torvalds/linux
3
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-03-21 23:16:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

drm/xe/vf: Abort VF post migration recovery on failure

Browse Source 
If VF post-migration recovery fails, the device is wedged. However,
submission queues still need to be enabled for proper cleanup. In such
cases, call into the GuC submission backend to restart all queues that
were previously paused.

v3:
 - s/Avort/Abort (Tomasz)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
Link: https://lore.kernel.org/r/20251008214532.3442967-26-matthew.brost@intel.com
This commit is contained in:
Matthew Brost
2025-10-08 14:45:23 -07:00
parent 16b6dd1a90
commit 7c4b7e34c8
3 changed files with 31 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/gpu/drm/xe/xe_gt_sriov_vf.c
View File

@@ -1144,6 +1144,15 @@ static void vf_post_migration_kickstart(struct xe_gt *gt)
xe_guc_submit_unpause(&gt->uc.guc);
}
static void vf_post_migration_abort(struct xe_gt *gt)
{
spin_lock_irq(&gt->sriov.vf.migration.lock);
WRITE_ONCE(gt->sriov.vf.migration.recovery_inprogress, false);
spin_unlock_irq(&gt->sriov.vf.migration.lock);
xe_guc_submit_pause_abort(&gt->uc.guc);
}
static int vf_post_migration_notify_resfix_done(struct xe_gt *gt)
{
bool skip_resfix = false;
@@ -1202,6 +1211,7 @@ static void vf_post_migration_recovery(struct xe_gt *gt)
xe_gt_sriov_notice(gt, "migration recovery ended\n");
return;
fail:
vf_post_migration_abort(gt);
xe_pm_runtime_put(xe);
xe_gt_sriov_err(gt, "migration recovery failed (%pe)\n", ERR_PTR(err));
xe_device_declare_wedged(xe);

20
drivers/gpu/drm/xe/xe_guc_submit.c
View File

@@ -2098,6 +2098,26 @@ void xe_guc_submit_unpause(struct xe_guc *guc)
wake_up_all(&guc->ct.wq);
}
/**
* xe_guc_submit_pause_abort - Abort all paused submission task on given GuC.
* @guc: the &xe_guc struct instance whose scheduler is to be aborted
*/
void xe_guc_submit_pause_abort(struct xe_guc *guc)
{
struct xe_exec_queue *q;
unsigned long index;
mutex_lock(&guc->submission_state.lock);
xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
struct xe_gpu_scheduler *sched = &q->guc->sched;
xe_sched_submission_start(sched);
if (exec_queue_killed_or_banned_or_wedged(q))
xe_guc_exec_queue_trigger_cleanup(q);
}
mutex_unlock(&guc->submission_state.lock);
}
static struct xe_exec_queue *
g2h_exec_queue_lookup(struct xe_guc *guc, u32 guc_id)
{

1
drivers/gpu/drm/xe/xe_guc_submit.h
View File

@@ -22,6 +22,7 @@ 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);
void xe_guc_submit_pause_abort(struct xe_guc *guc);
void xe_guc_submit_wedge(struct xe_guc *guc);
int xe_guc_read_stopped(struct xe_guc *guc);