All of lore.kernel.org
 help / color / mirror / Atom feed
From: Zhanjun Dong <zhanjun.dong@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Zhanjun Dong <zhanjun.dong@intel.com>,
	stable@vger.kernel.org, Matthew Brost <matthew.brost@intel.com>
Subject: [PATCH v8 3/7] drm/xe: Trigger queue cleanup if not in wedged mode 2
Date: Tue, 24 Feb 2026 11:35:51 -0500	[thread overview]
Message-ID: <20260224163555.218750-4-zhanjun.dong@intel.com> (raw)
In-Reply-To: <20260224163555.218750-1-zhanjun.dong@intel.com>

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: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 35 +++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index c8b59e662c9e..04a575221528 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1319,6 +1319,7 @@ 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;
@@ -1333,20 +1334,28 @@ 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)
-- 
2.34.1


  parent reply	other threads:[~2026-02-24 16:36 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-24 16:35 [PATCH v8 0/7] Attempt to fixup reset, wedge, unload corner cases Zhanjun Dong
2026-02-24 16:35 ` [PATCH v8 1/7] drm/xe: Always kill exec queues in xe_guc_submit_pause_abort Zhanjun Dong
2026-02-24 16:35 ` [PATCH v8 2/7] drm/xe: Forcefully tear down exec queues in GuC submit fini Zhanjun Dong
2026-02-24 16:35 ` Zhanjun Dong [this message]
2026-02-24 16:35 ` [PATCH v8 4/7] drm/xe: Use XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET enum instead of magic number Zhanjun Dong
2026-02-24 16:35 ` [PATCH v8 5/7] drm/xe/guc: Ensure CT state transitions via STOP before DISABLED Zhanjun Dong
2026-02-24 16:35 ` [PATCH v8 6/7] drm/xe/uc: Drop xe_guc_sanitize in favor of managed cleanup Zhanjun Dong
2026-02-24 16:35 ` [PATCH v8 7/7] drm/xe: Open-code GGTT MMIO access protection Zhanjun Dong
2026-03-05 15:22   ` Dong, Zhanjun
2026-02-24 16:43 ` ✓ CI.KUnit: success for Attempt to fixup reset, wedge, unload corner cases Patchwork
2026-02-26  0:43 ` ✓ CI.KUnit: success for Attempt to fixup reset, wedge, unload corner cases (rev2) Patchwork
2026-02-26  1:18 ` ✓ Xe.CI.BAT: " Patchwork
2026-02-26  4:45 ` ✗ Xe.CI.FULL: failure " Patchwork
2026-03-06 21:13 ` ✓ CI.KUnit: success for Attempt to fixup reset, wedge, unload corner cases (rev3) Patchwork
2026-03-06 21:58 ` ✓ Xe.CI.BAT: " Patchwork
2026-03-08  0:26 ` ✗ Xe.CI.FULL: failure " Patchwork
2026-03-09 21:52   ` Dong, Zhanjun

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260224163555.218750-4-zhanjun.dong@intel.com \
    --to=zhanjun.dong@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.