[Intel-xe] [PATCH v4 4/6] drm/xe: Allow num_batch_buffer == 0 in exec IOCTL

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

The idea being out-syncs can signal indicating all previous operations
on the exec queue are complete. An example use case of this would be
support for implementing vkQueueWaitIdle easily.

v2: Don't add last_fence for VM's that do not support dma fences
v3: Use a flags field instead of severval bools in sync parse (Thomas)
v4: s/vkQueueWaitForIdle/vkQueueWaitIdle
v5: Fix inverted lr_mode checks

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_exec.c             | 17 ++++++++++++++++-
 drivers/gpu/drm/xe/xe_exec_queue.c       |  5 ++++-
 drivers/gpu/drm/xe/xe_exec_queue_types.h |  5 +++--
 3 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index a8a025495b14..96d7506a4c72 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -161,7 +161,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM))
 		return -EINVAL;
 
-	if (XE_IOCTL_DBG(xe, q->width != args->num_batch_buffer))
+	if (XE_IOCTL_DBG(xe, args->num_batch_buffer &&
+			 q->width != args->num_batch_buffer))
 		return -EINVAL;
 
 	if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_BANNED)) {
@@ -235,6 +236,18 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto err_exec;
 	}
 
+	if (!args->num_batch_buffer) {
+		if (!xe_vm_in_lr_mode(vm)) {
+			struct dma_fence *fence =
+				xe_exec_queue_last_fence_get(q, vm);
+
+			for (i = 0; i < num_syncs; i++)
+				xe_sync_entry_signal(&syncs[i], NULL, fence);
+		}
+
+		goto err_exec;
+	}
+
 	if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
 		err = -EWOULDBLOCK;
 		goto err_exec;
@@ -328,6 +341,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	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);
 	xe_vm_reactivate_rebind(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index cb284c4ad049..67e3fd9dfc5f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -886,7 +886,10 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
 static void xe_exec_queue_last_fence_lockdep_assert(struct xe_exec_queue *q,
 						    struct xe_vm *vm)
 {
-	lockdep_assert_held_write(&vm->lock);
+	if (q->flags & EXEC_QUEUE_FLAG_VM)
+		lockdep_assert_held_write(&vm->lock);
+	else
+		xe_vm_assert_held(vm);
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 5ba47a5cfdbd..52f0927d0d9b 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -56,8 +56,9 @@ struct xe_exec_queue {
 	struct xe_hw_fence_irq *fence_irq;
 
 	/**
-	 * @last_fence: last fence on engine, protected by vm->lock in write
-	 * mode if bind engine
+	 * @last_fence: last fence on exec queue, protected by vm->lock in write
+	 * mode if bind exec queue, protected by dma resv lock if non-bind exec
+	 * queue
 	 */
 	struct dma_fence *last_fence;
 
-- 
2.34.1