From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH 26/28] drm/xe: Move queue init before LRC creation
Date: Tue, 16 Sep 2025 20:46:13 -0700 [thread overview]
Message-ID: <20250917034615.3977603-27-matthew.brost@intel.com> (raw)
In-Reply-To: <20250917034615.3977603-1-matthew.brost@intel.com>
A queue must be in the submission backend's tracking state before the
LRC is created to avoid a race condition where the LRC's GGTT addresses
are not properly fixed up during VF post-migration recovery.
Move the queue initialization—which adds the queue to the submission
backend's tracking state—before LRC creation.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/xe/xe_exec_queue.c | 38 ++++++++++++++++++++++--------
drivers/gpu/drm/xe/xe_execlist.c | 2 +-
drivers/gpu/drm/xe/xe_guc_submit.c | 2 +-
drivers/gpu/drm/xe/xe_lrc.h | 10 ++++++++
4 files changed, 40 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 5cacdc38330d..e3a010fc7b71 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -179,17 +179,28 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q)
flags |= XE_LRC_CREATE_RUNALONE;
}
+ err = q->ops->init(q);
+ if (err)
+ return err;
+
+ /*
+ * This must occur after q->ops->init to avoid race conditions during VF
+ * post-migration recovery, as the fixups for the LRC GGTT addresses
+ * depend on the queue being present in the backend tracking structure.
+ */
for (i = 0; i < q->width; ++i) {
- q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K, q->msix_vec, flags);
- if (IS_ERR(q->lrc[i])) {
- err = PTR_ERR(q->lrc[i]);
+ struct xe_lrc *lrc;
+
+ lrc = xe_lrc_create(q->hwe, q->vm, xe_lrc_ring_size(),
+ q->msix_vec, flags);
+ if (IS_ERR(lrc)) {
+ err = PTR_ERR(lrc);
goto err_lrc;
}
- }
- err = q->ops->init(q);
- if (err)
- goto err_lrc;
+ /* Pairs with READ_ONCE to xe_exec_queue_contexts_hwsp_rebase */
+ WRITE_ONCE(q->lrc[i], lrc);
+ }
return 0;
@@ -1087,9 +1098,16 @@ int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch)
int err = 0;
for (i = 0; i < q->width; ++i) {
- xe_lrc_update_memirq_regs_with_address(q->lrc[i], q->hwe, scratch);
- xe_lrc_update_hwctx_regs_with_address(q->lrc[i]);
- err = xe_lrc_setup_wa_bb_with_scratch(q->lrc[i], q->hwe, scratch);
+ struct xe_lrc *lrc;
+
+ /* Pairs with WRITE_ONCE in __xe_exec_queue_init */
+ lrc = READ_ONCE(q->lrc[i]);
+ if (!lrc)
+ continue;
+
+ xe_lrc_update_memirq_regs_with_address(lrc, q->hwe, scratch);
+ xe_lrc_update_hwctx_regs_with_address(lrc);
+ err = xe_lrc_setup_wa_bb_with_scratch(lrc, q->hwe, scratch);
if (err)
break;
}
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 788f56b066b6..c0d9b901e734 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -339,7 +339,7 @@ static int execlist_exec_queue_init(struct xe_exec_queue *q)
const struct drm_sched_init_args args = {
.ops = &drm_sched_ops,
.num_rqs = 1,
- .credit_limit = q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES,
+ .credit_limit = xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES,
.hang_limit = XE_SCHED_HANG_LIMIT,
.timeout = XE_SCHED_JOB_TIMEOUT,
.name = q->hwe->name,
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index ace633bb3c3c..fad6ffcfb83f 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1929,7 +1929,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
msecs_to_jiffies(q->sched_props.job_timeout_ms);
err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
- NULL, q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64,
+ NULL, xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES, 64,
timeout, guc_to_gt(guc)->ordered_wq, NULL,
q->name, gt_to_xe(q->gt)->drm.dev);
if (err)
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 188565465779..5fb6c74bdab5 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -74,6 +74,16 @@ static inline void xe_lrc_put(struct xe_lrc *lrc)
kref_put(&lrc->refcount, xe_lrc_destroy);
}
+/**
+ * xe_lrc_ring_size() - Xe LRC ring size
+ *
+ * Return: Size of LRC size
+ */
+static inline size_t xe_lrc_ring_size(void)
+{
+ return SZ_16K;
+}
+
size_t xe_gt_lrc_size(struct xe_gt *gt, enum xe_engine_class class);
u32 xe_lrc_pphwsp_offset(struct xe_lrc *lrc);
u32 xe_lrc_regs_offset(struct xe_lrc *lrc);
--
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 ` [PATCH 17/28] drm/xe/vf: Wakeup in GuC backend on " Matthew Brost
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 ` Matthew Brost [this message]
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=20250917034615.3977603-27-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