drm/xe: Wedge the entire device

Wedge the entire device, not just GT which may have triggered the wedge. To implement this, cleanup the layering so xe_device_declare_wedged() calls into the lower layers (GT) to ensure entire device is wedged. While we are here, also signal any pending GT TLB invalidations upon wedging device. Lastly, short circuit reset wait if device is wedged. v2: - Short circuit reset wait if device is wedged (Local testing) Fixes: 8ed9aaa ("drm/xe: Force wedged state and block GT reset upon any GPU hang") Cc: Rodrigo Vivi <[email protected]> Signed-off-by: Matthew Brost <[email protected]> Reviewed-by: Jonathan Cavitt <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit 7dbe8af) Signed-off-by: Rodrigo Vivi <[email protected]>
flukejones · Jul 18, 2024 · c9474b7 · c9474b7
1 parent bf07ca9
commit c9474b7
Show file tree

Hide file tree

Showing 9 changed files with 80 additions and 13 deletions.
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
@@ -870,6 +870,9 @@ u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address)
  */
 void xe_device_declare_wedged(struct xe_device *xe)
 {
+	struct xe_gt *gt;
+	u8 id;
+
 	if (xe->wedged.mode == 0) {
 		drm_dbg(&xe->drm, "Wedged mode is forcibly disabled\n");
 		return;
@@ -883,4 +886,7 @@ void xe_device_declare_wedged(struct xe_device *xe)
 			"Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/xe/kernel/issues/new\n",
 			dev_name(xe->drm.dev));
 	}
+
+	for_each_gt(gt, xe, id)
+		xe_gt_declare_wedged(gt);
 }
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
@@ -904,3 +904,18 @@ struct xe_hw_engine *xe_gt_any_hw_engine(struct xe_gt *gt)
 
 	return NULL;
 }
+
+/**
+ * xe_gt_declare_wedged() - Declare GT wedged
+ * @gt: the GT object
+ *
+ * Wedge the GT which stops all submission, saves desired debug state, and
+ * cleans up anything which could timeout.
+ */
+void xe_gt_declare_wedged(struct xe_gt *gt)
+{
+	xe_gt_assert(gt, gt_to_xe(gt)->wedged.mode);
+
+	xe_uc_declare_wedged(&gt->uc);
+	xe_gt_tlb_invalidation_reset(gt);
+}
diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
@@ -37,6 +37,7 @@ struct xe_gt *xe_gt_alloc(struct xe_tile *tile);
 int xe_gt_init_hwconfig(struct xe_gt *gt);
 int xe_gt_init_early(struct xe_gt *gt);
 int xe_gt_init(struct xe_gt *gt);
+void xe_gt_declare_wedged(struct xe_gt *gt);
 int xe_gt_record_default_lrcs(struct xe_gt *gt);
 
 /**

diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
@@ -1178,3 +1178,19 @@ void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p)
 	xe_guc_ct_print(&guc->ct, p, false);
 	xe_guc_submit_print(guc, p);
 }
+
+/**
+ * xe_guc_declare_wedged() - Declare GuC wedged
+ * @guc: the GuC object
+ *
+ * Wedge the GuC which stops all submission, saves desired debug state, and
+ * cleans up anything which could timeout.
+ */
+void xe_guc_declare_wedged(struct xe_guc *guc)
+{
+	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
+
+	xe_guc_reset_prepare(guc);
+	xe_guc_ct_stop(&guc->ct);
+	xe_guc_submit_wedge(guc);
+}
diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
@@ -37,6 +37,7 @@ void xe_guc_reset_wait(struct xe_guc *guc);
 void xe_guc_stop_prepare(struct xe_guc *guc);
 void xe_guc_stop(struct xe_guc *guc);
 int xe_guc_start(struct xe_guc *guc);
+void xe_guc_declare_wedged(struct xe_guc *guc);
 
 static inline u16 xe_engine_class_to_guc_class(enum xe_engine_class class)
 {

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -861,36 +861,47 @@ static void xe_guc_exec_queue_trigger_cleanup(struct xe_exec_queue *q)
 		xe_sched_tdr_queue_imm(&q->guc->sched);
 }
 
-static bool guc_submit_hint_wedged(struct xe_guc *guc)
+/**
+ * xe_guc_submit_wedge() - Wedge GuC submission
+ * @guc: the GuC object
+ *
+ * Save exec queue's registered with GuC state by taking a ref to each queue.
+ * Register a DRMM handler to drop refs upon driver unload.
+ */
+void xe_guc_submit_wedge(struct xe_guc *guc)
 {
 	struct xe_device *xe = guc_to_xe(guc);
 	struct xe_exec_queue *q;
 	unsigned long index;
 	int err;
 
-	if (xe->wedged.mode != 2)
-		return false;
-
-	if (xe_device_wedged(xe))
-		return true;
-
-	xe_device_declare_wedged(xe);
-
-	xe_guc_submit_reset_prepare(guc);
-	xe_guc_ct_stop(&guc->ct);
+	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
 
 	err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm,
 				       guc_submit_wedged_fini, guc);
 	if (err) {
 		drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n");
-		return true; /* Device is wedged anyway */
+		return;
 	}
 
 	mutex_lock(&guc->submission_state.lock);
 	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
 		if (xe_exec_queue_get_unless_zero(q))
 			set_exec_queue_wedged(q);
 	mutex_unlock(&guc->submission_state.lock);
+}
+
+static bool guc_submit_hint_wedged(struct xe_guc *guc)
+{
+	struct xe_device *xe = guc_to_xe(guc);
+
+	if (xe->wedged.mode != 2)
+		return false;
+
+	if (xe_device_wedged(xe))
+		return true;
+
+	xe_device_declare_wedged(xe);
 
 	return true;
 }
@@ -1677,7 +1688,8 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 
 void xe_guc_submit_reset_wait(struct xe_guc *guc)
 {
-	wait_event(guc->ct.wq, !guc_read_stopped(guc));
+	wait_event(guc->ct.wq, xe_device_wedged(guc_to_xe(guc)) ||
+		   !guc_read_stopped(guc));
 }
 
 void xe_guc_submit_stop(struct xe_guc *guc)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -18,6 +18,7 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc);
 void xe_guc_submit_reset_wait(struct xe_guc *guc);
 void xe_guc_submit_stop(struct xe_guc *guc);
 int xe_guc_submit_start(struct xe_guc *guc);
+void xe_guc_submit_wedge(struct xe_guc *guc);
 
 int xe_guc_sched_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len);

diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
@@ -300,3 +300,17 @@ void xe_uc_remove(struct xe_uc *uc)
 {
 	xe_gsc_remove(&uc->gsc);
 }
+
+/**
+ * xe_uc_declare_wedged() - Declare UC wedged
+ * @uc: the UC object
+ *
+ * Wedge the UC which stops all submission, saves desired debug state, and
+ * cleans up anything which could timeout.
+ */
+void xe_uc_declare_wedged(struct xe_uc *uc)
+{
+	xe_gt_assert(uc_to_gt(uc), uc_to_xe(uc)->wedged.mode);
+
+	xe_guc_declare_wedged(&uc->guc);
+}
diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h
@@ -21,5 +21,6 @@ int xe_uc_start(struct xe_uc *uc);
 int xe_uc_suspend(struct xe_uc *uc);
 int xe_uc_sanitize_reset(struct xe_uc *uc);
 void xe_uc_remove(struct xe_uc *uc);
+void xe_uc_declare_wedged(struct xe_uc *uc);
 
 #endif