drm/xe: Relax runtime pm protection during execution

Limit the protection only during moments of actual job execution,
and introduce protection for guc submit fini, which is currently
unprotected due to the absence of exec_queue life protection.

In the regular use case scenario, user space will create an
exec queue, and keep it alive to reuse that until it is done
with that kind of workload.

For the regular desktop cases, it means that the exec_queue
is alive even on idle scenarios where display goes off. This
is unacceptable since this would entirely block runtime PM
indefinitely, blocking deeper Package-C state. This would be
a waste drainage of power.

Cc: Matthew Brost <matthew.brost@intel.com>
Tested-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240522170105.327472-3-rodrigo.vivi@intel.comSigned-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_exec_queue.c

@@ -106,7 +106,6 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 
 static int __xe_exec_queue_init(struct xe_exec_queue *q)
 {
-	struct xe_device *xe = gt_to_xe(q->gt);
 	int i, err;
 
 	for (i = 0; i < q->width; ++i) {
@@ -119,17 +118,6 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q)
 	if (err)
 		goto err_lrc;
 
-	/*
-	 * Normally the user vm holds an rpm ref to keep the device
-	 * awake, and the context holds a ref for the vm, however for
-	 * some engines we use the kernels migrate vm underneath which offers no
-	 * such rpm ref, or we lack a vm. Make sure we keep a ref here, so we
-	 * can perform GuC CT actions when needed. Caller is expected to have
-	 * already grabbed the rpm ref outside any sensitive locks.
-	 */
-	if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm))
-		xe_pm_runtime_get_noresume(xe);
-
 	return 0;
 
 err_lrc:
@@ -216,8 +204,6 @@ void xe_exec_queue_fini(struct xe_exec_queue *q)
 
 	for (i = 0; i < q->width; ++i)
 		xe_lrc_finish(q->lrc + i);
-	if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm))
-		xe_pm_runtime_put(gt_to_xe(q->gt));
 	__xe_exec_queue_free(q);
 }
 

drivers/gpu/drm/xe/xe_guc_submit.c

@@ -35,6 +35,7 @@
 #include "xe_macros.h"
 #include "xe_map.h"
 #include "xe_mocs.h"
+#include "xe_pm.h"
 #include "xe_ring_ops_types.h"
 #include "xe_sched_job.h"
 #include "xe_trace.h"
@@ -1088,6 +1089,7 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 	struct xe_exec_queue *q = ge->q;
 	struct xe_guc *guc = exec_queue_to_guc(q);
 
+	xe_pm_runtime_get(guc_to_xe(guc));
 	trace_xe_exec_queue_destroy(q);
 
 	if (xe_exec_queue_is_lr(q))
@@ -1098,6 +1100,7 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	kfree(ge);
 	xe_exec_queue_fini(q);
+	xe_pm_runtime_put(guc_to_xe(guc));
 }
 
 static void guc_exec_queue_fini_async(struct xe_exec_queue *q)

drivers/gpu/drm/xe/xe_sched_job.c

@@ -158,11 +158,7 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
 	for (i = 0; i < width; ++i)
 		job->batch_addr[i] = batch_addr[i];
 
-	/* All other jobs require a VM to be open which has a ref */
-	if (unlikely(q->flags & EXEC_QUEUE_FLAG_KERNEL))
-		xe_pm_runtime_get_noresume(job_to_xe(job));
-	xe_device_assert_mem_access(job_to_xe(job));
-
+	xe_pm_runtime_get_noresume(job_to_xe(job));
 	trace_xe_sched_job_create(job);
 	return job;
 
@@ -191,13 +187,13 @@ void xe_sched_job_destroy(struct kref *ref)
 {
 	struct xe_sched_job *job =
 		container_of(ref, struct xe_sched_job, refcount);
+	struct xe_device *xe = job_to_xe(job);
 
-	if (unlikely(job->q->flags & EXEC_QUEUE_FLAG_KERNEL))
-		xe_pm_runtime_put(job_to_xe(job));
 	xe_exec_queue_put(job->q);
 	dma_fence_put(job->fence);
 	drm_sched_job_cleanup(&job->drm);
 	job_free(job);
+	xe_pm_runtime_put(xe);
 }
 
 void xe_sched_job_set_error(struct xe_sched_job *job, int error)