From: Tomasz Lis Date: Thu, 26 Feb 2026 21:27:01 +0000 (+0100) Subject: drm/xe/vf: Redo LRC creation while in VF fixups X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=c692ae39e9fd33d0e58ac24bf3d98b352b5064da;p=thirdparty%2Flinux.git drm/xe/vf: Redo LRC creation while in VF fixups If the xe module within a VM was creating a new LRC during save/ restore, this LRC will be invalid. The fixups procedure may not be able to reach it, as there will be a race to add the new LRC reference to an exec queue. Even if the new LRC which was being created during VM migration is added to EQ in time for fixups, said LRC may still remain damaged. In a small percentage of specially crafted test cases, the resulting LRC was still damaged and caused GPU hang. Any LRC which could be created in such a situation, have to be re-created. Due to VM having arbitrarily set amount of CPU cores, it is possible to limit the amount to 1. In such case, there is a possibility that kernel will switch CPU contexts in a way which allows to miss VF migration recovery running in parallel (by simply not switching to the LRC creation thread during recovery). Therefore checking if the migration is in progress just after LRC creation, is not enough to ensure detection. Free the incorrectly created LRC, and trigger a re-run of the creation, but only after waiting for default LRC to get fixups. Use additional atomic value increased after fixups, to ensure any VF migration that avoided detection by just checking for recovery in progress, will be caught. v2: Merge marker and wait for default LRC, reducing amount of calls within xe_init_eq(). Alter the LRC creation loop to remove a race with post-migration fixups worker. v3: Kerneldoc fixes. Rename fixups_complete_count. Signed-off-by: Tomasz Lis Reviewed-by: Matthew Brost Signed-off-by: Michal Wajdeczko Link: https://patch.msgid.link/20260226212701.2937065-5-tomasz.lis@intel.com --- diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 0e46cbed90069..bb273ca02d280 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -368,17 +368,28 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags) * from the moment vCPU resumes execution. */ for (i = 0; i < q->width; ++i) { - struct xe_lrc *lrc; + struct xe_lrc *__lrc = NULL; + int marker; - xe_gt_sriov_vf_wait_valid_ggtt(q->gt); - lrc = xe_lrc_create(q->hwe, q->vm, q->replay_state, - xe_lrc_ring_size(), q->msix_vec, flags); - if (IS_ERR(lrc)) { - err = PTR_ERR(lrc); - goto err_lrc; - } + do { + struct xe_lrc *lrc; + + marker = xe_gt_sriov_vf_wait_valid_ggtt(q->gt); + + lrc = xe_lrc_create(q->hwe, q->vm, q->replay_state, + xe_lrc_ring_size(), q->msix_vec, flags); + if (IS_ERR(lrc)) { + err = PTR_ERR(lrc); + goto err_lrc; + } + + xe_exec_queue_set_lrc(q, lrc, i); + + if (__lrc) + xe_lrc_put(__lrc); + __lrc = lrc; - xe_exec_queue_set_lrc(q, lrc, i); + } while (marker != xe_vf_migration_fixups_complete_count(q->gt)); } return 0; diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c index 7f83c0d3b099b..8989c8e1be95e 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c @@ -1277,6 +1277,8 @@ static int vf_post_migration_fixups(struct xe_gt *gt) if (err) return err; + atomic_inc(>->sriov.vf.migration.fixups_complete_count); + return 0; } @@ -1515,20 +1517,50 @@ static bool vf_valid_ggtt(struct xe_gt *gt) return true; } +/** + * xe_vf_migration_fixups_complete_count() - Get count of VF fixups completions. + * @gt: the &xe_gt instance which contains affected Global GTT + * + * Return: number of times VF fixups were completed since driver + * probe, or 0 if migration is not available, or -1 if fixups are + * pending or being applied right now. + */ +int xe_vf_migration_fixups_complete_count(struct xe_gt *gt) +{ + if (!IS_SRIOV_VF(gt_to_xe(gt)) || + !xe_sriov_vf_migration_supported(gt_to_xe(gt))) + return 0; + + /* should never match fixups_complete_count value */ + if (!vf_valid_ggtt(gt)) + return -1; + + return atomic_read(>->sriov.vf.migration.fixups_complete_count); +} + /** * xe_gt_sriov_vf_wait_valid_ggtt() - wait for valid GGTT nodes and address refs - * @gt: the &xe_gt + * @gt: the &xe_gt instance which contains affected Global GTT + * + * Return: number of times VF fixups were completed since driver + * probe, or 0 if migration is not available. */ -void xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt) +int xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt) { int ret; + /* + * this condition needs to be identical to one in + * xe_vf_migration_fixups_complete_count() + */ if (!IS_SRIOV_VF(gt_to_xe(gt)) || !xe_sriov_vf_migration_supported(gt_to_xe(gt))) - return; + return 0; ret = wait_event_interruptible_timeout(gt->sriov.vf.migration.wq, vf_valid_ggtt(gt), HZ * 5); xe_gt_WARN_ON(gt, !ret); + + return atomic_read(>->sriov.vf.migration.fixups_complete_count); } diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h index 7d97189c2d3d9..a6f7127521a5d 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h @@ -39,6 +39,7 @@ void xe_gt_sriov_vf_print_config(struct xe_gt *gt, struct drm_printer *p); void xe_gt_sriov_vf_print_runtime(struct xe_gt *gt, struct drm_printer *p); void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p); -void xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt); +int xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt); +int xe_vf_migration_fixups_complete_count(struct xe_gt *gt); #endif diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h index fca18be589db9..80562ffadb169 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h @@ -54,6 +54,8 @@ struct xe_gt_sriov_vf_migration { wait_queue_head_t wq; /** @scratch: Scratch memory for VF recovery */ void *scratch; + /** @fixups_complete_count: Counts completed fixups stages */ + atomic_t fixups_complete_count; /** @debug: Debug hooks for delaying migration */ struct { /**