drm/xe: Track LR jobs in DRM scheduler pending list

VF migration requires jobs to remain pending so they can be replayed
after the VF comes back. Previously, LR job fences were intentionally
signaled immediately after submission to avoid the risk of exporting
them, as these fences do not naturally signal in a timely manner and
could break dma-fence contracts. A side effect of this approach was that
LR jobs were never added to the DRM scheduler’s pending list, preventing
them from being tracked for later resubmission.

We now avoid signaling LR job fences and ensure they are never exported;
Xe already guards against exporting these internal fences. With that
guarantee in place, we can safely track LR jobs in the scheduler’s
pending list so they are eligible for resubmission during VF
post-migration recovery (and similar recovery paths).

An added benefit is that LR queues now gain the DRM scheduler’s built-in
flow control over ring usage rather than rejecting new jobs in the exec
IOCTL if the ring is full.

v2:
 - Ensure DRM scheduler TDR doesn't run for LR jobs
 - Stack variable for killed_or_banned_or_wedged
v4:
 - Clarify commit message (Tomasz)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
Link: https://lore.kernel.org/r/20251008214532.3442967-5-matthew.brost@intel.com

1 files changed, 2 insertions, 10 deletions

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 83897950f0da..0dc27476832b 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -124,7 +124,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct xe_validation_ctx ctx;
 	struct xe_sched_job *job;
 	struct xe_vm *vm;
-	bool write_locked, skip_retry = false;
+	bool write_locked;
 	int err = 0;
 	struct xe_hw_engine_group *group;
 	enum xe_hw_engine_group_execution_mode mode, previous_mode;
@@ -266,12 +266,6 @@ retry:
 		goto err_exec;
 	}
 
-	if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
-		err = -EWOULDBLOCK;	/* Aliased to -EAGAIN */
-		skip_retry = true;
-		goto err_exec;
-	}
-
 	if (xe_exec_queue_uses_pxp(q)) {
 		err = xe_vm_validate_protected(q->vm);
 		if (err)
@@ -328,8 +322,6 @@ retry:
 		xe_sched_job_init_user_fence(job, &syncs[i]);
 	}
 
-	if (xe_exec_queue_is_lr(q))
-		q->ring_ops->emit_job(job);
 	if (!xe_vm_in_lr_mode(vm))
 		xe_exec_queue_last_fence_set(q, vm, &job->drm.s_fence->finished);
 	xe_sched_job_push(job);
@@ -355,7 +347,7 @@ err_exec:
 		xe_validation_ctx_fini(&ctx);
 err_unlock_list:
 	up_read(&vm->lock);
-	if (err == -EAGAIN && !skip_retry)
+	if (err == -EAGAIN)
 		goto retry;
 err_hw_exec_mode:
 	if (mode == EXEC_MODE_DMA_FENCE)