drm/xe: Don't short circuit TDR on jobs not started
Subsystems (2)
Matthew Brost
maintainerPATCH 1/1 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
Fixes 7ddb9403dd74 ("drm/xe: Sample ctx timestamp to determine if jobs have timed out")
Cc Paulo Zanoni <[email protected]>
Signed-off-by Matthew Brost <[email protected]>
--- drivers/gpu/drm/xe/xe_guc_submit.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-)
drivers/gpu/drm/xe/xe_guc_submit.c +13 -6
@@ -941,12 +941,19 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job) running_time_ms =ADJUST_FIVE_PERCENT (xe_gt_clock_interval_to_ms (gt, diff)); -xe_gt_dbg (gt, -"Check job timeout: seqno=%u, lrc_seqno=%u, guc_id=%d, running_time_ms=%llu, timeout_ms=%u, diff=0x%08x" , -xe_sched_job_seqno (job),xe_sched_job_lrc_seqno (job), - q->guc->id, running_time_ms, timeout_ms, diff); - -return running_time_ms >= timeout_ms; +if (!xe_sched_job_started (job)) { +xe_gt_notice (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 ); + }else { +xe_gt_dbg (gt, +"Check job timeout: seqno=%u, lrc_seqno=%u, guc_id=%d, running_time_ms=%llu, timeout_ms=%u, diff=0x%08x" , +xe_sched_job_seqno (job),xe_sched_job_lrc_seqno (job), + q->guc->id, running_time_ms, timeout_ms, diff); +return running_time_ms >= timeout_ms; + } }static void enable_scheduling (struct xe_exec_queue *q)
Signature · 1 line
2.34.1