[PATCH v6 28/30] drm/xe/vf: Ensure media GT VF recovery runs after primary GT on PTL

[Matthew Brost <matthew.brost@intel.com>]

It is possible that the media GT's VF post-migration recovery work item
gets scheduled before the primary GT's work item. Since the media GT
depends on the primary GT's work item to complete CCS restore, if the
media GT's work item is scheduled first, detect this condition and
re-queue the media GT's work item for a later time.

v5:
 - Adjust debug message (Tomasz)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index bf1806e90370..d43e18bb8f01 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -1112,8 +1112,22 @@ void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p)
 		   pf_version->major, pf_version->minor);
 }
 
-static void vf_post_migration_shutdown(struct xe_gt *gt)
+static bool vf_post_migration_shutdown(struct xe_gt *gt)
 {
+	struct xe_device *xe = gt_to_xe(gt);
+
+	/*
+	 * On platforms where CCS must be restored by the primary GT, the media
+	 * GT's VF post-migration recovery must run afterward. Detect this case
+	 * and re-queue the media GT's restore work item if necessary.
+	 */
+	if (xe->info.needs_shared_vf_gt_wq && xe_gt_is_media_type(gt)) {
+		struct xe_gt *primary_gt = gt_to_tile(gt)->primary_gt;
+
+		if (xe_gt_sriov_vf_recovery_pending(primary_gt))
+			return true;
+	}
+
 	spin_lock_irq(&gt->sriov.vf.migration.lock);
 	gt->sriov.vf.migration.recovery_queued = false;
 	spin_unlock_irq(&gt->sriov.vf.migration.lock);
@@ -1121,6 +1135,8 @@ static void vf_post_migration_shutdown(struct xe_gt *gt)
 	xe_guc_ct_flush_and_stop(&gt->uc.guc.ct);
 	xe_guc_submit_pause(&gt->uc.guc);
 	xe_tlb_inval_reset(&gt->tlb_inval);
+
+	return false;
 }
 
 static size_t post_migration_scratch_size(struct xe_device *xe)
@@ -1195,11 +1211,14 @@ static void vf_post_migration_recovery(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int err;
+	bool retry;
 
 	xe_gt_sriov_dbg(gt, "migration recovery in progress\n");
 
 	xe_pm_runtime_get(xe);
-	vf_post_migration_shutdown(gt);
+	retry = vf_post_migration_shutdown(gt);
+	if (retry)
+		goto queue;
 
 	if (!xe_sriov_vf_migration_supported(xe)) {
 		xe_gt_sriov_err(gt, "migration is not supported\n");
@@ -1227,6 +1246,12 @@ static void vf_post_migration_recovery(struct xe_gt *gt)
 	xe_pm_runtime_put(xe);
 	xe_gt_sriov_err(gt, "migration recovery failed (%pe)\n", ERR_PTR(err));
 	xe_device_declare_wedged(xe);
+	return;
+
+queue:
+	xe_gt_sriov_info(gt, "Re-queuing migration recovery\n");
+	queue_work(gt->ordered_wq, &gt->sriov.vf.migration.worker);
+	xe_pm_runtime_put(xe);
 }
 
 static void migration_worker_func(struct work_struct *w)
-- 
2.34.1