Be cautious and ensure the VF post-migration worker is not running
during driver unload.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c       | 17 +++++++++++++++--
 drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h |  4 +++-
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 807fdced0228..4eaffad6ebcf 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -811,7 +811,8 @@ static void xe_gt_sriov_vf_start_migration_recovery(struct xe_gt *gt)
 
 	spin_lock(&gt->sriov.vf.migration.lock);
 
-	if (!gt->sriov.vf.migration.recovery_queued) {
+	if (!gt->sriov.vf.migration.recovery_queued ||
+	    !gt->sriov.vf.migration.recovery_teardown) {

We're registering `vf_migration_fini` very early in the init. That means it will be called very late. With that in mind, is it even possible to hit?

During `xe_gt_sriov_vf_migration_init_early`, interrupts are not enabled yet. Doesn't that mean they are disabled already when vf_migration_fini is called?

Both ggtt_fini_early and guc_submit_fini should be finished by then; so if the recovery was running, it already crashed or errored out at this point.

So, maybe register the fini later? We need to `init` before IRQs are enabled, but for `fini` - it should be before `exec_queue_lookup` is torn down.

-Tomasz

 		gt->sriov.vf.migration.recovery_queued = true;
 		WRITE_ONCE(gt->sriov.vf.migration.recovery_inprogress, true);
 
@@ -1280,6 +1281,17 @@ static void migration_worker_func(struct work_struct *w)
 	vf_post_migration_recovery(gt);
 }
 
+static void vf_migration_fini(struct drm_device *drm, void *arg)
+{
+	struct xe_gt *gt = arg;
+
+	spin_lock_irq(&gt->sriov.vf.migration.lock);
+	gt->sriov.vf.migration.recovery_teardown = true;
+	spin_unlock_irq(&gt->sriov.vf.migration.lock);
+
+	cancel_work_sync(&gt->sriov.vf.migration.worker);
+}
+
 /**
  * xe_gt_sriov_vf_migration_init_early() - VF post migration init early
  * @gt: the &xe_gt
@@ -1308,7 +1320,8 @@ int xe_gt_sriov_vf_migration_init_early(struct xe_gt *gt)
 	if (!xe_sriov_vf_migration_supported(gt_to_xe(gt)))
 		xe_gt_sriov_info(gt, "migration not supported by this module version\n");
 
-	return 0;
+	return drmm_add_action_or_reset(&gt_to_xe(gt)->drm,
+					vf_migration_fini, 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 61484c7c9a36..beb9978336bb 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
@@ -59,10 +59,12 @@ struct xe_gt_sriov_vf_runtime {
 struct xe_gt_sriov_vf_migration {
 	/** @migration: VF migration recovery worker */
 	struct work_struct worker;
-	/** @lock: Protects recovery_queued */
+	/** @lock: Protects recovery_queued, teardown */
 	spinlock_t lock;
 	/** @lrc_wa_bb: Scratch memory for LRC WA BB in recovery */
 	void *lrc_wa_bb;
+	/** @recovery_teardown: VF post migration recovery is being torn down */
+	bool recovery_teardown;
 	/** @recovery_queued: VF post migration recovery in queued */
 	bool recovery_queued;
 	/** @recovery_inprogress: VF post migration recovery in progress */