UPSTREAM: drm/virtio: set seqno for dma-fence

This is motivated by having meaningful ftrace events, but it also
fixes use cases where dma_fence_is_later is called, such as in
sync_file_merge.

In other drivers, fence creation and cmdbuf submission normally
happen atomically,

  mutex_lock();
  fence = dma_fence_create(..., ++timeline->seqno);
  submit_cmdbuf();
  mutex_unlock();

and have no such issue.  But in our driver, because most ioctls
queue commands into ctrlq, we do not want to grab a lock.  Instead,
we set seqno to 0 when a fence is created, and update it when the
command is finally queued and the seqno is known.

Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20190429220825.156644-1-olvaffe@gmail.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit efe2bf9)
Signed-off-by: Gurchetan Singh <gurchetansingh@chromium.org>

BUG=chromium:924405
TEST=glxgears in Crostini

Change-Id: If4e3a085ba9569814fc3c398b1d308a56a5dcaa9
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/1684746
Commit-Queue: Gurchetan Singh <gurchetansingh@chromium.org>
Tested-by: Gurchetan Singh <gurchetansingh@chromium.org>
Reviewed-by: Dominik Behr <dbehr@chromium.org>
Reviewed-by: Stéphane Marchesin <marcheu@chromium.org>

drivers/gpu/drm/virtio/virtgpu_drv.h

@@ -109,7 +109,6 @@ struct virtio_gpu_fence {
 	struct dma_fence f;
 	struct virtio_gpu_fence_driver *drv;
 	struct list_head node;
-	uint64_t seq;
 };
 #define to_virtio_fence(x) \
 	container_of(x, struct virtio_gpu_fence, f)

drivers/gpu/drm/virtio/virtgpu_fence.c

@@ -40,16 +40,14 @@ bool virtio_fence_signaled(struct dma_fence *f)
 {
 	struct virtio_gpu_fence *fence = to_virtio_fence(f);
 
-	if (atomic64_read(&fence->drv->last_seq) >= fence->seq)
+	if (atomic64_read(&fence->drv->last_seq) >= fence->f.seqno)
 		return true;
 	return false;
 }
 
 static void virtio_fence_value_str(struct dma_fence *f, char *str, int size)
 {
-	struct virtio_gpu_fence *fence = to_virtio_fence(f);
-
-	snprintf(str, size, "%llu", fence->seq);
+	snprintf(str, size, "%llu", f->seqno);
 }
 
 static void virtio_timeline_value_str(struct dma_fence *f, char *str, int size)
@@ -76,6 +74,11 @@ struct virtio_gpu_fence *virtio_gpu_fence_alloc(struct virtio_gpu_device *vgdev)
 		return fence;
 
 	fence->drv = drv;
+
+	/* This only partially initializes the fence because the seqno is
+	 * unknown yet.  The fence must not be used outside of the driver
+	 * until virtio_gpu_fence_emit is called.
+	 */
 	dma_fence_init(&fence->f, &virtio_fence_ops, &drv->lock, drv->context, 0);
 
 	return fence;
@@ -89,13 +92,13 @@ int virtio_gpu_fence_emit(struct virtio_gpu_device *vgdev,
 	unsigned long irq_flags;
 
 	spin_lock_irqsave(&drv->lock, irq_flags);
-	fence->seq = ++drv->sync_seq;
+	fence->f.seqno = ++drv->sync_seq;
 	dma_fence_get(&fence->f);
 	list_add_tail(&fence->node, &drv->fences);
 	spin_unlock_irqrestore(&drv->lock, irq_flags);
 
 	cmd_hdr->flags |= cpu_to_le32(VIRTIO_GPU_FLAG_FENCE);
-	cmd_hdr->fence_id = cpu_to_le64(fence->seq);
+	cmd_hdr->fence_id = cpu_to_le64(fence->f.seqno);
 	return 0;
 }
 
@@ -109,7 +112,7 @@ void virtio_gpu_fence_event_process(struct virtio_gpu_device *vgdev,
 	spin_lock_irqsave(&drv->lock, irq_flags);
 	atomic64_set(&vgdev->fence_drv.last_seq, last_seq);
 	list_for_each_entry_safe(fence, tmp, &drv->fences, node) {
-		if (last_seq < fence->seq)
+		if (last_seq < fence->f.seqno)
 			continue;
 		dma_fence_signal_locked(&fence->f);
 		list_del(&fence->node);