struct intel_engine_cs *ring;
/** Breadcrumb of last rendering to the buffer. */
- uint32_t last_read_seqno;
- uint32_t last_write_seqno;
+ struct drm_i915_gem_request *last_read_req;
+ struct drm_i915_gem_request *last_write_req;
/** Breadcrumb of last fenced GPU access to the buffer. */
- uint32_t last_fenced_seqno;
+ struct drm_i915_gem_request *last_fenced_req;
/** Current tiling stride for the object, if it's tiled. */
uint32_t stride;
* The request queue allows us to note sequence numbers that have been emitted
* and may be associated with active buffers to be retired.
*
- * By keeping this list, we can avoid having to do questionable
- * sequence-number comparisons on buffer last_rendering_seqnos, and associate
- * an emission time with seqnos for tracking how far ahead of the GPU we are.
+ * By keeping this list, we can avoid having to do questionable sequence
+ * number comparisons on buffer last_read|write_seqno. It also allows an
+ * emission time to be associated with the request for tracking how far ahead
+ * of the GPU the submission is.
*/
struct drm_i915_gem_request {
struct kref ref;
/* Manually manage the write flush as we may have not yet
* retired the buffer.
*
- * Note that the last_write_seqno is always the earlier of
- * the two (read/write) seqno, so if we haved successfully waited,
+ * Note that the last_write_req is always the earlier of
+ * the two (read/write) requests, so if we haved successfully waited,
* we know we have passed the last write.
*/
- obj->last_write_seqno = 0;
+ i915_gem_request_assign(&obj->last_write_req, NULL);
return 0;
}
i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
bool readonly)
{
+ struct drm_i915_gem_request *req;
struct intel_engine_cs *ring = obj->ring;
u32 seqno;
int ret;
- seqno = readonly ? obj->last_write_seqno : obj->last_read_seqno;
- if (seqno == 0)
+ req = readonly ? obj->last_write_req : obj->last_read_req;
+ if (!req)
return 0;
+ seqno = i915_gem_request_get_seqno(req);
+ WARN_ON(seqno == 0);
+
ret = i915_wait_seqno(ring, seqno);
if (ret)
return ret;
struct drm_i915_file_private *file_priv,
bool readonly)
{
+ struct drm_i915_gem_request *req;
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring = obj->ring;
BUG_ON(!mutex_is_locked(&dev->struct_mutex));
BUG_ON(!dev_priv->mm.interruptible);
- seqno = readonly ? obj->last_write_seqno : obj->last_read_seqno;
- if (seqno == 0)
+ req = readonly ? obj->last_write_req : obj->last_read_req;
+ if (!req)
return 0;
+ seqno = i915_gem_request_get_seqno(req);
+ WARN_ON(seqno == 0);
+
ret = i915_gem_check_wedge(&dev_priv->gpu_error, true);
if (ret)
return ret;
i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
struct intel_engine_cs *ring)
{
- u32 seqno = intel_ring_get_seqno(ring);
+ struct drm_i915_gem_request *req = intel_ring_get_request(ring);
BUG_ON(ring == NULL);
- if (obj->ring != ring && obj->last_write_seqno) {
- /* Keep the seqno relative to the current ring */
- obj->last_write_seqno = seqno;
+ if (obj->ring != ring && obj->last_write_req) {
+ /* Keep the request relative to the current ring */
+ i915_gem_request_assign(&obj->last_write_req, req);
}
obj->ring = ring;
list_move_tail(&obj->ring_list, &ring->active_list);
- obj->last_read_seqno = seqno;
+ i915_gem_request_assign(&obj->last_read_req, req);
}
void i915_vma_move_to_active(struct i915_vma *vma,
list_del_init(&obj->ring_list);
obj->ring = NULL;
- obj->last_read_seqno = 0;
- obj->last_write_seqno = 0;
+ i915_gem_request_assign(&obj->last_read_req, NULL);
+ i915_gem_request_assign(&obj->last_write_req, NULL);
obj->base.write_domain = 0;
- obj->last_fenced_seqno = 0;
+ i915_gem_request_assign(&obj->last_fenced_req, NULL);
obj->active = 0;
drm_gem_object_unreference(&obj->base);
return;
if (i915_seqno_passed(ring->get_seqno(ring, true),
- obj->last_read_seqno))
+ i915_gem_request_get_seqno(obj->last_read_req)))
i915_gem_object_move_to_inactive(obj);
}
struct drm_i915_gem_object,
ring_list);
- if (!i915_seqno_passed(seqno, obj->last_read_seqno))
+ if (!i915_seqno_passed(seqno,
+ i915_gem_request_get_seqno(obj->last_read_req)))
break;
i915_gem_object_move_to_inactive(obj);
int ret;
if (obj->active) {
- ret = i915_gem_check_olr(obj->ring, obj->last_read_seqno);
+ ret = i915_gem_check_olr(obj->ring,
+ i915_gem_request_get_seqno(obj->last_read_req));
if (ret)
return ret;
if (ret)
goto out;
- if (obj->active) {
- seqno = obj->last_read_seqno;
- ring = obj->ring;
- }
+ if (!obj->active || !obj->last_read_req)
+ goto out;
- if (seqno == 0)
- goto out;
+ seqno = i915_gem_request_get_seqno(obj->last_read_req);
+ WARN_ON(seqno == 0);
+ ring = obj->ring;
/* Do this after OLR check to make sure we make forward progress polling
* on this IOCTL with a timeout <=0 (like busy ioctl)
idx = intel_ring_sync_index(from, to);
- seqno = obj->last_read_seqno;
+ seqno = i915_gem_request_get_seqno(obj->last_read_req);
/* Optimization: Avoid semaphore sync when we are sure we already
* waited for an object with higher seqno */
if (seqno <= from->semaphore.sync_seqno[idx])
trace_i915_gem_ring_sync_to(from, to, seqno);
ret = to->semaphore.sync_to(to, from, seqno);
if (!ret)
- /* We use last_read_seqno because sync_to()
+ /* We use last_read_req because sync_to()
* might have just caused seqno wrap under
* the radar.
*/
- from->semaphore.sync_seqno[idx] = obj->last_read_seqno;
+ from->semaphore.sync_seqno[idx] =
+ i915_gem_request_get_seqno(obj->last_read_req);
return ret;
}
static int
i915_gem_object_wait_fence(struct drm_i915_gem_object *obj)
{
- if (obj->last_fenced_seqno) {
- int ret = i915_wait_seqno(obj->ring, obj->last_fenced_seqno);
+ if (obj->last_fenced_req) {
+ int ret = i915_wait_seqno(obj->ring,
+ i915_gem_request_get_seqno(obj->last_fenced_req));
if (ret)
return ret;
- obj->last_fenced_seqno = 0;
+ i915_gem_request_assign(&obj->last_fenced_req, NULL);
}
return 0;
i915_gem_execbuffer_move_to_active(struct list_head *vmas,
struct intel_engine_cs *ring)
{
- u32 seqno = intel_ring_get_seqno(ring);
+ struct drm_i915_gem_request *req = intel_ring_get_request(ring);
struct i915_vma *vma;
list_for_each_entry(vma, vmas, exec_list) {
i915_vma_move_to_active(vma, ring);
if (obj->base.write_domain) {
obj->dirty = 1;
- obj->last_write_seqno = seqno;
+ i915_gem_request_assign(&obj->last_write_req, req);
intel_fb_obj_invalidate(obj, ring);
obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
}
if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
- obj->last_fenced_seqno = seqno;
+ i915_gem_request_assign(&obj->last_fenced_req, req);
if (entry->flags & __EXEC_OBJECT_HAS_FENCE) {
struct drm_i915_private *dev_priv = to_i915(ring->dev);
list_move_tail(&dev_priv->fence_regs[obj->fence_reg].lru_list,