drm/xe: Don't short circuit TDR on jobs not started

Short circuiting TDR on jobs not started is an optimization which is not
required. On LNL we are facing an issue where jobs do not get scheduled
by the GuC if it misses a GGTT page update. When this occurs let the TDR
fire, toggle the scheduling which may get the job unstuck, and print a
warning message. If the TDR fires twice on job that hasn't started,
timeout the job.

v2:
 - Add warning message (Paulo)
 - Add fixes tag (Paulo)
 - Timeout job which hasn't started after TDR firing twice
v3:
 - Include local change
v4:
 - Short circuit check_timeout on job not started
 - use warn level rather than notice (Paulo)

Fixes: 7ddb9403dd74 ("drm/xe: Sample ctx timestamp to determine if jobs have timed out")
Cc: stable@vger.kernel.org
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241025214330.2010521-2-matthew.brost@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

1 files changed, 12 insertions, 6 deletions

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index d2dcc9afd223..ad194fd297dc 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -991,12 +991,22 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w)
 static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job)
 {
 	struct xe_gt *gt = guc_to_gt(exec_queue_to_guc(q));
-	u32 ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
-	u32 ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
+	u32 ctx_timestamp, ctx_job_timestamp;
 	u32 timeout_ms = q->sched_props.job_timeout_ms;
 	u32 diff;
 	u64 running_time_ms;
 
+	if (!xe_sched_job_started(job)) {
+		xe_gt_warn(gt, "Check job timeout: seqno=%u, lrc_seqno=%u, guc_id=%d, not started",
+			   xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),
+			   q->guc->id);
+
+		return xe_sched_invalidate_job(job, 2);
+	}
+
+	ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
+	ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
+
 	/*
 	 * Counter wraps at ~223s at the usual 19.2MHz, be paranoid catch
 	 * possible overflows with a high timeout.
@@ -1126,10 +1136,6 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 		exec_queue_killed_or_banned_or_wedged(q) ||
 		exec_queue_destroyed(q);
 
-	/* Job hasn't started, can't be timed out */
-	if (!skip_timeout_check && !xe_sched_job_started(job))
-		goto rearm;
-
 	/*
 	 * If devcoredump not captured and GuC capture for the job is not ready
 	 * do manual capture first and decide later if we need to use it