Revert "drm/xe: Skip exec queue schedule toggle if queue is idle during suspend"

This reverts commit 8533051ce92015e9cc6f75e0d52119b9d91610b6.

The idle-skip optimization bypasses GuC suspend, so the GPU may not
perform the context switch that flushes TLB entries for invalidated
userptr VMAs. In LR/preempt-fence VM mode, this can lead to missed TLB
invalidation and page faults during userptr invalidation tests.

Restore unconditional schedule toggling on suspend so the context-switch
TLB flush is always performed.

This optimization will be reintroduced with a fix that does not skip
suspend in LR/preempt-fence VM mode.

Fixes: 8533051ce920 ("drm/xe: Skip exec queue schedule toggle if queue is idle during suspend")
Cc: stable@vger.kernel.org # v7.0+
Suggested-by: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Signed-off-by: Tangudu Tilak Tirumalesh <tilak.tirumalesh.tangudu@intel.com>
Reviewed-by: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patch.msgid.link/20260603065217.3131066-2-tilak.tirumalesh.tangudu@intel.com
(cherry picked from commit 6a1e7934d9a6cf46aecae00a99c2603d1295e170)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>

3 files changed, 5 insertions, 77 deletions

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index a82d99bd77bc..0225426c57b0 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -162,21 +162,4 @@ int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
 struct xe_lrc *xe_exec_queue_lrc(struct xe_exec_queue *q);
 struct xe_lrc *xe_exec_queue_get_lrc(struct xe_exec_queue *q, u16 idx);
 
-/**
- * xe_exec_queue_idle_skip_suspend() - Can exec queue skip suspend
- * @q: The exec_queue
- *
- * If an exec queue is not parallel and is idle, the suspend steps can be
- * skipped in the submission backend immediatley signaling the suspend fence.
- * Parallel queues cannot skip this step due to limitations in the submission
- * backend.
- *
- * Return: True if exec queue is idle and can skip suspend steps, False
- * otherwise
- */
-static inline bool xe_exec_queue_idle_skip_suspend(struct xe_exec_queue *q)
-{
-	return !xe_exec_queue_is_parallel(q) && xe_exec_queue_is_idle(q);
-}
-
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index ab501513d806..d1ab66ca1856 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -71,7 +71,6 @@ exec_queue_to_guc(struct xe_exec_queue *q)
 #define EXEC_QUEUE_STATE_WEDGED			(1 << 8)
 #define EXEC_QUEUE_STATE_BANNED			(1 << 9)
 #define EXEC_QUEUE_STATE_PENDING_RESUME		(1 << 10)
-#define EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND	(1 << 11)
 
 static bool exec_queue_registered(struct xe_exec_queue *q)
 {
@@ -218,21 +217,6 @@ static void clear_exec_queue_pending_resume(struct xe_exec_queue *q)
 	atomic_and(~EXEC_QUEUE_STATE_PENDING_RESUME, &q->guc->state);
 }
 
-static bool exec_queue_idle_skip_suspend(struct xe_exec_queue *q)
-{
-	return atomic_read(&q->guc->state) & EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND;
-}
-
-static void set_exec_queue_idle_skip_suspend(struct xe_exec_queue *q)
-{
-	atomic_or(EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND, &q->guc->state);
-}
-
-static void clear_exec_queue_idle_skip_suspend(struct xe_exec_queue *q)
-{
-	atomic_and(~EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND, &q->guc->state);
-}
-
 static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 {
 	return (atomic_read(&q->guc->state) &
@@ -1157,7 +1141,7 @@ static void submit_exec_queue(struct xe_exec_queue *q, struct xe_sched_job *job)
 	if (!job->restore_replay || job->last_replay) {
 		if (xe_exec_queue_is_parallel(q))
 			wq_item_append(q);
-		else if (!exec_queue_idle_skip_suspend(q))
+		else
 			xe_lrc_set_ring_tail(lrc, lrc->ring.tail);
 		job->last_replay = false;
 	}
@@ -1812,10 +1796,9 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg)
 {
 	struct xe_exec_queue *q = msg->private_data;
 	struct xe_guc *guc = exec_queue_to_guc(q);
-	bool idle_skip_suspend = xe_exec_queue_idle_skip_suspend(q);
 
-	if (!idle_skip_suspend && guc_exec_queue_allowed_to_change_state(q) &&
-	    !exec_queue_suspended(q) && exec_queue_enabled(q)) {
+	if (guc_exec_queue_allowed_to_change_state(q) && !exec_queue_suspended(q) &&
+	    exec_queue_enabled(q)) {
 		wait_event(guc->ct.wq, vf_recovery(guc) ||
 			   ((q->guc->resume_time != RESUME_PENDING ||
 			   xe_guc_read_stopped(guc)) && !exec_queue_pending_disable(q)));
@@ -1834,33 +1817,11 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg)
 			disable_scheduling(q, false);
 		}
 	} else if (q->guc->suspend_pending) {
-		if (idle_skip_suspend)
-			set_exec_queue_idle_skip_suspend(q);
 		set_exec_queue_suspended(q);
 		suspend_fence_signal(q);
 	}
 }
 
-static void sched_context(struct xe_exec_queue *q)
-{
-	struct xe_guc *guc = exec_queue_to_guc(q);
-	struct xe_lrc *lrc = q->lrc[0];
-	u32 action[] = {
-		XE_GUC_ACTION_SCHED_CONTEXT,
-		q->guc->id,
-	};
-
-	xe_gt_assert(guc_to_gt(guc), !xe_exec_queue_is_parallel(q));
-	xe_gt_assert(guc_to_gt(guc), !exec_queue_destroyed(q));
-	xe_gt_assert(guc_to_gt(guc), exec_queue_registered(q));
-	xe_gt_assert(guc_to_gt(guc), !exec_queue_pending_disable(q));
-
-	trace_xe_exec_queue_submit(q);
-
-	xe_lrc_set_ring_tail(lrc, lrc->ring.tail);
-	xe_guc_ct_send(&guc->ct, action, ARRAY_SIZE(action), 0, 0);
-}
-
 static void __guc_exec_queue_process_msg_resume(struct xe_sched_msg *msg)
 {
 	struct xe_exec_queue *q = msg->private_data;
@@ -1868,22 +1829,12 @@ static void __guc_exec_queue_process_msg_resume(struct xe_sched_msg *msg)
 	if (guc_exec_queue_allowed_to_change_state(q)) {
 		clear_exec_queue_suspended(q);
 		if (!exec_queue_enabled(q)) {
-			if (exec_queue_idle_skip_suspend(q)) {
-				struct xe_lrc *lrc = q->lrc[0];
-
-				clear_exec_queue_idle_skip_suspend(q);
-				xe_lrc_set_ring_tail(lrc, lrc->ring.tail);
-			}
 			q->guc->resume_time = RESUME_PENDING;
 			set_exec_queue_pending_resume(q);
 			enable_scheduling(q);
-		} else if (exec_queue_idle_skip_suspend(q)) {
-			clear_exec_queue_idle_skip_suspend(q);
-			sched_context(q);
 		}
 	} else {
 		clear_exec_queue_suspended(q);
-		clear_exec_queue_idle_skip_suspend(q);
 	}
 }
 
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c
index 4c2b113364d3..02cf32ae5aa9 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_group.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c
@@ -208,21 +208,15 @@ static int xe_hw_engine_group_suspend_faulting_lr_jobs(struct xe_hw_engine_group
 	lockdep_assert_held_write(&group->mode_sem);
 
 	list_for_each_entry(q, &group->exec_queue_list, hw_engine_group_link) {
-		bool idle_skip_suspend;
 
 		if (!xe_vm_in_fault_mode(q->vm))
 			continue;
 
-		idle_skip_suspend = xe_exec_queue_idle_skip_suspend(q);
-		if (!idle_skip_suspend && has_deps)
+		if (has_deps)
 			return -EAGAIN;
 
 		xe_gt_stats_incr(q->gt, XE_GT_STATS_ID_HW_ENGINE_GROUP_SUSPEND_LR_QUEUE_COUNT, 1);
-		if (idle_skip_suspend)
-			xe_gt_stats_incr(q->gt,
-					 XE_GT_STATS_ID_HW_ENGINE_GROUP_SKIP_LR_QUEUE_COUNT, 1);
-
-		need_resume |= !idle_skip_suspend;
+		need_resume = true;
 		q->ops->suspend(q);
 		gt = q->gt;
 	}