Merge tag 'drm-xe-fixes-2026-06-11' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

UAPI Changes:

Cross-subsystem Changes:

Core Changes:

Driver Changes:
 - fix oops in suspend/shutdown without display (Jani)
 - RAS fixes (Raag)
 - Use HW_ERR prefix in log (Raag)
 - include all registered queues in TLB invalidation (Tangudu)
 - Fix refcount leak in xe_range_tree in error paths (Wentao)
 - fix job timeout recovery for unstarted jobs and kernel queues (Rodrigo)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/aitt8ZkYmxIT9cdP@gsse-cloud1.jf.intel.com

6 files changed, 79 insertions, 63 deletions

diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index 00dfa68af29a..b17fb698d2f8 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -124,6 +124,15 @@ int xe_display_init_early(struct xe_device *xe)
 
 	intel_display_driver_early_probe(display);
 
+	intel_display_device_info_runtime_init(display);
+
+	/* Display may have been disabled at runtime init */
+	if (!intel_display_device_present(display)) {
+		xe->info.probe_display = false;
+		unset_display_features(xe);
+		return 0;
+	}
+
 	/* Early display init.. */
 	intel_opregion_setup(display);
 
@@ -137,8 +146,6 @@ int xe_display_init_early(struct xe_device *xe)
 
 	intel_bw_init_hw(display);
 
-	intel_display_device_info_runtime_init(display);
-
 	err = intel_display_driver_probe_noirq(display);
 	if (err)
 		goto err_opregion;
diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index e07dc23a155e..c6cd32b7eeda 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -52,7 +52,7 @@ static struct xe_drm_ras_counter *allocate_and_copy_counters(struct xe_device *x
 	struct xe_drm_ras_counter *counter;
 	int i;
 
-	counter = kcalloc(DRM_XE_RAS_ERR_COMP_MAX, sizeof(*counter), GFP_KERNEL);
+	counter = drmm_kcalloc(&xe->drm, DRM_XE_RAS_ERR_COMP_MAX, sizeof(*counter), GFP_KERNEL);
 	if (!counter)
 		return ERR_PTR(-ENOMEM);
 
@@ -100,54 +100,47 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node,
 	return 0;
 }
 
-static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_error_severity severity)
+static void cleanup_node_param(struct drm_ras_node *node)
 {
-	struct drm_ras_node *node = &ras->node[severity];
-
-	kfree(ras->info[severity]);
-	ras->info[severity] = NULL;
-
 	kfree(node->device_name);
 	node->device_name = NULL;
 }
 
+static void cleanup_node(struct drm_device *drm, void *node)
+{
+	drm_ras_node_unregister(node);
+	cleanup_node_param(node);
+}
+
 static int register_nodes(struct xe_device *xe)
 {
 	struct xe_drm_ras *ras = &xe->ras;
-	int i;
+	struct drm_ras_node *node;
+	int i, ret;
 
 	for_each_error_severity(i) {
-		struct drm_ras_node *node = &ras->node[i];
-		int ret;
+		node = &ras->node[i];
 
 		ret = assign_node_params(xe, node, i);
-		if (ret) {
-			cleanup_node_param(ras, i);
-			return ret;
-		}
+		if (ret)
+			goto free_param;
 
 		ret = drm_ras_node_register(node);
-		if (ret) {
-			cleanup_node_param(ras, i);
-			return ret;
-		}
+		if (ret)
+			goto free_param;
+
+		ret = drmm_add_action_or_reset(&xe->drm, cleanup_node, node);
+		if (ret)
+			goto null_info;
 	}
 
 	return 0;
-}
-
-static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg)
-{
-	struct xe_device *xe = arg;
-	struct xe_drm_ras *ras = &xe->ras;
-	int i;
-
-	for_each_error_severity(i) {
-		struct drm_ras_node *node = &ras->node[i];
 
-		drm_ras_node_unregister(node);
-		cleanup_node_param(ras, i);
-	}
+free_param:
+	cleanup_node_param(node);
+null_info:
+	ras->info[i] = NULL;
+	return ret;
 }
 
 /**
@@ -176,11 +169,5 @@ int xe_drm_ras_init(struct xe_device *xe)
 		return err;
 	}
 
-	err = drmm_add_action_or_reset(&xe->drm, xe_drm_ras_unregister_nodes, xe);
-	if (err) {
-		drm_err(&xe->drm, "Failed to add action for Xe DRM RAS (%pe)\n", ERR_PTR(err));
-		return err;
-	}
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index a4a8f0d41fe8..42110e01b7d0 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -157,6 +157,11 @@ static void set_exec_queue_banned(struct xe_exec_queue *q)
 	atomic_or(EXEC_QUEUE_STATE_BANNED, &q->guc->state);
 }
 
+static void clear_exec_queue_banned(struct xe_exec_queue *q)
+{
+	atomic_andnot(EXEC_QUEUE_STATE_BANNED, &q->guc->state);
+}
+
 static bool exec_queue_suspended(struct xe_exec_queue *q)
 {
 	return atomic_read(&q->guc->state) & EXEC_QUEUE_STATE_SUSPENDED;
@@ -1361,7 +1366,8 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job)
 			   xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),
 			   q->guc->id);
 
-		return xe_sched_invalidate_job(job, 2);
+		/* GuC never scheduled this job - let the caller trigger a GT reset. */
+		return true;
 	}
 
 	ctx_timestamp = lower_32_bits(xe_lrc_timestamp(q->lrc[0]));
@@ -1458,6 +1464,21 @@ static void disable_scheduling(struct xe_exec_queue *q, bool immediate)
 			       G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, 1);
 }
 
+/*
+ * Recover via GT reset for a kernel queue, or for a GuC scheduling failure (job
+ * never started) on a queue that was not already killed or banned. An already
+ * banned queue must stay banned, so its unstarted jobs do not clear the ban or
+ * trigger a reset.
+ */
+static bool timeout_needs_gt_reset(struct xe_exec_queue *q, struct xe_sched_job *job,
+				   bool skip_timeout_check)
+{
+	if (q->flags & EXEC_QUEUE_FLAG_KERNEL)
+		return true;
+
+	return !skip_timeout_check && !xe_sched_job_started(job);
+}
+
 static enum drm_gpu_sched_stat
 guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 {
@@ -1606,19 +1627,19 @@ trigger_reset:
 			       xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),
 			       q->guc->id, q->flags);
 
-	/*
-	 * Kernel jobs should never fail, nor should VM jobs if they do
-	 * somethings has gone wrong and the GT needs a reset
-	 */
-	xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_KERNEL,
-		   "Kernel-submitted job timed out\n");
-	xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q),
-		   "VM job timed out on non-killed execqueue\n");
-	if (!wedged && (q->flags & EXEC_QUEUE_FLAG_KERNEL ||
-			(q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q)))) {
-		if (!xe_sched_invalidate_job(job, 2)) {
-			xe_gt_reset_async(q->gt);
-			goto rearm;
+	if (!wedged) {
+		if (timeout_needs_gt_reset(q, job, skip_timeout_check)) {
+			if (!xe_sched_invalidate_job(job, 2)) {
+				clear_exec_queue_banned(q);
+				xe_gt_reset_async(q->gt);
+				goto rearm;
+			}
+			if (q->flags & EXEC_QUEUE_FLAG_KERNEL) {
+				xe_gt_WARN(q->gt, true, "Kernel-submitted job timed out\n");
+				xe_device_declare_wedged(gt_to_xe(q->gt));
+			}
+		} else if (q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q)) {
+			xe_gt_WARN(q->gt, true, "VM job timed out on non-killed execqueue\n");
 		}
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
index ced58f46f846..cf6d106e6036 100644
--- a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
@@ -255,9 +255,8 @@ static int send_tlb_inval_ctx_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno,
 #undef EXEC_QUEUE_COUNT_FULL_THRESHOLD
 
 	/*
-	 * Move exec queues to a temporary list to issue invalidations. The exec
-	 * queue must active and a reference must be taken to prevent concurrent
-	 * deregistrations.
+	 * Move exec queues to a temporary list to issue invalidations. A
+	 * reference must be taken to prevent concurrent deregistrations.
 	 *
 	 * List modification is safe because we hold 'vm->exec_queues.lock' for
 	 * reading, which prevents external modifications. Using a per-GT list
@@ -266,7 +265,7 @@ static int send_tlb_inval_ctx_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno,
 	 */
 	list_for_each_entry_safe(q, next, &vm->exec_queues.list[id],
 				 vm_exec_queue_link) {
-		if (q->ops->active(q) && xe_exec_queue_get_unless_zero(q)) {
+		if (xe_exec_queue_get_unless_zero(q)) {
 			last_q = q;
 			list_move_tail(&q->vm_exec_queue_link, &tlb_inval_list);
 		}
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 2a31b430570e..e869bc3948d9 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -219,9 +219,9 @@ static void log_hw_error(struct xe_tile *tile, const char *name,
 	struct xe_device *xe = tile_to_xe(tile);
 
 	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
-		drm_warn(&xe->drm, "%s %s detected\n", name, severity_str);
+		drm_warn(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
 	else
-		drm_err_ratelimited(&xe->drm, "%s %s detected\n", name, severity_str);
+		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
 }
 
 static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
@@ -231,10 +231,10 @@ static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
 	struct xe_device *xe = tile_to_xe(tile);
 
 	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
-		drm_warn(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
+		drm_warn(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
 			 name, severity_str, i, err);
 	else
-		drm_err_ratelimited(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
+		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
 				    name, severity_str, i, err);
 }
 
@@ -251,9 +251,9 @@ static void log_soc_error(struct xe_tile *tile, const char * const *reg_info,
 
 	if (strcmp(name, "Undefined")) {
 		if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
-			drm_warn(&xe->drm, "%s SOC %s detected", name, severity_str);
+			drm_warn(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
 		else
-			drm_err_ratelimited(&xe->drm, "%s SOC %s detected", name, severity_str);
+			drm_err_ratelimited(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
 		atomic_inc(&info[index].counter);
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c
index 372378e89e98..3d8fa194a7b0 100644
--- a/drivers/gpu/drm/xe/xe_range_fence.c
+++ b/drivers/gpu/drm/xe/xe_range_fence.c
@@ -77,6 +77,8 @@ int xe_range_fence_insert(struct xe_range_fence_tree *tree,
 	} else if (err == 0) {
 		xe_range_fence_tree_insert(rfence, &tree->root);
 		return 0;
+	} else {
+		dma_fence_put(fence);
 	}
 
 free: