Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v2] drm/xe: Don't restart parallel queues multiple times on GT reset
@ 2024-10-22 10:35 Nirmoy Das
  2024-10-22 11:39 ` ✓ CI.Patch_applied: success for drm/xe: Don't restart parallel queues multiple times on GT reset (rev2) Patchwork
                   ` (8 more replies)
  0 siblings, 9 replies; 11+ messages in thread
From: Nirmoy Das @ 2024-10-22 10:35 UTC (permalink / raw)
  To: intel-xe
  Cc: Nirmoy Das, Jonathan Cavitt, Himal Prasad Ghimiray, Matthew Auld,
	Matthew Brost, Tejas Upadhyay

In case of parallel submissions multiple GuC id will point to the
same exec queue and on GT reset such exec queues will get restarted
multiple times which is not desirable.

v2: don't use exec_queue_enabled() which could race,
    do the same for xe_guc_submit_stop (Matt B)

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2295
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 0b81972ff651..0a7c4cb9272d 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1745,8 +1745,13 @@ void xe_guc_submit_stop(struct xe_guc *guc)
 
 	mutex_lock(&guc->submission_state.lock);
 
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to stop parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_stop(guc, q);
+	}
 
 	mutex_unlock(&guc->submission_state.lock);
 
@@ -1784,8 +1789,13 @@ int xe_guc_submit_start(struct xe_guc *guc)
 
 	mutex_lock(&guc->submission_state.lock);
 	atomic_dec(&guc->submission_state.stopped);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to start parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_start(q);
+	}
 	mutex_unlock(&guc->submission_state.lock);
 
 	wake_up_all(&guc->ct.wq);
-- 
2.46.0


^ permalink raw reply related	[flat|nested] 11+ messages in thread
end of thread, other threads:[~2024-10-23 11:30 UTC | newest]

Thread overview: 11+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-10-22 10:35 [PATCH v2] drm/xe: Don't restart parallel queues multiple times on GT reset Nirmoy Das
2024-10-22 11:39 ` ✓ CI.Patch_applied: success for drm/xe: Don't restart parallel queues multiple times on GT reset (rev2) Patchwork
2024-10-22 11:39 ` ✓ CI.checkpatch: " Patchwork
2024-10-22 11:40 ` ✓ CI.KUnit: " Patchwork
2024-10-22 11:51 ` ✓ CI.Build: " Patchwork
2024-10-22 11:54 ` ✓ CI.Hooks: " Patchwork
2024-10-22 11:55 ` ✓ CI.checksparse: " Patchwork
2024-10-22 12:16 ` ✓ CI.BAT: " Patchwork
2024-10-22 14:34 ` ✗ CI.FULL: failure " Patchwork
2024-10-23 11:30   ` Nirmoy Das
2024-10-22 17:52 ` [PATCH v2] drm/xe: Don't restart parallel queues multiple times on GT reset Matthew Brost

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox