From 5459e16b215c18529782e7746992653f00de0779 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 24 Jun 2025 10:41:03 -0700 Subject: [PATCH] drm/xe: Do not wedge device on killed exec queues When a user closes an exec queue or interrupts an app with Ctrl-C, this does not warrant wedging the device in mode 2. Avoid this by skipping the wedge check for killed exec queues in the TDR and LR exec queue cleanup worker. Signed-off-by: Matthew Brost Reviewed-by: Rodrigo Vivi Link: https://lore.kernel.org/r/20250624174103.2707941-1-matthew.brost@intel.com (cherry picked from commit 5a2f117a80c207372513ca8964eeb178874f4990) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_guc_submit.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 9567f6700cf21..2ac87ff4a057f 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -891,12 +891,13 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w) struct xe_exec_queue *q = ge->q; struct xe_guc *guc = exec_queue_to_guc(q); struct xe_gpu_scheduler *sched = &ge->sched; - bool wedged; + bool wedged = false; xe_gt_assert(guc_to_gt(guc), xe_exec_queue_is_lr(q)); trace_xe_exec_queue_lr_cleanup(q); - wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); + if (!exec_queue_killed(q)) + wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); /* Kill the run_job / process_msg entry points */ xe_sched_submission_stop(sched); @@ -1070,7 +1071,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) int err = -ETIME; pid_t pid = -1; int i = 0; - bool wedged, skip_timeout_check; + bool wedged = false, skip_timeout_check; /* * TDR has fired before free job worker. Common if exec queue @@ -1116,7 +1117,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) * doesn't work for SRIOV. For now assuming timeouts in wedged mode are * genuine timeouts. */ - wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); + if (!exec_queue_killed(q)) + wedged = guc_submit_hint_wedged(exec_queue_to_guc(q)); /* Engine state now stable, disable scheduling to check timestamp */ if (!wedged && exec_queue_registered(q)) { -- 2.47.2