From: Matthew Brost <matthew.brost@intel.com>
Date: Fri, 9 Aug 2024 19:19:29 +0000 (-0700)
Subject: drm/xe: Allow suspend / resume to be safely called multiple times
X-Git-Tag: microblaze-v6.13~18^2~19^2~84
X-Git-Url: http://git.monstr.eu/?a=commitdiff_plain;h=d79fdaef2b55deea0df3fc6af4d4ac60e81a527c;p=linux-2.6-microblaze.git

drm/xe: Allow suspend / resume to be safely called multiple times

Switching modes between LR and dma-fence can result in multiple calls to
suspend / resume. Make these calls safe while still enforcing call
order.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240809191929.3138956-6-matthew.brost@intel.com
---

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index a9af33ff8aa7..da63be550d4d 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1388,6 +1388,8 @@ static void __guc_exec_queue_process_msg_resume(struct xe_sched_msg *msg)
 #define SET_SCHED_PROPS	2
 #define SUSPEND		3
 #define RESUME		4
+#define OPCODE_MASK	0xf
+#define MSG_LOCKED	BIT(8)
 
 static void guc_exec_queue_process_msg(struct xe_sched_msg *msg)
 {
@@ -1432,7 +1434,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	struct xe_device *xe = guc_to_xe(guc);
 	struct xe_guc_exec_queue *ge;
 	long timeout;
-	int err;
+	int err, i;
 
 	xe_assert(xe, xe_device_uc_enabled(guc_to_xe(guc)));
 
@@ -1444,6 +1446,9 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	ge->q = q;
 	init_waitqueue_head(&ge->suspend_wait);
 
+	for (i = 0; i < MAX_STATIC_MSG_TYPE; ++i)
+		INIT_LIST_HEAD(&ge->static_msgs[i].link);
+
 	timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
 		  msecs_to_jiffies(q->sched_props.job_timeout_ms);
 	err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
@@ -1506,11 +1511,26 @@ static void guc_exec_queue_add_msg(struct xe_exec_queue *q, struct xe_sched_msg
 	xe_pm_runtime_get_noresume(guc_to_xe(exec_queue_to_guc(q)));
 
 	INIT_LIST_HEAD(&msg->link);
-	msg->opcode = opcode;
+	msg->opcode = opcode & OPCODE_MASK;
 	msg->private_data = q;
 
 	trace_xe_sched_msg_add(msg);
-	xe_sched_add_msg(&q->guc->sched, msg);
+	if (opcode & MSG_LOCKED)
+		xe_sched_add_msg_locked(&q->guc->sched, msg);
+	else
+		xe_sched_add_msg(&q->guc->sched, msg);
+}
+
+static bool guc_exec_queue_try_add_msg(struct xe_exec_queue *q,
+				       struct xe_sched_msg *msg,
+				       u32 opcode)
+{
+	if (!list_empty(&msg->link))
+		return false;
+
+	guc_exec_queue_add_msg(q, msg, opcode | MSG_LOCKED);
+
+	return true;
 }
 
 #define STATIC_MSG_CLEANUP	0
@@ -1584,13 +1604,16 @@ static int guc_exec_queue_set_preempt_timeout(struct xe_exec_queue *q,
 
 static int guc_exec_queue_suspend(struct xe_exec_queue *q)
 {
+	struct xe_gpu_scheduler *sched = &q->guc->sched;
 	struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_SUSPEND;
 
-	if (exec_queue_killed_or_banned_or_wedged(q) || q->guc->suspend_pending)
+	if (exec_queue_killed_or_banned_or_wedged(q))
 		return -EINVAL;
 
-	q->guc->suspend_pending = true;
-	guc_exec_queue_add_msg(q, msg, SUSPEND);
+	xe_sched_msg_lock(sched);
+	if (guc_exec_queue_try_add_msg(q, msg, SUSPEND))
+		q->guc->suspend_pending = true;
+	xe_sched_msg_unlock(sched);
 
 	return 0;
 }
@@ -1624,13 +1647,16 @@ static int guc_exec_queue_suspend_wait(struct xe_exec_queue *q)
 
 static void guc_exec_queue_resume(struct xe_exec_queue *q)
 {
+	struct xe_gpu_scheduler *sched = &q->guc->sched;
 	struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_RESUME;
 	struct xe_guc *guc = exec_queue_to_guc(q);
 	struct xe_device *xe = guc_to_xe(guc);
 
 	xe_assert(xe, !q->guc->suspend_pending);
 
-	guc_exec_queue_add_msg(q, msg, RESUME);
+	xe_sched_msg_lock(sched);
+	guc_exec_queue_try_add_msg(q, msg, RESUME);
+	xe_sched_msg_unlock(sched);
 }
 
 static bool guc_exec_queue_reset_status(struct xe_exec_queue *q)