[Intel-xe] [PATCH v3 1/3] drm/xe: fix submissions without vm

[Daniele Ceraolo Spurio]

Kernel queues can submit privileged batches directly in GGTT, so they
don't always need a vm. The submission front-end already supports
creating and submitting jobs without a vm, but some parts of the
back-end assume the vm is always there. Fix this by handling a lack of
vm in the back-end as well.

v2: s/XE_BUG_ON/XE_WARN_ON, s/engine/exec_queue

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
Reviewed-by: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 2 +-
 drivers/gpu/drm/xe/xe_ring_ops.c   | 8 ++++----
 drivers/gpu/drm/xe/xe_sched_job.c  | 3 +++
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 8f64b164987a..4614605d937f 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1133,7 +1133,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	ge->q = q;
 	init_waitqueue_head(&ge->suspend_wait);
 
-	timeout = xe_vm_no_dma_fences(q->vm) ? MAX_SCHEDULE_TIMEOUT :
+	timeout = (q->vm && xe_vm_no_dma_fences(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
 		  q->hwe->eclass->sched_props.job_timeout_ms;
 	err = drm_sched_init(&ge->sched, &drm_sched_ops, NULL,
 			     q->lrc[0].ring.size / MAX_JOB_SIZE_BYTES,
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 11a089ae79b2..ad5c3f9b80d3 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -213,7 +213,7 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 	u32 ppgtt_flag = get_ppgtt_flag(job);
 	struct xe_vm *vm = job->q->vm;
 
-	if (vm->batch_invalidate_tlb) {
+	if (vm && vm->batch_invalidate_tlb) {
 		dw[i++] = preparser_disable(true);
 		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, true, dw, i);
@@ -271,13 +271,13 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 			i = emit_aux_table_inv(gt, VE0_AUX_NV, dw, i);
 	}
 
-	if (vm->batch_invalidate_tlb)
+	if (vm && vm->batch_invalidate_tlb)
 		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, true, dw, i);
 
 	dw[i++] = preparser_disable(false);
 
-	if (!vm->batch_invalidate_tlb)
+	if (!vm || !vm->batch_invalidate_tlb)
 		i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, dw, i);
 
@@ -316,7 +316,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 		mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS;
 
 	/* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */
-	i = emit_pipe_invalidate(mask_flags, vm->batch_invalidate_tlb, dw, i);
+	i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i);
 
 	/* hsdes: 1809175790 */
 	if (has_aux_ccs(xe))
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 753aab0cc6f4..6f33c50ec214 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -87,6 +87,9 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
 	int i, j;
 	u32 width;
 
+	/* only a kernel context can submit a vm-less job */
+	XE_WARN_ON(!q->vm && !(q->flags & EXEC_QUEUE_FLAG_KERNEL));
+
 	/* Migration and kernel engines have their own locking */
 	if (!(q->flags & (EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_VM |
 			  EXEC_QUEUE_FLAG_WA))) {
-- 
2.41.0