Merge tag 'drm-xe-fixes-2025-05-01' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

Driver Changes:
- Eustall locking fix and disabling on VF
- Documentation fix kernel version supporting hwmon entries
- SVM fixes on error handling

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/fqkoqvo62fbkvw6xoxoxutzozqksxxudbmqacjm3durid2pkak@imlxghgrk3ob

Author: airlied

Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon

@@ -111,15 +111,15 @@ Description:	RO. Package current voltage in millivolt.
 
 What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/temp2_input
 Date:		March 2025
-KernelVersion:	6.14
+KernelVersion:	6.15
 Contact:	intel-xe@lists.freedesktop.org
 Description:	RO. Package temperature in millidegree Celsius.
 
 		Only supported for particular Intel Xe graphics platforms.
 
 What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/temp3_input
 Date:		March 2025
-KernelVersion:	6.14
+KernelVersion:	6.15
 Contact:	intel-xe@lists.freedesktop.org
 Description:	RO. VRAM temperature in millidegree Celsius.
 

drivers/gpu/drm/drm_gpusvm.c

@@ -1469,9 +1469,9 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
 		}
 		i += 1 << order;
 		num_dma_mapped = i;
+		range->flags.has_dma_mapping = true;
 	}
 
-	range->flags.has_dma_mapping = true;
 	if (zdd) {
 		range->flags.has_devmem_pages = true;
 		range->dpagemap = dpagemap;

drivers/gpu/drm/xe/xe_eu_stall.c

@@ -52,6 +52,8 @@ struct xe_eu_stall_data_stream {
 
 	struct xe_gt *gt;
 	struct xe_bo *bo;
+	/* Lock to protect data buffer pointers */
+	struct mutex xecore_buf_lock;
 	struct per_xecore_buf *xecore_buf;
 	struct {
 		bool reported_to_user;
@@ -208,6 +210,9 @@ int xe_eu_stall_init(struct xe_gt *gt)
 	struct xe_device *xe = gt_to_xe(gt);
 	int ret;
 
+	if (!xe_eu_stall_supported_on_platform(xe))
+		return 0;
+
 	gt->eu_stall = kzalloc(sizeof(*gt->eu_stall), GFP_KERNEL);
 	if (!gt->eu_stall) {
 		ret = -ENOMEM;
@@ -378,7 +383,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream)
 	u16 group, instance;
 	unsigned int xecore;
 
-	mutex_lock(&gt->eu_stall->stream_lock);
+	mutex_lock(&stream->xecore_buf_lock);
 	for_each_dss_steering(xecore, gt, group, instance) {
 		xecore_buf = &stream->xecore_buf[xecore];
 		read_ptr = xecore_buf->read;
@@ -396,7 +401,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream)
 			set_bit(xecore, stream->data_drop.mask);
 		xecore_buf->write = write_ptr;
 	}
-	mutex_unlock(&gt->eu_stall->stream_lock);
+	mutex_unlock(&stream->xecore_buf_lock);
 
 	return min_data_present;
 }
@@ -511,11 +516,13 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st
 	unsigned int xecore;
 	int ret = 0;
 
+	mutex_lock(&stream->xecore_buf_lock);
 	if (bitmap_weight(stream->data_drop.mask, XE_MAX_DSS_FUSE_BITS)) {
 		if (!stream->data_drop.reported_to_user) {
 			stream->data_drop.reported_to_user = true;
 			xe_gt_dbg(gt, "EU stall data dropped in XeCores: %*pb\n",
 				  XE_MAX_DSS_FUSE_BITS, stream->data_drop.mask);
+			mutex_unlock(&stream->xecore_buf_lock);
 			return -EIO;
 		}
 		stream->data_drop.reported_to_user = false;
@@ -527,6 +534,7 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st
 		if (ret || count == total_size)
 			break;
 	}
+	mutex_unlock(&stream->xecore_buf_lock);
 	return total_size ?: (ret ?: -EAGAIN);
 }
 
@@ -583,6 +591,7 @@ static void xe_eu_stall_stream_free(struct xe_eu_stall_data_stream *stream)
 {
 	struct xe_gt *gt = stream->gt;
 
+	mutex_destroy(&stream->xecore_buf_lock);
 	gt->eu_stall->stream = NULL;
 	kfree(stream);
 }
@@ -718,6 +727,7 @@ static int xe_eu_stall_stream_init(struct xe_eu_stall_data_stream *stream,
 	}
 
 	init_waitqueue_head(&stream->poll_wq);
+	mutex_init(&stream->xecore_buf_lock);
 	INIT_DELAYED_WORK(&stream->buf_poll_work, eu_stall_data_buf_poll_work_fn);
 	stream->per_xecore_buf_size = per_xecore_buf_size;
 	stream->sampling_rate_mult = props->sampling_rate_mult;

drivers/gpu/drm/xe/xe_eu_stall.h

@@ -7,6 +7,7 @@
 #define __XE_EU_STALL_H__
 
 #include "xe_gt_types.h"
+#include "xe_sriov.h"
 
 size_t xe_eu_stall_get_per_xecore_buf_size(void);
 size_t xe_eu_stall_data_record_size(struct xe_device *xe);
@@ -19,6 +20,6 @@ int xe_eu_stall_stream_open(struct drm_device *dev,
 
 static inline bool xe_eu_stall_supported_on_platform(struct xe_device *xe)
 {
-	return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20;
+	return !IS_SRIOV_VF(xe) && (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20);
 }
 #endif

drivers/gpu/drm/xe/xe_guc_capture.c

@@ -359,7 +359,7 @@ static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
 
 	ext->reg = XE_REG(extlist->reg.__reg.addr);
 	ext->flags = FIELD_PREP(GUC_REGSET_STEERING_NEEDED, 1);
-	ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
+	ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
 	ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
 	ext->regname = extlist->name;
 }

drivers/gpu/drm/xe/xe_svm.c

@@ -79,7 +79,7 @@ xe_svm_range_alloc(struct drm_gpusvm *gpusvm)
 
 	range = kzalloc(sizeof(*range), GFP_KERNEL);
 	if (!range)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	INIT_LIST_HEAD(&range->garbage_collector_link);
 	xe_vm_get(gpusvm_to_vm(gpusvm));