From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [PATCH v10 16/34] drm/xe/vf: Don't allow GT reset to be queued during VF post migration recovery
Date: Wed, 8 Oct 2025 14:45:14 -0700 [thread overview]
Message-ID: <20251008214532.3442967-17-matthew.brost@intel.com> (raw)
In-Reply-To: <20251008214532.3442967-1-matthew.brost@intel.com>
With well-behaved software, a GT reset should never occur, nor should it
happen during VF post-migration recovery. If it does, trigger a warning
but suppress the GT reset, as VF post-migration recovery is expected to
bring the VF back to a working state.
v3:
- Better commit message (Tomasz)
v5:
- Use xe_gt_WARN_ON (Michal)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
---
drivers/gpu/drm/xe/xe_gt.c | 9 -------
drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 7 -----
drivers/gpu/drm/xe/xe_guc_submit.c | 42 ++++-------------------------
drivers/gpu/drm/xe/xe_guc_submit.h | 3 ---
4 files changed, 5 insertions(+), 56 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index d713b649447b..6951fedd4350 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -803,11 +803,6 @@ static int do_gt_restart(struct xe_gt *gt)
return 0;
}
-static int gt_wait_reset_unblock(struct xe_gt *gt)
-{
- return xe_guc_wait_reset_unblock(>->uc.guc);
-}
-
static int gt_reset(struct xe_gt *gt)
{
unsigned int fw_ref;
@@ -822,10 +817,6 @@ static int gt_reset(struct xe_gt *gt)
xe_gt_info(gt, "reset started\n");
- err = gt_wait_reset_unblock(gt);
- if (!err)
- xe_gt_warn(gt, "reset block failed to get lifted");
-
xe_pm_runtime_get(gt_to_xe(gt));
if (xe_fault_inject_gt_reset()) {
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 1aae4e40a366..96c93a64d754 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -1097,17 +1097,11 @@ void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p)
static void vf_post_migration_shutdown(struct xe_gt *gt)
{
- int ret = 0;
-
spin_lock_irq(>->sriov.vf.migration.lock);
gt->sriov.vf.migration.recovery_queued = false;
spin_unlock_irq(>->sriov.vf.migration.lock);
xe_guc_submit_pause(>->uc.guc);
- ret |= xe_guc_submit_reset_block(>->uc.guc);
-
- if (ret)
- xe_gt_sriov_info(gt, "migration recovery encountered ongoing reset\n");
}
static size_t post_migration_scratch_size(struct xe_device *xe)
@@ -1142,7 +1136,6 @@ static void vf_post_migration_kickstart(struct xe_gt *gt)
*/
xe_irq_resume(gt_to_xe(gt));
- xe_guc_submit_reset_unblock(>->uc.guc);
xe_guc_submit_unpause(>->uc.guc);
}
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index d123bdb63369..59371b7cc8a4 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -27,6 +27,7 @@
#include "xe_gt.h"
#include "xe_gt_clock.h"
#include "xe_gt_printk.h"
+#include "xe_gt_sriov_vf.h"
#include "xe_guc.h"
#include "xe_guc_capture.h"
#include "xe_guc_ct.h"
@@ -1900,47 +1901,14 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
}
}
-/**
- * xe_guc_submit_reset_block - Disallow reset calls on given GuC.
- * @guc: the &xe_guc struct instance
- */
-int xe_guc_submit_reset_block(struct xe_guc *guc)
-{
- return atomic_fetch_or(1, &guc->submission_state.reset_blocked);
-}
-
-/**
- * xe_guc_submit_reset_unblock - Allow back reset calls on given GuC.
- * @guc: the &xe_guc struct instance
- */
-void xe_guc_submit_reset_unblock(struct xe_guc *guc)
-{
- atomic_set_release(&guc->submission_state.reset_blocked, 0);
- wake_up_all(&guc->ct.wq);
-}
-
-static int guc_submit_reset_is_blocked(struct xe_guc *guc)
-{
- return atomic_read_acquire(&guc->submission_state.reset_blocked);
-}
-
-/* Maximum time of blocking reset */
-#define RESET_BLOCK_PERIOD_MAX (HZ * 5)
-
-/**
- * xe_guc_wait_reset_unblock - Wait until reset blocking flag is lifted, or timeout.
- * @guc: the &xe_guc struct instance
- */
-int xe_guc_wait_reset_unblock(struct xe_guc *guc)
-{
- return wait_event_timeout(guc->ct.wq,
- !guc_submit_reset_is_blocked(guc), RESET_BLOCK_PERIOD_MAX);
-}
-
int xe_guc_submit_reset_prepare(struct xe_guc *guc)
{
int ret;
+ if (xe_gt_WARN_ON(guc_to_gt(guc),
+ xe_gt_sriov_vf_recovery_pending(guc_to_gt(guc))))
+ return 0;
+
if (!guc->submission_state.initialized)
return 0;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 5b4a0a6fd818..f535fe3895e5 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -22,9 +22,6 @@ void xe_guc_submit_stop(struct xe_guc *guc);
int xe_guc_submit_start(struct xe_guc *guc);
void xe_guc_submit_pause(struct xe_guc *guc);
void xe_guc_submit_unpause(struct xe_guc *guc);
-int xe_guc_submit_reset_block(struct xe_guc *guc);
-void xe_guc_submit_reset_unblock(struct xe_guc *guc);
-int xe_guc_wait_reset_unblock(struct xe_guc *guc);
void xe_guc_submit_wedge(struct xe_guc *guc);
int xe_guc_read_stopped(struct xe_guc *guc);
--
2.34.1
next prev parent reply other threads:[~2025-10-08 21:46 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-08 21:44 [PATCH v10 00/34] VF migration redesign Matthew Brost
2025-10-08 21:44 ` [PATCH v10 01/34] drm/xe: Add NULL checks to scratch LRC allocation Matthew Brost
2025-10-08 21:45 ` [PATCH v10 02/34] drm/xe: Save off position in ring in which a job was programmed Matthew Brost
2025-10-08 21:45 ` [PATCH v10 03/34] drm/xe/guc: Track pending-enable source in submission state Matthew Brost
2025-10-08 21:45 ` [PATCH v10 04/34] drm/xe: Track LR jobs in DRM scheduler pending list Matthew Brost
2025-10-08 21:45 ` [PATCH v10 05/34] drm/xe: Return first unsignaled job first pending job helper Matthew Brost
2025-10-08 21:45 ` [PATCH v10 06/34] drm/xe: Don't change LRC ring head on job resubmission Matthew Brost
2025-10-08 21:45 ` [PATCH v10 07/34] drm/xe: Make LRC W/A scratch buffer usage consistent Matthew Brost
2025-10-08 21:45 ` [PATCH v10 08/34] drm/xe/vf: Add xe_gt_recovery_pending helper Matthew Brost
2025-10-08 21:45 ` [PATCH v10 09/34] drm/xe/vf: Make VF recovery run on per-GT worker Matthew Brost
2025-10-08 21:45 ` [PATCH v10 10/34] drm/xe/vf: Abort H2G sends during VF post-migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 11/34] drm/xe/vf: Remove memory allocations from VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 12/34] drm/xe: Move GGTT lock init to alloc Matthew Brost
2025-10-08 21:45 ` [PATCH v10 13/34] drm/xe/vf: Move LMEM config to tile layer Matthew Brost
2025-10-08 21:45 ` [PATCH v10 14/34] drm/xe/vf: Close multi-GT GGTT shift race Matthew Brost
2025-10-08 21:45 ` [PATCH v10 15/34] drm/xe/vf: Teardown VF post migration worker on driver unload Matthew Brost
2025-10-08 21:45 ` Matthew Brost [this message]
2025-10-08 21:45 ` [PATCH v10 17/34] drm/xe/vf: Wakeup in GuC backend on VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 18/34] drm/xe/vf: Avoid indefinite blocking in preempt rebind worker for VFs supporting migration Matthew Brost
2025-10-08 21:45 ` [PATCH v10 19/34] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register Matthew Brost
2025-10-08 21:45 ` [PATCH v10 20/34] drm/xe/vf: Flush and stop CTs in VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 21/34] drm/xe/vf: Reset TLB invalidations during " Matthew Brost
2025-10-08 21:45 ` [PATCH v10 22/34] drm/xe/vf: Kickstart after resfix in " Matthew Brost
2025-10-08 21:45 ` [PATCH v10 23/34] drm/xe: Add CTB_H2G_BUFFER_OFFSET define Matthew Brost
2025-10-08 21:45 ` [PATCH v10 24/34] drm/xe/vf: Start CTs before resfix VF post migration recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 25/34] drm/xe/vf: Abort VF post migration recovery on failure Matthew Brost
2025-10-08 21:45 ` [PATCH v10 26/34] drm/xe/vf: Replay GuC submission state on pause / unpause Matthew Brost
2025-10-13 11:54 ` Raag Jadav
2025-10-08 21:45 ` [PATCH v10 27/34] drm/xe: Move queue init before LRC creation Matthew Brost
2025-10-08 21:45 ` [PATCH v10 28/34] drm/xe/vf: Add debug prints for GuC replaying state during VF recovery Matthew Brost
2025-10-08 21:45 ` [PATCH v10 29/34] drm/xe/vf: Workaround for race condition in GuC firmware during VF pause Matthew Brost
2025-10-08 21:45 ` [PATCH v10 30/34] drm/xe: Use PPGTT addresses for TLB invalidation to avoid GGTT fixups Matthew Brost
2025-10-08 21:45 ` [PATCH v10 31/34] drm/xe/vf: Use primary GT ordered work queue on media GT on PTL VF Matthew Brost
2025-10-08 21:45 ` [PATCH v10 32/34] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL Matthew Brost
2025-10-08 21:45 ` [PATCH v10 33/34] drm/xe/vf: Rebase CCS save/restore BB GGTT addresses Matthew Brost
2025-10-08 21:45 ` [PATCH v10 34/34] drm/xe/guc: Increase wait timeout to 2sec after BUSY reply from GuC Matthew Brost
2025-10-08 21:53 ` ✗ CI.checkpatch: warning for VF migration redesign (rev10) Patchwork
2025-10-08 21:54 ` ✓ CI.KUnit: success " Patchwork
2025-10-08 22:35 ` ✓ Xe.CI.BAT: " Patchwork
2025-10-09 2:36 ` ✗ Xe.CI.Full: failure " 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=20251008214532.3442967-17-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