From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH 17/28] drm/xe/vf: Wakeup in GuC backend on VF post migration recovery
Date: Tue, 16 Sep 2025 20:46:04 -0700 [thread overview]
Message-ID: <20250917034615.3977603-18-matthew.brost@intel.com> (raw)
In-Reply-To: <20250917034615.3977603-1-matthew.brost@intel.com>
If VF post-migration recovery is in progress, the recovery flow will
rebuild all GuC submission state. In this case, exit all waiters to
ensure that submission queue scheduling can also be paused. Avoid taking
any adverse actions after aborting the wait.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 3 ++
drivers/gpu/drm/xe/xe_guc_submit.c | 51 +++++++++++++++++++++--------
2 files changed, 41 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 12a56a975358..877f6e1c3a3a 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -815,6 +815,9 @@ static void xe_gt_sriov_vf_start_migration_recovery(struct xe_gt *gt)
!gt->sriov.vf.migration.recovery_teardown) {
gt->sriov.vf.migration.recovery_queued = true;
WRITE_ONCE(gt->sriov.vf.migration.recovery_inprogress, true);
+ smp_wmb();
+
+ wake_up_all(>->uc.guc.ct.wq);
started = queue_work(gt->ordered_wq, >->sriov.vf.migration.worker);
xe_gt_sriov_info(gt, "VF migration recovery %s\n", started ?
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 0cd5987606f1..5f08b009ace1 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -984,6 +984,9 @@ static u32 wq_space_until_wrap(struct xe_exec_queue *q)
return (WQ_SIZE - q->guc->wqi_tail);
}
+#define vf_recovery(guc) \
+ xe_gt_sriov_vf_recovery_inprogress(guc_to_gt(guc))
+
static int wq_wait_for_space(struct xe_exec_queue *q, u32 wqi_size)
{
struct xe_guc *guc = exec_queue_to_guc(q);
@@ -993,7 +996,7 @@ static int wq_wait_for_space(struct xe_exec_queue *q, u32 wqi_size)
#define AVAILABLE_SPACE \
CIRC_SPACE(q->guc->wqi_tail, q->guc->wqi_head, WQ_SIZE)
- if (wqi_size > AVAILABLE_SPACE) {
+ if (wqi_size > AVAILABLE_SPACE && !vf_recovery(guc)) {
try_again:
q->guc->wqi_head = parallel_read(xe, map, wq_desc.head);
if (wqi_size > AVAILABLE_SPACE) {
@@ -1192,9 +1195,10 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
ret = wait_event_timeout(guc->ct.wq,
(!exec_queue_pending_enable(q) &&
!exec_queue_pending_disable(q)) ||
- xe_guc_read_stopped(guc),
+ xe_guc_read_stopped(guc) ||
+ vf_recovery(guc),
HZ * 5);
- if (!ret) {
+ if (!ret && !vf_recovery(guc)) {
struct xe_gpu_scheduler *sched = &q->guc->sched;
xe_gt_warn(q->gt, "Pending enable/disable failed to respond\n");
@@ -1297,6 +1301,10 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w)
bool wedged = false;
xe_gt_assert(guc_to_gt(guc), xe_exec_queue_is_lr(q));
+
+ if (vf_recovery(guc))
+ return;
+
trace_xe_exec_queue_lr_cleanup(q);
if (!exec_queue_killed(q))
@@ -1329,7 +1337,11 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w)
*/
ret = wait_event_timeout(guc->ct.wq,
!exec_queue_pending_disable(q) ||
- xe_guc_read_stopped(guc), HZ * 5);
+ xe_guc_read_stopped(guc) ||
+ vf_recovery(guc), HZ * 5);
+ if (vf_recovery(guc))
+ return;
+
if (!ret) {
xe_gt_warn(q->gt, "Schedule disable failed to respond, guc_id=%d\n",
q->guc->id);
@@ -1419,8 +1431,9 @@ static void enable_scheduling(struct xe_exec_queue *q)
ret = wait_event_timeout(guc->ct.wq,
!exec_queue_pending_enable(q) ||
- xe_guc_read_stopped(guc), HZ * 5);
- if (!ret || xe_guc_read_stopped(guc)) {
+ xe_guc_read_stopped(guc) ||
+ vf_recovery(guc), HZ * 5);
+ if ((!ret && !vf_recovery(guc)) || xe_guc_read_stopped(guc)) {
xe_gt_warn(guc_to_gt(guc), "Schedule enable failed to respond");
set_exec_queue_banned(q);
xe_gt_reset_async(q->gt);
@@ -1491,7 +1504,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
* list so job can be freed and kick scheduler ensuring free job is not
* lost.
*/
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags))
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags) ||
+ vf_recovery(guc))
return DRM_GPU_SCHED_STAT_NO_HANG;
/* Kill the run_job entry point */
@@ -1543,7 +1557,10 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
ret = wait_event_timeout(guc->ct.wq,
(!exec_queue_pending_enable(q) &&
!exec_queue_pending_disable(q)) ||
- xe_guc_read_stopped(guc), HZ * 5);
+ xe_guc_read_stopped(guc) ||
+ vf_recovery(guc), HZ * 5);
+ if (vf_recovery(guc))
+ goto handle_vf_resume;
if (!ret || xe_guc_read_stopped(guc))
goto trigger_reset;
@@ -1568,7 +1585,10 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
smp_rmb();
ret = wait_event_timeout(guc->ct.wq,
!exec_queue_pending_disable(q) ||
- xe_guc_read_stopped(guc), HZ * 5);
+ xe_guc_read_stopped(guc) ||
+ vf_recovery(guc), HZ * 5);
+ if (vf_recovery(guc))
+ goto handle_vf_resume;
if (!ret || xe_guc_read_stopped(guc)) {
trigger_reset:
if (!ret)
@@ -1673,6 +1693,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
* some thought, do this in a follow up.
*/
xe_sched_submission_start(sched);
+handle_vf_resume:
return DRM_GPU_SCHED_STAT_NO_HANG;
}
@@ -1785,8 +1806,9 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg)
if (guc_exec_queue_allowed_to_change_state(q) && !exec_queue_suspended(q) &&
exec_queue_enabled(q)) {
- wait_event(guc->ct.wq, (q->guc->resume_time != RESUME_PENDING ||
- xe_guc_read_stopped(guc)) && !exec_queue_pending_disable(q));
+ wait_event(guc->ct.wq, vf_recovery(guc) ||
+ ((q->guc->resume_time != RESUME_PENDING ||
+ xe_guc_read_stopped(guc)) && !exec_queue_pending_disable(q)));
if (!xe_guc_read_stopped(guc)) {
s64 since_resume_ms =
@@ -1913,7 +1935,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
q->entity = &ge->entity;
- if (xe_guc_read_stopped(guc))
+ if (xe_guc_read_stopped(guc) || vf_recovery(guc))
xe_sched_stop(sched);
mutex_unlock(&guc->submission_state.lock);
@@ -2066,12 +2088,15 @@ static int guc_exec_queue_suspend_wait(struct xe_exec_queue *q)
* suspend_pending upon kill but to be paranoid but races in which
* suspend_pending is set after kill also check kill here.
*/
+retry:
ret = wait_event_interruptible_timeout(q->guc->suspend_wait,
!READ_ONCE(q->guc->suspend_pending) ||
exec_queue_killed(q) ||
xe_guc_read_stopped(guc),
HZ * 5);
+ if (vf_recovery(guc) && !xe_device_wedged((guc_to_xe(guc))))
+ goto retry;
if (!ret) {
xe_gt_warn(guc_to_gt(guc),
"Suspend fence, guc_id=%d, failed to respond",
@@ -2177,7 +2202,7 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
{
int ret;
- if (WARN_ON_ONCE(xe_gt_sriov_vf_recovery_inprogress(guc_to_gt(guc))))
+ if (WARN_ON_ONCE(vf_recovery(guc)))
return 0;
if (!guc->submission_state.initialized)
--
2.34.1
next prev parent reply other threads:[~2025-09-17 3:46 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-17 3:45 [PATCH 00/28] VF migration redesign Matthew Brost
2025-09-17 3:45 ` [PATCH 01/28] drm/xe/vf: Lock querying GGTT config during driver init Matthew Brost
2025-09-17 3:45 ` [PATCH 02/28] Revert "drm/xe/vf: Rebase exec queue parallel commands during migration recovery" Matthew Brost
2025-09-17 3:45 ` [PATCH 03/28] Revert "drm/xe/vf: Post migration, repopulate ring area for pending request" Matthew Brost
2025-09-17 3:45 ` [PATCH 04/28] Revert "drm/xe/vf: Fixup CTB send buffer messages after migration" Matthew Brost
2025-09-17 3:45 ` [PATCH 05/28] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-09-17 3:45 ` [PATCH 06/28] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-09-17 3:45 ` [PATCH 07/28] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-09-17 3:45 ` [PATCH 08/28] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-09-17 3:45 ` [PATCH 09/28] drm/xe/guc: Document GuC submission backend Matthew Brost
2025-09-17 3:45 ` [PATCH 10/28] drm/xe/vf: Add xe_gt_sriov_vf_recovery_inprogress helper Matthew Brost
2025-09-17 3:45 ` [PATCH 11/28] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-09-17 3:45 ` [PATCH 12/28] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-09-17 3:46 ` [PATCH 13/28] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-09-17 3:46 ` [PATCH 14/28] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-09-17 3:46 ` [PATCH 15/28] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-09-17 3:46 ` [PATCH 16/28] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery Matthew Brost
2025-09-17 3:46 ` Matthew Brost [this message]
2025-09-17 3:46 ` [PATCH 18/28] drm/xe/vf: Extra debug on GGTT shift Matthew Brost
2025-09-17 3:46 ` [PATCH 19/28] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-09-17 3:46 ` [PATCH 20/28] drm/xe/vf: Stop and flush CTs in VF post migration recovery Matthew Brost
2025-09-17 3:46 ` [PATCH 21/28] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-09-17 3:46 ` [PATCH 22/28] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-09-17 3:46 ` [PATCH 23/28] drm/xe/vf: Start CTs before resfix " Matthew Brost
2025-09-17 3:46 ` [PATCH 24/28] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-09-17 3:46 ` [PATCH 25/28] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-09-17 3:46 ` [PATCH 26/28] drm/xe: Move queue init before LRC creation Matthew Brost
2025-09-17 3:46 ` [PATCH 27/28] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-09-17 3:46 ` [PATCH 28/28] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-09-17 3:55 ` ✗ CI.checkpatch: warning for VF migration redesign Patchwork
2025-09-17 3:56 ` ✓ CI.KUnit: success " Patchwork
2025-09-17 4:39 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-09-17 6:38 ` ✗ Xe.CI.Full: " Patchwork
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=20250917034615.3977603-18-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