[PATCH v6 21/24] drm/xe: Add ULLS migration job support to GuC submission

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

Add ULLS migration job support to GuC submission backend.

Changes required:
- On migration queue, reduce max jobs to the number of ULLS semaphores
  minus one
- Skip writing the saved ring tail for ULLS jobs except for the first
  ULLS job - the ring updates both the saved tail and the tail register
  itself
- Set ULLS sempahore for current job releasing last job except for first
  ULLS job
- Suppress submit H2G for ULLS except for first ULLS job

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260228013501.106680-24-matthew.brost@intel.com
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 5e3e911a397b..a83360fcbbf3 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1189,9 +1189,10 @@ static void submit_exec_queue(struct xe_exec_queue *q, struct xe_sched_job *job)
 	xe_gt_assert(guc_to_gt(guc), exec_queue_registered(q));
 
 	if (!job->restore_replay || job->last_replay) {
+		/* A ULLS job past the first publishes its own ring tail */
 		if (xe_exec_queue_is_parallel(q))
 			wq_item_append(q);
-		else
+		else if (!xe_sched_job_ulls_is_chained(job))
 			xe_lrc_set_ring_tail(lrc, lrc->ring.tail);
 		job->last_replay = false;
 	}
@@ -1208,6 +1209,9 @@ static void submit_exec_queue(struct xe_exec_queue *q, struct xe_sched_job *job)
 	if (exec_queue_suspended(q))
 		return;
 
+	if (xe_sched_job_ulls_is_chained(job))
+		xe_lrc_set_ulls_semaphore(lrc, xe_sched_job_lrc_seqno(job));
+
 	if (!exec_queue_enabled(q)) {
 		action[len++] = XE_GUC_ACTION_SCHED_CONTEXT_MODE_SET;
 		action[len++] = q->guc->id;
@@ -1221,13 +1225,14 @@ static void submit_exec_queue(struct xe_exec_queue *q, struct xe_sched_job *job)
 		set_exec_queue_pending_enable(q);
 		set_exec_queue_enabled(q);
 		trace_xe_exec_queue_scheduling_enable(q);
-	} else {
+	} else if (!xe_sched_job_ulls_is_chained(job)) {
 		action[len++] = XE_GUC_ACTION_SCHED_CONTEXT;
 		action[len++] = q->guc->id;
 		trace_xe_exec_queue_submit(q);
 	}
 
-	xe_guc_ct_send(&guc->ct, action, len, g2h_len, num_g2h);
+	if (!xe_sched_job_ulls_is_chained(job) || num_g2h)
+		xe_guc_ct_send(&guc->ct, action, len, g2h_len, num_g2h);
 
 	if (extra_submit) {
 		len = 0;
@@ -2098,6 +2103,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	struct xe_guc_exec_queue *ge;
 	long timeout;
 	int err, i;
+	int max_jobs = (xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES);
 
 	xe_gt_assert(guc_to_gt(guc), xe_device_uc_enabled(guc_to_xe(guc)));
 
@@ -2137,8 +2143,11 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 		submit_wq = primary->guc->sched.base.submit_wq;
 	}
 
+	if (q->vm && q->vm->flags & XE_VM_FLAG_MIGRATION)
+		max_jobs = min(max_jobs, LRC_MIGRATION_ULLS_SEMAPHORE_COUNT - 1);
+
 	err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
-			    submit_wq, xe_lrc_ring_size() / MAX_JOB_SIZE_BYTES, 64,
+			    submit_wq, max_jobs, 64,
 			    timeout, guc_to_gt(guc)->ordered_wq, NULL,
 			    ge->name, gt_to_xe(q->gt)->drm.dev);
 	if (err)
-- 
2.34.1