Merge remote-tracking branch 'drm_xe_push/drm-xe-next' into drm-tip

# Conflicts:
#	drivers/gpu/drm/xe/display/xe_display.c

17 files changed, 142 insertions, 78 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index 70ced57ab102..a7b4cf8b6d50 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -519,6 +519,19 @@ bool intel_fb_needs_64k_phys(u64 modifier)
 				      INTEL_PLANE_CAP_NEED64K_PHYS);
 }
 
+/**
+ * intel_fb_is_tile4_modifier: Check if a modifier is a tile4 modifier type
+ * @modifier: Modifier to check
+ *
+ * Returns:
+ * Returns %true if @modifier is a tile4 modifier.
+ */
+bool intel_fb_is_tile4_modifier(u64 modifier)
+{
+	return plane_caps_contain_any(lookup_modifier(modifier)->plane_caps,
+				      INTEL_PLANE_CAP_TILING_4);
+}
+
 static bool check_modifier_display_ver_range(const struct intel_modifier_desc *md,
 					     u8 display_ver_from, u8 display_ver_until)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_fb.h b/drivers/gpu/drm/i915/display/intel_fb.h
index 8240febff84c..d78993e5eb62 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.h
+++ b/drivers/gpu/drm/i915/display/intel_fb.h
@@ -36,6 +36,7 @@ bool intel_fb_is_ccs_modifier(u64 modifier);
 bool intel_fb_is_rc_ccs_cc_modifier(u64 modifier);
 bool intel_fb_is_mc_ccs_modifier(u64 modifier);
 bool intel_fb_needs_64k_phys(u64 modifier);
+bool intel_fb_is_tile4_modifier(u64 modifier);
 
 bool intel_fb_is_ccs_aux_plane(const struct drm_framebuffer *fb, int color_plane);
 int intel_fb_rc_ccs_cc_plane(const struct drm_framebuffer *fb);
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 9557b08ca2e2..a0a7ed01415a 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1618,6 +1618,17 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
+	/*
+	 * Display20 onward tile4 hflip is not supported
+	 */
+	if (rotation & DRM_MODE_REFLECT_X &&
+	    intel_fb_is_tile4_modifier(fb->modifier) &&
+	    DISPLAY_VER(dev_priv) >= 20) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "horizontal flip is not supported with tile4 surface formats\n");
+		return -EINVAL;
+	}
+
 	if (drm_rotation_90_or_270(rotation)) {
 		if (!intel_fb_supports_90_270_rotation(to_intel_framebuffer(fb))) {
 			drm_dbg_kms(&dev_priv->drm,
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h
index cb6c7598824b..9c4cf050059a 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h
@@ -29,7 +29,7 @@ static inline int i915_gem_stolen_insert_node_in_range(struct xe_device *xe,
 
 	bo = xe_bo_create_locked_range(xe, xe_device_get_root_tile(xe),
 				       NULL, size, start, end,
-				       ttm_bo_type_kernel, flags);
+				       ttm_bo_type_kernel, flags, 0);
 	if (IS_ERR(bo)) {
 		err = PTR_ERR(bo);
 		bo = NULL;
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index 957ae763531d..695c27ac6b0f 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -345,6 +345,9 @@ static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime)
 	intel_opregion_suspend(display, s2idle ? PCI_D1 : PCI_D3cold);
 
 	intel_dmc_suspend(display);
+
+	if (runtime && has_display(xe))
+		intel_hpd_poll_enable(xe);
 }
 
 void xe_display_pm_suspend(struct xe_device *xe)
@@ -379,7 +382,7 @@ void xe_display_pm_shutdown(struct xe_device *xe)
 
 	intel_opregion_suspend(display, PCI_D3cold);
 
-	intel_dmc_suspend(xe);
+	intel_dmc_suspend(display);
 }
 
 void xe_display_pm_runtime_suspend(struct xe_device *xe)
@@ -387,8 +390,10 @@ void xe_display_pm_runtime_suspend(struct xe_device *xe)
 	if (!xe->info.probe_display)
 		return;
 
-	if (xe->d3cold.allowed)
+	if (xe->d3cold.allowed) {
 		__xe_display_pm_suspend(xe, true);
+		return;
+	}
 
 	intel_hpd_poll_enable(xe);
 }
@@ -453,9 +458,11 @@ static void __xe_display_pm_resume(struct xe_device *xe, bool runtime)
 		intel_display_driver_resume(xe);
 		drm_kms_helper_poll_enable(&xe->drm);
 		intel_display_driver_enable_user_access(xe);
-		intel_hpd_poll_disable(xe);
 	}
 
+	if (has_display(xe))
+		intel_hpd_poll_disable(xe);
+
 	intel_opregion_resume(display);
 
 	if (!runtime)
@@ -474,10 +481,13 @@ void xe_display_pm_runtime_resume(struct xe_device *xe)
 	if (!xe->info.probe_display)
 		return;
 
-	intel_hpd_poll_disable(xe);
-
-	if (xe->d3cold.allowed)
+	if (xe->d3cold.allowed) {
 		__xe_display_pm_resume(xe, true);
+		return;
+	}
+
+	intel_hpd_init(xe);
+	intel_hpd_poll_disable(xe);
 }
 
 
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 79dbbbe03c7f..761510ae0690 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -79,7 +79,8 @@ write_dpt_remapped(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs,
 
 static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 			       const struct i915_gtt_view *view,
-			       struct i915_vma *vma)
+			       struct i915_vma *vma,
+			       u64 physical_alignment)
 {
 	struct xe_device *xe = to_xe_device(fb->base.dev);
 	struct xe_tile *tile0 = xe_device_get_root_tile(xe);
@@ -99,23 +100,29 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 				 XE_PAGE_SIZE);
 
 	if (IS_DGFX(xe))
-		dpt = xe_bo_create_pin_map(xe, tile0, NULL, dpt_size,
-					   ttm_bo_type_kernel,
-					   XE_BO_FLAG_VRAM0 |
-					   XE_BO_FLAG_GGTT |
-					   XE_BO_FLAG_PAGETABLE);
+		dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL,
+						      dpt_size, ~0ull,
+						      ttm_bo_type_kernel,
+						      XE_BO_FLAG_VRAM0 |
+						      XE_BO_FLAG_GGTT |
+						      XE_BO_FLAG_PAGETABLE,
+						      physical_alignment);
 	else
-		dpt = xe_bo_create_pin_map(xe, tile0, NULL, dpt_size,
-					   ttm_bo_type_kernel,
-					   XE_BO_FLAG_STOLEN |
-					   XE_BO_FLAG_GGTT |
-					   XE_BO_FLAG_PAGETABLE);
+		dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL,
+						      dpt_size,  ~0ull,
+						      ttm_bo_type_kernel,
+						      XE_BO_FLAG_STOLEN |
+						      XE_BO_FLAG_GGTT |
+						      XE_BO_FLAG_PAGETABLE,
+						      physical_alignment);
 	if (IS_ERR(dpt))
-		dpt = xe_bo_create_pin_map(xe, tile0, NULL, dpt_size,
-					   ttm_bo_type_kernel,
-					   XE_BO_FLAG_SYSTEM |
-					   XE_BO_FLAG_GGTT |
-					   XE_BO_FLAG_PAGETABLE);
+		dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL,
+						      dpt_size,  ~0ull,
+						      ttm_bo_type_kernel,
+						      XE_BO_FLAG_SYSTEM |
+						      XE_BO_FLAG_GGTT |
+						      XE_BO_FLAG_PAGETABLE,
+						      physical_alignment);
 	if (IS_ERR(dpt))
 		return PTR_ERR(dpt);
 
@@ -184,7 +191,8 @@ write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo
 
 static int __xe_pin_fb_vma_ggtt(const struct intel_framebuffer *fb,
 				const struct i915_gtt_view *view,
-				struct i915_vma *vma)
+				struct i915_vma *vma,
+				u64 physical_alignment)
 {
 	struct drm_gem_object *obj = intel_fb_bo(&fb->base);
 	struct xe_bo *bo = gem_to_xe_bo(obj);
@@ -266,7 +274,8 @@ out:
 }
 
 static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
-					const struct i915_gtt_view *view)
+					const struct i915_gtt_view *view,
+					u64 physical_alignment)
 {
 	struct drm_device *dev = fb->base.dev;
 	struct xe_device *xe = to_xe_device(dev);
@@ -315,9 +324,9 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 
 	vma->bo = bo;
 	if (intel_fb_uses_dpt(&fb->base))
-		ret = __xe_pin_fb_vma_dpt(fb, view, vma);
+		ret = __xe_pin_fb_vma_dpt(fb, view, vma, physical_alignment);
 	else
-		ret = __xe_pin_fb_vma_ggtt(fb, view, vma);
+		ret = __xe_pin_fb_vma_ggtt(fb, view, vma,  physical_alignment);
 	if (ret)
 		goto err_unpin;
 
@@ -358,7 +367,7 @@ intel_fb_pin_to_ggtt(const struct drm_framebuffer *fb,
 {
 	*out_flags = 0;
 
-	return __xe_pin_fb_vma(to_intel_framebuffer(fb), view);
+	return __xe_pin_fb_vma(to_intel_framebuffer(fb), view, phys_alignment);
 }
 
 void intel_fb_unpin_vma(struct i915_vma *vma, unsigned long flags)
@@ -372,11 +381,15 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state)
 	struct drm_gem_object *obj = intel_fb_bo(fb);
 	struct xe_bo *bo = gem_to_xe_bo(obj);
 	struct i915_vma *vma;
+	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	u64 phys_alignment = plane->min_alignment(plane, fb, 0);
 
 	/* We reject creating !SCANOUT fb's, so this is weird.. */
 	drm_WARN_ON(bo->ttm.base.dev, !(bo->flags & XE_BO_FLAG_SCANOUT));
 
-	vma = __xe_pin_fb_vma(to_intel_framebuffer(fb), &plane_state->view.gtt);
+	vma = __xe_pin_fb_vma(intel_fb, &plane_state->view.gtt, phys_alignment);
+
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index c74c121ea7bb..5b232f2951b1 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1454,7 +1454,8 @@ static struct xe_bo *
 __xe_bo_create_locked(struct xe_device *xe,
 		      struct xe_tile *tile, struct xe_vm *vm,
 		      size_t size, u64 start, u64 end,
-		      u16 cpu_caching, enum ttm_bo_type type, u32 flags)
+		      u16 cpu_caching, enum ttm_bo_type type, u32 flags,
+		      u64 alignment)
 {
 	struct xe_bo *bo = NULL;
 	int err;
@@ -1483,6 +1484,8 @@ __xe_bo_create_locked(struct xe_device *xe,
 	if (IS_ERR(bo))
 		return bo;
 
+	bo->min_align = alignment;
+
 	/*
 	 * Note that instead of taking a reference no the drm_gpuvm_resv_bo(),
 	 * to ensure the shared resv doesn't disappear under the bo, the bo
@@ -1523,16 +1526,18 @@ struct xe_bo *
 xe_bo_create_locked_range(struct xe_device *xe,
 			  struct xe_tile *tile, struct xe_vm *vm,
 			  size_t size, u64 start, u64 end,
-			  enum ttm_bo_type type, u32 flags)
+			  enum ttm_bo_type type, u32 flags, u64 alignment)
 {
-	return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, flags);
+	return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type,
+				     flags, alignment);
 }
 
 struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile,
 				  struct xe_vm *vm, size_t size,
 				  enum ttm_bo_type type, u32 flags)
 {
-	return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type, flags);
+	return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type,
+				     flags, 0);
 }
 
 struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile,
@@ -1542,7 +1547,7 @@ struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile,
 {
 	struct xe_bo *bo = __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL,
 						 cpu_caching, ttm_bo_type_device,
-						 flags | XE_BO_FLAG_USER);
+						 flags | XE_BO_FLAG_USER, 0);
 	if (!IS_ERR(bo))
 		xe_bo_unlock_vm_held(bo);
 
@@ -1566,6 +1571,17 @@ struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile
 				      size_t size, u64 offset,
 				      enum ttm_bo_type type, u32 flags)
 {
+	return xe_bo_create_pin_map_at_aligned(xe, tile, vm, size, offset,
+					       type, flags, 0);
+}
+
+struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe,
+					      struct xe_tile *tile,
+					      struct xe_vm *vm,
+					      size_t size, u64 offset,
+					      enum ttm_bo_type type, u32 flags,
+					      u64 alignment)
+{
 	struct xe_bo *bo;
 	int err;
 	u64 start = offset == ~0ull ? 0 : offset;
@@ -1576,7 +1592,8 @@ struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile
 		flags |= XE_BO_FLAG_GGTT;
 
 	bo = xe_bo_create_locked_range(xe, tile, vm, size, start, end, type,
-				       flags | XE_BO_FLAG_NEEDS_CPU_ACCESS);
+				       flags | XE_BO_FLAG_NEEDS_CPU_ACCESS,
+				       alignment);
 	if (IS_ERR(bo))
 		return bo;
 
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 31f4ba3bd8c1..7fa44a0138b0 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -77,7 +77,7 @@ struct xe_bo *
 xe_bo_create_locked_range(struct xe_device *xe,
 			  struct xe_tile *tile, struct xe_vm *vm,
 			  size_t size, u64 start, u64 end,
-			  enum ttm_bo_type type, u32 flags);
+			  enum ttm_bo_type type, u32 flags, u64 alignment);
 struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile,
 				  struct xe_vm *vm, size_t size,
 				  enum ttm_bo_type type, u32 flags);
@@ -94,6 +94,12 @@ struct xe_bo *xe_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile,
 struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile,
 				      struct xe_vm *vm, size_t size, u64 offset,
 				      enum ttm_bo_type type, u32 flags);
+struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe,
+					      struct xe_tile *tile,
+					      struct xe_vm *vm,
+					      size_t size, u64 offset,
+					      enum ttm_bo_type type, u32 flags,
+					      u64 alignment);
 struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
 				     const void *data, size_t size,
 				     enum ttm_bo_type type, u32 flags);
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 8b9201775081..13c6d8a69e91 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -76,6 +76,11 @@ struct xe_bo {
 
 	/** @vram_userfault_link: Link into @mem_access.vram_userfault.list */
 		struct list_head vram_userfault_link;
+
+	/** @min_align: minimum alignment needed for this BO if different
+	 * from default
+	 */
+	u64 min_align;
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 7b38485817dc..f23ac1e2ed88 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -41,11 +41,6 @@
  * user knows an exec writes to a BO and reads from the BO in the next exec, it
  * is the user's responsibility to pass in / out fence between the two execs).
  *
- * Implicit dependencies for external BOs are handled by using the dma-buf
- * implicit dependency uAPI (TODO: add link). To make this works each exec must
- * install the job's fence into the DMA_RESV_USAGE_WRITE slot of every external
- * BO mapped in the VM.
- *
  * We do not allow a user to trigger a bind at exec time rather we have a VM
  * bind IOCTL which uses the same in / out fence interface as exec. In that
  * sense, a VM bind is basically the same operation as an exec from the user
@@ -59,8 +54,8 @@
  * behind any pending kernel operations on any external BOs in VM or any BOs
  * private to the VM. This is accomplished by the rebinds waiting on BOs
  * DMA_RESV_USAGE_KERNEL slot (kernel ops) and kernel ops waiting on all BOs
- * slots (inflight execs are in the DMA_RESV_USAGE_BOOKING for private BOs and
- * in DMA_RESV_USAGE_WRITE for external BOs).
+ * slots (inflight execs are in the DMA_RESV_USAGE_BOOKKEEP for private BOs and
+ * for external BOs).
  *
  * Rebinds / dma-resv usage applies to non-compute mode VMs only as for compute
  * mode VMs we use preempt fences and a rebind worker (TODO: add link).
@@ -304,7 +299,8 @@ retry:
 	xe_sched_job_arm(job);
 	if (!xe_vm_in_lr_mode(vm))
 		drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, &job->drm.s_fence->finished,
-					 DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_WRITE);
+					 DMA_RESV_USAGE_BOOKKEEP,
+					 DMA_RESV_USAGE_BOOKKEEP);
 
 	for (i = 0; i < num_syncs; i++) {
 		xe_sync_entry_signal(&syncs[i], &job->drm.s_fence->finished);
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 47bfd9d2635d..1b3178226987 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -603,7 +603,7 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 				  u64 start, u64 end)
 {
 	int err;
-	u64 alignment = XE_PAGE_SIZE;
+	u64 alignment = bo->min_align > 0 ? bo->min_align : XE_PAGE_SIZE;
 
 	if (xe_bo_is_vram(bo) && ggtt->flags & XE_GGTT_FLAGS_64K)
 		alignment = SZ_64K;
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index 5ad5629a6c60..64b2ae6839db 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -63,7 +63,9 @@ xe_sched_invalidate_job(struct xe_sched_job *job, int threshold)
 static inline void xe_sched_add_pending_job(struct xe_gpu_scheduler *sched,
 					    struct xe_sched_job *job)
 {
+	spin_lock(&sched->base.job_list_lock);
 	list_add(&job->drm.list, &sched->base.pending_list);
+	spin_unlock(&sched->base.job_list_lock);
 }
 
 static inline
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 93921f04153f..cc70f448d879 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -122,7 +122,7 @@ void xe_guc_log_snapshot_free(struct xe_guc_log_snapshot *snapshot)
 	if (!snapshot)
 		return;
 
-	if (!snapshot->copy) {
+	if (snapshot->copy) {
 		for (i = 0; i < snapshot->num_chunks; i++)
 			kfree(snapshot->copy[i]);
 		kfree(snapshot->copy);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 443d6c6e402a..79729f6650ed 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1032,10 +1032,13 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 
 	/*
 	 * TDR has fired before free job worker. Common if exec queue
-	 * immediately closed after last fence signaled.
+	 * immediately closed after last fence signaled. Add back to pending
+	 * list so job can be freed and kick scheduler ensuring free job is not
+	 * lost.
 	 */
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags)) {
-		guc_exec_queue_free_job(drm_job);
+		xe_sched_add_pending_job(sched, job);
+		xe_sched_submission_start(sched);
 
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 158629971eab..5093a243e9fe 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -85,16 +85,13 @@ static __ktime_func_t __clock_id_to_func(clockid_t clk_id)
 }
 
 static void
-__read_timestamps(struct xe_gt *gt,
-		  struct xe_reg lower_reg,
-		  struct xe_reg upper_reg,
-		  u64 *engine_ts,
-		  u64 *cpu_ts,
-		  u64 *cpu_delta,
-		  __ktime_func_t cpu_clock)
+hwe_read_timestamp(struct xe_hw_engine *hwe, u64 *engine_ts, u64 *cpu_ts,
+		   u64 *cpu_delta, __ktime_func_t cpu_clock)
 {
-	struct xe_mmio *mmio = &gt->mmio;
+	struct xe_mmio *mmio = &hwe->gt->mmio;
 	u32 upper, lower, old_upper, loop = 0;
+	struct xe_reg upper_reg = RING_TIMESTAMP_UDW(hwe->mmio_base),
+		      lower_reg = RING_TIMESTAMP(hwe->mmio_base);
 
 	upper = xe_mmio_read32(mmio, upper_reg);
 	do {
@@ -155,28 +152,21 @@ query_engine_cycles(struct xe_device *xe,
 	if (xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL))
 		return -EIO;
 
-	__read_timestamps(gt,
-			  RING_TIMESTAMP(hwe->mmio_base),
-			  RING_TIMESTAMP_UDW(hwe->mmio_base),
-			  &resp.engine_cycles,
-			  &resp.cpu_timestamp,
-			  &resp.cpu_delta,
-			  cpu_clock);
+	hwe_read_timestamp(hwe, &resp.engine_cycles, &resp.cpu_timestamp,
+			   &resp.cpu_delta, cpu_clock);
 
 	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	resp.width = 36;
 
-	/* Only write to the output fields of user query */
-	if (put_user(resp.cpu_timestamp, &query_ptr->cpu_timestamp))
-		return -EFAULT;
-
-	if (put_user(resp.cpu_delta, &query_ptr->cpu_delta))
-		return -EFAULT;
-
-	if (put_user(resp.engine_cycles, &query_ptr->engine_cycles))
-		return -EFAULT;
+	if (GRAPHICS_VER(xe) >= 20)
+		resp.width = 64;
+	else
+		resp.width = 36;
 
-	if (put_user(resp.width, &query_ptr->width))
+	/* Only write to the output fields of user query */
+	if (put_user(resp.cpu_timestamp, &query_ptr->cpu_timestamp) ||
+	    put_user(resp.cpu_delta, &query_ptr->cpu_delta) ||
+	    put_user(resp.engine_cycles, &query_ptr->engine_cycles) ||
+	    put_user(resp.width, &query_ptr->width))
 		return -EFAULT;
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index bb3c2a830362..c6cf227ead40 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -58,7 +58,7 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 	if (!access_ok(ptr, sizeof(*ptr)))
 		return ERR_PTR(-EFAULT);
 
-	ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
+	ufence = kzalloc(sizeof(*ufence), GFP_KERNEL);
 	if (!ufence)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/gpu/drm/xe/xe_wait_user_fence.c b/drivers/gpu/drm/xe/xe_wait_user_fence.c
index d46fa8374980..f5deb81eba01 100644
--- a/drivers/gpu/drm/xe/xe_wait_user_fence.c
+++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c
@@ -169,9 +169,6 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data,
 			args->timeout = 0;
 	}
 
-	if (!timeout && !(err < 0))
-		err = -ETIME;
-
 	if (q)
 		xe_exec_queue_put(q);