drm/xe/vf: Wait for all fixups before using default LRCs

When a context is being created during save/restore, the LRC creation
needs to wait for GGTT address space to be shifted. But it also needs
to have fixed default LRCs. This is mandatory to avoid the situation
where LRC will be created based on data from before the fixups, but
reference within exec queue will be set too late for fixups.

This fixes an issue where contexts created during save/restore have
a large chance of having one unfixed LRC, due to the xe_lrc_create()
being synced for equal start to race with default LRC fixups.

v2: Move the fixups confirmation further, behind all fixups.
  Revert some renames.

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20260226212701.2937065-4-tomasz.lis@intel.com

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 527ded3c9c22ffd1dd86a6cca7f72cc7f00802c1..7f83c0d3b099ba8808d56dd065b7a634875820a7 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -536,12 +536,6 @@ static int vf_get_ggtt_info(struct xe_gt *gt)
         */
        xe_ggtt_shift_nodes(tile->mem.ggtt, start);
 
-       if (xe_sriov_vf_migration_supported(gt_to_xe(gt))) {
-               WRITE_ONCE(gt->sriov.vf.migration.ggtt_need_fixes, false);
-               smp_wmb();      /* Ensure above write visible before wake */
-               wake_up_all(&gt->sriov.vf.migration.wq);
-       }
-
        return 0;
 }
 
@@ -846,6 +840,13 @@ static void xe_gt_sriov_vf_default_lrcs_hwsp_rebase(struct xe_gt *gt)
                xe_default_lrc_update_memirq_regs_with_address(hwe);
 }
 
+static void vf_post_migration_mark_fixups_done(struct xe_gt *gt)
+{
+       WRITE_ONCE(gt->sriov.vf.migration.ggtt_need_fixes, false);
+       smp_wmb();      /* Ensure above write visible before wake */
+       wake_up_all(&gt->sriov.vf.migration.wq);
+}
+
 static void vf_start_migration_recovery(struct xe_gt *gt)
 {
        bool started;
@@ -1380,6 +1381,7 @@ static void vf_post_migration_recovery(struct xe_gt *gt)
        if (err)
                goto fail;
 
+       vf_post_migration_mark_fixups_done(gt);
        vf_post_migration_rearm(gt);
 
        err = vf_post_migration_resfix_done(gt, marker);
@@ -1514,7 +1516,7 @@ static bool vf_valid_ggtt(struct xe_gt *gt)
 }
 
 /**
- * xe_gt_sriov_vf_wait_valid_ggtt() - VF wait for valid GGTT addresses
+ * xe_gt_sriov_vf_wait_valid_ggtt() - wait for valid GGTT nodes and address refs
  * @gt: the &xe_gt
  */
 void xe_gt_sriov_vf_wait_valid_ggtt(struct xe_gt *gt)

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 4ef881b9b6623c4919d2fcf9376a8c32d159c5fa..fca18be589db97b4bcbd1320133316a5d67ed3f0 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
@@ -73,7 +73,7 @@ struct xe_gt_sriov_vf_migration {
        bool recovery_queued;
        /** @recovery_inprogress: VF post migration recovery in progress */
        bool recovery_inprogress;
-       /** @ggtt_need_fixes: VF GGTT needs fixes */
+       /** @ggtt_need_fixes: VF GGTT and references to it need fixes */
        bool ggtt_need_fixes;
 };