tt_len = 0; @@ -835,14 +837,26 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (*tt_data)->vlan_data; + num_vlan = 0; hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); tt_vlan->reserved = 0; tt_vlan++; + num_vlan++; } + /* recalculate in case number of VLANs reduced */ + change_offset = struct_size(*tt_data, vlan_data, num_vlan); + tvlv_len = *tt_len + change_offset; + + (*tt_data)->num_vlan = htons(num_vlan); + tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; From 179eb62506a02d00370bd6478898cb632e10986c Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 2 May 2026 19:53:21 +0200 Subject: [PATCH 1297/1518] batman-adv: tt: fix negative last_changeset_len commit fc92cdfcb295cefa4344d71a527d61b638b7bfc4 upstream. batadv_piv_tt::last_changeset_len len was declared as s16, but the field is never intended to hold a negative value. When a value greater than 32767 is assigned, it wraps to a negative signed integer. In batadv_send_my_tt_response(), last_changeset_len is temporarily widened to s32. The incorrectly negative s16 value propagates into the s32, causing batadv_tt_prepare_tvlv_local_data() to allocate a full sized buffer but populates only a small portion of it with the collected changeset. All remaining bits are kept uninitialized. Using an u16 avoids this type confusion and ensures that no (negative) sign extension is performed in batadv_send_my_tt_response(). Cc: stable@kernel.org Fixes: a73105b8d4c7 ("batman-adv: improved client announcement mechanism") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 6b4c48bff561a..71845ca097543 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -996,7 +996,7 @@ struct batadv_priv_tt { * @last_changeset_len: length of last tt changeset this host has * generated */ - s16 last_changeset_len; + u16 last_changeset_len; /** * @last_changeset_lock: lock protecting last_changeset & From 730de8733dd90f70d7580a9b329b971f8e1474a2 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 2 May 2026 19:53:21 +0200 Subject: [PATCH 1298/1518] batman-adv: tt: fix negative tt_buff_len commit b64963a2ceeb7529310b6cf253a1e540784422f4 upstream. batadv_orig_node::tt_buff_len was declared as s16, but the field is never intended to hold a negative value. When a value greater than 32767 is assigned, it wraps to a negative signed integer. In batadv_send_other_tt_response(), tt_buff_len is temporarily widened to s32. The incorrectly negative s16 value propagates into the s32, causing batadv_tt_prepare_tvlv_global_data() to allocate a full sized buffer but populates only a small portion of it with the collected changeset. All remaining bits are kept uninitialized. Using an u16 avoids this type confusion and ensures that no (negative) sign extension is performed in batadv_send_other_tt_response(). Cc: stable@kernel.org Fixes: a73105b8d4c7 ("batman-adv: improved client announcement mechanism") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 71845ca097543..c9bd49d23547e 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -455,7 +455,7 @@ struct batadv_orig_node { * @tt_buff_len: length of the last tt changeset this node received * from the orig node */ - s16 tt_buff_len; + u16 tt_buff_len; /** @tt_buff_lock: lock that protects tt_buff and tt_buff_len */ spinlock_t tt_buff_lock; From e37dbe150515ff70113c7117a50c981978f5d3a1 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 2 May 2026 21:25:19 +0200 Subject: [PATCH 1299/1518] batman-adv: tt: prevent TVLV entry number overflow commit 99d9958fa10fb684b2a8e2c48a8d704122721420 upstream. The helpers to prepare the buffers for the local and global TT based replies are trying to sum up all TT entries which can be found for each VLAN. In theory, this sum can be too big for an u16 and therefore overflow. A too small buffer would then be allocated for the TVLV. The too small buffer will be handled gracefully by batadv_tt_tvlv_generate() and is not causing a buffer overflow - just a truncated reply. But this overflow shouldn't have happened in the first and the too small buffer should never have been allocated when an overflow was detected. Cc: stable@kernel.org Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific") Signed-off-by: Sven Eckelmann Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/translation-table.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 2259b241e0b56..9f6e67771ffa8 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -804,11 +804,18 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, u16 total_entries = 0; u8 *tt_change_ptr; int vlan_entries; + u16 sum_entries; spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); - total_entries += vlan_entries; + + if (check_add_overflow(vlan_entries, total_entries, &sum_entries)) { + *tt_len = 0; + goto out; + } + + total_entries = sum_entries; num_vlan++; } @@ -893,15 +900,22 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, struct batadv_meshif_vlan *vlan; size_t change_offset; u16 num_vlan = 0; - u16 vlan_entries = 0; u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; + int vlan_entries; + u16 sum_entries; spin_lock_bh(&bat_priv->meshif_vlan_list_lock); hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); - total_entries += vlan_entries; + + if (check_add_overflow(vlan_entries, total_entries, &sum_entries)) { + tvlv_len = 0; + goto out; + } + + total_entries = sum_entries; num_vlan++; } From e9b8f85daebffc34506c4705e34eb0f152ac88bf Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Fri, 15 May 2026 15:11:47 -0700 Subject: [PATCH 1300/1518] hwmon: (pmbus/adm1266) seed timestamp from the real-time clock commit b86095e3d7dcf2bf80c747349a35912a87a85098 upstream. adm1266_set_rtc() seeds the chip's SET_RTC register from ktime_get_seconds(), which returns CLOCK_MONOTONIC -- i.e. seconds since the host last booted, not seconds since the Unix epoch. The chip stamps that value into every blackbox record it captures. Userspace reading those timestamps back expects wall-clock seconds: that's what the SET_RTC frame layout documents (datasheet Rev. D, Table 84) and what every other consumer of "seconds since epoch" assumes. Seeding from CLOCK_MONOTONIC gives blackbox records a timestamp that is only meaningful within a single boot of the host and silently resets to small values on every reboot. Switch to ktime_get_real_seconds() so the seed matches what the register is documented to hold. Fixes: 15609d189302 ("hwmon: (pmbus/adm1266) read blackbox") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Link: https://lore.kernel.org/r/20260515-adm1266-fixes-v1-1-1c1ea1349cfe@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 5348feefd1e64..94691dec13599 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -432,7 +432,7 @@ static int adm1266_set_rtc(struct adm1266_data *data) char write_buf[6]; int i; - kt = ktime_get_seconds(); + kt = ktime_get_real_seconds(); memset(write_buf, 0, sizeof(write_buf)); From 75c862adf3d3caab4f49bb3530723c215376e37c Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Fri, 15 May 2026 15:11:49 -0700 Subject: [PATCH 1301/1518] hwmon: (pmbus/adm1266) reject implausible blackbox record_count commit 4afca954622d672ea65ed961bed01cf91caa034e upstream. adm1266_nvmem_read_blackbox() loops over a record_count that comes straight from byte 3 of the BLACKBOX_INFO response. The destination buffer is data->dev_mem, sized for the nvmem cell's declared 2048 bytes (ADM1266_BLACKBOX_MAX_RECORDS * ADM1266_BLACKBOX_SIZE = 32 * 64). A device that reports a record_count greater than 32 -- whether due to firmware bugs, bus corruption, or a non-responsive slave returning 0xff -- would walk read_buff past the end of the dev_mem allocation on the trailing iterations. Cap record_count at ADM1266_BLACKBOX_MAX_RECORDS (introduced here) before entering the loop and return -EIO on any larger value, so a malformed BLACKBOX_INFO response cannot drive the loop out of bounds. Fixes: 15609d189302 ("hwmon: (pmbus/adm1266) read blackbox") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Link: https://lore.kernel.org/r/20260515-adm1266-fixes-v1-3-1c1ea1349cfe@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 94691dec13599..43d9e74077954 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -46,6 +46,7 @@ #define ADM1266_BLACKBOX_OFFSET 0 #define ADM1266_BLACKBOX_SIZE 64 +#define ADM1266_BLACKBOX_MAX_RECORDS 32 #define ADM1266_PMBUS_BLOCK_MAX 255 @@ -360,6 +361,8 @@ static int adm1266_nvmem_read_blackbox(struct adm1266_data *data, u8 *read_buff) return -EIO; record_count = buf[3]; + if (record_count > ADM1266_BLACKBOX_MAX_RECORDS) + return -EIO; for (index = 0; index < record_count; index++) { ret = adm1266_pmbus_block_xfer(data, ADM1266_READ_BLACKBOX, 1, &index, read_buff); From 2279c342d94eca225bf9f301c8806a05a1c81619 Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Fri, 15 May 2026 15:11:50 -0700 Subject: [PATCH 1302/1518] hwmon: (pmbus/adm1266) include PEC byte in pmbus_block_xfer read buffer commit 487566cb1ccdf3756fdd7bf8d875e612ff3169bb upstream. adm1266_pmbus_block_xfer() sets up the read transaction with .buf = data->read_buf, .len = ADM1266_PMBUS_BLOCK_MAX + 2, but read_buf in struct adm1266_data is declared as u8 read_buf[ADM1266_PMBUS_BLOCK_MAX + 1]; For a max-length block response (length byte = 255 + up to 1 PEC byte), the i2c controller is told to write 257 bytes into a 256-byte buffer, putting one byte past the end of read_buf. The same response also makes the subsequent PEC compare if (crc != msgs[1].buf[msgs[1].buf[0] + 1]) read a byte beyond the array. Bump the read_buf declaration to ADM1266_PMBUS_BLOCK_MAX + 2 so the buffer can hold the length byte, up to 255 payload bytes, and the PEC byte the i2c_msg length already accounts for. Fixes: 407dc802a9c0 ("hwmon: (pmbus/adm1266) Add Block process call") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Link: https://lore.kernel.org/r/20260515-adm1266-fixes-v1-4-1c1ea1349cfe@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 43d9e74077954..5c68e3177f64e 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -61,7 +61,7 @@ struct adm1266_data { u8 *dev_mem; struct mutex buf_mutex; u8 write_buf[ADM1266_PMBUS_BLOCK_MAX + 1] ____cacheline_aligned; - u8 read_buf[ADM1266_PMBUS_BLOCK_MAX + 1] ____cacheline_aligned; + u8 read_buf[ADM1266_PMBUS_BLOCK_MAX + 2] ____cacheline_aligned; }; static const struct nvmem_cell_info adm1266_nvmem_cells[] = { From 97a9cf2a8217ca1cdaf48cb9ab26e471632c7e7f Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Fri, 15 May 2026 15:11:51 -0700 Subject: [PATCH 1303/1518] hwmon: (pmbus/adm1266) bounce blackbox records through a protocol-sized buffer commit 43cae21424ff8e33894a0f86c6b80b840c049fd7 upstream. adm1266_pmbus_block_xfer() copies the device-supplied block payload into the caller-provided buffer using the device-supplied length: memcpy(data_r, &msgs[1].buf[1], msgs[1].buf[0]); The helper does not know how large data_r is and trusts the device to return at most one record's worth of bytes. adm1266_nvmem_read_blackbox() violates that contract: it advances read_buff inside data->dev_mem in ADM1266_BLACKBOX_SIZE (64-byte) strides while the helper is willing to write up to ADM1266_PMBUS_BLOCK_MAX (255) bytes. A device that returns more than 64 bytes on the trailing record (read_buff offset 1984 in the 2048-byte dev_mem allocation) overflows dev_mem by up to 191 bytes before the post-call if (ret != ADM1266_BLACKBOX_SIZE) return -EIO; can reject the response. Contain the fix in the caller without changing the helper signature: read each record into a 255-byte local bounce buffer that matches the helper's maximum output, validate the returned length, and only then copy exactly ADM1266_BLACKBOX_SIZE bytes into the dev_mem slot. Fixes: 407dc802a9c0 ("hwmon: (pmbus/adm1266) Add Block process call") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Link: https://lore.kernel.org/r/20260515-adm1266-fixes-v1-5-1c1ea1349cfe@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 5c68e3177f64e..ea1edb89d2a0c 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -348,6 +348,7 @@ static void adm1266_init_debugfs(struct adm1266_data *data) static int adm1266_nvmem_read_blackbox(struct adm1266_data *data, u8 *read_buff) { + u8 record[ADM1266_PMBUS_BLOCK_MAX]; int record_count; char index; u8 buf[I2C_SMBUS_BLOCK_MAX]; @@ -365,13 +366,14 @@ static int adm1266_nvmem_read_blackbox(struct adm1266_data *data, u8 *read_buff) return -EIO; for (index = 0; index < record_count; index++) { - ret = adm1266_pmbus_block_xfer(data, ADM1266_READ_BLACKBOX, 1, &index, read_buff); + ret = adm1266_pmbus_block_xfer(data, ADM1266_READ_BLACKBOX, 1, &index, record); if (ret < 0) return ret; if (ret != ADM1266_BLACKBOX_SIZE) return -EIO; + memcpy(read_buff, record, ADM1266_BLACKBOX_SIZE); read_buff += ADM1266_BLACKBOX_SIZE; } From fa7ca363069a70b0d1aa51e8892e3095fe2ac1ec Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Mon, 18 May 2026 17:52:25 -0700 Subject: [PATCH 1304/1518] hwmon: (pmbus/adm1266) cap PDIO scan in get_multiple at ADM1266_PDIO_NR commit d7834d92251baade796812876e95555e2066fa9f upstream. adm1266_gpio_get_multiple() iterates the PDIO portion of the caller-supplied mask using for_each_set_bit_from(gpio_nr, mask, ADM1266_GPIO_NR + ADM1266_PDIO_STATUS) { ... } where ADM1266_PDIO_STATUS is the PMBus command code (0xE9, i.e. 233), not the number of PDIO pins. The intended upper bound is ADM1266_GPIO_NR + ADM1266_PDIO_NR = 25. gpiolib hands in a mask sized for gc.ngpio (= 25 bits on this chip), so the iteration walks find_next_bit() up to 242, reading up to 217 extra bits (a handful of unsigned-long words: four on 64-bit, seven on 32-bit) of whatever lives past the end of the mask in the caller's stack. Any incidental set bit in that range then drives a set_bit(gpio_nr, bits) call that writes past the end of the caller-supplied bits array too -- both out-of-bounds. Substitute ADM1266_PDIO_NR for the constant so the scan stops at the last real PDIO bit. Fixes: d98dfad35c38 ("hwmon: (pmbus/adm1266) Add support for GPIOs") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Reviewed-by: Bartosz Golaszewski Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20260518-adm1266-gpio-fixes-v3-1-e425e4f88139@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index ea1edb89d2a0c..0e2e80bf6c8c0 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -212,7 +212,7 @@ static int adm1266_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask status = read_buf[0] + (read_buf[1] << 8); *bits = 0; - for_each_set_bit_from(gpio_nr, mask, ADM1266_GPIO_NR + ADM1266_PDIO_STATUS) { + for_each_set_bit_from(gpio_nr, mask, ADM1266_GPIO_NR + ADM1266_PDIO_NR) { if (test_bit(gpio_nr - ADM1266_GPIO_NR, &status)) set_bit(gpio_nr, bits); } From b2998ae903315af553d4860312d5189084eeedd9 Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Mon, 18 May 2026 17:52:26 -0700 Subject: [PATCH 1305/1518] hwmon: (pmbus/adm1266) don't clobber GPIO bits before PDIO read in get_multiple commit 3327a12aee9e10ffa903e28b8445dfd1af5307c0 upstream. adm1266_gpio_get_multiple() zeroes *bits before the GPIO_STATUS loop and then a second time before the PDIO_STATUS loop: *bits = 0; for_each_set_bit(gpio_nr, mask, ADM1266_GPIO_NR) { ... set_bit(gpio_nr, bits); } ret = i2c_smbus_read_block_data(data->client, ADM1266_PDIO_STATUS, ...); ... *bits = 0; for_each_set_bit_from(gpio_nr, mask, ADM1266_GPIO_NR + ADM1266_PDIO_NR) { ... set_bit(gpio_nr, bits); } The second *bits = 0 throws away every GPIO bit the first loop just populated, so callers asking for any combination of GPIO and PDIO pins always see the GPIO portion of the returned bits as zero. Drop the redundant second assignment so both halves of the result survive. Fixes: d98dfad35c38 ("hwmon: (pmbus/adm1266) Add support for GPIOs") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Reviewed-by: Bartosz Golaszewski Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20260518-adm1266-gpio-fixes-v3-2-e425e4f88139@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 0e2e80bf6c8c0..0c8d49dd3ef16 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -211,7 +211,6 @@ static int adm1266_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask status = read_buf[0] + (read_buf[1] << 8); - *bits = 0; for_each_set_bit_from(gpio_nr, mask, ADM1266_GPIO_NR + ADM1266_PDIO_NR) { if (test_bit(gpio_nr - ADM1266_GPIO_NR, &status)) set_bit(gpio_nr, bits); From a203125c0e818809b206f269a6386c827c3286ff Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Mon, 18 May 2026 17:52:28 -0700 Subject: [PATCH 1306/1518] hwmon: (pmbus/adm1266) register the gpio_chip after pmbus_do_probe() commit 491403b9b76cf66abd81301c5901aa4a4549f1e8 upstream. adm1266_probe() calls adm1266_config_gpio() -- which goes on to devm_gpiochip_add_data() and exposes the gpio_chip callbacks to gpiolib -- before pmbus_do_probe() has initialised the per-client PMBus state (notably the pmbus_lock mutex the core hands out via pmbus_get_data()). That ordering is already a latent hazard: any GPIO access that lands between adm1266_config_gpio() and the end of pmbus_do_probe() (for example a sysfs read from a user space agent that opens the gpiochip the instant gpiolib advertises it) races pmbus_do_probe()'s own device accesses with no serialisation. Move adm1266_config_gpio() down past pmbus_do_probe() so the chip isn't reachable from userspace until the PMBus state it depends on is fully initialised. Fixes: d98dfad35c38 ("hwmon: (pmbus/adm1266) Add support for GPIOs") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Reviewed-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20260518-adm1266-gpio-fixes-v3-4-e425e4f88139@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 0c8d49dd3ef16..575a6642e8506 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -466,10 +466,6 @@ static int adm1266_probe(struct i2c_client *client) crc8_populate_msb(pmbus_crc_table, 0x7); mutex_init(&data->buf_mutex); - ret = adm1266_config_gpio(data); - if (ret < 0) - return ret; - ret = adm1266_set_rtc(data); if (ret < 0) return ret; @@ -482,6 +478,10 @@ static int adm1266_probe(struct i2c_client *client) if (ret) return ret; + ret = adm1266_config_gpio(data); + if (ret < 0) + return ret; + adm1266_init_debugfs(data); return 0; From dd12c6dbe2ac1c16e4d86af7b8a5a3858977c54c Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Mon, 18 May 2026 17:52:29 -0700 Subject: [PATCH 1307/1518] hwmon: (pmbus/adm1266) register the nvmem device after pmbus_do_probe() commit 6af713af91d5c34ec049eb3cc2c5b3f5eba953b8 upstream. adm1266_probe() calls adm1266_config_nvmem() -- which goes on to devm_nvmem_register() and exposes adm1266_nvmem_read() to userspace -- before pmbus_do_probe() has initialised the per-client PMBus state. Same latent hazard as the gpio_chip one fixed in the previous patch: once the nvmem device is registered, gpiolib's nvmem char-dev / sysfs interface is reachable, and any concurrent read triggers adm1266_nvmem_read() -> adm1266_nvmem_read_blackbox(), which issues PMBus traffic that races pmbus_do_probe()'s own device accesses with no serialisation. Move adm1266_config_nvmem() down past pmbus_do_probe() so the nvmem device isn't reachable from userspace until the PMBus state the nvmem accessors depend on is fully initialised. Fixes: 15609d189302 ("hwmon: (pmbus/adm1266) read blackbox") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Link: https://lore.kernel.org/r/20260518-adm1266-gpio-fixes-v3-5-e425e4f88139@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 575a6642e8506..8aa52215cff7a 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -470,14 +470,14 @@ static int adm1266_probe(struct i2c_client *client) if (ret < 0) return ret; - ret = adm1266_config_nvmem(data); - if (ret < 0) - return ret; - ret = pmbus_do_probe(client, &data->info); if (ret) return ret; + ret = adm1266_config_nvmem(data); + if (ret < 0) + return ret; + ret = adm1266_config_gpio(data); if (ret < 0) return ret; From eb3cd9bb590460c6127145cb245be925d23f5232 Mon Sep 17 00:00:00 2001 From: Abdurrahman Hussain Date: Mon, 18 May 2026 17:52:27 -0700 Subject: [PATCH 1308/1518] hwmon: (pmbus/adm1266) reject short block-read responses in the GPIO accessors commit a7232f68c43ca62f545049b7f5fbfc75137b843b upstream. adm1266_gpio_get() and adm1266_gpio_get_multiple() both compose the pin-status word as pins_status = read_buf[0] + (read_buf[1] << 8); right after i2c_smbus_read_block_data(), guarding only against an error return. A well-behaved device returns 2 bytes for GPIO_STATUS/PDIO_STATUS, but the helper happily reports a 0- or 1-byte response too. If the device returns 0 bytes, both read_buf slots are uninitialized stack memory; if it returns 1 byte, read_buf[1] is. The composed value then flows through set_bit() into the caller's *bits in adm1266_gpio_get_multiple(), or into the return value of adm1266_gpio_get(), and ends up in userspace via gpiolib (sysfs and the char-dev ioctls). That leaks a few bits of kernel stack per request on any device whose firmware glitch, bus error, or hostile slave produces a short block-read response. Add the missing length check to both call sites and surface a short response as -EIO. Fixes: d98dfad35c38 ("hwmon: (pmbus/adm1266) Add support for GPIOs") Cc: stable@vger.kernel.org Signed-off-by: Abdurrahman Hussain Reviewed-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20260518-adm1266-gpio-fixes-v3-3-e425e4f88139@nexthop.ai Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/adm1266.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index 8aa52215cff7a..9631a64cb1ebb 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -176,6 +176,8 @@ static int adm1266_gpio_get(struct gpio_chip *chip, unsigned int offset) ret = i2c_smbus_read_block_data(data->client, pmbus_cmd, read_buf); if (ret < 0) return ret; + if (ret < 2) + return -EIO; pins_status = read_buf[0] + (read_buf[1] << 8); if (offset < ADM1266_GPIO_NR) @@ -196,6 +198,8 @@ static int adm1266_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask ret = i2c_smbus_read_block_data(data->client, ADM1266_GPIO_STATUS, read_buf); if (ret < 0) return ret; + if (ret < 2) + return -EIO; status = read_buf[0] + (read_buf[1] << 8); @@ -208,6 +212,8 @@ static int adm1266_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask ret = i2c_smbus_read_block_data(data->client, ADM1266_PDIO_STATUS, read_buf); if (ret < 0) return ret; + if (ret < 2) + return -EIO; status = read_buf[0] + (read_buf[1] << 8); From 00aca89f5e3453b30b73e31aa31099b1433f8370 Mon Sep 17 00:00:00 2001 From: Til Kaiser Date: Mon, 13 Apr 2026 15:52:34 +0200 Subject: [PATCH 1309/1518] pinctrl: qcom: ipq4019: mark gpio as a GPIO pin function [ Upstream commit b51d33ea8a164bb5f0eec8ad817fa9730ac2b577 ] The qcom pinctrl core supports marking functions that represent GPIO mode via PINCTRL_GPIO_PINFUNCTION(), so that strict pinmuxing does not reject GPIO requests for pins that are muxed to the GPIO function. ipq4019 still describes its gpio function with QCA_PIN_FUNCTION(gpio), so it is not treated as a GPIO pin function. As a result, GPIO consumers can still conflict with pinctrl states that select the "gpio" function. Add a QCA_GPIO_PIN_FUNCTION() helper and use it for the ipq4019 gpio function, matching how the msm-based qcom drivers handle this. This allows ipq4019 to keep the GPIO-related pin configuration in DTS without tripping over strict pinmux ownership checks. Fixes: cc85cb96e2e4 ("pinctrl: qcom: make the pinmuxing strict") Signed-off-by: Til Kaiser Reviewed-by: Dmitry Baryshkov Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/qcom/pinctrl-ipq4019.c | 2 +- drivers/pinctrl/qcom/pinctrl-msm.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c index 6ede3149b6e17..07df812fb7282 100644 --- a/drivers/pinctrl/qcom/pinctrl-ipq4019.c +++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c @@ -480,7 +480,7 @@ static const struct pinfunction ipq4019_functions[] = { QCA_PIN_FUNCTION(blsp_uart0), QCA_PIN_FUNCTION(blsp_uart1), QCA_PIN_FUNCTION(chip_rst), - QCA_PIN_FUNCTION(gpio), + QCA_GPIO_PIN_FUNCTION(gpio), QCA_PIN_FUNCTION(i2s_rx), QCA_PIN_FUNCTION(i2s_spdif_in), QCA_PIN_FUNCTION(i2s_spdif_out), diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 4625fa5320a95..120217012a9f6 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -39,6 +39,11 @@ struct pinctrl_pin_desc; fname##_groups, \ ARRAY_SIZE(fname##_groups)) +#define QCA_GPIO_PIN_FUNCTION(fname) \ + [qca_mux_##fname] = PINCTRL_GPIO_PINFUNCTION(#fname, \ + fname##_groups, \ + ARRAY_SIZE(fname##_groups)) + /** * struct msm_pingroup - Qualcomm pingroup definition * @grp: Generic data of the pin group (name and pins) From d27b29e474a6274cf34eb3afb59e137025ced83c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 28 Mar 2026 00:42:10 +0100 Subject: [PATCH 1310/1518] ARM: dts: renesas: genmai: Drop superfluous cells [ Upstream commit 714e1d6bba0e0abe5c87c8e189a35fa690540df4 ] Drop superfluous address-cells and size-cells to fix DTC W=1 warning: arch/arm/boot/dts/renesas/r7s72100-genmai.dts:28.17-55.4: Warning (avoid_unnecessary_addr_size): /flash@18000000: unnecessary #address-cells/#size-cells without "ranges", "dma-ranges" or child "reg" or "ranges" property Signed-off-by: Marek Vasut Fixes: 30e0a8cf886cb459 ("ARM: dts: renesas: genmai: Add FLASH nodes") Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260327234244.91707-6-marek.vasut+renesas@mailbox.org Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/arm/boot/dts/renesas/r7s72100-genmai.dts | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm/boot/dts/renesas/r7s72100-genmai.dts b/arch/arm/boot/dts/renesas/r7s72100-genmai.dts index 3c37565097145..da552a66615e0 100644 --- a/arch/arm/boot/dts/renesas/r7s72100-genmai.dts +++ b/arch/arm/boot/dts/renesas/r7s72100-genmai.dts @@ -34,9 +34,6 @@ clocks = <&mstp9_clks R7S72100_CLK_SPIBSC0>; power-domains = <&cpg_clocks>; - #address-cells = <1>; - #size-cells = <1>; - partitions { compatible = "fixed-partitions"; #address-cells = <1>; From a7fee132268376ac706605a4526bda60e6e1d7ee Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 28 Mar 2026 00:42:11 +0100 Subject: [PATCH 1311/1518] ARM: dts: renesas: rskrza1: Drop superfluous cells [ Upstream commit ab83176d3cf1cf1c1f6e604432905bda4515d17f ] Drop superfluous address-cells and size-cells to fix DTC W=1 warning: arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts:32.17-72.4: Warning (avoid_unnecessary_addr_size): /flash@18000000: unnecessary #address-cells/#size-cells without "ranges", "dma-ranges" or child "reg" or "ranges" property Signed-off-by: Marek Vasut Fixes: 98537eb77d3ef185 ("ARM: dts: renesas: rskrza1: Add FLASH nodes") Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260327234244.91707-7-marek.vasut+renesas@mailbox.org Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts b/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts index 91178fb9e7210..3306bc9b7bc37 100644 --- a/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts +++ b/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts @@ -36,8 +36,6 @@ power-domains = <&cpg_clocks>; bank-width = <4>; device-width = <1>; - #address-cells = <1>; - #size-cells = <1>; partitions { compatible = "fixed-partitions"; From c4cfa8ee77374630017b9cbd20ba2f6f46c08084 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 28 Mar 2026 09:05:45 +0000 Subject: [PATCH 1312/1518] pinctrl: renesas: rzg2l: Fix incorrect PUPD register offset for high pins during suspend/resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6dba9b7268cc50166bce47608670192fd874e363 ] When saving/restoring pull-up/down register state during suspend/resume, the second PUPD register access was incorrectly using the same base offset as the first, effectively reading/writing the same register twice instead of the adjacent one. Add the correct + 4 byte offset to the second RZG2L_PCTRL_REG_ACCESS32 call so that pupd[1][port] is properly saved and restored from the next 32-bit register in the PUPD register pair, covering pins 4–7 of ports with 4 or more pins. Fixes: b2bd65fbb617 ("pinctrl: renesas: rzg2l: Add suspend/resume support for pull up/down") Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260328090548.84124-1-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/pinctrl/renesas/pinctrl-rzg2l.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index ca360185740a8..df784e3807af0 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -3035,7 +3035,7 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + PUPD(off), cache->pupd[0][port]); if (pincnt >= 4) { - RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + PUPD(off), + RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + PUPD(off) + 4, cache->pupd[1][port]); } } From 8d1c6b603327b22f151de7fbeb7f9f64bec31ccf Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Mon, 13 Apr 2026 19:24:51 +0100 Subject: [PATCH 1313/1518] pinctrl: renesas: rzg2l: Fix SMT register cache handling [ Upstream commit c88ab9407986836820848128ce1f90f2fa49da95 ] Store SMT register cache per bank instead of using a single array. On RZ/V2H(P), RZ/V2N, and RZ/G3E, the SMT register is split across two 32-bit registers: bits 0/8/16/24 control pins 0-3, while pins 4-7 are controlled by the corresponding bits in the next register. The previous implementation cached only a single SMT register, leading to incomplete save/restore of SMT state. Convert cache->smt to a per-bank array and allocate storage for both halves. Update suspend/resume handling to save and restore both SMT registers when present. Fixes: 837afa592c623 ("pinctrl: renesas: rzg2l: Add suspend/resume support for Schmitt control registers") Signed-off-by: Lad Prabhakar Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260413182456.811543-2-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/pinctrl/renesas/pinctrl-rzg2l.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index df784e3807af0..aaa783c79e6dd 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -335,7 +335,7 @@ struct rzg2l_pinctrl_reg_cache { u32 *iolh[2]; u32 *ien[2]; u32 *pupd[2]; - u32 *smt; + u32 *smt[2]; u8 sd_ch[2]; u8 eth_poc[2]; u8 oen; @@ -2723,10 +2723,6 @@ static int rzg2l_pinctrl_reg_cache_alloc(struct rzg2l_pinctrl *pctrl) if (!cache->pfc) return -ENOMEM; - cache->smt = devm_kcalloc(pctrl->dev, nports, sizeof(*cache->smt), GFP_KERNEL); - if (!cache->smt) - return -ENOMEM; - for (u8 i = 0; i < 2; i++) { u32 n_dedicated_pins = pctrl->data->n_dedicated_pins; @@ -2745,6 +2741,11 @@ static int rzg2l_pinctrl_reg_cache_alloc(struct rzg2l_pinctrl *pctrl) if (!cache->pupd[i]) return -ENOMEM; + cache->smt[i] = devm_kcalloc(pctrl->dev, nports, sizeof(*cache->smt[i]), + GFP_KERNEL); + if (!cache->smt[i]) + return -ENOMEM; + /* Allocate dedicated cache. */ dedicated_cache->iolh[i] = devm_kcalloc(pctrl->dev, n_dedicated_pins, sizeof(*dedicated_cache->iolh[i]), @@ -3052,8 +3053,14 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen } } - if (has_smt) - RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + SMT(off), cache->smt[port]); + if (has_smt) { + RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + SMT(off), + cache->smt[0][port]); + if (pincnt >= 4) { + RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + SMT(off) + 4, + cache->smt[1][port]); + } + } } } From e917713f013423069782ff554935c7a5d4266783 Mon Sep 17 00:00:00 2001 From: Xianwei Zhao Date: Wed, 22 Apr 2026 11:44:13 +0000 Subject: [PATCH 1314/1518] pinctrl: meson: amlogic-a4: fix deadlock issue [ Upstream commit e72ce029810390eb987a036fb2c8a5da9a23b685 ] Accessing the pinconf-pins sysfs node may deadlock. pinconf_pins_show() holds pctldev->mutex, and the platform driver calls pinctrl_find_gpio_range_from_pin(), which tries to acquire the same mutex again, leading to a deadlock. Use pinctrl_find_gpio_range_from_pin_nolock() to fix this issue. Fixes: 6e9be3abb78c ("pinctrl: Add driver support for Amlogic SoCs") Signed-off-by: Xianwei Zhao Reviewed-by: Neil Armstrong Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c index e2293a872dcb7..35d27626a336b 100644 --- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c +++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c @@ -292,7 +292,7 @@ static int aml_calc_reg_and_bit(struct pinctrl_gpio_range *range, static int aml_pinconf_get_pull(struct aml_pinctrl *info, unsigned int pin) { struct pinctrl_gpio_range *range = - pinctrl_find_gpio_range_from_pin(info->pctl, pin); + pinctrl_find_gpio_range_from_pin_nolock(info->pctl, pin); struct aml_gpio_bank *bank = gpio_chip_to_bank(range->gc); unsigned int reg, bit, val; int ret, conf; @@ -326,7 +326,7 @@ static int aml_pinconf_get_drive_strength(struct aml_pinctrl *info, u16 *drive_strength_ua) { struct pinctrl_gpio_range *range = - pinctrl_find_gpio_range_from_pin(info->pctl, pin); + pinctrl_find_gpio_range_from_pin_nolock(info->pctl, pin); struct aml_gpio_bank *bank = gpio_chip_to_bank(range->gc); unsigned int reg, bit; unsigned int val; @@ -365,7 +365,7 @@ static int aml_pinconf_get_gpio_bit(struct aml_pinctrl *info, unsigned int reg_type) { struct pinctrl_gpio_range *range = - pinctrl_find_gpio_range_from_pin(info->pctl, pin); + pinctrl_find_gpio_range_from_pin_nolock(info->pctl, pin); struct aml_gpio_bank *bank = gpio_chip_to_bank(range->gc); unsigned int reg, bit, val; int ret; From 1fce9dcb3a662059011b4ce341a9cfb947bf2e1d Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Thu, 23 Apr 2026 16:55:24 +0530 Subject: [PATCH 1315/1518] pinctrl: qcom: Fix GPIO to PDC wake irq map for qcs615 [ Upstream commit 9d69033ad967b6e09b1e5b30d1a32c6c4876465d ] PDC interrupts 122-125 were meant for ibi_i3c wakeup but qcs615 do not support i3c. GPIOs 39,51,88 and 89 are also connected to different PDC pin to support non-ibi wakeup. Update the wakeirq map to reflect same. Fixes: b698f36a9d40 ("pinctrl: qcom: add the tlmm driver for QCS615 platform") Signed-off-by: Maulik Shah Signed-off-by: Navya Malempati Reviewed-by: Konrad Dybcio Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/qcom/pinctrl-qcs615.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c index f1c827ddbfbfa..4d474c312c10b 100644 --- a/drivers/pinctrl/qcom/pinctrl-qcs615.c +++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c @@ -1043,11 +1043,11 @@ static const struct msm_pingroup qcs615_groups[] = { static const struct msm_gpio_wakeirq_map qcs615_pdc_map[] = { { 1, 45 }, { 3, 31 }, { 7, 55 }, { 9, 110 }, { 11, 34 }, { 13, 33 }, { 14, 35 }, { 17, 46 }, { 19, 48 }, { 21, 83 }, - { 22, 36 }, { 26, 38 }, { 35, 37 }, { 39, 125 }, { 41, 47 }, - { 47, 49 }, { 48, 51 }, { 50, 52 }, { 51, 123 }, { 55, 56 }, + { 22, 36 }, { 26, 38 }, { 35, 37 }, { 39, 118 }, { 41, 47 }, + { 47, 49 }, { 48, 51 }, { 50, 52 }, { 51, 116 }, { 55, 56 }, { 56, 57 }, { 57, 58 }, { 60, 60 }, { 71, 54 }, { 80, 73 }, { 81, 64 }, { 82, 50 }, { 83, 65 }, { 84, 92 }, { 85, 99 }, - { 86, 67 }, { 87, 84 }, { 88, 124 }, { 89, 122 }, { 90, 69 }, + { 86, 67 }, { 87, 84 }, { 88, 117 }, { 89, 115 }, { 90, 69 }, { 92, 88 }, { 93, 75 }, { 94, 91 }, { 95, 72 }, { 96, 82 }, { 97, 74 }, { 98, 95 }, { 99, 94 }, { 100, 100 }, { 101, 40 }, { 102, 93 }, { 103, 77 }, { 104, 78 }, { 105, 96 }, { 107, 97 }, From e912d5dc00965e69fe95554769b2032ab728d212 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 23 Apr 2026 10:10:02 +0300 Subject: [PATCH 1316/1518] HID: intel-thc-hid: Intel-quickspi: Fix some error codes [ Upstream commit ae4ac077332ea3341a0f4c0973556c6b7ac5b7a1 ] If we have a partial read that is supposed to be treated as failure but in this code we forgot to set the error code. Return -EINVAL. Fixes: 9d8d51735a3a ("HID: intel-thc-hid: intel-quickspi: Add HIDSPI protocol implementation") Signed-off-by: Dan Carpenter Reviewed-by: Even Xu Reviewed-by: Mark Pearson Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c index 16f780bc879b1..cb19057f1191b 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c @@ -94,7 +94,7 @@ static int quickspi_get_device_descriptor(struct quickspi_device *qsdev) dev_err_once(qsdev->dev, "Read DEVICE_DESCRIPTOR failed, ret = %d\n", ret); dev_err_once(qsdev->dev, "DEVICE_DESCRIPTOR expected len = %u, actual read = %u\n", input_len, read_len); - return ret; + return ret ?: -EINVAL; } input_rep_type = ((struct input_report_body_header *)read_buf)->input_report_type; @@ -318,7 +318,7 @@ int reset_tic(struct quickspi_device *qsdev) dev_err_once(qsdev->dev, "Read RESET_RESPONSE body failed, ret = %d\n", ret); dev_err_once(qsdev->dev, "RESET_RESPONSE body expected len = %u, actual = %u\n", read_len, actual_read_len); - return ret; + return ret ?: -EINVAL; } input_rep_type = FIELD_GET(HIDSPI_IN_REP_BDY_HDR_REP_TYPE, reset_response); From 4894847fcec140636c1a8f9c719a9652ef1c1b6c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 28 Apr 2026 10:33:16 +0200 Subject: [PATCH 1317/1518] HID: uclogic: Fix regression of input name assignment [ Upstream commit 487359284509a6745e14b8c0518768bc277809b0 ] The previous fix for adding the devm_kasprintf() return check in the commit bd07f751208b ("HID: uclogic: Add NULL check in uclogic_input_configured()") changed the condition of hi->input->name assignment, and it resulted in missing the proper input device name when no custom suffix is defined. Restore the conditional to the original content to address the regression. Fixes: bd07f751208b ("HID: uclogic: Add NULL check in uclogic_input_configured()") Signed-off-by: Takashi Iwai Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-uclogic-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 34fb03ae8ee2f..c6db3e7c5fd30 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -184,7 +184,9 @@ static int uclogic_input_configured(struct hid_device *hdev, suffix = "System Control"; break; } - } else { + } + + if (suffix) { hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s %s", hdev->name, suffix); if (!hi->input->name) From 820245d86ce58898fb48b4fefc77d0cafc02801d Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:25 +0100 Subject: [PATCH 1318/1518] firmware: arm_ffa: Check for NULL FF-A ID table while driver registration [ Upstream commit 0a5e695095c557d2380131b613dea4e8d90371be ] The bus match callback assumes that every FF-A driver provides an id_table and dereferences it unconditionally. Enforce that contract at registration time so a buggy client driver cannot crash the bus during match. Fixes: 92743071464f ("firmware: arm_ffa: Ensure drivers provide a probe function") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-1-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/bus.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 50bfe56c755e9..6779923e35c55 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -26,6 +26,8 @@ static int ffa_device_match(struct device *dev, const struct device_driver *drv) id_table = to_ffa_driver(drv)->id_table; ffa_dev = to_ffa_dev(dev); + if (!id_table) + return 0; while (!uuid_is_null(&id_table->uuid)) { /* @@ -123,7 +125,7 @@ int ffa_driver_register(struct ffa_driver *driver, struct module *owner, { int ret; - if (!driver->probe) + if (!driver->probe || !driver->id_table) return -EINVAL; driver->driver.bus = &ffa_bus_type; From 1418765d28ab11efd1abbee8b691d2a3e50fd20e Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:26 +0100 Subject: [PATCH 1319/1518] firmware: arm_ffa: Skip free_pages on RX buffer alloc failure [ Upstream commit 09527e2c534911619d7e098729711100290bc3e1 ] If the RX buffer allocation fails in ffa_init(), the error path jumps to free_pages even though no buffer has been allocated yet. Route that case directly to free_drv_info so the cleanup path is only used after at least one RX/TX buffer allocation has succeeded. Fixes: 3bbfe9871005 ("firmware: arm_ffa: Add initial Arm FFA driver support") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-2-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index d71a2ef335d1c..cf7f913a55b6e 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -2063,7 +2063,7 @@ static int __init ffa_init(void) drv_info->rx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); if (!drv_info->rx_buffer) { ret = -ENOMEM; - goto free_pages; + goto free_drv_info; } drv_info->tx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); From 07907b897bb72c580bc6432b8fd652e8f2d47857 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:28 +0100 Subject: [PATCH 1320/1518] firmware: arm_ffa: Fix per-vcpu self notifications handling in workqueue [ Upstream commit 9985d5357ed93af0d1933969c247e966957730e1 ] Per-vcpu notification handling already runs from a per-cpu work item on the target cpu. Routing that path back through smp_call_function_single() re-enters the call-function IPI path and executes the notification handler with interrupts disabled. That makes the framework path unsafe, since it takes a mutex, allocates memory with GFP_KERNEL, and invokes client callbacks. Handle per-vcpu self notifications directly from the existing per-cpu work item instead. This keeps the per-vcpu path in task context and avoids the extra IPI hop entirely. Fixes: 3a3e2b83e805 ("firmware: arm_ffa: Avoid queuing work when running on the worker queue") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-4-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index cf7f913a55b6e..30f8e0ff694fb 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1538,7 +1538,7 @@ static void notif_pcpu_irq_work_fn(struct work_struct *work) struct ffa_drv_info *info = container_of(work, struct ffa_drv_info, notif_pcpu_work); - ffa_self_notif_handle(smp_processor_id(), true, info); + notif_get_and_handle(info); } static const struct ffa_info_ops ffa_drv_info_ops = { From 1aa01b46fe3ba0d36c2d0bac382a62a740b6eb80 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:29 +0100 Subject: [PATCH 1321/1518] firmware: arm_ffa: Unregister bus notifier on teardown for FF-A v1.0 [ Upstream commit 6d3daa9b8d313f42d52e75590310f26a29b61b44 ] For FF-A v1.0 the driver registers a bus notifier to backfill UUID matching, but the notifier was never unregistered on cleanup paths. Track the registration state and unregister it during teardown and early partition-setup failure. Fixes: 9dd15934f60d ("firmware: arm_ffa: Move the FF-A v1.0 NULL UUID workaround to bus notifier") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-5-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 30f8e0ff694fb..287db85286106 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -100,6 +100,7 @@ struct ffa_drv_info { bool mem_ops_native; bool msg_direct_req2_supp; bool bitmap_created; + bool bus_notifier_registered; bool notif_enabled; unsigned int sched_recv_irq; unsigned int notif_pend_irq; @@ -1625,6 +1626,15 @@ static struct notifier_block ffa_bus_nb = { .notifier_call = ffa_bus_notifier, }; +static void ffa_bus_notifier_unregister(void) +{ + if (!drv_info->bus_notifier_registered) + return; + + bus_unregister_notifier(&ffa_bus_type, &ffa_bus_nb); + drv_info->bus_notifier_registered = false; +} + static int ffa_xa_add_partition_info(struct ffa_device *dev) { struct ffa_dev_part_info *info; @@ -1708,6 +1718,8 @@ static void ffa_partitions_cleanup(void) struct list_head *phead; unsigned long idx; + ffa_bus_notifier_unregister(); + /* Clean up/free all registered devices */ ffa_devices_unregister(); @@ -1735,11 +1747,14 @@ static int ffa_setup_partitions(void) ret = bus_register_notifier(&ffa_bus_type, &ffa_bus_nb); if (ret) pr_err("Failed to register FF-A bus notifiers\n"); + else + drv_info->bus_notifier_registered = true; } count = ffa_partition_probe(&uuid_null, &pbuf); if (count <= 0) { pr_info("%s: No partitions found, error %d\n", __func__, count); + ffa_bus_notifier_unregister(); return -EINVAL; } From f3216d930c0fa99ed6bbfb1e13c193cee0bea788 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Thu, 9 Apr 2026 09:11:39 +0000 Subject: [PATCH 1322/1518] riscv: errata: Fix bitwise vs logical AND in MIPS errata patching [ Upstream commit 4d2b03699460b8fd5df34408a03a84a1a7ff8aa1 ] The condition checking whether a specific errata needs patching uses logical AND (&&) instead of bitwise AND (&). Since logical AND only checks that both operands are non-zero, this causes all errata patches to be applied whenever any single errata is detected, rather than only applying the matching one. The SiFive errata implementation correctly uses bitwise AND for the same check. Fixes: 0b0ca959d206 ("riscv: errata: Fix the PAUSE Opcode for MIPS P8700") Signed-off-by: Michael Neuling Assisted-by: Cursor:claude-4.6-opus-high-thinking Link: https://patch.msgid.link/20260409091143.1348853-2-mikey@neuling.org [pjw@kernel.org: fixed checkpatch warning] Signed-off-by: Paul Walmsley Signed-off-by: Sasha Levin --- arch/riscv/errata/mips/errata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/errata/mips/errata.c b/arch/riscv/errata/mips/errata.c index e984a8152208c..2c3dc2259e93e 100644 --- a/arch/riscv/errata/mips/errata.c +++ b/arch/riscv/errata/mips/errata.c @@ -57,7 +57,7 @@ void mips_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, } tmp = (1U << alt->patch_id); - if (cpu_req_errata && tmp) { + if (cpu_req_errata & tmp) { mutex_lock(&text_mutex); patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt), alt->alt_len); From 96b8b9d0dead730ede84e81df473552cd4127c70 Mon Sep 17 00:00:00 2001 From: "Guo Ren (Alibaba DAMO Academy)" Date: Sun, 25 Jan 2026 00:52:12 -0500 Subject: [PATCH 1323/1518] riscv: mm: Fixup no5lvl failure when vaddr is invalid MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit db909bd7986c10da074917af3dae83a60fa65093 ] Unlike no4lvl, no5lvl still continues to detect satp, which requires va=pa mapping. When pa=0x800000000000, no5lvl would fail in Sv48 mode due to an illegal VA value of 0x800000000000. So, prevent detecting the satp flow for no5lvl, when vaddr is invalid. Add the is_vaddr_valid() function for checking. Fixes: 26e7aacb83df ("riscv: Allow to downgrade paging mode from the command line") Cc: Alexandre Ghiti Cc: Björn Töpel Signed-off-by: Guo Ren (Alibaba DAMO Academy) Tested-by: Fangyu Yu Link: https://patch.msgid.link/20260125055212.433163-1-guoren@kernel.org [pjw@kernel.org: cleaned up commit message] Signed-off-by: Paul Walmsley Signed-off-by: Sasha Levin --- arch/riscv/mm/init.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index d85efe74a4b69..ee40ca01ac663 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -852,6 +852,27 @@ static void __init set_mmap_rnd_bits_max(void) mmap_rnd_bits_max = MMAP_VA_BITS - PAGE_SHIFT - 3; } +static bool __init is_vaddr_valid(unsigned long va) +{ + unsigned long up = 0; + + switch (satp_mode) { + case SATP_MODE_39: + up = 1UL << 38; + break; + case SATP_MODE_48: + up = 1UL << 47; + break; + case SATP_MODE_57: + up = 1UL << 56; + break; + default: + return false; + } + + return (va < up) || (va >= (ULONG_MAX - up + 1)); +} + /* * There is a simple way to determine if 4-level is supported by the * underlying hardware: establish 1:1 mapping in 4-level page table mode @@ -893,6 +914,9 @@ static __init void set_satp_mode(uintptr_t dtb_pa) set_satp_mode_pmd + PMD_SIZE, PMD_SIZE, PAGE_KERNEL_EXEC); retry: + if (!is_vaddr_valid(set_satp_mode_pmd)) + goto out; + create_pgd_mapping(early_pg_dir, set_satp_mode_pmd, pgtable_l5_enabled ? @@ -915,6 +939,7 @@ static __init void set_satp_mode(uintptr_t dtb_pa) disable_pgtable_l4(); } +out: memset(early_pg_dir, 0, PAGE_SIZE); memset(early_p4d, 0, PAGE_SIZE); memset(early_pud, 0, PAGE_SIZE); From 91e4446b35f657915db0a6623aeeb0ea4c27a1f0 Mon Sep 17 00:00:00 2001 From: David Gow Date: Sat, 25 Apr 2026 11:41:53 +0800 Subject: [PATCH 1324/1518] kunit: config: Enable KUNIT_DEBUGFS by default [ Upstream commit 17e4c68ff35090d8cb743e3c82c09f92fda1ebda ] The KUNIT_DEBUGFS option is currently enabled based on the value of KUNIT_ALL_TESTS, but it really doesn't have anything to do with the set of enabled tests, so just enable it by default anyway. In particular, this shouldn't be only visible if KUNIT_ALL_TESTS is set, which is quite confusing. Link: https://lore.kernel.org/r/20260425034155.53913-1-david@davidgow.net Fixes: beaed42c427d ("kunit: default KUNIT_* fragments to KUNIT_ALL_TESTS") Signed-off-by: David Gow Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- lib/kunit/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 7a6af361d2fc6..2b9fd107a69fe 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -16,8 +16,8 @@ menuconfig KUNIT if KUNIT config KUNIT_DEBUGFS - bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" if !KUNIT_ALL_TESTS - default KUNIT_ALL_TESTS + bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" + default y help Enable debugfs representation for kunit. Currently this consists of /sys/kernel/debug/kunit//results files for each From 3f4d827800017ed5244b8cd1b9d0f8217e1417ff Mon Sep 17 00:00:00 2001 From: David Gow Date: Sat, 25 Apr 2026 11:41:54 +0800 Subject: [PATCH 1325/1518] kunit: config: KUNIT_DEBUGFS should depend on DEBUG_FS [ Upstream commit 8f80b5b227ef9ea422080487715c841856339aed ] CONFIG_KUNIT_DEBUGFS is totally useless without debugfs, so it should depend on CONFIG_DEBUG_FS. Link: https://lore.kernel.org/r/20260425034155.53913-2-david@davidgow.net Fixes: e2219db280e3 ("kunit: add debugfs /sys/kernel/debug/kunit//results display") Signed-off-by: David Gow Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- lib/kunit/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 2b9fd107a69fe..889380c2702c3 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -17,6 +17,7 @@ if KUNIT config KUNIT_DEBUGFS bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" + depends on DEBUG_FS default y help Enable debugfs representation for kunit. Currently this consists From fd2b01637e56d1098ab0dc9a2f0f64090e4a6e25 Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Tue, 28 Apr 2026 17:44:58 +0530 Subject: [PATCH 1326/1518] pinctrl: qcom: Fix wakeirq map by removing disconnected irqs for sm8150 [ Upstream commit 52ac35b8a151446481496404af3a8e5e889b3c5a ] PDC interrupts 122-125 were meant for ibi_i3c wakeup but sm8150 do not support i3c. GPIOs 39,51,88 and 144 are also connected to different PDC pin and already reflected in the wake irq map. Remove the unsupported wakeup interrupts from the map. Fixes: 90337380c809 ("pinctrl: qcom: sm8150: Specify PDC map") Reviewed-by: Konrad Dybcio Signed-off-by: Maulik Shah Signed-off-by: Navya Malempati Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/qcom/pinctrl-sm8150.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-sm8150.c b/drivers/pinctrl/qcom/pinctrl-sm8150.c index ad861cd66958c..e4c561a9c50ae 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8150.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8150.c @@ -1496,18 +1496,18 @@ static const struct msm_gpio_wakeirq_map sm8150_pdc_map[] = { { 3, 31 }, { 5, 32 }, { 8, 33 }, { 9, 34 }, { 10, 100 }, { 12, 104 }, { 24, 37 }, { 26, 38 }, { 27, 41 }, { 28, 42 }, { 30, 39 }, { 36, 43 }, { 37, 44 }, { 38, 30 }, { 39, 118 }, - { 39, 125 }, { 41, 47 }, { 42, 48 }, { 46, 50 }, { 47, 49 }, - { 48, 51 }, { 49, 53 }, { 50, 52 }, { 51, 116 }, { 51, 123 }, + { 41, 47 }, { 42, 48 }, { 46, 50 }, { 47, 49 }, + { 48, 51 }, { 49, 53 }, { 50, 52 }, { 51, 116 }, { 53, 54 }, { 54, 55 }, { 55, 56 }, { 56, 57 }, { 58, 58 }, { 60, 60 }, { 61, 61 }, { 68, 62 }, { 70, 63 }, { 76, 71 }, { 77, 66 }, { 81, 64 }, { 83, 65 }, { 86, 67 }, { 87, 84 }, - { 88, 117 }, { 88, 124 }, { 90, 69 }, { 91, 70 }, { 93, 75 }, + { 88, 117 }, { 90, 69 }, { 91, 70 }, { 93, 75 }, { 95, 72 }, { 96, 73 }, { 97, 74 }, { 101, 40 }, { 103, 77 }, { 104, 78 }, { 108, 79 }, { 112, 80 }, { 113, 81 }, { 114, 82 }, { 117, 85 }, { 118, 101 }, { 119, 87 }, { 120, 88 }, { 121, 89 }, { 122, 90 }, { 123, 91 }, { 124, 92 }, { 125, 93 }, { 129, 94 }, { 132, 105 }, { 133, 83 }, { 134, 36 }, { 136, 97 }, { 142, 103 }, - { 144, 115 }, { 144, 122 }, { 147, 102 }, { 150, 107 }, + { 144, 115 }, { 147, 102 }, { 150, 107 }, { 152, 108 }, { 153, 109 } }; From f39bc7ebe75e2186b417a024a7f7e2fd4cc7eb95 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:30 +0100 Subject: [PATCH 1327/1518] firmware: arm_ffa: Bound PARTITION_INFO_GET_REGS copies [ Upstream commit 3974ea1938406f9bfa7c1f48d4e43533f447bb08 ] The register-based PARTITION_INFO_GET path trusted the firmware-provided indices when copying partition descriptors into the caller buffer. Reject inconsistent counts or index progressions so the copy loop cannot write past the allocated array. Fixes: ba85c644ac8d ("firmware: arm_ffa: Add support for FFA_PARTITION_INFO_GET_REGS") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-6-8595ae450034@kernel.org (fixed cur_idx when exactly one descriptor in the first fragment) Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 287db85286106..e597a9cf64dc9 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -319,6 +319,12 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, #define PART_INFO_ID_MASK GENMASK(15, 0) #define PART_INFO_EXEC_CXT_MASK GENMASK(31, 16) #define PART_INFO_PROPS_MASK GENMASK(63, 32) +#define FFA_PART_INFO_GET_REGS_FIRST_REG 3 +#define FFA_PART_INFO_GET_REGS_REGS_PER_DESC 3 +#define FFA_PART_INFO_GET_REGS_MAX_DESC \ + (((sizeof(ffa_value_t) / sizeof_field(ffa_value_t, a0)) - \ + FFA_PART_INFO_GET_REGS_FIRST_REG) / \ + FFA_PART_INFO_GET_REGS_REGS_PER_DESC) #define PART_INFO_ID(x) ((u16)(FIELD_GET(PART_INFO_ID_MASK, (x)))) #define PART_INFO_EXEC_CXT(x) ((u16)(FIELD_GET(PART_INFO_EXEC_CXT_MASK, (x)))) #define PART_INFO_PROPERTIES(x) ((u32)(FIELD_GET(PART_INFO_PROPS_MASK, (x)))) @@ -326,15 +332,13 @@ static int __ffa_partition_info_get_regs(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, struct ffa_partition_info *buffer, int num_parts) { - u16 buf_sz, start_idx, cur_idx, count = 0, prev_idx = 0, tag = 0; + u16 buf_sz, start_idx = 0, cur_idx, count = 0, tag = 0; struct ffa_partition_info *buf = buffer; ffa_value_t partition_info; do { __le64 *regs; - int idx; - - start_idx = prev_idx ? prev_idx + 1 : 0; + int idx, nr_desc, buf_idx; invoke_ffa_fn((ffa_value_t){ .a0 = FFA_PARTITION_INFO_GET_REGS, @@ -350,15 +354,28 @@ __ffa_partition_info_get_regs(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, count = PARTITION_COUNT(partition_info.a2); if (!buffer || !num_parts) /* count only */ return count; + if (count > num_parts) + return -EINVAL; cur_idx = CURRENT_INDEX(partition_info.a2); + if (cur_idx < start_idx || cur_idx >= count) + return -EINVAL; + + nr_desc = cur_idx - start_idx + 1; + if (nr_desc > FFA_PART_INFO_GET_REGS_MAX_DESC) + return -EINVAL; + + buf_idx = buf - buffer; + if (buf_idx + nr_desc > num_parts) + return -EINVAL; + tag = UUID_INFO_TAG(partition_info.a2); buf_sz = PARTITION_INFO_SZ(partition_info.a2); if (buf_sz > sizeof(*buffer)) buf_sz = sizeof(*buffer); regs = (void *)&partition_info.a3; - for (idx = 0; idx < cur_idx - start_idx + 1; idx++, buf++) { + for (idx = 0; idx < nr_desc; idx++, buf++) { union { uuid_t uuid; u64 regs[2]; @@ -376,7 +393,7 @@ __ffa_partition_info_get_regs(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, uuid_copy(&buf->uuid, &uuid_regs.uuid); regs += 3; } - prev_idx = cur_idx; + start_idx = cur_idx + 1; } while (cur_idx < (count - 1)); From 0a5dbac5ef53a8f953164e1da471b698de3d1bb0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:31 +0100 Subject: [PATCH 1328/1518] firmware: arm_ffa: Keep framework RX release under lock [ Upstream commit 2af18f8e36b277730527cacc2256b1332f56aa28 ] The framework notification handler drops rx_lock before issuing FFA_RX_RELEASE, leaving a window where another RX-buffer user can start a new FF-A transaction before ownership has actually been returned to firmware. Move the FFA_RX_RELEASE calls so they execute while rx_lock is still held on both the kmemdup() failure path and the normal success path. While doing that, switch the handler to scoped_guard() to keep the critical section explicit. Fixes: 285a5ea0f542 ("firmware: arm_ffa: Add support for handling framework notifications") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-7-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index e597a9cf64dc9..c6a9bf3497cf7 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1488,25 +1488,22 @@ static void handle_fwk_notif_callbacks(u32 bitmap) if (!(bitmap & FRAMEWORK_NOTIFY_RX_BUFFER_FULL)) return; - mutex_lock(&drv_info->rx_lock); + scoped_guard(mutex, &drv_info->rx_lock) { + msg = drv_info->rx_buffer; + buf = kmemdup((void *)msg + msg->offset, msg->size, GFP_KERNEL); + if (!buf) { + ffa_rx_release(); + return; + } - msg = drv_info->rx_buffer; - buf = kmemdup((void *)msg + msg->offset, msg->size, GFP_KERNEL); - if (!buf) { - mutex_unlock(&drv_info->rx_lock); - return; + target = SENDER_ID(msg->send_recv_id); + if (msg->offset >= sizeof(*msg)) + uuid_copy(&uuid, &msg->uuid); + else + uuid_copy(&uuid, &uuid_null); + ffa_rx_release(); } - target = SENDER_ID(msg->send_recv_id); - if (msg->offset >= sizeof(*msg)) - uuid_copy(&uuid, &msg->uuid); - else - uuid_copy(&uuid, &uuid_null); - - mutex_unlock(&drv_info->rx_lock); - - ffa_rx_release(); - read_lock(&drv_info->notify_lock); cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, &uuid); read_unlock(&drv_info->notify_lock); From 3c51d99449dc5a01c08a7fce6071d6721f5aac83 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:32 +0100 Subject: [PATCH 1329/1518] firmware: arm_ffa: Validate framework notification message layout [ Upstream commit 4a1cc9e96b311d2609a6f963a5e35bd4ae730d97 ] Framework notifications carry an indirect message in the shared RX buffer. Validate the reported offset and size before using them, reject zero-length payloads, and ensure that any non-header payload starts at the UUID field rather than in the middle of the message header. Use the validated offset and size values for both kmemdup() and the UUID parsing path so malformed firmware data cannot drive an out-of-bounds read or an oversized allocation. Fixes: 285a5ea0f542 ("firmware: arm_ffa: Add support for handling framework notifications") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-8-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index c6a9bf3497cf7..f96bb84af55e3 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1483,21 +1483,35 @@ static void handle_fwk_notif_callbacks(u32 bitmap) int notify_id = 0, target; struct ffa_indirect_msg_hdr *msg; struct notifier_cb_info *cb_info = NULL; + size_t min_offset = offsetof(struct ffa_indirect_msg_hdr, uuid); /* Only one framework notification defined and supported for now */ if (!(bitmap & FRAMEWORK_NOTIFY_RX_BUFFER_FULL)) return; scoped_guard(mutex, &drv_info->rx_lock) { + u32 offset, size; + msg = drv_info->rx_buffer; - buf = kmemdup((void *)msg + msg->offset, msg->size, GFP_KERNEL); + offset = msg->offset; + size = msg->size; + + if (!size || (offset != min_offset && offset < sizeof(*msg)) || + offset > drv_info->rxtx_bufsz || + size > drv_info->rxtx_bufsz - offset) { + pr_err("invalid framework notification message\n"); + ffa_rx_release(); + return; + } + + buf = kmemdup((void *)msg + offset, size, GFP_KERNEL); if (!buf) { ffa_rx_release(); return; } target = SENDER_ID(msg->send_recv_id); - if (msg->offset >= sizeof(*msg)) + if (offset >= sizeof(*msg)) uuid_copy(&uuid, &msg->uuid); else uuid_copy(&uuid, &uuid_null); From 419cef661ae86a591c6c5d8534b2909706399824 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:33 +0100 Subject: [PATCH 1330/1518] firmware: arm_ffa: Align RxTx buffer size before mapping [ Upstream commit 0399e3f872ca3d78044bb715a73ea645806d2c7b ] Commit 83210251fd70 ("firmware: arm_ffa: Use the correct buffer size during RXTX_MAP") advertises PAGE_ALIGN(rxtx_bufsz) to firmware when mapping the buffers but the driver continues to stores the minimum FF-A buffer size in drv_info->rxtx_bufsz which is used elsewhere in the driver. Align the size before storing it so that the allocation, validation and FFA_RXTX_MAP all use the same buffer size. Fixes: 83210251fd70 ("firmware: arm_ffa: Use the correct buffer size during RXTX_MAP") Cc: Sebastian Ene Link: https://sashiko.dev/#/patchset/20260402113939.930221-1-sebastianene@google.com Reviewed-by: Sebastian Ene Link: https://patch.msgid.link/20260428-ffa_fixes-v2-9-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index f96bb84af55e3..70f34f58f3832 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -2102,6 +2102,7 @@ static int __init ffa_init(void) rxtx_bufsz = SZ_4K; } + rxtx_bufsz = PAGE_ALIGN(rxtx_bufsz); drv_info->rxtx_bufsz = rxtx_bufsz; drv_info->rx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); if (!drv_info->rx_buffer) { @@ -2117,7 +2118,7 @@ static int __init ffa_init(void) ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), virt_to_phys(drv_info->rx_buffer), - PAGE_ALIGN(rxtx_bufsz) / FFA_PAGE_SIZE); + rxtx_bufsz / FFA_PAGE_SIZE); if (ret) { pr_err("failed to register FFA RxTx buffers\n"); goto free_pages; From d1e38551fadea230649bc428f0f35c9ee062a072 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:34 +0100 Subject: [PATCH 1331/1518] firmware: arm_ffa: Snapshot notifier callbacks under lock [ Upstream commit 38290b180a4d5746baed796d49f88d56d2f336cd ] Both notification handlers currently look up a notifier callback under notify_lock, drop the lock, and then dereference the returned notifier entry. A concurrent unregister can delete and free that entry in the gap, leaving the handler to dereference stale memory. Copy the callback pointer and callback data while notify_lock is still held and invoke the callback only after the lock is dropped. This keeps the existing callback execution model while removing the use-after-free window in both the framework and non-framework notification paths. Fixes: 285a5ea0f542 ("firmware: arm_ffa: Add support for handling framework notifications") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-10-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 35 ++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 70f34f58f3832..f518c87031022 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1459,20 +1459,25 @@ static int ffa_notify_send(struct ffa_device *dev, int notify_id, static void handle_notif_callbacks(u64 bitmap, enum notify_type type) { + ffa_notifier_cb cb; + void *cb_data; int notify_id; - struct notifier_cb_info *cb_info = NULL; for (notify_id = 0; notify_id <= FFA_MAX_NOTIFICATIONS && bitmap; notify_id++, bitmap >>= 1) { if (!(bitmap & 1)) continue; - read_lock(&drv_info->notify_lock); - cb_info = notifier_hnode_get_by_type(notify_id, type); - read_unlock(&drv_info->notify_lock); + scoped_guard(read_lock, &drv_info->notify_lock) { + struct notifier_cb_info *cb_info; + + cb_info = notifier_hnode_get_by_type(notify_id, type); + cb = cb_info ? cb_info->cb : NULL; + cb_data = cb_info ? cb_info->cb_data : NULL; + } - if (cb_info && cb_info->cb) - cb_info->cb(notify_id, cb_info->cb_data); + if (cb) + cb(notify_id, cb_data); } } @@ -1480,9 +1485,10 @@ static void handle_fwk_notif_callbacks(u32 bitmap) { void *buf; uuid_t uuid; + void *fwk_cb_data; int notify_id = 0, target; + ffa_fwk_notifier_cb fwk_cb; struct ffa_indirect_msg_hdr *msg; - struct notifier_cb_info *cb_info = NULL; size_t min_offset = offsetof(struct ffa_indirect_msg_hdr, uuid); /* Only one framework notification defined and supported for now */ @@ -1518,12 +1524,17 @@ static void handle_fwk_notif_callbacks(u32 bitmap) ffa_rx_release(); } - read_lock(&drv_info->notify_lock); - cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, &uuid); - read_unlock(&drv_info->notify_lock); + scoped_guard(read_lock, &drv_info->notify_lock) { + struct notifier_cb_info *cb_info; + + cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, + &uuid); + fwk_cb = cb_info ? cb_info->fwk_cb : NULL; + fwk_cb_data = cb_info ? cb_info->cb_data : NULL; + } - if (cb_info && cb_info->fwk_cb) - cb_info->fwk_cb(notify_id, cb_info->cb_data, buf); + if (fwk_cb) + fwk_cb(notify_id, fwk_cb_data, buf); kfree(buf); } From 9e472874c9541a34ad2f3377177b28d9adb8e2f5 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 28 Apr 2026 19:33:35 +0100 Subject: [PATCH 1332/1518] firmware: arm_ffa: Fix sched-recv callback partition lookup [ Upstream commit a6848a50404eefb6f0b131c21881a2d8d21b31a9 ] ffa_sched_recv_cb_update() used list_for_each_entry_safe() to search for a matching partition and then tested the iterator against NULL. That is not a valid end-of-list check for circular lists and can fall through with an invalid pointer. Use a normal iterator and detect the not-found case correctly before touching the partition state. Fixes: be61da938576 ("firmware: arm_ffa: Allow multiple UUIDs per partition to register SRI callback") Link: https://patch.msgid.link/20260428-ffa_fixes-v2-11-8595ae450034@kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index f518c87031022..827aac08a8e9e 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1203,7 +1203,7 @@ static int ffa_sched_recv_cb_update(struct ffa_device *dev, ffa_sched_recv_cb callback, void *cb_data, bool is_registration) { - struct ffa_dev_part_info *partition = NULL, *tmp; + struct ffa_dev_part_info *partition = NULL; struct list_head *phead; bool cb_valid; @@ -1216,11 +1216,11 @@ ffa_sched_recv_cb_update(struct ffa_device *dev, ffa_sched_recv_cb callback, return -EINVAL; } - list_for_each_entry_safe(partition, tmp, phead, node) + list_for_each_entry(partition, phead, node) if (partition->dev == dev) break; - if (!partition) { + if (&partition->node == phead) { pr_err("%s: No such partition ID 0x%x\n", __func__, dev->vm_id); return -EINVAL; } From e984dc22e2c24dc34d6728e338c82b1ce7862753 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 5 May 2026 21:15:37 +0200 Subject: [PATCH 1333/1518] ARM: integrator: Fix early initialization [ Upstream commit 90d77b30a666049ad24df463f52e5d529c44e8cd ] Starting with commit bdb249fce9ad4 ("ARM: integrator: read counter using syscon/regmap"), intcp_init_early calls syscon_regmap_lookup_by_compatible which in turn calls of_syscon_register. This function allocates memory. Since the memory management code has not been initialized at that time, the call always fails. It either returns -ENOMEM or crashes as follows. Unable to handle kernel NULL pointer dereference at virtual address 0000000c when read [0000000c] *pgd=00000000 Internal error: Oops: 5 [#1] ARM Modules linked in: CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.15.0-rc5-00026-g5fcc9bf84ee5 #1 PREEMPT Hardware name: ARM Integrator/CP (Device Tree) PC is at __kmalloc_cache_noprof+0xec/0x39c LR is at __kmalloc_cache_noprof+0x34/0x39c ... Call trace: __kmalloc_cache_noprof from of_syscon_register+0x7c/0x310 of_syscon_register from device_node_get_regmap+0xa4/0xb0 device_node_get_regmap from intcp_init_early+0xc/0x40 intcp_init_early from start_kernel+0x60/0x688 start_kernel from 0x0 The crash is seen due to a dereferenced pointer which is not supposed to be NULL but is NULL if the memory management subsystem has not been initialized. The crash is not seen with all versions of gcc. Some versions such as gcc 9.x apparently do not dereference the pointer, presumably if tracing is disabled. The problem has been reproduced with gcc 10.x, 11.x, and 13.x. Either case, if the crash is not seen, the call to syscon_regmap_lookup_by_compatible returns -ENOMEM, and sched_clock_register is never called. Fix the problem by moving the early initialization code into the standard machine initialization code. Fixes: bdb249fce9ad4 ("ARM: integrator: read counter using syscon/regmap") Cc: Linus Walleij Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/20250518164118.3859567-1-linux@roeck-us.net Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20260505-integrator-fixes-v1-1-56ab9aac59db@kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/mach-versatile/integrator_cp.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/arch/arm/mach-versatile/integrator_cp.c b/arch/arm/mach-versatile/integrator_cp.c index 2ed4ded56b3fe..03dfb5f720b7b 100644 --- a/arch/arm/mach-versatile/integrator_cp.c +++ b/arch/arm/mach-versatile/integrator_cp.c @@ -86,14 +86,6 @@ static u64 notrace intcp_read_sched_clock(void) return val; } -static void __init intcp_init_early(void) -{ - cm_map = syscon_regmap_lookup_by_compatible("arm,core-module-integrator"); - if (IS_ERR(cm_map)) - return; - sched_clock_register(intcp_read_sched_clock, 32, 24000000); -} - static void __init intcp_init_irq_of(void) { cm_init(); @@ -119,6 +111,10 @@ static void __init intcp_init_of(void) { struct device_node *cpcon; + cm_map = syscon_regmap_lookup_by_compatible("arm,core-module-integrator"); + if (!IS_ERR(cm_map)) + sched_clock_register(intcp_read_sched_clock, 32, 24000000); + cpcon = of_find_matching_node(NULL, intcp_syscon_match); if (!cpcon) return; @@ -138,7 +134,6 @@ static const char * intcp_dt_board_compat[] = { DT_MACHINE_START(INTEGRATOR_CP_DT, "ARM Integrator/CP (Device Tree)") .reserve = integrator_reserve, .map_io = intcp_map_io, - .init_early = intcp_init_early, .init_irq = intcp_init_irq_of, .init_machine = intcp_init_of, .dt_compat = intcp_dt_board_compat, From fecae8b1fb2d3790e19a134fead83cee51189644 Mon Sep 17 00:00:00 2001 From: Shuhao Fu Date: Tue, 28 Apr 2026 16:01:39 +0800 Subject: [PATCH 1334/1518] ALSA: hda: cs35l56: Put ACPI device after setting companion [ Upstream commit aa2fbece1b07954ef26488c800d126a36a8ab93e ] acpi_dev_get_first_match_dev() returns a refcounted ACPI device and callers are expected to balance it with acpi_dev_put(). When no companion is already attached, cs35l56_hda_read_acpi() looks up an ACPI device and sets it with ACPI_COMPANION_SET(), but leaves the lookup reference held. ACPI_COMPANION_SET() does not take ownership of that reference, so drop it with acpi_dev_put() after attaching the companion. Fixes: 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier") Signed-off-by: Shuhao Fu Tested-by: Simon Trimmer Signed-off-by: Takashi Iwai Link: https://patch.msgid.link/20260428080139.GA1649104@chcpu16 Signed-off-by: Sasha Levin --- sound/hda/codecs/side-codecs/cs35l56_hda.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c index 79c15e21d4bcb..1d25fe01066ee 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c @@ -949,6 +949,7 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) return -ENODEV; } ACPI_COMPANION_SET(cs35l56->base.dev, adev); + acpi_dev_put(adev); } /* Initialize things that could be overwritten by a fixup */ From 373f65b448ed4d7ced253724aa36babb808c72ff Mon Sep 17 00:00:00 2001 From: Shuhao Fu Date: Tue, 28 Apr 2026 16:12:38 +0800 Subject: [PATCH 1335/1518] ALSA: hda: cs35l41: Put ACPI device on missing physical node [ Upstream commit fca7401fe37f7abc6e54147ea560f37279231137 ] acpi_dev_get_first_match_dev() returns a refcounted ACPI device and callers must balance it with acpi_dev_put(). cs35l41_hda_read_acpi() stores the returned ACPI device in cs35l41->dacpi. That reference is normally released by the later probe cleanup or the remove path, but the NULL-check on physdev exits before either of those paths can run. Drop the lookup reference before returning -ENODEV. Fixes: c34b04cc6178 ("ALSA: hda: cs35l41: Fix NULL pointer dereference in cs35l41_hda_read_acpi()") Signed-off-by: Shuhao Fu Tested-by: Simon Trimmer Signed-off-by: Takashi Iwai Link: https://patch.msgid.link/20260428081238.GA1659932@chcpu16 Signed-off-by: Sasha Levin --- sound/hda/codecs/side-codecs/cs35l41_hda.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/hda/codecs/side-codecs/cs35l41_hda.c b/sound/hda/codecs/side-codecs/cs35l41_hda.c index 21e00055c0c44..47263c5a021cb 100644 --- a/sound/hda/codecs/side-codecs/cs35l41_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l41_hda.c @@ -1901,8 +1901,10 @@ static int cs35l41_hda_read_acpi(struct cs35l41_hda *cs35l41, const char *hid, i cs35l41->dacpi = adev; physdev = get_device(acpi_get_first_physical_node(adev)); - if (!physdev) + if (!physdev) { + acpi_dev_put(adev); return -ENODEV; + } sub = acpi_get_subsystem_id(ACPI_HANDLE(physdev)); if (IS_ERR(sub)) From c32a7e0e3c73c1c0768556a56bd78de9f7b83780 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 28 Apr 2026 16:58:56 +0100 Subject: [PATCH 1336/1518] btrfs: tracepoints: fix sleep while in atomic context in btrfs_sync_file() [ Upstream commit c73370c677646e86fc4b1780fb07027bdf847375 ] The trace event btrfs_sync_file() is called in an atomic context (all trace events are) and its call to dput(), which is needed due to the call to dget_parent(), can sleep, triggering a kernel splat. This can be reproduced by enabling the trace event and running btrfs/056 from fstests for example. The splat shown in dmesg is the following: [53.919] BUG: sleeping function called from invalid context at fs/dcache.c:970 [53.947] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 32773, name: xfs_io [53.988] preempt_count: 2, expected: 0 [53.967] RCU nest depth: 0, expected: 0 [53.943] Preemption disabled at: [53.944] [<0000000000000000>] 0x0 [54.078] CPU: 0 UID: 0 PID: 32773 Comm: xfs_io Tainted: G W 7.1.0-rc1-btrfs-next-232+ #1 PREEMPT(full) [54.070] Tainted: [W]=WARN [54.071] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [54.072] Call Trace: [54.074] [54.076] dump_stack_lvl+0x56/0x80 [54.079] __might_resched.cold+0xd6/0x10f [54.072] dput.part.0+0x24/0x110 [54.078] trace_event_raw_event_btrfs_sync_file+0x75/0x140 [btrfs] [54.089] btrfs_sync_file+0x1ed/0x530 [btrfs] [54.087] ? __handle_mm_fault+0x8ae/0xed0 [54.089] btrfs_do_write_iter+0x172/0x210 [btrfs] [54.091] vfs_write+0x21f/0x450 [54.094] __x64_sys_pwrite64+0x8d/0xc0 [54.096] ? do_user_addr_fault+0x20c/0x670 [54.099] do_syscall_64+0x60/0xf20 [54.092] ? clear_bhb_loop+0x60/0xb0 [54.094] entry_SYSCALL_64_after_hwframe+0x76/0x7e So stop using dget_parent() and dput() and access the parent dentry directly as dentry->d_parent. This is also what ext4 is doing in its equivalent trace event ext4_sync_file_enter(). Fixes: a85b46db143f ("btrfs: tracepoints: get correct superblock from dentry in event btrfs_sync_file()") Reviewed-by: Boris Burkov Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- include/trace/events/btrfs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 0864700f76e0a..fa090a455037a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -771,10 +771,8 @@ TRACE_EVENT(btrfs_sync_file, TP_fast_assign( struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); - struct dentry *parent = dget_parent(dentry); - struct inode *parent_inode = d_inode(parent); + struct inode *parent_inode = d_inode(dentry->d_parent); - dput(parent); TP_fast_assign_fsid(btrfs_sb(inode->i_sb)); __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->parent = btrfs_ino(BTRFS_I(parent_inode)); From a9b2f73f6ba7c3f92ae483686b9a92797a290071 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 May 2026 12:07:16 +0200 Subject: [PATCH 1337/1518] netfilter: x_tables: unregister the templates first [ Upstream commit d338693d778579b676a61346849bebd892427158 ] When the module is going away we need to zap the template first. Else there is a small race window where userspace could instantiate a new table after the pernet exit function has removed the current table. Fixes: fdacd57c79b7 ("netfilter: x_tables: never register tables by default") Reported-by: Tristan Madani Reviewed-by: Tristan Madani Closes: https://lore.kernel.org/netfilter-devel/20260429175613.1459342-1-tristmd@gmail.com/ Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/ipv4/netfilter/arptable_filter.c | 2 +- net/ipv4/netfilter/iptable_filter.c | 2 +- net/ipv4/netfilter/iptable_mangle.c | 2 +- net/ipv4/netfilter/iptable_raw.c | 2 +- net/ipv4/netfilter/iptable_security.c | 2 +- net/ipv6/netfilter/ip6table_filter.c | 2 +- net/ipv6/netfilter/ip6table_mangle.c | 2 +- net/ipv6/netfilter/ip6table_raw.c | 2 +- net/ipv6/netfilter/ip6table_security.c | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 78cd5ee24448f..359d00d74095b 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -82,8 +82,8 @@ static int __init arptable_filter_init(void) static void __exit arptable_filter_fini(void) { - unregister_pernet_subsys(&arptable_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&arptable_filter_net_ops); kfree(arpfilter_ops); } diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 3ab908b747951..595bfb492b1c1 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -101,8 +101,8 @@ static int __init iptable_filter_init(void) static void __exit iptable_filter_fini(void) { - unregister_pernet_subsys(&iptable_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&iptable_filter_net_ops); kfree(filter_ops); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 385d945d8ebea..db90db7057cc4 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -135,8 +135,8 @@ static int __init iptable_mangle_init(void) static void __exit iptable_mangle_fini(void) { - unregister_pernet_subsys(&iptable_mangle_net_ops); xt_unregister_template(&packet_mangler); + unregister_pernet_subsys(&iptable_mangle_net_ops); kfree(mangle_ops); } diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 0e7f53964d0af..b46a790917306 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -100,9 +100,9 @@ static int __init iptable_raw_init(void) static void __exit iptable_raw_fini(void) { + xt_unregister_template(&packet_raw); unregister_pernet_subsys(&iptable_raw_net_ops); kfree(rawtable_ops); - xt_unregister_template(&packet_raw); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index d885443cb2679..2b89adc1e5751 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -89,9 +89,9 @@ static int __init iptable_security_init(void) static void __exit iptable_security_fini(void) { + xt_unregister_template(&security_table); unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); - xt_unregister_template(&security_table); } module_init(iptable_security_init); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index e8992693e14a0..9dcd4501fe800 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -100,8 +100,8 @@ static int __init ip6table_filter_init(void) static void __exit ip6table_filter_fini(void) { - unregister_pernet_subsys(&ip6table_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&ip6table_filter_net_ops); kfree(filter_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 8dd4cd0c47bd4..ce2cbce9e3ed3 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -128,8 +128,8 @@ static int __init ip6table_mangle_init(void) static void __exit ip6table_mangle_fini(void) { - unregister_pernet_subsys(&ip6table_mangle_net_ops); xt_unregister_template(&packet_mangler); + unregister_pernet_subsys(&ip6table_mangle_net_ops); kfree(mangle_ops); } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index fc9f6754028f2..8af0f8bd036dc 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -98,8 +98,8 @@ static int __init ip6table_raw_init(void) static void __exit ip6table_raw_fini(void) { - unregister_pernet_subsys(&ip6table_raw_net_ops); xt_unregister_template(&packet_raw); + unregister_pernet_subsys(&ip6table_raw_net_ops); kfree(rawtable_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 4df14a9bae782..66018b169b010 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -88,8 +88,8 @@ static int __init ip6table_security_init(void) static void __exit ip6table_security_fini(void) { - unregister_pernet_subsys(&ip6table_security_net_ops); xt_unregister_template(&security_table); + unregister_pernet_subsys(&ip6table_security_net_ops); kfree(sectbl_ops); } From 89ebafe7910d51c745185f55ed663f38b8e43d89 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 May 2026 12:07:15 +0200 Subject: [PATCH 1338/1518] netfilter: x_tables: add and use xt_unregister_table_pre_exit [ Upstream commit 527d6931473b75d90e38942aae6537d1a527f1fd ] Remove the copypasted variants of _pre_exit and add one single function in the xtables core. ebtables is not compatible with x_tables and therefore unchanged. This is a preparation patch to reduce noise in the followup bug fixes. Reviewed-by: Tristan Madani Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Stable-dep-of: b4597d5fd7d2 ("netfilter: x_tables: add and use xtables_unregister_table_exit") Signed-off-by: Sasha Levin --- include/linux/netfilter/x_tables.h | 1 + include/linux/netfilter_arp/arp_tables.h | 1 - include/linux/netfilter_ipv4/ip_tables.h | 1 - include/linux/netfilter_ipv6/ip6_tables.h | 1 - net/ipv4/netfilter/arp_tables.c | 9 ------- net/ipv4/netfilter/arptable_filter.c | 2 +- net/ipv4/netfilter/ip_tables.c | 9 ------- net/ipv4/netfilter/iptable_filter.c | 2 +- net/ipv4/netfilter/iptable_mangle.c | 2 +- net/ipv4/netfilter/iptable_nat.c | 1 + net/ipv4/netfilter/iptable_raw.c | 2 +- net/ipv4/netfilter/iptable_security.c | 2 +- net/ipv6/netfilter/ip6_tables.c | 9 ------- net/ipv6/netfilter/ip6table_filter.c | 2 +- net/ipv6/netfilter/ip6table_mangle.c | 2 +- net/ipv6/netfilter/ip6table_nat.c | 1 + net/ipv6/netfilter/ip6table_raw.c | 2 +- net/ipv6/netfilter/ip6table_security.c | 2 +- net/netfilter/x_tables.c | 29 +++++++++++++++++++++++ 19 files changed, 41 insertions(+), 39 deletions(-) diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 77c778d84d4cb..f7916fd0e8073 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -300,6 +300,7 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); void *xt_unregister_table(struct xt_table *table); +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index a40aaf645fa47..05631a25e6229 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); -void arpt_unregister_table_pre_exit(struct net *net, const char *name); extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 132b0e4a6d4df..13593391d6058 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -26,7 +26,6 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops); -void ipt_unregister_table_pre_exit(struct net *net, const char *name); void ipt_unregister_table_exit(struct net *net, const char *name); /* Standard entry. */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8b8885a73c764..c6d5b927830dd 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -27,7 +27,6 @@ extern void *ip6t_alloc_initial_table(const struct xt_table *); int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops); -void ip6t_unregister_table_pre_exit(struct net *net, const char *name); void ip6t_unregister_table_exit(struct net *net, const char *name); extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 97ead883e4a13..d19fce8589809 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1581,15 +1581,6 @@ int arpt_register_table(struct net *net, return ret; } -void arpt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); -} -EXPORT_SYMBOL(arpt_unregister_table_pre_exit); - void arpt_unregister_table(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 359d00d74095b..382345567a600 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -43,7 +43,7 @@ static int arptable_filter_table_init(struct net *net) static void __net_exit arptable_filter_net_pre_exit(struct net *net) { - arpt_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_ARP, "filter"); } static void __net_exit arptable_filter_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 23c8deff8095a..663868cc5f6d6 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1789,14 +1789,6 @@ int ipt_register_table(struct net *net, const struct xt_table *table, return ret; } -void ipt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); -} - void ipt_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); @@ -1887,7 +1879,6 @@ static void __exit ip_tables_fini(void) } EXPORT_SYMBOL(ipt_register_table); -EXPORT_SYMBOL(ipt_unregister_table_pre_exit); EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 595bfb492b1c1..0dea754a91209 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -61,7 +61,7 @@ static int __net_init iptable_filter_net_init(struct net *net) static void __net_exit iptable_filter_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "filter"); } static void __net_exit iptable_filter_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index db90db7057cc4..4d3b124923080 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -96,7 +96,7 @@ static int iptable_mangle_table_init(struct net *net) static void __net_exit iptable_mangle_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "mangle"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "mangle"); } static void __net_exit iptable_mangle_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 625a1ca13b1ba..8fc4912e790d8 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -129,6 +129,7 @@ static int iptable_nat_table_init(struct net *net) static void __net_exit iptable_nat_net_pre_exit(struct net *net) { ipt_nat_unregister_lookups(net); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); } static void __net_exit iptable_nat_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index b46a790917306..6f7afec7954bd 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -53,7 +53,7 @@ static int iptable_raw_table_init(struct net *net) static void __net_exit iptable_raw_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "raw"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "raw"); } static void __net_exit iptable_raw_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 2b89adc1e5751..81175c20ccbe8 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -50,7 +50,7 @@ static int iptable_security_table_init(struct net *net) static void __net_exit iptable_security_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "security"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "security"); } static void __net_exit iptable_security_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index d585ac3c11133..08abf0df04500 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1795,14 +1795,6 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, return ret; } -void ip6t_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); -} - void ip6t_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); @@ -1894,7 +1886,6 @@ static void __exit ip6_tables_fini(void) } EXPORT_SYMBOL(ip6t_register_table); -EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 9dcd4501fe800..cf561919bde84 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -60,7 +60,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) static void __net_exit ip6table_filter_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "filter"); } static void __net_exit ip6table_filter_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index ce2cbce9e3ed3..1a758f2bc5379 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -89,7 +89,7 @@ static int ip6table_mangle_table_init(struct net *net) static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "mangle"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "mangle"); } static void __net_exit ip6table_mangle_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 5be723232df8f..bb8aa3fc42b45 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -131,6 +131,7 @@ static int ip6table_nat_table_init(struct net *net) static void __net_exit ip6table_nat_net_pre_exit(struct net *net) { ip6t_nat_unregister_lookups(net); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat"); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 8af0f8bd036dc..923455921c1dd 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -52,7 +52,7 @@ static int ip6table_raw_table_init(struct net *net) static void __net_exit ip6table_raw_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "raw"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "raw"); } static void __net_exit ip6table_raw_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 66018b169b010..c44834d93fc79 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -49,7 +49,7 @@ static int ip6table_security_table_init(struct net *net) static void __net_exit ip6table_security_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "security"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "security"); } static void __net_exit ip6table_security_net_exit(struct net *net) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 1ca4fa9d249b8..2d93f189a79b9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1538,6 +1538,35 @@ void *xt_unregister_table(struct xt_table *table) return private; } EXPORT_SYMBOL_GPL(xt_unregister_table); + +/** + * xt_unregister_table_pre_exit - pre-shutdown unregister of a table + * @net: network namespace + * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) + * @name: name of the table to unregister + * + * Unregisters the specified netfilter table from the given network namespace + * and also unregisters the hooks from netfilter core: no new packets will be + * processed. + */ +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) +{ + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *t; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(t, &xt_net->tables[af], list) { + if (strcmp(t->name, name) == 0) { + mutex_unlock(&xt[af].mutex); + + if (t->ops) /* nat table registers with nat core, t->ops is NULL. */ + nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); + return; + } + } + mutex_unlock(&xt[af].mutex); +} +EXPORT_SYMBOL(xt_unregister_table_pre_exit); #endif #ifdef CONFIG_PROC_FS From 86ee5bc9c0f0e652e19f395675a432de11b75514 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 May 2026 12:07:17 +0200 Subject: [PATCH 1339/1518] netfilter: x_tables: add and use xtables_unregister_table_exit [ Upstream commit b4597d5fd7d2f8cebfffd40dffb5e003cc78964c ] Previous change added xtables_unregister_table_pre_exit to detach the table from the packetpath and to unlink it from the active table list. In case of rmmod, userspace that is doing set/getsockopt for this table will not be able to re-instantiate the table: 1. The larval table has been removed already 2. existing instantiated table is no longer on the xt pernet table list. This adds the second stage helper: unlink the table from the dying list, free the hook ops (if any) and do the audit notification. It replaces xt_unregister_table(). Fixes: fdacd57c79b7 ("netfilter: x_tables: never register tables by default") Reported-by: Tristan Madani Reviewed-by: Tristan Madani Closes: https://lore.kernel.org/netfilter-devel/20260429175613.1459342-1-tristmd@gmail.com/ Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/linux/netfilter/x_tables.h | 2 +- net/ipv4/netfilter/arp_tables.c | 9 ++-- net/ipv4/netfilter/ip_tables.c | 9 ++-- net/ipv4/netfilter/iptable_nat.c | 5 +- net/ipv6/netfilter/ip6_tables.c | 9 ++-- net/ipv6/netfilter/ip6table_nat.c | 5 +- net/netfilter/x_tables.c | 81 +++++++++++++++++++++++------- 7 files changed, 83 insertions(+), 37 deletions(-) diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index f7916fd0e8073..3aef60abd362c 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -299,8 +299,8 @@ struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); -void *xt_unregister_table(struct xt_table *table); void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name); +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d19fce8589809..f3dadbc416a3a 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1501,13 +1501,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len static void __arpt_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; + void *loc_cpu_entry; struct arpt_entry *iter; - private = xt_unregister_table(table); - /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) @@ -1515,6 +1513,7 @@ static void __arpt_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int arpt_register_table(struct net *net, @@ -1583,7 +1582,7 @@ int arpt_register_table(struct net *net, void arpt_unregister_table(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_ARP, name); if (table) __arpt_unregister_table(net, table); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 663868cc5f6d6..f4079f0718dea 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1704,12 +1704,10 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) static void __ipt_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; struct ipt_entry *iter; - - private = xt_unregister_table(table); + void *loc_cpu_entry; /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; @@ -1718,6 +1716,7 @@ static void __ipt_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int ipt_register_table(struct net *net, const struct xt_table *table, @@ -1791,7 +1790,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table, void ipt_unregister_table_exit(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV4, name); if (table) __ipt_unregister_table(net, table); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 8fc4912e790d8..a0df725540251 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -119,8 +119,11 @@ static int iptable_nat_table_init(struct net *net) } ret = ipt_nat_register_lookups(net); - if (ret < 0) + if (ret < 0) { + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); + synchronize_rcu(); ipt_unregister_table_exit(net, "nat"); + } kfree(repl); return ret; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 08abf0df04500..dfaea4f6727ed 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1713,12 +1713,10 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; struct ip6t_entry *iter; - - private = xt_unregister_table(table); + void *loc_cpu_entry; /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; @@ -1727,6 +1725,7 @@ static void __ip6t_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int ip6t_register_table(struct net *net, const struct xt_table *table, @@ -1797,7 +1796,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, void ip6t_unregister_table_exit(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index bb8aa3fc42b45..c2394e2c94b56 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -121,8 +121,11 @@ static int ip6table_nat_table_init(struct net *net) } ret = ip6t_nat_register_lookups(net); - if (ret < 0) + if (ret < 0) { + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat"); + synchronize_rcu(); ip6t_unregister_table_exit(net, "nat"); + } kfree(repl); return ret; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 2d93f189a79b9..76fd0999db4a8 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -55,6 +55,9 @@ static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; + + /* stash area used during netns exit */ + struct list_head dead_tables[NFPROTO_NUMPROTO]; }; struct compat_delta { @@ -1522,23 +1525,6 @@ struct xt_table *xt_register_table(struct net *net, } EXPORT_SYMBOL_GPL(xt_register_table); -void *xt_unregister_table(struct xt_table *table) -{ - struct xt_table_info *private; - - mutex_lock(&xt[table->af].mutex); - private = table->private; - list_del(&table->list); - mutex_unlock(&xt[table->af].mutex); - audit_log_nfcfg(table->name, table->af, private->number, - AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); - kfree(table->ops); - kfree(table); - - return private; -} -EXPORT_SYMBOL_GPL(xt_unregister_table); - /** * xt_unregister_table_pre_exit - pre-shutdown unregister of a table * @net: network namespace @@ -1548,6 +1534,14 @@ EXPORT_SYMBOL_GPL(xt_unregister_table); * Unregisters the specified netfilter table from the given network namespace * and also unregisters the hooks from netfilter core: no new packets will be * processed. + * + * This must be called prior to xt_unregister_table_exit() from the pernet + * .pre_exit callback. After this call, the table is no longer visible to + * the get/setsockopt path. In case of rmmod, module exit path must have + * called xt_unregister_template() prior to unregistering pernet ops to + * prevent re-instantiation of the table. + * + * See also: xt_unregister_table_exit() */ void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) { @@ -1557,6 +1551,7 @@ void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) { if (strcmp(t->name, name) == 0) { + list_move(&t->list, &xt_net->dead_tables[af]); mutex_unlock(&xt[af].mutex); if (t->ops) /* nat table registers with nat core, t->ops is NULL. */ @@ -1567,6 +1562,50 @@ void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_table_pre_exit); + +/** + * xt_unregister_table_exit - remove a table during namespace teardown + * @net: the network namespace from which to unregister the table + * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) + * @name: name of the table to unregister + * + * Completes the unregister process for a table. This must be called from + * the pernet ops .exit callback. This is the second stage after + * xt_unregister_table_pre_exit(). + * + * pair with xt_unregister_table_pre_exit() during namespace shutdown. + * + * Return: the unregistered table or NULL if the table was never + * instantiated. The caller needs to kfree() the table after it + * has removed the family specific matches/targets. + */ +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name) +{ + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *table; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(table, &xt_net->dead_tables[af], list) { + struct nf_hook_ops *ops = NULL; + + if (strcmp(table->name, name) != 0) + continue; + + list_del(&table->list); + + audit_log_nfcfg(table->name, table->af, table->private->number, + AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + swap(table->ops, ops); + mutex_unlock(&xt[af].mutex); + + kfree(ops); + return table; + } + mutex_unlock(&xt[af].mutex); + + return NULL; +} +EXPORT_SYMBOL_GPL(xt_unregister_table_exit); #endif #ifdef CONFIG_PROC_FS @@ -2013,8 +2052,10 @@ static int __net_init xt_net_init(struct net *net) struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) { INIT_LIST_HEAD(&xt_net->tables[i]); + INIT_LIST_HEAD(&xt_net->dead_tables[i]); + } return 0; } @@ -2023,8 +2064,10 @@ static void __net_exit xt_net_exit(struct net *net) struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) { WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); + WARN_ON_ONCE(!list_empty(&xt_net->dead_tables[i])); + } } static struct pernet_operations xt_net_ops = { From 739d5dac7b2da44a756aa4d758ee3f1ccf5a27f1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 May 2026 12:07:18 +0200 Subject: [PATCH 1340/1518] netfilter: ebtables: move to two-stage removal scheme [ Upstream commit b7f0544d86d439cb946515d2ef6a0a75e8626710 ] Like previous patches for x_tables, follow same pattern in ebtables. We can't reuse xt helpers: ebt_table struct layout is incompatible. table->ops assignment is now done while still holding the ebt mutex to make sure we never expose partially-filled table struct. Fixes: 87663c39f898 ("netfilter: ebtables: do not hook tables by default") Reviewed-by: Tristan Madani Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/bridge/netfilter/ebtable_broute.c | 2 +- net/bridge/netfilter/ebtable_filter.c | 2 +- net/bridge/netfilter/ebtable_nat.c | 2 +- net/bridge/netfilter/ebtables.c | 60 +++++++++++++++++---------- 4 files changed, 40 insertions(+), 26 deletions(-) diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 7413602195525..e6f9e343b41f1 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -128,8 +128,8 @@ static int __init ebtable_broute_init(void) static void __exit ebtable_broute_fini(void) { - unregister_pernet_subsys(&broute_net_ops); ebt_unregister_template(&broute_table); + unregister_pernet_subsys(&broute_net_ops); } module_init(ebtable_broute_init); diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index dacd81b12e626..02b6501c15a5e 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -109,8 +109,8 @@ static int __init ebtable_filter_init(void) static void __exit ebtable_filter_fini(void) { - unregister_pernet_subsys(&frame_filter_net_ops); ebt_unregister_template(&frame_filter); + unregister_pernet_subsys(&frame_filter_net_ops); } module_init(ebtable_filter_init); diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 0f2a8c6118d42..9985a82555c41 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -109,8 +109,8 @@ static int __init ebtable_nat_init(void) static void __exit ebtable_nat_fini(void) { - unregister_pernet_subsys(&frame_nat_net_ops); ebt_unregister_template(&frame_nat); + unregister_pernet_subsys(&frame_nat_net_ops); } module_init(ebtable_nat_init); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index a04fc17575289..bfaba18f0e6a8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -42,6 +42,7 @@ struct ebt_pernet { struct list_head tables; + struct list_head dead_tables; }; struct ebt_template { @@ -1162,11 +1163,6 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) static void __ebt_unregister_table(struct net *net, struct ebt_table *table) { - mutex_lock(&ebt_mutex); - list_del(&table->list); - mutex_unlock(&ebt_mutex); - audit_log_nfcfg(table->name, AF_BRIDGE, table->private->nentries, - AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size, ebt_cleanup_entry, net, NULL); if (table->private->nentries) @@ -1267,13 +1263,15 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, for (i = 0; i < num_ops; i++) ops[i].priv = table; - list_add(&table->list, &ebt_net->tables); - mutex_unlock(&ebt_mutex); - table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); - if (ret) + if (ret) { + synchronize_rcu(); __ebt_unregister_table(net, table); + } else { + list_add(&table->list, &ebt_net->tables); + } + mutex_unlock(&ebt_mutex); audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries, AUDIT_XT_OP_REGISTER, GFP_KERNEL); @@ -1339,7 +1337,7 @@ void ebt_unregister_template(const struct ebt_table *t) } EXPORT_SYMBOL(ebt_unregister_template); -static struct ebt_table *__ebt_find_table(struct net *net, const char *name) +void ebt_unregister_table_pre_exit(struct net *net, const char *name) { struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); struct ebt_table *t; @@ -1348,30 +1346,36 @@ static struct ebt_table *__ebt_find_table(struct net *net, const char *name) list_for_each_entry(t, &ebt_net->tables, list) { if (strcmp(t->name, name) == 0) { + list_move(&t->list, &ebt_net->dead_tables); mutex_unlock(&ebt_mutex); - return t; + nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); + return; } } mutex_unlock(&ebt_mutex); - return NULL; -} - -void ebt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct ebt_table *table = __ebt_find_table(net, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } EXPORT_SYMBOL(ebt_unregister_table_pre_exit); void ebt_unregister_table(struct net *net, const char *name) { - struct ebt_table *table = __ebt_find_table(net, name); + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + struct ebt_table *t; - if (table) - __ebt_unregister_table(net, table); + mutex_lock(&ebt_mutex); + + list_for_each_entry(t, &ebt_net->dead_tables, list) { + if (strcmp(t->name, name) == 0) { + list_del(&t->list); + audit_log_nfcfg(t->name, AF_BRIDGE, t->private->nentries, + AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + __ebt_unregister_table(net, t); + mutex_unlock(&ebt_mutex); + return; + } + } + + mutex_unlock(&ebt_mutex); } /* userspace just supplied us with counters */ @@ -2556,11 +2560,21 @@ static int __net_init ebt_pernet_init(struct net *net) struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); INIT_LIST_HEAD(&ebt_net->tables); + INIT_LIST_HEAD(&ebt_net->dead_tables); return 0; } +static void __net_exit ebt_pernet_exit(struct net *net) +{ + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + + WARN_ON_ONCE(!list_empty(&ebt_net->tables)); + WARN_ON_ONCE(!list_empty(&ebt_net->dead_tables)); +} + static struct pernet_operations ebt_net_ops = { .init = ebt_pernet_init, + .exit = ebt_pernet_exit, .id = &ebt_pernet_id, .size = sizeof(struct ebt_pernet), }; From cc989ef1c04425fd64d025f9c9df50dc031fc21a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 May 2026 12:07:19 +0200 Subject: [PATCH 1341/1518] netfilter: ebtables: close dangling table module init race [ Upstream commit 92c603fa07bc0d6a17345de3ad7954730b8de44b ] sashiko reported for a related patch: In modules like iptable_raw.c, [..], if register_pernet_subsys() fails, the rollback might call kfree(rawtable_ops) before [..] During this window, could a concurrent userspace process find the globally visible template, trigger table_init(), [..] The table init functions must always register the template last. Otherwise, set/getsockopt can instantiate a table in a namespace while the required pernet ops (contain the destructor) isn't available. This change is also required in x_tables, handled in followup change. Fixes: 87663c39f898 ("netfilter: ebtables: do not hook tables by default") Reviewed-by: Tristan Madani Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/bridge/netfilter/ebtable_broute.c | 12 +++++------- net/bridge/netfilter/ebtable_filter.c | 12 +++++------- net/bridge/netfilter/ebtable_nat.c | 10 ++++------ 3 files changed, 14 insertions(+), 20 deletions(-) diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index e6f9e343b41f1..f05c79f215ea0 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -112,18 +112,16 @@ static struct pernet_operations broute_net_ops = { static int __init ebtable_broute_init(void) { - int ret = ebt_register_template(&broute_table, broute_table_init); + int ret = register_pernet_subsys(&broute_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&broute_net_ops); - if (ret) { - ebt_unregister_template(&broute_table); - return ret; - } + ret = ebt_register_template(&broute_table, broute_table_init); + if (ret) + unregister_pernet_subsys(&broute_net_ops); - return 0; + return ret; } static void __exit ebtable_broute_fini(void) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 02b6501c15a5e..0fc03b07e62ae 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,18 +93,16 @@ static struct pernet_operations frame_filter_net_ops = { static int __init ebtable_filter_init(void) { - int ret = ebt_register_template(&frame_filter, frame_filter_table_init); + int ret = register_pernet_subsys(&frame_filter_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&frame_filter_net_ops); - if (ret) { - ebt_unregister_template(&frame_filter); - return ret; - } + ret = ebt_register_template(&frame_filter, frame_filter_table_init); + if (ret) + unregister_pernet_subsys(&frame_filter_net_ops); - return 0; + return ret; } static void __exit ebtable_filter_fini(void) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 9985a82555c41..8a10375d89099 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -93,16 +93,14 @@ static struct pernet_operations frame_nat_net_ops = { static int __init ebtable_nat_init(void) { - int ret = ebt_register_template(&frame_nat, frame_nat_table_init); + int ret = register_pernet_subsys(&frame_nat_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&frame_nat_net_ops); - if (ret) { - ebt_unregister_template(&frame_nat); - return ret; - } + ret = ebt_register_template(&frame_nat, frame_nat_table_init); + if (ret) + unregister_pernet_subsys(&frame_nat_net_ops); return ret; } From 524b6337277aabb162bc9c3f018e55fc4b8b8882 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 May 2026 12:07:20 +0200 Subject: [PATCH 1342/1518] netfilter: x_tables: close dangling table module init race [ Upstream commit 16bc4b6686b2c112c10e67d6b493adc3607256d3 ] Similar to the previous ebtables patch: template add exposes the table to userspace, we must do this last to rnsure the pernet ops are set up (contain the destructors). Fixes: fdacd57c79b7 ("netfilter: x_tables: never register tables by default") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/ipv4/netfilter/arptable_filter.c | 23 ++++++++++++----------- net/ipv4/netfilter/iptable_filter.c | 23 ++++++++++++----------- net/ipv4/netfilter/iptable_mangle.c | 25 +++++++++++++------------ net/ipv4/netfilter/iptable_raw.c | 22 +++++++++++----------- net/ipv4/netfilter/iptable_security.c | 23 ++++++++++++----------- net/ipv6/netfilter/ip6table_filter.c | 22 +++++++++++----------- net/ipv6/netfilter/ip6table_mangle.c | 23 ++++++++++++----------- net/ipv6/netfilter/ip6table_raw.c | 20 ++++++++++---------- net/ipv6/netfilter/ip6table_security.c | 23 ++++++++++++----------- 9 files changed, 105 insertions(+), 99 deletions(-) diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 382345567a600..370b635e3523b 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -58,25 +58,26 @@ static struct pernet_operations arptable_filter_net_ops = { static int __init arptable_filter_init(void) { - int ret = xt_register_template(&packet_filter, - arptable_filter_table_init); - - if (ret < 0) - return ret; + int ret; arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table); - if (IS_ERR(arpfilter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(arpfilter_ops)) return PTR_ERR(arpfilter_ops); - } ret = register_pernet_subsys(&arptable_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, + arptable_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(arpfilter_ops); - return ret; + unregister_pernet_subsys(&arptable_filter_net_ops); + goto err_free; } + return 0; +err_free: + kfree(arpfilter_ops); return ret; } diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 0dea754a91209..672d7da1071d3 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -77,26 +77,27 @@ static struct pernet_operations iptable_filter_net_ops = { static int __init iptable_filter_init(void) { - int ret = xt_register_template(&packet_filter, - iptable_filter_table_init); - - if (ret < 0) - return ret; + int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table); - if (IS_ERR(filter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); - } ret = register_pernet_subsys(&iptable_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, + iptable_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(filter_ops); - return ret; + unregister_pernet_subsys(&iptable_filter_net_ops); + goto err_free; } return 0; +err_free: + kfree(filter_ops); + return ret; } static void __exit iptable_filter_fini(void) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 4d3b124923080..13d25d9a4610e 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -111,25 +111,26 @@ static struct pernet_operations iptable_mangle_net_ops = { static int __init iptable_mangle_init(void) { - int ret = xt_register_template(&packet_mangler, - iptable_mangle_table_init); - if (ret < 0) - return ret; + int ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); - if (IS_ERR(mangle_ops)) { - xt_unregister_template(&packet_mangler); - ret = PTR_ERR(mangle_ops); - return ret; - } + if (IS_ERR(mangle_ops)) + return PTR_ERR(mangle_ops); ret = register_pernet_subsys(&iptable_mangle_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_mangler, + iptable_mangle_table_init); if (ret < 0) { - xt_unregister_template(&packet_mangler); - kfree(mangle_ops); - return ret; + unregister_pernet_subsys(&iptable_mangle_net_ops); + goto err_free; } + return 0; +err_free: + kfree(mangle_ops); return ret; } diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 6f7afec7954bd..2745c22f4034d 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -77,24 +77,24 @@ static int __init iptable_raw_init(void) pr_info("Enabling raw table before defrag\n"); } - ret = xt_register_template(table, - iptable_raw_table_init); - if (ret < 0) - return ret; - rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table); - if (IS_ERR(rawtable_ops)) { - xt_unregister_template(table); + if (IS_ERR(rawtable_ops)) return PTR_ERR(rawtable_ops); - } ret = register_pernet_subsys(&iptable_raw_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(table, + iptable_raw_table_init); if (ret < 0) { - xt_unregister_template(table); - kfree(rawtable_ops); - return ret; + unregister_pernet_subsys(&iptable_raw_net_ops); + goto err_free; } + return 0; +err_free: + kfree(rawtable_ops); return ret; } diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 81175c20ccbe8..491894511c544 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -65,25 +65,26 @@ static struct pernet_operations iptable_security_net_ops = { static int __init iptable_security_init(void) { - int ret = xt_register_template(&security_table, - iptable_security_table_init); - - if (ret < 0) - return ret; + int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table); - if (IS_ERR(sectbl_ops)) { - xt_unregister_template(&security_table); + if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); - } ret = register_pernet_subsys(&iptable_security_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&security_table, + iptable_security_table_init); if (ret < 0) { - xt_unregister_template(&security_table); - kfree(sectbl_ops); - return ret; + unregister_pernet_subsys(&iptable_security_net_ops); + goto err_free; } + return 0; +err_free: + kfree(sectbl_ops); return ret; } diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index cf561919bde84..b074fc4776764 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -76,25 +76,25 @@ static struct pernet_operations ip6table_filter_net_ops = { static int __init ip6table_filter_init(void) { - int ret = xt_register_template(&packet_filter, - ip6table_filter_table_init); - - if (ret < 0) - return ret; + int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table); - if (IS_ERR(filter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); - } ret = register_pernet_subsys(&ip6table_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, ip6table_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(filter_ops); - return ret; + unregister_pernet_subsys(&ip6table_filter_net_ops); + goto err_free; } + return 0; +err_free: + kfree(filter_ops); return ret; } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 1a758f2bc5379..e6ee036a9b2c5 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -104,25 +104,26 @@ static struct pernet_operations ip6table_mangle_net_ops = { static int __init ip6table_mangle_init(void) { - int ret = xt_register_template(&packet_mangler, - ip6table_mangle_table_init); - - if (ret < 0) - return ret; + int ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) { - xt_unregister_template(&packet_mangler); + if (IS_ERR(mangle_ops)) return PTR_ERR(mangle_ops); - } ret = register_pernet_subsys(&ip6table_mangle_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_mangler, + ip6table_mangle_table_init); if (ret < 0) { - xt_unregister_template(&packet_mangler); - kfree(mangle_ops); - return ret; + unregister_pernet_subsys(&ip6table_mangle_net_ops); + goto err_free; } + return 0; +err_free: + kfree(mangle_ops); return ret; } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 923455921c1dd..3b161ee875bcc 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -75,24 +75,24 @@ static int __init ip6table_raw_init(void) pr_info("Enabling raw table before defrag\n"); } - ret = xt_register_template(table, ip6table_raw_table_init); - if (ret < 0) - return ret; - /* Register hooks */ rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table); - if (IS_ERR(rawtable_ops)) { - xt_unregister_template(table); + if (IS_ERR(rawtable_ops)) return PTR_ERR(rawtable_ops); - } ret = register_pernet_subsys(&ip6table_raw_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(table, ip6table_raw_table_init); if (ret < 0) { - kfree(rawtable_ops); - xt_unregister_template(table); - return ret; + unregister_pernet_subsys(&ip6table_raw_net_ops); + goto err_free; } + return 0; +err_free: + kfree(rawtable_ops); return ret; } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index c44834d93fc79..4bd5d97b8ab65 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -64,25 +64,26 @@ static struct pernet_operations ip6table_security_net_ops = { static int __init ip6table_security_init(void) { - int ret = xt_register_template(&security_table, - ip6table_security_table_init); - - if (ret < 0) - return ret; + int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); - if (IS_ERR(sectbl_ops)) { - xt_unregister_template(&security_table); + if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); - } ret = register_pernet_subsys(&ip6table_security_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&security_table, + ip6table_security_table_init); if (ret < 0) { - kfree(sectbl_ops); - xt_unregister_template(&security_table); - return ret; + unregister_pernet_subsys(&ip6table_security_net_ops); + goto err_free; } + return 0; +err_free: + kfree(sectbl_ops); return ret; } From c647e2a21bbbaceda6cdb8a44a56f44d231dc4b4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 7 May 2026 11:19:22 +0200 Subject: [PATCH 1343/1518] netfilter: bridge: eb_tables: close module init race [ Upstream commit 27414ff1b287ea9a2a11675149ec28e05539f3cc ] sashiko reports for unrelated patch: Does the core ebtables initialization in ebtables.c suffer from a similar race? Once nf_register_sockopt() completes, the sockopts are exposed globally. sockopt has to be registered last, just like in ip/ip6/arptables. Fixes: 5b53951cfc85 ("netfilter: ebtables: use net_generic infra") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/bridge/netfilter/ebtables.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bfaba18f0e6a8..77df9e856c2e7 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2583,19 +2583,20 @@ static int __init ebtables_init(void) { int ret; - ret = xt_register_target(&ebt_standard_target); + ret = register_pernet_subsys(&ebt_net_ops); if (ret < 0) return ret; - ret = nf_register_sockopt(&ebt_sockopts); + + ret = xt_register_target(&ebt_standard_target); if (ret < 0) { - xt_unregister_target(&ebt_standard_target); + unregister_pernet_subsys(&ebt_net_ops); return ret; } - ret = register_pernet_subsys(&ebt_net_ops); + ret = nf_register_sockopt(&ebt_sockopts); if (ret < 0) { - nf_unregister_sockopt(&ebt_sockopts); xt_unregister_target(&ebt_standard_target); + unregister_pernet_subsys(&ebt_net_ops); return ret; } From ae8a5c6b0316ce7b3f7b2c8d13daaf2ffa5be6c7 Mon Sep 17 00:00:00 2001 From: Jianpeng Chang Date: Fri, 8 May 2026 09:56:36 +0900 Subject: [PATCH 1344/1518] kprobes: skip non-symbol addresses in kprobe_add_ksym_blacklist() [ Upstream commit 307abfac04a254c09c5705d816b33354acee97a0 ] When kprobe_add_area_blacklist() iterates through a section like .kprobes.text, the start address may not correspond to a named symbol. On ARM64 with CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS=y (introduced by commit baaf553d3bc3 ("arm64: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS")), the compiler flag -fpatchable-function-entry=4,2 inserts 2 NOPs before each function entry point for ftrace call_ops. These pre-function NOPs sit at the section base address, before the first named function symbol. The compiler emits a $x mapping symbol at offset 0x00 to mark the start of code, but find_kallsyms_symbol() ignores mapping symbols. Without CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS (e.g. defconfig), no pre-function NOPs are inserted, the first function starts at offset 0x00, and the bug does not trigger. This only affects modules that have a .kprobes.text section (i.e. those using the __kprobes annotation). Modules using NOKPROBE_SYMBOL() instead (like kretprobe_example.ko) blacklist exact function addresses via the _kprobe_blacklist section and are not affected. For kprobe_example.ko on ARM64 with -fpatchable-function-entry=4,2, the .kprobes.text section layout is: offset 0x00: $x + 2 NOPs (mapping symbol + ftrace preamble) offset 0x08: handler_post (64 bytes) offset 0x50: handler_pre (68 bytes) kprobe_add_area_blacklist() starts iterating from the section base address (offset 0x00), which only has the $x mapping symbol. kprobe_add_ksym_blacklist() then calls kallsyms_lookup_size_offset() for this address, which goes through: kallsyms_lookup_size_offset() -> module_address_lookup() -> find_kallsyms_symbol() find_kallsyms_symbol() scans all module symbols to find the closest preceding symbol. Since no named text symbol exists at offset 0x00, find_kallsyms_symbol() picks __UNIQUE_ID_vermagic (a .modinfo symbol whose address is in the temporary image) as the "best" match. The computed "size" = next_text_symbol - modinfo_symbol spans across these two unrelated memory regions, creating a blacklist entry with a bogus range of tens of terabytes. Whether this causes a visible failure depends on address randomization, here is what happens on Raspberry Pi 4/5: - On RPi5, the bogus size was ~35 TB. start + size stayed within 64-bit range, so the blacklist entry covered the entire kernel text. register_kprobe() in the module's own init function failed with -EINVAL. - On RPi4, the bogus size was ~75 TB. start + size overflowed 64 bits and wrapped to a small address near zero. The range check (addr >= start && addr < end) then failed because end wrapped around, so the bogus entry was accidentally harmless and kprobes worked by luck. The same bug exists on both machines, but randomization determines whether the integer overflow masks it or not. Fix this by adding notrace to the __kprobes macro. Functions in .kprobes.text are kprobe infrastructure handlers that should never be traced by ftrace. With notrace, the compiler stops inserting them and the non-symbol gap at the section start disappears entirely. Link: https://lore.kernel.org/all/20260506012706.2785785-1-jianpeng.chang.cn@windriver.com/ Fixes: baaf553d3bc3 ("arm64: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS") Signed-off-by: Jianpeng Chang Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin --- include/asm-generic/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h index 060eab094e5a2..5290a2b2e15a0 100644 --- a/include/asm-generic/kprobes.h +++ b/include/asm-generic/kprobes.h @@ -14,7 +14,7 @@ static unsigned long __used \ _kbl_addr_##fname = (unsigned long)fname; # define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname) /* Use this to forbid a kprobes attach on very low level functions */ -# define __kprobes __section(".kprobes.text") +# define __kprobes notrace __section(".kprobes.text") # define nokprobe_inline __always_inline #else # define NOKPROBE_SYMBOL(fname) From 1c24cf1fd67f6702c719ab73499392cb7af956ae Mon Sep 17 00:00:00 2001 From: Martin Kaiser Date: Fri, 8 May 2026 09:56:36 +0900 Subject: [PATCH 1345/1518] test_kprobes: clear kprobes between test runs [ Upstream commit ef5581bb30efb939cc2bf093475c6cc85258e5cd ] Running the kprobes sanity tests twice makes all tests fail and eventually crashes the kernel. [root@martin-riscv-1 ~]# echo 1 > /sys/kernel/debug/kunit/kprobes_test/run ... # Totals: pass:5 fail:0 skip:0 total:5 ok 1 kprobes_test [root@martin-riscv-1 ~]# echo 1 > /sys/kernel/debug/kunit/kprobes_test/run ... # test_kprobe: EXPECTATION FAILED at lib/tests/test_kprobes.c:64 Expected 0 == register_kprobe(&kp), but register_kprobe(&kp) == -22 (0xffffffffffffffea) ... Unable to handle kernel paging request ... The testsuite defines several kprobes and kretprobes as static variables that are preserved across test runs. After register_kprobe and unregister_kprobe, a kprobe contains some leftover data that must be cleared before the kprobe can be registered again. The tests are setting symbol_name to define the probe location. Address and flags must be cleared. The existing code clears some of the probes between subsequent tests, but not between two test runs. The leftover data from a previous test run makes the registrations fail in the next run. Move the cleanups for all kprobes into kprobes_test_init, this function is called before each single test (including the first test of a test run). Link: https://lore.kernel.org/all/20260507134615.1010905-1-martin@kaiser.cx/ Fixes: e44e81c5b90f ("kprobes: convert tests to kunit") Signed-off-by: Martin Kaiser Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin --- lib/tests/test_kprobes.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/lib/tests/test_kprobes.c b/lib/tests/test_kprobes.c index b7582010125c3..06e729e4de051 100644 --- a/lib/tests/test_kprobes.c +++ b/lib/tests/test_kprobes.c @@ -12,6 +12,12 @@ #define div_factor 3 +#define KP_CLEAR(_kp) \ +do { \ + (_kp).addr = NULL; \ + (_kp).flags = 0; \ +} while (0) + static u32 rand1, preh_val, posth_val; static u32 (*target)(u32 value); static u32 (*recursed_target)(u32 value); @@ -125,10 +131,6 @@ static void test_kprobes(struct kunit *test) current_test = test; - /* addr and flags should be cleard for reusing kprobe. */ - kp.addr = NULL; - kp.flags = 0; - KUNIT_EXPECT_EQ(test, 0, register_kprobes(kps, 2)); preh_val = 0; posth_val = 0; @@ -226,9 +228,6 @@ static void test_kretprobes(struct kunit *test) struct kretprobe *rps[2] = {&rp, &rp2}; current_test = test; - /* addr and flags should be cleard for reusing kprobe. */ - rp.kp.addr = NULL; - rp.kp.flags = 0; KUNIT_EXPECT_EQ(test, 0, register_kretprobes(rps, 2)); krph_val = 0; @@ -290,8 +289,6 @@ static void test_stacktrace_on_kretprobe(struct kunit *test) unsigned long myretaddr = (unsigned long)__builtin_return_address(0); current_test = test; - rp3.kp.addr = NULL; - rp3.kp.flags = 0; /* * Run the stacktrace_driver() to record correct return address in @@ -352,8 +349,6 @@ static void test_stacktrace_on_nested_kretprobe(struct kunit *test) struct kretprobe *rps[2] = {&rp3, &rp4}; current_test = test; - rp3.kp.addr = NULL; - rp3.kp.flags = 0; //KUNIT_ASSERT_NE(test, myretaddr, stacktrace_driver()); @@ -367,6 +362,18 @@ static void test_stacktrace_on_nested_kretprobe(struct kunit *test) static int kprobes_test_init(struct kunit *test) { + KP_CLEAR(kp); + KP_CLEAR(kp2); + KP_CLEAR(kp_missed); +#ifdef CONFIG_KRETPROBES + KP_CLEAR(rp.kp); + KP_CLEAR(rp2.kp); +#ifdef CONFIG_ARCH_CORRECT_STACKTRACE_ON_KRETPROBE + KP_CLEAR(rp3.kp); + KP_CLEAR(rp4.kp); +#endif +#endif + target = kprobe_target; target2 = kprobe_target2; recursed_target = kprobe_recursed_target; From 77e7818eb3473f342bf297b30d6eb8d92f3dfe97 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 6 May 2026 03:59:19 +0000 Subject: [PATCH 1346/1518] tcp: Fix imbalanced icsk_accept_queue count. [ Upstream commit 7eca3292cac7c26dad4c236f51ba225c39a0523f ] When TCP socket migration happens in reqsk_timer_handler(), @sk_listener will be updated with the new listener. When we call __inet_csk_reqsk_queue_drop(), the listener must be the one stored in req->rsk_listener. The cited commit accidentally replaced oreq->rsk_listener with sk_listener, leading to imbalanced icsk_accept_queue count. Let's pass the correct listener to __inet_csk_reqsk_queue_drop(). Fixes: e8c526f2bdf1 ("tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().") Reported-by: Damiano Melotti Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260506035954.1563147-3-kuniyu@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/inet_connection_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ed773cd488769..c777895a720ee 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1149,7 +1149,7 @@ static void reqsk_timer_handler(struct timer_list *t) } drop: - __inet_csk_reqsk_queue_drop(sk_listener, oreq, true); + __inet_csk_reqsk_queue_drop(oreq->rsk_listener, oreq, true); reqsk_put(oreq); } From bfe08fe5624b341aa2e23a1be0e3c6d10a9456ac Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Wed, 6 May 2026 09:08:08 +0000 Subject: [PATCH 1347/1518] net: napi: Avoid gro timer misfiring at end of busypoll [ Upstream commit 58e2330bd45572a6e3d46ea94cf7a9641f43591a ] When in irq deferral mode (defer-hard-irqs > 0), a short enough gro-flush timeout can trigger before NAPI_STATE_SCHED is cleared if the last poll in busy_poll_stop() takes too long. This can have the effect of leaving the queue stuck with interrupts disabled and no timer armed which results in a tx timeout if there is no subsequent busypoll cycle. To prevent this, defer the gro-flush timer arm after the last poll. Fixes: 7fd3253a7de6 ("net: Introduce preferred busy-polling") Co-developed-by: Martin Karsten Signed-off-by: Martin Karsten Signed-off-by: Dragos Tatulea Reviewed-by: Tariq Toukan Reviewed-by: Cosmin Ratiu Reviewed-by: Joe Damato Link: https://patch.msgid.link/20260506090808.820559-2-dtatulea@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/dev.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 29f2f35ae5ebe..681d7de89c505 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6777,9 +6777,9 @@ static void skb_defer_free_flush(void) #if defined(CONFIG_NET_RX_BUSY_POLL) -static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) +static void __busy_poll_stop(struct napi_struct *napi, unsigned long timeout) { - if (!skip_schedule) { + if (!timeout) { gro_normal_list(&napi->gro); __napi_schedule(napi); return; @@ -6789,6 +6789,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) gro_flush_normal(&napi->gro, HZ >= 1000); clear_bit(NAPI_STATE_SCHED, &napi->state); + hrtimer_start(&napi->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); } enum { @@ -6800,8 +6802,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; - bool skip_schedule = false; - unsigned long timeout; + unsigned long timeout = 0; int rc; /* Busy polling means there is a high chance device driver hard irq @@ -6821,10 +6822,12 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); - timeout = napi_get_gro_flush_timeout(napi); - if (napi->defer_hard_irqs_count && timeout) { - hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); - skip_schedule = true; + if (napi->defer_hard_irqs_count) { + /* A short enough gro flush timeout and long enough + * poll can result in timer firing too early. + * Timer will be armed later if necessary. + */ + timeout = napi_get_gro_flush_timeout(napi); } } @@ -6839,7 +6842,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) - __busy_poll_stop(napi, skip_schedule); + __busy_poll_stop(napi, timeout); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } From a248793f00ab589d26cdf603ea09487b1533cd17 Mon Sep 17 00:00:00 2001 From: Mohsin Bashir Date: Wed, 6 May 2026 16:37:45 -0700 Subject: [PATCH 1348/1518] net: shaper: Reject reparenting of existing nodes [ Upstream commit a77d5a069d959dc45f5f472d48cba37d8cba0f1c ] When an existing node-scope shaper is moved to a different parent via the group operation, the framework fails to update the leaves count on both the old and new parent shapers. Only newly created nodes (handle.id == NET_SHAPER_ID_UNSPEC) trigger the parent leaves increment at line 1039. This causes the parent's leaves counter to diverge from the actual number of children in the xarray. When the node is later deleted, pre_del_node() allocates an array sized by the stale leaves count, but the xarray iteration finds more children than expected, hitting the WARN_ON_ONCE guard and returning -EINVAL. Rather than adding reparenting support with complex leaves count bookkeeping, reject group calls that attempt to change an existing node's parent. Updates to an existing node's rate or leaves under the same parent remain permitted. We expect that for any modification of the topology user should always create new groups and let the kernel garbage collect the leaf-less nodes. Fixes: 5d5d4700e75d ("net-shapers: implement NL group operation") Signed-off-by: Mohsin Bashir Link: https://patch.msgid.link/20260506233745.111895-1-mohsin.bashr@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index be9999ab62e39..e41a82241230d 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -964,15 +964,22 @@ static int __net_shaper_group(struct net_shaper_binding *binding, int i, ret; if (node->handle.scope == NET_SHAPER_SCOPE_NODE) { + struct net_shaper *cur = NULL; + new_node = node->handle.id == NET_SHAPER_ID_UNSPEC; - if (!new_node && !net_shaper_lookup(binding, &node->handle)) { - /* The related attribute is not available when - * reaching here from the delete() op. - */ - NL_SET_ERR_MSG_FMT(extack, "Node shaper %d:%d does not exists", - node->handle.scope, node->handle.id); - return -ENOENT; + if (!new_node) { + cur = net_shaper_lookup(binding, &node->handle); + if (!cur) { + /* The related attribute is not available + * when reaching here from the delete() op. + */ + NL_SET_ERR_MSG_FMT(extack, + "Node shaper %d:%d does not exist", + node->handle.scope, + node->handle.id); + return -ENOENT; + } } /* When unspecified, the node parent scope is inherited from @@ -986,6 +993,15 @@ static int __net_shaper_group(struct net_shaper_binding *binding, return ret; } + if (cur && net_shaper_handle_cmp(&cur->parent, + &node->parent)) { + NL_SET_ERR_MSG_FMT(extack, + "Cannot reparent node shaper %d:%d", + node->handle.scope, + node->handle.id); + return -EOPNOTSUPP; + } + } else { net_shaper_default_parent(&node->handle, &node->parent); } From eb5991d4c8ba2e8153dfcda3e66a9608377b7dce Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Wed, 6 May 2026 14:48:12 -0700 Subject: [PATCH 1349/1518] idpf: fix read_dev_clk_lock spinlock init in idpf_ptp_init() [ Upstream commit da4f76b6a84ede14a71282ef841768299ead0221 ] In idpf_ptp_init(), read_dev_clk_lock is initialized after ptp_schedule_worker() had already been called (and after idpf_ptp_settime64() could reach the lock). The PTP aux worker fires immediately upon scheduling and can call into idpf_ptp_read_src_clk_reg_direct(), which takes spin_lock(&ptp->read_dev_clk_lock) on an uninitialized lock, triggering the lockdep "non-static key" warning: [12973.796587] idpf 0000:83:00.0: Device HW Reset initiated [12974.094507] INFO: trying to register non-static key. ... [12974.097208] Call Trace: [12974.097213] [12974.097218] dump_stack_lvl+0x93/0xe0 [12974.097234] register_lock_class+0x4c4/0x4e0 [12974.097249] ? __lock_acquire+0x427/0x2290 [12974.097259] __lock_acquire+0x98/0x2290 [12974.097272] lock_acquire+0xc6/0x310 [12974.097281] ? idpf_ptp_read_src_clk_reg+0xb7/0x150 [idpf] [12974.097311] ? lockdep_hardirqs_on_prepare+0xde/0x190 [12974.097318] ? finish_task_switch.isra.0+0xd2/0x350 [12974.097330] ? __pfx_ptp_aux_kworker+0x10/0x10 [ptp] [12974.097343] _raw_spin_lock+0x30/0x40 [12974.097353] ? idpf_ptp_read_src_clk_reg+0xb7/0x150 [idpf] [12974.097373] idpf_ptp_read_src_clk_reg+0xb7/0x150 [idpf] [12974.097391] ? kthread_worker_fn+0x88/0x3d0 [12974.097404] ? kthread_worker_fn+0x4e/0x3d0 [12974.097411] idpf_ptp_update_cached_phctime+0x26/0x120 [idpf] [12974.097428] ? _raw_spin_unlock_irq+0x28/0x50 [12974.097436] idpf_ptp_do_aux_work+0x15/0x20 [idpf] [12974.097454] ptp_aux_kworker+0x20/0x40 [ptp] [12974.097464] kthread_worker_fn+0xd5/0x3d0 [12974.097474] ? __pfx_kthread_worker_fn+0x10/0x10 [12974.097482] kthread+0xf4/0x130 [12974.097489] ? __pfx_kthread+0x10/0x10 [12974.097498] ret_from_fork+0x32c/0x410 [12974.097512] ? __pfx_kthread+0x10/0x10 [12974.097519] ret_from_fork_asm+0x1a/0x30 [12974.097540] Move the call to spin_lock_init() up a bit to make sure read_dev_clk_lock is not touched before it's been initialized. Fixes: 5cb8805d2366 ("idpf: negotiate PTP capabilities and get PTP clock") Signed-off-by: Emil Tantilov Reviewed-by: Madhu Chittim Reviewed-by: Aleksandr Loktionov Reviewed-by: Simon Horman Tested-by: Samuel Salin Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260506-jk-iwl-net-2026-05-04-v2-3-a5ea4dc837a9@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/idpf/idpf_ptp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index 0a8b50350b860..31c5593550e1a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -949,6 +949,8 @@ int idpf_ptp_init(struct idpf_adapter *adapter) goto free_ptp; } + spin_lock_init(&adapter->ptp->read_dev_clk_lock); + err = idpf_ptp_create_clock(adapter); if (err) goto free_ptp; @@ -974,8 +976,6 @@ int idpf_ptp_init(struct idpf_adapter *adapter) goto remove_clock; } - spin_lock_init(&adapter->ptp->read_dev_clk_lock); - pci_dbg(adapter->pdev, "PTP init successful\n"); return 0; From 34ad3c782644710beb3c5548faaf763711d5b975 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Wed, 6 May 2026 14:48:14 -0700 Subject: [PATCH 1350/1518] ice: fix setting RSS VSI hash for E830 [ Upstream commit b3cda96feb60d91fe88d52b974ff110dcfa91239 ] ice_set_rss_hfunc() performs a VSI update, in which it sets hashing function, leaving other VSI options unchanged. However, ::q_opt_flags is mistakenly set to the value of another field, instead of its original value, probably due to a typo. What happens next is hardware-dependent: On E810, only the first bit is meaningful (see ICE_AQ_VSI_Q_OPT_PE_FLTR_EN) and can potentially end up in a different state than before VSI update. On E830, some of the remaining bits are not reserved. Setting them to some unrelated values can cause the firmware to reject the update because of invalid settings, or worse - succeed. Reproducer: sudo ethtool -X $PF1 equal 8 Output in dmesg: Failed to configure RSS hash for VSI 6, error -5 Fixes: 352e9bf23813 ("ice: enable symmetric-xor RSS for Toeplitz hash function") Reviewed-by: Aleksandr Loktionov Reviewed-by: Przemek Kitszel Signed-off-by: Marcin Szycik Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260506-jk-iwl-net-2026-05-04-v2-5-a5ea4dc837a9@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d42b65e29e485..dc5d821bf3348 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8075,7 +8075,7 @@ int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc) ctx->info.q_opt_rss |= FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc); ctx->info.q_opt_tc = vsi->info.q_opt_tc; - ctx->info.q_opt_flags = vsi->info.q_opt_rss; + ctx->info.q_opt_flags = vsi->info.q_opt_flags; err = ice_update_vsi(hw, vsi->idx, ctx, NULL); if (err) { From d91a9a0496986eac19ab142b38938b6ec43310fb Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 6 May 2026 14:48:15 -0700 Subject: [PATCH 1351/1518] ice: fix locking in ice_dcb_rebuild() [ Upstream commit 0ded1f36ba4021cba50513e80be6b6e173710168 ] Move the mutex_lock() call up to prevent that DCB settings change after the first ice_query_port_ets() call. The second ice_query_port_ets() call in ice_dcb_rebuild() is already protected by pf->tc_mutex. This also fixes a bug in an error path, as before taking the first "goto dcb_error" in the function jumped over mutex_lock() to mutex_unlock(). This bug has been detected by the clang thread-safety analyzer. Cc: intel-wired-lan@lists.osuosl.org Fixes: 242b5e068b25 ("ice: Fix DCB rebuild after reset") Signed-off-by: Bart Van Assche Reviewed-by: Aleksandr Loktionov Reviewed-by: Przemek Kitszel Tested-by: Arpana Arland Signed-off-by: Jacob Keller Link: https://patch.msgid.link/20260506-jk-iwl-net-2026-05-04-v2-6-a5ea4dc837a9@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 9fc8681cc58ea..270f5a00ece3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -537,14 +537,14 @@ void ice_dcb_rebuild(struct ice_pf *pf) struct ice_dcbx_cfg *err_cfg; int ret; + mutex_lock(&pf->tc_mutex); + ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { dev_err(dev, "Query Port ETS failed\n"); goto dcb_error; } - mutex_lock(&pf->tc_mutex); - if (!pf->hw.port_info->qos_cfg.is_sw_lldp) ice_cfg_etsrec_defaults(pf->hw.port_info); From 7df3e1dfee5362fddee7b13585055403192f57ca Mon Sep 17 00:00:00 2001 From: Myeonghun Pak Date: Wed, 6 May 2026 21:43:11 +0900 Subject: [PATCH 1352/1518] net: lan966x: avoid unregistering netdev on register failure [ Upstream commit c4f3d6eb1fcf6cd9ce4644f604d5aad1ce594dfc ] lan966x_probe_port() stores the newly allocated net_device in the port before calling register_netdev(). If register_netdev() fails, the probe error path calls lan966x_cleanup_ports(), which sees port->dev and calls unregister_netdev() for a device that was never registered. Destroy the phylink instance created for this port and clear port->dev before returning the registration error. The common cleanup path now skips ports without port->dev before reaching the registered netdev cleanup, so it only handles ports that reached the registered-netdev lifetime. This also avoids treating an uninitialized FDMA netdev and the failed port as a NULL == NULL match in the common cleanup path. Fixes: d28d6d2e37d1 ("net: lan966x: add port module support") Co-developed-by: Ijae Kim Signed-off-by: Ijae Kim Signed-off-by: Myeonghun Pak Link: https://patch.msgid.link/20260506124331.31945-1-mhun512@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/microchip/lan966x/lan966x_main.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 47752d3fde0b1..1179a6e127c52 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -749,11 +749,10 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) for (p = 0; p < lan966x->num_phys_ports; p++) { port = lan966x->ports[p]; - if (!port) + if (!port || !port->dev) continue; - if (port->dev) - unregister_netdev(port->dev); + unregister_netdev(port->dev); lan966x_xdp_port_deinit(port); if (lan966x->fdma && lan966x->fdma_ndev == port->dev) @@ -873,6 +872,9 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, err = register_netdev(dev); if (err) { dev_err(lan966x->dev, "register_netdev failed\n"); + phylink_destroy(phylink); + port->phylink = NULL; + port->dev = NULL; return err; } From 994358adc0982d17731ffea7dfacd25afcc89773 Mon Sep 17 00:00:00 2001 From: Shitalkumar Gandhi Date: Thu, 7 May 2026 01:28:13 +0530 Subject: [PATCH 1353/1518] net: ti: icssm-prueth: fix eth_ports_node leak in probe [ Upstream commit 6635fa84403c3a59455b66007c019a7cc632db30 ] The error path on of_property_read_u32() failure inside icssm_prueth_probe() returns without putting eth_ports_node, which was acquired before the for_each_child_of_node() loop. Drop it before returning. Fixes: 511f6c1ae093 ("net: ti: icssm-prueth: Adds ICSSM Ethernet driver") Signed-off-by: Shitalkumar Gandhi Link: https://patch.msgid.link/20260506195813.641610-1-shitalkumar.gandhi@cambiumnetworks.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/icssm/icssm_prueth.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth.c b/drivers/net/ethernet/ti/icssm/icssm_prueth.c index 293b7af04263f..cc92f20685843 100644 --- a/drivers/net/ethernet/ti/icssm/icssm_prueth.c +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth.c @@ -1347,6 +1347,7 @@ static int icssm_prueth_probe(struct platform_device *pdev) dev_err(dev, "%pOF error reading port_id %d\n", eth_node, ret); of_node_put(eth_node); + of_node_put(eth_ports_node); return ret; } From e9405f7041271e119134c23438738de1476e7c92 Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Sat, 21 Mar 2026 15:42:32 +0100 Subject: [PATCH 1354/1518] phy: marvell: mvebu-a3700-utmi: fix incorrect USB2_PHY_CTRL register access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 91ddf6f722084383fb05be731c0107814b055c0c ] The mvebu_a3700_utmi_phy_power_off() function tries to modify the USB2_PHY_CTRL register by using the IO address of the PHY IP block along with the readl/writel IO accessors. However, the register exist in the USB miscellaneous register space, and as such it must be accessed via regmap like it is done in the mvebu_a3700_utmi_phy_power_on() function. Change the code to use regmap_update_bits() for modífying the register to fix this. Fixes: cc8b7a0ae866 ("phy: add A3700 UTMI PHY driver") Signed-off-by: Gabor Juhos Reviewed-by: Miquel Raynal Link: https://patch.msgid.link/20260321-a3700-utmi-fix-usb2_phy_ctrl-access-v1-1-6005ff4b5058@gmail.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/marvell/phy-mvebu-a3700-utmi.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/phy/marvell/phy-mvebu-a3700-utmi.c b/drivers/phy/marvell/phy-mvebu-a3700-utmi.c index 04f4fb4bed702..f882bc57649c7 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-utmi.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-utmi.c @@ -168,9 +168,8 @@ static int mvebu_a3700_utmi_phy_power_off(struct phy *phy) u32 reg; /* Disable PHY pull-up and enable USB2 suspend */ - reg = readl(utmi->regs + USB2_PHY_CTRL(usb32)); - reg &= ~(RB_USB2PHY_PU | RB_USB2PHY_SUSPM(usb32)); - writel(reg, utmi->regs + USB2_PHY_CTRL(usb32)); + regmap_update_bits(utmi->usb_misc, USB2_PHY_CTRL(usb32), + RB_USB2PHY_PU | RB_USB2PHY_SUSPM(usb32), 0); /* Power down OTG module */ if (usb32) { From fe59ae27d7346245f5d8d97220f374e63efd28b5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 19 Apr 2026 14:52:59 -0400 Subject: [PATCH 1355/1518] NFSD: Fix infinite loop in layout state revocation [ Upstream commit 4f8ef58c10bfe5f86a643c7c8331b37e69e3dae1 ] find_one_sb_stid() skips stids whose sc_status is non-zero, but the SC_TYPE_LAYOUT case in nfsd4_revoke_states() never sets sc_status before calling nfsd4_close_layout(). The retry loop therefore finds the same layout stid on every iteration, hanging the revoker indefinitely. Fixes: 1e33e1414bec ("nfsd: allow layout state to be admin-revoked.") Reported-by: Dai Ngo Reviewed-by: Jeff Layton Tested-by: Dai Ngo Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4state.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index cb8096e94f518..a9e95df2fdb68 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1848,6 +1848,13 @@ void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) break; case SC_TYPE_LAYOUT: ls = layoutstateid(stid); + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + } + spin_unlock(&clp->cl_lock); nfsd4_close_layout(ls); break; } From 5afefecfe054c5315a02e2d8c62aada80c93bdb1 Mon Sep 17 00:00:00 2001 From: Mac Chiang Date: Fri, 8 May 2026 17:32:23 +0800 Subject: [PATCH 1356/1518] ASoC: sdw_utils: Add quirk to ignore RT712 CODEC_MIC [ Upstream commit 9c37daee7c17fa17e8d41089ee1f658b06cb672a ] Some devices do not use CODEC_MIC but use the host PCH_DMIC instead. Add a quirk to skip the CODEC_MIC DAI when it is not present in disco table, ensuring the correct capture device is used. If CODEC_MIC is present, it continues to be used as default. Fixes: 9489db97f6f0 ("ASoC: sdw_utils: add SmartMic DAI for RT712 VB") Signed-off-by: Mac Chiang Signed-off-by: Bard Liao Link: https://patch.msgid.link/20260508093224.1246282-2-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sdw_utils/soc_sdw_utils.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index 3848c7df1916f..050ca17ff105d 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -170,6 +170,8 @@ struct asoc_sdw_codec_info codec_info_list[] = { .dai_type = SOC_SDW_DAI_TYPE_MIC, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_DMIC_DAI_ID}, .rtd_init = asoc_sdw_rt_dmic_rtd_init, + .quirk = SOC_SDW_CODEC_MIC, + .quirk_exclude = true, }, }, .dai_num = 3, From 36dc0cea30db09a21512a4094dee2de4cc5ff558 Mon Sep 17 00:00:00 2001 From: Mac Chiang Date: Fri, 8 May 2026 17:32:24 +0800 Subject: [PATCH 1357/1518] ASoC: sdw_utils: Add quirk to ignore RT721 CODEC_MIC [ Upstream commit fa749a77bdc50f0d695aaf81f1bd55967d77d10f ] Add a quirk to skip the CODEC_MIC DAI when it is not present. This ensures PCH_DMIC is used as the fallback; otherwise, CODEC_MIC remains the default. Fixes: 846a8d3cf3ba ("ASoC: Intel: soc-acpi-intel-ptl-match: Add rt721 support") Signed-off-by: Mac Chiang Signed-off-by: Bard Liao Link: https://patch.msgid.link/20260508093224.1246282-3-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sdw_utils/soc_sdw_utils.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index 050ca17ff105d..3facb78748acf 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -431,6 +431,8 @@ struct asoc_sdw_codec_info codec_info_list[] = { .dai_type = SOC_SDW_DAI_TYPE_MIC, .dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_DMIC_DAI_ID}, .rtd_init = asoc_sdw_rt_dmic_rtd_init, + .quirk = SOC_SDW_CODEC_MIC, + .quirk_exclude = true, }, }, .dai_num = 3, From 56b4cfcf1518245493c60fd39c56978f508f1816 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 7 May 2026 16:46:29 +0900 Subject: [PATCH 1358/1518] fprobe: Fix unregister_fprobe() to wait for RCU grace period [ Upstream commit 657b594b2084b39a4bc6d8493aa2140cb00cea49 ] Commit 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") changed fprobe to register struct fprobe to an rcu-hlist, but it forgot to wait for RCU GP. Thus there can be use-after-free if the fprobe is released right after unregistering. This can be happened on fprobe event and sample module code. To fix this issue, add synchronize_rcu() in unregister_fprobe(). Note that BPF is OK because fprobe is used as a part of bpf_kprobe_multi_link. This unregisters its fprobe in bpf_kprobe_multi_link_release() and it is deallocated via bpf_kprobe_multi_link_dealloc(), which is invoked from bpf_link_defer_dealloc_rcu_gp() RCU callback. For BPF, this also introduced unregister_fprobe_async() which does NOT wait for RCU grace priod. Link: https://lore.kernel.org/all/177813998919.256460.2809243930741138224.stgit@mhiramat.tok.corp.google.com/ Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin --- include/linux/fprobe.h | 5 +++++ kernel/trace/bpf_trace.c | 3 ++- kernel/trace/fprobe.c | 23 +++++++++++++++++++++-- 3 files changed, 28 insertions(+), 3 deletions(-) diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 0a3bcd1718f37..be1b38c981d4d 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -94,6 +94,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); int unregister_fprobe(struct fprobe *fp); +int unregister_fprobe_async(struct fprobe *fp); bool fprobe_is_registered(struct fprobe *fp); int fprobe_count_ips_from_filter(const char *filter, const char *notfilter); #else @@ -113,6 +114,10 @@ static inline int unregister_fprobe(struct fprobe *fp) { return -EOPNOTSUPP; } +static inline int unregister_fprobe_async(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} static inline bool fprobe_is_registered(struct fprobe *fp) { return false; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 70f1292b7ddbd..88f470b31375a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2371,7 +2371,8 @@ static void bpf_kprobe_multi_link_release(struct bpf_link *link) struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); - unregister_fprobe(&kmulti_link->fp); + /* Don't wait for RCU GP here. */ + unregister_fprobe_async(&kmulti_link->fp); kprobe_multi_put_modules(kmulti_link->mods, kmulti_link->mods_cnt); } diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 6419c8d772731..b9346f4efa6dc 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -1000,14 +1000,15 @@ static int unregister_fprobe_nolock(struct fprobe *fp) } /** - * unregister_fprobe() - Unregister fprobe. + * unregister_fprobe_async() - Unregister fprobe without RCU GP wait * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). + * This function will NOT wait until the fprobe is no longer used. * * Return 0 if @fp is unregistered successfully, -errno if not. */ -int unregister_fprobe(struct fprobe *fp) +int unregister_fprobe_async(struct fprobe *fp) { guard(mutex)(&fprobe_mutex); if (!fp || !fprobe_registered(fp)) @@ -1015,6 +1016,24 @@ int unregister_fprobe(struct fprobe *fp) return unregister_fprobe_nolock(fp); } + +/** + * unregister_fprobe() - Unregister fprobe with RCU GP wait + * @fp: A fprobe data structure to be unregistered. + * + * Unregister fprobe (and remove ftrace hooks from the function entries). + * This function will block until the fprobe is no longer used. + * + * Return 0 if @fp is unregistered successfully, -errno if not. + */ +int unregister_fprobe(struct fprobe *fp) +{ + int ret = unregister_fprobe_async(fp); + + if (!ret) + synchronize_rcu(); + return ret; +} EXPORT_SYMBOL_GPL(unregister_fprobe); static int __init fprobe_initcall(void) From e37ea2c6f17f273813ea4e8e94c102591d598ce1 Mon Sep 17 00:00:00 2001 From: Junyoung Jang Date: Mon, 4 May 2026 20:26:49 +0900 Subject: [PATCH 1359/1518] fs/statmount: fix slab out-of-bounds write in statmount_mnt_idmap [ Upstream commit a3bf0f28d4ba16e1f35f8c983bb04426b87e2a78 ] statmount_mnt_idmap() writes one mapping with seq_printf() and then manually advances seq->count to include the NUL separator. If seq_printf() overflows, seq_set_overflow() sets seq->count to seq->size. The manual seq->count++ changes this to seq->size + 1. seq_has_overflowed() then no longer detects the overflow. The corrupted count returns to statmount_string(), which later executes: seq->buf[seq->count++] = '\0'; This causes a 1-byte NULL out-of-bounds write on the dynamically allocated seq buffer. Fix this by checking for overflow immediately after seq_printf(). Fixes: 37c4a9590e1e ("statmount: allow to retrieve idmappings") Signed-off-by: Junyoung Jang Link: https://patch.msgid.link/20260504112649.1862936-1-graypanda.inzag@gmail.com Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/mnt_idmapping.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c index a37991fdb194d..3640230a4d43b 100644 --- a/fs/mnt_idmapping.c +++ b/fs/mnt_idmapping.c @@ -375,6 +375,8 @@ int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_ continue; seq_printf(seq, "%u %u %u", extent->first, lower, extent->count); + if (seq_has_overflowed(seq)) + return -EAGAIN; seq->count++; /* mappings are separated by \0 */ if (seq_has_overflowed(seq)) From ace6b3e033c6337a7a7c5eebe671270f0fa0d377 Mon Sep 17 00:00:00 2001 From: Hongling Zeng Date: Fri, 1 May 2026 15:10:58 +0800 Subject: [PATCH 1360/1518] fs: Fix return in jfs_mkdir and orangefs_mkdir [ Upstream commit a7cf1da7ac016490d6a1106f2aa6b602d34e9a12 ] Return NULL instead of passing to ERR_PTR while err is zero Fixes these smatch warnings: - fs/jfs/namei.c:311 jfs_mkdir() warn: passing zero to 'ERR_PTR' - fs/orangefs/namei.c:369 orangefs_mkdir() warn: passing zero to 'ERR_PTR' Fixes: 88d5baf69082 ("Change inode_operations.mkdir to return struct dentry *") Signed-off-by: Hongling Zeng Link: https://patch.msgid.link/20260501071058.1243245-1-zenghongling@kylinos.cn Reviewed-by: Jori Koolstra Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/jfs/namei.c | 2 +- fs/orangefs/namei.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 7879c049632b3..553fca69cf425 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -308,7 +308,7 @@ static struct dentry *jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, out1: jfs_info("jfs_mkdir: rc:%d", rc); - return ERR_PTR(rc); + return rc ? ERR_PTR(rc) : NULL; } /* diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index bec5475de094d..75e65e72c2d64 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -362,7 +362,7 @@ static struct dentry *orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, __orangefs_setattr(dir, &iattr); out: op_release(new_op); - return ERR_PTR(ret); + return ret ? ERR_PTR(ret) : NULL; } static int orangefs_rename(struct mnt_idmap *idmap, From 617a2564d8634c06d19097dc0f89bd3a72bcb1b4 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Wed, 6 May 2026 01:55:22 -0700 Subject: [PATCH 1361/1518] irqchip/ath79-cpu: Remove unused function [ Upstream commit 0fa10fb77069fb67aa51384868ef3702b7791465 ] ath79_cpu_irq_init() was part of the legacy pre-OF code that got removed a while back. Remove it to get rid of a missing prototype warning, reported by the kernel test robot. [ tglx: Fix the subject prefix. Sigh ... ] Fixes: 51fa4f8912c0 ("MIPS: ath79: drop legacy IRQ code") Reported-by: kernel test robot Signed-off-by: Rosen Penev Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260506085522.1210143-1-rosenp@gmail.com Closes: https://lore.kernel.org/oe-kbuild-all/202412011509.kGQkDr1y-lkp@intel.com/ Signed-off-by: Sasha Levin --- drivers/irqchip/irq-ath79-cpu.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/irqchip/irq-ath79-cpu.c b/drivers/irqchip/irq-ath79-cpu.c index 923e4bba37767..9b7273a7f8ced 100644 --- a/drivers/irqchip/irq-ath79-cpu.c +++ b/drivers/irqchip/irq-ath79-cpu.c @@ -85,10 +85,3 @@ static int __init ar79_cpu_intc_of_init( } IRQCHIP_DECLARE(ar79_cpu_intc, "qca,ar7100-cpu-intc", ar79_cpu_intc_of_init); - -void __init ath79_cpu_irq_init(unsigned irq_wb_chan2, unsigned irq_wb_chan3) -{ - irq_wb_chan[2] = irq_wb_chan2; - irq_wb_chan[3] = irq_wb_chan3; - mips_cpu_irq_init(); -} From d168a71fc1d6dd3e30d0d66aae098ebcda91db65 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 10 May 2026 22:48:43 +0800 Subject: [PATCH 1362/1518] ublk: reject max_sectors smaller than PAGE_SECTORS in parameter validation [ Upstream commit 1860c2f85922917d8a46f16a6f4bd2298ffa0fb5 ] blk_validate_limits() requires max_hw_sectors >= PAGE_SECTORS and fires a WARN_ON_ONCE if this invariant is violated. ublk_validate_params() only checked the upper bound of max_sectors against max_io_buf_bytes, allowing userspace to pass small values (including zero) that trigger the warning when blk_mq_alloc_disk() is called from ublk_ctrl_start_dev(). Before 494ea040bcb5, ublk used blk_queue_max_hw_sectors() which silently clamped small values up to PAGE_SECTORS. The conversion to passing queue_limits directly to blk_mq_alloc_disk() lost that clamping and now hits blk_validate_limits()'s WARN_ON_ONCE instead. Validate that max_sectors is at least PAGE_SECTORS in ublk_validate_params() so invalid values are rejected early with -EINVAL instead of reaching the block layer. Fixes: 494ea040bcb5 ("ublk: pass queue_limits to blk_mq_alloc_disk") Signed-off-by: Ming Lei Link: https://patch.msgid.link/20260510144843.769031-1-tom.leiming@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/ublk_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 2729b1556e810..c339222513b03 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -601,6 +601,9 @@ static int ublk_validate_params(const struct ublk_device *ub) if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9)) return -EINVAL; + if (p->max_sectors < PAGE_SECTORS) + return -EINVAL; + if (ublk_dev_is_zoned(ub) && !p->chunk_sectors) return -EINVAL; } else From 06ee55f78fbe2e103cc01c62c18e9c55f3a9b019 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Thu, 7 May 2026 19:23:01 +0800 Subject: [PATCH 1363/1518] nsfs: fix wrong error code returned for pidns ioctls [ Upstream commit 725ecd80688bf3c57ca9205431f2c06174ff0756 ] When executing NS_GET_PID_FROM_PIDNS (or similar pidns ioctls), if the target task cannot be found in the corresponding pid_ns, the error code should be ESRCH instead of ENOTTY. This bug was introduced when the extensible ioctl handling was added. Without proper return, ret would be overwritten by the default case in the extensible ioctl switch statement. Fixes: a1d220d9dafa8 ("nsfs: iterate through mount namespaces") Signed-off-by: Zhihao Cheng Link: https://patch.msgid.link/20260507112301.1042757-1-chengzhihao1@huawei.com Reviewed-by: Yang Erkun Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/nsfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nsfs.c b/fs/nsfs.c index f22c2a636e8f3..e2f9a725883c7 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -261,7 +261,7 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, else tsk = find_task_by_pid_ns(arg, pid_ns); if (!tsk) - break; + return ret; switch (ioctl) { case NS_GET_PID_FROM_PIDNS: From 18c0456ea2615b1a743a6db739c74411c3b42bc6 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Mon, 30 Mar 2026 15:32:29 +0800 Subject: [PATCH 1364/1518] irq_work: Fix use-after-free in irq_work_single() on PREEMPT_RT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 91840be8f710370607f949a627e070896faeddb8 ] On PREEMPT_RT, non-HARD irq_work runs in per-CPU kthreads via run_irq_workd(), so irq_work_sync() uses rcuwait() to wait for BUSY==0. After irq_work_single() clears BUSY via atomic_cmpxchg(), it still dereferences @work for irq_work_is_hard() and rcuwait_wake_up(). An irq_work_sync() caller on another CPU that enters after BUSY is cleared can observe BUSY==0 immediately, return, and free the work before those accesses complete — causing a use-after-free. Fix this by wrapping run_irq_workd() in guard(rcu)() so that the entire irq_work_single() execution is within an RCU read-side critical section. Then add synchronize_rcu() in irq_work_sync() after rcuwait_wait_event() to ensure the caller waits for the RCU grace period before returning, preventing premature frees. Fixes: 810979682ccc ("irq_work: Allow irq_work_sync() to sleep if irq_work() no IRQ support.") Suggested-by: Sebastian Andrzej Siewior Suggested-by: Steven Rostedt Signed-off-by: Jiayuan Chen Signed-off-by: Thomas Gleixner Reviewed-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20260330073234.303732-1-jiayuan.chen@linux.dev Signed-off-by: Sasha Levin --- kernel/irq_work.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 73f7e1fd4ab4d..bf411656c3160 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -292,6 +292,12 @@ void irq_work_sync(struct irq_work *work) !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); + /* + * Ensure irq_work_single() does not access @work + * after removing IRQ_WORK_BUSY. It is always + * accessed within a RCU-read section. + */ + synchronize_rcu(); return; } @@ -302,6 +308,7 @@ EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { + guard(rcu)(); irq_work_run_list(this_cpu_ptr(&lazy_list)); } From fea4b46f84c50caf93c6c0f2a54b1be2edfb4491 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 6 May 2026 06:16:02 -0700 Subject: [PATCH 1365/1518] nvme: fix bio leak on mapping failure [ Upstream commit 2279cd9c61a330e5de4d6eb0bc422820dd6fdf36 ] The local bio is always NULL, so we'd leak the bio if the integrity mapping failed. Just get it directly from the request. Fixes: d0d1d522316e91f ("blk-map: provide the bdev to bio if one exists") Reviewed-by: Sagi Grimberg Reviewed-by: John Garry Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/ioctl.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index c212fa952c0f4..5bbaf257fd6c5 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -122,7 +122,6 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk); struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; bool has_metadata = meta_buffer && meta_len; - struct bio *bio = NULL; int ret; if (!nvme_ctrl_sgl_supported(ctrl)) @@ -154,8 +153,8 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, return ret; out_unmap: - if (bio) - blk_rq_unmap_user(bio); + if (req->bio) + blk_rq_unmap_user(req->bio); return ret; } From 9525e3a6fbb1d126a22ab2ee86ddea25af581a7c Mon Sep 17 00:00:00 2001 From: "Chia-Lin Kao (AceLan)" Date: Wed, 29 Apr 2026 16:11:16 +0800 Subject: [PATCH 1366/1518] nvme-pci: fix use-after-free in nvme_free_host_mem() [ Upstream commit b35a13036755c5803168a7cb93bc66035c3e65b8 ] nvme_free_host_mem() frees dev->hmb_sgt via dma_free_noncontiguous() but never clears the pointer afterward. This leads to a use-after-free if nvme_free_host_mem() is called twice in the same error path. This can happen during nvme_probe() when nvme_setup_host_mem() succeeds in allocating the HMB (setting dev->hmb_sgt) but nvme_set_host_mem() fails with an I/O error: nvme_setup_host_mem() nvme_alloc_host_mem_single() -> sets dev->hmb_sgt nvme_set_host_mem() -> fails with -EIO nvme_free_host_mem() -> frees hmb_sgt, but does NOT NULL it return error nvme_probe() error path: nvme_free_host_mem() -> dev->hmb_sgt is stale, use-after-free The second call dereferences the freed sgt, causing a NULL pointer dereference in iommu_dma_free_noncontiguous() when it accesses sgt->sgl->dma_address (the backing memory has been freed and zeroed). This is reproducible on Thunderbolt-attached NVMe devices (e.g., OWC Envoy Express behind a Dell WD22TB4 dock) where the device intermittently returns I/O errors during HMB setup due to PCIe link instability. BUG: kernel NULL pointer dereference, address: 0000000000000010 RIP: 0010:iommu_dma_free_noncontiguous+0x22/0x80 Call Trace: dma_free_noncontiguous+0x3b/0x130 nvme_free_host_mem+0x30/0xf0 [nvme] nvme_probe.cold+0xcc/0x275 [nvme] local_pci_probe+0x43/0xa0 pci_device_probe+0xeea/0x290 really_probe+0xf9/0x3b0 __driver_probe_device+0x8b/0x170 driver_probe_device+0x24/0xd0 __driver_attach_async_helper+0x6b/0x110 async_run_entry_fn+0x37/0x170 process_one_work+0x1ac/0x3d0 worker_thread+0x1b8/0x360 kthread+0xf7/0x130 ret_from_fork+0x2d8/0x3a0 ret_from_fork_asm+0x1a/0x30 Fix this by setting dev->hmb_sgt to NULL after freeing it, so the second call takes the multi-descriptor path which safely handles the already-cleaned-up state. Fixes: 63a5c7a4b4c4 ("nvme-pci: use dma_alloc_noncontigous if possible") Signed-off-by: Chia-Lin Kao (AceLan) Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 2e32242bed67c..5e36a5926fe03 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2320,11 +2320,13 @@ static void nvme_free_host_mem_multi(struct nvme_dev *dev) static void nvme_free_host_mem(struct nvme_dev *dev) { - if (dev->hmb_sgt) + if (dev->hmb_sgt) { dma_free_noncontiguous(dev->dev, dev->host_mem_size, dev->hmb_sgt, DMA_BIDIRECTIONAL); - else + dev->hmb_sgt = NULL; + } else { nvme_free_host_mem_multi(dev); + } dma_free_coherent(dev->dev, dev->host_mem_descs_size, dev->host_mem_descs, dev->host_mem_descs_dma); From eba8af785fde3cb2e9aeabd3fe66a478827eda72 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 29 Apr 2026 22:58:15 +0200 Subject: [PATCH 1367/1518] zonefs: handle integer overflow in zonefs_fname_to_fno [ Upstream commit 3a8389d42bdf4213730f4067f8bfa78bae6564ef ] In zonefs the file name in one of the two directories corresponds to the zone number. Here Alexey reported a possible integer overflow in zonefs_fname_to_fno(), where the parsing of the zone number from the file name can overflow the 'long' data type. Add a check for integer overflows and if the fno 'long' did overflow return -ENOENT. Reported-by: Alexey Dobriyan Fixes: d207794ababe ("zonefs: Dynamically create file inodes when needed") Signed-off-by: Johannes Thumshirn Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- fs/zonefs/super.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 70be0b3dda496..7e345a6aa5510 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -610,10 +610,14 @@ static long zonefs_fname_to_fno(const struct qstr *fname) return c - '0'; for (i = 0, rname = name + len - 1; i < len; i++, rname--) { + long digit; + c = *rname; if (!isdigit(c)) return -ENOENT; - fno += (c - '0') * shift; + digit = (c - '0') * shift; + if (check_add_overflow(fno, digit, &fno)) + return -ENOENT; shift *= 10; } From 510db031ba6eb40134f84c90ef963ea4b6dfb878 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 8 May 2026 12:08:46 +0000 Subject: [PATCH 1368/1518] tcp: Fix out-of-bounds access for twsk in tcp_ao_established_key(). [ Upstream commit 03cb001ef87b3f8d859cf7f96329acf3d6235d29 ] lockdep_sock_is_held() was added in tcp_ao_established_key() by the cited commit. It can be called from tcp_v[46]_timewait_ack() with twsk. Since it does not have sk->sk_lock, the lockdep annotation results in out-of-bound access. $ pahole -C tcp_timewait_sock vmlinux | grep size /* size: 288, cachelines: 5, members: 8 */ $ pahole -C sock vmlinux | grep sk_lock socket_lock_t sk_lock; /* 440 192 */ Let's not use lockdep_sock_is_held() for TCP_TIME_WAIT. Fixes: 6b2d11e2d8fc ("net/tcp: Add missing lockdep annotations for TCP-AO hlist traversals") Reported-by: Damiano Melotti Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260508120853.4098365-1-kuniyu@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_ao.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 849a69c1f497f..aa624434b5556 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -116,7 +116,8 @@ struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, { struct tcp_ao_key *key; - hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) { + hlist_for_each_entry_rcu(key, &ao->head, node, + sk_fullsock(sk) && lockdep_sock_is_held(sk)) { if ((sndid >= 0 && key->sndid != sndid) || (rcvid >= 0 && key->rcvid != rcvid)) continue; From aed60070ed7b072f71f048c99e6e76145ddc1224 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 11 May 2026 10:36:36 -0500 Subject: [PATCH 1369/1518] ASoC: SOF: amd: Fix error code handling in psp_send_cmd() [ Upstream commit 2c7b1227e582e88db7917412dca4e752c1aff691 ] The smn_read_register() helper returns negative error codes on failure or the register value on success. When used with read_poll_timeout(), the return value is stored in the 'data' variable. Currently 'data' is declared as u32, which causes negative error codes to be cast to large positive values. This makes the condition 'data > 0' incorrectly treat errors as success. Fix by changing 'data' from u32 to int, matching the pattern used in psp_mbox_ready() which correctly handles the same helper function. Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-sound/agGES8vWrLOrBu28@stanley.mountain/ Fixes: f120cf33d232 ("ASoC: SOF: amd: Use AMD_NODE") Signed-off-by: Mario Limonciello Link: https://patch.msgid.link/20260511153638.724810-1-mario.limonciello@amd.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/amd/acp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index 71a18f156de23..f615b8d1c8020 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -223,7 +223,7 @@ static int psp_send_cmd(struct acp_dev_data *adata, int cmd) { struct snd_sof_dev *sdev = adata->dev; int ret; - u32 data; + int data; if (!cmd) return -EINVAL; From 822bb1614ec4198562a6ce86dbcbab684e260595 Mon Sep 17 00:00:00 2001 From: Ally Heev Date: Sun, 16 Nov 2025 19:55:44 +0530 Subject: [PATCH 1370/1518] powerpc: 82xx: fix uninitialized pointers with free attribute [ Upstream commit acd1e47db03d4b528fd5efb8565dd0de1c79f62a ] Uninitialized pointers with `__free` attribute can cause undefined behavior as the memory allocated to the pointer is freed automatically when the pointer goes out of scope. powerpc/km82xx doesn't have any bugs related to this as of now, but, it is better to initialize and assign pointers with `__free` attribute in one statement to ensure proper scope-based cleanup Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/aPiG_F5EBQUjZqsl@stanley.mountain/ Signed-off-by: Ally Heev Fixes: 4aa5cc1e0012 ("powerpc-km82xx.c: replace of_node_put() with __free") Reviewed-by: Christophe Leroy (CS GROUP) Reviewed-by: Krzysztof Kozlowski Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20251116-aheev-uninitialized-free-attr-km82xx-v2-1-4307e2b5300d@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/82xx/km82xx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c index 99f0f0f418767..4ad223525e893 100644 --- a/arch/powerpc/platforms/82xx/km82xx.c +++ b/arch/powerpc/platforms/82xx/km82xx.c @@ -27,8 +27,8 @@ static void __init km82xx_pic_init(void) { - struct device_node *np __free(device_node); - np = of_find_compatible_node(NULL, NULL, "fsl,pq2-pic"); + struct device_node *np __free(device_node) = of_find_compatible_node(NULL, + NULL, "fsl,pq2-pic"); if (!np) { pr_err("PIC init: can not find cpm-pic node\n"); From 9c6f23cf3a07483ae180a382cea8cf33b45df1f9 Mon Sep 17 00:00:00 2001 From: Julian Braha Date: Sun, 5 Apr 2026 17:15:45 +0100 Subject: [PATCH 1371/1518] powerpc: fix dead default for GUEST_STATE_BUFFER_TEST [ Upstream commit aef656a0e6c01796190bb5bd2bdba1c644ed7811 ] The GUEST_STATE_BUFFER_TEST config option should default to KUNIT_ALL_TESTS so that if all tests are enabled then it is included, but currently the 'default KUNIT_ALL_TESTS' statement is shadowed by 'def_tristate n', meaning that this second default statement is currently dead code. It looks to me like the commit 6ccbbc33f06a ("KVM: PPC: Add helper library for Guest State Buffers") intended to set the default to KUNIT_ALL_TESTS, but mistakenly missed the def_tristate. This dead code was found by kconfirm, a static analysis tool for Kconfig. Fixes: 6ccbbc33f06a ("KVM: PPC: Add helper library for Guest State Buffers") Signed-off-by: Julian Braha Tested-by: Gautam Menghani Reviewed-by: Amit Machhiwal Reviewed-by: Harsh Prateek Bora Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260405161545.161006-1-julianbraha@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/Kconfig.debug | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index f15e5920080ba..e8718bc13eeb1 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -83,11 +83,10 @@ config MSI_BITMAP_SELFTEST depends on DEBUG_KERNEL config GUEST_STATE_BUFFER_TEST - def_tristate n + def_tristate KUNIT_ALL_TESTS prompt "Enable Guest State Buffer unit tests" depends on KUNIT depends on KVM_BOOK3S_HV_POSSIBLE - default KUNIT_ALL_TESTS help The Guest State Buffer is a data format specified in the PAPR. It is by hcalls to communicate the state of L2 guests between From 5366199be46fb53de62861721d34ba816e7e440e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:38 +0100 Subject: [PATCH 1372/1518] netfs: Fix cancellation of a DIO and single read subrequests [ Upstream commit 6f0f7ac1915abc0d202f0eb4b003a6548a5ba60d ] When the preparation of a new subrequest for a read fails, if the subrequest has already been added to the stream->subrequests list, it can't simply be put and abandoned as the collector may see it. Also, if it hasn't been queued yet, it has two outstanding refs that both need to be put. Both DIO read and single-read dispatch fail at this; further, both differ in the order they do things to the way buffered read works. Fix cancellation of both DIO-read and single-read subrequests that failed preparation by the following steps: (1) Harmonise all three reads (buffered, dio, single) to queue the subreq before prepping it. (2) Make all three call netfs_queue_read() to do the queuing. (3) Set NETFS_RREQ_ALL_QUEUED independently of the queuing as we don't know the length of the subreq at this point. (4) In all cases, set the error and NETFS_SREQ_FAILED flag on the subreq and then call netfs_read_subreq_terminated() to deal with it. This will pass responsibility off to the collector for dealing with it. Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item") Closes: https://sashiko.dev/#/patchset/20260425125426.3855807-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-2-dhowells@redhat.com cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 34 +++++++++++++------------------- fs/netfs/direct_read.c | 42 +++++++++++++--------------------------- fs/netfs/internal.h | 3 +++ fs/netfs/read_collect.c | 11 +++++++++++ fs/netfs/read_single.c | 23 ++++++++++------------ 5 files changed, 50 insertions(+), 63 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 88361e8c70961..10b13924ed543 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -156,9 +156,8 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } -static void netfs_queue_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq, - bool last_subreq) +void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) { struct netfs_io_stream *stream = &rreq->io_streams[0]; @@ -178,11 +177,6 @@ static void netfs_queue_read(struct netfs_io_request *rreq, } } - if (last_subreq) { - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); - } - spin_unlock(&rreq->lock); } @@ -233,6 +227,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, subreq->start = start; subreq->len = size; + netfs_queue_read(rreq, subreq); + source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); subreq->source = source; if (source == NETFS_DOWNLOAD_FROM_SERVER) { @@ -253,6 +249,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, rreq->debug_id, subreq->debug_index, subreq->len, size, subreq->start, ictx->zero_point, rreq->i_size); + netfs_cancel_read(subreq, ret); break; } subreq->len = len; @@ -261,12 +258,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - subreq->error = ret; - /* Not queued - release both refs. */ - netfs_put_subrequest(subreq, - netfs_sreq_trace_put_cancel); - netfs_put_subrequest(subreq, - netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); break; } trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); @@ -289,23 +281,23 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, pr_err("Unexpected read source %u\n", source); WARN_ON_ONCE(1); + netfs_cancel_read(subreq, ret); break; issue: slice = netfs_prepare_read_iterator(subreq, ractl); if (slice < 0) { ret = slice; - subreq->error = ret; - trace_netfs_sreq(subreq, netfs_sreq_trace_cancel); - /* Not queued - release both refs. */ - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); break; } - size -= slice; start += slice; + size -= slice; + if (size <= 0) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } - netfs_queue_read(rreq, subreq, size <= 0); netfs_issue_read(rreq, subreq); cond_resched(); } while (size > 0); diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index f72e6da88cca7..6a8fb0d55e040 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -45,12 +45,11 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) * Perform a read to a buffer from the server, slicing up the region to be read * according to the network rsize. */ -static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) +static void netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) { - struct netfs_io_stream *stream = &rreq->io_streams[0]; unsigned long long start = rreq->start; ssize_t size = rreq->len; - int ret = 0; + int ret; do { struct netfs_io_subrequest *subreq; @@ -58,7 +57,10 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) subreq = netfs_alloc_subrequest(rreq); if (!subreq) { - ret = -ENOMEM; + /* Stash the error in the request if there's not + * already an error set. + */ + cmpxchg(&rreq->error, 0, -ENOMEM); break; } @@ -66,25 +68,13 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) subreq->start = start; subreq->len = size; - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - - spin_lock(&rreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); - if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - if (!stream->active) { - stream->collected_to = subreq->start; - /* Store list pointers before active flag */ - smp_store_release(&stream->active, true); - } - } - trace_netfs_sreq(subreq, netfs_sreq_trace_added); - spin_unlock(&rreq->lock); + netfs_queue_read(rreq, subreq); netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); break; } } @@ -113,8 +103,6 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); netfs_wake_collector(rreq); } - - return ret; } /* @@ -137,21 +125,17 @@ static ssize_t netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) // TODO: Use bounce buffer if requested inode_dio_begin(rreq->inode); + netfs_dispatch_unbuffered_reads(rreq); - ret = netfs_dispatch_unbuffered_reads(rreq); - - if (!rreq->submitted) { - netfs_put_request(rreq, netfs_rreq_trace_put_no_submit); - inode_dio_end(rreq->inode); - ret = 0; - goto out; - } + /* The collector will get run, even if we don't manage to submit any + * subreqs, so we shouldn't call inode_dio_end() here. + */ if (sync) ret = netfs_wait_for_read(rreq); else ret = -EIOCBQUEUED; -out: + _leave(" = %zd", ret); return ret; } diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index d436e20d34185..645996ecfc803 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -23,6 +23,8 @@ /* * buffered_read.c */ +void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq); void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); @@ -108,6 +110,7 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, */ bool netfs_read_collection(struct netfs_io_request *rreq); void netfs_read_collection_worker(struct work_struct *work); +void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error); void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error); /* diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index e5f6665b3341e..d2d902f466271 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -575,6 +575,17 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) } EXPORT_SYMBOL(netfs_read_subreq_terminated); +/* + * Cancel a read subrequest due to preparation failure. + */ +void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error) +{ + trace_netfs_sreq(subreq, netfs_sreq_trace_cancel); + subreq->error = error; + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + netfs_read_subreq_terminated(subreq); +} + /* * Handle termination of a read from the cache. */ diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 9d48ced80d1fa..cb422de66d0c5 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -89,7 +89,6 @@ static void netfs_single_read_cache(struct netfs_io_request *rreq, */ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) { - struct netfs_io_stream *stream = &rreq->io_streams[0]; struct netfs_io_subrequest *subreq; int ret = 0; @@ -102,14 +101,7 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) subreq->len = rreq->len; subreq->io_iter = rreq->buffer.iter; - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - - spin_lock(&rreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); - trace_netfs_sreq(subreq, netfs_sreq_trace_added); - /* Store list pointers before active flag */ - smp_store_release(&stream->active, true); - spin_unlock(&rreq->lock); + netfs_queue_read(rreq, subreq); netfs_single_cache_prepare_read(rreq, subreq); switch (subreq->source) { @@ -121,10 +113,14 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) goto cancel; } + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); rreq->netfs_ops->issue_read(subreq); rreq->submitted += subreq->len; break; case NETFS_READ_FROM_CACHE: + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_single_read_cache(rreq, subreq); rreq->submitted += subreq->len; @@ -134,14 +130,15 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) pr_warn("Unexpected single-read source %u\n", subreq->source); WARN_ON_ONCE(true); ret = -EIO; - break; + goto cancel; } - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); return ret; cancel: - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + netfs_wake_collector(rreq); return ret; } From 884c4c4f35e577aba6a0593c80cbea9ca5e6e2b8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:41 +0100 Subject: [PATCH 1373/1518] netfs: Fix netfs_read_to_pagecache() to pause on subreq failure [ Upstream commit 8a8c0cfdf4658fc5b295b7fc87be56e0d76741f4 ] Fix netfs_read_to_pagecache() so that it pauses the generation of new subrequests if an already-issued subrequest fails. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Closes: https://sashiko.dev/#/patchset/20260425125426.3855807-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-5-dhowells@redhat.com cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 10b13924ed543..e6157122da3a4 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -299,6 +299,11 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, } netfs_issue_read(rreq, subreq); + + if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + netfs_wait_for_paused_read(rreq); + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) + break; cond_resched(); } while (size > 0); From b63971238beb79cf701dac33c6cefc56c07c89fa Mon Sep 17 00:00:00 2001 From: Viacheslav Dubeyko Date: Tue, 12 May 2026 13:33:44 +0100 Subject: [PATCH 1374/1518] netfs: fix VM_BUG_ON_FOLIO() issue in netfs_write_begin() call [ Upstream commit dc7832d05deb4d632e8035e3299e31a3528fa0d0 ] The multiple runs of generic/013 test-case is capable to reproduce a kernel BUG at mm/filemap.c:1504 with probability of 30%. while true; do sudo ./check generic/013 done [ 9849.452376] page: refcount:3 mapcount:0 mapping:00000000e58ff252 index:0x10781 pfn:0x1c322 [ 9849.452412] memcg:ffff8881a1915800 [ 9849.452417] aops:ceph_aops ino:1000058db9e dentry name(?):"f9XXXXXX" [ 9849.452432] flags: 0x17ffffc0000000(node=0|zone=2|lastcpupid=0x1fffff) [ 9849.452441] raw: 0017ffffc0000000 0000000000000000 dead000000000122 ffff88816110d248 [ 9849.452445] raw: 0000000000010781 0000000000000000 00000003ffffffff ffff8881a1915800 [ 9849.452447] page dumped because: VM_BUG_ON_FOLIO(!folio_test_locked(folio)) [ 9849.452474] ------------[ cut here ]------------ [ 9849.452476] kernel BUG at mm/filemap.c:1504! [ 9849.478635] Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI [ 9849.481772] CPU: 2 UID: 0 PID: 84223 Comm: fsstress Not tainted 7.0.0-rc1+ #18 PREEMPT(full) [ 9849.482881] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-9.fc43 06/1 0/2025 [ 9849.484539] RIP: 0010:folio_unlock+0x85/0xa0 [ 9849.485076] Code: 89 df 31 f6 e8 1c f3 ff ff 48 8b 5d f8 c9 31 c0 31 d2 31 f6 31 ff c3 cc cc cc cc 48 c7 c6 80 6c d9 a7 48 89 df e8 4b b3 10 00 <0f> 0b 48 89 df e8 21 e6 2c 00 eb 9d 0f 1f 40 00 66 66 2e 0f 1f 84 [ 9849.493818] RSP: 0018:ffff8881bb8076b0 EFLAGS: 00010246 [ 9849.495740] RAX: 0000000000000000 RBX: ffffea00070c8980 RCX: 0000000000000000 [ 9849.498678] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 9849.500559] RBP: ffff8881bb8076b8 R08: 0000000000000000 R09: 0000000000000000 [ 9849.501097] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000010782000 [ 9849.502108] R13: ffff8881935de738 R14: ffff88816110d010 R15: 0000000000001000 [ 9849.502516] FS: 00007e36cbe94740(0000) GS:ffff88824a899000(0000) knlGS:0000000000000000 [ 9849.502996] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9849.503810] CR2: 000000c0002b0000 CR3: 000000011bbf6004 CR4: 0000000000772ef0 [ 9849.504459] PKRU: 55555554 [ 9849.504626] Call Trace: [ 9849.505242] [ 9849.505379] netfs_write_begin+0x7c8/0x10a0 [ 9849.505877] ? __kasan_check_read+0x11/0x20 [ 9849.506384] ? __pfx_netfs_write_begin+0x10/0x10 [ 9849.507178] ceph_write_begin+0x8c/0x1c0 [ 9849.507934] generic_perform_write+0x391/0x8f0 [ 9849.508503] ? __pfx_generic_perform_write+0x10/0x10 [ 9849.509062] ? file_update_time_flags+0x19a/0x4b0 [ 9849.509581] ? ceph_get_caps+0x63/0xf0 [ 9849.510259] ? ceph_get_caps+0x63/0xf0 [ 9849.510530] ceph_write_iter+0xe79/0x1ae0 [ 9849.511282] ? __pfx_ceph_write_iter+0x10/0x10 [ 9849.511839] ? lock_acquire+0x1ad/0x310 [ 9849.512334] ? ksys_write+0xf9/0x230 [ 9849.512582] ? lock_is_held_type+0xaa/0x140 [ 9849.513128] vfs_write+0x512/0x1110 [ 9849.513634] ? __fget_files+0x33/0x350 [ 9849.513893] ? __pfx_vfs_write+0x10/0x10 [ 9849.514143] ? mutex_lock_nested+0x1b/0x30 [ 9849.514394] ksys_write+0xf9/0x230 [ 9849.514621] ? __pfx_ksys_write+0x10/0x10 [ 9849.514887] ? do_syscall_64+0x25e/0x1520 [ 9849.515122] ? __kasan_check_read+0x11/0x20 [ 9849.515366] ? trace_hardirqs_on_prepare+0x178/0x1c0 [ 9849.515655] __x64_sys_write+0x72/0xd0 [ 9849.515885] ? trace_hardirqs_on+0x24/0x1c0 [ 9849.516130] x64_sys_call+0x22f/0x2390 [ 9849.516341] do_syscall_64+0x12b/0x1520 [ 9849.516545] ? do_syscall_64+0x27c/0x1520 [ 9849.516783] ? do_syscall_64+0x27c/0x1520 [ 9849.517003] ? lock_release+0x318/0x480 [ 9849.517220] ? __x64_sys_io_getevents+0x143/0x2d0 [ 9849.517479] ? percpu_ref_put_many.constprop.0+0x8f/0x210 [ 9849.517779] ? entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 9849.518073] ? do_syscall_64+0x25e/0x1520 [ 9849.518291] ? __kasan_check_read+0x11/0x20 [ 9849.518519] ? trace_hardirqs_on_prepare+0x178/0x1c0 [ 9849.518799] ? do_syscall_64+0x27c/0x1520 [ 9849.519024] ? local_clock_noinstr+0xf/0x120 [ 9849.519262] ? entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 9849.519544] ? do_syscall_64+0x25e/0x1520 [ 9849.519781] ? __kasan_check_read+0x11/0x20 [ 9849.520008] ? trace_hardirqs_on_prepare+0x178/0x1c0 [ 9849.520273] ? do_syscall_64+0x27c/0x1520 [ 9849.520491] ? trace_hardirqs_on_prepare+0x178/0x1c0 [ 9849.520767] ? irqentry_exit+0x10c/0x6c0 [ 9849.520984] ? trace_hardirqs_off+0x86/0x1b0 [ 9849.521224] ? exc_page_fault+0xab/0x130 [ 9849.521472] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 9849.521766] RIP: 0033:0x7e36cbd14907 [ 9849.521989] Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 [ 9849.523057] RSP: 002b:00007ffff2d2a968 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 9849.523484] RAX: ffffffffffffffda RBX: 000000000000e549 RCX: 00007e36cbd14907 [ 9849.523885] RDX: 000000000000e549 RSI: 00005bd797ec6370 RDI: 0000000000000004 [ 9849.524277] RBP: 0000000000000004 R08: 0000000000000047 R09: 00005bd797ec6370 [ 9849.524652] R10: 0000000000000078 R11: 0000000000000246 R12: 0000000000000049 [ 9849.525062] R13: 0000000010781a37 R14: 00005bd797ec6370 R15: 0000000000000000 [ 9849.525447] [ 9849.525574] Modules linked in: intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry intel_vsec kvm_intel joydev kvm irqbypass ghash_clmulni_intel aesni_intel input_leds rapl mac_hid psmouse vga16fb serio_raw vgastate floppy i2c_piix4 bochs qemu_fw_cfg i2c_smbus pata_acpi sch_fq_codel rbd msr parport_pc ppdev lp parport efi_pstore [ 9849.529150] ---[ end trace 0000000000000000 ]--- [ 9849.529502] RIP: 0010:folio_unlock+0x85/0xa0 [ 9849.530813] Code: 89 df 31 f6 e8 1c f3 ff ff 48 8b 5d f8 c9 31 c0 31 d2 31 f6 31 ff c3 cc cc cc cc 48 c7 c6 80 6c d9 a7 48 89 df e8 4b b3 10 00 <0f> 0b 48 89 df e8 21 e6 2c 00 eb 9d 0f 1f 40 00 66 66 2e 0f 1f 84 [ 9849.534986] RSP: 0018:ffff8881bb8076b0 EFLAGS: 00010246 [ 9849.536198] RAX: 0000000000000000 RBX: ffffea00070c8980 RCX: 0000000000000000 [ 9849.537718] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 9849.539321] RBP: ffff8881bb8076b8 R08: 0000000000000000 R09: 0000000000000000 [ 9849.540862] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000010782000 [ 9849.542438] R13: ffff8881935de738 R14: ffff88816110d010 R15: 0000000000001000 [ 9849.543996] FS: 00007e36cbe94740(0000) GS:ffff88824b899000(0000) knlGS:0000000000000000 [ 9849.545854] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9849.547092] CR2: 00007e36cb3ff000 CR3: 000000011bbf6006 CR4: 0000000000772ef0 [ 9849.548679] PKRU: 55555554 The race sequence: 1. Read completes -> netfs_read_collection() runs 2. netfs_wake_rreq_flag(rreq, NETFS_RREQ_IN_PROGRESS, ...) 3. netfs_wait_for_read() returns -EFAULT to netfs_write_begin() 4. The netfs_unlock_abandoned_read_pages() unlocks the folio 5. netfs_write_begin() calls folio_unlock(folio) -> VM_BUG_ON_FOLIO() The key reason of the issue that netfs_unlock_abandoned_read_pages() doesn't check the flag NETFS_RREQ_NO_UNLOCK_FOLIO and executes folio_unlock() unconditionally. This patch implements in netfs_unlock_abandoned_read_pages() logic similar to netfs_unlock_read_folio(). Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Signed-off-by: Viacheslav Dubeyko Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-8-dhowells@redhat.com Reviewed-by: Paulo Alcantara (Red Hat) cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: Ceph Development Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/read_retry.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index cca9ac43c0773..68fc869513ef1 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -288,8 +288,15 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) struct folio *folio = folioq_folio(p, slot); if (folio && !folioq_is_marked2(p, slot)) { - trace_netfs_folio(folio, netfs_folio_trace_abandon); - folio_unlock(folio); + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, + &rreq->flags)) { + _debug("no unlock"); + } else { + trace_netfs_folio(folio, + netfs_folio_trace_abandon); + folio_unlock(folio); + } } } } From afeb32d9bf9aaeea51d0f723a19f14afb73bd94d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:47 +0100 Subject: [PATCH 1375/1518] netfs: Fix overrun check in netfs_extract_user_iter() [ Upstream commit 0ef37eef83fad3542ee06db2940433ae1a92b39d ] Fix netfs_extract_user_iter() so that if iov_iter_extract_pages() overfills pages[], then those pages don't get included in the iterator constructed at the end of the function. If there was an overfill, memory corruption has already happened. Fixes: 85dd2c8ff368 ("netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator") Closes: https://sashiko.dev/#/patchset/20260427154639.180684-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-11-dhowells@redhat.com cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/iterator.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 429e4396e1b00..b375567e0520e 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -72,21 +72,24 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, break; } - if (ret > count) { - pr_err("get_pages rc=%zd more than %zu\n", ret, count); + if (WARN(ret > count, + "%s: extract_pages overrun %zd > %zu bytes\n", + __func__, ret, count)) { + ret = -EIO; break; } - count -= ret; - ret += offset; - cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE); - - if (npages + cur_npages > max_pages) { - pr_err("Out of bvec array capacity (%u vs %u)\n", - npages + cur_npages, max_pages); + cur_npages = DIV_ROUND_UP(offset + ret, PAGE_SIZE); + if (WARN(cur_npages > max_pages - npages, + "%s: extract_pages overrun %u > %u pages\n", + __func__, npages + cur_npages, max_pages)) { + ret = -EIO; break; } + count -= ret; + ret += offset; + for (i = 0; i < cur_npages; i++) { len = ret > PAGE_SIZE ? PAGE_SIZE : ret; bvec_set_page(bv + npages + i, *pages++, len - offset, offset); @@ -97,6 +100,11 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, npages += cur_npages; } + /* Note: Don't try to clean up after EIO. Either we got no pages, so + * nothing to clean up, or we got a buffer overrun, memory corruption + * and can't trust the stuff in the buffer (a WARN was emitted). + */ + if (ret < 0 && (ret == -ENOMEM || npages == 0)) { for (i = 0; i < npages; i++) unpin_user_page(bv[i].bv_page); From fb6ec883b48b8789e5e690dcd440d2db941e840c Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:48 +0100 Subject: [PATCH 1376/1518] netfs: Fix netfs_invalidate_folio() to clear dirty bit if all changes gone [ Upstream commit 156ac2ec2ee77c44c4eb7439d6d165247ba12247 ] If a streaming write is made, this will leave the relevant modified folio in a not-uptodate, but dirty state with a netfs_folio struct hung off of folio->private indicating the dirty range. Subsequently truncating the file such that the dirty data in the folio is removed, but the first part of the folio theoretically remains will cause the netfs_folio struct to be discarded... but will leave the dirty flag set. If the folio is then read via mmap(), netfs_read_folio() will see that the page is dirty and jump to netfs_read_gaps() to fill in the missing bits. netfs_read_gaps(), however, expects there to be a netfs_folio struct present and can oops because truncate removed it. Fix this by calling folio_cancel_dirty() in netfs_invalidate_folio() in the event that all the dirty data in the folio is erased (as nfs does). Also add some tracepoints to log modifications to a dirty page. This can be reproduced with something like: dd if=/dev/zero of=/xfstest.test/foo bs=1M count=1 umount /xfstest.test mount /xfstest.test xfs_io -c "w 0xbbbf 0xf96c" \ -c "truncate 0xbbbf" \ -c "mmap -r 0xb000 0x11000" \ -c "mr 0xb000 0x11000" \ /xfstest.test/foo with fscaching disabled (otherwise streaming writes are suppressed) and a change to netfs_perform_write() to disallow streaming writes if the fd is open O_RDWR: if (//(file->f_mode & FMODE_READ) || <--- comment this out netfs_is_cache_enabled(ctx)) { It should be reproducible even without this change, but if prevents the above trivial xfs_io command from reproducing it. Note that the initial dd is important: the file must start out sufficiently large that the zero-point logic doesn't just clear the gaps because it knows there's nothing in the file to read yet. Unmounting and mounting is needed to clear the pagecache (there are other ways to do that that may also work). This was initially reproduced with the generic/522 xfstest on some patches that remove the FMODE_READ restriction. Fixes: 9ebff83e6481 ("netfs: Prep to use folio->private for write grouping and streaming write") Reported-by: Marc Dionne Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-12-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/misc.c | 6 +++++- include/trace/events/netfs.h | 4 ++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 486166460e177..eb309bef72608 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -256,6 +256,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) /* Move the start of the data. */ finfo->dirty_len = fend - iend; finfo->dirty_offset = offset; + trace_netfs_folio(folio, netfs_folio_trace_invalidate_front); return; } @@ -264,12 +265,14 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) */ if (iend >= fend) { finfo->dirty_len = offset - fstart; + trace_netfs_folio(folio, netfs_folio_trace_invalidate_tail); return; } /* A partial write was split. The caller has already zeroed * it, so just absorb the hole. */ + trace_netfs_folio(folio, netfs_folio_trace_invalidate_middle); } return; @@ -277,8 +280,9 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) netfs_put_group(netfs_folio_group(folio)); folio_detach_private(folio); folio_clear_uptodate(folio); + folio_cancel_dirty(folio); kfree(finfo); - return; + trace_netfs_folio(folio, netfs_folio_trace_invalidate_all); } EXPORT_SYMBOL(netfs_invalidate_folio); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index cbe28211106c5..88d814ba1e697 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -194,6 +194,10 @@ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ + EM(netfs_folio_trace_invalidate_all, "inval-all") \ + EM(netfs_folio_trace_invalidate_front, "inval-front") \ + EM(netfs_folio_trace_invalidate_middle, "inval-mid") \ + EM(netfs_folio_trace_invalidate_tail, "inval-tail") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ EM(netfs_folio_trace_kill_g, "kill-g") \ From 185ded4112cd4e2969ca2b80e83caefb94a353fc Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:49 +0100 Subject: [PATCH 1377/1518] netfs: Defer the emission of trace_netfs_folio() [ Upstream commit daeb443b92817021c1234e8eded219e164b7c35d ] Change netfs_perform_write() to keep the netfs_folio trace value in a variable and emit it later to make it easier to choose the value displayed. This is a prerequisite for a subsequent patch. Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-13-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Stable-dep-of: 7b4dcf1b9455 ("netfs: Fix streaming write being overwritten") Signed-off-by: Sasha Levin --- fs/netfs/buffered_write.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 09394ac2c180d..1fa13c2629a73 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -150,6 +150,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } do { + enum netfs_folio_trace trace; struct netfs_folio *finfo; struct netfs_group *group; unsigned long long fpos; @@ -223,7 +224,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(copied == 0)) goto copy_failed; netfs_set_group(folio, netfs_group); - trace_netfs_folio(folio, netfs_folio_is_uptodate); + trace = netfs_folio_is_uptodate; goto copied; } @@ -239,7 +240,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, folio_zero_segment(folio, offset + copied, flen); __netfs_set_group(folio, netfs_group); folio_mark_uptodate(folio); - trace_netfs_folio(folio, netfs_modify_and_clear); + trace = netfs_modify_and_clear; goto copied; } @@ -257,7 +258,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } __netfs_set_group(folio, netfs_group); folio_mark_uptodate(folio); - trace_netfs_folio(folio, netfs_whole_folio_modify); + trace = netfs_whole_folio_modify; goto copied; } @@ -284,7 +285,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(copied == 0)) goto copy_failed; netfs_set_group(folio, netfs_group); - trace_netfs_folio(folio, netfs_just_prefetch); + trace = netfs_just_prefetch; goto copied; } @@ -298,7 +299,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (offset == 0 && copied == flen) { __netfs_set_group(folio, netfs_group); folio_mark_uptodate(folio); - trace_netfs_folio(folio, netfs_streaming_filled_page); + trace = netfs_streaming_filled_page; goto copied; } @@ -313,7 +314,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, finfo->dirty_len = copied; folio_attach_private(folio, (void *)((unsigned long)finfo | NETFS_FOLIO_INFO)); - trace_netfs_folio(folio, netfs_streaming_write); + trace = netfs_streaming_write; goto copied; } @@ -333,9 +334,9 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, folio_detach_private(folio); folio_mark_uptodate(folio); kfree(finfo); - trace_netfs_folio(folio, netfs_streaming_cont_filled_page); + trace = netfs_streaming_cont_filled_page; } else { - trace_netfs_folio(folio, netfs_streaming_write_cont); + trace = netfs_streaming_write_cont; } goto copied; } @@ -351,6 +352,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, continue; copied: + trace_netfs_folio(folio, trace); flush_dcache_folio(folio); /* Update the inode size if we moved the EOF marker */ From ef9b521212e4863814ef7dfe19889abaf55ca840 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:50 +0100 Subject: [PATCH 1378/1518] netfs: Fix streaming write being overwritten [ Upstream commit 7b4dcf1b9455a6e52ac7478b4057dbe10359576d ] In order to avoid reading whilst writing, netfslib will allow "streaming writes" in which dirty data is stored directly into folios without reading them first. Such folios are marked dirty but may not be marked uptodate. If a folio is entirely written by a streaming write, uptodate will be set, otherwise it will have a netfs_folio struct attached to ->private recording the dirty region. In the event that a partially written streaming write page is to be overwritten entirely by a single write(), netfs_perform_write() will try to copy over it, but doesn't discard the netfs_folio if it succeeds; further, it doesn't correctly handle a partial copy that overwrites some of the dirty data. Fix this by the following: (1) If the folio is successfully overwritten, free the netfs_folio struct before marking the page uptodate. (2) If the copy to the folio partially fails, but short of the dirty data, just ignore the copy. (3) If the copy partially fails and overwrites some of the dirty data, accept the copy, update the netfs_folio struct to record the new data. If the folio is now filled, free the netfs_folio and set uptodate, otherwise return a partial write. Found with: fsx -q -N 1000000 -p 10000 -o 128000 -l 600000 \ /xfstest.test/junk --replay-ops=junk.fsxops using the following as junk.fsxops: truncate 0x0 0 0x927c0 write 0x63fb8 0x53c8 0 copy_range 0xb704 0x19b9 0x24429 0x79380 write 0x2402b 0x144a2 0x90660 * write 0x204d5 0x140a0 0x927c0 * copy_range 0x1f72c 0x137d0 0x7a906 0x927c0 * read 0x00000 0x20000 0x9157c read 0x20000 0x20000 0x9157c read 0x40000 0x20000 0x9157c read 0x60000 0x20000 0x9157c read 0x7e1a0 0xcfb9 0x9157c on cifs with the default cache option. It shows folio 0x24 misbehaving if the FMODE_READ check is commented out in netfs_perform_write(): if (//(file->f_mode & FMODE_READ) || netfs_is_cache_enabled(ctx)) { and no fscache. This was initially found with the generic/522 xfstest. Fixes: 8f52de0077ba ("netfs: Reduce number of conditional branches in netfs_perform_write()") Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-14-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_write.c | 47 ++++++++++++++++++++++++++---------- include/trace/events/netfs.h | 3 +++ 2 files changed, 37 insertions(+), 13 deletions(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 1fa13c2629a73..99736895e964f 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -247,18 +247,38 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, /* See if we can write a whole folio in one go. */ if (!maybe_trouble && offset == 0 && part >= flen) { copied = copy_folio_from_iter_atomic(folio, offset, part, iter); - if (unlikely(copied == 0)) + if (likely(copied == part)) { + if (finfo) { + trace = netfs_whole_folio_modify_filled; + goto folio_now_filled; + } + __netfs_set_group(folio, netfs_group); + folio_mark_uptodate(folio); + trace = netfs_whole_folio_modify; + goto copied; + } + if (copied == 0) goto copy_failed; - if (unlikely(copied < part)) { + if (!finfo || copied <= finfo->dirty_offset) { maybe_trouble = true; iov_iter_revert(iter, copied); copied = 0; folio_unlock(folio); goto retry; } - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); - trace = netfs_whole_folio_modify; + + /* We overwrote some existing dirty data, so we have to + * accept the partial write. + */ + finfo->dirty_len += finfo->dirty_offset; + if (finfo->dirty_len == flen) { + trace = netfs_whole_folio_modify_filled_efault; + goto folio_now_filled; + } + if (copied > finfo->dirty_len) + finfo->dirty_len = copied; + finfo->dirty_offset = 0; + trace = netfs_whole_folio_modify_efault; goto copied; } @@ -328,16 +348,10 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto copy_failed; finfo->dirty_len += copied; if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) { - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - folio_mark_uptodate(folio); - kfree(finfo); trace = netfs_streaming_cont_filled_page; - } else { - trace = netfs_streaming_write_cont; + goto folio_now_filled; } + trace = netfs_streaming_write_cont; goto copied; } @@ -351,6 +365,13 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto out; continue; + folio_now_filled: + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + folio_mark_uptodate(folio); + kfree(finfo); copied: trace_netfs_folio(folio, trace); flush_dcache_folio(folio); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 88d814ba1e697..db045135406c9 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -177,6 +177,9 @@ EM(netfs_folio_is_uptodate, "mod-uptodate") \ EM(netfs_just_prefetch, "mod-prefetch") \ EM(netfs_whole_folio_modify, "mod-whole-f") \ + EM(netfs_whole_folio_modify_efault, "mod-whole-f!") \ + EM(netfs_whole_folio_modify_filled, "mod-whole-f+") \ + EM(netfs_whole_folio_modify_filled_efault, "mod-whole-f+!") \ EM(netfs_modify_and_clear, "mod-n-clear") \ EM(netfs_streaming_write, "mod-streamw") \ EM(netfs_streaming_write_cont, "mod-streamw+") \ From 003aa0dd26c964025acd6d1213bcdbd674db2ca9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:51 +0100 Subject: [PATCH 1379/1518] netfs: Fix potential deadlock in write-through mode [ Upstream commit b6a4ae1634b3ad2aaa05222e53d36da532852faf ] Fix netfs_advance_writethrough() to always unlock the supplied folio and to mark it dirty if it isn't yet written to the end. Unfortunately, it can't be marked for writeback until the folio is done with as that may cause a deadlock against mmapped reads and writes. Even though it has been marked dirty, premature writeback can't occur as the caller is holding both inode->i_rwsem (which will prevent concurrent truncation, fallocation, DIO and other writes) and ictx->wb_lock (which will cause flushing to wait and writeback to skip or wait). Note that this may be easier to deal with once the queuing of folios is split from the generation of subrequests. Fixes: 288ace2f57c9 ("netfs: New writeback implementation") Closes: https://sashiko.dev/#/patchset/20260427154639.180684-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-15-dhowells@redhat.com cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/write_issue.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 2db688f941251..9bf05099155dc 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -413,12 +413,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, if (streamw) netfs_issue_write(wreq, cache); - /* Flip the page to the writeback state and unlock. If we're called - * from write-through, then the page has already been put into the wb - * state. - */ - if (wreq->origin == NETFS_WRITEBACK) - folio_start_writeback(folio); + folio_start_writeback(folio); folio_unlock(folio); if (fgroup == NETFS_FOLIO_COPY_TO_CACHE) { @@ -646,29 +641,41 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c struct folio *folio, size_t copied, bool to_page_end, struct folio **writethrough_cache) { + int ret; + _enter("R=%x ic=%zu ws=%u cp=%zu tp=%u", wreq->debug_id, wreq->buffer.iter.count, wreq->wsize, copied, to_page_end); - if (!*writethrough_cache) { - if (folio_test_dirty(folio)) - /* Sigh. mmap. */ - folio_clear_dirty_for_io(folio); + /* The folio is locked. */ + if (*writethrough_cache != folio) { + if (*writethrough_cache) { + /* Did the folio get moved? */ + folio_put(*writethrough_cache); + *writethrough_cache = NULL; + } /* We can make multiple writes to the folio... */ - folio_start_writeback(folio); if (wreq->len == 0) trace_netfs_folio(folio, netfs_folio_trace_wthru); else trace_netfs_folio(folio, netfs_folio_trace_wthru_plus); *writethrough_cache = folio; + folio_get(folio); } wreq->len += copied; - if (!to_page_end) + + if (!to_page_end) { + folio_mark_dirty(folio); + folio_unlock(folio); return 0; + } + ret = netfs_write_folio(wreq, wbc, folio); + folio_put(*writethrough_cache); *writethrough_cache = NULL; - return netfs_write_folio(wreq, wbc, folio); + wreq->submitted = wreq->len; + return ret; } /* @@ -682,8 +689,12 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c _enter("R=%x", wreq->debug_id); - if (writethrough_cache) + if (writethrough_cache) { + folio_lock(writethrough_cache); netfs_write_folio(wreq, wbc, writethrough_cache); + folio_put(writethrough_cache); + wreq->submitted = wreq->len; + } netfs_end_issue_write(wreq); From 0b18cd70ebab7ea13e9883e4e9a62011e65c7d3b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:52 +0100 Subject: [PATCH 1380/1518] netfs: Fix read-gaps to remove netfs_folio from filled folio [ Upstream commit a41168aef634356a9b87ec44349e3c82835700a5 ] Fix netfs_read_gaps() to remove the netfs_folio record from the folio record before marking the folio uptodate if it successfully fills the gaps around the dirty data in a streaming write folio (dirty, but not uptodate). Found with: fsx -q -N 1000000 -p 10000 -o 128000 -l 600000 \ /xfstest.test/junk --replay-ops=junk.fsxops using the following as junk.fsxops: truncate 0x0 0x138b1 0x8b15d * write 0x507ee 0x10df7 0x927c0 write 0x19993 0x10e04 0x927c0 * mapwrite 0x66214 0x1a253 0x927c0 copy_range 0xb704 0x89b9 0x24429 0x79380 write 0x2402b 0x144a2 0x90660 * mapwrite 0x204d5 0x140a0 0x927c0 * copy_range 0x1f72c 0x137d0 0x7a906 0x927c0 * read 0 0x9157c 0x9157c on cifs with the default cache option. It shows folio 0x24 misbehaving if the FMODE_READ check is commented out in netfs_perform_write(): if (//(file->f_mode & FMODE_READ) || netfs_is_cache_enabled(ctx)) { and no fscache. This was initially found with the generic/522 xfstest. Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-16-dhowells@redhat.com Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index e6157122da3a4..3531c19eea97a 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -394,6 +394,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) { struct netfs_io_request *rreq; struct address_space *mapping = folio->mapping; + struct netfs_group *group = netfs_folio_group(folio); struct netfs_folio *finfo = netfs_folio_info(folio); struct netfs_inode *ctx = netfs_inode(mapping->host); struct folio *sink = NULL; @@ -460,6 +461,12 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) ret = netfs_wait_for_read(rreq); if (ret >= 0) { + if (group) + folio_change_private(folio, group); + else + folio_detach_private(folio); + kfree(finfo); + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); flush_dcache_folio(folio); folio_mark_uptodate(folio); } @@ -495,10 +502,8 @@ int netfs_read_folio(struct file *file, struct folio *folio) struct netfs_inode *ctx = netfs_inode(mapping->host); int ret; - if (folio_test_dirty(folio)) { - trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + if (folio_test_dirty(folio)) return netfs_read_gaps(file, folio); - } _enter("%lx", folio->index); From 616578e40dcba3f94810d841c5a52b7e3bc8ede7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:53 +0100 Subject: [PATCH 1381/1518] netfs: Fix write streaming disablement if fd open O_RDWR [ Upstream commit 70a7b9193bbbfceaab5974de66834c64ccc875dd ] In netfs_perform_write(), "write streaming" (the caching of dirty data in dirty but !uptodate folios) is performed to avoid the need to read data that is just going to get immediately overwritten. However, this is/will be disabled in three circumstances: if the fd is open O_RDWR, if fscache is in use (as we need to round out the blocks for DIO) or if content encryption is enabled (again for rounding out purposes). The idea behind disabling it if the fd is open O_RDWR is that we'd need to flush the write-streaming page before we could read the data, particularly through mmap. But netfs now fills in the gaps if ->read_folio() is called on the page, so that is unnecessary. Further, this doesn't actually work if a separate fd is open for reading. Fix this by removing the check for O_RDWR, thereby allowing streaming writes even when we might read. This caused a number of problems with the generic/522 xfstest, but those are now fixed. Fixes: c38f4e96e605 ("netfs: Provide func to copy data to pagecache for buffered write") Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-17-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_write.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 99736895e964f..60215a7723574 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -204,11 +204,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } /* Decide how we should modify a folio. We might be attempting - * to do write-streaming, in which case we don't want to a - * local RMW cycle if we can avoid it. If we're doing local - * caching or content crypto, we award that priority over - * avoiding RMW. If the file is open readably, then we also - * assume that we may want to read what we wrote. + * to do write-streaming, as we don't want to a local RMW cycle + * if we can avoid it. If we're doing local caching or content + * crypto, we award that priority over avoiding RMW. If the + * file is open readably, then we let ->read_folio() fill in + * the gaps. */ finfo = netfs_folio_info(folio); group = netfs_folio_group(folio); @@ -284,12 +284,9 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, /* We don't want to do a streaming write on a file that loses * caching service temporarily because the backing store got - * culled and we don't really want to get a streaming write on - * a file that's open for reading as ->read_folio() then has to - * be able to flush it. + * culled. */ - if ((file->f_mode & FMODE_READ) || - netfs_is_cache_enabled(ctx)) { + if (netfs_is_cache_enabled(ctx)) { if (finfo) { netfs_stat(&netfs_n_wh_wstream_conflict); goto flush_content; From d4f4bc87c76511cf2532448b0fa40c25e894bd7d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:54 +0100 Subject: [PATCH 1382/1518] netfs: Fix early put of sink folio in netfs_read_gaps() [ Upstream commit 3e5dd91b87a8b1450217b56a336bee315f40da7d ] Fix netfs_read_gaps() to release the sink page it uses after waiting for the request to complete. The way the sink page is used is that an ITER_BVEC-class iterator is created that has the gaps from the target folio at either end, but has the sink page tiled over the middle so that a single read op can fill in both gaps. The bug was found by KASAN detecting a UAF on the generic/075 xfstest in the cifsd kernel thread that handles reception of data from the TCP socket: BUG: KASAN: use-after-free in _copy_to_iter+0x48a/0xa20 Write of size 885 at addr ffff888107f92000 by task cifsd/1285 CPU: 2 UID: 0 PID: 1285 Comm: cifsd Not tainted 7.0.0 #6 PREEMPT(lazy) Call Trace: dump_stack_lvl+0x5d/0x80 print_report+0x17f/0x4f1 kasan_report+0x100/0x1e0 kasan_check_range+0x10f/0x1e0 __asan_memcpy+0x3c/0x60 _copy_to_iter+0x48a/0xa20 __skb_datagram_iter+0x2c9/0x430 skb_copy_datagram_iter+0x6e/0x160 tcp_recvmsg_locked+0xce0/0x1130 tcp_recvmsg+0xeb/0x300 inet_recvmsg+0xcf/0x3a0 sock_recvmsg+0xea/0x100 cifs_readv_from_socket+0x3a6/0x4d0 [cifs] cifs_read_iter_from_socket+0xdd/0x130 [cifs] cifs_readv_receive+0xaad/0xb10 [cifs] cifs_demultiplex_thread+0x1148/0x1740 [cifs] kthread+0x1cf/0x210 Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Reported-by: Steve French Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-18-dhowells@redhat.com Reviewed-by: Paulo Alcantara (Red Hat) cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 3531c19eea97a..762ff928bc878 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -456,9 +456,6 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) netfs_read_to_pagecache(rreq, NULL); - if (sink) - folio_put(sink); - ret = netfs_wait_for_read(rreq); if (ret >= 0) { if (group) @@ -470,6 +467,9 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) flush_dcache_folio(folio); folio_mark_uptodate(folio); } + + if (sink) + folio_put(sink); folio_unlock(folio); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; From 22ae28aae43623be235ff455558cdd13fbe2daeb Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:55 +0100 Subject: [PATCH 1383/1518] netfs: Fix leak of request in netfs_write_begin() error handling [ Upstream commit 5046a34f0643441f05b0253ea64e1a3af87efe14 ] Fix netfs_write_begin() to not leak our ref on the request in the event that we get an error from netfs_wait_for_read(). Fixes: 4090b31422a6 ("netfs: Add a function to consolidate beginning a read") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-19-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 762ff928bc878..085cd392bf5ac 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -686,9 +686,9 @@ int netfs_write_begin(struct netfs_inode *ctx, netfs_read_to_pagecache(rreq, NULL); ret = netfs_wait_for_read(rreq); + netfs_put_request(rreq, netfs_rreq_trace_put_return); if (ret < 0) goto error; - netfs_put_request(rreq, netfs_rreq_trace_put_return); have_folio: ret = folio_wait_private_2_killable(folio); From 6080fa3ecfbb4448a3b47368629534c09b6ec750 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:56 +0100 Subject: [PATCH 1384/1518] netfs: Fix potential UAF in netfs_unlock_abandoned_read_pages() [ Upstream commit dbe556972100fabb8e5a1b3d2163831ff07b1e8e ] netfs_unlock_abandoned_read_pages(rreq) accesses the index of the folios it is wanting to unlock and compares that to rreq->no_unlock_folio so that it doesn't unlock a folio being read for netfs_perform_write() or netfs_write_begin(). However, given that netfs_unlock_abandoned_read_pages() is called _after_ NETFS_RREQ_IN_PROGRESS is cleared, the one folio that it's not allowed to dereference is the one specified by ->no_unlock_folio as ownership immediately reverts to the caller. Fix this by storing the folio pointer instead and using that rather than the index. Also fix netfs_unlock_read_folio() where the same applies. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-20-dhowells@redhat.com cc: Paulo Alcantara cc: Viacheslav Dubeyko cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 4 ++-- fs/netfs/read_collect.c | 2 +- fs/netfs/read_retry.c | 2 +- include/linux/netfs.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 085cd392bf5ac..ebaabec376326 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -669,7 +669,7 @@ int netfs_write_begin(struct netfs_inode *ctx, ret = PTR_ERR(rreq); goto error; } - rreq->no_unlock_folio = folio->index; + rreq->no_unlock_folio = folio; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); @@ -735,7 +735,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, goto error; } - rreq->no_unlock_folio = folio->index; + rreq->no_unlock_folio = folio; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index d2d902f466271..4c7312a4c8597 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -83,7 +83,7 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, } just_unlock: - if (folio->index == rreq->no_unlock_folio && + if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { _debug("no unlock"); } else { diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 68fc869513ef1..999177426141a 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -288,7 +288,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) struct folio *folio = folioq_folio(p, slot); if (folio && !folioq_is_marked2(p, slot)) { - if (folio->index == rreq->no_unlock_folio && + if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { _debug("no unlock"); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ba17ac5bf356a..62a528f90666b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -252,7 +252,7 @@ struct netfs_io_request { unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ unsigned long long abandon_to; /* Position to abandon folios to */ - pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ + const struct folio *no_unlock_folio; /* Don't unlock this folio after read */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ From 3d9601c029b934b5b6a10f99791467b10eb6b211 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:57 +0100 Subject: [PATCH 1385/1518] netfs: Fix partial invalidation of streaming-write folio [ Upstream commit 6d91acc7fb85d33ea58fca9b964a32a453937f4b ] In netfs_invalidate_folio(), if the region of a partial invalidation overlaps the front (but not all) of a dirty write cached in a streaming write page (dirty, but not uptodate, with the dirty region tracked by a netfs_folio struct), the function modifies the dirty region - but incorrectly as it moves the region forward by setting the start to the start, not the end, of the invalidation region. Fix this by setting finfo->dirty_offset to the end of the invalidation region (iend). Fixes: cce6bfa6ca0e ("netfs: Fix trimming of streaming-write folios in netfs_inval_folio()") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-21-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/misc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index eb309bef72608..1109ac3791281 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -255,7 +255,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) goto erase_completely; /* Move the start of the data. */ finfo->dirty_len = fend - iend; - finfo->dirty_offset = offset; + finfo->dirty_offset = iend; trace_netfs_folio(folio, netfs_folio_trace_invalidate_front); return; } From 551b5c71ee312ca7646ddb605231c1016e8cbb18 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:58 +0100 Subject: [PATCH 1386/1518] netfs: Fix folio->private handling in netfs_perform_write() [ Upstream commit ccde2ac757c713535b224233a296de40efe5212d ] Under some circumstances, netfs_perform_write() doesn't correctly manipulate folio->private between NULL, NETFS_FOLIO_COPY_TO_CACHE, pointing to a group and pointing to a netfs_folio struct, leading to potential multiple attachments of private data with associated folio ref leaks and also leaks of netfs_folio structs or netfs_group refs. Fix this by consolidating the place at which a folio is marked uptodate in one place and having that look at what's attached to folio->private and decide how to clean it up and then set the new group. Also, the content shouldn't be flushed if group is NULL, even if a group is specified in the netfs_group parameter, as that would be the case for a new folio. A filesystem should always specify netfs_group or never specify netfs_group. The Sashiko auto-review tool noted that it was theoretically possible that the fpos >= ctx->zero_point section might leak if it modified a streaming write folio. This is unlikely, but with a network filesystem, third party changes can happen. It also pointed out that __netfs_set_group() would leak if called multiple times on the same folio from the "whole folio modify section". Fixes: 8f52de0077ba ("netfs: Reduce number of conditional branches in netfs_perform_write()") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-22-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_write.c | 134 +++++++++++++++++++++-------------- include/trace/events/netfs.h | 1 + 2 files changed, 82 insertions(+), 53 deletions(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 60215a7723574..dd0ce7b769ce0 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -13,24 +13,6 @@ #include #include "internal.h" -static void __netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) -{ - if (netfs_group) - folio_attach_private(folio, netfs_get_group(netfs_group)); -} - -static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) -{ - void *priv = folio_get_private(folio); - - if (unlikely(priv != netfs_group)) { - if (netfs_group && (!priv || priv == NETFS_FOLIO_COPY_TO_CACHE)) - folio_attach_private(folio, netfs_get_group(netfs_group)); - else if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) - folio_detach_private(folio); - } -} - /* * Grab a folio for writing and lock it. Attempt to allocate as large a folio * as possible to hold as much of the remaining length as possible in one go. @@ -158,6 +140,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, size_t offset; /* Offset into pagecache folio */ size_t part; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + void *priv; offset = pos & (max_chunk - 1); part = min(max_chunk - offset, iov_iter_count(iter)); @@ -203,6 +186,25 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto error_folio_unlock; } + finfo = netfs_folio_info(folio); + group = netfs_folio_group(folio); + + /* If the requested group differs from the group set on the + * page, then we need to flush out the folio if it has a group + * set (ie. is non-NULL). Note that COPY_TO_CACHE is a special + * case, being a netfs annotation rather than an actual group. + * + * The filesystem isn't permitted to mix writes with groups and + * writes without groups as the NULL group is used to indicate + * that no group is set. + */ + if (unlikely(group != netfs_group) && + group != NETFS_FOLIO_COPY_TO_CACHE && + group) { + WARN_ON_ONCE(!netfs_group); + goto flush_content; + } + /* Decide how we should modify a folio. We might be attempting * to do write-streaming, as we don't want to a local RMW cycle * if we can avoid it. If we're doing local caching or content @@ -210,22 +212,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, * file is open readably, then we let ->read_folio() fill in * the gaps. */ - finfo = netfs_folio_info(folio); - group = netfs_folio_group(folio); - - if (unlikely(group != netfs_group) && - group != NETFS_FOLIO_COPY_TO_CACHE) - goto flush_content; - if (folio_test_uptodate(folio)) { if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (unlikely(copied == 0)) goto copy_failed; - netfs_set_group(folio, netfs_group); trace = netfs_folio_is_uptodate; - goto copied; + goto copied_uptodate; } /* If the page is above the zero-point then we assume that the @@ -238,24 +232,22 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(copied == 0)) goto copy_failed; folio_zero_segment(folio, offset + copied, flen); - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); - trace = netfs_modify_and_clear; - goto copied; + if (finfo) + trace = netfs_modify_and_clear_rm_finfo; + else + trace = netfs_modify_and_clear; + goto mark_uptodate; } /* See if we can write a whole folio in one go. */ if (!maybe_trouble && offset == 0 && part >= flen) { copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (likely(copied == part)) { - if (finfo) { + if (finfo) trace = netfs_whole_folio_modify_filled; - goto folio_now_filled; - } - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); - trace = netfs_whole_folio_modify; - goto copied; + else + trace = netfs_whole_folio_modify; + goto mark_uptodate; } if (copied == 0) goto copy_failed; @@ -273,7 +265,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, finfo->dirty_len += finfo->dirty_offset; if (finfo->dirty_len == flen) { trace = netfs_whole_folio_modify_filled_efault; - goto folio_now_filled; + goto mark_uptodate; } if (copied > finfo->dirty_len) finfo->dirty_len = copied; @@ -301,11 +293,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (unlikely(copied == 0)) goto copy_failed; - netfs_set_group(folio, netfs_group); trace = netfs_just_prefetch; - goto copied; + goto copied_uptodate; } + /* Do a streaming write on a folio that has nothing in it yet. */ if (!finfo) { ret = -EIO; if (WARN_ON(folio_get_private(folio))) @@ -314,10 +306,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(copied == 0)) goto copy_failed; if (offset == 0 && copied == flen) { - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); trace = netfs_streaming_filled_page; - goto copied; + goto mark_uptodate; } finfo = kzalloc(sizeof(*finfo), GFP_KERNEL); @@ -346,7 +336,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, finfo->dirty_len += copied; if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) { trace = netfs_streaming_cont_filled_page; - goto folio_now_filled; + goto mark_uptodate; } trace = netfs_streaming_write_cont; goto copied; @@ -362,13 +352,36 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto out; continue; - folio_now_filled: - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); + /* Mark a folio as being up to data when we've filled it + * completely. If the folio has a group attached, then it must + * be the same group, otherwise we should have flushed it out + * above. We have to get rid of the netfs_folio struct if + * there was one. + */ + mark_uptodate: folio_mark_uptodate(folio); - kfree(finfo); + + copied_uptodate: + priv = folio_get_private(folio); + if (likely(priv == netfs_group)) { + /* Already set correctly; no change required. */ + } else if (priv == NETFS_FOLIO_COPY_TO_CACHE) { + if (!netfs_group) + folio_detach_private(folio); + else + folio_change_private(folio, netfs_get_group(netfs_group)); + } else if (!priv) { + folio_attach_private(folio, netfs_get_group(netfs_group)); + } else { + WARN_ON_ONCE(!finfo); + if (netfs_group) + /* finfo->netfs_group has a ref */ + folio_change_private(folio, netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } + copied: trace_netfs_folio(folio, trace); flush_dcache_folio(folio); @@ -531,6 +544,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr struct inode *inode = file_inode(file); struct netfs_inode *ictx = netfs_inode(inode); vm_fault_t ret = VM_FAULT_NOPAGE; + void *priv; int err; _enter("%lx", folio->index); @@ -551,7 +565,9 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr } group = netfs_folio_group(folio); - if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE) { + if (group && + group != netfs_group && + group != NETFS_FOLIO_COPY_TO_CACHE) { folio_unlock(folio); err = filemap_fdatawrite_range(mapping, folio_pos(folio), @@ -573,7 +589,19 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus); else trace_netfs_folio(folio, netfs_folio_trace_mkwrite); - netfs_set_group(folio, netfs_group); + + priv = folio_get_private(folio); + if (priv != netfs_group) { + if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) + folio_detach_private(folio); + else if (netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) + folio_change_private(folio, netfs_get_group(netfs_group)); + else if (netfs_group && !priv) + folio_attach_private(folio, netfs_get_group(netfs_group)); + else + WARN_ON_ONCE(1); + } + file_update_time(file); set_bit(NETFS_ICTX_MODIFIED_ATTR, &ictx->flags); if (ictx->ops->post_modify) diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index db045135406c9..3fe3980902c24 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -181,6 +181,7 @@ EM(netfs_whole_folio_modify_filled, "mod-whole-f+") \ EM(netfs_whole_folio_modify_filled_efault, "mod-whole-f+!") \ EM(netfs_modify_and_clear, "mod-n-clear") \ + EM(netfs_modify_and_clear_rm_finfo, "mod-n-clear+") \ EM(netfs_streaming_write, "mod-streamw") \ EM(netfs_streaming_write_cont, "mod-streamw+") \ EM(netfs_flush_content, "flush") \ From f17b9121bb99f88188ec9be2db5da1d561f4c01b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:59 +0100 Subject: [PATCH 1387/1518] netfs: Fix netfs_read_folio() to wait on writeback [ Upstream commit ded0c6f1606061148c202825f7e53d711f9f84cf ] Fix netfs_read_folio() to wait for an ongoing writeback to complete so that it can trust the dirty flag and whatever is attached to folio->private (folio->private may get cleaned up by the collector before it clears the writeback flag). Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-23-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index ebaabec376326..fab3181c7f869 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -502,6 +502,8 @@ int netfs_read_folio(struct file *file, struct folio *folio) struct netfs_inode *ctx = netfs_inode(mapping->host); int ret; + folio_wait_writeback(folio); + if (folio_test_dirty(folio)) return netfs_read_gaps(file, folio); From 77bb293049d61e04c12b24ebbffafaf5ab36af90 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:34:00 +0100 Subject: [PATCH 1388/1518] netfs, afs: Fix write skipping in dir/link writepages [ Upstream commit 9871938f99cc6cb266a77265491660e2375271f5 ] Fix netfs_write_single() and afs_single_writepages() to better handle a write that would be skipped due to lock contention and WB_SYNC_NONE by returning 1 from netfs_write_single() if it skipped and making afs_single_writepages() skip also. If a skip occurs, the inode must be re-marked as the VFS may have cleared the mark. This is really only theoretical for directories in netfs_write_single() as the only path to that is through afs_single_writepages() that takes the ->validate_lock around it, thereby serialising it. Fixes: 6dd80936618c ("afs: Use netfslib for directories") Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-24-dhowells@redhat.com cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/afs/dir.c | 11 ++++++++++- fs/netfs/write_issue.c | 7 ++++++- 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 89d36e3e5c799..fa84610e0b0d9 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -2207,7 +2207,14 @@ int afs_single_writepages(struct address_space *mapping, /* Need to lock to prevent the folio queue and folios from being thrown * away. */ - down_read(&dvnode->validate_lock); + if (!down_read_trylock(&dvnode->validate_lock)) { + if (wbc->sync_mode == WB_SYNC_NONE) { + /* The VFS will have undirtied the inode. */ + netfs_single_mark_inode_dirty(&dvnode->netfs.inode); + return 0; + } + down_read(&dvnode->validate_lock); + } if (is_dir ? test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) : @@ -2215,6 +2222,8 @@ int afs_single_writepages(struct address_space *mapping, iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size_read(&dvnode->netfs.inode)); ret = netfs_writeback_single(mapping, wbc, &iter); + if (ret == 1) + ret = 0; /* Skipped write due to lock conflict. */ } up_read(&dvnode->validate_lock); diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9bf05099155dc..03d170b9022b7 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -829,6 +829,9 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq, * * Write a monolithic, non-pagecache object back to the server and/or * the cache. + * + * Return: 0 if successful; 1 if skipped due to lock conflict and WB_SYNC_NONE; + * or a negative error code. */ int netfs_writeback_single(struct address_space *mapping, struct writeback_control *wbc, @@ -845,8 +848,10 @@ int netfs_writeback_single(struct address_space *mapping, if (!mutex_trylock(&ictx->wb_lock)) { if (wbc->sync_mode == WB_SYNC_NONE) { + /* The VFS will have undirtied the inode. */ + netfs_single_mark_inode_dirty(&ictx->inode); netfs_stat(&netfs_n_wb_lock_skip); - return 0; + return 1; } netfs_stat(&netfs_n_wb_lock_wait); mutex_lock(&ictx->wb_lock); From cfd62907f3cdbc3b6da8f49ba907c0390018fe5e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 9 May 2026 00:13:37 +0200 Subject: [PATCH 1389/1518] net: ethernet: cortina: Make RX SKB per-port [ Upstream commit 06937db21ee311ed07eba47954447245041a982d ] The SKB used to assemble packets from fragments in gmac_rx() is static local, but the Gemini has two ethernet ports, meaning there can be races between the ports on a bad day if a device is using both. Make the RX SKB a per-port variable and carry it over between invocations in the port struct instead. Zero the pointer once we call napi_gro_frags(), on error (after calling napi_free_frags()) or if the port is stopped. Zero it in some place where not strictly necessary just to emphasize what is going on. This was found by Sashiko during normal patch review. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Link: https://sashiko.dev/#/patchset/20260505-gemini-ethernet-fix-v2-1-997c31d06079%40kernel.org Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260509-gemini-ethernet-fixes-v1-2-6c5d20ddc35b@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/cortina/gemini.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 6a2004bbe87f9..7cf3ed7215a30 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -122,6 +122,8 @@ struct gemini_ethernet_port { struct napi_struct napi; struct hrtimer rx_coalesce_timer; unsigned int rx_coalesce_nsecs; + struct sk_buff *rx_skb; + unsigned int freeq_refill; struct gmac_txq txq[TX_QUEUE_NUM]; unsigned int txq_order; @@ -1443,10 +1445,10 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short m = (1 << port->rxq_order) - 1; struct gemini_ethernet *geth = port->geth; void __iomem *ptr_reg = port->rxq_rwptr; + struct sk_buff *skb = port->rx_skb; unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; - static struct sk_buff *skb; union gmac_rxdesc_0 word0; union gmac_rxdesc_1 word1; union gmac_rxdesc_3 word3; @@ -1500,6 +1502,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (skb) { napi_free_frags(&port->napi); port->stats.rx_dropped++; + skb = NULL; } skb = gmac_skb_if_good_frame(port, word0, frame_len); @@ -1550,6 +1553,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) port->stats.rx_dropped++; } + port->rx_skb = skb; writew(r, ptr_reg); return budget; } @@ -1877,6 +1881,7 @@ static int gmac_stop(struct net_device *netdev) gmac_disable_tx_rx(netdev); gmac_stop_dma(port); napi_disable(&port->napi); + port->rx_skb = NULL; gmac_enable_irq(netdev, 0); gmac_cleanup_rxq(netdev); From 3cd05250a2dfa9f17035f51a0b23d0b70dfa9209 Mon Sep 17 00:00:00 2001 From: Andreas Haarmann-Thiemann Date: Tue, 5 May 2026 23:52:17 +0200 Subject: [PATCH 1390/1518] net: ethernet: cortina: Drop half-assembled SKB MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b266bacba796ff5c4dcd2ae2fc08aacf7ab39153 ] In gmac_rx() (drivers/net/ethernet/cortina/gemini.c), when gmac_get_queue_page() returns NULL for the second page of a multi-page fragment, the driver logs an error and continues — but does not free the partially assembled skb that was being assembled via napi_build_skb() / napi_get_frags(). Free the in-progress partially assembled skb via napi_free_frags() and increase the number of dropped frames appropriately and assign the skb pointer NULL to make sure it is not lingering around, matching the pattern already used elsewhere in the driver. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Signed-off-by: Andreas Haarmann-Thiemann Signed-off-by: Linus Walleij Reviewed-by: Alexander Lobakin Link: https://patch.msgid.link/20260505-gemini-ethernet-fix-v2-1-997c31d06079@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/cortina/gemini.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 7cf3ed7215a30..63f444e13d6f2 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1494,6 +1494,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) gpage = gmac_get_queue_page(geth, port, mapping + PAGE_SIZE); if (!gpage) { dev_err(geth->dev, "could not find mapping\n"); + if (skb) { + napi_free_frags(&port->napi); + port->stats.rx_dropped++; + skb = NULL; + } continue; } page = gpage->page; From c373b34877afea61c89e0dd2e38948c624249b9b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 9 May 2026 00:13:38 +0200 Subject: [PATCH 1391/1518] net: ethernet: cortina: Carry over frag counter [ Upstream commit ebd8ec2b309e3a447851b456ccaf8fb39f3661e7 ] The gmac_rx() NAPI poll function assembles packets in an SKB from a ring buffer. If the ring buffer gets completely emptied during a poll cycle, we exit gmac_rx(), but the packet is not yet completely assembled in the SKB, yet the fragment counter frag_nr is reset to zero on the next invocation. Solve this by making the RX fragment counter a part of the port struct, and carry it over between invocations. Reset the fragment counter only right after calling napi_gro_frags(), on error (after calling napi_free_frags()) or if stopping the port. Reset it in some place where not strictly necessary just to emphasize what is going on. This was found by Sashiko during normal patch review. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Link: https://sashiko.dev/#/patchset/20260505-gemini-ethernet-fix-v2-1-997c31d06079%40kernel.org Signed-off-by: Linus Walleij Link: https://patch.msgid.link/20260509-gemini-ethernet-fixes-v1-3-6c5d20ddc35b@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/cortina/gemini.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 63f444e13d6f2..40bec34f06a7b 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -123,6 +123,7 @@ struct gemini_ethernet_port { struct hrtimer rx_coalesce_timer; unsigned int rx_coalesce_nsecs; struct sk_buff *rx_skb; + unsigned int rx_frag_nr; unsigned int freeq_refill; struct gmac_txq txq[TX_QUEUE_NUM]; @@ -1445,6 +1446,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short m = (1 << port->rxq_order) - 1; struct gemini_ethernet *geth = port->geth; void __iomem *ptr_reg = port->rxq_rwptr; + unsigned int frag_nr = port->rx_frag_nr; struct sk_buff *skb = port->rx_skb; unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; @@ -1458,7 +1460,6 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short r, w; union dma_rwptr rw; dma_addr_t mapping; - int frag_nr = 0; spin_lock_irqsave(&geth->irq_lock, flags); rw.bits32 = readl(ptr_reg); @@ -1498,6 +1499,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) napi_free_frags(&port->napi); port->stats.rx_dropped++; skb = NULL; + frag_nr = 0; } continue; } @@ -1508,6 +1510,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) napi_free_frags(&port->napi); port->stats.rx_dropped++; skb = NULL; + frag_nr = 0; } skb = gmac_skb_if_good_frame(port, word0, frame_len); @@ -1542,6 +1545,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (word3.bits32 & EOF_BIT) { napi_gro_frags(&port->napi); skb = NULL; + frag_nr = 0; --budget; } continue; @@ -1550,6 +1554,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (skb) { napi_free_frags(&port->napi); skb = NULL; + frag_nr = 0; } if (mapping) @@ -1559,6 +1564,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) } port->rx_skb = skb; + port->rx_frag_nr = frag_nr; writew(r, ptr_reg); return budget; } @@ -1887,6 +1893,7 @@ static int gmac_stop(struct net_device *netdev) gmac_stop_dma(port); napi_disable(&port->napi); port->rx_skb = NULL; + port->rx_frag_nr = 0; gmac_enable_irq(netdev, 0); gmac_cleanup_rxq(netdev); From 9bc70fe995da15dab1de93174f8a7e6db9b55c88 Mon Sep 17 00:00:00 2001 From: Ethan Nelson-Moore Date: Fri, 8 May 2026 19:37:28 -0700 Subject: [PATCH 1392/1518] net: ethernet: cs89x0: remove stale CONFIG_MACH_MX31ADS reference [ Upstream commit 36a8d04a8293afcb9304cf0cd3741f67698f2a1a ] The legacy ARM board file for MACH_MX31ADS was removed in commit c93197b0041d ("ARM: imx: Remove i.MX31 board files"), but a reference to it remained in the cs89x0 driver. Drop this unused code. Signed-off-by: Ethan Nelson-Moore Fixes: c93197b0041d ("ARM: imx: Remove i.MX31 board files") Link: https://patch.msgid.link/20260509023732.42256-1-enelsonmoore@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/cirrus/cs89x0.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index fa5857923db4c..b4bfd6c174e78 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1271,7 +1271,6 @@ static const struct net_device_ops net_ops = { static void __init reset_chip(struct net_device *dev) { -#if !defined(CONFIG_MACH_MX31ADS) struct net_local *lp = netdev_priv(dev); unsigned long reset_start_time; @@ -1298,7 +1297,6 @@ static void __init reset_chip(struct net_device *dev) while ((readreg(dev, PP_SelfST) & INIT_DONE) == 0 && time_before(jiffies, reset_start_time + 2)) ; -#endif /* !CONFIG_MACH_MX31ADS */ } /* This is the real probe routine. From acde4692afcdaea6de3e2996ddfaeaa7ae6b0130 Mon Sep 17 00:00:00 2001 From: Nicolas Escande Date: Wed, 6 May 2026 15:42:38 +0200 Subject: [PATCH 1393/1518] wifi: ath11k: fix error path leaks in some WMI WOW calls [ Upstream commit 55dda532bbc261aef495e403c8900c5e2ab5fa34 ] Fix two instances where we used to directly return the result of ath11k_wmi_cmd_send(...). Because we did not check the return value, we also did not free the skb in the error path. Fixes: 79802b13a492 ("ath11k: implement WoW enable and wakeup commands") Signed-off-by: Nicolas Escande Reviewed-by: Baochen Qiang Reviewed-by: Rameshkumar Sundaram Link: https://patch.msgid.link/20260506134240.2284016-2-nico.escande@gmail.com Signed-off-by: Jeff Johnson Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/wmi.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 110035dae8a61..e1b00dc811e7b 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -9191,6 +9191,7 @@ int ath11k_wmi_wow_host_wakeup_ind(struct ath11k *ar) struct wmi_wow_host_wakeup_ind *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9204,14 +9205,20 @@ int ath11k_wmi_wow_host_wakeup_ind(struct ath11k *ar) ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow host wakeup ind\n"); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_wow_enable(struct ath11k *ar) { struct wmi_wow_enable_cmd *cmd; struct sk_buff *skb; - int len; + int ret, len; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9226,7 +9233,13 @@ int ath11k_wmi_wow_enable(struct ath11k *ar) cmd->pause_iface_config = WOW_IFACE_PAUSE_ENABLED; ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow enable\n"); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_ENABLE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_scan_prob_req_oui(struct ath11k *ar, From d94127d04017f48408a1d0378b173f4ce4d7f72b Mon Sep 17 00:00:00 2001 From: Nicolas Escande Date: Wed, 6 May 2026 15:42:40 +0200 Subject: [PATCH 1394/1518] wifi: ath11k: fix error path leak in ath11k_tm_cmd_wmi_ftm() [ Upstream commit 7320d6eb861e9913193a7801834c661381756a79 ] This is similar to what was fixed by previous patches. We have a call to ath11k_wmi_cmd_send() which does check the return value, but forgot to free the related skb on error. Fixes: b43310e44edc ("wifi: ath11k: factory test mode support") Signed-off-by: Nicolas Escande Reviewed-by: Baochen Qiang Reviewed-by: Rameshkumar Sundaram Link: https://patch.msgid.link/20260506134240.2284016-4-nico.escande@gmail.com Signed-off-by: Jeff Johnson Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/testmode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/ath/ath11k/testmode.c b/drivers/net/wireless/ath/ath11k/testmode.c index a9751ea2a0b73..c72eed358f6dd 100644 --- a/drivers/net/wireless/ath/ath11k/testmode.c +++ b/drivers/net/wireless/ath/ath11k/testmode.c @@ -457,6 +457,7 @@ static int ath11k_tm_cmd_wmi_ftm(struct ath11k *ar, struct nlattr *tb[]) ret = ath11k_wmi_cmd_send(wmi, skb, cmd_id); if (ret) { ath11k_warn(ar->ab, "failed to send wmi ftm command: %d\n", ret); + dev_kfree_skb(skb); goto out; } From e1b429d8e712e656d25915548f621244e9fb2223 Mon Sep 17 00:00:00 2001 From: Kang Yang Date: Tue, 28 Apr 2026 14:17:37 +0800 Subject: [PATCH 1395/1518] wifi: ath10k: skip WMI and beacon transmission when device is wedged [ Upstream commit 54a5b38e4396530e5b2f12b54d3844e860ab6784 ] In ath10k_wmi_cmd_send(), the current code detects ATH10K_STATE_WEDGED and sets ret to -ESHUTDOWN, but still proceeds to transmit pending beacons and calls ath10k_wmi_cmd_send_nowait(). This can lead to incorrect behavior, as WMI commands and beacons are still sent after the device has been marked as wedged, and the original -ESHUTDOWN return value may be overwritten by the result of the send path. The wedged state indicates the hardware is already unreliable, and no further interaction with firmware is expected or meaningful in this state. Fix this by skipping beacon transmission and the WMI send path entirely once ATH10K_STATE_WEDGED is detected, ensuring consistent return values and avoiding unnecessary firmware interaction. Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00288-QCARMSWPZ-1 Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00189 Fixes: c256a94d1b1b ("wifi: ath10k: shutdown driver when hardware is unreliable") Signed-off-by: Kang Yang Reviewed-by: Rameshkumar Sundaram Reviewed-by: Baochen Qiang Link: https://patch.msgid.link/20260428061737.37-1-kang.yang@oss.qualcomm.com Signed-off-by: Jeff Johnson Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/wmi.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index ce22141e5efd9..cd20508399b9a 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1947,15 +1946,15 @@ int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id) ret = -ESHUTDOWN; ath10k_dbg(ar, ATH10K_DBG_WMI, "drop wmi command %d, hardware is wedged\n", cmd_id); - } - /* try to send pending beacons first. they take priority */ - ath10k_wmi_tx_beacons_nowait(ar); + } else { + /* try to send pending beacons first. they take priority */ + ath10k_wmi_tx_beacons_nowait(ar); - ret = ath10k_wmi_cmd_send_nowait(ar, skb, cmd_id); - - if (ret && test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags)) - ret = -ESHUTDOWN; + ret = ath10k_wmi_cmd_send_nowait(ar, skb, cmd_id); + if (ret && test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags)) + ret = -ESHUTDOWN; + } (ret != -EAGAIN); }), 3 * HZ); From d947e6685ff4bb379dd7c5c14aaf511c689f561f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:28:55 -0700 Subject: [PATCH 1396/1518] net: shaper: flip the polarity of the valid flag [ Upstream commit 7cee43fcb0c3f71441d2faaa8c2202b6a88b6bef ] The usual way of inserting entries which are not yet fully ready into XArray is to have a VALID flag. The shaper code has a NOT_VALID flag. Since XArray code does not let us create entries with marks already set - the creation of entries is currently not atomic. Flip the polarity of the VALID flag. This closes the tiny race in net_shaper_pre_insert() of entries being created without the NOT_VALID flag. Fixes: 93954b40f6a4 ("net-shapers: implement NL set and delete operations") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-2-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index e41a82241230d..64c9d6cf6756c 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -275,11 +275,13 @@ static void net_shaper_default_parent(const struct net_shaper_handle *handle, parent->id = 0; } -/* - * MARK_0 is already in use due to XA_FLAGS_ALLOC, can't reuse such flag as - * it's cleared by xa_store(). +/* MARK_0 is already in use due to XA_FLAGS_ALLOC. The VALID mark is set on + * an entry only after the device-side configuration has completed + * successfully (see net_shaper_commit()). Lookups and dumps must filter on + * this mark to avoid exposing tentative entries inserted by + * net_shaper_pre_insert() while the driver call is still in flight. */ -#define NET_SHAPER_NOT_VALID XA_MARK_1 +#define NET_SHAPER_VALID XA_MARK_1 static struct net_shaper * net_shaper_lookup(struct net_shaper_binding *binding, @@ -289,8 +291,8 @@ net_shaper_lookup(struct net_shaper_binding *binding, struct net_shaper_hierarchy *hierarchy; hierarchy = net_shaper_hierarchy_rcu(binding); - if (!hierarchy || xa_get_mark(&hierarchy->shapers, index, - NET_SHAPER_NOT_VALID)) + if (!hierarchy || !xa_get_mark(&hierarchy->shapers, index, + NET_SHAPER_VALID)) return NULL; return xa_load(&hierarchy->shapers, index); @@ -370,13 +372,10 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding, goto free_id; } - /* Mark 'tentative' shaper inside the hierarchy container. - * xa_set_mark is a no-op if the previous store fails. + /* Insert as 'tentative' (no VALID mark). The mark will be set by + * net_shaper_commit() once the driver-side configuration succeeds. */ - xa_lock(&hierarchy->shapers); - prev = __xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL); - __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_NOT_VALID); - xa_unlock(&hierarchy->shapers); + prev = xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL); if (xa_err(prev)) { NL_SET_ERR_MSG(extack, "Can't insert shaper into device store"); kfree_rcu(cur, rcu); @@ -413,8 +412,7 @@ static void net_shaper_commit(struct net_shaper_binding *binding, /* Successful update: drop the tentative mark * and update the hierarchy container. */ - __xa_clear_mark(&hierarchy->shapers, index, - NET_SHAPER_NOT_VALID); + __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); *cur = shapers[i]; } xa_unlock(&hierarchy->shapers); @@ -431,8 +429,9 @@ static void net_shaper_rollback(struct net_shaper_binding *binding) return; xa_lock(&hierarchy->shapers); - xa_for_each_marked(&hierarchy->shapers, index, cur, - NET_SHAPER_NOT_VALID) { + xa_for_each(&hierarchy->shapers, index, cur) { + if (xa_get_mark(&hierarchy->shapers, index, NET_SHAPER_VALID)) + continue; __xa_erase(&hierarchy->shapers, index); kfree(cur); } @@ -836,7 +835,8 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb, goto out_unlock; for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index, - U32_MAX, XA_PRESENT)); ctx->start_index++) { + U32_MAX, NET_SHAPER_VALID)); + ctx->start_index++) { ret = net_shaper_fill_one(skb, binding, shaper, info); if (ret) break; From d6128451c5918dbdd6777425e701fbf8bc5c07aa Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:28:56 -0700 Subject: [PATCH 1397/1518] net: shaper: fix trivial ordering issue in net_shaper_commit() [ Upstream commit 235fb5376139c3419f2218349f1fa2f06f24f7ad ] We should update the entry before we mark it as valid. Fixes: 93954b40f6a4 ("net-shapers: implement NL set and delete operations") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-3-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 64c9d6cf6756c..92ca3b4c7925d 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -295,6 +295,10 @@ net_shaper_lookup(struct net_shaper_binding *binding, NET_SHAPER_VALID)) return NULL; + /* Pairs with smp_wmb() in net_shaper_commit(): if the entry is + * valid, its contents must be visible too. + */ + smp_rmb(); return xa_load(&hierarchy->shapers, index); } @@ -412,8 +416,9 @@ static void net_shaper_commit(struct net_shaper_binding *binding, /* Successful update: drop the tentative mark * and update the hierarchy container. */ - __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); *cur = shapers[i]; + smp_wmb(); + __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); } xa_unlock(&hierarchy->shapers); } @@ -837,6 +842,10 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb, for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index, U32_MAX, NET_SHAPER_VALID)); ctx->start_index++) { + /* Pairs with smp_wmb() in net_shaper_commit(): the entry + * is marked VALID, so its contents must be visible too. + */ + smp_rmb(); ret = net_shaper_fill_one(skb, binding, shaper, info); if (ret) break; From 5098b223f0f0c5c18a3884a8b0ea5bd4a0c7bd75 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:28:57 -0700 Subject: [PATCH 1398/1518] net: shaper: reject duplicate leaves in GROUP request [ Upstream commit a9a2fa1da619f276580b0d4c5d12efac89e8642b ] net_shaper_nl_group_doit() does not deduplicate NET_SHAPER_A_LEAVES entries. When userspace supplies the same leaf handle twice, the same old-parent pointer lands twice in old_nodes[]. The cleanup loop double frees the parent. Of course the same parent may still be in old_nodes[] twice if we are moving multiple of its leaves. Note that this patch also implicitly fixes the fact that the i >= leaves_count path forgets to set ret. Fixes: 5d5d4700e75d ("net-shapers: implement NL group operation") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-4-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 60 +++++++++++++++++++++++++++++++++------------ 1 file changed, 45 insertions(+), 15 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 92ca3b4c7925d..ae19af13c2247 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -941,6 +941,46 @@ static int net_shaper_handle_cmp(const struct net_shaper_handle *a, return memcmp(a, b, sizeof(*a)); } +static int net_shaper_parse_leaves(struct net_shaper_binding *binding, + struct genl_info *info, + const struct net_shaper *node, + struct net_shaper *leaves, + int leaves_count) +{ + struct nlattr *attr; + int i, j, ret, rem; + + i = 0; + nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + if (WARN_ON_ONCE(i >= leaves_count)) + return -EINVAL; + + ret = net_shaper_parse_leaf(binding, attr, info, + node, &leaves[i]); + if (ret) + return ret; + + /* Reject duplicates */ + for (j = 0; j < i; j++) { + if (net_shaper_handle_cmp(&leaves[i].handle, + &leaves[j].handle)) + continue; + + NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr, + "Duplicate leaf shaper %d:%d", + leaves[i].handle.scope, + leaves[i].handle.id); + return -EINVAL; + } + + i++; + } + + return 0; +} + static int net_shaper_parent_from_leaves(int leaves_count, const struct net_shaper *leaves, struct net_shaper *node, @@ -1198,10 +1238,9 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) struct net_shaper **old_nodes, *leaves, node = {}; struct net_shaper_hierarchy *hierarchy; struct net_shaper_binding *binding; - int i, ret, rem, leaves_count; + int i, ret, leaves_count; int old_nodes_count = 0; struct sk_buff *msg; - struct nlattr *attr; if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_LEAVES)) return -EINVAL; @@ -1229,19 +1268,10 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_leaves; - i = 0; - nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES, - genlmsg_data(info->genlhdr), - genlmsg_len(info->genlhdr), rem) { - if (WARN_ON_ONCE(i >= leaves_count)) - goto free_leaves; - - ret = net_shaper_parse_leaf(binding, attr, info, - &node, &leaves[i]); - if (ret) - goto free_leaves; - i++; - } + ret = net_shaper_parse_leaves(binding, info, &node, + leaves, leaves_count); + if (ret) + goto free_leaves; /* Prepare the msg reply in advance, to avoid device operation * rollback on allocation failure. From f817ce8d1943841949a322408bf9b7ec31368ad5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:28:59 -0700 Subject: [PATCH 1399/1518] net: shaper: set ret to -ENOMEM when genlmsg_new() fails in group_doit [ Upstream commit 8054f85b83f42a37d482fc77ea7c9ff06a9407d9 ] genlmsg_new() alloc failure path in net_shaper_nl_group_doit() forgets to set ret before jumping to error handling. Fixes: 5d5d4700e75d ("net-shapers: implement NL group operation") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-6-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index ae19af13c2247..ee0d1f0613430 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -1277,8 +1277,10 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) * rollback on allocation failure. */ msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL); - if (!msg) + if (!msg) { + ret = -ENOMEM; goto free_leaves; + } hierarchy = net_shaper_hierarchy_setup(binding); if (!hierarchy) { From d7c2bbbaa2c428fbcf4697ff949de5426ae42d12 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:29:00 -0700 Subject: [PATCH 1400/1518] net: shaper: fix undersized reply skb allocation in GROUP command [ Upstream commit 0f9a857e34d0f8c018a3e4435c6f0e92e8d2f38c ] net_shaper_group_send_reply() writes both the NET_SHAPER_A_IFINDEX attribute (via net_shaper_fill_binding()) and the nested NET_SHAPER_A_HANDLE attribute (via net_shaper_fill_handle()), but the reply skb at the call site in net_shaper_nl_group_doit() is allocated using net_shaper_handle_size(), which only accounts for the nested handle. The allocation is therefore short by nla_total_size(sizeof(u32)) (8 bytes) for the IFINDEX attribute. In practice the slab allocator rounds up the small allocation so the bug is latent, but the size accounting is wrong and could bite if the reply grew further. Introduce net_shaper_group_reply_size() that accounts for the full reply payload and use it both at the genlmsg_new() call site and in the defensive WARN_ONCE message. Fixes: 5d5d4700e75d ("net-shapers: implement NL group operation") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-7-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index ee0d1f0613430..5338842122a2a 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -90,6 +90,12 @@ static int net_shaper_handle_size(void) nla_total_size(sizeof(u32))); } +static int net_shaper_group_reply_size(void) +{ + return nla_total_size(sizeof(u32)) + /* NET_SHAPER_A_IFINDEX */ + net_shaper_handle_size(); /* NET_SHAPER_A_HANDLE */ +} + static int net_shaper_fill_binding(struct sk_buff *msg, const struct net_shaper_binding *binding, u32 type) @@ -1228,7 +1234,7 @@ static int net_shaper_group_send_reply(struct net_shaper_binding *binding, free_msg: /* Should never happen as msg is pre-allocated with enough space. */ WARN_ONCE(true, "calculated message payload length (%d)", - net_shaper_handle_size()); + net_shaper_group_reply_size()); nlmsg_free(msg); return -EMSGSIZE; } @@ -1276,7 +1282,7 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) /* Prepare the msg reply in advance, to avoid device operation * rollback on allocation failure. */ - msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL); + msg = genlmsg_new(net_shaper_group_reply_size(), GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto free_leaves; From 77ec90d41c5955b88f5c5d9ee21d0650b9fd7c12 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:29:03 -0700 Subject: [PATCH 1401/1518] net: shaper: enforce singleton NETDEV scope with id 0 [ Upstream commit b62b29e6de6711f5918940aa6ff2bbab6d6af502 ] The NETDEV scope represents a singleton root shaper in the per-device hierarchy. All code assumes NETDEV shapers have id 0: net_shaper_default_parent() hardcodes parent->id = 0 when returning the NETDEV parent for QUEUE/NODE children, and the UAPI documentation describes NETDEV scope as "the main shaper" (singular, not plural). Make sure we reject non-0 IDs. Fixes: 4b623f9f0f59 ("net-shapers: implement NL get operation") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-10-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 5338842122a2a..5cd244b8109ae 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -480,6 +480,12 @@ static int net_shaper_parse_handle(const struct nlattr *attr, else if (handle->scope == NET_SHAPER_SCOPE_NODE) id = NET_SHAPER_ID_UNSPEC; + if (id && handle->scope == NET_SHAPER_SCOPE_NETDEV) { + NL_SET_ERR_MSG_ATTR(info->extack, id_attr, + "Netdev scope is a singleton, must use ID 0"); + return -EINVAL; + } + handle->id = id; return 0; } From a524863944933e883ff3743d0607e84abd62f377 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 10 May 2026 12:29:04 -0700 Subject: [PATCH 1402/1518] net: shaper: reject QUEUE scope handle with missing id [ Upstream commit ce372e869f9f492f3d5aa9a0ae75ed52c61d2d6f ] net_shaper_parse_handle() does not enforce that the user provides the handle ID. For NODE the ID defaults to UNSPEC for all other cases it defaults to 0. For NETDEV 0 is the only option. For QUEUE defaulting to 0 makes less intuitive sense. Specifically because the behavior should (IMHO) be the same for all cases where there may be more than one ID (QUEUE and NODE). We should either document this as intentional or reject. I picked the latter with no strong conviction. Fixes: 4b623f9f0f59 ("net-shapers: implement NL get operation") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260510192904.3987113-11-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 5cd244b8109ae..fa85200252827 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -475,10 +475,15 @@ static int net_shaper_parse_handle(const struct nlattr *attr, * shaper (any other value). */ id_attr = tb[NET_SHAPER_A_HANDLE_ID]; - if (id_attr) + if (id_attr) { id = nla_get_u32(id_attr); - else if (handle->scope == NET_SHAPER_SCOPE_NODE) + } else if (handle->scope == NET_SHAPER_SCOPE_NODE) { id = NET_SHAPER_ID_UNSPEC; + } else if (handle->scope == NET_SHAPER_SCOPE_QUEUE) { + NL_SET_ERR_ATTR_MISS(info->extack, attr, + NET_SHAPER_A_HANDLE_ID); + return -EINVAL; + } if (id && handle->scope == NET_SHAPER_SCOPE_NETDEV) { NL_SET_ERR_MSG_ATTR(info->extack, id_attr, From 0d48654af4d1390c888389206cc13b51b82c30e6 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Mon, 11 May 2026 22:51:51 +0100 Subject: [PATCH 1403/1518] block: don't overwrite bip_vcnt in bio_integrity_copy_user() [ Upstream commit 637ad3a56a3b889527d1dacea6fea2a8bd648140 ] bio_integrity_add_page() already sets bip_vcnt to 1 for the bounce segment. Overwriting it with nr_vecs breaks bip_vcnt <= bip_max_vcnt on WRITE (bip_max_vcnt is 1), so the gap-merge checks in block/blk.h read past the bip_vec[] flex array. On READ the read is in bounds but lands on a saved user bvec instead of the bounce. The line was added for split propagation, but bio_integrity_clone() doesn't copy bip_vcnt and BIP_CLONE_FLAGS excludes BIP_COPY_USER. Fixes: 3991657ae707 ("block: set bip_vcnt correctly") Signed-off-by: David Carlier Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260511215151.346228-1-devnexen@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/bio-integrity.c | 1 - 1 file changed, 1 deletion(-) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 12d887349c260..ab4a15437925e 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -205,7 +205,6 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, } bip->bip_flags |= BIP_COPY_USER; - bip->bip_vcnt = nr_vecs; return 0; free_bip: bio_integrity_free(bio); From 0943f81e1b3176f27dbaf6db268fc69d8a94f0ba Mon Sep 17 00:00:00 2001 From: Casey Chen Date: Mon, 11 May 2026 15:22:30 -0600 Subject: [PATCH 1404/1518] block: recompute nr_integrity_segments in blk_insert_cloned_request [ Upstream commit 2c6e6a18a37b905cb584eb0dda3ae482162a81ca ] blk_insert_cloned_request() already recomputes nr_phys_segments against the bottom queue, because "the queue settings related to segment counting may differ from the original queue." The exact same reasoning applies to integrity segments: a stacked driver's underlying queue can have tighter virt_boundary_mask, seg_boundary_mask, or max_segment_size than the top queue, in which case blk_rq_count_integrity_sg() against the bottom queue produces a different count than the cached rq->nr_integrity_segments inherited from the source request by blk_rq_prep_clone(). When the cached count is lower than the bottom queue's actual count, blk_rq_map_integrity_sg() trips BUG_ON(segments > rq->nr_integrity_segments); on dispatch. The same families of stacked setups that motivated the existing nr_phys_segments recompute -- dm-multipath fanning out to nvme-rdma in particular -- can produce this. Mirror the nr_phys_segments handling: when the request carries integrity, recompute nr_integrity_segments against the bottom queue and reject the request if it exceeds the bottom queue's max_integrity_segments. blk_rq_count_integrity_sg() and queue_max_integrity_segments() are both already available via , which blk-mq.c includes. This closes a latent gap in the stacking contract and brings the integrity-segment accounting in line with the existing phys-segment accounting. Fixes: 76c313f658d2 ("blk-integrity: improved sg segment mapping") Signed-off-by: Casey Chen Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260511212230.27511-1-cachen@purestorage.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-mq.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/block/blk-mq.c b/block/blk-mq.c index 4ebb92014eae1..ab05c5c9e6ae2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3285,6 +3285,25 @@ blk_status_t blk_insert_cloned_request(struct request *rq) return BLK_STS_IOERR; } + /* + * Integrity segment counting depends on the same queue limits + * (virt_boundary_mask, seg_boundary_mask, max_segment_size) that + * vary across stacked queues, so recompute against the bottom + * queue just like nr_phys_segments above. + */ + if (blk_integrity_rq(rq) && rq->bio) { + unsigned short max_int_segs = queue_max_integrity_segments(q); + + rq->nr_integrity_segments = + blk_rq_count_integrity_sg(rq->q, rq->bio); + if (rq->nr_integrity_segments > max_int_segs) { + printk(KERN_ERR "%s: over max integrity segments limit. (%u > %u)\n", + __func__, rq->nr_integrity_segments, + max_int_segs); + return BLK_STS_IOERR; + } + } + if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; From 086695145000cc518b69811164ce4aa8e45211b1 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 5 Feb 2026 09:11:31 +0100 Subject: [PATCH 1405/1518] HID: quirks: really enable the intended work around for appledisplay [ Upstream commit 5f90dcfa8dc32a488581b78e575cdd7808ba5c78 ] Commit c7fabe4ad921 ("HID: quirks: work around VID/PID conflict for appledisplay") intends to add a quirk for kernels built with Apple Cinema Display support, but it refers to the non-existing config option CONFIG_APPLEDISPLAY, whereas the config option for Apple Cinema Display support is named CONFIG_USB_APPLEDISPLAY. Refer to the intended config option CONFIG_USB_APPLEDISPLAY in the ifdef directive. Fixes: c7fabe4ad921 ("HID: quirks: work around VID/PID conflict for appledisplay") Signed-off-by: Lukas Bulwahn Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index f6be3ffee0232..04d3ec360c1dc 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -234,7 +234,7 @@ static const struct hid_device_id hid_quirks[] = { * used as a driver. See hid_scan_report(). */ static const struct hid_device_id hid_have_special_driver[] = { -#if IS_ENABLED(CONFIG_APPLEDISPLAY) +#if IS_ENABLED(CONFIG_USB_APPLEDISPLAY) { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9218) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9219) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x921c) }, From 76410790f1491c8e06a451045ae223a61c652455 Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Tue, 12 May 2026 01:09:29 -0400 Subject: [PATCH 1406/1518] block: bio-integrity: Fix null-ptr-deref in bio_integrity_map_user() [ Upstream commit 8582792cf23b3d94674d4d838f7cde9a28d0fcaf ] pin_user_pages_fast() can partially succeed and return the number of pages that were actually pinned. However, the bio_integrity_map_user() does not handle this partial pinning. This leads to a general protection fault since bvec_from_pages() dereferences an unpinned page address, which is 0. To fix this, add a check to verify that all requested memory is pinned. If partial pinning occurs, unpin the memory and return -EFAULT. Kernel Oops: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 0 UID: 0 PID: 1061 Comm: nvme-passthroug Not tainted 7.0.0-11783-g90957f9314e8-dirty #16 PREEMPT(lazy) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 RIP: 0010:bio_integrity_map_user.cold+0x1b0/0x9d6 Fixes: 492c5d455969 ("block: bio-integrity: directly map user buffers") Acked-by: Chao Shi Acked-by: Weidong Zhu Acked-by: Dave Tian Signed-off-by: Sungwoo Kim Tested-by: Shin'ichiro Kawasaki Link: https://github.com/linux-blktests/blktests/pull/244 Link: https://patch.msgid.link/20260512050929.541397-2-iam@sung-woo.kim Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/bio-integrity.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index ab4a15437925e..46c59ed92bd1c 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -299,6 +299,24 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) if (unlikely(ret < 0)) goto free_bvec; + /* + * Handle partial pinning. This can happen when pin_user_pages_fast() + * returns fewer pages than requested. + */ + if (user_backed_iter(iter) && unlikely(ret != bytes)) { + if (ret > 0) { + int npinned = DIV_ROUND_UP(offset + ret, PAGE_SIZE); + int i; + + for (i = 0; i < npinned; i++) + unpin_user_page(pages[i]); + } + if (pages != stack_pages) + kvfree(pages); + ret = -EFAULT; + goto free_bvec; + } + nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset, &is_p2p); if (pages != stack_pages) From 97a8e89cdef36207a8776edc03d6931763a06ad0 Mon Sep 17 00:00:00 2001 From: Zack McKevitt Date: Thu, 30 Apr 2026 12:39:01 -0700 Subject: [PATCH 1407/1518] accel/qaic: Add overflow check to remap_pfn_range during mmap [ Upstream commit aa16b2bc0f02709919e2435f531406531e5bcc69 ] The call to remap_pfn_range in qaic_gem_object_mmap is susceptible to (re)mapping beyond the VMA if the BO is too large. This can cause use after free issues when munmap() unmaps only the VMA region and not the additional mappings. To prevent this, check the remaining size of the VMA before remapping and truncate the remapped length if sg->length is too large. Reported-by: Lukas Maar Fixes: ff13be830333 ("accel/qaic: Add datapath") Reviewed-by: Karol Wachowski Signed-off-by: Zack McKevitt Reviewed-by: Jeff Hugo [jhugo: fix braces from checkpatch --strict] Signed-off-by: Jeff Hugo Link: https://patch.msgid.link/20260430193858.1178641-1-zachary.mckevitt@oss.qualcomm.com Signed-off-by: Sasha Levin --- drivers/accel/qaic/qaic_data.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index c4f117edb266e..3335c92b0d7dc 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -605,8 +605,11 @@ static const struct vm_operations_struct drm_vm_ops = { static int qaic_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) { struct qaic_bo *bo = to_qaic_bo(obj); + unsigned long remap_start; unsigned long offset = 0; + unsigned long remap_end; struct scatterlist *sg; + unsigned long length; int ret = 0; if (drm_gem_is_imported(obj)) @@ -614,11 +617,27 @@ static int qaic_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struc for (sg = bo->sgt->sgl; sg; sg = sg_next(sg)) { if (sg_page(sg)) { + /* if sg is too large for the VMA, so truncate it to fit */ + if (check_add_overflow(vma->vm_start, offset, &remap_start)) + return -EINVAL; + if (check_add_overflow(remap_start, sg->length, &remap_end)) + return -EINVAL; + + if (remap_end > vma->vm_end) { + if (check_sub_overflow(vma->vm_end, remap_start, &length)) + return -EINVAL; + } else { + length = sg->length; + } + + if (length == 0) + goto out; + ret = remap_pfn_range(vma, vma->vm_start + offset, page_to_pfn(sg_page(sg)), - sg->length, vma->vm_page_prot); + length, vma->vm_page_prot); if (ret) goto out; - offset += sg->length; + offset += length; } } From d2ea0b8aef8746e147602eac87ca8538f4bc7e66 Mon Sep 17 00:00:00 2001 From: Xiang Mei Date: Sun, 10 May 2026 15:26:40 -0700 Subject: [PATCH 1408/1518] net/smc: avoid NULL deref of conn->lnk in smc_msg_event tracepoint [ Upstream commit 7bf563badd37cb796df5477d2b78bb64148a1268 ] The smc_msg_event tracepoint class, shared by smc_tx_sendmsg and smc_rx_recvmsg, unconditionally dereferences smc->conn.lnk: __string(name, smc->conn.lnk->ibname) conn->lnk is only set for SMC-R; for SMC-D it is NULL. Other code on these paths already handles this (e.g. !conn->lnk in SMC_STAT_RMB_TX_SIZE_SMALL()). With the tracepoint enabled, the first sendmsg()/recvmsg() on an SMC-D socket crashes: Oops: general protection fault, probably for non-canonical address KASAN: null-ptr-deref in range [...] RIP: 0010:strlen+0x1e/0xa0 Call Trace: trace_event_raw_event_smc_msg_event (net/smc/smc_tracepoint.h:44) smc_rx_recvmsg (net/smc/smc_rx.c:515) smc_recvmsg (net/smc/af_smc.c:2859) __sys_recvfrom (net/socket.c:2315) __x64_sys_recvfrom (net/socket.c:2326) do_syscall_64 The faulting address 0x3e0 is offsetof(struct smc_link, ibname), confirming the NULL ->lnk deref. Enabling the tracepoint requires root, but the trigger itself is unprivileged: socket(AF_SMC, ...) has no capability check, and SMC-D negotiation needs no admin step on s390 or on x86 with the loopback ISM device loaded. Log an empty device name for SMC-D instead of dereferencing NULL. Fixes: aff3083f10bf ("net/smc: Introduce tracepoints for tx and rx msg") Reported-by: Weiming Shi Signed-off-by: Xiang Mei Reviewed-by: Dust Li Reviewed-by: Sidraya Jayagond Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/smc/smc_tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h index a9a6e3c1113aa..53da84f57fd6f 100644 --- a/net/smc/smc_tracepoint.h +++ b/net/smc/smc_tracepoint.h @@ -51,7 +51,7 @@ DECLARE_EVENT_CLASS(smc_msg_event, __field(const void *, smc) __field(u64, net_cookie) __field(size_t, len) - __string(name, smc->conn.lnk->ibname) + __string(name, smc->conn.lnk ? smc->conn.lnk->ibname : "") ), TP_fast_assign( From d235f8f7b2644934a6aeac6e3e0fdc1108b3ac08 Mon Sep 17 00:00:00 2001 From: Chenguang Zhao Date: Mon, 11 May 2026 09:43:43 +0800 Subject: [PATCH 1409/1518] ethtool: fix ethnl_bitmap32_not_zero() bit interval semantics [ Upstream commit 3d042592ebd4c7e44974d556de0b727cb7db4dab ] ethnl_bitmap32_not_zero() should return true if some bit in [start, end) is set: - Fix inverted memchr_inv() sense: return true when the scan finds a non-zero byte, not when the middle words are all zero. - Return false for an empty interval (end <= start). - When end is 32-bit aligned, indices in [start, end) do not include any bits from map[end_word]; return false after earlier checks found no non-zero data. Fixes: 10b518d4e6dd ("ethtool: netlink bitset handling") Signed-off-by: Chenguang Zhao Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ethtool/bitset.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index f0883357d12e5..4691d6d0f2b75 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -91,7 +91,7 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, u32 mask; if (end <= start) - return true; + return false; if (start % 32) { mask = ethnl_upper_bits(start); @@ -104,11 +104,11 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, start_word++; } - if (!memchr_inv(map + start_word, '\0', - (end_word - start_word) * sizeof(u32))) + if (memchr_inv(map + start_word, '\0', + (end_word - start_word) * sizeof(u32))) return true; if (end % 32 == 0) - return true; + return false; return map[end_word] & ethnl_lower_bits(end); } From a184aec790135938b0fadb415e55accd1f8685a0 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 28 Apr 2026 20:21:38 +0300 Subject: [PATCH 1410/1518] drm/msm/dsi: don't dump registers past the mapped region [ Upstream commit 5b49a46baa853b26dbefa65c6c75dd9ff69f63d4 ] On DSI 6G platforms the IO address space is internally adjusted by io_offset. Later this adjusted address might be used for memory dumping. However the size that is used for memory dumping isn't adjusted to account for the io_offset, leading to the potential access to the unmapped region. Lower ctrl_size by the io_offset value to prevent access past the mapped area. msm_disp_snapshot_add_block+0x1d4/0x3c8 [msm] (P) msm_dsi_host_snapshot+0x4c/0x78 [msm] msm_dsi_snapshot+0x28/0x50 [msm] msm_disp_snapshot_capture_state+0x74/0x140 [msm] msm_disp_snapshot_state_sync+0x60/0x90 [msm] _msm_disp_snapshot_work+0x30/0x90 [msm] kthread_worker_fn+0xdc/0x460 kthread+0x120/0x140 Fixes: bac2c6a62ed9 ("drm/msm: get rid of msm_iomap_size") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Patchwork: https://patchwork.freedesktop.org/patch/721747/ Link: https://lore.kernel.org/r/20260428-msm-fix-dsi-dump-v1-1-5d4cb5ccfac7@oss.qualcomm.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dsi/dsi_host.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 1c0841a1c1013..50474c994d473 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -2003,6 +2003,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) /* fixup base address by io offset */ msm_host->ctrl_base += cfg->io_offset; + msm_host->ctrl_size -= cfg->io_offset; ret = devm_regulator_bulk_get_const(&pdev->dev, cfg->num_regulators, cfg->regulator_data, From ff58e5ef1b46ce614af048d2d04986df05ffab90 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 5 May 2026 03:24:58 +0300 Subject: [PATCH 1411/1518] drm/msm/dpu: don't mix devm and drmm functions [ Upstream commit c0c70a11365cba7fba25a77463582bcec0f7846e ] Mixing devm and drmm functions will result in a use-after-free on msm driver teardown if userspace keeps a reference on the drm device: The WB connector data will be destroyed because of the use of devm_kzalloc()), while the usersoace still can try interacting with the WB connector (which uses drmm_ functions). Change dpu_writeback_init() to use drmm_. Fixes: 0b37ac63fc9d ("drm/msm/dpu: use drmm_writeback_connector_init()") Reported-by: Christophe JAILLET Closes: https://lore.kernel.org/r/78c764b8-44cf-4db5-88e7-807a85954518@wanadoo.fr Signed-off-by: Dmitry Baryshkov Reviewed-by: John.Harrison@Igalia.com Patchwork: https://patchwork.freedesktop.org/patch/722656/ Link: https://lore.kernel.org/r/20260505-wb-drop-encoder-v5-1-42567b7c7af2@oss.qualcomm.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index 7545c0293efbd..6f2370c9dd988 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -5,6 +5,7 @@ #include #include +#include #include "dpu_writeback.h" @@ -125,7 +126,7 @@ int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc, struct dpu_wb_connector *dpu_wb_conn; int rc = 0; - dpu_wb_conn = devm_kzalloc(dev->dev, sizeof(*dpu_wb_conn), GFP_KERNEL); + dpu_wb_conn = drmm_kzalloc(dev, sizeof(*dpu_wb_conn), GFP_KERNEL); if (!dpu_wb_conn) return -ENOMEM; From 15dba511d5694dea40dce263be3fa655a1a65f3f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 13 May 2026 18:19:40 +0800 Subject: [PATCH 1412/1518] selftests: ublk: cap nthreads to kernel's actual nr_hw_queues [ Upstream commit 87d0740b7c4cc847be1b6f307ab6d8547cb1a726 ] dev->nthreads is derived from the user-requested queue count before the ADD command, but the kernel may reduce nr_hw_queues (capped to nr_cpu_ids). When the VM has fewer CPUs than requested queues, the daemon creates more handler threads than there are kernel queues. In non-batch mode, the extra threads access uninitialized queues (q_depth=0), submit zero io_uring SQEs, and block forever in io_cqring_wait. In batch mode, the extra threads cause similar hangs during device removal. In both cases, the stuck threads prevent the daemon from closing the char device, holding the last ublk_device reference and causing ublk_ctrl_del_dev() to hang in wait_event_interruptible(). Fix by capping dev->nthreads to the kernel-returned nr_hw_queues after the ADD command completes. per_io_tasks mode is excluded because threads interleave across all queues, so nthreads > nr_hw_queues is valid. Fixes: abe54c160346 ("selftests: ublk: kublk: decouple ublk_queues from ublk server threads") Signed-off-by: Ming Lei Link: https://patch.msgid.link/20260513101941.1373998-1-tom.leiming@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- tools/testing/selftests/ublk/kublk.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index cbd23444c8a98..ac47979349a4b 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -1220,6 +1220,17 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) goto fail; } + /* + * The kernel may reduce nr_hw_queues (e.g. capped to nr_cpu_ids). + * Cap nthreads to the actual queue count to avoid creating extra + * handler threads that will hang during device removal. + * + * per_io_tasks mode is excluded: threads interleave across all + * queues so nthreads > nr_hw_queues is valid and intentional. + */ + if (!ctx->per_io_tasks && dev->nthreads > info->nr_hw_queues) + dev->nthreads = info->nr_hw_queues; + ret = ublk_start_daemon(ctx, dev); ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret); if (ret < 0) From 3ad2d8be6e4ddf7d26d27f56e2f58b9b81537f2c Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Mon, 16 Mar 2026 16:12:00 +0100 Subject: [PATCH 1413/1518] x86/mce: Restore MCA polling interval halving [ Upstream commit ea324444ece9f301b5c4ff71b258cc68990c4d61 ] RongQing reported that the MCA polling interval doesn't halve when an error gets logged. It was traced down to the commit in Fixes:, because: mce_timer_fn() |-> mce_poll_banks() |-> machine_check_poll() |-> mce_log() which will queue the work and return. Now, back in mce_timer_fn(): /* * Alert userspace if needed. If we logged an MCE, reduce the polling * interval, otherwise increase the polling interval. */ if (mce_notify_irq()) <--- here we haven't ran the notifier chain yet so mce_need_notify is not set yet so this won't hit and we won't halve the interval iv. Now the notifier chain runs. mce_early_notifier() sets the bit, does mce_notify_irq(), that clears the bit and then the notifier chain a little later logs the error. So this is a silly timing issue. But, that's all unnecessary. All it needs to happen here is, the "should we notify of a logged MCE" mce_notify_irq() asks, should be simply a question to the mce gen pool: "Are you empty?" And that then turns into a simple yes or no answer and it all JustWorks(tm). So do that and also distribute the functionality where it belongs: - Print that MCE events have been logged in mce_log() - Trigger the mcelog tool specific work in the first notifier As a result, mce_notify_irq() can go now. Fixes: 011d82611172 ("RAS: Add a Corrected Errors Collector") Reported-by: Li RongQing Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Tested-by: Qiuxu Zhuo Link: https://lore.kernel.org/r/20260112082747.2842-1-lirongqing@baidu.com Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/mce/core.c | 33 +++++---------------------------- 1 file changed, 5 insertions(+), 28 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 460e90a1a0b17..c8b112c6c5492 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -89,7 +89,6 @@ struct mca_config mca_cfg __read_mostly = { }; static DEFINE_PER_CPU(struct mce_hw_err, hw_errs_seen); -static unsigned long mce_need_notify; /* * MCA banks polled by the period polling timer for corrected events. @@ -151,8 +150,10 @@ EXPORT_PER_CPU_SYMBOL_GPL(injectm); void mce_log(struct mce_hw_err *err) { - if (mce_gen_pool_add(err)) + if (mce_gen_pool_add(err)) { + pr_info(HW_ERR "Machine check events logged\n"); irq_work_queue(&mce_irq_work); + } } EXPORT_SYMBOL_GPL(mce_log); @@ -584,28 +585,6 @@ bool mce_is_correctable(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_correctable); -/* - * Notify the user(s) about new machine check events. - * Can be called from interrupt context, but not from machine check/NMI - * context. - */ -static bool mce_notify_irq(void) -{ - /* Not more than two messages every minute */ - static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); - - if (test_and_clear_bit(0, &mce_need_notify)) { - mce_work_trigger(); - - if (__ratelimit(&ratelimit)) - pr_info(HW_ERR "Machine check events logged\n"); - - return true; - } - - return false; -} - static int mce_early_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -617,9 +596,7 @@ static int mce_early_notifier(struct notifier_block *nb, unsigned long val, /* Emit the trace record: */ trace_mce_record(err); - set_bit(0, &mce_need_notify); - - mce_notify_irq(); + mce_work_trigger(); return NOTIFY_DONE; } @@ -1771,7 +1748,7 @@ static void mce_timer_fn(struct timer_list *t) * Alert userspace if needed. If we logged an MCE, reduce the polling * interval, otherwise increase the polling interval. */ - if (mce_notify_irq()) + if (!mce_gen_pool_empty()) iv = max(iv / 2, (unsigned long) HZ/100); else iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); From 3a7b59d2385d477526cb5b5822754def29953ac0 Mon Sep 17 00:00:00 2001 From: Ricardo Neri Date: Fri, 24 Apr 2026 14:41:13 -0700 Subject: [PATCH 1414/1518] Documentation: intel_pstate: Fix description of asymmetric packing with SMT [ Upstream commit ee047fc7a2da90554410128195058c409a391d43 ] Patchset [1], including commits 046a5a95c3b0 ("x86/sched/itmt: Give all SMT siblings of a core the same priority") 995998ebdebd ("x86/sched: Remove SD_ASYM_PACKING from the SMT domain flags") overhauled asym_packing handling in the scheduler on x86 hybrid processors with SMT. It removed SD_ASYM_PACKING from the x86 SMT scheduling domain and made all SMT siblings of a core share the same priority. As a result, asym_packing operates only across physical cores, spreading tasks among them and only using idle SMT siblings once all physical cores are busy. Fix the documentation to reflect this behavior. Fixes: f20af84c29b2 ("cpufreq: intel_pstate: Document hybrid processor support") Link: https://lore.kernel.org/r/20230406203148.19182-1-ricardo.neri-calderon@linux.intel.com [1] Signed-off-by: Ricardo Neri [ rjw: Changelog edits ] Link: https://patch.msgid.link/20260424-rneri-fix-intel-pstate-doc-smt-asym-packing-v1-1-317bf7d5c362@linux.intel.com Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- Documentation/admin-guide/pm/intel_pstate.rst | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index 26e702c7016e5..66287f8d645f0 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -348,11 +348,12 @@ HyperThreading (HT) in the context of Intel processors, is enabled on at least one core, ``intel_pstate`` assigns performance-based priorities to CPUs. Namely, the priority of a given CPU reflects its highest HWP performance level which causes the CPU scheduler to generally prefer more performant CPUs, so the less -performant CPUs are used when the other ones are fully loaded. However, SMT -siblings (that is, logical CPUs sharing one physical core) are treated in a -special way such that if one of them is in use, the effective priority of the -other ones is lowered below the priorities of the CPUs located in the other -physical cores. +performant CPUs are used when the other ones are fully loaded. SMT siblings +(that is, logical CPUs sharing one physical core) are given the same priority. +The scheduler can pull tasks from lower-priority cores and place them on any +sibling. Since the scheduler spreads tasks among physical cores, tasks will be +placed on the SMT siblings of physical cores only after all physical cores are +busy. This approach maximizes performance in the majority of cases, but unfortunately it also leads to excessive energy usage in some important scenarios, like video From eea43d5ed45089705bc5d70971c39076962d5951 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 11 Apr 2026 17:59:15 +0300 Subject: [PATCH 1415/1518] drm/msm/adreno: fix userspace-triggered crash on a2xx-a4xx [ Upstream commit 2b4abf879360ea00a9e2b46d2d15dcdbc0687eed ] Before a5xx Adreno driver will not try fetching UBWC params (because those generations didn't support UBWC anyway), however it's still possible to query UBWC-related params from the userspace, triggering possible NULL pointer dereference. Check for UBWC config in adreno_get_param() and return sane defaults if there is none. Fixes: a452510aad53 ("drm/msm/adreno: Switch to the common UBWC config struct") Signed-off-by: Dmitry Baryshkov Reviewed-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/717778/ Message-ID: <20260411-adreno-fix-ubwc-v3-1-4983156f3f80@oss.qualcomm.com> Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/adreno_gpu.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 4b5a4edd07028..056a9e18cd4ac 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -419,15 +419,21 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, *value = vm->mm_range; return 0; case MSM_PARAM_HIGHEST_BANK_BIT: + if (!adreno_gpu->ubwc_config) + return UERR(ENOENT, drm, "no UBWC on this platform"); *value = adreno_gpu->ubwc_config->highest_bank_bit; return 0; case MSM_PARAM_RAYTRACING: *value = adreno_gpu->has_ray_tracing; return 0; case MSM_PARAM_UBWC_SWIZZLE: + if (!adreno_gpu->ubwc_config) + return UERR(ENOENT, drm, "no UBWC on this platform"); *value = adreno_gpu->ubwc_config->ubwc_swizzle; return 0; case MSM_PARAM_MACROTILE_MODE: + if (!adreno_gpu->ubwc_config) + return UERR(ENOENT, drm, "no UBWC on this platform"); *value = adreno_gpu->ubwc_config->macrotile_mode; return 0; case MSM_PARAM_UCHE_TRAP_BASE: From f4e37f3df436c2bdd2621c21f9c72c8f149a221d Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Tue, 21 Apr 2026 13:02:38 +0900 Subject: [PATCH 1416/1518] drm/msm: Fix iommu_map_sgtable() return value check and avoid WARN [ Upstream commit 55e0f0d1c1a4ee1e46da7da4d443eb3044fb3851 ] Commit "iommu: return full error code from iommu_map_sg[_atomic]()" changed iommu_map_sgtable() to return an ssize_t and negative values in error cases, rather than a size_t and a zero. Store the return value in the appropriate type and in case of error, return it rather than WARNing. Fixes: ad8f36e4b6b1 ("iommu: return full error code from iommu_map_sg[_atomic]()") Signed-off-by: Mikko Perttunen Patchwork: https://patchwork.freedesktop.org/patch/719685/ Message-ID: <20260421-iommu_map_sgtable-return-v1-3-fb484c07d2a1@nvidia.com> Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_iommu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index a188617653e85..82a172f21a3ec 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -677,7 +677,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, int prot) { struct msm_iommu *iommu = to_msm_iommu(mmu); - size_t ret; + ssize_t ret; WARN_ON(off != 0); @@ -686,7 +686,8 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, iova |= GENMASK_ULL(63, 49); ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot); - WARN_ON(!ret); + if (ret < 0) + return ret; return (ret == len) ? 0 : -EINVAL; } From 6dcd072a5ae3aed336e4a67a7d4cc5205b240065 Mon Sep 17 00:00:00 2001 From: Sayali Patil Date: Wed, 13 May 2026 13:44:13 +0530 Subject: [PATCH 1417/1518] powerpc/time: Remove redundant preempt_disable|enable() calls from arch_irq_work_raise() [ Upstream commit 31467b23823ffec1f6fff407f8e3ca9af8b7491a ] A kernel panic is observed when handling machine check exceptions from real mode. BUG: Unable to handle kernel data access on read at 0xc00000006be21300 Oops: Kernel access of bad area, sig: 11 [#1] MSR: 8000000000001003 CR: 88222248 XER: 00000005 CFAR: c00000000003ffc4 DAR: c00000006be21300 DSISR: 40000000 IRQMASK: 0 NIP [c000000000029e40] arch_irq_work_raise+0x10/0x70 LR [c00000000003ffc8] machine_check_queue_event+0xa8/0x150 Call Trace: [c0000000179d3c70] [c00000000003ff64] machine_check_queue_event+0x44/0x150 [c0000000179d3d30] [c0000000000084e0] machine_check_early_common+0x1f0/0x2c0 The crash occurs because arch_irq_work_raise() calls preempt_disable() from machine check exception (MCE) handlers running in real mode. In this context, accessing the preempt_count can fault, leading to the panic. The preempt_disable()/preempt_enable() pair in arch_irq_work_raise() was originally added by commit 0fe1ac48bef0 ("powerpc/perf_event: Fix oops due to perf_event_do_pending call") to avoid races while raising irq work from exception context. Later, commit 471ba0e686cb ("irq_work: Do not raise an IPI when queueing work on the local CPU") added preemption protection in irq_work_queue() path, while commit 20b876918c06 ("irq_work: Use per cpu atomics instead of regular atomics") added equivalent protection in irq_work_queue_on() before reaching arch_irq_work_raise(): irq_work_queue() / irq_work_queue_on() -> preempt_disable() -> __irq_work_queue_local() -> irq_work_raise() -> arch_irq_work_raise() As a result, callers other than mce_irq_work_raise() already execute with preemption disabled, making the additional preempt_disable()/preempt_enable() pair in arch_irq_work_raise() redundant. The arch_irq_work_raise() function executes in NMI context when called from MCE handler. Hence we will not be preempted or scheduled out since we are in NMI context with MSR[EE]=0. Therefore, it is safe to remove the preempt_disable()/preempt_enable() calls from here. Remove it to avoid accessing preempt_count from real mode context. Fixes: cc15ff327569 ("powerpc/mce: Avoid using irq_work_queue() in realmode") Suggested-by: Mahesh Salgaonkar Acked-by: Shrikanth Hegde Reviewed-by: Ritesh Harjani (IBM) Signed-off-by: Sayali Patil [Maddy: Fixed the commit title] Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260513081413.222490-1-sayalip@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/time.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 4bbeb8644d3da..b4472288e0d43 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -458,6 +458,10 @@ DEFINE_PER_CPU(u8, irq_work_pending); #endif /* 32 vs 64 bit */ +/* + * Must be called with preemption disabled since it updates + * per-CPU irq_work state and programs the local CPU decrementer. + */ void arch_irq_work_raise(void) { /* @@ -471,10 +475,8 @@ void arch_irq_work_raise(void) * which could get tangled up if we're messing with the same state * here. */ - preempt_disable(); set_irq_work_pending_flag(); set_dec(1); - preempt_enable(); } static void set_dec_or_work(u64 val) From afa9036b8c9963947b487c36e332df6a42c96fcb Mon Sep 17 00:00:00 2001 From: Xiang Mei Date: Sun, 10 May 2026 23:21:38 -0700 Subject: [PATCH 1418/1518] net/smc: reject CHID-0 ACCEPT that matches an empty ism_dev slot [ Upstream commit 277740023def559a4a2ddc3e8e784ee37a0f16a9 ] On the SMC-D client, slot 0 of ini->ism_dev[]/ini->ism_chid[] is reserved for an SMC-Dv1 device. smc_find_ism_v2_device_clnt() populates V2 entries starting at index 1, so when no V1 device is selected slot 0 is left in its kzalloc()'ed state with ism_dev[0] == NULL and ism_chid[0] == 0. smc_v2_determine_accepted_chid() then matches the peer's CHID against the array starting from index 0 using the CHID alone. A malicious peer replying to a SMC-Dv2-only proposal with d1.chid == 0 matches the empty slot, ini->ism_selected becomes 0, and the subsequent ism_dev[0]->lgr_lock dereference in smc_conn_create() faults at offsetof(struct smcd_dev, lgr_lock) == 0x68: BUG: KASAN: null-ptr-deref in _raw_spin_lock_bh+0x79/0xe0 Write of size 4 at addr 0000000000000068 by task exploit/144 Call Trace: _raw_spin_lock_bh smc_conn_create (net/smc/smc_core.c:1997) __smc_connect (net/smc/af_smc.c:1447) smc_connect (net/smc/af_smc.c:1720) __sys_connect __x64_sys_connect do_syscall_64 Require ism_dev[i] to be non-NULL before accepting a CHID match. Fixes: a7c9c5f4af7f ("net/smc: CLC accept / confirm V2") Reported-by: Weiming Shi Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Xiang Mei Link: https://patch.msgid.link/20260511062138.2839584-1-xmei5@asu.edu Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/smc/af_smc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 6421c2e1c84de..5915fcdef743d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1400,7 +1400,8 @@ smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc, int i; for (i = 0; i < ini->ism_offered_cnt + 1; i++) { - if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) { + if (ini->ism_dev[i] && + ini->ism_chid[i] == ntohs(aclc->d1.chid)) { ini->ism_selected = i; return 0; } From eca989eab4b2599dcb02f72140a7c08f08838520 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 11 May 2026 10:49:17 -0700 Subject: [PATCH 1419/1518] net: tls: fix off-by-one in sg_chain entry count for wrapped sk_msg ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 285943c6e7ca309bbea84b253745154241d9788a ] When an sk_msg scatterlist ring wraps (sg.end < sg.start), tls_push_record() chains the tail portion of the ring to the head using sg_chain(). An extra entry in the sg array is reserved for this: struct sk_msg_sg { [...] /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the * chaining; * 2) to chain tailer SG entries after the message. */ struct scatterlist data[MAX_MSG_FRAGS + 2]; The current code uses MAX_SKB_FRAGS + 1 as the ring size: sg_chain(&msg_pl->sg.data[msg_pl->sg.start], MAX_SKB_FRAGS - msg_pl->sg.start + 1, msg_pl->sg.data); This places the chain pointer at sg_chain(data[start], (MAX_SKB_FRAGS - msg_start + 1) .. = &data[start] + (MAX_SKB_FRAGS - msg_start + 1) - 1 = data[start + (MAX_SKB_FRAGS - start + 1) - 1] = data[MAX_SKB_FRAGS] instead of the true last entry. This is likely due to a "race" of the commit under Fixes landing close to commit 031097d9e079 ("bpf: sk_msg, zap ingress queue on psock down") Convert to ARRAY_SIZE and drop the data[start] / - start (as suggested by Sabrina). Reported-by: 钱一铭 Fixes: 9aaaa56845a0 ("bpf: Sockmap/tls, skmsg can have wrapped skmsg that needs extra chaining") Signed-off-by: Jakub Kicinski Reviewed-by: Sabrina Dubroca Link: https://patch.msgid.link/20260511174920.433155-2-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/tls/tls_sw.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index f2ea190777f0b..1ad5d0e7ae27f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -800,11 +800,9 @@ static int tls_push_record(struct sock *sk, int flags, sg_mark_end(sk_msg_elem(msg_pl, i)); } - if (msg_pl->sg.end < msg_pl->sg.start) { - sg_chain(&msg_pl->sg.data[msg_pl->sg.start], - MAX_SKB_FRAGS - msg_pl->sg.start + 1, + if (msg_pl->sg.end < msg_pl->sg.start) + sg_chain(msg_pl->sg.data, ARRAY_SIZE(msg_pl->sg.data), msg_pl->sg.data); - } i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]); From af855f4c966afafef74faf8390c7b86568c0d46d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 11 May 2026 10:49:18 -0700 Subject: [PATCH 1420/1518] net: tls: prevent chain-after-chain in plain text SG [ Upstream commit ff26a0e8377dec07e4a7230db7675bed1b9a6d03 ] Sashiko points out that if end = 0 (start != 0) the current code will create a chain link to content type right after the wrap link: This would create a chain where the wrap link points directly to another chain link. The scatterlist API sg_next iterator does not recursively resolve consecutive chain links. meaning this is illegal input to crypto. The wrapping link is unnecessary if end = 0. end is the entry after the last one used so end = 0 means there's nothing pushed after the wrap: end start i v v v [ ]...[ ][ d ][ d ][ d ][ d ][rsv for wrap] Skip the wrapping in this case. TLS 1.3 can use the "wrapping slot" for it's chaining if end = 0. This avoids the chain-after-chain. Move the wrap chaining before marking END and chaining off content type, that feels like more logical ordering to me, but should not matter from functional perspective. Reported-by: Sashiko Fixes: 9aaaa56845a0 ("bpf: Sockmap/tls, skmsg can have wrapped skmsg that needs extra chaining") Signed-off-by: Jakub Kicinski Link: https://patch.msgid.link/20260511174920.433155-3-kuba@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/tls/tls_sw.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 1ad5d0e7ae27f..b28eb04075d1b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -789,21 +789,33 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_pl->sg.end; sk_msg_iter_var_prev(i); + /* msg_pl->sg.data is a ring; data[MAX+1] is reserved for the wrap + * link (frags won't use it). 'i' is now the last filled entry: + * + * i end start + * v v v [ rsv ] + * [ d ][ d ][ ][ ]...[ ][ d ][ d ][ d ][chain] + * ^ END v + * `-----------------------------------------' + * + * Note that SGL does not allow chain-after-chain, so for TLS 1.3, + * we must make sure we don't create the wrap entry and then chain + * link to content_type immediately at index 0. + */ + if (i < msg_pl->sg.start) + sg_chain(msg_pl->sg.data, ARRAY_SIZE(msg_pl->sg.data), + msg_pl->sg.data); + rec->content_type = record_type; if (prot->version == TLS_1_3_VERSION) { /* Add content type to end of message. No padding added */ sg_set_buf(&rec->sg_content_type, &rec->content_type, 1); sg_mark_end(&rec->sg_content_type); - sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1, - &rec->sg_content_type); + sg_chain(msg_pl->sg.data, i + 2, &rec->sg_content_type); } else { sg_mark_end(sk_msg_elem(msg_pl, i)); } - if (msg_pl->sg.end < msg_pl->sg.start) - sg_chain(msg_pl->sg.data, ARRAY_SIZE(msg_pl->sg.data), - msg_pl->sg.data); - i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]); From 2bc34520ce5cf0c49151fe5f1fa403f5f097751c Mon Sep 17 00:00:00 2001 From: Sven Schuchmann Date: Tue, 12 May 2026 09:19:47 +0200 Subject: [PATCH 1421/1518] net: phy: DP83TC811: add reading of abilities [ Upstream commit c78bdba7b9666020c0832150a4fc4c0aebc7c6ac ] At this time the driver is not listing any speeds it supports. This should be ETHTOOL_LINK_MODE_100baseT1_Full_BIT for DP83TC811. Add the missing call for phylib to read the abilities. Fixes: b753a9faaf9a ("net: phy: DP83TC811: Introduce support for the DP83TC811 phy") Suggested-by: Andrew Lunn Signed-off-by: Sven Schuchmann Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260512071949.6218-1-schuchmann@schleissheimer.de [pabeni@redhat.com: dropped revision history] Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/phy/dp83tc811.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index e480c2a074505..252fb12b3e68e 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -393,6 +393,7 @@ static struct phy_driver dp83811_driver[] = { .config_init = dp83811_config_init, .config_aneg = dp83811_config_aneg, .soft_reset = dp83811_phy_reset, + .get_features = genphy_c45_pma_read_ext_abilities, .get_wol = dp83811_get_wol, .set_wol = dp83811_set_wol, .config_intr = dp83811_config_intr, From e5460eb7238c19d651a9b22b2378b587033a4095 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Wed, 13 May 2026 11:55:20 +0100 Subject: [PATCH 1422/1518] ovpn: tcp - use cached peer pointer in ovpn_tcp_close() [ Upstream commit 775d8d7ad02aa345e1588424a6a8b9ae49fb9012 ] ovpn_tcp_close() loads the ovpn_socket via rcu_dereference_sk_user_data() under rcu_read_lock(), takes a reference on sock->peer, caches the peer pointer in a local, and drops the read lock. It then passes sock->peer (rather than the cached local) to ovpn_peer_del(), re-dereferencing the ovpn_socket after the RCU read section has ended. Unlike ovpn_tcp_sendmsg(), which uses the same "load under RCU, use after unlock" pattern but is protected by lock_sock() held across the function, ovpn_tcp_close() runs without the socket lock: inet_release() invokes sk_prot->close() without taking lock_sock first. ovpn_socket_release() can therefore complete its kref_put -> detach -> synchronize_rcu -> kfree(sock) sequence concurrently, in the window after ovpn_tcp_close() drops rcu_read_lock() but before it dereferences sock->peer. The synchronize_rcu() in ovpn_socket_release() protects readers that use the dereferenced pointer inside the RCU read section, not those that escape the pointer to a local and use it afterwards. A reproducer follows the pattern of commit 94560267d6c4 ("ovpn: tcp - don't deref NULL sk_socket member after tcp_close()"): trigger a peer removal (keepalive expiration or netlink OVPN_CMD_DEL_PEER) at the same moment userspace closes the TCP fd. That commit fixed the detach-side of the same race window; this one fixes the close-side at a different victim. Tighten the entry block to read sock->peer exactly once into the cached peer local, and route all subsequent uses (the hold check, the ovpn_peer_del() call, and the prot->close() invocation) through that local. sock->peer is only ever written once in ovpn_socket_new() under lock_sock(), before rcu_assign_sk_user_data() publishes the ovpn_socket, and is never reassigned afterwards - but the previous multi-read pattern made that invariant implicit rather than explicit. The same multi-read shape exists in ovpn_tcp_recvmsg(), ovpn_tcp_sendmsg(), ovpn_tcp_data_ready() and ovpn_tcp_write_space(); those will be cleaned up via a dedicated helper in a follow-up net-next series. Fixes: 11851cbd60ea ("ovpn: implement TCP transport") Reviewed-by: Sabrina Dubroca Assisted-by: Claude:claude-opus-4-7 Signed-off-by: David Carlier Signed-off-by: Antonio Quartulli Signed-off-by: Sasha Levin --- drivers/net/ovpn/tcp.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 5499c1572f3e2..5f345ae7d59d2 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -581,14 +581,19 @@ static void ovpn_tcp_close(struct sock *sk, long timeout) rcu_read_lock(); sock = rcu_dereference_sk_user_data(sk); - if (!sock || !sock->peer || !ovpn_peer_hold(sock->peer)) { + if (!sock) { rcu_read_unlock(); return; } + peer = sock->peer; + if (!peer || !ovpn_peer_hold(peer)) { + rcu_read_unlock(); + return; + } rcu_read_unlock(); - ovpn_peer_del(sock->peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT); + ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT); peer->tcp.sk_cb.prot->close(sk, timeout); ovpn_peer_put(peer); } From 8298834912d76dbc82c12b6b4ab7590ed2bb8ae5 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Wed, 13 May 2026 11:55:21 +0100 Subject: [PATCH 1423/1518] ovpn: respect peer refcount in CMD_NEW_PEER error path [ Upstream commit 1fef6614673ff0846d30acdeeaf3cf98bb5f6116 ] ovpn_nl_peer_new_doit()'s error path calls ovpn_peer_release() directly rather than ovpn_peer_put(), bypassing the kref. The accompanying comment ("peer was not yet hashed, thus it is not used in any context") holds for UDP but not for TCP. For UDP, the ovpn_socket union uses the .ovpn arm and never points back at a peer; UDP encap_recv looks up peers via the not-yet-populated hashtables, so the new peer is unreachable until ovpn_peer_add() publishes it. For TCP, ovpn_socket_new() sets ovpn_sock->peer and ovpn_tcp_socket_attach() publishes ovpn_sock via rcu_assign_sk_user_data(). From that moment until ovpn_socket_release() detaches in the error path, the TCP fd is fully wired: userspace recvmsg / sendmsg / close / poll on the fd, as well as the strparser-driven ovpn_tcp_rcv() path, can reach the peer through sk_user_data -> ovpn_sock->peer and bump its refcount via ovpn_peer_hold(). ovpn_tcp_socket_wait_finish() (called inside ovpn_socket_release()) drains strparser and the tx work, but does not synchronize with userspace syscall callers that already hold a peer reference. If ovpn_nl_peer_modify() or ovpn_peer_add() returns an error while such a caller is in flight - notably an ovpn_tcp_recvmsg() blocked in __skb_recv_datagram() on peer->tcp.user_queue - the direct ovpn_peer_release() destroys the peer while the caller still holds the reference, and the eventual ovpn_peer_put() from that caller operates on freed memory. Replace the direct destructor call with ovpn_peer_put() so the kref correctly defers destruction until the last reference is dropped. In the common case where no concurrent user is present, behaviour is unchanged: the kref hits zero immediately and ovpn_peer_release_kref() runs the same destructor. With this conversion ovpn_peer_release() has no callers outside peer.c - ovpn_peer_release_kref() in the same translation unit is the only remaining user - so make it static and drop its declaration from peer.h. Fixes: 11851cbd60ea ("ovpn: implement TCP transport") Reviewed-by: Sabrina Dubroca Assisted-by: Claude:claude-opus-4-7 Signed-off-by: David Carlier Signed-off-by: Antonio Quartulli Signed-off-by: Sasha Levin --- drivers/net/ovpn/netlink.c | 8 +++++--- drivers/net/ovpn/peer.c | 2 +- drivers/net/ovpn/peer.h | 1 - 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c index c7f3824376302..bdb56ef0c9040 100644 --- a/drivers/net/ovpn/netlink.c +++ b/drivers/net/ovpn/netlink.c @@ -455,10 +455,12 @@ int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info) sock_release: ovpn_socket_release(peer); peer_release: - /* release right away because peer was not yet hashed, thus it is not - * used in any context + /* For UDP, the peer is unreachable until added to the hashtables, so + * dropping the initial reference is enough. For TCP, the peer may be + * concurrently reachable via sk_user_data->peer until + * ovpn_socket_release() detaches; rely on the refcount. */ - ovpn_peer_release(peer); + ovpn_peer_put(peer); return ret; } diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index 4bfcab0c8652e..a3d856724b84a 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -348,7 +348,7 @@ static void ovpn_peer_release_rcu(struct rcu_head *head) * ovpn_peer_release - release peer private members * @peer: the peer to release */ -void ovpn_peer_release(struct ovpn_peer *peer) +static void ovpn_peer_release(struct ovpn_peer *peer) { ovpn_crypto_state_release(&peer->crypto); spin_lock_bh(&peer->lock); diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h index a1423f2b09e06..4de5aeae33f7d 100644 --- a/drivers/net/ovpn/peer.h +++ b/drivers/net/ovpn/peer.h @@ -125,7 +125,6 @@ static inline bool ovpn_peer_hold(struct ovpn_peer *peer) return kref_get_unless_zero(&peer->refcount); } -void ovpn_peer_release(struct ovpn_peer *peer); void ovpn_peer_release_kref(struct kref *kref); /** From 097d62df38314c14b88fab9096f3461baf158e2b Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 17 Mar 2026 14:47:56 +0100 Subject: [PATCH 1424/1518] ovpn: fix race between deleting interface and adding new peer [ Upstream commit 982422b11e6f95f766a8cd2c2b1cbdb77e234a61 ] While deleting an existing ovpn interface, there is a very narrow window where adding a new peer via netlink may cause the netdevice to hang and prevent its unregistration. It may happen during ovpn_dellink(), when all existing peers are freed and the device is queued for deregistration, but a CMD_PEER_NEW message comes in adding a new peer that takes again a reference to the netdev. At this point there is no way to release the device because we are under the assumption that all peers were already released. Fix the race condition by releasing all peers in ndo_uninit(), when the netdevice has already been removed from the netdev list. Also ovpn_peer_add() has now an extra check that forces the function to bail out if the device reg_state is not REGISTERED. This way any incoming CMD_PEER_NEW racing with the interface deletion routine will simply stop before adding the peer. Note that the above check happens while holding the netdev_lock to prevent racing netdev state changes. ovpn_dellink() is now empty and can be removed. Reported-by: Hyunwoo Kim Closes: https://lore.kernel.org/netdev/aaVgJ16edTfQkYbx@v4bel/ Suggested-by: Sabrina Dubroca Fixes: 80747caef33d ("ovpn: introduce the ovpn_peer object") Reviewed-by: Sabrina Dubroca Signed-off-by: Antonio Quartulli Signed-off-by: Sasha Levin --- drivers/net/ovpn/main.c | 12 ++---------- drivers/net/ovpn/peer.c | 21 ++++++++++++++++++--- 2 files changed, 20 insertions(+), 13 deletions(-) diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 1bb1afe766a41..3f76b1b0e5f60 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -92,6 +92,8 @@ static void ovpn_net_uninit(struct net_device *dev) { struct ovpn_priv *ovpn = netdev_priv(dev); + disable_delayed_work_sync(&ovpn->keepalive_work); + ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN); gro_cells_destroy(&ovpn->gro_cells); } @@ -208,15 +210,6 @@ static int ovpn_newlink(struct net_device *dev, return register_netdevice(dev); } -static void ovpn_dellink(struct net_device *dev, struct list_head *head) -{ - struct ovpn_priv *ovpn = netdev_priv(dev); - - cancel_delayed_work_sync(&ovpn->keepalive_work); - ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN); - unregister_netdevice_queue(dev, head); -} - static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ovpn_priv *ovpn = netdev_priv(dev); @@ -235,7 +228,6 @@ static struct rtnl_link_ops ovpn_link_ops = { .policy = ovpn_policy, .maxtype = IFLA_OVPN_MAX, .newlink = ovpn_newlink, - .dellink = ovpn_dellink, .fill_info = ovpn_fill_info, }; diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index a3d856724b84a..87a83321f1dd5 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -1029,14 +1029,29 @@ static int ovpn_peer_add_p2p(struct ovpn_priv *ovpn, struct ovpn_peer *peer) */ int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer) { + int ret = -ENODEV; + + /* Prevent adding new peers while destroying the ovpn interface. + * Failing to do so would end up holding the device reference + * endlessly hostage of the new peer object with no chance of + * release.. + */ + netdev_lock(ovpn->dev); + if (ovpn->dev->reg_state != NETREG_REGISTERED) + goto out; + switch (ovpn->mode) { case OVPN_MODE_MP: - return ovpn_peer_add_mp(ovpn, peer); + ret = ovpn_peer_add_mp(ovpn, peer); + break; case OVPN_MODE_P2P: - return ovpn_peer_add_p2p(ovpn, peer); + ret = ovpn_peer_add_p2p(ovpn, peer); + break; } +out: + netdev_unlock(ovpn->dev); - return -EOPNOTSUPP; + return ret; } /** From 2378d25675dacf29b2074dd5a010d7883f6a621a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 14 Mar 2026 14:24:56 +0100 Subject: [PATCH 1425/1518] gcc-plugins: Always define CONST_CAST_GIMPLE and CONST_CAST_TREE [ Upstream commit 905c559e51497b8bfdbb68df8be56d2f70f0de8e ] For gcc-16, the CONST_CAST macro family was removed. Add back what we were using in gcc-common.h, as they are simple wrappers. See GCC commits: c3d96ff9e916c02584aa081f03ab999292efbb50 458c7926d48959abcb2c1adaa22458e27459a551 Suggested-by: Ingo Saitz Link: https://lore.kernel.org/lkml/ab6OKoay0OWkywjK@spatz.zoo Fixes: 6b90bd4ba40b ("GCC plugin infrastructure") Tested-by: Ivan Bulatovic Tested-by: Christopher Cradock Signed-off-by: Kees Cook Signed-off-by: Sasha Levin --- scripts/gcc-plugins/gcc-common.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 8f1b3500f8e2d..abb1964c44d4e 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -309,7 +309,9 @@ typedef const gimple *const_gimple_ptr; #define gimple gimple_ptr #define const_gimple const_gimple_ptr #undef CONST_CAST_GIMPLE -#define CONST_CAST_GIMPLE(X) CONST_CAST(gimple, (X)) +#define CONST_CAST_GIMPLE(X) const_cast((X)) +#undef CONST_CAST_TREE +#define CONST_CAST_TREE(X) const_cast((X)) /* gimple related */ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree lhs, tree op1, tree op2 MEM_STAT_DECL) From f7808b7ddcf21486776cf6e39902e4de7446e7a1 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 5 May 2026 12:24:17 +0200 Subject: [PATCH 1426/1518] x86/xen: Fix xen_e820_swap_entry_with_ram() [ Upstream commit 28e03f78e69cf6628b81f24777799778528a84c1 ] When swapping a not page-aligned E820 map entry with RAM, the start address of the modified entry is calculated wrong (the offset into the page is subtracted instead of being added to the page address). Fixes: be35d91c8880 ("xen: tolerate ACPI NVS memory overlapping with Xen allocated memory") Reported-by: Jan Beulich Reviewed-by: Jan Beulich Signed-off-by: Juergen Gross Message-ID: <20260505102417.208138-1-jgross@suse.com> Signed-off-by: Sasha Levin --- arch/x86/xen/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 3823e52aef523..6260f65a78c5e 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -655,7 +655,7 @@ static void __init xen_e820_swap_entry_with_ram(struct e820_entry *swap_entry) /* Fill new entry (keep size and page offset). */ entry->type = swap_entry->type; entry->addr = entry_end - swap_size + - swap_addr - swap_entry->addr; + swap_entry->addr - swap_addr; entry->size = swap_entry->size; /* Convert old entry to RAM, align to pages. */ From 1370acb8bc390de37ea50d9c414eba3cc0b90f9f Mon Sep 17 00:00:00 2001 From: Ralf Lici Date: Wed, 13 May 2026 15:26:10 +0200 Subject: [PATCH 1427/1518] ovpn: disable BHs when updating device stats [ Upstream commit 0c0dddc07d272a8d25922e48041e8e4d2434df7e ] ovpn updates dev->dstats from both process and softirq contexts. In particular, TCP paths may run from socket callbacks, workqueues or strparser work, while UDP receive and ovpn's ndo_start_xmit path may update the same per-device dstats from BH context. Add ovpn device drop-stat helpers that disable BHs around dev_dstats_rx_dropped() and dev_dstats_tx_dropped(), and use them for drop accounting. The successful RX dev_dstats_rx_add() update is already covered by the BH-disabled section around gro_cells_receive(). For the successful TCP TX dev_dstats_tx_add() update, replace the existing preempt-disabled section with a BH-disabled one. Fixes: 11851cbd60ea ("ovpn: implement TCP transport") Signed-off-by: Ralf Lici Signed-off-by: Antonio Quartulli Signed-off-by: Sasha Levin --- drivers/net/ovpn/io.c | 12 ++++++------ drivers/net/ovpn/stats.h | 16 ++++++++++++++++ drivers/net/ovpn/tcp.c | 10 +++++----- drivers/net/ovpn/udp.c | 2 +- 4 files changed, 28 insertions(+), 12 deletions(-) diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index 955c9a37e1f8d..c03e58e28a860 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -196,7 +196,7 @@ void ovpn_decrypt_post(void *data, int ret) skb = NULL; drop: if (unlikely(skb)) - dev_dstats_rx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); kfree_skb(skb); drop_nocount: if (likely(peer)) @@ -220,7 +220,7 @@ void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb) net_info_ratelimited("%s: no available key for peer %u, key-id: %u\n", netdev_name(peer->ovpn->dev), peer->id, key_id); - dev_dstats_rx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); kfree_skb(skb); ovpn_peer_put(peer); return; @@ -298,7 +298,7 @@ void ovpn_encrypt_post(void *data, int ret) rcu_read_unlock(); err: if (unlikely(skb)) - dev_dstats_tx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); if (likely(peer)) ovpn_peer_put(peer); if (likely(ks)) @@ -340,7 +340,7 @@ static void ovpn_send(struct ovpn_priv *ovpn, struct sk_buff *skb, */ skb_list_walk_safe(skb, curr, next) { if (unlikely(!ovpn_encrypt_one(peer, curr))) { - dev_dstats_tx_dropped(ovpn->dev); + ovpn_dev_dstats_tx_dropped(ovpn->dev); kfree_skb(curr); } } @@ -411,7 +411,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!curr)) { net_err_ratelimited("%s: skb_share_check failed for payload packet\n", netdev_name(dev)); - dev_dstats_tx_dropped(ovpn->dev); + ovpn_dev_dstats_tx_dropped(ovpn->dev); continue; } @@ -437,7 +437,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) drop: ovpn_peer_put(peer); drop_no_peer: - dev_dstats_tx_dropped(ovpn->dev); + ovpn_dev_dstats_tx_dropped(ovpn->dev); skb_tx_error(skb); kfree_skb_list(skb); return NETDEV_TX_OK; diff --git a/drivers/net/ovpn/stats.h b/drivers/net/ovpn/stats.h index 53433d8b6c331..3a45b97c00568 100644 --- a/drivers/net/ovpn/stats.h +++ b/drivers/net/ovpn/stats.h @@ -11,6 +11,8 @@ #ifndef _NET_OVPN_OVPNSTATS_H_ #define _NET_OVPN_OVPNSTATS_H_ +#include + /* one stat */ struct ovpn_peer_stat { atomic64_t bytes; @@ -44,4 +46,18 @@ static inline void ovpn_peer_stats_increment_tx(struct ovpn_peer_stats *stats, ovpn_peer_stats_increment(&stats->tx, n); } +static inline void ovpn_dev_dstats_tx_dropped(struct net_device *dev) +{ + local_bh_disable(); + dev_dstats_tx_dropped(dev); + local_bh_enable(); +} + +static inline void ovpn_dev_dstats_rx_dropped(struct net_device *dev) +{ + local_bh_disable(); + dev_dstats_rx_dropped(dev); + local_bh_enable(); +} + #endif /* _NET_OVPN_OVPNSTATS_H_ */ diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 5f345ae7d59d2..505c2f214c9f1 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -152,7 +152,7 @@ static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb) if (WARN_ON(!ovpn_peer_hold(peer))) goto err_nopeer; schedule_work(&peer->tcp.defer_del_work); - dev_dstats_rx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); err_nopeer: kfree_skb(skb); } @@ -298,9 +298,9 @@ static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk) } while (peer->tcp.out_msg.len > 0); if (!peer->tcp.out_msg.len) { - preempt_disable(); + local_bh_disable(); dev_dstats_tx_add(peer->ovpn->dev, skb->len); - preempt_enable(); + local_bh_enable(); } kfree_skb(peer->tcp.out_msg.skb); @@ -331,7 +331,7 @@ static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk, ovpn_tcp_send_sock(peer, sk); if (peer->tcp.out_msg.skb) { - dev_dstats_tx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); kfree_skb(skb); return; } @@ -353,7 +353,7 @@ void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct sock *sk, if (sock_owned_by_user(sk)) { if (skb_queue_len(&peer->tcp.out_queue) >= READ_ONCE(net_hotdata.max_backlog)) { - dev_dstats_tx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); kfree_skb(skb); goto unlock; } diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c index 272b535ecaad4..367563d84472f 100644 --- a/drivers/net/ovpn/udp.c +++ b/drivers/net/ovpn/udp.c @@ -126,7 +126,7 @@ static int ovpn_udp_encap_recv(struct sock *sk, struct sk_buff *skb) return 0; drop: - dev_dstats_rx_dropped(ovpn->dev); + ovpn_dev_dstats_rx_dropped(ovpn->dev); drop_noovpn: kfree_skb(skb); return 0; From 81c8a9f75a4268f2b4756107b298c69be9248c0d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 13 May 2026 08:58:25 -0400 Subject: [PATCH 1428/1518] tls: Preserve sk_err across recvmsg() when data has been copied [ Upstream commit f508262ae9f21fe0e6c0749948b9dc7dd5a62a70 ] The sk_err check in tls_rx_rec_wait() consumes the error via sock_error(), which clears sk_err atomically. When the caller (tls_sw_recvmsg, tls_sw_splice_read, or tls_sw_read_sock) already has bytes copied to userspace, it returns those bytes and discards the error from this call. sk_err is now zero on the socket, so the next read syscall observes only RCV_SHUTDOWN and reports a clean EOF instead of the actual error (typically -ECONNRESET). The race is reachable when tls_read_flush_backlog()'s periodic sk_flush_backlog() triggers tcp_reset() in the middle of a multi-record read. Pass a has_copied flag to tls_rx_rec_wait(). When has_copied is false, consume sk_err via sock_error() as before. When has_copied is true, report the error from READ_ONCE() but leave sk_err set: the caller returns the byte count and discards the err from this call, and the next read syscall surfaces the preserved sk_err. This mirrors the tcp_recvmsg() preserve-and-surface pattern. The decrypt-abort path is unaffected: tls_err_abort() raises sk_err to EBADMSG after tls_rx_rec_wait() returns, and nothing on the caller's return path consumes it, so the EBADMSG surfaces on the next read. tls_sw_splice_read() passes has_copied=false: it processes one record per call, so no bytes have been copied within the function when tls_rx_rec_wait() runs. A reset that arrives between iterations of splice_direct_to_actor() (the sendfile() path) is still consumed by sock_error() in the later call, and the outer loop returns the prior iterations' byte count and drops the error. tcp_splice_read() exhibits the same pattern at the iteration boundary; addressing it belongs at the splice_direct_to_actor() layer and is out of scope here. Fixes: c46b01839f7a ("tls: rx: periodically flush socket backlog") Suggested-by: Jakub Kicinski Signed-off-by: Chuck Lever Link: https://patch.msgid.link/20260513125825.205189-1-cel@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/tls/tls_sw.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b28eb04075d1b..034f322054e53 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1366,9 +1366,14 @@ void tls_sw_splice_eof(struct socket *sock) mutex_unlock(&tls_ctx->tx_lock); } +/* When has_copied is true the caller has already moved bytes to + * userspace. Report sk_err but leave it set so the next read + * surfaces it instead of a spurious EOF, otherwise sk_err is + * consumed via sock_error(). + */ static int tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, - bool released) + bool released, bool has_copied) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1386,8 +1391,11 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, if (!sk_psock_queue_empty(psock)) return 0; - if (sk->sk_err) + if (sk->sk_err) { + if (has_copied) + return -READ_ONCE(sk->sk_err); return sock_error(sk); + } if (ret < 0) return ret; @@ -1423,7 +1431,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, } if (unlikely(!tls_strp_msg_load(&ctx->strp, released))) - return tls_rx_rec_wait(sk, psock, nonblock, false); + return tls_rx_rec_wait(sk, psock, nonblock, false, has_copied); return 1; } @@ -2111,7 +2119,7 @@ int tls_sw_recvmsg(struct sock *sk, int to_decrypt, chunk; err = tls_rx_rec_wait(sk, psock, flags & MSG_DONTWAIT, - released); + released, !!(decrypted + copied)); if (err <= 0) { if (psock) { chunk = sk_msg_recvmsg(sk, psock, msg, len, @@ -2298,7 +2306,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct tls_decrypt_arg darg; err = tls_rx_rec_wait(sk, NULL, flags & SPLICE_F_NONBLOCK, - true); + true, false); if (err <= 0) goto splice_read_end; @@ -2384,7 +2392,7 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc, } else { struct tls_decrypt_arg darg; - err = tls_rx_rec_wait(sk, NULL, true, released); + err = tls_rx_rec_wait(sk, NULL, true, released, !!copied); if (err <= 0) goto read_sock_end; From b4dc0056397fe8c94cd440ae219ae2b68b875625 Mon Sep 17 00:00:00 2001 From: Jeroen Massar Date: Wed, 13 May 2026 09:33:02 +0300 Subject: [PATCH 1429/1518] net/mlx5: Do not restore destination-less TC rules [ Upstream commit 8d0a5af8b1ba598e7340761729801624e7a9330e ] After IPsec policy/state TX rules are added, any TC flow rule, which forwards packets to uplink, is modified to forward to IPsec TX tables. As these tables are destroyed dynamically, whenever there is no reference to them, the destinations of this kind of rules must be restored to uplink, unless there is no destination for that rule. The flow rules FLOW_ACTION_ACCEPT, DROP, TRAP, GOTO and SAMPLE do not have a destination port, and thus out_count = 0. At cleanup time of the rules in mlx5_esw_ipsec_modify_flow_dests we call mlx5_eswitch_restore_ipsec_rule but as the above types do not have a destination we get an underflow of out_count, as the port is passed, which is esw_attr->out_count - 1. This change avoids calling mlx5_eswitch_restore_ipsec_rule when there are no output destinations and thus avoids the underflow. Fixes: d1569537a837 ("net/mlx5e: Modify and restore TC rules for IPSec TX rules") Signed-off-by: Jeroen Massar Reviewed-by: Jianbo Liu Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20260513063302.333761-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 3cfe743610d3f..ab50d2c734ede 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -142,7 +142,8 @@ static int mlx5_esw_ipsec_modify_flow_dests(struct mlx5_eswitch *esw, attr = flow->attr; esw_attr = attr->esw_attr; - if (esw_attr->out_count - esw_attr->split_count > 1) + if (!esw_attr->out_count || + esw_attr->out_count - esw_attr->split_count > 1) return 0; err = mlx5_eswitch_restore_ipsec_rule(esw, flow->rule[0], esw_attr, From 36de63965464026ebc520c30d4634ae8be513212 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 11 May 2026 12:53:17 -0500 Subject: [PATCH 1430/1518] scsi: sd: Fix return code handling in sd_spinup_disk() [ Upstream commit 6ea68a8dc7d2711504d944811981a5304af7d7a9 ] As found by smatch-ci, scsi_execute_cmd() can return negative or positve values so we should use a int instead of unsigned int. Fixes: b4d0c33a32c3 ("scsi: sd: Fix sshdr use in sd_spinup_disk") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-scsi/agFbI7E6JQwd3wGW@stanley.mountain/T/#u Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Link: https://patch.msgid.link/20260511175317.114007-1-michael.christie@oracle.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/sd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 072d4c4add334..d9bae23cb929e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2398,8 +2398,7 @@ sd_spinup_disk(struct scsi_disk *sdkp) { static const u8 cmd[10] = { TEST_UNIT_READY }; unsigned long spintime_expire = 0; - int spintime, sense_valid = 0; - unsigned int the_result; + int the_result, spintime, sense_valid = 0; struct scsi_sense_hdr sshdr; struct scsi_failure failure_defs[] = { /* Do not retry Medium Not Present */ From 1ddf678bb75b6383c775ece61d40956c441d8a26 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Wed, 13 May 2026 21:08:52 +0200 Subject: [PATCH 1431/1518] ASoC: codecs: fs210x: fix possible buffer overflow [ Upstream commit 0d435a7ebcd4e97e47673c1ab6fb27f973a053ec ] In fs210x_effect_scene_info(), a string was copied like this: strscpy(DST, SRC, strlen(SRC) + 1); A buffer overflow would happen if strlen(SRC) >= sizeof(DST). Actually, strscpy() must be used this way: strscpy(DST, SRC, sizeof(DST)); strscpy(DST, SRC); // defaults to sizeof(DST) Fixes: 756117701779 ("ASoC: codecs: Add FourSemi FS2104/5S audio amplifier driver") Signed-off-by: Alexander A. Klimov Link: https://patch.msgid.link/20260513190852.196723-2-grandmaster@al2klimov.de Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/fs210x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/fs210x.c b/sound/soc/codecs/fs210x.c index e2f85714972d5..e2207c53c50d5 100644 --- a/sound/soc/codecs/fs210x.c +++ b/sound/soc/codecs/fs210x.c @@ -968,7 +968,7 @@ static int fs210x_effect_scene_info(struct snd_kcontrol *kcontrol, if (scene->name) name = scene->name; - strscpy(uinfo->value.enumerated.name, name, strlen(name) + 1); + strscpy(uinfo->value.enumerated.name, name); return 0; } From c53cac053d625b3e54bce39b996a2434bb62801f Mon Sep 17 00:00:00 2001 From: Robertus Diawan Chris Date: Fri, 8 May 2026 10:39:14 +0700 Subject: [PATCH 1432/1518] ALSA: scarlett2: Add missing error check when initialise Autogain Status [ Upstream commit c0e4fffc0f474b7ed10adee4ab2bc1a66d36fc72 ] When initialise new control with scarlett2_add_new_ctl() function for Autogain Status, scarlett2_add_new_ctl() might throw an error. So, add error check after initialise new control for Autogain Status. This is reported by Coverity Scan with CID 1598781 as UNUSED_VALUE. Fixes: 0a995e38dc44 ("ALSA: scarlett2: Add support for software-controllable input gain") Signed-off-by: Robertus Diawan Chris Link: https://patch.msgid.link/20260508033914.111596-1-robertusdchris@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/mixer_scarlett2.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index d0cad1d1efa35..da3c2741ef575 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -6707,6 +6707,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) err = scarlett2_add_new_ctl( mixer, &scarlett2_autogain_status_ctl, i, 1, s, &private->autogain_status_ctls[i]); + if (err < 0) + return err; } /* Add autogain target controls */ From 782693eb53f8111bd736026448847faa01b8c30b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 May 2026 10:19:09 -0600 Subject: [PATCH 1433/1518] io_uring/net: punt IORING_OP_BIND async if it needs file create [ Upstream commit ccd25890f73c082fe2657ed227b497d6ac5fdc40 ] For two reasons: 1) An opcode cannot block inside io_uring_enter() doing submissions, as it'll stall the submission side pipeline. 2) Ending up in sb_start_write() -> __sb_start_write() -> percpu_down_read_freezable() introduces a new lockdep edge, which it correctly complains about. Check if the socket type is AF_UNIX and has a non-empty pathname. If it does, mark it REQ_F_FORCE_ASYNC to punt the submission to io-wq rather than attempt to do it inline. Fixes: 7481fd93fa0a ("io_uring: Introduce IORING_OP_BIND") Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/net.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/io_uring/net.c b/io_uring/net.c index ad08f693bccb9..7595850c2217a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -1837,11 +1838,29 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) return IOU_COMPLETE; } +/* + * Check if bind request would potentially end up with filename_create(), + * which in turn end up in mnt_want_write() which will grab the fs + * percpu start write sem. This can trigger a lockdep warning. + */ +static int io_bind_file_create(const struct io_async_msghdr *io, int addr_len) +{ + const struct sockaddr_un *sun; + + if (io->addr.ss_family != AF_UNIX) + return 0; + if (addr_len <= offsetof(struct sockaddr_un, sun_path)) + return 0; + sun = (const struct sockaddr_un *) &io->addr; + return sun->sun_path[0] != '\0'; +} + int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); struct sockaddr __user *uaddr; struct io_async_msghdr *io; + int ret; if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; @@ -1852,7 +1871,12 @@ int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) io = io_msg_alloc_async(req); if (unlikely(!io)) return -ENOMEM; - return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); + ret = move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); + if (unlikely(ret)) + return ret; + if (io_bind_file_create(io, bind->addr_len)) + req->flags |= REQ_F_FORCE_ASYNC; + return 0; } int io_bind(struct io_kiocb *req, unsigned int issue_flags) From 76b995bc57bd90cb6e954e1966fbd8786da47f0d Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 14 May 2026 11:29:48 +0200 Subject: [PATCH 1434/1518] vsock/virtio: fix zerocopy completion for multi-skb sends [ Upstream commit ae38d9179190a956e2a87a69ef1dd6f451b51c4d ] When a large message is fragmented into multiple skbs, the zerocopy uarg is only allocated and attached to the last skb in the loop. Non-final skbs carry pinned user pages with no completion tracking, so the kernel has no way to notify userspace when those pages are safe to reuse. If the loop breaks early the uarg is never allocated at all, leaking pinned pages with no completion notification. Fix this by following the approach used by TCP: allocate the zerocopy uarg (if not provided by the caller) before the send loop and attach it to every skb via skb_zcopy_set(), which takes a reference per skb. Each skb's completion properly decrements the refcount, and the notification only fires after the last skb is freed. On failure, if no data was sent, the uarg is cleanly aborted via net_zcopy_put_abort(). This issue was initially discovered by sashiko while reviewing commit 1cb36e252211 ("vsock/virtio: fix MSG_ZEROCOPY pinned-pages accounting") but was pre-existing. Fixes: 581512a6dc93 ("vsock/virtio: MSG_ZEROCOPY flag support") Closes: https://sashiko.dev/#/patchset/20260420132051.217589-1-sgarzare%40redhat.com Reported-by: Maher Azzouzi Signed-off-by: Stefano Garzarella Acked-by: Michael S. Tsirkin Acked-by: Arseniy Krasnov Link: https://patch.msgid.link/20260514092948.268720-1-sgarzare@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/vmw_vsock/virtio_transport_common.c | 83 ++++++++++--------------- 1 file changed, 34 insertions(+), 49 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 65e2b24892346..ed42e08798a96 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -72,34 +72,6 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, return true; } -static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk, - struct sk_buff *skb, - struct msghdr *msg, - size_t pkt_len, - bool zerocopy) -{ - struct ubuf_info *uarg; - - if (msg->msg_ubuf) { - uarg = msg->msg_ubuf; - net_zcopy_get(uarg); - } else { - struct ubuf_info_msgzc *uarg_zc; - - uarg = msg_zerocopy_realloc(sk_vsock(vsk), - pkt_len, NULL, false); - if (!uarg) - return -1; - - uarg_zc = uarg_to_msgzc(uarg); - uarg_zc->zerocopy = zerocopy ? 1 : 0; - } - - skb_zcopy_init(skb, uarg); - - return 0; -} - static int virtio_transport_fill_skb(struct sk_buff *skb, struct virtio_vsock_pkt_info *info, size_t len, @@ -319,8 +291,10 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, u32 src_cid, src_port, dst_cid, dst_port; const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; + struct ubuf_info *uarg = NULL; u32 pkt_len = info->pkt_len; bool can_zcopy = false; + bool have_uref = false; u32 rest_len; int ret; @@ -362,6 +336,25 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, if (can_zcopy) max_skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, (MAX_SKB_FRAGS * PAGE_SIZE)); + + if (info->msg->msg_flags & MSG_ZEROCOPY && + info->op == VIRTIO_VSOCK_OP_RW) { + uarg = info->msg->msg_ubuf; + + if (!uarg) { + uarg = msg_zerocopy_realloc(sk_vsock(vsk), + pkt_len, NULL, false); + if (!uarg) { + virtio_transport_put_credit(vvs, pkt_len); + return -ENOMEM; + } + + if (!can_zcopy) + uarg_to_msgzc(uarg)->zerocopy = 0; + + have_uref = true; + } + } } rest_len = pkt_len; @@ -380,27 +373,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, break; } - /* We process buffer part by part, allocating skb on - * each iteration. If this is last skb for this buffer - * and MSG_ZEROCOPY mode is in use - we must allocate - * completion for the current syscall. - * - * Pass pkt_len because msg iter is already consumed - * by virtio_transport_fill_skb(), so iter->count - * can not be used for RLIMIT_MEMLOCK pinned-pages - * accounting done by msg_zerocopy_realloc(). - */ - if (info->msg && info->msg->msg_flags & MSG_ZEROCOPY && - skb_len == rest_len && info->op == VIRTIO_VSOCK_OP_RW) { - if (virtio_transport_init_zcopy_skb(vsk, skb, - info->msg, - pkt_len, - can_zcopy)) { - kfree_skb(skb); - ret = -ENOMEM; - break; - } - } + skb_zcopy_set(skb, uarg, NULL); virtio_transport_inc_tx_pkt(vvs, skb); @@ -424,6 +397,18 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_put_credit(vvs, rest_len); + /* msg_zerocopy_realloc() initializes the ubuf_info refcnt to 1. + * skb_zcopy_set() increases it for each skb, so we can drop that + * initial reference to keep it balanced. + */ + if (have_uref) { + if (rest_len == pkt_len) + /* No data sent, abort the notification. */ + net_zcopy_put_abort(uarg, true); + else + net_zcopy_put(uarg); + } + /* Return number of bytes, if any data has been sent. */ if (rest_len != pkt_len) ret = pkt_len - rest_len; From 35f69e993d002b22b108b1785c5a2b2c0a14acde Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 15 Oct 2025 12:40:06 +0100 Subject: [PATCH 1435/1518] btrfs: add macros to facilitate printing of keys [ Upstream commit 95de4b097e25225d4deb5a33a4bfc27bb441f2d8 ] There's a lot of places where we need to print a key, and it's tiresome to type the format specifier, typically "(%llu %u %llu)", as well as passing 3 arguments to a prink family function (key->objectid, key->type, key->offset). So add a couple macros for this just like we have for csum values in btrfs_inode.h (CSUM_FMT and CSUM_FMT_VALUE). This also ensures that we consistently print a key in the same format, always as "(%llu %llu %llu)", which is the most common format we use, but we have a few variations such as "[%llu %llu %llu]" for no good reason. This patch introduces the macros while the next one makes use of it. This is to ease backports of future patches, since then we can backport this patch which is simple and short and then backport those future patches, as the next patch in the series that makes use of these new macros is quite large and may have some dependencies. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 1e92637722ae ("btrfs: check for subvolume before deleting squota qgroup") Signed-off-by: Sasha Levin --- fs/btrfs/fs.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 37aa8d141a83d..acdb9e52f6fd7 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -73,6 +73,9 @@ struct btrfs_space_info; #define BTRFS_SUPER_INFO_SIZE 4096 static_assert(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE); +#define BTRFS_KEY_FMT "(%llu %u %llu)" +#define BTRFS_KEY_FMT_VALUE(key) (key)->objectid, (key)->type, (key)->offset + /* * Number of metadata items necessary for an unlink operation: * From 16141bef6fb1a72bb11a5e46965facc9846c9d42 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 15 Oct 2025 13:16:26 +0100 Subject: [PATCH 1436/1518] btrfs: use the key format macros when printing keys [ Upstream commit af1e800c0244a04f5eb0993745c23d974f262628 ] Change all locations that print a key to use the new macros to print them in order to ensure a consistent style and avoid repetitive code. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 1e92637722ae ("btrfs: check for subvolume before deleting squota qgroup") Signed-off-by: Sasha Levin --- fs/btrfs/backref.c | 11 +++++------ fs/btrfs/ctree.c | 17 +++++++---------- fs/btrfs/extent-tree.c | 14 +++++++------- fs/btrfs/inode.c | 4 ++-- fs/btrfs/print-tree.c | 14 ++++++-------- fs/btrfs/qgroup.c | 6 ++---- fs/btrfs/relocation.c | 4 ++-- fs/btrfs/root-tree.c | 4 ++-- fs/btrfs/send.c | 10 ++++------ fs/btrfs/tree-checker.c | 21 +++++++++------------ fs/btrfs/tree-log.c | 38 ++++++++++++++++++-------------------- 11 files changed, 64 insertions(+), 79 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2ab550a1e715a..e050d0938dc45 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -666,10 +666,9 @@ static int resolve_indirect_ref(struct btrfs_backref_walk_ctx *ctx, ret = btrfs_search_old_slot(root, &search_key, path, ctx->time_seq); btrfs_debug(ctx->fs_info, - "search slot in root %llu (level %d, ref count %d) returned %d for key (%llu %u %llu)", - ref->root_id, level, ref->count, ret, - ref->key_for_search.objectid, ref->key_for_search.type, - ref->key_for_search.offset); +"search slot in root %llu (level %d, ref count %d) returned %d for key " BTRFS_KEY_FMT, + ref->root_id, level, ref->count, ret, + BTRFS_KEY_FMT_VALUE(&ref->key_for_search)); if (ret < 0) goto out; @@ -3323,9 +3322,9 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, eb = path->nodes[level]; if (btrfs_node_blockptr(eb, path->slots[level]) != cur->bytenr) { btrfs_err(fs_info, -"couldn't find block (%llu) (level %d) in tree (%llu) with key (%llu %u %llu)", +"couldn't find block (%llu) (level %d) in tree (%llu) with key " BTRFS_KEY_FMT, cur->bytenr, level - 1, btrfs_root_id(root), - tree_key->objectid, tree_key->type, tree_key->offset); + BTRFS_KEY_FMT_VALUE(tree_key)); btrfs_put_root(root); ret = -ENOENT; goto out; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 6e053caa6e101..27e2adc2ee717 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2599,12 +2599,11 @@ void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, if (unlikely(btrfs_comp_keys(&disk_key, new_key) >= 0)) { btrfs_print_leaf(eb); btrfs_crit(fs_info, - "slot %u key (%llu %u %llu) new key (%llu %u %llu)", + "slot %u key " BTRFS_KEY_FMT " new key " BTRFS_KEY_FMT, slot, btrfs_disk_key_objectid(&disk_key), btrfs_disk_key_type(&disk_key), btrfs_disk_key_offset(&disk_key), - new_key->objectid, new_key->type, - new_key->offset); + BTRFS_KEY_FMT_VALUE(new_key)); BUG(); } } @@ -2613,12 +2612,11 @@ void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, if (unlikely(btrfs_comp_keys(&disk_key, new_key) <= 0)) { btrfs_print_leaf(eb); btrfs_crit(fs_info, - "slot %u key (%llu %u %llu) new key (%llu %u %llu)", + "slot %u key " BTRFS_KEY_FMT " new key " BTRFS_KEY_FMT, slot, btrfs_disk_key_objectid(&disk_key), btrfs_disk_key_type(&disk_key), btrfs_disk_key_offset(&disk_key), - new_key->objectid, new_key->type, - new_key->offset); + BTRFS_KEY_FMT_VALUE(new_key)); BUG(); } } @@ -2677,10 +2675,9 @@ static bool check_sibling_keys(const struct extent_buffer *left, btrfs_crit(left->fs_info, "right extent buffer:"); btrfs_print_tree(right, false); btrfs_crit(left->fs_info, -"bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)", - left_last.objectid, left_last.type, - left_last.offset, right_first.objectid, - right_first.type, right_first.offset); +"bad key order, sibling blocks, left last " BTRFS_KEY_FMT " right first " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(&left_last), + BTRFS_KEY_FMT_VALUE(&right_first)); return true; } return false; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 863b45092a190..e40835fe4bde6 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -165,8 +165,8 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans, if (unlikely(num_refs == 0)) { ret = -EUCLEAN; btrfs_err(fs_info, - "unexpected zero reference count for extent item (%llu %u %llu)", - key.objectid, key.type, key.offset); + "unexpected zero reference count for extent item " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(&key)); btrfs_abort_transaction(trans, ret); return ret; } @@ -597,8 +597,8 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, num_refs = btrfs_shared_data_ref_count(leaf, ref2); } else { btrfs_err(trans->fs_info, - "unrecognized backref key (%llu %u %llu)", - key.objectid, key.type, key.offset); + "unrecognized backref key " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(&key)); btrfs_abort_transaction(trans, -EUCLEAN); return -EUCLEAN; } @@ -3324,9 +3324,9 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (iref) { if (unlikely(path->slots[0] != extent_slot)) { abort_and_dump(trans, path, -"invalid iref, extent item key (%llu %u %llu) slot %u doesn't have wanted iref", - key.objectid, key.type, - key.offset, path->slots[0]); +"invalid iref, extent item key " BTRFS_KEY_FMT " slot %u doesn't have wanted iref", + BTRFS_KEY_FMT_VALUE(&key), + path->slots[0]); ret = -EUCLEAN; goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2c361e0691fc5..dcc0e53782c61 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5668,9 +5668,9 @@ static int btrfs_inode_by_name(struct btrfs_inode *dir, struct dentry *dentry, location->type != BTRFS_ROOT_ITEM_KEY)) { ret = -EUCLEAN; btrfs_warn(root->fs_info, -"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))", +"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location " BTRFS_KEY_FMT ")", __func__, fname.disk_name.name, btrfs_ino(dir), - location->objectid, location->type, location->offset); + BTRFS_KEY_FMT_VALUE(location)); } if (!ret) *type = btrfs_dir_ftype(path->nodes[0], di); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 62b993fae54ff..06edc5cdb00d3 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -131,7 +131,7 @@ static void print_extent_item(const struct extent_buffer *eb, int slot, int type struct btrfs_tree_block_info *info; info = (struct btrfs_tree_block_info *)(ei + 1); btrfs_tree_block_key(eb, info, &key); - pr_info("\t\ttree block key (%llu %u %llu) level %d\n", + pr_info("\t\ttree block key " BTRFS_KEY_FMT " level %d\n", btrfs_disk_key_objectid(&key), key.type, btrfs_disk_key_offset(&key), btrfs_tree_block_level(eb, info)); @@ -277,9 +277,8 @@ static void print_dir_item(const struct extent_buffer *eb, int i) struct btrfs_key location; btrfs_dir_item_key_to_cpu(eb, di, &location); - pr_info("\t\tlocation key (%llu %u %llu) type %d\n", - location.objectid, location.type, location.offset, - btrfs_dir_ftype(eb, di)); + pr_info("\t\tlocation key " BTRFS_KEY_FMT " type %d\n", + BTRFS_KEY_FMT_VALUE(&location), btrfs_dir_ftype(eb, di)); pr_info("\t\ttransid %llu data_len %u name_len %u\n", btrfs_dir_transid(eb, di), data_len, name_len); di = (struct btrfs_dir_item *)((char *)di + len); @@ -598,10 +597,9 @@ void btrfs_print_tree(const struct extent_buffer *c, bool follow) print_eb_refs_lock(c); for (i = 0; i < nr; i++) { btrfs_node_key_to_cpu(c, &key, i); - pr_info("\tkey %d (%llu %u %llu) block %llu gen %llu\n", - i, key.objectid, key.type, key.offset, - btrfs_node_blockptr(c, i), - btrfs_node_ptr_generation(c, i)); + pr_info("\tkey %d " BTRFS_KEY_FMT " block %llu gen %llu\n", + i, BTRFS_KEY_FMT_VALUE(&key), btrfs_node_blockptr(c, i), + btrfs_node_ptr_generation(c, i)); } if (!follow) return; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 302bb3ecf39a3..1f83af14568ca 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3734,10 +3734,8 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans, path, 1, 0); btrfs_debug(fs_info, - "current progress key (%llu %u %llu), search_slot ret %d", - fs_info->qgroup_rescan_progress.objectid, - fs_info->qgroup_rescan_progress.type, - fs_info->qgroup_rescan_progress.offset, ret); + "current progress key " BTRFS_KEY_FMT ", search_slot ret %d", + BTRFS_KEY_FMT_VALUE(&fs_info->qgroup_rescan_progress), ret); if (ret) { /* diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 0765e06d00b80..fc76013b1a3e0 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -615,8 +615,8 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress); btrfs_err(fs_info, - "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)", - objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset); + "cannot relocate partially dropped subvolume %llu, drop progress key " BTRFS_KEY_FMT, + objectid, BTRFS_KEY_FMT_VALUE(&cpu_key)); ret = -EUCLEAN; goto fail; } diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index d07eab70f759d..6a7e297ab0a7a 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -147,8 +147,8 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root if (unlikely(ret > 0)) { btrfs_crit(fs_info, - "unable to find root key (%llu %u %llu) in tree %llu", - key->objectid, key->type, key->offset, btrfs_root_id(root)); + "unable to find root key " BTRFS_KEY_FMT " in tree %llu", + BTRFS_KEY_FMT_VALUE(key), btrfs_root_id(root)); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 9012ce7a742f4..04473387ee8bf 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1053,10 +1053,8 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path, } if (unlikely(start < p->buf)) { btrfs_err(root->fs_info, - "send: path ref buffer underflow for key (%llu %u %llu)", - found_key->objectid, - found_key->type, - found_key->offset); + "send: path ref buffer underflow for key " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(found_key)); ret = -EINVAL; goto out; } @@ -7276,8 +7274,8 @@ static int search_key_again(const struct send_ctx *sctx, if (unlikely(ret > 0)) { btrfs_print_tree(path->nodes[path->lowest_level], false); btrfs_err(root->fs_info, -"send: key (%llu %u %llu) not found in %s root %llu, lowest_level %d, slot %d", - key->objectid, key->type, key->offset, +"send: key " BTRFS_KEY_FMT" not found in %s root %llu, lowest_level %d, slot %d", + BTRFS_KEY_FMT_VALUE(key), (root == sctx->parent_root ? "parent" : "send"), btrfs_root_id(root), path->lowest_level, path->slots[path->lowest_level]); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 33a45737c4cf4..db7402836340a 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1635,10 +1635,9 @@ static int check_extent_item(struct extent_buffer *leaf, if (unlikely(prev_end > key->objectid)) { extent_err(leaf, slot, - "previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]", - prev_key->objectid, prev_key->type, - prev_key->offset, key->objectid, key->type, - key->offset); + "previous extent " BTRFS_KEY_FMT " overlaps current extent " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(prev_key), + BTRFS_KEY_FMT_VALUE(key)); return -EUCLEAN; } } @@ -2077,10 +2076,9 @@ enum btrfs_tree_block_status __btrfs_check_leaf(struct extent_buffer *leaf) /* Make sure the keys are in the right order */ if (unlikely(btrfs_comp_cpu_keys(&prev_key, &key) >= 0)) { generic_err(leaf, slot, - "bad key order, prev (%llu %u %llu) current (%llu %u %llu)", - prev_key.objectid, prev_key.type, - prev_key.offset, key.objectid, key.type, - key.offset); + "bad key order, prev " BTRFS_KEY_FMT " current " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(&prev_key), + BTRFS_KEY_FMT_VALUE(&key)); return BTRFS_TREE_BLOCK_BAD_KEY_ORDER; } @@ -2198,10 +2196,9 @@ enum btrfs_tree_block_status __btrfs_check_node(struct extent_buffer *node) if (unlikely(btrfs_comp_cpu_keys(&key, &next_key) >= 0)) { generic_err(node, slot, - "bad key order, current (%llu %u %llu) next (%llu %u %llu)", - key.objectid, key.type, key.offset, - next_key.objectid, next_key.type, - next_key.offset); + "bad key order, current " BTRFS_KEY_FMT " next " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(&key), + BTRFS_KEY_FMT_VALUE(&next_key)); return BTRFS_TREE_BLOCK_BAD_KEY_ORDER; } } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c45c5112c0350..4fd9a417fc5f7 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -199,9 +199,9 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function, if (wc->log_leaf) { btrfs_crit(fs_info, - "log tree (for root %llu) leaf currently being processed (slot %d key %llu %u %llu):", +"log tree (for root %llu) leaf currently being processed (slot %d key " BTRFS_KEY_FMT "):", btrfs_root_id(wc->root), wc->log_slot, - wc->log_key.objectid, wc->log_key.type, wc->log_key.offset); + BTRFS_KEY_FMT_VALUE(&wc->log_key)); btrfs_print_leaf(wc->log_leaf); } @@ -511,9 +511,9 @@ static int overwrite_item(struct walk_control *wc) ret = btrfs_search_slot(NULL, root, &wc->log_key, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, - "failed to search subvolume tree for key (%llu %u %llu) root %llu", - wc->log_key.objectid, wc->log_key.type, - wc->log_key.offset, btrfs_root_id(root)); + "failed to search subvolume tree for key " BTRFS_KEY_FMT " root %llu", + BTRFS_KEY_FMT_VALUE(&wc->log_key), + btrfs_root_id(root)); return ret; } @@ -619,9 +619,8 @@ static int overwrite_item(struct walk_control *wc) btrfs_extend_item(trans, wc->subvol_path, item_size - found_size); } else if (ret) { btrfs_abort_log_replay(wc, ret, - "failed to insert item for key (%llu %u %llu)", - wc->log_key.objectid, wc->log_key.type, - wc->log_key.offset); + "failed to insert item for key " BTRFS_KEY_FMT, + BTRFS_KEY_FMT_VALUE(&wc->log_key)); return ret; } dst_ptr = btrfs_item_ptr_offset(dst_eb, dst_slot); @@ -830,9 +829,9 @@ static noinline int replay_one_extent(struct walk_control *wc) &wc->log_key, sizeof(*item)); if (ret) { btrfs_abort_log_replay(wc, ret, - "failed to insert item with key (%llu %u %llu) root %llu", - wc->log_key.objectid, wc->log_key.type, - wc->log_key.offset, btrfs_root_id(root)); + "failed to insert item with key " BTRFS_KEY_FMT " root %llu", + BTRFS_KEY_FMT_VALUE(&wc->log_key), + btrfs_root_id(root)); goto out; } dest_offset = btrfs_item_ptr_offset(wc->subvol_path->nodes[0], @@ -1349,9 +1348,9 @@ static inline int __add_inode_ref(struct walk_control *wc, ret = btrfs_search_slot(NULL, root, &search_key, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, - "failed to search subvolume tree for key (%llu %u %llu) root %llu", - search_key.objectid, search_key.type, - search_key.offset, btrfs_root_id(root)); + "failed to search subvolume tree for key " BTRFS_KEY_FMT " root %llu", + BTRFS_KEY_FMT_VALUE(&search_key), + btrfs_root_id(root)); return ret; } else if (ret == 0) { /* @@ -1484,9 +1483,9 @@ static int unlink_old_inode_refs(struct walk_control *wc, struct btrfs_inode *in } if (ret < 0) { btrfs_abort_log_replay(wc, ret, - "failed to search subvolume tree for key (%llu %u %llu) root %llu", - wc->log_key.objectid, wc->log_key.type, - wc->log_key.offset, btrfs_root_id(root)); + "failed to search subvolume tree for key " BTRFS_KEY_FMT " root %llu", + BTRFS_KEY_FMT_VALUE(&wc->log_key), + btrfs_root_id(root)); goto out; } @@ -2701,10 +2700,9 @@ static noinline int replay_dir_deletes(struct walk_control *wc, wc->subvol_path, 0, 0); if (ret < 0) { btrfs_abort_log_replay(wc, ret, - "failed to search root %llu for key (%llu %u %llu)", + "failed to search root %llu for key " BTRFS_KEY_FMT, btrfs_root_id(root), - dir_key.objectid, dir_key.type, - dir_key.offset); + BTRFS_KEY_FMT_VALUE(&dir_key)); goto out; } From 76ad957a72c713d48a4232bb56d6e19477d32094 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 18 Nov 2025 17:08:43 +0100 Subject: [PATCH 1437/1518] btrfs: don't search back for dir inode item in INO_LOOKUP_USER [ Upstream commit 70085399b1a1623ef488d96b4c2d0c67be1d0607 ] We don't need to search back to the inode item, the directory inode number is in key.offset, so simply use that. If we can't find the directory we'll get an ENOENT at the iget(). Note: The patch was taken from v5 of fscrypt patchset (https://lore.kernel.org/linux-btrfs/cover.1706116485.git.josef@toxicpanda.com/) which was handled over time by various people: Omar Sandoval, Sweet Tea Dorminy, Josef Bacik. Reviewed-by: Johannes Thumshirn Signed-off-by: Josef Bacik Signed-off-by: Daniel Vacek Reviewed-by: David Sterba [ add note ] Signed-off-by: David Sterba Stable-dep-of: 1e92637722ae ("btrfs: check for subvolume before deleting squota qgroup") Signed-off-by: Sasha Levin --- fs/btrfs/ioctl.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c0691e93e0a58..41e549d37aac8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1832,7 +1832,7 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, struct btrfs_root_ref *rref; struct btrfs_root *root = NULL; struct btrfs_path *path; - struct btrfs_key key, key2; + struct btrfs_key key; struct extent_buffer *leaf; char *ptr; int slot; @@ -1887,24 +1887,6 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, read_extent_buffer(leaf, ptr, (unsigned long)(iref + 1), len); - /* Check the read+exec permission of this directory */ - ret = btrfs_previous_item(root, path, dirid, - BTRFS_INODE_ITEM_KEY); - if (ret < 0) { - goto out_put; - } else if (ret > 0) { - ret = -ENOENT; - goto out_put; - } - - leaf = path->nodes[0]; - slot = path->slots[0]; - btrfs_item_key_to_cpu(leaf, &key2, slot); - if (key2.objectid != dirid) { - ret = -ENOENT; - goto out_put; - } - /* * We don't need the path anymore, so release it and * avoid deadlocks and lockdep warnings in case @@ -1912,11 +1894,12 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, * btree and lock the same leaf. */ btrfs_release_path(path); - temp_inode = btrfs_iget(key2.objectid, root); + temp_inode = btrfs_iget(key.offset, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); goto out_put; } + /* Check the read+exec permission of this directory. */ ret = inode_permission(idmap, &temp_inode->vfs_inode, MAY_READ | MAY_EXEC); iput(&temp_inode->vfs_inode); From a1296bb9f44a446ba3f8e06a7cec575979e988a4 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 18 Nov 2025 17:06:46 +0100 Subject: [PATCH 1438/1518] btrfs: remaining BTRFS_PATH_AUTO_FREE conversions [ Upstream commit 10934c131f9bcfb616dd8be9456f11efd6b240ec ] Do the remaining btrfs_path conversion to the auto cleaning, this seems to be the last one. Most of the conversions are trivial, only adding the declaration and removing the freeing, or changing the goto patterns to return. There are some functions with many changes, like __btrfs_free_extent(), btrfs_remove_from_free_space_tree() or btrfs_add_to_free_space_tree() but it still follows the same pattern. Signed-off-by: David Sterba Stable-dep-of: 1e92637722ae ("btrfs: check for subvolume before deleting squota qgroup") Signed-off-by: Sasha Levin --- fs/btrfs/block-group.c | 3 +- fs/btrfs/dir-item.c | 3 +- fs/btrfs/extent-tree.c | 41 +++++------ fs/btrfs/free-space-tree.c | 29 ++++---- fs/btrfs/inode-item.c | 3 +- fs/btrfs/inode.c | 3 +- fs/btrfs/ioctl.c | 37 ++++------ fs/btrfs/qgroup.c | 142 ++++++++++++++----------------------- fs/btrfs/super.c | 10 +-- fs/btrfs/tree-log.c | 4 +- fs/btrfs/volumes.c | 3 +- fs/btrfs/xattr.c | 3 +- 12 files changed, 105 insertions(+), 176 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index a277c8cc91661..1e57f7d04c47e 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1065,7 +1065,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_chunk_map *map) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_block_group *block_group; struct btrfs_free_cluster *cluster; struct inode *inode; @@ -1305,7 +1305,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, btrfs_put_block_group(block_group); if (remove_rsv) btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); - btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 77e1bcb2a74bf..085a83ae9e62f 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -112,7 +112,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, int ret = 0; int ret2 = 0; struct btrfs_root *root = dir->root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_dir_item *dir_item; struct extent_buffer *leaf; unsigned long name_ptr; @@ -164,7 +164,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, ret2 = btrfs_insert_delayed_dir_index(trans, name->name, name->len, dir, &disk_key, type, index); out_free: - btrfs_free_path(path); if (ret) return ret; if (ret2) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e40835fe4bde6..663526d909ab1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3084,7 +3084,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_key key; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_root *extent_root; struct extent_buffer *leaf; struct btrfs_extent_item *ei; @@ -3119,7 +3119,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, node->bytenr, refs_to_drop); ret = -EINVAL; btrfs_abort_transaction(trans, ret); - goto out; + return ret; } if (is_data) @@ -3164,15 +3164,14 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, abort_and_dump(trans, path, "invalid iref slot %u, no EXTENT/METADATA_ITEM found but has inline extent ref", path->slots[0]); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } /* Must be SHARED_* item, remove the backref first */ ret = remove_extent_backref(trans, extent_root, path, NULL, refs_to_drop, is_data); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } btrfs_release_path(path); @@ -3221,7 +3220,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, } if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } extent_slot = path->slots[0]; } @@ -3230,10 +3229,10 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu slot %d", bytenr, node->parent, node->ref_root, owner_objectid, owner_offset, path->slots[0]); - goto out; + return ret; } else { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } leaf = path->nodes[0]; @@ -3244,7 +3243,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, "unexpected extent item size, has %u expect >= %zu", item_size, sizeof(*ei)); btrfs_abort_transaction(trans, ret); - goto out; + return ret; } ei = btrfs_item_ptr(leaf, extent_slot, struct btrfs_extent_item); @@ -3258,8 +3257,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, key.objectid, key.type, key.offset, path->slots[0], owner_objectid, item_size, sizeof(*ei) + sizeof(*bi)); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } bi = (struct btrfs_tree_block_info *)(ei + 1); WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi)); @@ -3270,8 +3268,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, abort_and_dump(trans, path, "trying to drop %d refs but we only have %llu for bytenr %llu slot %u", refs_to_drop, refs, bytenr, path->slots[0]); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } refs -= refs_to_drop; @@ -3287,8 +3284,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, abort_and_dump(trans, path, "invalid iref, got inlined extent ref but no EXTENT/METADATA_ITEM found, slot %u", path->slots[0]); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } } else { btrfs_set_extent_refs(leaf, ei, refs); @@ -3298,7 +3294,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, iref, refs_to_drop, is_data); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } } } else { @@ -3318,8 +3314,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, "invalid refs_to_drop, current refs %u refs_to_drop %u slot %u", extent_data_ref_count(path, iref), refs_to_drop, path->slots[0]); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } if (iref) { if (unlikely(path->slots[0] != extent_slot)) { @@ -3327,8 +3322,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, "invalid iref, extent item key " BTRFS_KEY_FMT " slot %u doesn't have wanted iref", BTRFS_KEY_FMT_VALUE(&key), path->slots[0]); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } } else { /* @@ -3341,8 +3335,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, abort_and_dump(trans, path, "invalid SHARED_* item slot %u, previous item is not EXTENT/METADATA_ITEM", path->slots[0]); - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } path->slots[0] = extent_slot; num_to_del = 2; @@ -3363,7 +3356,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, num_to_del); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } btrfs_release_path(path); @@ -3371,8 +3364,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, } btrfs_release_path(path); -out: - btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index d86541073d42d..c3734892d6548 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -841,7 +841,7 @@ int btrfs_remove_from_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { struct btrfs_block_group *block_group; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) @@ -851,7 +851,7 @@ int btrfs_remove_from_free_space_tree(struct btrfs_trans_handle *trans, if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); - goto out; + return ret; } block_group = btrfs_lookup_block_group(trans->fs_info, start); @@ -859,7 +859,7 @@ int btrfs_remove_from_free_space_tree(struct btrfs_trans_handle *trans, DEBUG_WARN("no block group found for start=%llu", start); ret = -ENOENT; btrfs_abort_transaction(trans, ret); - goto out; + return ret; } mutex_lock(&block_group->free_space_lock); @@ -869,8 +869,7 @@ int btrfs_remove_from_free_space_tree(struct btrfs_trans_handle *trans, btrfs_abort_transaction(trans, ret); btrfs_put_block_group(block_group); -out: - btrfs_free_path(path); + return ret; } @@ -1023,7 +1022,7 @@ int btrfs_add_to_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { struct btrfs_block_group *block_group; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) @@ -1033,7 +1032,7 @@ int btrfs_add_to_free_space_tree(struct btrfs_trans_handle *trans, if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); - goto out; + return ret; } block_group = btrfs_lookup_block_group(trans->fs_info, start); @@ -1041,7 +1040,7 @@ int btrfs_add_to_free_space_tree(struct btrfs_trans_handle *trans, DEBUG_WARN("no block group found for start=%llu", start); ret = -ENOENT; btrfs_abort_transaction(trans, ret); - goto out; + return ret; } mutex_lock(&block_group->free_space_lock); @@ -1051,8 +1050,7 @@ int btrfs_add_to_free_space_tree(struct btrfs_trans_handle *trans, btrfs_abort_transaction(trans, ret); btrfs_put_block_group(block_group); -out: - btrfs_free_path(path); + return ret; } @@ -1466,7 +1464,7 @@ int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_root *root = btrfs_free_space_root(block_group); - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key, found_key; struct extent_buffer *leaf; u64 start, end; @@ -1485,7 +1483,7 @@ int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans, if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); - goto out; + return ret; } start = block_group->start; @@ -1499,7 +1497,7 @@ int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans, ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } leaf = path->nodes[0]; @@ -1530,14 +1528,13 @@ int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans, ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); - goto out; + return ret; } btrfs_release_path(path); } ret = 0; -out: - btrfs_free_path(path); + return ret; } diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 1bd73b80f9fac..7e14e1bbcf389 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -444,7 +444,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_truncate_control *control) { struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; struct btrfs_key key; @@ -730,6 +730,5 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, if (!ret && control->last_size > new_size) control->last_size = new_size; - btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dcc0e53782c61..a4f1810db079d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4448,7 +4448,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, { struct btrfs_root *root = dir->root; struct btrfs_inode *inode = BTRFS_I(d_inode(dentry)); - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key key; @@ -4541,7 +4541,6 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, if (ret) btrfs_abort_transaction(trans, ret); out: - btrfs_free_path(path); fscrypt_free_filename(&fname); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 41e549d37aac8..2f1c5f5e2e725 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1613,7 +1613,7 @@ static noinline int search_ioctl(struct btrfs_root *root, { struct btrfs_fs_info *info = root->fs_info; struct btrfs_key key; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); int ret; int num_found = 0; unsigned long sk_offset = 0; @@ -1633,10 +1633,8 @@ static noinline int search_ioctl(struct btrfs_root *root, } else { /* Look up the root from the arguments. */ root = btrfs_get_fs_root(info, sk->tree_id, true); - if (IS_ERR(root)) { - btrfs_free_path(path); + if (IS_ERR(root)) return PTR_ERR(root); - } } key.objectid = sk->min_objectid; @@ -1670,7 +1668,6 @@ static noinline int search_ioctl(struct btrfs_root *root, sk->nr_items = num_found; btrfs_put_root(root); - btrfs_free_path(path); return ret; } @@ -1753,7 +1750,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, int total_len = 0; struct btrfs_inode_ref *iref; struct extent_buffer *l; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); if (dirid == BTRFS_FIRST_FREE_OBJECTID) { name[0]='\0'; @@ -1814,7 +1811,6 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, ret = 0; out: btrfs_put_root(root); - btrfs_free_path(path); return ret; } @@ -1831,7 +1827,7 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, struct btrfs_inode_ref *iref; struct btrfs_root_ref *rref; struct btrfs_root *root = NULL; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct extent_buffer *leaf; char *ptr; @@ -1852,10 +1848,8 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, ptr = &args->path[BTRFS_INO_LOOKUP_USER_PATH_MAX - 1]; root = btrfs_get_fs_root(fs_info, treeid, true); - if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; - } + if (IS_ERR(root)) + return PTR_ERR(root); key.objectid = dirid; key.type = BTRFS_INODE_REF_KEY; @@ -1930,12 +1924,10 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, key.type = BTRFS_ROOT_REF_KEY; key.offset = args->treeid; ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); - if (ret < 0) { - goto out; - } else if (ret > 0) { - ret = -ENOENT; - goto out; - } + if (ret < 0) + return ret; + else if (ret > 0) + return -ENOENT; leaf = path->nodes[0]; slot = path->slots[0]; @@ -1945,10 +1937,8 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, item_len = btrfs_item_size(leaf, slot); /* Check if dirid in ROOT_REF corresponds to passed dirid */ rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref); - if (args->dirid != btrfs_root_ref_dirid(leaf, rref)) { - ret = -EINVAL; - goto out; - } + if (args->dirid != btrfs_root_ref_dirid(leaf, rref)) + return -EINVAL; /* Copy subvolume's name */ item_off += sizeof(struct btrfs_root_ref); @@ -1958,8 +1948,7 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, out_put: btrfs_put_root(root); -out: - btrfs_free_path(path); + return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1f83af14568ca..7b62d2faaf7ec 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -660,7 +660,7 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, { int ret; struct btrfs_root *quota_root = trans->fs_info->quota_root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; path = btrfs_alloc_path(); @@ -672,7 +672,6 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, key.offset = dst; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, 0); - btrfs_free_path(path); return ret; } @@ -681,7 +680,7 @@ static int del_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, { int ret; struct btrfs_root *quota_root = trans->fs_info->quota_root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; path = btrfs_alloc_path(); @@ -694,24 +693,19 @@ static int del_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, ret = btrfs_search_slot(trans, quota_root, &key, path, -1, 1); if (ret < 0) - goto out; + return ret; - if (ret > 0) { - ret = -ENOENT; - goto out; - } + if (ret > 0) + return -ENOENT; - ret = btrfs_del_item(trans, quota_root, path); -out: - btrfs_free_path(path); - return ret; + return btrfs_del_item(trans, quota_root, path); } static int add_qgroup_item(struct btrfs_trans_handle *trans, struct btrfs_root *quota_root, u64 qgroupid) { int ret; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_qgroup_info_item *qgroup_info; struct btrfs_qgroup_limit_item *qgroup_limit; struct extent_buffer *leaf; @@ -737,7 +731,7 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*qgroup_info)); if (ret && ret != -EEXIST) - goto out; + return ret; leaf = path->nodes[0]; qgroup_info = btrfs_item_ptr(leaf, path->slots[0], @@ -754,7 +748,7 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*qgroup_limit)); if (ret && ret != -EEXIST) - goto out; + return ret; leaf = path->nodes[0]; qgroup_limit = btrfs_item_ptr(leaf, path->slots[0], @@ -765,17 +759,14 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_rsv_rfer(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_rsv_excl(leaf, qgroup_limit, 0); - ret = 0; -out: - btrfs_free_path(path); - return ret; + return 0; } static int del_qgroup_item(struct btrfs_trans_handle *trans, u64 qgroupid) { int ret; struct btrfs_root *quota_root = trans->fs_info->quota_root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; path = btrfs_alloc_path(); @@ -787,33 +778,27 @@ static int del_qgroup_item(struct btrfs_trans_handle *trans, u64 qgroupid) key.offset = qgroupid; ret = btrfs_search_slot(trans, quota_root, &key, path, -1, 1); if (ret < 0) - goto out; + return ret; - if (ret > 0) { - ret = -ENOENT; - goto out; - } + if (ret > 0) + return -ENOENT; ret = btrfs_del_item(trans, quota_root, path); if (ret) - goto out; + return ret; btrfs_release_path(path); key.type = BTRFS_QGROUP_LIMIT_KEY; ret = btrfs_search_slot(trans, quota_root, &key, path, -1, 1); if (ret < 0) - goto out; + return ret; - if (ret > 0) { - ret = -ENOENT; - goto out; - } + if (ret > 0) + return -ENOENT; ret = btrfs_del_item(trans, quota_root, path); -out: - btrfs_free_path(path); return ret; } @@ -821,7 +806,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, struct btrfs_qgroup *qgroup) { struct btrfs_root *quota_root = trans->fs_info->quota_root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct extent_buffer *l; struct btrfs_qgroup_limit_item *qgroup_limit; @@ -841,7 +826,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, ret = -ENOENT; if (ret) - goto out; + return ret; l = path->nodes[0]; slot = path->slots[0]; @@ -851,8 +836,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, qgroup->max_excl); btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, qgroup->rsv_rfer); btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, qgroup->rsv_excl); -out: - btrfs_free_path(path); + return ret; } @@ -861,7 +845,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *quota_root = fs_info->quota_root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct extent_buffer *l; struct btrfs_qgroup_info_item *qgroup_info; @@ -884,7 +868,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans, ret = -ENOENT; if (ret) - goto out; + return ret; l = path->nodes[0]; slot = path->slots[0]; @@ -894,8 +878,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_rfer_cmpr(l, qgroup_info, qgroup->rfer_cmpr); btrfs_set_qgroup_info_excl(l, qgroup_info, qgroup->excl); btrfs_set_qgroup_info_excl_cmpr(l, qgroup_info, qgroup->excl_cmpr); -out: - btrfs_free_path(path); + return ret; } @@ -903,7 +886,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *quota_root = fs_info->quota_root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct extent_buffer *l; struct btrfs_qgroup_status_item *ptr; @@ -923,7 +906,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) ret = -ENOENT; if (ret) - goto out; + return ret; l = path->nodes[0]; slot = path->slots[0]; @@ -933,8 +916,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) btrfs_set_qgroup_status_generation(l, ptr, trans->transid); btrfs_set_qgroup_status_rescan(l, ptr, fs_info->qgroup_rescan_progress.objectid); -out: - btrfs_free_path(path); + return ret; } @@ -944,7 +926,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root) { - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct extent_buffer *leaf = NULL; int ret; @@ -961,7 +943,7 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, while (1) { ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) - goto out; + return ret; leaf = path->nodes[0]; nr = btrfs_header_nritems(leaf); if (!nr) @@ -974,14 +956,12 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, path->slots[0] = 0; ret = btrfs_del_items(trans, root, path, 0, nr); if (ret) - goto out; + return ret; btrfs_release_path(path); } - ret = 0; -out: - btrfs_free_path(path); - return ret; + + return 0; } int btrfs_quota_enable(struct btrfs_fs_info *fs_info, @@ -1712,8 +1692,7 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) { struct btrfs_key key; - struct btrfs_path *path; - int ret; + BTRFS_PATH_AUTO_FREE(path); /* * Squota would never be inconsistent, but there can still be case @@ -1746,13 +1725,11 @@ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup if (!path) return -ENOMEM; - ret = btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL); - btrfs_free_path(path); /* * The @ret from btrfs_find_root() exactly matches our definition for * the return value, thus can be returned directly. */ - return ret; + return btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL); } int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) @@ -2301,7 +2278,7 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, bool trace_leaf) { struct btrfs_key key; - struct btrfs_path *src_path; + BTRFS_PATH_AUTO_FREE(src_path); struct btrfs_fs_info *fs_info = trans->fs_info; u32 nodesize = fs_info->nodesize; int cur_level = root_level; @@ -2313,10 +2290,8 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, return -EINVAL; src_path = btrfs_alloc_path(); - if (!src_path) { - ret = -ENOMEM; - goto out; - } + if (!src_path) + return -ENOMEM; if (dst_level) btrfs_node_key_to_cpu(dst_path->nodes[dst_level], &key, 0); @@ -2342,10 +2317,8 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, parent_slot = src_path->slots[cur_level + 1]; eb = btrfs_read_node_slot(eb, parent_slot); - if (IS_ERR(eb)) { - ret = PTR_ERR(eb); - goto out; - } + if (IS_ERR(eb)) + return PTR_ERR(eb); src_path->nodes[cur_level] = eb; @@ -2366,10 +2339,8 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, &src_key, src_path->slots[cur_level]); } /* Content mismatch, something went wrong */ - if (btrfs_comp_cpu_keys(&dst_key, &src_key)) { - ret = -ENOENT; - goto out; - } + if (btrfs_comp_cpu_keys(&dst_key, &src_key)) + return -ENOENT; cur_level--; } @@ -2380,21 +2351,20 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, ret = btrfs_qgroup_trace_extent(trans, src_path->nodes[dst_level]->start, nodesize); if (ret < 0) - goto out; + return ret; ret = btrfs_qgroup_trace_extent(trans, dst_path->nodes[dst_level]->start, nodesize); if (ret < 0) - goto out; + return ret; /* Record leaf file extents */ if (dst_level == 0 && trace_leaf) { ret = btrfs_qgroup_trace_leaf_items(trans, src_path->nodes[0]); if (ret < 0) - goto out; + return ret; ret = btrfs_qgroup_trace_leaf_items(trans, dst_path->nodes[0]); } -out: - btrfs_free_path(src_path); + return ret; } @@ -2595,7 +2565,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, int level; u8 drop_subptree_thres; struct extent_buffer *eb = root_eb; - struct btrfs_path *path = NULL; + BTRFS_PATH_AUTO_FREE(path); ASSERT(0 <= root_level && root_level < BTRFS_MAX_LEVEL); ASSERT(root_eb != NULL); @@ -2628,12 +2598,12 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, ret = btrfs_read_extent_buffer(root_eb, &check); if (ret) - goto out; + return ret; } if (root_level == 0) { ret = btrfs_qgroup_trace_leaf_items(trans, root_eb); - goto out; + return ret; } path = btrfs_alloc_path(); @@ -2669,10 +2639,8 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, child_bytenr = btrfs_node_blockptr(eb, parent_slot); eb = btrfs_read_node_slot(eb, parent_slot); - if (IS_ERR(eb)) { - ret = PTR_ERR(eb); - goto out; - } + if (IS_ERR(eb)) + return PTR_ERR(eb); path->nodes[level] = eb; path->slots[level] = 0; @@ -2683,14 +2651,14 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, ret = btrfs_qgroup_trace_extent(trans, child_bytenr, fs_info->nodesize); if (ret) - goto out; + return ret; } if (level == 0) { ret = btrfs_qgroup_trace_leaf_items(trans, path->nodes[level]); if (ret) - goto out; + return ret; /* Nonzero return here means we completed our search */ ret = adjust_slots_upwards(path, root_level); @@ -2704,11 +2672,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, level--; } - ret = 0; -out: - btrfs_free_path(path); - - return ret; + return 0; } static void qgroup_iterator_nested_add(struct list_head *head, struct btrfs_qgroup *qgroup) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c40944ca7b948..f1bfe97beacf1 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -805,17 +805,15 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, struct btrfs_root_ref *root_ref; struct btrfs_inode_ref *inode_ref; struct btrfs_key key; - struct btrfs_path *path = NULL; + BTRFS_PATH_AUTO_FREE(path); char *name = NULL, *ptr; u64 dirid; int len; int ret; path = btrfs_alloc_path(); - if (!path) { - ret = -ENOMEM; - goto err; - } + if (!path) + return ERR_PTR(-ENOMEM); name = kmalloc(PATH_MAX, GFP_KERNEL); if (!name) { @@ -903,7 +901,6 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, fs_root = NULL; } - btrfs_free_path(path); if (ptr == name + PATH_MAX - 1) { name[0] = '/'; name[1] = '\0'; @@ -914,7 +911,6 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, err: btrfs_put_root(fs_root); - btrfs_free_path(path); kfree(name); return ERR_PTR(ret); } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 4fd9a417fc5f7..a0e12b4fb9561 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2647,7 +2647,7 @@ static noinline int replay_dir_deletes(struct walk_control *wc, int ret = 0; struct btrfs_key dir_key; struct btrfs_key found_key; - struct btrfs_path *log_path; + BTRFS_PATH_AUTO_FREE(log_path); struct btrfs_inode *dir; dir_key.objectid = dirid; @@ -2664,7 +2664,6 @@ static noinline int replay_dir_deletes(struct walk_control *wc, * we replay the deletes before we copy in the inode item from the log. */ if (IS_ERR(dir)) { - btrfs_free_path(log_path); ret = PTR_ERR(dir); if (ret == -ENOENT) ret = 0; @@ -2744,7 +2743,6 @@ static noinline int replay_dir_deletes(struct walk_control *wc, ret = 0; out: btrfs_release_path(wc->subvol_path); - btrfs_free_path(log_path); iput(&dir->vfs_inode); return ret; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ef9f24076ccae..630fb5885692b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4205,7 +4205,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) struct btrfs_root *chunk_root = fs_info->chunk_root; u64 chunk_type; struct btrfs_chunk *chunk; - struct btrfs_path *path = NULL; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct btrfs_key found_key; struct extent_buffer *leaf; @@ -4382,7 +4382,6 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) goto again; } error: - btrfs_free_path(path); if (enospc_errors) { btrfs_info(fs_info, "%d enospc errors during balance", enospc_errors); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 79fb1614bd0c3..b6f01d6c79e7f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -85,7 +85,7 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, { struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); size_t name_len = strlen(name); int ret = 0; @@ -212,7 +212,6 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, */ } out: - btrfs_free_path(path); if (!ret) { set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); From 22d558df51d90e62894b1b7320857ad47dc23d6b Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 1 Dec 2025 15:33:49 -0800 Subject: [PATCH 1439/1518] btrfs: check squota parent usage on membership change [ Upstream commit 9c46bcda5f347febdbb4d117fb21a37ffcec5fa4 ] We could have detected the quick inherit bug more directly if we had an extra warning about squota hierarchy consistency while modifying the hierarchy. In squotas, the parent usage always simply adds up to the sum of its children, so we can just check for that when changing membership and detect more accounting bugs. Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Signed-off-by: David Sterba Stable-dep-of: 1e92637722ae ("btrfs: check for subvolume before deleting squota qgroup") Signed-off-by: Sasha Levin --- fs/btrfs/qgroup.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 7b62d2faaf7ec..db1df67bccf38 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -346,6 +346,42 @@ int btrfs_verify_qgroup_counts(const struct btrfs_fs_info *fs_info, u64 qgroupid } #endif +static bool squota_check_parent_usage(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *parent) +{ + u64 excl_sum = 0; + u64 rfer_sum = 0; + u64 excl_cmpr_sum = 0; + u64 rfer_cmpr_sum = 0; + struct btrfs_qgroup_list *glist; + int nr_members = 0; + bool mismatch; + + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE) + return false; + if (btrfs_qgroup_level(parent->qgroupid) == 0) + return false; + + /* Eligible parent qgroup. Squota; level > 0; empty members list. */ + list_for_each_entry(glist, &parent->members, next_member) { + excl_sum += glist->member->excl; + rfer_sum += glist->member->rfer; + excl_cmpr_sum += glist->member->excl_cmpr; + rfer_cmpr_sum += glist->member->rfer_cmpr; + nr_members++; + } + mismatch = (parent->excl != excl_sum || parent->rfer != rfer_sum || + parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != excl_cmpr_sum); + + WARN(mismatch, + "parent squota qgroup %hu/%llu has mismatched usage from its %d members. " + "%llu %llu %llu %llu vs %llu %llu %llu %llu\n", + btrfs_qgroup_level(parent->qgroupid), + btrfs_qgroup_subvolid(parent->qgroupid), nr_members, parent->excl, + parent->rfer, parent->excl_cmpr, parent->rfer_cmpr, excl_sum, + rfer_sum, excl_cmpr_sum, rfer_cmpr_sum); + return mismatch; +} + __printf(2, 3) static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info, const char *fmt, ...) { @@ -1565,6 +1601,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst goto out; } ret = quick_update_accounting(fs_info, src, dst, 1); + squota_check_parent_usage(fs_info, parent); spin_unlock(&fs_info->qgroup_lock); out: kfree(prealloc); @@ -1623,6 +1660,8 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, spin_lock(&fs_info->qgroup_lock); del_relation_rb(fs_info, src, dst); ret = quick_update_accounting(fs_info, src, dst, -1); + ASSERT(parent); + squota_check_parent_usage(fs_info, parent); spin_unlock(&fs_info->qgroup_lock); } out: From b422609291f6158d0c12e8503124b1a3221d6d8d Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 1 Dec 2025 15:35:02 -0800 Subject: [PATCH 1440/1518] btrfs: relax squota parent qgroup deletion rule [ Upstream commit adb0af40fe89fd42f1ef277bf60d9cfa7c2ae472 ] Currently, with squotas, we do not allow removing a parent qgroup with no members if it still has usage accounted to it. This makes it really difficult to recover from accounting bugs, as we have no good way of getting back to 0 usage. Instead, allow deletion (it's safe at 0 members..) while still warning about the inconsistency by adding a squota parent check. Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Signed-off-by: David Sterba Stable-dep-of: 1e92637722ae ("btrfs: check for subvolume before deleting squota qgroup") Signed-off-by: Sasha Levin --- fs/btrfs/qgroup.c | 50 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 35 insertions(+), 15 deletions(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index db1df67bccf38..c7bc2065bcd68 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1723,6 +1723,36 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) return ret; } +static bool can_delete_parent_qgroup(struct btrfs_qgroup *qgroup) + +{ + ASSERT(btrfs_qgroup_level(qgroup->qgroupid)); + return list_empty(&qgroup->members); +} + +/* + * Return true if we can delete the squota qgroup and false otherwise. + * + * Rules for whether we can delete: + * + * A subvolume qgroup can be removed iff the subvolume is fully deleted, which + * is iff there is 0 usage in the qgroup. + * + * A higher level qgroup can be removed iff it has no members. + * Note: We audit its usage to warn on inconsitencies without blocking deletion. + */ +static bool can_delete_squota_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) +{ + ASSERT(btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE); + + if (btrfs_qgroup_level(qgroup->qgroupid) > 0) { + squota_check_parent_usage(fs_info, qgroup); + return can_delete_parent_qgroup(qgroup); + } + + return !(qgroup->rfer || qgroup->excl || qgroup->rfer_cmpr || qgroup->excl_cmpr); +} + /* * Return 0 if we can not delete the qgroup (not empty or has children etc). * Return >0 if we can delete the qgroup. @@ -1733,23 +1763,13 @@ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup struct btrfs_key key; BTRFS_PATH_AUTO_FREE(path); - /* - * Squota would never be inconsistent, but there can still be case - * where a dropped subvolume still has qgroup numbers, and squota - * relies on such qgroup for future accounting. - * - * So for squota, do not allow dropping any non-zero qgroup. - */ - if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && - (qgroup->rfer || qgroup->excl || qgroup->excl_cmpr || qgroup->rfer_cmpr)) - return 0; + /* Since squotas cannot be inconsistent, they have special rules for deletion. */ + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + return can_delete_squota_qgroup(fs_info, qgroup); /* For higher level qgroup, we can only delete it if it has no child. */ - if (btrfs_qgroup_level(qgroup->qgroupid)) { - if (!list_empty(&qgroup->members)) - return 0; - return 1; - } + if (btrfs_qgroup_level(qgroup->qgroupid)) + return can_delete_parent_qgroup(qgroup); /* * For level-0 qgroups, we can only delete it if it has no subvolume From ca56ffdb017b33e68c69d1b59428b7466f5a4a13 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 11 May 2026 13:07:11 -0700 Subject: [PATCH 1441/1518] btrfs: check for subvolume before deleting squota qgroup [ Upstream commit 1e92637722ae4bd417f7a37e8d1485dc23b93935 ] The invariant that we want to maintain with subvolume qgroups is that the qgroup can only be deleted if there is no root. With squotas, we thought that it was sufficient to just check the usage, because we assumed that deleting a subvolume will drive it's qgroups usage to 0, and thus 0 usage implies no subvolume. However, this is false, for two reasons: - A subvol whose extents are all from before squotas was enabled. - A subvol that was created in this transaction and for which we have not yet run any delayed refs. In both cases, deleting the qgroup breaks the desired invariant and we are left with a subvolume with no qgroup but squotas are enabled. Fix this by unifying the deletion check logic between full qgroups and squotas. Squotas do all the same checks *and* the additional usage == 0 check, which is the one extra rule peculiar to squotas. Link: https://lore.kernel.org/linux-btrfs/adnBhWfJQ1n3hZC8@merlins.org/ Fixes: a8df35619948 ("btrfs: forbid deleting live subvol qgroup") Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/qgroup.c | 50 +++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c7bc2065bcd68..a0d364e009d88 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1723,32 +1723,24 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) return ret; } -static bool can_delete_parent_qgroup(struct btrfs_qgroup *qgroup) - +static bool can_delete_parent_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) { ASSERT(btrfs_qgroup_level(qgroup->qgroupid)); + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + squota_check_parent_usage(fs_info, qgroup); return list_empty(&qgroup->members); } /* - * Return true if we can delete the squota qgroup and false otherwise. - * - * Rules for whether we can delete: - * - * A subvolume qgroup can be removed iff the subvolume is fully deleted, which - * is iff there is 0 usage in the qgroup. - * - * A higher level qgroup can be removed iff it has no members. - * Note: We audit its usage to warn on inconsitencies without blocking deletion. + * Because a shared extent can outlive its owning subvolume, we cannot delete a + * subvol squota qgroup until all of the extents it owns are gone, even if the + * subvolume itself has been deleted. */ -static bool can_delete_squota_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) +static bool can_delete_squota_subvol_qgroup(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup) { ASSERT(btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE); - - if (btrfs_qgroup_level(qgroup->qgroupid) > 0) { - squota_check_parent_usage(fs_info, qgroup); - return can_delete_parent_qgroup(qgroup); - } + ASSERT(btrfs_qgroup_level(qgroup->qgroupid) == 0); return !(qgroup->rfer || qgroup->excl || qgroup->rfer_cmpr || qgroup->excl_cmpr); } @@ -1762,14 +1754,11 @@ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup { struct btrfs_key key; BTRFS_PATH_AUTO_FREE(path); - - /* Since squotas cannot be inconsistent, they have special rules for deletion. */ - if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) - return can_delete_squota_qgroup(fs_info, qgroup); + int ret; /* For higher level qgroup, we can only delete it if it has no child. */ if (btrfs_qgroup_level(qgroup->qgroupid)) - return can_delete_parent_qgroup(qgroup); + return can_delete_parent_qgroup(fs_info, qgroup); /* * For level-0 qgroups, we can only delete it if it has no subvolume @@ -1785,10 +1774,21 @@ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup return -ENOMEM; /* - * The @ret from btrfs_find_root() exactly matches our definition for - * the return value, thus can be returned directly. + * Any subvol qgroup, regardless of mode, cannot be deleted if the + * subvol still exists. + */ + ret = btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL); + /* + * btrfs_find_root returns <0 on error, 0 if found, and >0 if not, + * so the "found" and "error" cases match our desired return values. */ - return btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL); + if (ret <= 0) + return ret; + + /* Squotas require additional checks, even if the subvol is deleted. */ + if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) + return can_delete_squota_subvol_qgroup(fs_info, qgroup); + return 1; } int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) From 7e91d3a1a98a3748e079b24379873b0318d10178 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 11 May 2026 19:53:46 -0700 Subject: [PATCH 1442/1518] btrfs: fix squota accounting during enable generation [ Upstream commit d7c600554816b8ef70adffe078a0e360c055d82b ] The first transaction that enables squotas is special and a bit tricky. We have to set BTRFS_FS_QUOTA_ENABLED after the transaction to avoid a deadlock, so any delayed refs that run before we set the bit are not squota accounted. For data this is fine, we don't get an owner_ref, so there is no real harm, it's as if the extent predated squotas. However for metadata, the tree block will have gen == enable_gen so when we free it later, we will decrement the squota accounting, which can result in an underflow. Before it is freed, btrfs check shows errors, as we have mismatched usage between the node generations/owners and the squota values. There are two angles to this fix: 1. For extents that come in delayed_refs that run during the enable_gen transaction, we must actually set enable_gen to the *next* transaction. That is the first transaction that we can really properly account in any way. 2. For extents that come in between the end of our transaction handle and the time we set the BTRFS_FS_QUOTA_ENABLED bit, we need an additional bit, BTRFS_FS_SQUOTA_ENABLING which only affects recording squota deltas, so we do pick up those extents. Otherwise, we would miss them, even for enable_gen + 1. Fixes: bd7c1ea3a302 ("btrfs: qgroup: check generation when recording simple quota delta") Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/fs.h | 1 + fs/btrfs/qgroup.c | 31 +++++++++++++++++++++++++++---- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index acdb9e52f6fd7..eccc61463947b 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -136,6 +136,7 @@ enum { BTRFS_FS_LOG_RECOVERING, BTRFS_FS_OPEN, BTRFS_FS_QUOTA_ENABLED, + BTRFS_FS_SQUOTA_ENABLING, BTRFS_FS_UPDATE_UUID_TREE_GEN, BTRFS_FS_CREATING_FREE_SPACE_TREE, BTRFS_FS_BTREE_ERR, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a0d364e009d88..261aa65019207 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1111,7 +1111,13 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); - btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); + /* + * Set the enable generation to the next transaction, as we cannot + * ensure that extents written during this transaction will see any + * state we have set here. So we should treat all extents of the + * transaction as coming in before squotas was enabled. + */ + btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid + 1); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; } @@ -1214,7 +1220,15 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, goto out_free_path; } - fs_info->qgroup_enable_gen = trans->transid; + /* + * Set fs_info->qgroup_enable_gen and BTRFS_FS_SQUOTA_ENABLING + * under the transaction handle. We want to ensure that all extents in + * the next transaction definitely see them. + */ + if (simple) { + fs_info->qgroup_enable_gen = trans->transid + 1; + set_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags); + } mutex_unlock(&fs_info->qgroup_ioctl_lock); /* @@ -1228,9 +1242,15 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, */ ret = btrfs_commit_transaction(trans); trans = NULL; + mutex_lock(&fs_info->qgroup_ioctl_lock); - if (ret) + if (ret) { + if (simple) { + clear_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags); + fs_info->qgroup_enable_gen = 0; + } goto out_free_path; + } /* * Set quota enabled flag after committing the transaction, to avoid @@ -1240,6 +1260,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); + if (simple) + clear_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ @@ -4930,7 +4952,8 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, u64 num_bytes = delta->num_bytes; const int sign = (delta->is_inc ? 1 : -1); - if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE) + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE && + !test_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags)) return 0; if (!btrfs_is_fstree(root)) From fecfed41da734c006aff722ab67f1e6fe0c77eec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Mon, 11 May 2026 13:42:02 -0300 Subject: [PATCH 1443/1518] ASoC: amd: acp-sdw-legacy: check CPU DAI name before logging MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1afd8f06dcb1d561af3b239c5b14a88b87c13454 ] devm_kasprintf() can fail and return NULL. The legacy AMD SoundWire machine driver logs cpus->dai_name before checking the allocation result. Move the debug print after the NULL check, matching the ordering used by the SOF AMD SoundWire path after commit 5726b68473f7 ("ASoC: amd/sdw_utils: avoid NULL deref when devm_kasprintf() fails"). Fixes: 2981d9b0789c ("ASoC: amd: acp: add soundwire machine driver for legacy stack") Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260511-asoc-amd-acp-sdw-legacy-dai-name-null-v1-1-dc6151b6da8a@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/amd/acp/acp-sdw-legacy-mach.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c index 798c73d7e26de..e87d9e9991e1c 100644 --- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c +++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c @@ -244,9 +244,9 @@ static int create_sdw_dailink(struct snd_soc_card *card, cpus->dai_name = devm_kasprintf(dev, GFP_KERNEL, "SDW%d Pin%d", link_num, cpu_pin_id); - dev_dbg(dev, "cpu->dai_name:%s\n", cpus->dai_name); if (!cpus->dai_name) return -ENOMEM; + dev_dbg(dev, "cpu->dai_name:%s\n", cpus->dai_name); codec_maps[j].cpu = 0; codec_maps[j].codec = j; From 0fa225896f4b4cb24c519e1173e9e3347189bc23 Mon Sep 17 00:00:00 2001 From: Felix Gu Date: Sun, 10 May 2026 01:55:37 +0800 Subject: [PATCH 1444/1518] spi: mtk-snfi: Fix resource leak in mtk_snand_read_page_cache() [ Upstream commit 496ba79b9496b8b3747cbc764ebd33ee7325e806 ] When DMA read times out in mtk_snand_read_page_cache(), the original code erroneously jumped to cleanup label which skips DMA unmapping and ECC disable, causing a resource leak. Fixes: 764f1b748164 ("spi: add driver for MTK SPI NAND Flash Interface") Signed-off-by: Felix Gu Link: https://patch.msgid.link/20260510-snfi-v1-1-bc375cf1af8e@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-mtk-snfi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-mtk-snfi.c b/drivers/spi/spi-mtk-snfi.c index a026b0e61994b..9e6038a5a2ad0 100644 --- a/drivers/spi/spi-mtk-snfi.c +++ b/drivers/spi/spi-mtk-snfi.c @@ -961,7 +961,7 @@ static int mtk_snand_read_page_cache(struct mtk_snand *snf, &snf->op_done, usecs_to_jiffies(SNFI_POLL_INTERVAL))) { dev_err(snf->dev, "DMA timed out for reading from cache.\n"); ret = -ETIMEDOUT; - goto cleanup; + goto cleanup2; } // Wait for BUS_SEC_CNTR returning expected value From df19b6af171695a1352314597c9a4311d48d5171 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 12 May 2026 11:30:49 +0200 Subject: [PATCH 1445/1518] netfilter: nft_inner: release local_lock before re-enabling softirqs [ Upstream commit a6cb3ff979855f7f0ee9450a947fe8f96c2ba37a ] Quoting sashiko: In the error path, local_bh_enable() is called before local_unlock_nested_bh(). Fixes: ba36fada9ab4 ("netfilter: nft_inner: Use nested-BH locking for nft_pcpu_tun_ctx") Signed-off-by: Florian Westphal Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_inner.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 1b3e7a976f560..ad08a43535b55 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -246,8 +246,8 @@ static bool nft_inner_restore_tun_ctx(const struct nft_pktinfo *pkt, local_lock_nested_bh(&nft_pcpu_tun_ctx.bh_lock); this_cpu_tun_ctx = this_cpu_ptr(&nft_pcpu_tun_ctx.ctx); if (this_cpu_tun_ctx->cookie != (unsigned long)pkt->skb) { - local_bh_enable(); local_unlock_nested_bh(&nft_pcpu_tun_ctx.bh_lock); + local_bh_enable(); return false; } *tun_ctx = *this_cpu_tun_ctx; From 0c9e4d9484cc33a3e1425bb505145d80d1b09401 Mon Sep 17 00:00:00 2001 From: Eric Naim Date: Sat, 16 May 2026 19:15:31 +0800 Subject: [PATCH 1446/1518] ALSA: hda/realtek: Use ALC287_FIXUP_TXNW2781_I2C for ASUS Strix Gxx5 [ Upstream commit 4372286ac774536e8e68bc6dfa0f0b0152b31fce ] These devices were incorrectly using the ALC287_FIXUP_TAS2781_I2C quirk leading to errors: [ 18.765990] Serial bus multi instantiate pseudo device driver TXNW2781:00: error -ENXIO: IRQ index 0 not found [ 18.768153] Serial bus multi instantiate pseudo device driver TXNW2781:00: error -ENXIO: IRQ index 0 not found [ 18.768476] Serial bus multi instantiate pseudo device driver TXNW2781:00: error -ENXIO: IRQ index 0 not found [ 18.768899] Serial bus multi instantiate pseudo device driver TXNW2781:00: Instantiated 3 I2C devices. Use the ALC287_FIXUP_TXNW2781_I2C quirk instead to fix this and restore speaker audio on affected devices. Fixes: 1e9c708dc3ae ("ALSA: hda/tas2781: Add new quirk for Lenovo, ASUS, Dell projects") Link: https://lore.kernel.org/59fd4aa4-76b9-4984-8db9-a60e55ec6e80@losource.net/ Closes: https://lore.kernel.org/CACB9z7kjs8rhLstEc8fV29BCTb5dd881JwGozoKdO5cwCb=YwQ@mail.gmail.com Signed-off-by: Eric Naim Link: https://patch.msgid.link/20260516111532.111463-1-dnaim@cachyos.org Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/codecs/realtek/alc269.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index ea98cbc4310df..4cd5b719556ec 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7182,12 +7182,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x3e00, "ASUS G814FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x3e20, "ASUS G814PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x3e30, "ASUS TP3607SA", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1043, 0x3ee0, "ASUS Strix G815_JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1043, 0x3ef0, "ASUS Strix G635LR_LW_LX", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1043, 0x3f00, "ASUS Strix G815LH_LM_LP", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1043, 0x3f10, "ASUS Strix G835LR_LW_LX", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1043, 0x3f20, "ASUS Strix G615LR_LW", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1043, 0x3f30, "ASUS Strix G815LR_LW", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x1043, 0x3ee0, "ASUS Strix G815_JHR_JMR_JPR", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x1043, 0x3ef0, "ASUS Strix G635LR_LW_LX", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x1043, 0x3f00, "ASUS Strix G815LH_LM_LP", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x1043, 0x3f10, "ASUS Strix G835LR_LW_LX", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x1043, 0x3f20, "ASUS Strix G615LR_LW", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x1043, 0x3f30, "ASUS Strix G815LR_LW", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x1043, 0x3fd0, "ASUS B3605CVA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x3ff0, "ASUS B5405CVA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), From cdd1aaf0ee962f50810b9aef7928f2313989d55f Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 16 May 2026 14:53:45 +0300 Subject: [PATCH 1447/1518] drm/msm/snapshot: fix dumping of the unaligned regions [ Upstream commit 76824d2467feb1828b745d6add2541918d7be3da ] The snapshotting code internally aligns data segment to 16 bytes. This works fine for DPU code (where most of the regions are aligned), but fails for snapshotting of the DSI data (because DSI data region is shifted by 4 bytes). Fix the code by removing length alignment and by accurately printing last registers in the region. While reworking the code also fix the 16x memory overallocation in msm_disp_state_dump_regs(). Fixes: 98659487b845 ("drm/msm: add support to take dpu snapshot") Reported-by: Salendarsingh Gaud Signed-off-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/725449/ Message-ID: <20260516-msm-fix-dsi-dump-2-v2-1-9e49fb2d240e@oss.qualcomm.com> Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- .../gpu/drm/msm/disp/msm_disp_snapshot_util.c | 24 ++++++++++++++----- 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index 071bcdea80f71..591507db26468 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -9,7 +9,7 @@ #include "msm_disp_snapshot.h" -static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *base_addr) +static void msm_disp_state_dump_regs(u32 **reg, u32 len, void __iomem *base_addr) { u32 len_padded; u32 num_rows; @@ -19,11 +19,11 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b void __iomem *end_addr; int i; - len_padded = aligned_len * REG_DUMP_ALIGN; - num_rows = aligned_len / REG_DUMP_ALIGN; + len_padded = round_up(len, REG_DUMP_ALIGN); + num_rows = DIV_ROUND_UP(len, REG_DUMP_ALIGN); addr = base_addr; - end_addr = base_addr + aligned_len; + end_addr = base_addr + len; *reg = kvzalloc(len_padded, GFP_KERNEL); if (!*reg) @@ -48,8 +48,8 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, void __iomem *base_addr, struct drm_printer *p) { + void __iomem *addr, *end_addr; int i; - void __iomem *addr; u32 num_rows; if (!dump_addr) { @@ -58,6 +58,7 @@ static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, } addr = base_addr; + end_addr = base_addr + len; num_rows = len / REG_DUMP_ALIGN; for (i = 0; i < num_rows; i++) { @@ -67,6 +68,17 @@ static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, dump_addr[i * 4 + 2], dump_addr[i * 4 + 3]); addr += REG_DUMP_ALIGN; } + + if (addr != end_addr) { + drm_printf(p, "0x%lx : %08x", + (unsigned long)(addr - base_addr), + dump_addr[i * 4]); + if (addr + 0x4 < end_addr) + drm_printf(p, " %08x", dump_addr[i * 4 + 1]); + if (addr + 0x8 < end_addr) + drm_printf(p, " %08x", dump_addr[i * 4 + 2]); + drm_printf(p, "\n"); + } } void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p) @@ -186,7 +198,7 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len, va_end(va); INIT_LIST_HEAD(&new_blk->node); - new_blk->size = ALIGN(len, REG_DUMP_ALIGN); + new_blk->size = len; new_blk->base_addr = base_addr; msm_disp_state_dump_regs(&new_blk->state, new_blk->size, base_addr); From c98107817b0f6cdf51adc5e84e75c39ee25d8b28 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 14 May 2026 14:31:49 -0700 Subject: [PATCH 1448/1518] hwmon: (lm90) Stop work before releasing hwmon device [ Upstream commit b09a45601094c7f4ec4db8090b825fa61e169d93 ] Sashiko reports: In lm90_probe(), the devm action to cancel the alert_work and report_work (lm90_restore_conf) is registered in lm90_init_client() before devm_hwmon_device_register_with_info() is called. Because devm executes cleanup actions in reverse order during module unbind or probe failure, the hwmon device is unregistered and freed first. If lm90_alert_work() or lm90_report_alarms() runs in the window between the hwmon device being freed and the delayed works being cancelled, lm90_update_alarms() will dereference the freed data->hwmon_dev here. Fix the problem by canceling the workers separately after registering the hwmon device and before registering the interrupt handler. This ensures that the workers are canceled after interrupts are disabled and before the hwmon device is released. Add "shutdown" flag to indicate that device shutdown is in progress to prevent workers from being re-armed. Fixes: f6d0775119fb9 ("hwmon: (lm90) Rework alarm/status handling") Reported-by: Sashiko Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/lm90.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index c1f528e292f3d..41ee2309fe8a2 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -738,6 +738,7 @@ struct lm90_data { struct mutex update_lock; struct delayed_work alert_work; struct work_struct report_work; + bool shutdown; /* true if shutting down */ bool valid; /* true if register values are valid */ bool alarms_valid; /* true if status register values are valid */ unsigned long last_updated; /* in jiffies */ @@ -1156,6 +1157,9 @@ static void lm90_report_alarms(struct work_struct *work) static int lm90_update_alarms_locked(struct lm90_data *data, bool force) { + if (data->shutdown) + return 0; + if (force || !data->alarms_valid || time_after(jiffies, data->alarms_updated + msecs_to_jiffies(data->update_interval))) { struct i2c_client *client = data->client; @@ -2600,15 +2604,23 @@ static void lm90_restore_conf(void *_data) struct lm90_data *data = _data; struct i2c_client *client = data->client; - cancel_delayed_work_sync(&data->alert_work); - cancel_work_sync(&data->report_work); - /* Restore initial configuration */ if (data->flags & LM90_HAVE_CONVRATE) lm90_write_convrate(data, data->convrate_orig); lm90_write_reg(client, LM90_REG_CONFIG1, data->config_orig); } +static void lm90_stop_work(void *_data) +{ + struct lm90_data *data = _data; + + hwmon_lock(data->hwmon_dev); + data->shutdown = true; + hwmon_unlock(data->hwmon_dev); + cancel_delayed_work_sync(&data->alert_work); + cancel_work_sync(&data->report_work); +} + static int lm90_init_client(struct i2c_client *client, struct lm90_data *data) { struct device_node *np = client->dev.of_node; @@ -2919,6 +2931,10 @@ static int lm90_probe(struct i2c_client *client) data->hwmon_dev = hwmon_dev; + err = devm_add_action_or_reset(&client->dev, lm90_stop_work, data); + if (err) + return err; + if (client->irq) { dev_dbg(dev, "IRQ: %d\n", client->irq); err = devm_request_threaded_irq(dev, client->irq, @@ -2947,7 +2963,7 @@ static void lm90_alert(struct i2c_client *client, enum i2c_alert_protocol type, */ struct lm90_data *data = i2c_get_clientdata(client); - if ((data->flags & LM90_HAVE_BROKEN_ALERT) && + if (!data->shutdown && (data->flags & LM90_HAVE_BROKEN_ALERT) && (data->current_alarms & data->alert_alarms)) { if (!(data->config & 0x80)) { dev_dbg(&client->dev, "Disabling ALERT#\n"); From bed1fc32e0eb653806fa98afcf55f9a311fc4ce2 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 14 May 2026 14:41:00 -0700 Subject: [PATCH 1449/1518] hwmon: (lm90) Add lock protection to lm90_alert [ Upstream commit 873e919e3101063a7a75989510ccfc125a4391cf ] Sashiko reports: lm90_alert() executes in the smbus alert context and calls lm90_update_confreg() to disable the hardware alert line, without acquiring hwmon_lock. Concurrently, sysfs write operations (such as lm90_write_convrate) hold the hwmon_lock, temporarily modify data->config, and then restore it. If an alert interrupt occurs concurrently with a sysfs write, the sysfs path will overwrite the alert handler's modifications to data->config and the hardware register. This unintentionally re-enables the hardware alert line while the alarm is still active, causing an interrupt storm. Add the missing lock to lm90_alert() to solve the problem. Fixes: 7a1d220ccb0cc ("hwmon: (lm90) Introduce function to update configuration register") Reported-by: Sashiko Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/lm90.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index 41ee2309fe8a2..a465a8a7ef5af 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -2963,6 +2963,7 @@ static void lm90_alert(struct i2c_client *client, enum i2c_alert_protocol type, */ struct lm90_data *data = i2c_get_clientdata(client); + hwmon_lock(data->hwmon_dev); if (!data->shutdown && (data->flags & LM90_HAVE_BROKEN_ALERT) && (data->current_alarms & data->alert_alarms)) { if (!(data->config & 0x80)) { @@ -2972,6 +2973,7 @@ static void lm90_alert(struct i2c_client *client, enum i2c_alert_protocol type, schedule_delayed_work(&data->alert_work, max_t(int, HZ, msecs_to_jiffies(data->update_interval))); } + hwmon_unlock(data->hwmon_dev); } else { dev_dbg(&client->dev, "Everything OK\n"); } From 9e360e610a73f62432e986775023d5382773f045 Mon Sep 17 00:00:00 2001 From: Cole Leavitt Date: Sat, 4 Apr 2026 22:41:44 -0700 Subject: [PATCH 1450/1518] wifi: iwlwifi: mld: fix TSO segmentation explosion when AMSDU is disabled [ Upstream commit 92cee08dc4f00e77fd1317e4343c5d458b0abab7 ] When the TLC notification disables AMSDU for a TID, the MLD driver sets max_tid_amsdu_len to the sentinel value 1. The TSO segmentation path in iwl_mld_tx_tso_segment() checks for zero but not for this sentinel, allowing it to reach the num_subframes calculation: num_subframes = (max_tid_amsdu_len + pad) / (subf_len + pad) = (1 + 2) / (1534 + 2) = 0 This zero propagates to iwl_tx_tso_segment() which sets: gso_size = num_subframes * mss = 0 Calling skb_gso_segment() with gso_size=0 creates over 32000 tiny segments from a single GSO skb. This floods the TX ring with ~1024 micro-frames (the rest are purged), creating a massive burst of TX completion events that can lead to memory corruption and a subsequent use-after-free in TCP's retransmit queue (refcount underflow in tcp_shifted_skb, NULL deref in tcp_rack_detect_loss). The MVM driver is immune because it checks mvmsta->amsdu_enabled before reaching the num_subframes calculation. The MLD driver has no equivalent bitmap check and relies solely on max_tid_amsdu_len, which does not catch the sentinel value. Fix this by detecting the sentinel value (max_tid_amsdu_len == 1) at the existing check and falling back to non-AMSDU TSO segmentation. Also add a WARN_ON_ONCE guard after the num_subframes division as defense-in-depth to catch any future code paths that produce zero through a different mechanism. Suggested-by: Miriam Rachel Korenblit Fixes: d1e879ec600f ("wifi: iwlwifi: add iwlmld sub-driver") Signed-off-by: Cole Leavitt Link: https://patch.msgid.link/20260405054145.1064152-3-cole@unwrap.rs Signed-off-by: Miri Korenblit Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mld/tx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.c b/drivers/net/wireless/intel/iwlwifi/mld/tx.c index c54ea3a91b667..a60bfb1a2ab22 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.c @@ -828,7 +828,7 @@ static int iwl_mld_tx_tso_segment(struct iwl_mld *mld, struct sk_buff *skb, return -EINVAL; max_tid_amsdu_len = sta->cur->max_tid_amsdu_len[tid]; - if (!max_tid_amsdu_len) + if (!max_tid_amsdu_len || max_tid_amsdu_len == 1) return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs); /* Sub frame header + SNAP + IP header + TCP header + MSS */ @@ -840,6 +840,9 @@ static int iwl_mld_tx_tso_segment(struct iwl_mld *mld, struct sk_buff *skb, */ num_subframes = (max_tid_amsdu_len + pad) / (subf_len + pad); + if (WARN_ON_ONCE(!num_subframes)) + return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs); + if (sta->max_amsdu_subframes && num_subframes > sta->max_amsdu_subframes) num_subframes = sta->max_amsdu_subframes; From 3a74aaad047353da3344aed32e9042d4f334f926 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Fri, 15 May 2026 15:14:56 +0300 Subject: [PATCH 1451/1518] wifi: iwlwifi: mld: don't dereference a pointer before NULL checking it [ Upstream commit d733ed481fd20a8e7bfe5119c4e77761ba3f87ee ] In iwl_mld_remove_link, the link->fw_id is saved at the beginning of the function so we have it after we freed the link. But the link pointer can be NULL, and is not checked when the fw_id is stored. Fix it by simply freeing the link at the end of the function. fFixes: 0e66a39f4f0e ("wifi: iwlwifi: fix potential use after free in iwl_mld_remove_link()") Reviewed-by: Johannes Berg Link: https://patch.msgid.link/20260515151351.371f40fc6711.I6a82cfe9655564e9c5731af91c36493b26b1208e@changeid Signed-off-by: Miri Korenblit Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mld/link.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c index f6f52d297a72c..e67ba3a24d025 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2024-2025 Intel Corporation + * Copyright (C) 2024-2026 Intel Corporation */ #include "constants.h" @@ -501,7 +501,6 @@ void iwl_mld_remove_link(struct iwl_mld *mld, struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_conf->vif); struct iwl_mld_link *link = iwl_mld_link_from_mac80211(bss_conf); bool is_deflink = link == &mld_vif->deflink; - u8 fw_id = link->fw_id; if (WARN_ON(!link || link->active)) return; @@ -509,15 +508,15 @@ void iwl_mld_remove_link(struct iwl_mld *mld, iwl_mld_rm_link_from_fw(mld, bss_conf); /* Continue cleanup on failure */ - if (!is_deflink) - kfree_rcu(link, rcu_head); - RCU_INIT_POINTER(mld_vif->link[bss_conf->link_id], NULL); - if (WARN_ON(fw_id >= mld->fw->ucode_capa.num_links)) + if (WARN_ON(link->fw_id >= mld->fw->ucode_capa.num_links)) return; - RCU_INIT_POINTER(mld->fw_id_to_bss_conf[fw_id], NULL); + RCU_INIT_POINTER(mld->fw_id_to_bss_conf[link->fw_id], NULL); + + if (!is_deflink) + kfree_rcu(link, rcu_head); } void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld, From 181e67bc11c5ec5b87c6c512c2078752b23ca8d4 Mon Sep 17 00:00:00 2001 From: Jianpeng Chang Date: Wed, 13 May 2026 15:22:09 +0800 Subject: [PATCH 1452/1518] dma-mapping: move dma_map_resource() sanity check into debug code [ Upstream commit af0c3f05866237f7592219bfe05387bc3bfc99b5 ] dma_map_resource() uses pfn_valid() to ensure the range is not RAM. However, pfn_valid() only checks for availability of the memory map for a PFN but it does not ensure that the PFN is actually backed by RAM. On ARM64 with SPARSEMEM (128MB section granularity), MMIO addresses that share a section with RAM will falsely trigger the WARN_ON_ONCE and cause dma_map_resource() to return DMA_MAPPING_ERROR. This causes a WARNING on Raspberry Pi 4 during spi_bcm2835 probe because the SPI FIFO register (0xfe204004) falls in the same sparsemem section as the end of RAM (0xf8000000-0xfbffffff), both in section 31 (0xf8000000-0xffffffff). Move the sanity check from dma_map_resource() into debug_dma_map_phys() and replace the unreliable pfn_valid() with pfn_valid() && !PageReserved(), which correctly identifies actual usable RAM without false positives for MMIO regions that happen to have struct pages. Since dma_map_resource() is dma_map_phys(DMA_ATTR_MMIO), the check applies equally to both APIs. Any non-reserved page represents kernel memory to a sufficient degree that using DMA_ATTR_MMIO on it is almost certainly wrong and risks breaking coherency on non-coherent platforms. ZONE_DEVICE pages used for PCI P2P DMA (MEMORY_DEVICE_PCI_P2PDMA) have PageReserved set, so they will not trigger a false positive. The check no longer blocks the mapping and uses err_printk() to integrate with dma-debug filtering. Fixes: f7326196a781 ("dma-mapping: export new dma_*map_phys() interface") Reviewed-by: Robin Murphy Signed-off-by: Jianpeng Chang Reviewed-by: Leon Romanovsky Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20260513072209.1486986-1-jianpeng.chang.cn@windriver.com Signed-off-by: Sasha Levin --- kernel/dma/debug.c | 9 ++++++++- kernel/dma/mapping.c | 4 ---- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 21db331185911..fa4aac3339172 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -1250,7 +1250,14 @@ void debug_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, entry->direction = direction; entry->map_err_type = MAP_ERR_NOT_CHECKED; - if (!(attrs & DMA_ATTR_MMIO)) { + if (attrs & DMA_ATTR_MMIO) { + unsigned long pfn = PHYS_PFN(phys); + + if (pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) + err_printk(dev, entry, + "dma_map_resource called for RAM address %pa\n", + &phys); + } else { check_for_stack(dev, phys); if (!PhysHighMem(phys)) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index fe7472f13b106..35e4556b95566 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -366,10 +366,6 @@ EXPORT_SYMBOL(dma_unmap_sg_attrs); dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (IS_ENABLED(CONFIG_DMA_API_DEBUG) && - WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr)))) - return DMA_MAPPING_ERROR; - return dma_map_phys(dev, phys_addr, size, dir, attrs | DMA_ATTR_MMIO); } EXPORT_SYMBOL(dma_map_resource); From 2c890e71ae26fa32f5a96c3694b71a2c310940e7 Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Mon, 11 May 2026 15:41:34 +0000 Subject: [PATCH 1453/1518] drm/xe/gsc: Fix double-free of managed BO in error path [ Upstream commit d3ded53fab90996e7d94a39049e11962dd066725 ] The error path in xe_gsc_init_post_hwconfig() explicitly frees a BO allocated with xe_managed_bo_create_pin_map() via xe_bo_unpin_map_no_vm(). Since the managed BO already has a devm cleanup action registered, this causes a double-free when devm unwinds during probe failure. Remove the explicit free and let devm handle it, consistent with all other xe_managed_bo_create_pin_map() callers. Fixes: 2e5d47fe7839 ("drm/xe/uc: Use managed bo for HuC and GSC objects") Reviewed-by: Daniele Ceraolo Spurio Assisted-by: Claude:claude-opus-4.6 Link: https://patch.msgid.link/20260511154134.223696-1-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 71d61e3e299a17139e47f980a4d6f425b2c59bf7) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_gsc.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index 8371ec002e4ed..2a496987b8299 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -487,8 +487,7 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc) EXEC_QUEUE_FLAG_PERMANENT, 0); if (IS_ERR(q)) { xe_gt_err(gt, "Failed to create queue for GSC submission\n"); - err = PTR_ERR(q); - goto out_bo; + return PTR_ERR(q); } wq = alloc_ordered_workqueue("gsc-ordered-wq", 0); @@ -511,8 +510,6 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc) out_q: xe_exec_queue_put(q); -out_bo: - xe_bo_unpin_map_no_vm(bo); return err; } From dc26e00860a15e5fbe000a74276dccd1690a0420 Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Thu, 14 May 2026 17:57:26 +0200 Subject: [PATCH 1454/1518] drm/xe/vf: Fix signature of print functions [ Upstream commit 9bb2f1d7e6e58b8e434ddc2048c661bf87ccdf2a ] We have plugged-in existing VF print functions into our GT debugfs show helper as-is, but we missed that the helper expects functions to return int, while they were defined as void. This can lead to errors being reported when CFI is enabled. Fixes: 63d8cb8fe3dd ("drm/xe/vf: Expose SR-IOV VF attributes to GT debugfs") Signed-off-by: Michal Wajdeczko Cc: Mohanram Meenakshisundaram Reviewed-by: Shuicheng Lin Link: https://patch.msgid.link/20260514155726.7165-1-michal.wajdeczko@intel.com (cherry picked from commit 314e31c9a8a1c421ee4f7f755b9348aefbbca090) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 24 ++++++++++++++++++------ drivers/gpu/drm/xe/xe_gt_sriov_vf.h | 6 +++--- 2 files changed, 21 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c index 0461d55134874..ca58ef3f9fd39 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c @@ -1030,13 +1030,15 @@ void xe_gt_sriov_vf_write32(struct xe_gt *gt, struct xe_reg reg, u32 val) } /** - * xe_gt_sriov_vf_print_config - Print VF self config. + * xe_gt_sriov_vf_print_config() - Print VF self config. * @gt: the &xe_gt * @p: the &drm_printer * * This function is for VF use only. + * + * Return: always 0. */ -void xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p) +int xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p) { struct xe_gt_sriov_vf_selfconfig *config = >->sriov.vf.self_config; struct xe_device *xe = gt_to_xe(gt); @@ -1060,16 +1062,20 @@ void xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p) drm_printf(p, "GuC contexts:\t%u\n", config->num_ctxs); drm_printf(p, "GuC doorbells:\t%u\n", config->num_dbs); + + return 0; } /** - * xe_gt_sriov_vf_print_runtime - Print VF's runtime regs received from PF. + * xe_gt_sriov_vf_print_runtime() - Print VF's runtime regs received from PF. * @gt: the &xe_gt * @p: the &drm_printer * * This function is for VF use only. + * + * Return: always 0. */ -void xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p) +int xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p) { struct vf_runtime_reg *vf_regs = gt->sriov.vf.runtime.regs; unsigned int size = gt->sriov.vf.runtime.num_regs; @@ -1078,16 +1084,20 @@ void xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p) for (; size--; vf_regs++) drm_printf(p, "%#x = %#x\n", vf_regs->offset, vf_regs->value); + + return 0; } /** - * xe_gt_sriov_vf_print_version - Print VF ABI versions. + * xe_gt_sriov_vf_print_version() - Print VF ABI versions. * @gt: the &xe_gt * @p: the &drm_printer * * This function is for VF use only. + * + * Return: always 0. */ -void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p) +int xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p) { struct xe_device *xe = gt_to_xe(gt); struct xe_uc_fw_version *guc_version = >->sriov.vf.guc_version; @@ -1117,4 +1127,6 @@ void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p) GUC_RELAY_VERSION_LATEST_MAJOR, GUC_RELAY_VERSION_LATEST_MINOR); drm_printf(p, "\thandshake:\t%u.%u\n", pf_version->major, pf_version->minor); + + return 0; } diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h index 0af1dc769fe09..7f6c59b1ef7b6 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h @@ -35,8 +35,8 @@ s64 xe_gt_sriov_vf_ggtt_shift(struct xe_gt *gt); u32 xe_gt_sriov_vf_read32(struct xe_gt *gt, struct xe_reg reg); void xe_gt_sriov_vf_write32(struct xe_gt *gt, struct xe_reg reg, u32 val); -void xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p); -void xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p); -void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p); +int xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p); +int xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p); +int xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p); #endif From 6c9e9272bc37f1bebab59f244c3e4c296a573dbc Mon Sep 17 00:00:00 2001 From: Mohanram Meenakshisundaram Date: Thu, 14 May 2026 23:19:18 +0530 Subject: [PATCH 1455/1518] drm/xe/pf: Fix CFI failure in debugfs access [ Upstream commit 96bf49b526e2d03a2b7f6e861925a08f46ed0d28 ] Reading debugfs file (/sys/kernel/debug/dri/0/gt*/pf/adverse_events) with CFI (Control Flow Integrity) enabled, the kernel panics at xe_gt_debugfs_simple_show+0x82/0xc0. xe_gt_debugfs_simple_show() declare a function pointer expecting int return type, but xe_gt_sriov_pf_monitor_print_events() is void return type, leading to CFI failure and kernel panic. [507620.973657] CFI failure at xe_gt_debugfs_simple_show+0x82/0xc0 [xe] (target: xe_gt_sriov_pf_monitor_print_events+0x0/0x130 [xe]; expected type: 0xd72c7139) Fix xe_gt_sriov_pf_monitor_print_events() function by updating to return an int type. Fixes: 1c99d3d3edab ("drm/xe/pf: Expose PF monitor details via debugfs") Signed-off-by: Mohanram Meenakshisundaram Reviewed-by: Michal Wajdeczko Signed-off-by: Michal Wajdeczko Link: https://patch.msgid.link/20260514174918.1556357-2-mohanram.meenakshisundaram@intel.com (cherry picked from commit ff1d386a8359746d9699ac30336e3b0684c68958) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c | 6 +++++- drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c index 7d532bded02a8..a85ba44353789 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.c @@ -114,8 +114,10 @@ int xe_gt_sriov_pf_monitor_process_guc2pf(struct xe_gt *gt, const u32 *msg, u32 * VFs with no events are not printed. * * This function can only be called on PF. + * + * Return: always 0 */ -void xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p) +int xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p) { unsigned int n, total_vfs = xe_gt_sriov_pf_get_totalvfs(gt); const struct xe_gt_sriov_monitor *data; @@ -144,4 +146,6 @@ void xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p #undef __format #undef __value } + + return 0; } diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h index 7ca9351a271b7..0b8f088d3a16a 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_monitor.h @@ -13,7 +13,7 @@ struct drm_printer; struct xe_gt; void xe_gt_sriov_pf_monitor_flr(struct xe_gt *gt, u32 vfid); -void xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p); +int xe_gt_sriov_pf_monitor_print_events(struct xe_gt *gt, struct drm_printer *p); #ifdef CONFIG_PCI_IOV int xe_gt_sriov_pf_monitor_process_guc2pf(struct xe_gt *gt, const u32 *msg, u32 len); From 926a08cf19be32f9c9e25e0b00cc7f211f4f85a3 Mon Sep 17 00:00:00 2001 From: Matthew Leach Date: Fri, 24 Apr 2026 10:50:35 +0100 Subject: [PATCH 1456/1518] wifi: ath11k: fix peer resolution on rx path when peer_id=0 [ Upstream commit 2a2451a34afdf563b3102d36a4b6cf335cf813e2 ] It has been observed that on certain chipsets a peer can be assigned peer_id=0. For reception of non-aggregated MPDUs this is fine as ath11k_dp_rx_h_find_peer() has a fallback case where it locates the peer based upon the source MAC address. On an aggregated link, the mpdu_start header is only populated by hardware on the first sub-MSDU. This causes the peer resolution to be skipped for the subsequent MSDUs and the encryption type of these frames to be set to an incorrect value, resulting in these MSDUs being dropped by ieee80211. ath11k_pci 0000:03:00.0: data rx skb 000000002f4b704d len 1534 peer xx:xx:xx:xx:xx:xx 0 ucast sn 3063 he160 rate_idx 9 vht_nss 2 freq 5240 band 1 flag 0x40d1a fcs-err 0 mic-err 0 amsdu-more 0 peer_id 0 first_msdu 1 last_msdu 0 ath11k_pci 0000:03:00.0: data rx skb 0000000038acd580 len 1534 peer (null) 0 ucast sn 3063 he160 rate_idx 9 vht_nss 2 freq 5240 band 1 flag 0x40d00 fcs-err 0 mic-err 0 amsdu-more 0 peer_id 0 first_msdu 0 last_msdu 1 Remove the null peer_id checks in ath11k_dp_rx_h_find_peer() and ath11k_hal_rx_parse_mon_status_tlv(), allowing peers with an assigned ID of 0 to be resolved. Tested-on: QCA2066 hw2.1 PCI WLAN.HSP.1.1-03926.13-QCAHSPSWPL_V2_SILICONZ_CE-2.52297.9 Fixes: 2167fa606c0f ("ath11k: Add support for RX decapsulation offload") Reviewed-by: Baochen Qiang Signed-off-by: Matthew Leach Reviewed-by: P Praneesh Link: https://patch.msgid.link/20260424-ath11k-null-peerid-workaround-v4-1-252b224d3cf6@collabora.com Signed-off-by: Jeff Johnson Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp_rx.c | 3 +-- drivers/net/wireless/ath/ath11k/hal_rx.c | 5 +---- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 44eea682c297b..5666f66474455 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -2214,8 +2214,7 @@ ath11k_dp_rx_h_find_peer(struct ath11k_base *ab, struct sk_buff *msdu) lockdep_assert_held(&ab->base_lock); - if (rxcb->peer_id) - peer = ath11k_peer_find_by_id(ab, rxcb->peer_id); + peer = ath11k_peer_find_by_id(ab, rxcb->peer_id); if (peer) return peer; diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c index 753bd93f02123..51e0840bc0d1e 100644 --- a/drivers/net/wireless/ath/ath11k/hal_rx.c +++ b/drivers/net/wireless/ath/ath11k/hal_rx.c @@ -1467,11 +1467,8 @@ ath11k_hal_rx_parse_mon_status_tlv(struct ath11k_base *ab, case HAL_RX_MPDU_START: { struct hal_rx_mpdu_info *mpdu_info = (struct hal_rx_mpdu_info *)tlv_data; - u16 peer_id; - peer_id = ath11k_hal_rx_mpduinfo_get_peerid(ab, mpdu_info); - if (peer_id) - ppdu_info->peer_id = peer_id; + ppdu_info->peer_id = ath11k_hal_rx_mpduinfo_get_peerid(ab, mpdu_info); break; } case HAL_RXPCU_PPDU_END_INFO: { From 8ea34da689646a1261445e1e40f25bdee2df14a6 Mon Sep 17 00:00:00 2001 From: Louis-Alexis Eyraud Date: Wed, 29 Apr 2026 11:59:01 +0200 Subject: [PATCH 1457/1518] drm/mediatek: mtk_cec: Fix non-static global variable [ Upstream commit 571f00a5fb725984049bd532ee8193cc34ff2994 ] The struct 'mtk_cec_driver' is not used outside of the mtk_cec.c file, so make it static to silence sparse warning: ``` drivers/gpu/drm/mediatek/mtk_cec.c:243:24: sparse: warning: symbol 'mtk_cec_driver' was not declared. Should it be static? ``` Fixes: 1e914a89ab7e ("drm/mediatek: mtk_cec: Switch to register as module_platform_driver") Signed-off-by: Louis-Alexis Eyraud Reviewed-by: CK Hu Link: https://patchwork.kernel.org/project/dri-devel/patch/20260429-mediatek-drm-fix-sparse-warnings-v1-3-d95c4d118b83@collabora.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_cec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_cec.c b/drivers/gpu/drm/mediatek/mtk_cec.c index c7be530ca041f..b8ccd6e55bedb 100644 --- a/drivers/gpu/drm/mediatek/mtk_cec.c +++ b/drivers/gpu/drm/mediatek/mtk_cec.c @@ -240,7 +240,7 @@ static const struct of_device_id mtk_cec_of_ids[] = { }; MODULE_DEVICE_TABLE(of, mtk_cec_of_ids); -struct platform_driver mtk_cec_driver = { +static struct platform_driver mtk_cec_driver = { .probe = mtk_cec_probe, .remove = mtk_cec_remove, .driver = { From 83b8a0f72ecc08bf71655a49b94fd69f7f06b5f1 Mon Sep 17 00:00:00 2001 From: Louis-Alexis Eyraud Date: Wed, 29 Apr 2026 11:59:02 +0200 Subject: [PATCH 1458/1518] drm/mediatek: mtk_hdmi_ddc: Fix non-static global variable [ Upstream commit 87ed4e845d5a90bba1a56c0a5c580a13982e8648 ] The struct 'mtk_hdmi_ddc_driver' is not used outside of the mtk_hdmi_ddc.c file, so make it static to silence sparse warning: ``` drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c:331:24: sparse: warning: symbol 'mtk_hdmi_ddc_driver' was not declared. Should it be static? ``` Fixes: c241118b6216 ("drm/mediatek: mtk_hdmi_ddc: Switch to register as module_platform_driver") Signed-off-by: Louis-Alexis Eyraud Reviewed-by: CK Hu Link: https://patchwork.kernel.org/project/dri-devel/patch/20260429-mediatek-drm-fix-sparse-warnings-v1-4-d95c4d118b83@collabora.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c index 6358e1af69b49..2acbdb025d893 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c @@ -328,7 +328,7 @@ static const struct of_device_id mtk_hdmi_ddc_match[] = { }; MODULE_DEVICE_TABLE(of, mtk_hdmi_ddc_match); -struct platform_driver mtk_hdmi_ddc_driver = { +static struct platform_driver mtk_hdmi_ddc_driver = { .probe = mtk_hdmi_ddc_probe, .remove = mtk_hdmi_ddc_remove, .driver = { From 6a01413a4e8fcb0263d7bef5075c5f8f4eb3a8b6 Mon Sep 17 00:00:00 2001 From: Qing Ming Date: Sat, 16 May 2026 15:08:49 +0800 Subject: [PATCH 1459/1518] cgroup/rstat: validate cpu before css_rstat_cpu() access [ Upstream commit 8817005efbdfdf5d4e4814cb5dc52b53d12917d7 ] css_rstat_updated() is exposed as a BPF kfunc and accepts a caller-provided cpu argument. The function uses cpu for per-cpu rstat lookups without checking whether it refers to a valid possible CPU. A BPF iter/cgroup program with CAP_BPF and CAP_PERFMON can pass an invalid cpu value. On an unfixed UBSCAN_BOUNDS test kernel, cpu == 0x7fffffff triggers: UBSAN: array-index-out-of-bounds in kernel/cgroup/rstat.c:31:9 index 2147483647 is out of range for type 'long unsigned int [64]' Call Trace: css_rstat_updated bpf_iter_run_prog cgroup_iter_seq_show bpf_seq_read Add cpu validation to the BPF-facing css_rstat_updated() kfunc and move the common implementation to __css_rstat_updated() for in-kernel callers. Fixes: a319185be9f5 ("cgroup: bpf: enable bpf programs to integrate with rstat") Signed-off-by: Qing Ming Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- block/blk-cgroup.c | 2 +- include/linux/cgroup.h | 1 + kernel/cgroup/rstat.c | 30 ++++++++++++++++++++---------- mm/memcontrol.c | 6 +++--- 4 files changed, 25 insertions(+), 14 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 9a8d047be580b..f1ea69743c544 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -2241,7 +2241,7 @@ void blk_cgroup_bio_start(struct bio *bio) } u64_stats_update_end_irqrestore(&bis->sync, flags); - css_rstat_updated(&blkcg->css, cpu); + __css_rstat_updated(&blkcg->css, cpu); put_cpu(); } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 6ed477338b166..7b2807009155a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -713,6 +713,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) /* * cgroup scalable recursive statistics. */ +void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu); void css_rstat_updated(struct cgroup_subsys_state *css, int cpu); void css_rstat_flush(struct cgroup_subsys_state *css); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 150e5871e66f2..ed60ba119c687 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" +#include #include #include @@ -53,7 +54,7 @@ static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) } /** - * css_rstat_updated - keep track of updated rstat_cpu + * __css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * @@ -63,20 +64,17 @@ static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a - * memory barrier is needed before the call to css_rstat_updated() i.e. a + * memory barrier is needed before the call to __css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling - * css_rstat_updated(). + * __css_rstat_updated(). */ -__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) +void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct llist_node *self; - /* - * Since bpf programs can call this function, prevent access to - * uninitialized rstat pointers. - */ + /* Prevent access to uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; @@ -125,6 +123,18 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) llist_add(&rstatc->lnode, lhead); } +/* + * BPF-facing wrapper for __css_rstat_updated(). Validate the caller-provided + * CPU before passing it to the internal rstat updater. + */ +__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) +{ + if (unlikely(cpu < 0 || cpu >= nr_cpu_ids || !cpu_possible(cpu))) + return; + + __css_rstat_updated(css, cpu); +} + static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu) { /* put @css and all ancestors on the corresponding updated lists */ @@ -170,7 +180,7 @@ static void css_process_update_tree(struct cgroup_subsys *ss, int cpu) * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before - * css_rstat_updated() by the user. + * __css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add @@ -614,7 +624,7 @@ static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatbc->bsync, flags); - css_rstat_updated(&cgrp->self, smp_processor_id()); + __css_rstat_updated(&cgrp->self, smp_processor_id()); put_cpu_ptr(rstatbc); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 61cf6af26f3c9..4df68e5468add 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -571,7 +571,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val, if (!val) return; - css_rstat_updated(&memcg->css, cpu); + __css_rstat_updated(&memcg->css, cpu); statc_pcpu = memcg->vmstats_percpu; for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) { statc = this_cpu_ptr(statc_pcpu); @@ -2525,7 +2525,7 @@ static inline void account_slab_nmi_safe(struct mem_cgroup *memcg, struct mem_cgroup_per_node *pn = memcg->nodeinfo[pgdat->node_id]; /* preemption is disabled in_nmi(). */ - css_rstat_updated(&memcg->css, smp_processor_id()); + __css_rstat_updated(&memcg->css, smp_processor_id()); if (idx == NR_SLAB_RECLAIMABLE_B) atomic_add(nr, &pn->slab_reclaimable); else @@ -2749,7 +2749,7 @@ static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val) mod_memcg_state(memcg, MEMCG_KMEM, val); } else { /* preemption is disabled in_nmi(). */ - css_rstat_updated(&memcg->css, smp_processor_id()); + __css_rstat_updated(&memcg->css, smp_processor_id()); atomic_add(val, &memcg->kmem_stat); } } From 0010296879dfec8e9f1aa8292510b03499370210 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Fri, 15 May 2026 11:24:11 -0700 Subject: [PATCH 1460/1518] ice: ptp: serialize E825 PHY timer start with PTP lock [ Upstream commit 781ff8f2d575a794a2a4f11605288ae06757f5eb ] ice_start_phy_timer_eth56g() programs TIMETUS registers and issues INIT_INCVAL without holding the global PTP semaphore. This allows concurrent PTP command paths to interleave with PHY timer start, which can make the sequence fail and leave timer initialization inconsistent. Take the PTP lock around TIMETUS registers programming and INIT_INCVAL command execution, and make sure the lock is released on all error paths. Keep the subsequent sync step outside of this critical section, since ice_sync_phy_timer_eth56g() takes the same semaphore internally. Fixes: 7cab44f1c35f ("ice: Introduce ETH56G PHY model for E825C products") Reviewed-by: Arkadiusz Kubalewski Signed-off-by: Grzegorz Nitka Reviewed-by: Aleksandr Loktionov Tested-by: Alexander Nowlin Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-5-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 30b7839398165..0f378e68f72f1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -2141,16 +2141,23 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) } incval = (u64)hi << 32 | lo; + if (!ice_ptp_lock(hw)) { + dev_err(ice_hw_to_dev(hw), "Failed to acquire PTP semaphore\n"); + return -EBUSY; + } + err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval); if (err) - return err; + goto err_ptp_unlock; err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); if (err) - return err; + goto err_ptp_unlock; ice_ptp_exec_tmr_cmd(hw); + ice_ptp_unlock(hw); + err = ice_sync_phy_timer_eth56g(hw, port); if (err) return err; @@ -2166,6 +2173,10 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) ice_debug(hw, ICE_DBG_PTP, "Enabled clock on PHY port %u\n", port); return 0; + +err_ptp_unlock: + ice_ptp_unlock(hw); + return err; } /** From 89964ddb322a65979ef867e240915223352922e2 Mon Sep 17 00:00:00 2001 From: Grzegorz Nitka Date: Fri, 15 May 2026 11:24:12 -0700 Subject: [PATCH 1461/1518] ice: ptp: use primary NAC semaphore on E825 [ Upstream commit 7b28523546c7e4adbb8436f2986efcfc8382985e ] For E825 2xNAC configurations, PTP semaphore operations must hit the primary NAC register block so both sides coordinate on the same lock. Commit e2193f9f9ec9 ("ice: enable timesync operation on 2xNAC E825 devices") updated other primary-only PTP register accesses to use the primary NAC on non-primary functions, but left ice_ptp_lock() and ice_ptp_unlock() operating on the local NAC. As a result, secondary NAC PTP paths can take a different semaphore than the primary side. Select the primary hardware in ice_ptp_lock() and ice_ptp_unlock() when the current function is not primary, keeping semaphore operations symmetric and consistent with the rest of the 2xNAC PTP register access path. Fixes: e2193f9f9ec9 ("ice: enable timesync operation on 2xNAC E825 devices") Reviewed-by: Arkadiusz Kubalewski Signed-off-by: Grzegorz Nitka Reviewed-by: Aleksandr Loktionov Tested-by: Alexander Nowlin Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-6-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 0f378e68f72f1..99bf38cf352a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -5264,9 +5264,13 @@ static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp) */ bool ice_ptp_lock(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); u32 hw_lock; int i; + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + #define MAX_TRIES 15 for (i = 0; i < MAX_TRIES; i++) { @@ -5293,6 +5297,11 @@ bool ice_ptp_lock(struct ice_hw *hw) */ void ice_ptp_unlock(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + wr32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), 0); } From 1f83545f432d106d5fc71d3997b2d382104ebcc4 Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Fri, 15 May 2026 11:24:15 -0700 Subject: [PATCH 1462/1518] igc: set tx buffer type for SMD frames [ Upstream commit 5acc641e590e008caaed480ed9ffae47cf7ecbdf ] Sashiko pointed out that igc_fpe_init_smd_frame() initializes igc_tx_buffer fields for an SMD skb, but does not set the buffer type: https://sashiko.dev/#/patchset/20260415025226.114115-1-kohei%40enjuk.jp Since igc_tx_buffer entries are reused, a stale XDP or XSK type can remain and make TX completion use the wrong cleanup path. Set the buffer type to IGC_TX_BUFFER_TYPE_SKB. Fixes: 5422570c0010 ("igc: add support for frame preemption verification") Signed-off-by: Kohei Enju Reviewed-by: Aleksandr Loktionov Reviewed-by: Simon Horman Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20260515182419.1597859-9-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_tsn.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 02dd9f0290a34..52de2bcbadbec 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -34,6 +34,7 @@ static int igc_fpe_init_smd_frame(struct igc_ring *ring, return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_SKB; buffer->skb = skb; buffer->protocol = 0; buffer->bytecount = skb->len; From ad8e3d096fa1e2f8b1009731c6e0cdae7ebedf79 Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Mon, 11 May 2026 18:02:15 +0530 Subject: [PATCH 1463/1518] drm/i915/dp: Fix readback for target_rr in Adaptive Sync SDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f87abd0c6604fb6cc31cc86fc7ccc6a576924352 ] Correct the bit-shift logic to properly readback the 10 bit target_rr from DB3 and DB4. v2: Align the style with readback for vtotal. (Ville) Fixes: 12ea89291603 ("drm/i915/dp: Add Read/Write support for Adaptive Sync SDP") Cc: Mitul Golani Cc: Ankit Nautiyal Signed-off-by: Ankit Nautiyal Reviewed-by: Ville Syrjälä Link: https://patch.msgid.link/20260511123218.1589830-2-ankit.k.nautiyal@intel.com (cherry picked from commit f7abc4af2b19240a145a221461dfe756cc01d74a) Signed-off-by: Tvrtko Ursulin Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/display/intel_dp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 61f22275403bf..a44fbac1e5e27 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4899,7 +4899,7 @@ int intel_dp_as_sdp_unpack(struct drm_dp_as_sdp *as_sdp, as_sdp->length = sdp->sdp_header.HB3 & DP_ADAPTIVE_SYNC_SDP_LENGTH; as_sdp->mode = sdp->db[0] & DP_ADAPTIVE_SYNC_SDP_OPERATION_MODE; as_sdp->vtotal = (sdp->db[2] << 8) | sdp->db[1]; - as_sdp->target_rr = (u64)sdp->db[3] | ((u64)sdp->db[4] & 0x3); + as_sdp->target_rr = ((sdp->db[4] & 0x3) << 8) | sdp->db[3]; as_sdp->target_rr_divider = sdp->db[4] & 0x20 ? true : false; return 0; From f1739debda62d8ed591ec8635857265ca6eef77d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Viktor=20J=C3=A4gersk=C3=BCpper?= Date: Fri, 15 May 2026 23:58:45 +0200 Subject: [PATCH 1464/1518] kbuild: pacman-pkg: make "rc" releases adhere to pacman versioning scheme MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 202550713128da20d9381d6d2dc0f6b73839f434 ] The package versioning scheme does not enable smooth upgrades from "rc" releases to the corresponding stable releases (e.g. 7.0.0-rc7 -> 7.0.0) because pacman considers that a downgrade due to the underscore in pkgver (e.g. 7.0.0_rc7), see e.g. vercmp(8) for an explanation of the package version comparison used by pacman. Package versions which are derived from said releases (e.g. built from git revisions) are similarly affected. Fix this by modifying pkgver in order to remove the hyphen from kernel versions containing "-rcN", where N is a non-negative integer. Acked-by: Thomas Weißschuh Signed-off-by: Viktor Jägersküpper Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Link: https://patch.msgid.link/20260515215913.92481-1-viktor_jaegerskuepper@freenet.de Fixes: c8578539deba ("kbuild: add script and target to generate pacman package") Signed-off-by: Nicolas Schier Signed-off-by: Sasha Levin --- scripts/package/PKGBUILD | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index 452374d63c244..1213c8e04671e 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -10,7 +10,7 @@ for pkg in $_extrapackages; do pkgname+=("${pkgbase}-${pkg}") done -pkgver="${KERNELRELEASE//-/_}" +pkgver="$(echo "${KERNELRELEASE}" | sed 's/-\(rc[0-9]\+\)/\1/;s/-/_/g')" # The PKGBUILD is evaluated multiple times. # Running scripts/build-version from here would introduce inconsistencies. pkgrel="${KBUILD_REVISION}" From 89bed786f23182fdf975668538bfee9df38aaaee Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Thu, 14 May 2026 15:04:21 +0100 Subject: [PATCH 1465/1518] net: dsa: mt7530: fix FDB entries not aging out with short timeout [ Upstream commit e824e40d0e841fab66ab7897d6c7b14dc81c66a7 ] The DSA forwarding selftests bridge_vlan_aware.sh and bridge_vlan_unaware.sh configure the bridge with ageing_time set to LOW_AGEING_TIME (1000 centiseconds, i.e. 10 seconds) and then run learning_test() in lib.sh, which expects a learned FDB entry to be removed after ageing_time + 10 seconds. On MT7530/MT7531 the entry persisted past the deadline and the "Found FDB record when should not" assertion failed. With msecs=10000, the algorithm in mt7530_set_ageing_time() finds AGE_CNT=0 and AGE_UNIT=9 as the first exact match (starting the search from tmp_age_count=0). The per-entry aging counter is initialized to AGE_CNT when a MAC address is learned, so with AGE_CNT=0 new entries start with a counter value of 0, which the hardware treats as "already aged" and never removes, effectively disabling aging. Fix this by starting the search from tmp_age_count=1 to ensure entries always have a non-zero initial aging counter. For a 10-second ageing time this yields AGE_CNT=1 and AGE_UNIT=4 instead: the timer ticks every 5 seconds and entries are removed after 2 ticks. Starting the search at AGE_CNT=1 raises the minimum representable ageing time from 1 to 2 seconds. Without bounds, a stale ageing_time of 1 second would now make the loop fall through without setting age_count and age_unit, leaving them uninitialized when written to the MT7530_AAC hardware register. Set ds->ageing_time_min and ds->ageing_time_max so the DSA core validates the range before the callback is invoked, and drop the now-redundant range check from mt7530_set_ageing_time(). Fixes: ea6d5c924e39 ("net: dsa: mt7530: support setting ageing time") Signed-off-by: Daniel Golle Link: https://patch.msgid.link/7788ded12dc07b1bce329ec35fa70f4b45f3f9b7.1778766629.git.daniel@makrotopia.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/dsa/mt7530.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 548b85befbf45..d6ce335f6688b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -973,12 +973,16 @@ mt7530_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) unsigned int age_count; unsigned int age_unit; - /* Applied timer is (AGE_CNT + 1) * (AGE_UNIT + 1) seconds */ - if (secs < 1 || secs > (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1)) - return -ERANGE; - - /* iterate through all possible age_count to find the closest pair */ - for (tmp_age_count = 0; tmp_age_count <= AGE_CNT_MAX; ++tmp_age_count) { + /* Applied timer is (AGE_CNT + 1) * (AGE_UNIT + 1) seconds. + * The DSA core has already validated the range using + * ds->ageing_time_min and ds->ageing_time_max. + * + * Iterate through all possible age_count values to find the closest + * pair. Start from 1 because the per-entry aging counter is + * initialized to AGE_CNT and a value of 0 means the entry will + * never be aged out. + */ + for (tmp_age_count = 1; tmp_age_count <= AGE_CNT_MAX; ++tmp_age_count) { unsigned int tmp_age_unit = secs / (tmp_age_count + 1) - 1; if (tmp_age_unit <= AGE_UNIT_MAX) { @@ -2378,6 +2382,8 @@ mt7530_setup(struct dsa_switch *ds) ds->assisted_learning_on_cpu_port = true; ds->mtu_enforcement_ingress = true; + ds->ageing_time_min = 2 * 1000; + ds->ageing_time_max = (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1) * 1000; if (priv->id == ID_MT7530) { regulator_set_voltage(priv->core_pwr, 1000000, 1000000); @@ -2567,6 +2573,8 @@ mt7531_setup_common(struct dsa_switch *ds) ds->assisted_learning_on_cpu_port = true; ds->mtu_enforcement_ingress = true; + ds->ageing_time_min = 2 * 1000; + ds->ageing_time_max = (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1) * 1000; mt753x_trap_frames(priv); From f71fc35b5e45973bf62543f6e91a8cceae6bfb3b Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Thu, 14 May 2026 15:04:35 +0100 Subject: [PATCH 1466/1518] net: dsa: mt7530: preserve VLAN tags on trapped link-local frames [ Upstream commit 3ac85bcfd404b588298c95c6fba8aad4ad334f57 ] The BPC, RGAC1 and RGAC2 registers control the handling of link-local frames with reserved MAC DAs (01:80:C2:00:00:0x). These frames are correctly trapped to the CPU port, but the egress VLAN tag attribute was set to MT7530_VLAN_EG_UNTAGGED which causes the switch to strip any VLAN tags from trapped frames before they reach the CPU. This causes VLAN-tagged link-local frames (STP BPDUs, LLDP, PTP Peer Delay Requests) to arrive at the CPU without their VLAN tag, so they are delivered to the base network interface instead of the VLAN sub-interface. The DSA local_termination selftest confirms this: all link-local protocol tests on VLAN upper interfaces fail. Set the EG_TAG attribute to MT7530_VLAN_EG_DISABLED (system default) so that the switch does not modify VLAN tags in trapped frames. This way VLAN-tagged frames retain their original tag and are delivered to the correct VLAN sub-interface, matching the behavior of non-trapped frames which pass through without VLAN tag modification. Fixes: 69ddba9d170b ("net: dsa: mt7530: fix handling of all link-local frames") Signed-off-by: Daniel Golle Acked-by: Chester A. Unal Link: https://patch.msgid.link/891e0cd34db2a5fe20ceb73283a81fb5f71427ca.1778766629.git.daniel@makrotopia.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/dsa/mt7530.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d6ce335f6688b..4571da0d7a8f6 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1250,37 +1250,40 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) static void mt753x_trap_frames(struct mt7530_priv *priv) { - /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them - * VLAN-untagged. + /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress + * them with the EG_TAG attribute set to disabled (system default) + * so that any VLAN tags in the frame are not modified by the + * switch egress VLAN tag processing. This preserves VLAN tags + * for reception on VLAN sub-interfaces. */ mt7530_rmw(priv, MT753X_BPC, PAE_BPDU_FR | PAE_EG_TAG_MASK | PAE_PORT_FW_MASK | BPDU_EG_TAG_MASK | BPDU_PORT_FW_MASK, - PAE_BPDU_FR | PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + PAE_BPDU_FR | PAE_EG_TAG(MT7530_VLAN_EG_DISABLED) | PAE_PORT_FW(TO_CPU_FW_CPU_ONLY) | - BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + BPDU_EG_TAG(MT7530_VLAN_EG_DISABLED) | TO_CPU_FW_CPU_ONLY); - /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress - * them VLAN-untagged. + /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and + * egress them with EG_TAG disabled. */ mt7530_rmw(priv, MT753X_RGAC1, R02_BPDU_FR | R02_EG_TAG_MASK | R02_PORT_FW_MASK | R01_BPDU_FR | R01_EG_TAG_MASK | R01_PORT_FW_MASK, - R02_BPDU_FR | R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R02_BPDU_FR | R02_EG_TAG(MT7530_VLAN_EG_DISABLED) | R02_PORT_FW(TO_CPU_FW_CPU_ONLY) | R01_BPDU_FR | - R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R01_EG_TAG(MT7530_VLAN_EG_DISABLED) | TO_CPU_FW_CPU_ONLY); - /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress - * them VLAN-untagged. + /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and + * egress them with EG_TAG disabled. */ mt7530_rmw(priv, MT753X_RGAC2, R0E_BPDU_FR | R0E_EG_TAG_MASK | R0E_PORT_FW_MASK | R03_BPDU_FR | R03_EG_TAG_MASK | R03_PORT_FW_MASK, - R0E_BPDU_FR | R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R0E_BPDU_FR | R0E_EG_TAG(MT7530_VLAN_EG_DISABLED) | R0E_PORT_FW(TO_CPU_FW_CPU_ONLY) | R03_BPDU_FR | - R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R03_EG_TAG(MT7530_VLAN_EG_DISABLED) | TO_CPU_FW_CPU_ONLY); } From 09ec063d87c2dd3fa6f3561361a017bd882e9f37 Mon Sep 17 00:00:00 2001 From: Erni Sri Satya Vennela Date: Thu, 14 May 2026 12:41:51 -0700 Subject: [PATCH 1467/1518] net: mana: Fix TOCTOU double-fetch of hwc_msg_id from DMA buffer [ Upstream commit 35f0f0a2536a4d604b4dbad92c85c4a8fdebb870 ] In mana_hwc_rx_event_handler(), resp->response.hwc_msg_id is read from DMA-coherent memory and bounds-checked, then mana_hwc_handle_resp() re-reads the same field from the same DMA buffer for test_bit() and pointer arithmetic. DMA-coherent memory is mapped uncacheable on x86 and is shared, unencrypted, in Confidential VMs (SEV-SNP/TDX), so each load goes directly to host-visible memory. A H/W can modify the value between the check and the use, bypassing the bounds validation. Fix this by reading hwc_msg_id exactly once using READ_ONCE() into a stack-local variable in mana_hwc_rx_event_handler(), and passing the validated value as a parameter to mana_hwc_handle_resp(). Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)") Signed-off-by: Erni Sri Satya Vennela Link: https://patch.msgid.link/20260514194156.466823-1-ernis@linux.microsoft.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- .../net/ethernet/microsoft/mana/hw_channel.c | 23 +++++++++++-------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 840c6b8957c90..1986bf493399f 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -77,21 +77,19 @@ static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq, } static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len, - struct hwc_work_request *rx_req) + struct hwc_work_request *rx_req, u16 msg_id) { const struct gdma_resp_hdr *resp_msg = rx_req->buf_va; struct hwc_caller_ctx *ctx; int err; - if (!test_bit(resp_msg->response.hwc_msg_id, - hwc->inflight_msg_res.map)) { - dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n", - resp_msg->response.hwc_msg_id); + if (!test_bit(msg_id, hwc->inflight_msg_res.map)) { + dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n", msg_id); mana_hwc_post_rx_wqe(hwc->rxq, rx_req); return; } - ctx = hwc->caller_ctx + resp_msg->response.hwc_msg_id; + ctx = hwc->caller_ctx + msg_id; err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len); if (err) goto out; @@ -251,6 +249,7 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id, struct gdma_sge *sge; u64 rq_base_addr; u64 rx_req_idx; + u16 msg_id; u8 *wqe; if (WARN_ON_ONCE(hwc_rxq->gdma_wq->id != gdma_rxq_id)) @@ -269,13 +268,17 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id, rx_req = &hwc_rxq->msg_buf->reqs[rx_req_idx]; resp = (struct gdma_resp_hdr *)rx_req->buf_va; - if (resp->response.hwc_msg_id >= hwc->num_inflight_msg) { - dev_err(hwc->dev, "HWC RX: wrong msg_id=%u\n", - resp->response.hwc_msg_id); + /* Read msg_id once from DMA buffer to prevent TOCTOU: + * DMA memory is shared/unencrypted in CVMs - host can + * modify it between reads. + */ + msg_id = READ_ONCE(resp->response.hwc_msg_id); + if (msg_id >= hwc->num_inflight_msg) { + dev_err(hwc->dev, "HWC RX: wrong msg_id=%u\n", msg_id); return; } - mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req); + mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req, msg_id); /* Can no longer use 'resp', because the buffer is posted to the HW * in mana_hwc_handle_resp() above. From 098419a4b0623a195ab1d88cfebf4a9f96a7598d Mon Sep 17 00:00:00 2001 From: Oliver White Date: Thu, 9 Apr 2026 15:43:47 +1200 Subject: [PATCH 1468/1518] platform/surface: aggregator_registry: omit battery & AC nodes on Surface Laptop 7 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0488073a6c84571dd3cffe581a4a73a5fceb099d ] Surface Laptop 7 exposes battery and AC status via Qualcomm PMIC GLINK qcom_battmgr. Registering the standard SSAM battery and AC client devices on this platform causes duplicate power-supply devices to appear. Drop the SSAM battery and AC nodes from the Surface Laptop 7 registry group so that only the qcom_battmgr power supplies are instantiated. Fixes: b27622f13172 ("platform/surface: Add OF support") Signed-off-by: Oliver White Link: https://patch.msgid.link/20260409034347.17381-1-oliverjwhite07@gmail.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/surface/surface_aggregator_registry.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index a594d5fcfcfd1..d29158faba3e8 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -295,8 +295,6 @@ static const struct software_node *ssam_node_group_sl6[] = { /* Devices for Surface Laptop 7. */ static const struct software_node *ssam_node_group_sl7[] = { &ssam_node_root, - &ssam_node_bat_ac, - &ssam_node_bat_main, &ssam_node_tmp_perf_profile_with_fan, &ssam_node_fan_speed, &ssam_node_hid_sam_keyboard, From 7ea5aad8d351a8791b86f49bdc39ec67e277c35c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 May 2026 17:11:49 +0200 Subject: [PATCH 1469/1518] platform/x86: adv_swbutton: Check ACPI_HANDLE() against NULL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e7a9a6ea40e352cd7977f6a8c80bdeadf65ad838 ] Every platform driver can be forced to match a device that doesn't match its list of device IDs because of device_match_driver_override(), so platform drivers that rely on the existence of a device's ACPI companion object need to verify its presence. Accordingly, add a requisite ACPI_HANDLE() check against NULL to the platform/x86 adv_swbutton driver. Fixes: 3d904005f686 ("platform/x86: add support for Advantech software defined button") Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/5115425.31r3eYUQgx@rafael.j.wysocki Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/adv_swbutton.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/adv_swbutton.c b/drivers/platform/x86/adv_swbutton.c index 6fa60f3fc53c0..8f7a26e6de81d 100644 --- a/drivers/platform/x86/adv_swbutton.c +++ b/drivers/platform/x86/adv_swbutton.c @@ -48,10 +48,14 @@ static int adv_swbutton_probe(struct platform_device *device) { struct adv_swbutton *button; struct input_dev *input; - acpi_handle handle = ACPI_HANDLE(&device->dev); + acpi_handle handle; acpi_status status; int error; + handle = ACPI_HANDLE(&device->dev); + if (!handle) + return -ENODEV; + button = devm_kzalloc(&device->dev, sizeof(*button), GFP_KERNEL); if (!button) return -ENOMEM; From ed864a7b881c82fd2ce74695afc3fccfab6fbe15 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 May 2026 17:12:40 +0200 Subject: [PATCH 1470/1518] platform/x86: hp_accel: Check ACPI_COMPANION() against NULL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit abfbe5ee8ae89f1f5449790423d5dd3e423545bd ] Every platform driver can be forced to match a device that doesn't match its list of device IDs because of device_match_driver_override(), so platform drivers that rely on the existence of a device's ACPI companion object need to verify its presence. Accordingly, add a requisite ACPI_COMPANION() check against NULL to the platform/x86 hp_accel driver. Fixes: 8ebcb6c94c71 ("platform/x86: hp_accel: Convert to be a platform driver") Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/2425918.ElGaqSPkdT@rafael.j.wysocki Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/hp/hp_accel.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/platform/x86/hp/hp_accel.c b/drivers/platform/x86/hp/hp_accel.c index 10d5af18d6398..39b73dc473f1c 100644 --- a/drivers/platform/x86/hp/hp_accel.c +++ b/drivers/platform/x86/hp/hp_accel.c @@ -300,6 +300,9 @@ static int lis3lv02d_probe(struct platform_device *device) int ret; lis3_dev.bus_priv = ACPI_COMPANION(&device->dev); + if (!lis3_dev.bus_priv) + return -ENODEV; + lis3_dev.init = lis3lv02d_acpi_init; lis3_dev.read = lis3lv02d_acpi_read; lis3_dev.write = lis3lv02d_acpi_write; From f6dfd64bfd9b20e7adda533ed3cf3bed528ae4e5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 May 2026 17:13:28 +0200 Subject: [PATCH 1471/1518] platform/x86: intel-hid: Check ACPI_HANDLE() against NULL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5c69e090ae5dd93d910f70db0796357080707d26 ] Every platform driver can be forced to match a device that doesn't match its list of device IDs because of device_match_driver_override(), so platform drivers that rely on the existence of a device's ACPI companion object need to verify its presence. Accordingly, add a requisite ACPI_HANDLE() check against NULL to the platform/x86 intel-hid driver. Fixes: ecc83e52b28c ("intel-hid: new hid event driver for hotkeys") Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/1971512.tdWV9SEqCh@rafael.j.wysocki Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/intel/hid.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index c5e80887d0cb0..f7e358be1af3a 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -682,12 +682,16 @@ static bool button_array_present(struct platform_device *device) static int intel_hid_probe(struct platform_device *device) { - acpi_handle handle = ACPI_HANDLE(&device->dev); unsigned long long mode, dummy; struct intel_hid_priv *priv; + acpi_handle handle; acpi_status status; int err; + handle = ACPI_HANDLE(&device->dev); + if (!handle) + return -ENODEV; + intel_hid_init_dsm(handle); if (!intel_hid_evaluate_method(handle, INTEL_HID_DSM_HDMM_FN, &mode)) { From 09deb063eecf43b91b04401f7452c58f1b9cd453 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 12 May 2026 17:16:22 +0200 Subject: [PATCH 1472/1518] platform/x86: intel-vbtn: Check ACPI_HANDLE() against NULL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a9f305c5a355efeb240d406d378491d9eec02d07 ] Every platform driver can be forced to match a device that doesn't match its list of device IDs because of device_match_driver_override(), so platform drivers that rely on the existence of a device's ACPI companion object need to verify its presence. Accordingly, add a requisite ACPI_HANDLE() check against NULL to the platform/x86 intel-vbtn driver. Fixes: 26173179fae1 ("platform/x86: intel-vbtn: Eval VBDL after registering our notifier") Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/3426431.aeNJFYEL58@rafael.j.wysocki Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Signed-off-by: Sasha Levin --- drivers/platform/x86/intel/vbtn.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 232cd12e3c9fa..03b5bf461a866 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -275,12 +275,16 @@ static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel) static int intel_vbtn_probe(struct platform_device *device) { - acpi_handle handle = ACPI_HANDLE(&device->dev); bool dual_accel, has_buttons, has_switches; struct intel_vbtn_priv *priv; + acpi_handle handle; acpi_status status; int err; + handle = ACPI_HANDLE(&device->dev); + if (!handle) + return -ENODEV; + dual_accel = dual_accel_detect(); has_buttons = acpi_has_method(handle, "VBDL"); has_switches = intel_vbtn_has_switches(handle, dual_accel); From d5b11e15ee676438a93a45b854a19b2177011084 Mon Sep 17 00:00:00 2001 From: Robertus Diawan Chris Date: Tue, 19 May 2026 12:40:24 +0700 Subject: [PATCH 1473/1518] ASoC: soc-utils: Add missing va_end in snd_soc_ret() [ Upstream commit 298a43b54432fbc3a32949a94c72544ee18c8c00 ] The default case in snd_soc_ret() use va_start without va_end to cleanup "args" object which can cause undefined behavior. So, add missing va_end to cleanup "args" object. This is reported by Coverity Scan as "Missing varargs init or cleanup". Fixes: 943116ba2a6a ("ASoC: add common snd_soc_ret() and use it") Signed-off-by: Robertus Diawan Chris Link: https://patch.msgid.link/20260519054024.274741-1-robertusdchris@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/soc-utils.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c index c8adfff826bd4..9cb7567e263eb 100644 --- a/sound/soc/soc-utils.c +++ b/sound/soc/soc-utils.c @@ -36,6 +36,7 @@ int snd_soc_ret(const struct device *dev, int ret, const char *fmt, ...) vaf.va = &args; dev_err(dev, "ASoC error (%d): %pV", ret, &vaf); + va_end(args); } return ret; From 8c63698737b4bdf333c3a2920f29988ee06eb19e Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Tue, 12 May 2026 02:42:09 -0700 Subject: [PATCH 1474/1518] RDMA/mana_ib: Report max_msg_sz in mana_ib_query_port [ Upstream commit c9a40f6531b81baa9619bcc2697ff86896afcce7 ] Report max_msg_sz for mana_ib, which is 16MB. Fixes: 4bda1d5332ec ("RDMA/mana_ib: Implement port parameters") Signed-off-by: Shiraz Saleem Signed-off-by: Konstantin Taranov Link: https://patch.msgid.link/20260512094209.264955-1-kotaranov@linux.microsoft.com Reviewed-by: Long Li Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mana/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c index fac159f7128d9..4143be70eea20 100644 --- a/drivers/infiniband/hw/mana/main.c +++ b/drivers/infiniband/hw/mana/main.c @@ -639,6 +639,7 @@ int mana_ib_query_port(struct ib_device *ibdev, u32 port, if (mana_ib_is_rnic(dev)) { props->gid_tbl_len = 16; props->ip_gids = true; + props->max_msg_sz = SZ_16M; if (port == 1) props->port_cap_flags = IB_PORT_CM_SUP; } From eae62c5451e67e8b033c1681fd3b85d7e9a9a28f Mon Sep 17 00:00:00 2001 From: Guangshuo Li Date: Thu, 14 May 2026 19:38:34 +0800 Subject: [PATCH 1475/1518] RDMA/rtrs: Fix use-after-free in path file creation cleanup [ Upstream commit 5b74373390113fba798a76b483837029ab010fef ] In the error path of rtrs_srv_create_path_files(), the sysfs root folders may already have been created and srv_path->kobj may already have been initialized. If a later step fails, the cleanup currently calls kobject_put(&srv_path->kobj) before rtrs_srv_destroy_once_sysfs_root_folders(srv_path). kobject_put() may drop the last reference to srv_path->kobj and invoke the release callback, rtrs_srv_release(), which frees srv_path. The following call to rtrs_srv_destroy_once_sysfs_root_folders(srv_path) then dereferences srv_path internally to access srv_path->srv, resulting in a use-after-free. This failure path is reached before rtrs_srv_create_path_files() returns success, so the successful-path lifetime handling is not involved. Fix this by destroying the sysfs root folders before calling kobject_put(&srv_path->kobj), so srv_path is still valid while the helper accesses it. This issue was found by a static analysis tool I am developing. Fixes: ae4c81644e91 ("RDMA/rtrs-srv: Rename rtrs_srv_sess to rtrs_srv_path") Signed-off-by: Guangshuo Li Link: https://patch.msgid.link/20260514113834.865530-1-lgs201920130244@gmail.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c index 3f305e694fe8c..1b1c6ea4ee5a4 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c @@ -295,8 +295,8 @@ int rtrs_srv_create_path_files(struct rtrs_srv_path *srv_path) put_kobj: kobject_del(&srv_path->kobj); destroy_root: - kobject_put(&srv_path->kobj); rtrs_srv_destroy_once_sysfs_root_folders(srv_path); + kobject_put(&srv_path->kobj); return err; } From 981aea2099770509aa41969c179afe52f87d20da Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 23 Oct 2025 16:45:37 +0200 Subject: [PATCH 1476/1518] net: bridge: Flush multicast groups when snooping is disabled [ Upstream commit 68800bbf583f26f71491141e4b3c8582f9cfcbde ] When forwarding multicast packets, the bridge takes MDB into account when IGMP / MLD snooping is enabled. Currently, when snooping is disabled, the MDB is retained, even though it is not used anymore. At the same time, during the time that snooping is disabled, the IGMP / MLD control packets are obviously ignored, and after the snooping is reenabled, the administrator has to assume it is out of sync. In particular, missed join and leave messages would lead to traffic being forwarded to wrong interfaces. Keeping the MDB entries around thus serves no purpose, and just takes memory. Note also that disabling per-VLAN snooping does actually flush the relevant MDB entries. This patch flushes non-permanent MDB entries as global snooping is disabled. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Link: https://patch.msgid.link/5e992df1bb93b88e19c0ea5819e23b669e3dde5d.1761228273.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski Stable-dep-of: 4df78ff02629 ("bridge: mcast: Fix a possible use-after-free when removing a bridge port") Signed-off-by: Sasha Levin --- net/bridge/br_multicast.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 5855eb0502085..e9a7e65304017 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4640,6 +4640,14 @@ static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, rcu_read_unlock(); } +static void br_multicast_del_grps(struct net_bridge *br) +{ + struct net_bridge_port *port; + + list_for_each_entry(port, &br->port_list, list) + __br_multicast_disable_port_ctx(&port->multicast_ctx); +} + int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { @@ -4660,6 +4668,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { change_snoopers = true; + br_multicast_del_grps(br); goto unlock; } From a9224862d597d0eed0a34bbb27343f703fc4113f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 17 May 2026 15:11:21 +0300 Subject: [PATCH 1477/1518] bridge: mcast: Fix a possible use-after-free when removing a bridge port [ Upstream commit 4df78ff02629c7729168f0696a7a2123c389818d ] When per-VLAN multicast snooping is enabled, the bridge iterates over all the bridge ports, disables the per-port multicast context on each port and enables the per-{port, VLAN} multicast contexts instead. The reverse happens when per-VLAN multicast snooping is disabled. When global multicast snooping is enabled, the bridge iterates over all the bridge ports and enables the per-port multicast context on each port. The reverse happens when multicast snooping is disabled. The above scheme can result in a situation where both types of contexts (per-port and per-{port, VLAN}) are enabled on a single bridge port: # ip link add name br1 up type bridge mcast_snooping 1 mcast_querier 1 vlan_filtering 1 # ip link add name dummy1 up master br1 type dummy # ip link set dev br1 type bridge mcast_vlan_snooping 1 # ip link set dev br1 type bridge mcast_snooping 0 # ip link set dev br1 type bridge mcast_snooping 1 This is not intended and it is a problem since the commit cited below. Prior to this commit, when removing a bridge port, br_multicast_disable_port() would disable the per-port multicast context and the per-{port, VLAN} multicast contexts would get disabled when flushing VLANs. After this commit, br_multicast_disable_port() only disables the per-port multicast context if per-VLAN multicast snooping is disabled. If both types of contexts were enabled on the port when it was removed, the per-port multicast context would remain enabled when freeing the bridge port, leading to a use-after-free [1]. Fix by preventing the bridge from enabling / disabling the per-port multicast contexts when toggling global multicast snooping if per-VLAN multicast snooping is enabled. [1] ODEBUG: free active (active state 0) object: ffff88810f8bda78 object type: timer_list hint: br_ip6_multicast_port_query_expired (net/bridge/br_multicast.c:1927) WARNING: lib/debugobjects.c:629 at debug_print_object+0x1b1/0x3e0, CPU#5: swapper/5/0 [...] Call Trace: __debug_check_no_obj_freed (lib/debugobjects.c:1116) kfree (mm/slub.c:2620 mm/slub.c:6250 mm/slub.c:6565) kobject_cleanup (lib/kobject.c:689) rcu_do_batch (kernel/rcu/tree.c:2617) rcu_core (kernel/rcu/tree.c:2869) handle_softirqs (kernel/softirq.c:622) __irq_exit_rcu (kernel/softirq.c:656 kernel/softirq.c:496 kernel/softirq.c:735) irq_exit_rcu (kernel/softirq.c:752) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1061 (discriminator 47) arch/x86/kernel/apic/apic.c:1061 (discriminator 47)) Fixes: 4b30ae9adb04 ("net: bridge: mcast: re-implement br_multicast_{enable, disable}_port functions") Reported-by: syzbot+ae231e0552fa77b26ea1@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/87qznowlfs.ffs@tglx/ Reported-by: Thomas Gleixner Acked-by: Nikolay Aleksandrov Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20260517121122.188333-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/bridge/br_multicast.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index e9a7e65304017..b77b3250afbd2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4640,10 +4640,24 @@ static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, rcu_read_unlock(); } -static void br_multicast_del_grps(struct net_bridge *br) +static void br_multicast_enable_all_ports(struct net_bridge *br) { struct net_bridge_port *port; + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return; + + list_for_each_entry(port, &br->port_list, list) + __br_multicast_enable_port_ctx(&port->multicast_ctx); +} + +static void br_multicast_disable_all_ports(struct net_bridge *br) +{ + struct net_bridge_port *port; + + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return; + list_for_each_entry(port, &br->port_list, list) __br_multicast_disable_port_ctx(&port->multicast_ctx); } @@ -4651,7 +4665,6 @@ static void br_multicast_del_grps(struct net_bridge *br) int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - struct net_bridge_port *port; bool change_snoopers = false; int err = 0; @@ -4668,7 +4681,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { change_snoopers = true; - br_multicast_del_grps(br); + br_multicast_disable_all_ports(br); goto unlock; } @@ -4676,8 +4689,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, goto unlock; br_multicast_open(br); - list_for_each_entry(port, &br->port_list, list) - __br_multicast_enable_port_ctx(&port->multicast_ctx); + br_multicast_enable_all_ports(br); change_snoopers = true; From bd731994cff13aba2a1786f5b5c2c042f6d903d1 Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Mon, 18 May 2026 10:23:09 +0200 Subject: [PATCH 1478/1518] net: phy: honor eee_disabled_modes in phy_support_eee() [ Upstream commit 3655063e083889ed4b79b7dda9cec65478dce09a ] phy_support_eee() copies supported_eee into advertising_eee unconditionally, overwriting any filtering applied during phy_probe() based on DT eee-broken-* properties or driver-populated eee_disabled_modes. MAC drivers that call phy_support_eee() after probe (e.g. bcmgenet, fec, lan743x, lan78xx, r8169) then cause the PHY to advertise EEE for modes the user marked as broken. The symptom is that ethtool --show-eee on the local interface reports "not supported" (supported & ~eee_disabled_modes is empty) while the link partner sees EEE negotiated and active. phy_probe() already filters advertising_eee via eee_disabled_modes after calling of_set_phy_eee_broken(). Apply the same mask in phy_support_eee() so the filtering survives the copy. Fixes: 49168d1980e2 ("net: phy: Add phy_support_eee() indicating MAC support EEE") Signed-off-by: Nicolai Buchwitz Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260518-devel-phy-support-eee-fix-v2-1-05b52626fa68@tipi-net.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/phy_device.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index dea8b94286d15..5d76bd1ffe279 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2818,7 +2818,8 @@ EXPORT_SYMBOL_GPL(phy_advertise_eee_all); */ void phy_support_eee(struct phy_device *phydev) { - linkmode_copy(phydev->advertising_eee, phydev->supported_eee); + linkmode_andnot(phydev->advertising_eee, phydev->supported_eee, + phydev->eee_disabled_modes); phydev->eee_cfg.tx_lpi_enabled = true; phydev->eee_cfg.eee_enabled = true; } From 0c277d203684c27bff62d6bd997a9fd77c88884f Mon Sep 17 00:00:00 2001 From: Nicolai Buchwitz Date: Mon, 18 May 2026 10:23:10 +0200 Subject: [PATCH 1479/1518] net: phy: honor eee_disabled_modes in phy_advertise_eee_all() [ Upstream commit 8baa7506d793f0636e3f6f01b01ef7be19674d06 ] phy_advertise_eee_all() copies supported_eee into advertising_eee unconditionally, overwriting any filtering applied during phy_probe() based on DT eee-broken-* properties or driver-populated eee_disabled_modes. genphy_c45_ethtool_set_eee() calls this helper when user space passes an empty advertisement, undoing the filtering. Apply the same eee_disabled_modes mask in phy_advertise_eee_all() so the filtering survives the copy, matching the pattern in phy_probe() and phy_support_eee(). Fixes: b64691274f5d ("net: phy: add helper phy_advertise_eee_all") Signed-off-by: Nicolai Buchwitz Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260518-devel-phy-support-eee-fix-v2-2-05b52626fa68@tipi-net.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/phy_device.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5d76bd1ffe279..78cf05a17f8ff 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2792,7 +2792,8 @@ EXPORT_SYMBOL(phy_advertise_supported); */ void phy_advertise_eee_all(struct phy_device *phydev) { - linkmode_copy(phydev->advertising_eee, phydev->supported_eee); + linkmode_andnot(phydev->advertising_eee, phydev->supported_eee, + phydev->eee_disabled_modes); } EXPORT_SYMBOL_GPL(phy_advertise_eee_all); From ce23832071aff284dc928775c0f8042c50b35cba Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 18 May 2026 15:44:57 +0200 Subject: [PATCH 1480/1518] net: airoha: Fix NPU RX DMA descriptor bits [ Upstream commit 0cb5a74faa3bdcfa3b18735d554e12c0f615e35d ] In an internal review from Airoha, it was notice that the RX DMA descriptor bits and mask are wrong. These values probably refer to an old NPU firmware never published. The previous value works correctly but it was reported that in some specific condition in mixed scenario with both Ethernet and WiFi offload it's possible that RX DMA descriptor signal wrong value with the problem to the RX ring or packets getting dropped. To handle these specific scenario, apply the new suggested bits mask from Airoha. Correct functionality of both AN7581 NPU and MT7996 variant were verified and confirmed working. Fixes: a7fc8c641cab ("net: airoha: Fix npu rx DMA definitions") Signed-off-by: Christian Marangi Acked-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260518134530.3683-1-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/linux/soc/airoha/airoha_offload.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h index 0e82f1f4d36c4..d4f6e8124a493 100644 --- a/include/linux/soc/airoha/airoha_offload.h +++ b/include/linux/soc/airoha/airoha_offload.h @@ -70,9 +70,9 @@ static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, #define NPU_RX1_DESC_NUM 512 /* CTRL */ -#define NPU_RX_DMA_DESC_LAST_MASK BIT(27) -#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(26, 14) -#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(13, 1) +#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) #define NPU_RX_DMA_DESC_DONE_MASK BIT(0) /* INFO */ #define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 29) From 784dd2bdc622ed3cc6ef8e113aa1852e252de36f Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Fri, 15 May 2026 21:29:05 +0000 Subject: [PATCH 1481/1518] pds_core: fix error handling in pdsc_devcmd_wait [ Upstream commit 0e46b6635b03d29807f810c3b415c4755a3f958d ] Fix two cases where pdsc_devcmd_wait() returns stale success from the completion register instead of an error: 1. FW crash: If firmware stops running, the wait loop breaks early with running=false. The condition "if ((!done || timeout) && running)" is false, so error handling is bypassed and stale status is returned. Check !running first and return -ENXIO. 2. Timeout: If a command times out, err is set to -ETIMEDOUT but then overwritten by pdsc_err_to_errno(status) which reads stale status. Return -ETIMEDOUT immediately after cleaning up. Both errors now propagate to pdsc_devcmd_locked() which queues health_work for recovery. Fixes: 45d76f492938 ("pds_core: set up device and adminq") Signed-off-by: Nikhil P. Rao Link: https://patch.msgid.link/20260515212907.998028-1-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/pds_core/dev.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index 495ef4ef8c103..1d1e559bd99d3 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -162,12 +162,19 @@ static int pdsc_devcmd_wait(struct pdsc *pdsc, u8 opcode, int max_seconds) dev_dbg(dev, "DEVCMD %d %s after %ld secs\n", opcode, pdsc_devcmd_str(opcode), duration / HZ); - if ((!done || timeout) && running) { + if (!running) { + dev_err(dev, "DEVCMD %d %s fw not running\n", + opcode, pdsc_devcmd_str(opcode)); + pdsc_devcmd_clean(pdsc); + return -ENXIO; + } + + if (!done || timeout) { dev_err(dev, "DEVCMD %d %s timeout, done %d timeout %d max_seconds=%d\n", opcode, pdsc_devcmd_str(opcode), done, timeout, max_seconds); - err = -ETIMEDOUT; pdsc_devcmd_clean(pdsc); + return -ETIMEDOUT; } status = pdsc_devcmd_status(pdsc); From 91d13e92b983e6c6d7631012c2e20ae8057de9f2 Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Fri, 15 May 2026 21:29:07 +0000 Subject: [PATCH 1482/1518] pds_core: fix debugfs_lookup dentry leak and error handling [ Upstream commit dc416e32baaeb620b9809e9e25fc7b30889686e9 ] debugfs_lookup() returns a dentry with an elevated reference count that must be released with dput(). The current code discards the returned dentry without calling dput(), causing a reference leak on every firmware reset recovery. Additionally, when CONFIG_DEBUG_FS is disabled, debugfs_lookup() returns ERR_PTR(-ENODEV), not NULL. The current check passes for error pointers and would call dput() on an invalid pointer, causing a crash. Fixes: bc90fbe0c318 ("pds_core: Rework teardown/setup flow to be more common") Signed-off-by: Nikhil P. Rao Link: https://patch.msgid.link/20260515212907.998028-3-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/pds_core/debugfs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c index 04c5e3abd8d70..810a0cd9bcac8 100644 --- a/drivers/net/ethernet/amd/pds_core/debugfs.c +++ b/drivers/net/ethernet/amd/pds_core/debugfs.c @@ -64,9 +64,14 @@ DEFINE_SHOW_ATTRIBUTE(identity); void pdsc_debugfs_add_ident(struct pdsc *pdsc) { + struct dentry *dentry; + /* This file will already exist in the reset flow */ - if (debugfs_lookup("identity", pdsc->dentry)) + dentry = debugfs_lookup("identity", pdsc->dentry); + if (!IS_ERR_OR_NULL(dentry)) { + dput(dentry); return; + } debugfs_create_file("identity", 0400, pdsc->dentry, pdsc, &identity_fops); From 425d32d6288d7d845e486af9419bbedccd8c9103 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 28 Apr 2026 12:34:31 +0800 Subject: [PATCH 1483/1518] erofs: fix managed cache race for unaligned extents [ Upstream commit 649932fc3815eda2f24eb4de4b3a5e94886ee0b9 ] After unaligned compressed extents were introduced, the following race could occur: [Thread 1] [Thread 2] (z_erofs_fill_bio_vec) ... filemap_add_folio (1) (z_erofs_bind_cache) .. .. folio_attach_private (2) filemap_add_folio (3) again Since (1) is executed but (2) hasn't been executed yet, it's possible that another thread finds the same managed folio in z_erofs_bind_cache() for a different pcluster and calls filemap_add_folio() again since folio->private is still Z_EROFS_PREALLOCATED_FOLIO. Fix this by explicitly clearing folio->private before making the folio visible in the managed cache so that another pcluster can simply wait on the locked managed folio as what we did for other shared cases [1]. This only impacts unaligned data compression (`-E48bit` with zstd, for example). [1] Commit 9e2f9d34dd12 ("erofs: handle overlapped pclusters out of crafted images properly") was originally introduced to handle crafted overlapped extents, but it addresses unaligned extents as well. Fixes: 7361d1e3763b ("erofs: support unaligned encoded data") Reported-by: Arseniy Krasnov Closes: https://lore.kernel.org/r/4a2f3801-fac1-42fe-ae75-da315822e088@salutedevices.com Tested-by: Arseniy Krasnov Signed-off-by: Gao Xiang Signed-off-by: Sasha Levin --- fs/erofs/zdata.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 71f01f0a07435..33932d56d3a46 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1511,8 +1511,15 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec, DBG_BUGON(z_erofs_is_shortlived_page(bvec->bv_page)); folio = page_folio(zbv.page); - /* For preallocated managed folios, add them to page cache here */ + /* + * Preallocated folios are added to the managed cache here rather than + * in z_erofs_bind_cache() in order to keep these folios locked in + * increasing (physical) address order. + * Clear folio->private before these folios become visible to others in + * the managed cache to avoid duplicate additions for unaligned extents. + */ if (folio->private == Z_EROFS_PREALLOCATED_FOLIO) { + folio->private = NULL; tocache = true; goto out_tocache; } @@ -1548,14 +1555,8 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec, } return; } - /* - * Already linked with another pcluster, which only appears in - * crafted images by fuzzers for now. But handle this anyway. - */ - tocache = false; /* use temporary short-lived pages */ } else { DBG_BUGON(1); /* referenced managed folios can't be truncated */ - tocache = true; } folio_unlock(folio); folio_put(folio); From 2d8379834800c30602f24c71ab7c40f5fe84d200 Mon Sep 17 00:00:00 2001 From: Alexandru Hossu Date: Fri, 15 May 2026 12:29:08 +0200 Subject: [PATCH 1484/1518] wifi: mac80211: bounds-check link_id in ieee80211_ml_epcs [ Upstream commit f718506edd2d9c6a308ded9d13c632bf7b7d5a2c ] IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID is 0x000f, so link_id extracted from a PRIO_ACCESS ML element PER_STA_PROFILE subelement can be 0..15. sdata->link[] has IEEE80211_MLD_MAX_NUM_LINKS (15) entries (indices 0..14), making index 15 out-of-bounds. A connected WiFi 7 AP can trigger this by sending an EPCS Enable Response action frame with a PER_STA_PROFILE subelement where link_id = 15. The unsolicited-notification path (dialog_token = 0) is reachable any time EPCS is already enabled, without any prior client request. sdata->link[15] reads into the first word of sdata->activate_links_work (a wiphy_work whose embedded list_head is non-NULL after INIT_LIST_HEAD), so the NULL check on the result does not catch the invalid access. The garbage pointer is then passed to ieee80211_sta_wmm_params(), which dereferences link->sdata and crashes the kernel. The same class of bug was fixed for ieee80211_ml_reconfiguration() by commit 162d331d833d ("wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration"). Fixes: de86c5f60839 ("wifi: mac80211: Add support for EPCS configuration") Signed-off-by: Alexandru Hossu Link: https://patch.msgid.link/20260515102908.1653088-1-hossu.alexandru@gmail.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/mlme.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ce247dde048c0..5d1da779cd6f2 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -10997,6 +10997,9 @@ static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata, control = get_unaligned_le16(pos); link_id = control & IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID; + if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + continue; + link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; From 55c479aae99b120489a432db9c717484e523dfd6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 8 May 2026 09:10:31 +0200 Subject: [PATCH 1485/1518] wifi: mac80211: fix MLE defragmentation [ Upstream commit a74e893f30db64cdce0fc7a96d3baa417bcd55f5 ] If either reconf or EPCS multi-link element (MLE) is contained in a non-transmitted profile, the defragmentation routine is called with a pointer to the defragmented copy, but the original elements. This is incorrect for two reasons: - if the original defragmentation was needed, it will not find the correct data - if the original frame is at a higher address, the parsing will potentially overrun the heap data (though given the layout of the buffers, only into the new defragmentation buffer, and then it has to stop and fail once that's filled with copied data. Fix it by tracking the container along with the pointer and in doing so also unify the two almost identical defragmentation routines. Fixes: 4d70e9c5488d ("wifi: mac80211: defragment reconfiguration MLE when parsing") Reviewed-by: Miriam Rachel Korenblit Reviewed-by: Ilan Peer Link: https://patch.msgid.link/20260508091031.8a6c34613178.I4de16ebbce2d27f2f8f98fc49949c7a376c2fe8d@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/parse.c | 71 +++++++++++++++++++------------------------- 1 file changed, 31 insertions(+), 40 deletions(-) diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index c5e0f7f460048..b9ec99f51851a 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -34,6 +34,13 @@ #include "led.h" #include "wep.h" +struct ieee80211_elem_defrag { + const struct element *elem; + /* container start/len */ + const u8 *start; + size_t len; +}; + struct ieee80211_elems_parse { /* must be first for kfree to work */ struct ieee802_11_elems elems; @@ -41,11 +48,7 @@ struct ieee80211_elems_parse { /* The basic Multi-Link element in the original elements */ const struct element *ml_basic_elem; - /* The reconfiguration Multi-Link element in the original elements */ - const struct element *ml_reconf_elem; - - /* The EPCS Multi-Link element in the original elements */ - const struct element *ml_epcs_elem; + struct ieee80211_elem_defrag ml_reconf, ml_epcs; bool multi_link_inner; bool skip_vendor; @@ -162,10 +165,14 @@ ieee80211_parse_extension_element(u32 *crc, } break; case IEEE80211_ML_CONTROL_TYPE_RECONF: - elems_parse->ml_reconf_elem = elem; + elems_parse->ml_reconf.elem = elem; + elems_parse->ml_reconf.start = params->start; + elems_parse->ml_reconf.len = params->len; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - elems_parse->ml_epcs_elem = elem; + elems_parse->ml_epcs.elem = elem; + elems_parse->ml_epcs.start = params->start; + elems_parse->ml_epcs.len = params->len; break; default: break; @@ -950,46 +957,27 @@ ieee80211_prep_mle_link_parse(struct ieee80211_elems_parse *elems_parse, sub->start, sub->len); } -static void -ieee80211_mle_defrag_reconf(struct ieee80211_elems_parse *elems_parse) -{ - struct ieee802_11_elems *elems = &elems_parse->elems; - ssize_t ml_len; - - ml_len = cfg80211_defragment_element(elems_parse->ml_reconf_elem, - elems->ie_start, - elems->total_len, - elems_parse->scratch_pos, - elems_parse->scratch + - elems_parse->scratch_len - - elems_parse->scratch_pos, - WLAN_EID_FRAGMENT); - if (ml_len < 0) - return; - elems->ml_reconf = (void *)elems_parse->scratch_pos; - elems->ml_reconf_len = ml_len; - elems_parse->scratch_pos += ml_len; -} - -static void -ieee80211_mle_defrag_epcs(struct ieee80211_elems_parse *elems_parse) +static const void * +ieee80211_mle_defrag(struct ieee80211_elems_parse *elems_parse, + struct ieee80211_elem_defrag *defrag, + size_t *out_len) { - struct ieee802_11_elems *elems = &elems_parse->elems; + const void *ret; ssize_t ml_len; - ml_len = cfg80211_defragment_element(elems_parse->ml_epcs_elem, - elems->ie_start, - elems->total_len, + ml_len = cfg80211_defragment_element(defrag->elem, + defrag->start, defrag->len, elems_parse->scratch_pos, elems_parse->scratch + elems_parse->scratch_len - elems_parse->scratch_pos, WLAN_EID_FRAGMENT); if (ml_len < 0) - return; - elems->ml_epcs = (void *)elems_parse->scratch_pos; - elems->ml_epcs_len = ml_len; + return NULL; + ret = elems_parse->scratch_pos; + *out_len = ml_len; elems_parse->scratch_pos += ml_len; + return ret; } struct ieee802_11_elems * @@ -1069,9 +1057,12 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) _ieee802_11_parse_elems_full(&sub, elems_parse, NULL); } - ieee80211_mle_defrag_reconf(elems_parse); - - ieee80211_mle_defrag_epcs(elems_parse); + elems->ml_reconf = ieee80211_mle_defrag(elems_parse, + &elems_parse->ml_reconf, + &elems->ml_reconf_len); + elems->ml_epcs = ieee80211_mle_defrag(elems_parse, + &elems_parse->ml_epcs, + &elems->ml_epcs_len); if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; From 95c82d498d74c4e587db30021ca1aec90e29b5a5 Mon Sep 17 00:00:00 2001 From: Shitalkumar Gandhi Date: Mon, 11 May 2026 09:57:32 +0530 Subject: [PATCH 1486/1518] wifi: wilc1000: fix dma_buffer leak on bus acquire failure [ Upstream commit dd7b6a8671939708cc4b7a46786d8c11297e8f69 ] wilc_wlan_firmware_download() allocates dma_buffer with kmalloc() at the top of the function and uses a 'fail:' label to free it via kfree(dma_buffer) on error. All later error paths correctly use 'goto fail' to route through this cleanup. However, the early failure path after the first acquire_bus() call uses a bare 'return ret;', which leaks dma_buffer whenever the bus acquire fails. Replace the early return with goto fail so the existing cleanup path runs. Found via a custom Coccinelle semantic patch hunting for kmalloc'd locals leaked on early-return error paths in driver firmware-download code. Fixes: 1241c5650ff7 ("wifi: wilc1000: Fill in missing error handling") Signed-off-by: Shitalkumar Gandhi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260511042732.998311-1-shitalkumar.gandhi@cambiumnetworks.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/microchip/wilc1000/wlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c index fedc7d59216ad..1cc4ee62987d4 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan.c +++ b/drivers/net/wireless/microchip/wilc1000/wlan.c @@ -1265,7 +1265,7 @@ int wilc_wlan_firmware_download(struct wilc *wilc, const u8 *buffer, ret = acquire_bus(wilc, WILC_BUS_ACQUIRE_AND_WAKEUP); if (ret) - return ret; + goto fail; wilc->hif_func->hif_read_reg(wilc, WILC_GLB_RESET_0, ®); reg &= ~BIT(10); From 3aab4a58d23fb22dac5b558bbe5df1a8dad00b4b Mon Sep 17 00:00:00 2001 From: Zhang Cen Date: Wed, 20 May 2026 18:32:49 +0800 Subject: [PATCH 1487/1518] ALSA: seq: Serialize UMP output teardown with event_input [ Upstream commit 60a1969fae6209644698fca91c185d153674f631 ] seq_ump_process_event() borrows client->out_rfile.output without synchronizing with the first-open and last-close transition in seq_ump_client_open() and seq_ump_client_close(). The last output unuse can therefore drop opened[STR_OUT] to zero and release the rawmidi file while an in-flight event_input callback is still inside snd_rawmidi_kernel_write(). That leaves the rawmidi substream runtime exposed to teardown before the write path has taken its own buffer reference. Add a per-client rwlock for the event_input-visible output file. Publish a newly opened output file under the write side, and hold the read side from the output lookup through snd_rawmidi_kernel_write(). The last output close copies and clears the visible output file under the write side, then drops the lock and releases the saved rawmidi file. Use IRQ-safe rwlock guards because event_input can also be reached from atomic sequencer delivery. The buggy scenario involves two paths, with each column showing the order within that path: path A label: event_input path path B label: last unuse path 1. seq_ump_process_event() reads 1. seq_ump_client_close() client->out_rfile.output. drops opened[STR_OUT] to zero. 2. snd_rawmidi_kernel_write1() 2. snd_rawmidi_kernel_release() has not yet pinned runtime. closes the output file. 3. The writer continues using 3. close_substream() frees the borrowed substream. substream->runtime. This keeps the output substream and runtime alive for the full event_input write while keeping rawmidi release outside the rwlock. KASAN reproduced this as a slab-use-after-free in snd_rawmidi_kernel_write1(), with allocation through seq_ump_use()/snd_seq_port_connect() and free through seq_ump_unuse()/snd_seq_port_disconnect(). Suggested-by: Takashi Iwai Validation reproduced this kernel report: KASAN slab-use-after-free in snd_rawmidi_kernel_write1+0x9d/0x400 RIP: 0033:0x7f5528af837f Read of size 8 Call trace: dump_stack_lvl+0x73/0xb0 (?:?) print_report+0xd1/0x650 (?:?) srso_alias_return_thunk+0x5/0xfbef5 (?:?) __virt_addr_valid+0x1a7/0x340 (?:?) kasan_complete_mode_report_info+0x64/0x200 (?:?) kasan_report+0xf7/0x130 (?:?) snd_rawmidi_kernel_write1+0x9d/0x400 (?:?) __asan_load8+0x82/0xb0 (?:?) update_stack_state+0x1ef/0x2d0 (?:?) snd_rawmidi_kernel_write+0x1a/0x20 (?:?) seq_ump_process_event+0xd4/0x120 (sound/core/seq/seq_ump_client.c:82) __snd_seq_deliver_single_event+0x8a/0xe0 (?:?) snd_seq_deliver_from_ump+0x2b2/0xd60 (?:?) lock_acquire+0x14e/0x2e0 (?:?) find_held_lock+0x31/0x90 (?:?) snd_seq_port_use_ptr+0xa6/0xe0 (?:?) __kasan_check_write+0x18/0x20 (?:?) do_raw_read_unlock+0x32/0xa0 (?:?) _raw_read_unlock+0x26/0x50 (?:?) snd_seq_deliver_single_event+0x45c/0x4b0 (?:?) snd_seq_deliver_event+0x10d/0x1b0 (?:?) snd_seq_client_enqueue_event+0x192/0x240 (?:?) snd_seq_write+0x2cd/0x450 (?:?) apparmor_file_permission+0x20/0x30 (?:?) security_file_permission+0x51/0x60 (?:?) vfs_write+0x1ce/0x850 (?:?) __fget_files+0x12b/0x220 (?:?) lock_release+0xc8/0x2a0 (?:?) __rcu_read_unlock+0x74/0x2d0 (?:?) __fget_files+0x135/0x220 (?:?) ksys_write+0x15a/0x180 (?:?) rcu_is_watching+0x24/0x60 (?:?) __x64_sys_write+0x46/0x60 (?:?) x64_sys_call+0x7d/0x20d0 (?:?) do_syscall_64+0xc1/0x360 (arch/x86/entry/syscall_64.c:87) entry_SYSCALL_64_after_hwframe+0x77/0x7f (?:?) Fixes: 81fd444aa371 ("ALSA: seq: Bind UMP device") Signed-off-by: Zhang Cen Link: https://patch.msgid.link/20260520103249.3048345-1-rollkingzzc@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/core/seq/seq_ump_client.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c index ebbe1cbe0b9b7..9a6b4b61bd74c 100644 --- a/sound/core/seq/seq_ump_client.c +++ b/sound/core/seq/seq_ump_client.c @@ -37,6 +37,7 @@ struct seq_ump_client { struct snd_ump_endpoint *ump; /* assigned endpoint */ int seq_client; /* sequencer client id */ int opened[2]; /* current opens for each direction */ + rwlock_t output_lock; /* protects out_rfile output access */ struct snd_rawmidi_file out_rfile; /* rawmidi for output */ struct seq_ump_input_buffer input; /* input parser context */ void *ump_info[SNDRV_UMP_MAX_BLOCKS + 1]; /* shadow of seq client ump_info */ @@ -88,6 +89,7 @@ static int seq_ump_process_event(struct snd_seq_event *ev, int direct, unsigned char type; int len; + guard(read_lock_irqsave)(&client->output_lock); substream = client->out_rfile.output; if (!substream) return -ENODEV; @@ -106,6 +108,7 @@ static int seq_ump_process_event(struct snd_seq_event *ev, int direct, static int seq_ump_client_open(struct seq_ump_client *client, int dir) { struct snd_ump_endpoint *ump = client->ump; + struct snd_rawmidi_file rfile = {}; int err; guard(mutex)(&ump->open_mutex); @@ -113,9 +116,11 @@ static int seq_ump_client_open(struct seq_ump_client *client, int dir) err = snd_rawmidi_kernel_open(&ump->core, 0, SNDRV_RAWMIDI_LFLG_OUTPUT | SNDRV_RAWMIDI_LFLG_APPEND, - &client->out_rfile); + &rfile); if (err < 0) return err; + scoped_guard(write_lock_irqsave, &client->output_lock) + client->out_rfile = rfile; } client->opened[dir]++; return 0; @@ -125,11 +130,19 @@ static int seq_ump_client_open(struct seq_ump_client *client, int dir) static int seq_ump_client_close(struct seq_ump_client *client, int dir) { struct snd_ump_endpoint *ump = client->ump; + struct snd_rawmidi_file rfile = {}; guard(mutex)(&ump->open_mutex); - if (!--client->opened[dir]) - if (dir == STR_OUT) - snd_rawmidi_kernel_release(&client->out_rfile); + if (!--client->opened[dir]) { + if (dir == STR_OUT) { + scoped_guard(write_lock_irqsave, &client->output_lock) { + rfile = client->out_rfile; + client->out_rfile = (struct snd_rawmidi_file){}; + } + if (rfile.rmidi) + snd_rawmidi_kernel_release(&rfile); + } + } return 0; } @@ -468,6 +481,7 @@ static int snd_seq_ump_probe(struct device *_dev) INIT_WORK(&client->group_notify_work, handle_group_notify); client->ump = ump; + rwlock_init(&client->output_lock); client->seq_client = snd_seq_create_kernel_client(card, ump->core.device, From 8bf00d3ac425ac0df1c0b2a82e32cdd9789964c3 Mon Sep 17 00:00:00 2001 From: Cunlong Li Date: Wed, 20 May 2026 11:30:54 +0800 Subject: [PATCH 1488/1518] cgroup: rstat: relax NMI guard after switch to try_cmpxchg [ Upstream commit 22572dbcd3486e6c4dced877125bbf50e4e24edf ] Commit 36df6e3dbd7e ("cgroup: make css_rstat_updated nmi safe") used this_cpu_cmpxchg() for the lockless insertion, and therefore required both ARCH_HAVE_NMI_SAFE_CMPXCHG and ARCH_HAS_NMI_SAFE_THIS_CPU_OPS in the NMI guard: on archs without the latter, this_cpu_cmpxchg() falls back to "local_irq_save() + plain cmpxchg", and local_irq_save() cannot mask NMIs. Commit 3309b63a2281 ("cgroup: rstat: use LOCK CMPXCHG in css_rstat_updated") later replaced this_cpu_cmpxchg() with plain try_cmpxchg() to fix cross-CPU lockless-list corruption, but left the NMI guard untouched. After that switch, css_rstat_updated() no longer performs any this_cpu_*() RMW operations and only relies on the arch having NMI-safe cmpxchg, so ARCH_HAS_NMI_SAFE_THIS_CPU_OPS is no longer required in the guard. Relax the guard accordingly so that archs which have HAVE_NMI and ARCH_HAVE_NMI_SAFE_CMPXCHG but not ARCH_HAS_NMI_SAFE_THIS_CPU_OPS (e.g. sparc, powerpc on PPC64/BOOK3S) can benefit from the existing CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC path. Without this, the css is never queued in NMI on those archs, and the atomics staged by account_{slab,kmem}_nmi_safe() are not drained by flush_nmi_stats(). Fixes: 3309b63a2281 ("cgroup: rstat: use LOCK CMPXCHG in css_rstat_updated") Signed-off-by: Cunlong Li Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/cgroup/rstat.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index ed60ba119c687..de816a43db9f0 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -81,11 +81,10 @@ void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu) lockdep_assert_preemption_disabled(); /* - * For archs withnot nmi safe cmpxchg or percpu ops support, ignore - * the requests from nmi context. + * The lockless insertion below relies on NMI-safe cmpxchg; + * bail out in NMI on archs that don't provide it. */ - if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || - !IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi()) + if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && in_nmi()) return; rstatc = css_rstat_cpu(css, cpu); From d6c8b3ebdcdb12b59ad4212acb137cc56cae453d Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 8 May 2026 20:57:47 +0100 Subject: [PATCH 1489/1518] tracing: Avoid NULL return from hist_field_name() on truncation [ Upstream commit 576ec047d20b368b43c4d5db98c4f2e0f3c101ec ] hist_field_name() returns "" everywhere except the fully-qualified VAR_REF/EXPR case, where snprintf() truncation returns NULL early and bypasses the bottom NULL->"" guard. Callers don't expect NULL: strcat(expr, hist_field_name(field, 0)) at trace_events_hist.c:1758 and the strcmp() in the sort-key match loop at :4804 both deref it. system and event_name are bounded by MAX_EVENT_NAME_LEN, but the field name on a VAR_REF is kstrdup'd from a histogram variable name parsed out of the trigger string and has no length cap, so a long enough var name in a fully qualified reference can reach the truncation path. Keep the length check but leave field_name as "" on overflow. Link: https://patch.msgid.link/20260508195747.25492-1-devnexen@gmail.com Fixes: 5ec1d1e97de1 ("tracing: Rebuild full_name on each hist_field_name() call") Signed-off-by: David Carlier Signed-off-by: Steven Rostedt Signed-off-by: Sasha Levin --- kernel/trace/trace_events_hist.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index cb9e067138683..0089c257b465f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1360,10 +1360,8 @@ static const char *hist_field_name(struct hist_field *field, len = snprintf(full_name, sizeof(full_name), "%s.%s.%s", field->system, field->event_name, field->name); - if (len >= sizeof(full_name)) - return NULL; - - field_name = full_name; + if (len < sizeof(full_name)) + field_name = full_name; } else field_name = field->name; } else if (field->flags & HIST_FIELD_FL_TIMESTAMP) From c7860b6a6d2d69d18566f10dfa8751c874b23ef1 Mon Sep 17 00:00:00 2001 From: Kiran K Date: Fri, 15 May 2026 00:32:48 +0530 Subject: [PATCH 1490/1518] Bluetooth: btintel_pcie: Fix incorrect MAC access programming [ Upstream commit 88365d04fdc821dc4e9eb0cc00fdf6905430d172 ] btintel_pcie_get_mac_access() and btintel_pcie_release_mac_access() were programming STOP_MAC_ACCESS_DIS and XTAL_CLK_REQ in addition to the MAC_ACCESS_REQ handshake. These bits are not part of the host MAC-access handshake on the supported parts; the driver was programming them incorrectly. Drop the writes so the register update contains only the bits the controller actually consumes. Fixes: b9465e6670a2 ("Bluetooth: btintel_pcie: Read hardware exception data") Signed-off-by: Kiran K Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btintel_pcie.c | 20 ++++++-------------- drivers/bluetooth/btintel_pcie.h | 3 --- 2 files changed, 6 insertions(+), 17 deletions(-) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index c68a8de3025b0..d0aa1666d6ac6 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -567,12 +567,10 @@ static int btintel_pcie_get_mac_access(struct btintel_pcie_data *data) reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG); - reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS; - reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ; - if ((reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS) == 0) + if (!(reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ)) { reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ; - - btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + } do { reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG); @@ -592,16 +590,10 @@ static void btintel_pcie_release_mac_access(struct btintel_pcie_data *data) reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG); - if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ) + if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ) { reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ; - - if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS) - reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS; - - if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ) - reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ; - - btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + } } static void *btintel_pcie_copy_tlv(void *dest, enum btintel_pcie_tlv_type type, diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h index 48e1ae1793e5c..481de85456e2b 100644 --- a/drivers/bluetooth/btintel_pcie.h +++ b/drivers/bluetooth/btintel_pcie.h @@ -34,9 +34,6 @@ #define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS (BIT(20)) #define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ (BIT(21)) -/* Stop MAC Access disconnection request */ -#define BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS (BIT(22)) -#define BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ (BIT(23)) #define BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_STS (BIT(28)) #define BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_DISCON (BIT(29)) From a0f5268c77eb73f84ba7c210ddfc54b1c73ff80c Mon Sep 17 00:00:00 2001 From: Jiajia Liu Date: Mon, 18 May 2026 10:24:02 +0800 Subject: [PATCH 1491/1518] Bluetooth: btmtk: fix urb->setup_packet leak in error paths [ Upstream commit dd1dda6b8d6e1f4376a5b3055a04f0ecbdb4d6bd ] The setup_packet of control urb is not freed if usb_submit_urb fails or the submitted urb is killed. Add free in these two paths. Fixes: a1c49c434e150 ("Bluetooth: btusb: Add protocol support for MediaTek MT7668U USB devices") Signed-off-by: Jiajia Liu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btmtk.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index cf05746e9db5a..38ba8f2bd2f96 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -496,6 +496,7 @@ static void btmtk_usb_wmt_recv(struct urb *urb) return; } else if (urb->status == -ENOENT) { /* Avoid suspend failed when usb_kill_urb */ + kfree(urb->setup_packet); return; } @@ -569,6 +570,7 @@ static int btmtk_usb_submit_wmt_recv_urb(struct hci_dev *hdev) if (err != -EPERM && err != -ENODEV) bt_dev_err(hdev, "urb %p submission failed (%d)", urb, -err); + kfree(dr); usb_unanchor_urb(urb); } From b5bd4249e430f5963d559708ee96a671716d2400 Mon Sep 17 00:00:00 2001 From: Prathamesh Deshpande Date: Sun, 10 May 2026 23:59:00 +0100 Subject: [PATCH 1492/1518] net/mlx5e: Fix eswitch mode block underflow on IPsec acquire SA [ Upstream commit abe003b33223ff33552f291644bf35d9c2f992fb ] mlx5e_xfrm_add_state() handles acquire-flow temporary SAs by allocating software state and skipping hardware offload setup. That path jumps to the common success label before taking the eswitch mode block. After tunnel-mode validation was moved earlier, the common success label unconditionally calls mlx5_eswitch_unblock_mode(). For acquire SAs, this decrements esw->offloads.num_block_mode without a matching increment. Return directly after installing the acquire SA offload handle, so only the paths that successfully called mlx5_eswitch_block_mode() call the matching unblock. Fixes: 22239eb258bc ("net/mlx5e: Prevent tunnel reformat when tunnel mode not allowed") Signed-off-by: Prathamesh Deshpande Reviewed-by: Simon Horman Reviewed-by: Tariq Toukan Link: https://patch.msgid.link/20260510225903.13184-1-prathameshdeshpande7@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index f03507a522b4f..51fb857a27665 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -794,8 +794,10 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, sa_entry->dev = dev; sa_entry->ipsec = ipsec; /* Check if this SA is originated from acquire flow temporary SA */ - if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) - goto out; + if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) { + x->xso.offload_handle = (unsigned long)sa_entry; + return 0; + } err = mlx5e_xfrm_validate_state(priv->mdev, x, extack); if (err) @@ -872,7 +874,6 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, xa_unlock_bh(&ipsec->sadb); } -out: x->xso.offload_handle = (unsigned long)sa_entry; if (allow_tunnel_mode) mlx5_eswitch_unblock_encap(priv->mdev); From 5a2c2aa139c8da2dcda0bd24d415fa7471bf693b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 15 May 2026 15:13:24 -0700 Subject: [PATCH 1493/1518] net: shaper: annotate the data races [ Upstream commit a3442936dd0523277e20aaf86207c574e755c634 ] As previously discussed we don't care about making the shaper state fully RCU-compliant because the hierarchy itself can't be dumped in one go over Netlink. Let's annotate the reads and writes to make that clear. The field-by-field assignments will also be useful for the next commit which adds explicit "valid" field (which we don't want to override with the current full struct assignment). Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260515221325.1685455-2-kuba@kernel.org Signed-off-by: Jakub Kicinski Stable-dep-of: b8d7519352ba ("net: shaper: rework the VALID marking (again)") Signed-off-by: Sasha Levin --- net/shaper/shaper.c | 53 ++++++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 15 deletions(-) diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index fa85200252827..a28096b150b35 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -136,35 +136,58 @@ static int net_shaper_fill_handle(struct sk_buff *msg, return -EMSGSIZE; } +static void net_shaper_copy(struct net_shaper *dst, + const struct net_shaper *src) +{ + WRITE_ONCE(dst->parent.scope, READ_ONCE(src->parent.scope)); + WRITE_ONCE(dst->parent.id, READ_ONCE(src->parent.id)); + WRITE_ONCE(dst->handle.scope, READ_ONCE(src->handle.scope)); + WRITE_ONCE(dst->handle.id, READ_ONCE(src->handle.id)); + + WRITE_ONCE(dst->metric, READ_ONCE(src->metric)); + WRITE_ONCE(dst->bw_min, READ_ONCE(src->bw_min)); + WRITE_ONCE(dst->bw_max, READ_ONCE(src->bw_max)); + WRITE_ONCE(dst->burst, READ_ONCE(src->burst)); + WRITE_ONCE(dst->priority, READ_ONCE(src->priority)); + WRITE_ONCE(dst->weight, READ_ONCE(src->weight)); + + /* private fields are only used on the write path under the lock */ + data_race(dst->leaves = src->leaves); +} + static int net_shaper_fill_one(struct sk_buff *msg, const struct net_shaper_binding *binding, const struct net_shaper *shaper, const struct genl_info *info) { + struct net_shaper cur; void *hdr; hdr = genlmsg_iput(msg, info); if (!hdr) return -EMSGSIZE; + /* Make a copy to avoid data races */ + net_shaper_copy(&cur, shaper); + if (net_shaper_fill_binding(msg, binding, NET_SHAPER_A_IFINDEX) || - net_shaper_fill_handle(msg, &shaper->parent, + net_shaper_fill_handle(msg, &cur.parent, NET_SHAPER_A_PARENT) || - net_shaper_fill_handle(msg, &shaper->handle, + net_shaper_fill_handle(msg, &cur.handle, NET_SHAPER_A_HANDLE) || - ((shaper->bw_min || shaper->bw_max || shaper->burst) && - nla_put_u32(msg, NET_SHAPER_A_METRIC, shaper->metric)) || - (shaper->bw_min && - nla_put_uint(msg, NET_SHAPER_A_BW_MIN, shaper->bw_min)) || - (shaper->bw_max && - nla_put_uint(msg, NET_SHAPER_A_BW_MAX, shaper->bw_max)) || - (shaper->burst && - nla_put_uint(msg, NET_SHAPER_A_BURST, shaper->burst)) || - (shaper->priority && - nla_put_u32(msg, NET_SHAPER_A_PRIORITY, shaper->priority)) || - (shaper->weight && - nla_put_u32(msg, NET_SHAPER_A_WEIGHT, shaper->weight))) + ((cur.bw_min || cur.bw_max || cur.burst) && + nla_put_u32(msg, NET_SHAPER_A_METRIC, cur.metric)) || + (cur.bw_min && + nla_put_uint(msg, NET_SHAPER_A_BW_MIN, cur.bw_min)) || + (cur.bw_max && + nla_put_uint(msg, NET_SHAPER_A_BW_MAX, cur.bw_max)) || + (cur.burst && + nla_put_uint(msg, NET_SHAPER_A_BURST, cur.burst)) || + (cur.priority && + nla_put_u32(msg, NET_SHAPER_A_PRIORITY, cur.priority)) || + (cur.weight && + nla_put_u32(msg, NET_SHAPER_A_WEIGHT, cur.weight))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -422,7 +445,7 @@ static void net_shaper_commit(struct net_shaper_binding *binding, /* Successful update: drop the tentative mark * and update the hierarchy container. */ - *cur = shapers[i]; + net_shaper_copy(cur, &shapers[i]); smp_wmb(); __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); } From 2417df5e7bb4184b9d3a2988036bf2c46e594545 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 15 May 2026 15:13:25 -0700 Subject: [PATCH 1494/1518] net: shaper: rework the VALID marking (again) [ Upstream commit b8d7519352ba8c6df83259295d4a3bad093cae90 ] Recent commit changed the semantics from NOT_VALID to VALID. I didn't realize that the flags are not stored atomically with the entry in XArray. There's still a race of reader observing a VALID mark for a slot, getting interrupted, writer replacing the entry with a different one, reader continuing, fetching the entry which is now a different pointer than the pointer for which VALID was meant. The biggest consequence of this is that we may see a UAF since net_shaper_rollback() assumed that entries without VALID can be freed without observing RCU. Looks like the XArray marks are buying us nothing at this point. Let's convert the code to an explicit valid field. The smp_load_acquire() / smp_store_release() barriers are marginally cleaner. Reported-by: Sashiko Fixes: 93954b40f6a4 ("net-shapers: implement NL set and delete operations") Reviewed-by: Simon Horman Link: https://patch.msgid.link/20260515221325.1685455-3-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/net_shaper.h | 1 + net/shaper/shaper.c | 45 ++++++++++++++++------------------------ 2 files changed, 19 insertions(+), 27 deletions(-) diff --git a/include/net/net_shaper.h b/include/net/net_shaper.h index 5c3f49b52fe96..3939b816b0011 100644 --- a/include/net/net_shaper.h +++ b/include/net/net_shaper.h @@ -53,6 +53,7 @@ struct net_shaper { /* private: */ u32 leaves; /* accounted only for NODE scope */ + bool valid; struct rcu_head rcu; }; diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index a28096b150b35..ce353042cfa16 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -304,31 +304,24 @@ static void net_shaper_default_parent(const struct net_shaper_handle *handle, parent->id = 0; } -/* MARK_0 is already in use due to XA_FLAGS_ALLOC. The VALID mark is set on - * an entry only after the device-side configuration has completed - * successfully (see net_shaper_commit()). Lookups and dumps must filter on - * this mark to avoid exposing tentative entries inserted by - * net_shaper_pre_insert() while the driver call is still in flight. - */ -#define NET_SHAPER_VALID XA_MARK_1 - static struct net_shaper * net_shaper_lookup(struct net_shaper_binding *binding, const struct net_shaper_handle *handle) { u32 index = net_shaper_handle_to_index(handle); struct net_shaper_hierarchy *hierarchy; + struct net_shaper *cur; hierarchy = net_shaper_hierarchy_rcu(binding); - if (!hierarchy || !xa_get_mark(&hierarchy->shapers, index, - NET_SHAPER_VALID)) + if (!hierarchy) return NULL; - /* Pairs with smp_wmb() in net_shaper_commit(): if the entry is - * valid, its contents must be visible too. - */ - smp_rmb(); - return xa_load(&hierarchy->shapers, index); + cur = xa_load(&hierarchy->shapers, index); + /* Check valid before reading fields */ + if (!cur || !smp_load_acquire(&cur->valid)) + return NULL; + + return cur; } /* Allocate on demand the per device shaper's hierarchy container. @@ -442,12 +435,10 @@ static void net_shaper_commit(struct net_shaper_binding *binding, if (WARN_ON_ONCE(!cur)) continue; - /* Successful update: drop the tentative mark - * and update the hierarchy container. - */ + /* Successful update: update the hierarchy container... */ net_shaper_copy(cur, &shapers[i]); - smp_wmb(); - __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); + /* ... publish to lockless readers. */ + smp_store_release(&cur->valid, true); } xa_unlock(&hierarchy->shapers); } @@ -464,10 +455,10 @@ static void net_shaper_rollback(struct net_shaper_binding *binding) xa_lock(&hierarchy->shapers); xa_for_each(&hierarchy->shapers, index, cur) { - if (xa_get_mark(&hierarchy->shapers, index, NET_SHAPER_VALID)) + if (cur->valid) continue; __xa_erase(&hierarchy->shapers, index); - kfree(cur); + kfree_rcu(cur, rcu); } xa_unlock(&hierarchy->shapers); } @@ -880,12 +871,12 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb, goto out_unlock; for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index, - U32_MAX, NET_SHAPER_VALID)); + U32_MAX, XA_PRESENT)); ctx->start_index++) { - /* Pairs with smp_wmb() in net_shaper_commit(): the entry - * is marked VALID, so its contents must be visible too. - */ - smp_rmb(); + /* Check valid before reading fields */ + if (!smp_load_acquire(&shaper->valid)) + continue; + ret = net_shaper_fill_one(skb, binding, shaper, info); if (ret) break; From 585f9f6aef5c4542ac9d6ec45cd7dbc7df9af3ff Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 16 May 2026 00:05:13 +0100 Subject: [PATCH 1495/1518] crypto/krb5, rxrpc: Fix lack of pre-decrypt/pre-verify length checks [ Upstream commit 2b50aceafe6606ea52ed42aadd1b4d44a188aade ] Change the krb5 crypto library to provide facilities to precheck the length of the message about to be decrypted or verified. Fix AF_RXRPC to make use of this to validate DATA packets secured with RxGK. Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)") Closes: https://sashiko.dev/#/patchset/20260511160753.607296-1-dhowells%40redhat.com Signed-off-by: David Howells cc: Herbert Xu cc: Simon Horman cc: Chuck Lever cc: linux-afs@lists.infradead.org Reviewed-by: Jeffrey Altman Tested-by: Marc Dionne Link: https://patch.msgid.link/20260515230516.2718212-2-dhowells@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- Documentation/crypto/krb5.rst | 17 ++++++++--- crypto/krb5/krb5_api.c | 54 +++++++++++++++++++++++++++++++---- include/crypto/krb5.h | 9 ++++-- include/trace/events/rxrpc.h | 1 + net/rxrpc/rxgk.c | 15 ++++++++-- 5 files changed, 81 insertions(+), 15 deletions(-) diff --git a/Documentation/crypto/krb5.rst b/Documentation/crypto/krb5.rst index beffa0133446d..f62e07ac68114 100644 --- a/Documentation/crypto/krb5.rst +++ b/Documentation/crypto/krb5.rst @@ -158,13 +158,22 @@ returned. When a message has been received, the location and size of the data with the message can be determined by calling:: - void crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, - enum krb5_crypto_mode mode, - size_t *_offset, size_t *_len); + int crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t *_offset, size_t *_len); The caller provides the offset and length of the message to the function, which then alters those values to indicate the region containing the data (plus any -padding). It is up to the caller to determine how much padding there is. +padding). It is up to the caller to determine how much padding there is. The +function returns an error if the length is too small or if the mode is +unsupported. An additional function:: + + int crypto_krb5_check_data_len(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t len, size_t min_content); + +is provided to just do a basic check that the decrypted/verified message would +have a sufficient minimum payload. Preparation Functions --------------------- diff --git a/crypto/krb5/krb5_api.c b/crypto/krb5/krb5_api.c index 23026d4206c82..c7ea40f900a77 100644 --- a/crypto/krb5/krb5_api.c +++ b/crypto/krb5/krb5_api.c @@ -134,27 +134,69 @@ EXPORT_SYMBOL(crypto_krb5_how_much_data); * Find the offset and size of the data in a secure message so that this * information can be used in the metadata buffer which will get added to the * digest by crypto_krb5_verify_mic(). + * + * Return: 0 if successful, -EBADMSG if the message is too short or -EINVAL if + * the mode is unsupported. */ -void crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, - enum krb5_crypto_mode mode, - size_t *_offset, size_t *_len) +int crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t *_offset, size_t *_len) { switch (mode) { case KRB5_CHECKSUM_MODE: + if (*_len < krb5->cksum_len) + return -EBADMSG; *_offset += krb5->cksum_len; *_len -= krb5->cksum_len; - return; + return 0; case KRB5_ENCRYPT_MODE: + if (*_len < krb5->conf_len + krb5->cksum_len) + return -EBADMSG; *_offset += krb5->conf_len; *_len -= krb5->conf_len + krb5->cksum_len; - return; + return 0; default: WARN_ON_ONCE(1); - return; + return -EINVAL; } } EXPORT_SYMBOL(crypto_krb5_where_is_the_data); +/** + * crypto_krb5_check_data_len - Check a message is big enough + * @krb5: The encoding to use. + * @mode: Mode of operation. + * @len: The length of the secure blob. + * @min_content: Minimum length of the content inside the blob. + * + * Check that a message is large enough to hold whatever bits the encryption + * type wants to glue on (nonce, checksum) plus a minimum amount of content. + * + * Return: 0 if successful, -EBADMSG if the message is too short or -EINVAL if + * the mode is unsupported. + */ +int crypto_krb5_check_data_len(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t len, size_t min_content) +{ + switch (mode) { + case KRB5_CHECKSUM_MODE: + if (len < krb5->cksum_len || + len - krb5->cksum_len < min_content) + return -EBADMSG; + return 0; + case KRB5_ENCRYPT_MODE: + if (len < krb5->conf_len + krb5->cksum_len || + len - (krb5->conf_len + krb5->cksum_len) < min_content) + return -EBADMSG; + return 0; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } +} +EXPORT_SYMBOL(crypto_krb5_check_data_len); + /* * Prepare the encryption with derived key data. */ diff --git a/include/crypto/krb5.h b/include/crypto/krb5.h index 71dd38f59be1d..aac3ecf88467c 100644 --- a/include/crypto/krb5.h +++ b/include/crypto/krb5.h @@ -121,9 +121,12 @@ size_t crypto_krb5_how_much_buffer(const struct krb5_enctype *krb5, size_t crypto_krb5_how_much_data(const struct krb5_enctype *krb5, enum krb5_crypto_mode mode, size_t *_buffer_size, size_t *_offset); -void crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, - enum krb5_crypto_mode mode, - size_t *_offset, size_t *_len); +int crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t *_offset, size_t *_len); +int crypto_krb5_check_data_len(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t len, size_t min_content); struct crypto_aead *crypto_krb5_prepare_encryption(const struct krb5_enctype *krb5, const struct krb5_buffer *TK, u32 usage, gfp_t gfp); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 573f2df3a2c99..704a10de66700 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -71,6 +71,7 @@ EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \ EM(rxkad_abort_resp_version, "rxkad-resp-version") \ /* RxGK security errors */ \ + EM(rxgk_abort_1_short_header, "rxgk1-short-hdr") \ EM(rxgk_abort_1_verify_mic_eproto, "rxgk1-vfy-mic-eproto") \ EM(rxgk_abort_2_decrypt_eproto, "rxgk2-dec-eproto") \ EM(rxgk_abort_2_short_data, "rxgk2-short-data") \ diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index c39f5066d8e86..04a761c79548a 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -480,8 +480,12 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, _enter(""); - crypto_krb5_where_is_the_data(gk->krb5, KRB5_CHECKSUM_MODE, - &data_offset, &data_len); + if (crypto_krb5_where_is_the_data(gk->krb5, KRB5_CHECKSUM_MODE, + &data_offset, &data_len) < 0) { + ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, + rxgk_abort_1_short_header); + goto put_gk; + } hdr = kzalloc(sizeof(*hdr), GFP_NOFS); if (!hdr) @@ -529,6 +533,13 @@ static int rxgk_verify_packet_encrypted(struct rxrpc_call *call, _enter(""); + if (crypto_krb5_check_data_len(gk->krb5, KRB5_ENCRYPT_MODE, + len, sizeof(hdr)) < 0) { + ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, + rxgk_abort_2_short_header); + goto error; + } + ret = rxgk_decrypt_skb(gk->krb5, gk->rx_enc, skb, &offset, &len, &ac); if (ret < 0) { if (ret != -ENOMEM) From 26f1d4522060ee1f16f1165d29a7aa2926bd21ff Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Sat, 16 May 2026 14:26:16 -0700 Subject: [PATCH 1496/1518] net: ag71xx: check error for platform_get_irq [ Upstream commit e7c70bf97e90d974cd575e4c90f8f9b07d056da3 ] Complete error handling for a failed platform_get_irq() call Fixes: d51b6ce441d3 ("net: ethernet: add ag71xx driver") Signed-off-by: Rosen Penev Reviewed-by: Oleksij Rempel Link: https://patch.msgid.link/20260516212616.11758-1-rosenp@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/atheros/ag71xx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index cbc730c7cff29..8e6bd99b22d72 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1856,6 +1856,9 @@ static int ag71xx_probe(struct platform_device *pdev) ag71xx_int_disable(ag, AG71XX_INT_POLL); ndev->irq = platform_get_irq(pdev, 0); + if (ndev->irq < 0) + return ndev->irq; + err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt, 0x0, dev_name(&pdev->dev), ndev); if (err) { From 1861d369efd62d67796563bf3e01fc22e5626f8b Mon Sep 17 00:00:00 2001 From: Xingwang Xiang Date: Sun, 17 May 2026 23:56:26 +0900 Subject: [PATCH 1497/1518] bpf, skmsg: fix verdict sk_data_ready racing with ktls rx [ Upstream commit ddf8029623a1af20e984c040e89ff918158397ab ] sk_psock_strp_data_ready() already checks tls_sw_has_ctx_rx() and defers to psock->saved_data_ready when a TLS RX context is present, avoiding a conflict with the TLS strparser's ownership of the receive queue (commit e91de6afa81c, "bpf: Fix running sk_skb program types with ktls"). sk_psock_verdict_data_ready() has no equivalent guard. When a socket is inserted into a sockmap (BPF_SK_SKB_VERDICT) before TLS RX is configured, tls_sw_strparser_arm() saves sk_psock_verdict_data_ready as rx_ctx->saved_data_ready. On data arrival: tls_data_ready -> tls_strp_data_ready -> tls_rx_msg_ready -> saved_data_ready() = sk_psock_verdict_data_ready() -> tcp_read_skb() drains sk_receive_queue via __skb_unlink() without calling tcp_eat_skb(), so copied_seq is not advanced. tls_strp_msg_load() then finds tcp_inq() >= full_len (stale), calls tcp_recv_skb() on the now-empty queue, hits WARN_ON_ONCE(!first), and returns with rx_ctx->strp.anchor.frag_list pointing at a psock-owned (potentially freed) skb. tls_decrypt_sg() subsequently walks that frag_list: use-after-free. Apply the same fix as sk_psock_strp_data_ready(): if a TLS RX context is present, call psock->saved_data_ready (sock_def_readable) to wake recv() waiters and return immediately, leaving the receive queue untouched. TLS retains sole ownership of the queue and decrypts the record normally through tls_sw_recvmsg(). Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program") Signed-off-by: Xingwang Xiang Link: https://patch.msgid.link/20260517145630.20521-2-v3rdant.xiang@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/skmsg.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 35a6acbf9a579..75ea4fdb27642 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1268,12 +1268,19 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) static void sk_psock_verdict_data_ready(struct sock *sk) { const struct proto_ops *ops = NULL; + struct sk_psock *psock; struct socket *sock; int copied; trace_sk_data_ready(sk); rcu_read_lock(); + psock = sk_psock(sk); + if (psock && tls_sw_has_ctx_rx(sk)) { + psock->saved_data_ready(sk); + rcu_read_unlock(); + return; + } sock = READ_ONCE(sk->sk_socket); if (likely(sock)) ops = READ_ONCE(sock->ops); @@ -1283,8 +1290,6 @@ static void sk_psock_verdict_data_ready(struct sock *sk) copied = ops->read_skb(sk, sk_psock_verdict_recv); if (copied >= 0) { - struct sk_psock *psock; - rcu_read_lock(); psock = sk_psock(sk); if (psock) From e47f7060eaf60894e3e4d0e3c4fe6e1f2eacfbdd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 19 May 2026 08:46:11 +0000 Subject: [PATCH 1498/1518] tcp: fix stale per-CPU tcp_tw_isn leak enabling ISN prediction [ Upstream commit 1bbf0ced1d9db73ac7893c2187f3459288603e0d ] Blamed commit moved the TIME_WAIT-derived ISN from the skb control block to a per-CPU variable, assuming the value would always be consumed by tcp_conn_request() for the same packet that wrote it. That assumption is violated by multiple drop paths between the producer (__this_cpu_write(tcp_tw_isn, isn) in tcp_v{4,6}_rcv()) and the consumer (tcp_conn_request()): - min_ttl / min_hopcount check - xfrm policy check - tcp_inbound_hash() MD5/AO mismatch - tcp_filter() eBPF/SO_ATTACH_FILTER drop - th->syn && th->fin discard in tcp_rcv_state_process() TCP_LISTEN - psp_sk_rx_policy_check() in tcp_v{4,6}_do_rcv() - tcp_checksum_complete() in tcp_v{4,6}_do_rcv() - tcp_v{4,6}_cookie_check() returning NULL When a packet is dropped on any of these paths, tcp_tw_isn is left set. The next SYN processed on the same CPU then consumes the non zero value in tcp_conn_request(), receiving a potentially predictable ISN. This patch moves back tcp_tw_isn to skb->cb[], getting rid of the per-cpu variable. Note that tcp_v{4,6}_fill_cb() do not set it. Very litle impact on overall code size/complexity: $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new add/remove: 0/0 grow/shrink: 2/1 up/down: 8/-15 (-7) Function old new delta tcp_v6_rcv 3038 3042 +4 tcp_v4_rcv 3035 3039 +4 tcp_conn_request 2938 2923 -15 Total: Before=24436060, After=24436053, chg -0.00% Fixes: 41eecbd712b7 ("tcp: replace TCP_SKB_CB(skb)->tcp_tw_isn with a per-cpu field") Reported-by: Chris Mason Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260519084611.2485277-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 7 ++++--- net/ipv4/tcp.c | 3 --- net/ipv4/tcp_input.c | 15 ++++++--------- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv6/tcp_ipv6.c | 3 ++- 5 files changed, 14 insertions(+), 17 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index cf507b989bff1..f460d2c391deb 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -65,8 +65,6 @@ static inline void tcp_orphan_count_dec(void) this_cpu_dec(tcp_orphan_count); } -DECLARE_PER_CPU(u32, tcp_tw_isn); - void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -1028,10 +1026,13 @@ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { - /* Note : + /* Notes : + * tcp_tw_isn is used in input path only + * (isn chosen by tcp_timewait_state_process()) * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ + u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2de4748269ca9..6fc00b38695ba 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -300,9 +300,6 @@ enum { DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); -DEFINE_PER_CPU(u32, tcp_tw_isn); -EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); - long sysctl_tcp_mem[3] __read_mostly; EXPORT_IPV6_MOD(sysctl_tcp_mem); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b5cf32a56c04a..c650398e91998 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7387,6 +7387,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct sock *sk, struct sk_buff *skb) { struct tcp_fastopen_cookie foc = { .len = -1 }; + u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); @@ -7397,20 +7398,16 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct dst_entry *dst; struct flowi fl; u8 syncookies; - u32 isn; #ifdef CONFIG_TCP_AO const struct tcp_ao_hdr *aoh; #endif - isn = __this_cpu_read(tcp_tw_isn); - if (isn) { - /* TW buckets are converted to open requests without - * limitations, they conserve resources and peer is - * evidently real one. - */ - __this_cpu_write(tcp_tw_isn, 0); - } else { + /* If isn is non-zero, this SYN originally matched a TIME_WAIT socket. + * TW sockets are converted to open requests without limitations, + * we skip the queue limits and syncookie checks in the block below. + */ + if (!isn) { syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); if (syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 702fdff58f7a3..36206fc6aed2d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2333,6 +2333,7 @@ int tcp_v4_rcv(struct sk_buff *skb) } } + isn = 0; process: if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ @@ -2361,6 +2362,7 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); + TCP_SKB_CB(skb)->tcp_tw_isn = isn; skb->dev = NULL; @@ -2446,7 +2448,6 @@ int tcp_v4_rcv(struct sk_buff *skb) sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; - __this_cpu_write(tcp_tw_isn, isn); goto process; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7f20db11e8ce9..59b5900dd42bd 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1863,6 +1863,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) } } + isn = 0; process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ @@ -1891,6 +1892,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); + TCP_SKB_CB(skb)->tcp_tw_isn = isn; skb->dev = NULL; @@ -1978,7 +1980,6 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; - __this_cpu_write(tcp_tw_isn, isn); goto process; } From 4669f84adcb1e0567bd9c2e1cae827b63c53103b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 21 May 2026 10:42:16 +0200 Subject: [PATCH 1499/1518] gpio: cdev: check if uAPI v2 config attributes are correctly zeroed [ Upstream commit 3e6ccd790ed69bedd3d9626d01dd35cf9821c121 ] We check the padding of other uAPI v2 structures but not that of line config attributes. For used attributes: check if their padding is zeroed, for unused: check if the entire structure is zeroed. Fixes: 3c0d9c635ae2 ("gpiolib: cdev: support GPIO_V2_GET_LINE_IOCTL and GPIO_V2_LINE_GET_VALUES_IOCTL") Reviewed-by: Kent Gibson Link: https://patch.msgid.link/20260521-gpio-cdev-attr-padding-check-v3-1-ec3bcbe2e358@oss.qualcomm.com Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpiolib-cdev.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 986312c71678f..89abf7a238d87 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1208,6 +1208,7 @@ static int gpio_v2_line_flags_validate(u64 flags) static int gpio_v2_line_config_validate(struct gpio_v2_line_config *lc, unsigned int num_lines) { + size_t unused_attrs; unsigned int i; u64 flags; int ret; @@ -1215,9 +1216,21 @@ static int gpio_v2_line_config_validate(struct gpio_v2_line_config *lc, if (lc->num_attrs > GPIO_V2_LINE_NUM_ATTRS_MAX) return -EINVAL; + unused_attrs = GPIO_V2_LINE_NUM_ATTRS_MAX - lc->num_attrs; + if (!mem_is_zero(lc->padding, sizeof(lc->padding))) return -EINVAL; + for (i = 0; i < lc->num_attrs; i++) { + if (lc->attrs[i].attr.padding != 0) + return -EINVAL; + } + + if (unused_attrs) { + if (!mem_is_zero(&lc->attrs[lc->num_attrs], unused_attrs * sizeof(*lc->attrs))) + return -EINVAL; + } + for (i = 0; i < num_lines; i++) { flags = gpio_v2_line_config_flags(lc, i); ret = gpio_v2_line_flags_validate(flags); From ea28b286649b70618e9dd3e895812417a7712a11 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 20 May 2026 10:49:11 +0200 Subject: [PATCH 1500/1518] gpio: aggregator: fix a potential use-after-free [ Upstream commit 30c073cab97afb31901f94de9605177b6b84367e ] On error we free aggr->lookups->dev_id before removing the entry from the lookup table. If a concurrent thread calls gpiod_find() before we remove the entry, it could iterate over the list and call gpiod_match_lookup_table() which unconditionally dereferences dev_id when calling strcmp(). Reverse the order of cleanup. Fixes: 86f162e73d2d ("gpio: aggregator: introduce basic configfs interface") Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260520084911.27938-1-bartosz.golaszewski@oss.qualcomm.com Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-aggregator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 416f265d09d07..a68665700733d 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -970,8 +970,8 @@ static int gpio_aggregator_activate(struct gpio_aggregator *aggr) return 0; err_remove_lookup_table: - kfree(aggr->lookups->dev_id); gpiod_remove_lookup_table(aggr->lookups); + kfree(aggr->lookups->dev_id); err_remove_swnode: fwnode_remove_software_node(swnode); err_remove_lookups: From 80d94cf1773a367f6c83ffc2a09dfc01fdf64de7 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 27 Mar 2026 11:31:12 +0100 Subject: [PATCH 1501/1518] gpio: aggregator: stop using dev-sync-probe [ Upstream commit 3a27f40b457053e6112a63d14590e4a3ff553b44 ] dev-err-probe is an overengineered solution to a simple problem. Use a combination of wait_for_probe() and device_is_bound() to synchronously wait for the platform device to probe. Reviewed-by: Linus Walleij Link: https://patch.msgid.link/20260327-gpio-kill-dev-sync-probe-v1-2-efac254f1a1d@oss.qualcomm.com Signed-off-by: Bartosz Golaszewski Stable-dep-of: 61fef83f239e ("gpio: aggregator: remove the software node when deactivating the aggregator") Signed-off-by: Sasha Levin --- drivers/gpio/Kconfig | 1 - drivers/gpio/gpio-aggregator.c | 38 +++++++++++++++++++--------------- 2 files changed, 21 insertions(+), 18 deletions(-) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 4d644dcecad93..3b7284938babf 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1968,7 +1968,6 @@ menu "Virtual GPIO drivers" config GPIO_AGGREGATOR tristate "GPIO Aggregator" select CONFIGFS_FS - select DEV_SYNC_PROBE help Say yes here to enable the GPIO Aggregator, which provides a way to aggregate existing GPIO lines into a new virtual GPIO chip. diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index a68665700733d..23987c38a2468 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -32,8 +32,6 @@ #include #include -#include "dev-sync-probe.h" - #define AGGREGATOR_MAX_GPIOS 512 #define AGGREGATOR_LEGACY_PREFIX "_sysfs" @@ -42,7 +40,7 @@ */ struct gpio_aggregator { - struct dev_sync_probe_data probe_data; + struct platform_device *pdev; struct config_group group; struct gpiod_lookup_table *lookups; struct mutex lock; @@ -135,7 +133,7 @@ static bool gpio_aggregator_is_active(struct gpio_aggregator *aggr) { lockdep_assert_held(&aggr->lock); - return aggr->probe_data.pdev && platform_get_drvdata(aggr->probe_data.pdev); + return aggr->pdev && platform_get_drvdata(aggr->pdev); } /* Only aggregators created via legacy sysfs can be "activating". */ @@ -143,7 +141,7 @@ static bool gpio_aggregator_is_activating(struct gpio_aggregator *aggr) { lockdep_assert_held(&aggr->lock); - return aggr->probe_data.pdev && !platform_get_drvdata(aggr->probe_data.pdev); + return aggr->pdev && !platform_get_drvdata(aggr->pdev); } static size_t gpio_aggregator_count_lines(struct gpio_aggregator *aggr) @@ -909,6 +907,7 @@ static int gpio_aggregator_activate(struct gpio_aggregator *aggr) { struct platform_device_info pdevinfo; struct gpio_aggregator_line *line; + struct platform_device *pdev; struct fwnode_handle *swnode; unsigned int n = 0; int ret = 0; @@ -963,12 +962,23 @@ static int gpio_aggregator_activate(struct gpio_aggregator *aggr) gpiod_add_lookup_table(aggr->lookups); - ret = dev_sync_probe_register(&aggr->probe_data, &pdevinfo); - if (ret) + pdev = platform_device_register_full(&pdevinfo); + if (IS_ERR(pdev)) { + ret = PTR_ERR(pdev); goto err_remove_lookup_table; + } + wait_for_device_probe(); + if (!device_is_bound(&pdev->dev)) { + ret = -ENXIO; + goto err_unregister_pdev; + } + + aggr->pdev = pdev; return 0; +err_unregister_pdev: + platform_device_unregister(pdev); err_remove_lookup_table: gpiod_remove_lookup_table(aggr->lookups); kfree(aggr->lookups->dev_id); @@ -982,7 +992,8 @@ static int gpio_aggregator_activate(struct gpio_aggregator *aggr) static void gpio_aggregator_deactivate(struct gpio_aggregator *aggr) { - dev_sync_probe_unregister(&aggr->probe_data); + platform_device_unregister(aggr->pdev); + aggr->pdev = NULL; gpiod_remove_lookup_table(aggr->lookups); kfree(aggr->lookups->dev_id); kfree(aggr->lookups); @@ -1146,7 +1157,7 @@ gpio_aggregator_device_dev_name_show(struct config_item *item, char *page) guard(mutex)(&aggr->lock); - pdev = aggr->probe_data.pdev; + pdev = aggr->pdev; if (pdev) return sysfs_emit(page, "%s\n", dev_name(&pdev->dev)); @@ -1323,7 +1334,6 @@ gpio_aggregator_make_group(struct config_group *group, const char *name) return ERR_PTR(ret); config_group_init_type_name(&aggr->group, name, &gpio_aggregator_device_type); - dev_sync_probe_init(&aggr->probe_data); return &aggr->group; } @@ -1473,12 +1483,6 @@ static ssize_t gpio_aggregator_new_device_store(struct device_driver *driver, scnprintf(name, sizeof(name), "%s.%d", AGGREGATOR_LEGACY_PREFIX, aggr->id); config_group_init_type_name(&aggr->group, name, &gpio_aggregator_device_type); - /* - * Since the device created by sysfs might be toggled via configfs - * 'live' attribute later, this initialization is needed. - */ - dev_sync_probe_init(&aggr->probe_data); - /* Expose to configfs */ res = configfs_register_group(&gpio_aggregator_subsys.su_group, &aggr->group); @@ -1497,7 +1501,7 @@ static ssize_t gpio_aggregator_new_device_store(struct device_driver *driver, goto remove_table; } - aggr->probe_data.pdev = pdev; + aggr->pdev = pdev; module_put(THIS_MODULE); return count; From 3e657619cf7258cb53b1beaf0d02998297695cde Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 20 May 2026 14:16:31 +0200 Subject: [PATCH 1502/1518] gpio: aggregator: remove the software node when deactivating the aggregator [ Upstream commit 61fef83f239ecace1cce716135762a2d9b7b1fc6 ] The dynamic software node we create for the aggregator platform device when using configfs is leaked when the device is deactivated. Destroy it as the last step in the tear-down path. Fixes: 86f162e73d2d ("gpio: aggregator: introduce basic configfs interface") Reported-by: Geert Uytterhoeven Closes: https://lore.kernel.org/all/CAMuHMdVZ=XUvJTGdDAjnkxgtw7Uvnn61iOy3XN_5XNZM2anctw@mail.gmail.com/ Link: https://patch.msgid.link/20260520121631.33976-1-bartosz.golaszewski@oss.qualcomm.com Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-aggregator.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 23987c38a2468..8cbebcb4bb1f9 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -992,11 +992,15 @@ static int gpio_aggregator_activate(struct gpio_aggregator *aggr) static void gpio_aggregator_deactivate(struct gpio_aggregator *aggr) { + struct fwnode_handle *swnode; + + swnode = dev_fwnode(&aggr->pdev->dev); platform_device_unregister(aggr->pdev); aggr->pdev = NULL; gpiod_remove_lookup_table(aggr->lookups); kfree(aggr->lookups->dev_id); kfree(aggr->lookups); + fwnode_remove_software_node(swnode); } static void gpio_aggregator_lockup_configfs(struct gpio_aggregator *aggr, From decacc6308c539db7b7152afd42b232aaf816ac9 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 18 May 2026 11:53:18 +0200 Subject: [PATCH 1503/1518] gpio: aggregator: lock device when calling device_is_bound() [ Upstream commit 598a2b3e2e0e6aa2e9f7843c96c45b5ea11e0411 ] The kerneldoc for device_is_bound() says it must be called with the device lock taken. Add missing synchronization to this driver. Fixes: 3a27f40b4570 ("gpio: aggregator: stop using dev-sync-probe") Link: https://patch.msgid.link/20260518-gpio-dev-lock-v1-2-cc4736f3ff0b@oss.qualcomm.com Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-aggregator.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 8cbebcb4bb1f9..17db07cf92d05 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -969,9 +969,12 @@ static int gpio_aggregator_activate(struct gpio_aggregator *aggr) } wait_for_device_probe(); - if (!device_is_bound(&pdev->dev)) { - ret = -ENXIO; - goto err_unregister_pdev; + + scoped_guard(device, &pdev->dev) { + if (!device_is_bound(&pdev->dev)) { + ret = -ENXIO; + goto err_unregister_pdev; + } } aggr->pdev = pdev; From db86ac6d8dafea982967e1bde249df8545af67ac Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 21 May 2026 13:30:57 +0100 Subject: [PATCH 1504/1518] ASoC: cs35l56: Fix flushing of IRQ work in cs35l56_sdw_remove() [ Upstream commit 18e7bd9f2446664053f8c34b72abd4606d22d858 ] Use flush_work() instead of cancel_work_sync() to terminate pending IRQ work in cs35l56_sdw_remove(). And flush_work() again after masking the interrupts to flush any queueing that was racing with the masking. This is the same sequence as cs35l56_sdw_system_suspend(). cs35l56_sdw_interrupt() takes the pm_runtime to prevent the bus powering- down before the interrupt status can be read and handled. The work releases this pm_runtime. So cancelling it, instead of flushing, could leave an unbalanced pm_runtime. Signed-off-by: Richard Fitzgerald Fixes: e49611252900 ("ASoC: cs35l56: Add driver for Cirrus Logic CS35L56") Link: https://patch.msgid.link/20260521123057.988732-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/cs35l56-sdw.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c index 42d24ac2977fc..a513a15d7e5a7 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -560,10 +560,11 @@ static int cs35l56_sdw_remove(struct sdw_slave *peripheral) /* Disable SoundWire interrupts */ cs35l56->sdw_irq_no_unmask = true; - cancel_work_sync(&cs35l56->sdw_irq_work); + flush_work(&cs35l56->sdw_irq_work); sdw_write_no_pm(peripheral, CS35L56_SDW_GEN_INT_MASK_1, 0); sdw_read_no_pm(peripheral, CS35L56_SDW_GEN_INT_STAT_1); sdw_write_no_pm(peripheral, CS35L56_SDW_GEN_INT_STAT_1, 0xFF); + flush_work(&cs35l56->sdw_irq_work); cs35l56_remove(cs35l56); From 04ef7592eaadd9ca8f8f66e76452f73525cff819 Mon Sep 17 00:00:00 2001 From: Shuicheng Lin Date: Thu, 14 May 2026 20:32:10 +0000 Subject: [PATCH 1505/1518] drm/xe/oa: Fix exec_queue leak on width check in stream open [ Upstream commit 4d25342543c01310fc4e0cba7cb17c775e2421e2 ] In xe_oa_stream_open_ioctl(), when param.exec_q->width > 1 the function returns -EOPNOTSUPP directly, skipping the existing err_exec_q cleanup path. The exec_queue reference obtained by xe_exec_queue_lookup() is leaked. The exec queue holds a reference on the xe_file, which is only dropped during queue teardown. The leaked lookup ref is not on the file's exec_queue xarray, so file close cannot release it. This keeps both the exec queue and the file private state pinned indefinitely. Jump to err_exec_q instead of returning directly so the reference is released. Fixes: f0ed39830e60 ("xe/oa: Fix query mode of operation for OAR/OAC") Assisted-by: Claude:claude-opus-4.6 Reviewed-by: Ashutosh Dixit Link: https://patch.msgid.link/20260514203210.593488-1-shuicheng.lin@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit 339fa0be9e4a5d69fa47e91f4a36574224fb478f) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/xe/xe_oa.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 98bfb127eafca..7d04591e297a8 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -2043,8 +2043,10 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f if (XE_IOCTL_DBG(oa->xe, !param.exec_q)) return -ENOENT; - if (XE_IOCTL_DBG(oa->xe, param.exec_q->width > 1)) - return -EOPNOTSUPP; + if (XE_IOCTL_DBG(oa->xe, param.exec_q->width > 1)) { + ret = -EOPNOTSUPP; + goto err_exec_q; + } } /* From 76dd50b7888d65956ca796d9b6cdd17a9001fb79 Mon Sep 17 00:00:00 2001 From: Nimrod Oren Date: Wed, 20 May 2026 18:39:28 +0300 Subject: [PATCH 1506/1518] selftests: net: Fix checksums in xdp_native [ Upstream commit dfc077043351a81887d1e4c9ac244e9243f3cbf2 ] Data adjustment cases failed with "Data exchange failed" when using IPv4 because the program did not update the IP and UDP checksums in the IPv4 branch. The issue was masked when both IPv4 and IPv6 were configured, since the test harness prefers IPv6. While here, generalize csum_fold_helper() to fold twice so it works for any 32-bit input. Fixes: 0b65cfcef9c5 ("selftests: drv-net: Test tail-adjustment support") Reviewed-by: Carolina Jubran Reviewed-by: Dragos Tatulea Signed-off-by: Nimrod Oren Link: https://patch.msgid.link/20260520153928.3371765-1-noren@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../selftests/net/lib/xdp_native.bpf.c | 55 ++++++++++--------- 1 file changed, 30 insertions(+), 25 deletions(-) diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index c368fc045f4b4..d5134f93f7d7f 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -268,6 +268,17 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) return XDP_PASS; } +static __always_inline __u16 csum_fold_helper(__u32 csum) +{ + csum = (csum & 0xffff) + (csum >> 16); + return ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline __u16 csum_fold_udp_helper(__u32 csum) +{ + return csum_fold_helper(csum) ? : 0xffff; +} + static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) { void *data_end = (void *)(long)ctx->data_end; @@ -281,21 +292,22 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) if (eth->h_proto == bpf_htons(ETH_P_IP)) { struct iphdr *iph = data + sizeof(*eth); - __u16 total_len; if (iph + 1 > (struct iphdr *)data_end) return NULL; - iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); - udph = (void *)eth + sizeof(*iph) + sizeof(*eth); if (!udph || udph + 1 > (struct udphdr *)data_end) return NULL; - len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + len = iph->tot_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + iph->tot_len = len_new; + iph->check = csum_fold_helper( + bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), ~((__u32)iph->check))); } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { struct ipv6hdr *ipv6h = data + sizeof(*eth); - __u16 payload_len; if (ipv6h + 1 > (struct ipv6hdr *)data_end) return NULL; @@ -304,33 +316,27 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) if (!udph || udph + 1 > (struct udphdr *)data_end) return NULL; - *udp_csum = ~((__u32)udph->check); - len = ipv6h->payload_len; len_new = bpf_htons(bpf_ntohs(len) + offset); ipv6h->payload_len = len_new; - - *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, - sizeof(len_new), *udp_csum); - - len = udph->len; - len_new = bpf_htons(bpf_ntohs(udph->len) + offset); - *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, - sizeof(len_new), *udp_csum); } else { return NULL; } + len = udph->len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + + *udp_csum = ~((__u32)udph->check); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + udph->len = len_new; return udph; } -static __u16 csum_fold_helper(__u32 csum) -{ - return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; -} - static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, __u32 hdr_len) { @@ -359,7 +365,7 @@ static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, return -1; udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) return -1; @@ -403,7 +409,7 @@ static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) return -1; udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); buff_len = bpf_xdp_get_buff_len(ctx); @@ -483,8 +489,7 @@ static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, return -1; udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); - - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) return -1; @@ -541,7 +546,7 @@ static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, return -1; udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) return -1; From bc0020490f8890ea83950a1f1883c7c1898a8a35 Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 20 May 2026 10:00:36 +0530 Subject: [PATCH 1507/1518] octeontx2-af: npc: Fix allmulticast skip logic for LBK and SDP VFs [ Upstream commit 9eddc819f00b5b74bb4ac91396f80bd35f5f3561 ] When installing the allmulticast NPC rule, rvu_npc_install_allmulti_entry() should skip LBK and SDP VFs (only CGX PF/VF may add the entry). The code combined is_lbk_vf() and is_sdp_vf() with logical AND, which is never true for a single pcifunc, so the intended early return never ran. Use logical OR instead. Cc: Geetha sowjanya Fixes: ae703539f49d2 ("octeontx2-af: Cleanup loopback device checks") Signed-off-by: Ratheesh Kannoth Link: https://patch.msgid.link/20260520043036.1523798-1-rkannoth@marvell.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 8658cb2143dfc..e28675fe18907 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -837,7 +837,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u16 vf_func; /* Only CGX PF/VF can add allmulticast entry */ - if (is_lbk_vf(rvu, pcifunc) && is_sdp_vf(rvu, pcifunc)) + if (is_lbk_vf(rvu, pcifunc) || is_sdp_vf(rvu, pcifunc)) return; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); From fa627a5eaa83fc0261f44ef3769693b886ca6e27 Mon Sep 17 00:00:00 2001 From: Aditya Garg Date: Tue, 19 May 2026 22:15:53 -0700 Subject: [PATCH 1508/1518] net: mana: validate rx_req_idx to prevent out-of-bounds array access [ Upstream commit b809d0409991b75a6cff846a5ac27c3062953f84 ] In mana_hwc_rx_event_handler(), rx_req_idx is derived from sge->address in DMA-coherent memory. In Confidential VMs (SEV-SNP/TDX), this memory is shared unencrypted and HW can modify WQE contents at any time. No bounds check exists on rx_req_idx, which can lead to an out-of-bounds access into reqs[]. Add bounds check on rx_req_idx in mana_hwc_rx_event_handler() before using it to index the reqs[] array. Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)") Signed-off-by: Aditya Garg Reviewed-by: Haiyang Zhang Link: https://patch.msgid.link/20260520051553.857120-1-gargaditya@linux.microsoft.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/microsoft/mana/hw_channel.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 1986bf493399f..5faf4ca75b0f4 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -265,6 +265,12 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id, rq_base_addr = hwc_rxq->msg_buf->mem_info.dma_handle; rx_req_idx = (sge->address - rq_base_addr) / hwc->max_req_msg_size; + if (rx_req_idx >= hwc_rxq->msg_buf->num_reqs) { + dev_err(hwc->dev, "HWC RX: wrong rx_req_idx=%llu, num_reqs=%u\n", + rx_req_idx, hwc_rxq->msg_buf->num_reqs); + return; + } + rx_req = &hwc_rxq->msg_buf->reqs[rx_req_idx]; resp = (struct gdma_resp_hdr *)rx_req->buf_va; From 719007c3492f0f1f9e9cdbed8ac45ba45bb13eeb Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Wed, 20 May 2026 00:57:38 -0700 Subject: [PATCH 1509/1518] tap: fix stack info leak in tap_ioctl() SIOCGIFHWADDR [ Upstream commit bddc09212c24934643bd44fc794748d2bbb3b6cd ] In the SIOCGIFHWADDR path, tap_ioctl() copies 16 bytes of an uninitialised on-stack struct sockaddr_storage to userspace via ifr_hwaddr, but netif_get_mac_address() only writes sa_family and dev->addr_len (6 for Ethernet) bytes, leaving sa_data[6..13] uninitialised. Those 8 trailing bytes leak kernel stack contents; SIOCGIFHWADDR on a macvtap chardev returns kernel .text and direct-map pointers, defeating KASLR. Initialise ss at declaration. Fixes: 3b23a32a6321 ("net: fix dev_ifsioc_locked() race condition") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20260520075736.3415676-3-bestswngs@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/tap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 1197f245e8737..6fd3b14273b37 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -919,11 +919,11 @@ static long tap_ioctl(struct file *file, unsigned int cmd, struct tap_queue *q = file->private_data; struct tap_dev *tap; void __user *argp = (void __user *)arg; + struct sockaddr_storage ss = {}; struct ifreq __user *ifr = argp; unsigned int __user *up = argp; unsigned short u; int __user *sp = argp; - struct sockaddr_storage ss; int s; int ret; From d1d76bbb6d7af470fa57bf4888d4912109c72bd2 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 20 May 2026 15:12:02 +0200 Subject: [PATCH 1510/1518] net: airoha: Disable GDM2 forwarding before configuring GDM2 loopback [ Upstream commit 985d4a55e64e43bd86eeb896b81ceba453301989 ] Hw design requires to disable GDM2 forwarding before configuring GDM2 loopback in airoha_set_gdm2_loopback routine. Fixes: 9cd451d414f6e ("net: airoha: Add loopback support for GDM2") Tested-by: Madhur Agrawal Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260520-airoha-disable-gdm2-fwd-v1-1-1eeea5dffc2f@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/airoha/airoha_eth.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 27d62acfcc39c..9781a6fc9bf9a 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1800,11 +1800,8 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) u32 val, pse_port, chan; int src_port; - /* Forward the traffic to the proper GDM port */ - pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 - : FE_PSE_PORT_GDM4; airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), - pse_port); + FE_PSE_PORT_DROP); airoha_fe_clear(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), GDM_STRIP_CRC_MASK); @@ -1822,6 +1819,11 @@ static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK, FIELD_PREP(GDM_SHORT_LEN_MASK, 60) | FIELD_PREP(GDM_LONG_LEN_MASK, AIROHA_MAX_MTU)); + /* Forward the traffic to the proper GDM port */ + pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 + : FE_PSE_PORT_GDM4; + airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), + pse_port); /* Disable VIP and IFC for GDM2 */ airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX)); From 8129611d4ede5c4b36a6b2649db140826fa0e569 Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Wed, 20 May 2026 20:58:42 +0000 Subject: [PATCH 1511/1518] pds_core: ensure null-termination for firmware version strings [ Upstream commit 3d4432d34c1992701289cbe12df9fd024f315998 ] The driver passes fw_version directly to devlink_info_version_stored_put() without ensuring null-termination. While current firmware null-terminates these strings, the driver should not rely on this behavior. Add explicit null-termination to prevent potential issues if firmware behavior changes. Fixes: 45d76f492938 ("pds_core: set up device and adminq") Signed-off-by: Nikhil P. Rao Link: https://patch.msgid.link/20260520205842.1486718-1-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/pds_core/devlink.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index d8dc39da4161f..621791a3c543b 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -121,12 +121,14 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { + char *fw_ver = fw_list.fw_names[i].fw_version; + if (i < ARRAY_SIZE(fw_slotnames)) strscpy(buf, fw_slotnames[i], sizeof(buf)); else snprintf(buf, sizeof(buf), "fw.slot_%d", i); - err = devlink_info_version_stored_put(req, buf, - fw_list.fw_names[i].fw_version); + fw_ver[sizeof(fw_list.fw_names[i].fw_version) - 1] = '\0'; + err = devlink_info_version_stored_put(req, buf, fw_ver); if (err) return err; } From e334cbf3388fd9334503a778a82d9e9f14dd2f71 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 20 May 2026 22:44:42 +0200 Subject: [PATCH 1512/1518] net: gro: don't merge zcopy skbs [ Upstream commit 4db79a322db8c97f7b73b8a347395ef4d685eb40 ] skb_gro_receive() can currently copy frags between the source and GRO skb, without checking the zerocopy status, and in particular the SKBFL_MANAGED_FRAG_REFS flag. When SKBFL_MANAGED_FRAG_REFS is set, the skb doesn't hold a reference on the pages in shinfo->frags. Appending those frags to another skb's frags without fixing up the page refcount can lead to UAF. When either the last skb in the GRO chain (the one we would append frags to) or the source skb is zerocopy, don't merge the skbs. Fixes: 753f1ca4e1e5 ("net: introduce managed frags infrastructure") Reported-by: Huzaifa Sidhpurwala Signed-off-by: Sabrina Dubroca Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/c3b7f906bbfcbdfd7b4fa9d6c18a438870df85be.1779307748.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/gro.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/gro.c b/net/core/gro.c index 867611d171dbb..b5f790a643d49 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -109,6 +109,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) if (p->pp_recycle != skb->pp_recycle) return -ETOOMANYREFS; + if (skb_zcopy(p) || skb_zcopy(skb)) + return -ETOOMANYREFS; + if (unlikely(p->len + len >= netif_get_gro_max_size(p->dev, p) || NAPI_GRO_CB(skb)->flush)) return -E2BIG; From 6836f694126e5dfb44da4f77706ae29e45cc2e1e Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Wed, 20 May 2026 20:00:44 +0200 Subject: [PATCH 1513/1518] io_uring/nop: pass all errors to userspace [ Upstream commit e97ff8b62d4690c69297f0f6de874f0564cc01a4 ] This fixes an inconsistency where io_nop() called req_set_fail() based on ret, but passed just nop->result to userspace. Originally, ret is a even copy of nop->result, but is set to an error when such happens subsequently. Now that's also passed to userspace. Fixes: a85f31052bce ("io_uring/nop: add support for testing registered files and buffers") Signed-off-by: Alexander A. Klimov Link: https://patch.msgid.link/20260520180045.538533-1-grandmaster@al2klimov.de Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/nop.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/io_uring/nop.c b/io_uring/nop.c index 3caf07878f8ac..f5c9969e7f64a 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -79,9 +79,9 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags) if (ret < 0) req_set_fail(req); if (nop->flags & IORING_NOP_CQE32) - io_req_set_res32(req, nop->result, 0, nop->extra1, nop->extra2); + io_req_set_res32(req, ret, 0, nop->extra1, nop->extra2); else - io_req_set_res(req, nop->result, 0); + io_req_set_res(req, ret, 0); if (nop->flags & IORING_NOP_TW) { req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); From a1a39f227c80cbf369767badc32cba2b225147d1 Mon Sep 17 00:00:00 2001 From: Junyi Liu Date: Mon, 18 May 2026 23:27:19 +0900 Subject: [PATCH 1514/1518] ksmbd: fix durable reconnect error path file lifetime [ Upstream commit 3515503322f4819277091839eed46b695096aca5 ] After a durable reconnect succeeds, ksmbd_reopen_durable_fd() republishes the same ksmbd_file into the session volatile-id table. If smb2_open() then takes a later error path, cleanup first calls ksmbd_fd_put(work, fp) and then unconditionally calls ksmbd_put_durable_fd(dh_info.fp). In this case fp and dh_info.fp are the same object. The first put drops the reconnect lookup reference, but the final durable put can run __ksmbd_close_fd(NULL, fp). Because the final close is not session-aware, it can free the file object without removing the volatile-id entry that was just published into the session table. Use the session-aware put for the final reconnect drop when the reconnect had already succeeded and the error path is cleaning up the republished file. Earlier reconnect failures, before fp is assigned to dh_info.fp, keep using the durable-only put path. Fixes: 1baff47b81f9 ("ksmbd: fix use-after-free in smb2_open during durable reconnect") Signed-off-by: Junyi Liu Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/smb2pdu.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 756624b4e90e0..da7b96707186e 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3812,8 +3812,19 @@ int smb2_open(struct ksmbd_work *work) ksmbd_debug(SMB, "Error response: %x\n", rsp->hdr.Status); } - if (dh_info.reconnected) - ksmbd_put_durable_fd(dh_info.fp); + if (dh_info.reconnected) { + /* + * If reconnect succeeded, fp was republished in the + * session file table. On a later error, ksmbd_fd_put() + * above drops the session reference; drop the durable + * lookup reference through the same session-aware path so + * final close removes the volatile id before freeing fp. + */ + if (rc && fp == dh_info.fp) + ksmbd_fd_put(work, dh_info.fp); + else + ksmbd_put_durable_fd(dh_info.fp); + } kfree(name); kfree(lc); From 306ba9d0e5aa98465c2d5588f91994fbdf95c4d6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 22 May 2026 15:05:07 +0800 Subject: [PATCH 1515/1518] LoongArch: kprobes: Fix handling of fatal unrecoverable recursions [ Upstream commit 1c856e158fd34ef2c4475a81c1dc386329989938 ] KPROBE_HIT_SS and KPROBE_REENTER are two types of fatal recursions that can not be safely recovered in kprobes. KPROBE_HIT_SS means that a kprobe is hit during single-stepping. At this point, the architecture-specific single-step context is already active. Nested single-stepping would corrupt the state, as the kprobe control block (kcb) and hardware registers cannot safely store multiple levels of stepping state. KPROBE_REENTER means that a third-level recursion occurs when a probe is hit while the system is already handling a nested probe (second- level). The kcb only provides a single slot (prev_kprobe) to backup the state. When a third probe is hit, there is no more space to save the state without corrupting the first-level backup. Kprobes work by replacing instructions with breakpoints. In order to execute the original instruction and continue, it must be moved to a temporary "single-step" slot. Since there is no backup space left to set up this slot safely, the CPU would be forced to return to the same original breakpoint address, triggering an endless loop. Currently, the code only prints a warning and returns. This leads to an infinite re-entry loop as the CPU repeatedly hits the same trap and a "stuck" CPU core because preemption was disabled at the start of the handler and never re-enabled in this early return path. Fix the logic by: 1. Merging KPROBE_HIT_SS and KPROBE_REENTER cases, as both represent fatal recursions that cannot be safely recovered. 2. Replacing WARN_ON_ONCE() with BUG() to terminate the system. This aligns LoongArch with other architectures (x86, arm64, riscv) and prevents stack overflow while providing diagnostic information. Fixes: 6d4cc40fb5f5 ("LoongArch: Add kprobes support") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen Signed-off-by: Sasha Levin --- arch/loongarch/kernel/kprobes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c index 04b5b05715cdc..1985ed30dd16f 100644 --- a/arch/loongarch/kernel/kprobes.c +++ b/arch/loongarch/kernel/kprobes.c @@ -186,16 +186,16 @@ static bool reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { switch (kcb->kprobe_status) { - case KPROBE_HIT_SS: case KPROBE_HIT_SSDONE: case KPROBE_HIT_ACTIVE: kprobes_inc_nmissed_count(p); setup_singlestep(p, regs, kcb, 1); break; + case KPROBE_HIT_SS: case KPROBE_REENTER: pr_warn("Failed to recover from reentered kprobes.\n"); dump_kprobe(p); - WARN_ON_ONCE(1); + BUG(); break; default: WARN_ON(1); From 239172639075ef745ca233386086ba4b2b5077f8 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 18 May 2026 15:17:14 -0700 Subject: [PATCH 1516/1518] drm/msm: Restore second parameter name in purge() and evict() [ Upstream commit 53676e4d44d6b38c8a0d9bff331f170ae2e41bbe ] After commit 3392291fc509 ("drm/msm: Fix shrinker deadlock"), all supported versions of clang warn (or error with CONFIG_WERROR=y): drivers/gpu/drm/msm/msm_gem_shrinker.c:105:58: error: omitting the parameter name in a function definition is a C23 extension [-Werror,-Wc23-extensions] 105 | purge(struct drm_gem_object *obj, struct ww_acquire_ctx *) | ^ drivers/gpu/drm/msm/msm_gem_shrinker.c:117:58: error: omitting the parameter name in a function definition is a C23 extension [-Werror,-Wc23-extensions] 117 | evict(struct drm_gem_object *obj, struct ww_acquire_ctx *) | ^ 2 errors generated. With older but supported versions of GCC, this is an unconditional hard error: drivers/gpu/drm/msm/msm_gem_shrinker.c: In function 'purge': drivers/gpu/drm/msm/msm_gem_shrinker.c:105:35: error: parameter name omitted purge(struct drm_gem_object *obj, struct ww_acquire_ctx *) ^~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/msm/msm_gem_shrinker.c: In function 'evict': drivers/gpu/drm/msm/msm_gem_shrinker.c:117:35: error: parameter name omitted evict(struct drm_gem_object *obj, struct ww_acquire_ctx *) ^~~~~~~~~~~~~~~~~~~~~~~ Restore the parameter name to clear up the warnings, renaming it "unused" to make it clear it is only needed to satisfy the prototype of drm_gem_lru_scan(). Cc: stable@vger.kernel.org Fixes: 3392291fc509 ("drm/msm: Fix shrinker deadlock") Signed-off-by: Nathan Chancellor Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_gem_shrinker.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 6e39e4e578bba..8f118b5185a1d 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -102,7 +102,7 @@ with_vm_locks(void (*fn)(struct drm_gem_object *obj), } static bool -purge(struct drm_gem_object *obj, struct ww_acquire_ctx *) +purge(struct drm_gem_object *obj, struct ww_acquire_ctx *unused) { if (!is_purgeable(to_msm_bo(obj))) return false; @@ -114,7 +114,7 @@ purge(struct drm_gem_object *obj, struct ww_acquire_ctx *) } static bool -evict(struct drm_gem_object *obj, struct ww_acquire_ctx *) +evict(struct drm_gem_object *obj, struct ww_acquire_ctx *unused) { if (is_unevictable(to_msm_bo(obj))) return false; From 50bb3435a5e627bfbdc52eb4536f49f88b3486b8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 28 May 2026 11:45:41 -0700 Subject: [PATCH 1517/1518] security/keys: fix missed RCU read section on lookup commit 43a1e3744548e6fd85873e6fb43e293eb4010694 upstream. Nicholas Carlini reports that the keyring code calls assoc_array_find() in find_key_to_update() without holding the RCU read lock, while the assoc_array_gc() code really is designed around removing the node from the tree and then freeing it after an RCU grace-period. The regular key handling doesn't see this because holding the keyring semaphore hides any lifetime issues, but the persistent key handling uses a different model. Instead of extending the keyring locking, just do the simple RCU locking that the assoc_array was designed for. Reported-by: Nicholas Carlini Cc: David Howells Cc: Jarkko Sakkinen Cc: Paul Moore Cc: James Morris James Morris Cc: Serge E. Hallyn Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- security/keys/keyring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/security/keys/keyring.c b/security/keys/keyring.c index f331725d5a370..df2580072cfe1 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1109,6 +1109,7 @@ key_ref_t find_key_to_update(key_ref_t keyring_ref, kenter("{%d},{%s,%s}", keyring->serial, index_key->type->name, index_key->description); + guard(rcu)(); object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, index_key); From 18ad16ce4a6b2714583fd1e1044c6ea8e53b3519 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 1 Jun 2026 17:51:08 +0200 Subject: [PATCH 1518/1518] Linux 6.18.34 Link: https://lore.kernel.org/r/20260528194638.371537336@linuxfoundation.org Tested-by: Ron Economos Tested-by: Miguel Ojeda Tested-by: Brett A C Sheffield Tested-by: Pavel Machek (CIP) Tested-by: Peter Schneider Tested-by: Wentao Guan Tested-by: Florian Fainelli Tested-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index dc63a98489a54..5087bd6183ddd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 33 +SUBLEVEL = 34 EXTRAVERSION = NAME = Baby Opossum Posse