Merge tag 'drm-fixes-2024-01-27' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Lots going on for rc2, ivpu has a bunch of stabilisation and debugging
  work, then amdgpu and xe are the main fixes. i915, exynos have a few,
  then some misc panel and bridge fixes.

  Worth mentioning are three regressions. One of the nouveau fixes in
  6.7 for a serious deadlock had side effects, so I guess we will bring
  back the deadlock until I can figure out what should be done properly.
  There was a scheduler regression vs amdgpu which was reported in a few
  places and is now fixed. There was an i915 vs simpledrm problem
  resulting in black screens, that is reverted also.

  I'll be working on a proper nouveau fix, it kinda looks like one of
  those cases where someone tried to use an atomic where they should
  have probably used a lock, but I'll see.

  fb:
   - fix simpledrm/i915 regression by reverting change

  scheduler:
   - fix regression affecting amdgpu users due to sched draining

  nouveau:
   - revert 6.7 deadlock fix as it has side effects

  dp:
   - fix documentation warning

  ttm:
   - fix dummy page read on some platforms

  bridge:
   - anx7625 suspend fix
   - sii902x: fix probing and audio registration
   - parade-ps8640: fix suspend of bridge, aux fixes
   - samsung-dsim: avoid using FORCE_STOP_STATE

  panel:
   - simple add missing bus flags
   - fix samsung-s6d7aa0 flags

  amdgpu:
   - AC/DC power supply tracking fix
   - Don't show invalid vram vendor data
   - SMU 13.0.x fixes
   - GART fix for umr on systems without VRAM
   - GFX 10/11 UNORD_DISPATCH fixes
   - IPS display fixes (required for S0ix on some platforms)
   - Misc fixes

  i915:
   - DSI sequence revert to fix GitLab #10071 and DP test-pattern fix
   - Drop -Wstringop-overflow (broken on GCC11)

  ivpu:
   - fix recovery/reset support
   - improve submit ioctl stability
   - fix dev open/close races on unbind
   - PLL disable reset fix
   - deprecate context priority param
   - improve debug buffer logging
   - disable buffer sharing across VPU contexts
   - free buffer sgt on unbind
   - fix missing lock around shmem vmap
   - add better boot diagnostics
   - add more debug prints around mapping
   - dump MMU events in case of timeout

  v3d:
   - NULL ptr dereference fix

  exynos:
   - fix stack usage
   - fix incorrect type
   - fix dt typo
   - fix gsc runtime resume

  xe:
   - Make an ops struct static
   - Fix an implicit 0 to NULL conversion
   - A couple of 32-bit fixes
   - A migration coherency fix for Lunar Lake.
   - An error path vm id leak fix
   - Remove PVC references in kunit tests"

* tag 'drm-fixes-2024-01-27' of git://anongit.freedesktop.org/drm/drm: (66 commits)
  Revert "nouveau: push event block/allowing out of the fence context"
  drm: bridge: samsung-dsim: Don't use FORCE_STOP_STATE
  drm/sched: Drain all entities in DRM sched run job worker
  drm/amd/display: "Enable IPS by default"
  drm/amd: Add a DC debug mask for IPS
  drm/amd/display: Disable ips before dc interrupt setting
  drm/amd/display: Replay + IPS + ABM in Full Screen VPB
  drm/amd/display: Add IPS checks before dcn register access
  drm/amd/display: Add Replay IPS register for DMUB command table
  drm/amd/display: Allow IPS2 during Replay
  drm/amdgpu/gfx11: set UNORD_DISPATCH in compute MQDs
  drm/amdgpu/gfx10: set UNORD_DISPATCH in compute MQDs
  drm/amd/amdgpu: Assign GART pages to AMD device mapping
  drm/amd/pm: Fetch current power limit from FW
  drm/amdgpu: Fix null pointer dereference
  drm/amdgpu: Show vram vendor only if available
  drm/amd/pm: update the power cap setting
  drm/amdgpu: Avoid fetching vram vendor information
  drm/amdgpu/pm: Fix the power source flag error
  drm/amd/display: Fix uninitialized variable usage in core_link_ 'read_dpcd() & write_dpcd()' functions
  ...

Author: torvalds

Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml

@@ -85,7 +85,7 @@ allOf:
         clocks:
           minItems: 6
           maxItems: 6
-        regs:
+        reg:
           minItems: 2
           maxItems: 2
 
@@ -99,7 +99,7 @@ allOf:
         clocks:
           minItems: 4
           maxItems: 4
-        regs:
+        reg:
           minItems: 2
           maxItems: 2
 
@@ -116,7 +116,7 @@ allOf:
         clocks:
           minItems: 3
           maxItems: 3
-        regs:
+        reg:
           minItems: 1
           maxItems: 1
 

drivers/accel/ivpu/ivpu_debugfs.c

@@ -102,7 +102,7 @@ static int reset_pending_show(struct seq_file *s, void *v)
 {
 	struct ivpu_device *vdev = seq_to_ivpu(s);
 
-	seq_printf(s, "%d\n", atomic_read(&vdev->pm->in_reset));
+	seq_printf(s, "%d\n", atomic_read(&vdev->pm->reset_pending));
 	return 0;
 }
 
@@ -130,7 +130,9 @@ dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size
 
 	fw->dvfs_mode = dvfs_mode;
 
-	ivpu_pm_schedule_recovery(vdev);
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
 
 	return size;
 }
@@ -190,7 +192,10 @@ fw_profiling_freq_fops_write(struct file *file, const char __user *user_buf,
 		return ret;
 
 	ivpu_hw_profiling_freq_drive(vdev, enable);
-	ivpu_pm_schedule_recovery(vdev);
+
+	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
+	if (ret)
+		return ret;
 
 	return size;
 }
@@ -301,11 +306,18 @@ static ssize_t
 ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
 {
 	struct ivpu_device *vdev = file->private_data;
+	int ret;
 
 	if (!size)
 		return -EINVAL;
 
-	ivpu_pm_schedule_recovery(vdev);
+	ret = ivpu_rpm_get(vdev);
+	if (ret)
+		return ret;
+
+	ivpu_pm_trigger_recovery(vdev, "debugfs");
+	flush_work(&vdev->pm->recovery_work);
+	ivpu_rpm_put(vdev);
 	return size;
 }
 

drivers/accel/ivpu/ivpu_drv.c

@@ -6,6 +6,7 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_accel.h>
 #include <drm/drm_file.h>
@@ -17,6 +18,7 @@
 #include "ivpu_debugfs.h"
 #include "ivpu_drv.h"
 #include "ivpu_fw.h"
+#include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
@@ -65,36 +67,36 @@ struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 	return file_priv;
 }
 
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id)
+static void file_priv_unbind(struct ivpu_device *vdev, struct ivpu_file_priv *file_priv)
 {
-	struct ivpu_file_priv *file_priv;
-
-	xa_lock_irq(&vdev->context_xa);
-	file_priv = xa_load(&vdev->context_xa, id);
-	/* file_priv may still be in context_xa during file_priv_release() */
-	if (file_priv && !kref_get_unless_zero(&file_priv->ref))
-		file_priv = NULL;
-	xa_unlock_irq(&vdev->context_xa);
-
-	if (file_priv)
-		ivpu_dbg(vdev, KREF, "file_priv get by id: ctx %u refcount %u\n",
-			 file_priv->ctx.id, kref_read(&file_priv->ref));
-
-	return file_priv;
+	mutex_lock(&file_priv->lock);
+	if (file_priv->bound) {
+		ivpu_dbg(vdev, FILE, "file_priv unbind: ctx %u\n", file_priv->ctx.id);
+
+		ivpu_cmdq_release_all_locked(file_priv);
+		ivpu_jsm_context_release(vdev, file_priv->ctx.id);
+		ivpu_bo_unbind_all_bos_from_context(vdev, &file_priv->ctx);
+		ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+		file_priv->bound = false;
+		drm_WARN_ON(&vdev->drm, !xa_erase_irq(&vdev->context_xa, file_priv->ctx.id));
+	}
+	mutex_unlock(&file_priv->lock);
 }
 
 static void file_priv_release(struct kref *ref)
 {
 	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
 	struct ivpu_device *vdev = file_priv->vdev;
 
-	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
+	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u bound %d\n",
+		 file_priv->ctx.id, (bool)file_priv->bound);
+
+	pm_runtime_get_sync(vdev->drm.dev);
+	mutex_lock(&vdev->context_list_lock);
+	file_priv_unbind(vdev, file_priv);
+	mutex_unlock(&vdev->context_list_lock);
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 
-	ivpu_cmdq_release_all(file_priv);
-	ivpu_jsm_context_release(vdev, file_priv->ctx.id);
-	ivpu_bo_remove_all_bos_from_context(vdev, &file_priv->ctx);
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-	drm_WARN_ON(&vdev->drm, xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
 	mutex_destroy(&file_priv->lock);
 	kfree(file_priv);
 }
@@ -176,9 +178,6 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
 		args->value = vdev->hw->ranges.user.start;
 		break;
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		args->value = file_priv->priority;
-		break;
 	case DRM_IVPU_PARAM_CONTEXT_ID:
 		args->value = file_priv->ctx.id;
 		break;
@@ -218,17 +217,10 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 
 static int ivpu_set_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct drm_ivpu_param *args = data;
 	int ret = 0;
 
 	switch (args->param) {
-	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
-		if (args->value <= DRM_IVPU_CONTEXT_PRIORITY_REALTIME)
-			file_priv->priority = args->value;
-		else
-			ret = -EINVAL;
-		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -241,50 +233,53 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_file_priv *file_priv;
 	u32 ctx_id;
-	void *old;
-	int ret;
+	int idx, ret;
 
-	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, NULL, vdev->context_xa_limit, GFP_KERNEL);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
-		return ret;
-	}
+	if (!drm_dev_enter(dev, &idx))
+		return -ENODEV;
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
 	if (!file_priv) {
 		ret = -ENOMEM;
-		goto err_xa_erase;
+		goto err_dev_exit;
 	}
 
 	file_priv->vdev = vdev;
-	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
+	file_priv->bound = true;
 	kref_init(&file_priv->ref);
 	mutex_init(&file_priv->lock);
 
+	mutex_lock(&vdev->context_list_lock);
+
+	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, file_priv,
+			   vdev->context_xa_limit, GFP_KERNEL);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
+		goto err_unlock;
+	}
+
 	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
 	if (ret)
-		goto err_mutex_destroy;
+		goto err_xa_erase;
 
-	old = xa_store_irq(&vdev->context_xa, ctx_id, file_priv, GFP_KERNEL);
-	if (xa_is_err(old)) {
-		ret = xa_err(old);
-		ivpu_err(vdev, "Failed to store context %u: %d\n", ctx_id, ret);
-		goto err_ctx_fini;
-	}
+	mutex_unlock(&vdev->context_list_lock);
+	drm_dev_exit(idx);
+
+	file->driver_priv = file_priv;
 
 	ivpu_dbg(vdev, FILE, "file_priv create: ctx %u process %s pid %d\n",
 		 ctx_id, current->comm, task_pid_nr(current));
 
-	file->driver_priv = file_priv;
 	return 0;
 
-err_ctx_fini:
-	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
-err_mutex_destroy:
-	mutex_destroy(&file_priv->lock);
-	kfree(file_priv);
 err_xa_erase:
 	xa_erase_irq(&vdev->context_xa, ctx_id);
+err_unlock:
+	mutex_unlock(&vdev->context_list_lock);
+	mutex_destroy(&file_priv->lock);
+	kfree(file_priv);
+err_dev_exit:
+	drm_dev_exit(idx);
 	return ret;
 }
 
@@ -340,8 +335,6 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 
 	if (!ret)
 		ivpu_dbg(vdev, PM, "VPU ready message received successfully\n");
-	else
-		ivpu_hw_diagnose_failure(vdev);
 
 	return ret;
 }
@@ -369,6 +362,9 @@ int ivpu_boot(struct ivpu_device *vdev)
 	ret = ivpu_wait_for_ready(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
+		ivpu_hw_diagnose_failure(vdev);
+		ivpu_mmu_evtq_dump(vdev);
+		ivpu_fw_log_dump(vdev);
 		return ret;
 	}
 
@@ -540,6 +536,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
 	INIT_LIST_HEAD(&vdev->bo_list);
 
+	ret = drmm_mutex_init(&vdev->drm, &vdev->context_list_lock);
+	if (ret)
+		goto err_xa_destroy;
+
 	ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock);
 	if (ret)
 		goto err_xa_destroy;
@@ -611,14 +611,30 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	return ret;
 }
 
+static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
+{
+	struct ivpu_file_priv *file_priv;
+	unsigned long ctx_id;
+
+	mutex_lock(&vdev->context_list_lock);
+
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv)
+		file_priv_unbind(vdev, file_priv);
+
+	mutex_unlock(&vdev->context_list_lock);
+}
+
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_pm_disable(vdev);
 	ivpu_shutdown(vdev);
 	if (IVPU_WA(d3hot_after_power_off))
 		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
+	ivpu_jobs_abort_all(vdev);
 	ivpu_job_done_consumer_fini(vdev);
 	ivpu_pm_cancel_recovery(vdev);
+	ivpu_bo_unbind_all_user_contexts(vdev);
 
 	ivpu_ipc_fini(vdev);
 	ivpu_fw_fini(vdev);

drivers/accel/ivpu/ivpu_drv.h

@@ -56,6 +56,7 @@
 #define IVPU_DBG_JSM	 BIT(10)
 #define IVPU_DBG_KREF	 BIT(11)
 #define IVPU_DBG_RPM	 BIT(12)
+#define IVPU_DBG_MMU_MAP BIT(13)
 
 #define ivpu_err(vdev, fmt, ...) \
 	drm_err(&(vdev)->drm, "%s(): " fmt, __func__, ##__VA_ARGS__)
@@ -114,6 +115,7 @@ struct ivpu_device {
 
 	struct ivpu_mmu_context gctx;
 	struct ivpu_mmu_context rctx;
+	struct mutex context_list_lock; /* Protects user context addition/removal */
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
 
@@ -145,8 +147,8 @@ struct ivpu_file_priv {
 	struct mutex lock; /* Protects cmdq */
 	struct ivpu_cmdq *cmdq[IVPU_NUM_ENGINES];
 	struct ivpu_mmu_context ctx;
-	u32 priority;
 	bool has_mmu_faults;
+	bool bound;
 };
 
 extern int ivpu_dbg_mask;
@@ -162,7 +164,6 @@ extern bool ivpu_disable_mmu_cont_pages;
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
-struct ivpu_file_priv *ivpu_file_priv_get_by_ctx_id(struct ivpu_device *vdev, unsigned long id);
 void ivpu_file_priv_put(struct ivpu_file_priv **link);
 
 int ivpu_boot(struct ivpu_device *vdev);