Skip to contentSkip to conversation

FAILED: patch "[PATCH] drm/xe: Trigger queue cleanup if not in wedged mode 2" failed to apply to 6.18-stable tree

PATCH [email protected] 1 participant 1 message Mar 21

Subsystems (3)
Stable branch DRM drivers Intel xe
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x e0f82655df6fbb15b318e9d56724cd54b1cfb04d
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026032130-saturday-simplify-bedc@gregkh' --subject-prefix 'PATCH 6.18.y' HEAD^..

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From e0f82655df6fbb15b318e9d56724cd54b1cfb04d Mon Sep 17 00:00:00 2001
From: Matthew Brost <[email protected]>
Date: Tue, 10 Mar 2026 18:50:35 -0400
Subject: [PATCH] drm/xe: Trigger queue cleanup if not in wedged mode 2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The intent of wedging a device is to allow queues to continue running only in wedged mode 2. In other modes, queues should initiate cleanup and signal all remaining fences. Fix xe_guc_submit_wedge to correctly clean up queues when wedge mode != 2.

Fixes 7dbe8af13c18 ("drm/xe: Wedge the entire device")
Cc [email protected]
Reviewed-by Zhanjun Dong <[email protected]>
Signed-off-by Matthew Brost <[email protected]>
Link https://patch.msgid.link/[email protected] open here
(cherry picked from commit e25ba41c8227c5393c16e4aab398076014bd345f)
Signed-off-by Thomas Hellström <[email protected]>
drivers/gpu/drm/xe/xe_guc_submit.c +22 -13
index ef4d37b5c73c..fc4f99d46763 100644
@@ -1271,6 +1271,7 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
  */
 void xe_guc_submit_wedge(struct xe_guc *guc)
 {
+	struct xe_device *xe = guc_to_xe(guc);
 	struct xe_gt *gt = guc_to_gt(guc);
 	struct xe_exec_queue *q;
 	unsigned long index;

@@ -1285,20 +1286,28 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 	if (!guc->submission_state.initialized)
 		return;
 
-	err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
-				       guc_submit_wedged_fini, guc);
-	if (err) {
-		xe_gt_err(gt, "Failed to register clean-up in wedged.mode=%s; "
-			  "Although device is wedged.\n",
-			  xe_wedged_mode_to_string(XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET));
-		return;
-	}
+	if (xe->wedged.mode == 2) {
+		err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
+					       guc_submit_wedged_fini, guc);
+		if (err) {
+			xe_gt_err(gt, "Failed to register clean-up on wedged.mode=2; "
+				  "Although device is wedged.\n");
+			return;
+		}
 
-	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		if (xe_exec_queue_get_unless_zero(q))
-			set_exec_queue_wedged(q);
-	mutex_unlock(&guc->submission_state.lock);
+		mutex_lock(&guc->submission_state.lock);
+		xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+			if (xe_exec_queue_get_unless_zero(q))
+				set_exec_queue_wedged(q);
+		mutex_unlock(&guc->submission_state.lock);
+	} else {
+		/* Forcefully kill any remaining exec queues, signal fences */
+		guc_submit_reset_prepare(guc);
+		xe_guc_submit_stop(guc);
+		xe_guc_softreset(guc);
+		xe_uc_fw_sanitize(&guc->fw);
+		xe_guc_submit_pause_abort(guc);
+	}
 }
 
 static bool guc_submit_hint_wedged(struct xe_guc *guc)