Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH v6 24/30] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery
Date: Mon,  6 Oct 2025 04:10:32 -0700	[thread overview]
Message-ID: <20251006111038.2234860-25-matthew.brost@intel.com> (raw)
In-Reply-To: <20251006111038.2234860-1-matthew.brost@intel.com>

Helpful to manually verify the GuC state machine can correctly replay
the state during a VF post-migration recovery. All replay paths have
been manually verified as triggered and working during testing.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 48d5133e76a6..b33a3dd883d7 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -2026,21 +2026,27 @@ void xe_guc_submit_stop(struct xe_guc *guc)
 
 }
 
-static void guc_exec_queue_revert_pending_state_change(struct xe_exec_queue *q)
+static void guc_exec_queue_revert_pending_state_change(struct xe_guc *guc,
+						       struct xe_exec_queue *q)
 {
 	bool pending_enable, pending_disable, pending_resume;
 
 	pending_enable = exec_queue_pending_enable(q);
 	pending_resume = exec_queue_pending_resume(q);
 
-	if (pending_enable && pending_resume)
+	if (pending_enable && pending_resume) {
 		q->guc->needs_resume = true;
+		xe_gt_dbg(guc_to_gt(guc), "Replay RESUME - guc_id=%d",
+			  q->guc->id);
+	}
 
 	if (pending_enable && !pending_resume &&
 	    !exec_queue_pending_tdr_exit(q)) {
 		clear_exec_queue_registered(q);
 		if (xe_exec_queue_is_lr(q))
 			xe_exec_queue_put(q);
+		xe_gt_dbg(guc_to_gt(guc), "Replay REGISTER - guc_id=%d",
+			  q->guc->id);
 	}
 
 	if (pending_enable) {
@@ -2048,6 +2054,8 @@ static void guc_exec_queue_revert_pending_state_change(struct xe_exec_queue *q)
 		clear_exec_queue_pending_resume(q);
 		clear_exec_queue_pending_tdr_exit(q);
 		clear_exec_queue_pending_enable(q);
+		xe_gt_dbg(guc_to_gt(guc), "Replay ENABLE - guc_id=%d",
+			  q->guc->id);
 	}
 
 	if (exec_queue_destroyed(q) && exec_queue_registered(q)) {
@@ -2057,6 +2065,8 @@ static void guc_exec_queue_revert_pending_state_change(struct xe_exec_queue *q)
 		else
 			q->guc->needs_cleanup = true;
 		clear_exec_queue_extra_ref(q);
+		xe_gt_dbg(guc_to_gt(guc), "Replay CLEANUP - guc_id=%d",
+			  q->guc->id);
 	}
 
 	pending_disable = exec_queue_pending_disable(q);
@@ -2064,6 +2074,8 @@ static void guc_exec_queue_revert_pending_state_change(struct xe_exec_queue *q)
 	if (pending_disable && exec_queue_suspended(q)) {
 		clear_exec_queue_suspended(q);
 		q->guc->needs_suspend = true;
+		xe_gt_dbg(guc_to_gt(guc), "Replay SUSPEND - guc_id=%d",
+			  q->guc->id);
 	}
 
 	if (pending_disable) {
@@ -2071,6 +2083,8 @@ static void guc_exec_queue_revert_pending_state_change(struct xe_exec_queue *q)
 			set_exec_queue_enabled(q);
 		clear_exec_queue_pending_disable(q);
 		clear_exec_queue_check_timeout(q);
+		xe_gt_dbg(guc_to_gt(guc), "Replay DISABLE - guc_id=%d",
+			  q->guc->id);
 	}
 
 	q->guc->resume_time = 0;
@@ -2096,7 +2110,7 @@ static void guc_exec_queue_pause(struct xe_guc *guc, struct xe_exec_queue *q)
 	else
 		cancel_delayed_work_sync(&sched->base.work_tdr);
 
-	guc_exec_queue_revert_pending_state_change(q);
+	guc_exec_queue_revert_pending_state_change(guc, q);
 
 	if (xe_exec_queue_is_parallel(q)) {
 		struct xe_device *xe = guc_to_xe(guc);
@@ -2206,6 +2220,9 @@ static void guc_exec_queue_unpause_prepare(struct xe_guc *guc,
 	list_for_each_entry(s_job, &sched->base.pending_list, list) {
 		job = to_xe_sched_job(s_job);
 
+		xe_gt_dbg(guc_to_gt(guc), "Replay JOB - guc_id=%d, seqno=%d",
+			  q->guc->id, xe_sched_job_seqno(job));
+
 		q->ring_ops->emit_job(job);
 		job->skip_emit = true;
 	}
-- 
2.34.1


  parent reply	other threads:[~2025-10-06 11:10 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-06 11:10 [PATCH v6 00/30] VF migration redesign Matthew Brost
2025-10-06 11:10 ` [PATCH v6 01/30] drm/xe: Add NULL checks to scratch LRC allocation Matthew Brost
2025-10-06 21:51   ` Lis, Tomasz
2025-10-06 11:10 ` [PATCH v6 02/30] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-10-06 11:10 ` [PATCH v6 03/30] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-10-06 11:10 ` [PATCH v6 04/30] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-10-06 11:10 ` [PATCH v6 05/30] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-10-06 11:10 ` [PATCH v6 06/30] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-10-06 11:10 ` [PATCH v6 07/30] drm/xe/vf: Add xe_gt_recovery_pending helper Matthew Brost
2025-10-06 13:10   ` Michal Wajdeczko
2025-10-06 11:10 ` [PATCH v6 08/30] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-10-06 11:10 ` [PATCH v6 09/30] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 10/30] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 11/30] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-10-06 14:27   ` Michal Wajdeczko
2025-10-06 14:56     ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 12/30] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-10-06 11:10 ` [PATCH v6 13/30] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 14/30] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
2025-10-06 14:35   ` Michal Wajdeczko
2025-10-06 15:54     ` Matthew Brost
2025-10-06 22:27   ` Lis, Tomasz
2025-10-06 23:07     ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 15/30] drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs supporting migration Matthew Brost
2025-10-06 11:10 ` [PATCH v6 16/30] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-10-06 14:51   ` Michal Wajdeczko
2025-10-06 16:02     ` Matthew Brost
2025-10-06 22:21   ` Lis, Tomasz
2025-10-06 22:57     ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 17/30] drm/xe/vf: Flush and stop CTs in VF post migration recovery Matthew Brost
2025-10-06 11:10 ` [PATCH v6 18/30] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-10-06 11:10 ` [PATCH v6 19/30] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-10-06 11:10 ` [PATCH v6 20/30] drm/xe/vf: Start CTs before resfix " Matthew Brost
2025-10-06 21:50   ` Lis, Tomasz
2025-10-06 11:10 ` [PATCH v6 21/30] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-10-06 11:10 ` [PATCH v6 22/30] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-10-06 11:10 ` [PATCH v6 23/30] drm/xe: Move queue init before LRC creation Matthew Brost
2025-10-06 15:22   ` Michal Wajdeczko
2025-10-06 21:33   ` Lis, Tomasz
2025-10-06 11:10 ` Matthew Brost [this message]
2025-10-06 11:10 ` [PATCH v6 25/30] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-10-06 11:10 ` [PATCH v6 26/30] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-10-06 11:10 ` [PATCH v6 27/30] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-10-06 22:24   ` Lucas De Marchi
2025-10-06 22:51     ` Matthew Brost
2025-10-07 17:00       ` Lucas De Marchi
2025-10-07 17:22         ` Matthew Brost
2025-10-07 20:36           ` Lucas De Marchi
2025-10-07 21:18             ` Matthew Brost
2025-10-06 11:10 ` [PATCH v6 28/30] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-10-06 11:10 ` [PATCH v6 29/30] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-10-06 11:10 ` [PATCH v6 30/30] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-10-06 11:17 ` ✗ CI.checkpatch: warning for VF migration redesign (rev6) Patchwork
2025-10-06 11:18 ` ✓ CI.KUnit: success " Patchwork
2025-10-06 12:24 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-10-06 14:28 ` ✗ Xe.CI.Full: " Patchwork
2025-10-07  0:20 ` [PATCH v6 00/30] VF migration redesign Niranjana Vishwanathapura
2025-10-07  1:11   ` Matthew Brost

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=20251006111038.2234860-25-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=intel-xe@lists.freedesktop.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox