return 0;
}
-/*
- * Compare arbitrary request against outstanding lazy request. Emit on match.
- */
-int
-i915_gem_check_olr(struct drm_i915_gem_request *req)
-{
- WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
-
- if (req == req->ring->outstanding_lazy_request)
- i915_add_request(req->ring);
-
- return 0;
-}
-
static void fake_irq(unsigned long data)
{
wake_up_process((struct task_struct *)data);
return ret;
}
+int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
+ struct drm_file *file)
+{
+ struct drm_i915_private *dev_private;
+ struct drm_i915_file_private *file_priv;
+
+ WARN_ON(!req || !file || req->file_priv);
+
+ if (!req || !file)
+ return -EINVAL;
+
+ if (req->file_priv)
+ return -EINVAL;
+
+ dev_private = req->ring->dev->dev_private;
+ file_priv = file->driver_priv;
+
+ spin_lock(&file_priv->mm.lock);
+ req->file_priv = file_priv;
+ list_add_tail(&req->client_list, &file_priv->mm.request_list);
+ spin_unlock(&file_priv->mm.lock);
+
+ req->pid = get_pid(task_pid(current));
+
+ return 0;
+}
+
static inline void
i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
{
list_del(&request->client_list);
request->file_priv = NULL;
spin_unlock(&file_priv->mm.lock);
+
+ put_pid(request->pid);
+ request->pid = NULL;
}
static void i915_gem_request_retire(struct drm_i915_gem_request *request)
list_del_init(&request->list);
i915_gem_request_remove_from_client(request);
- put_pid(request->pid);
-
i915_gem_request_unreference(request);
}
if (ret)
return ret;
- ret = i915_gem_check_olr(req);
- if (ret)
- return ret;
-
ret = __i915_wait_request(req,
atomic_read(&dev_priv->gpu_error.reset_counter),
interruptible, NULL, NULL);
if (req == NULL)
return 0;
- ret = i915_gem_check_olr(req);
- if (ret)
- goto err;
-
requests[n++] = i915_gem_request_reference(req);
} else {
for (i = 0; i < I915_NUM_RINGS; i++) {
if (req == NULL)
continue;
- ret = i915_gem_check_olr(req);
- if (ret)
- goto err;
-
requests[n++] = i915_gem_request_reference(req);
}
}
NULL, rps);
mutex_lock(&dev->struct_mutex);
-err:
for (i = 0; i < n; i++) {
if (ret == 0)
i915_gem_object_retire_request(obj, requests[i]);
}
void i915_vma_move_to_active(struct i915_vma *vma,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
struct drm_i915_gem_object *obj = vma->obj;
+ struct intel_engine_cs *ring;
+
+ ring = i915_gem_request_get_ring(req);
/* Add a reference if we're newly entering the active list. */
if (obj->active == 0)
obj->active |= intel_ring_flag(ring);
list_move_tail(&obj->ring_list[ring->id], &ring->active_list);
- i915_gem_request_assign(&obj->last_read_req[ring->id],
- intel_ring_get_request(ring));
+ i915_gem_request_assign(&obj->last_read_req[ring->id], req);
list_move_tail(&vma->mm_list, &vma->vm->active_list);
}
* request is not being tracked for completion but the work itself is
* going to happen on the hardware. This would be a Bad Thing(tm).
*/
-void __i915_add_request(struct intel_engine_cs *ring,
- struct drm_file *file,
+void __i915_add_request(struct drm_i915_gem_request *request,
struct drm_i915_gem_object *obj,
bool flush_caches)
{
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
- struct drm_i915_gem_request *request;
+ struct intel_engine_cs *ring;
+ struct drm_i915_private *dev_priv;
struct intel_ringbuffer *ringbuf;
u32 request_start;
int ret;
- request = ring->outstanding_lazy_request;
if (WARN_ON(request == NULL))
return;
- if (i915.enable_execlists) {
- ringbuf = request->ctx->engine[ring->id].ringbuf;
- } else
- ringbuf = ring->buffer;
+ ring = request->ring;
+ dev_priv = ring->dev->dev_private;
+ ringbuf = request->ringbuf;
/*
* To ensure that this call will not fail, space for its emissions
*/
if (flush_caches) {
if (i915.enable_execlists)
- ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
+ ret = logical_ring_flush_all_caches(request);
else
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(request);
/* Not allowed to fail! */
WARN(ret, "*_ring_flush_all_caches failed: %d!\n", ret);
}
request->postfix = intel_ring_get_tail(ringbuf);
if (i915.enable_execlists)
- ret = ring->emit_request(ringbuf, request);
+ ret = ring->emit_request(request);
else {
- ret = ring->add_request(ring);
+ ret = ring->add_request(request);
request->tail = intel_ring_get_tail(ringbuf);
}
request->emitted_jiffies = jiffies;
list_add_tail(&request->list, &ring->request_list);
- request->file_priv = NULL;
-
- if (file) {
- struct drm_i915_file_private *file_priv = file->driver_priv;
-
- spin_lock(&file_priv->mm.lock);
- request->file_priv = file_priv;
- list_add_tail(&request->client_list,
- &file_priv->mm.request_list);
- spin_unlock(&file_priv->mm.lock);
-
- request->pid = get_pid(task_pid(current));
- }
trace_i915_gem_request_add(request);
- ring->outstanding_lazy_request = NULL;
i915_queue_hangcheck(ring->dev);
typeof(*req), ref);
struct intel_context *ctx = req->ctx;
+ if (req->file_priv)
+ i915_gem_request_remove_from_client(req);
+
if (ctx) {
if (i915.enable_execlists) {
struct intel_engine_cs *ring = req->ring;
if (!req_out)
return -EINVAL;
- if ((*req_out = ring->outstanding_lazy_request) != NULL)
- return 0;
+ *req_out = NULL;
req = kmem_cache_zalloc(dev_priv->requests, GFP_KERNEL);
if (req == NULL)
* i915_add_request() call can't fail. Note that the reserve may need
* to be redone if the request is not actually submitted straight
* away, e.g. because a GPU scheduler has deferred it.
- *
- * Note further that this call merely notes the reserve request. A
- * subsequent call to *_ring_begin() is required to actually ensure
- * that the reservation is available. Without the begin, if the
- * request creator immediately submitted the request without adding
- * any commands to it then there might not actually be sufficient
- * room for the submission commands. Unfortunately, the current
- * *_ring_begin() implementations potentially call back here to
- * i915_gem_request_alloc(). Thus calling _begin() here would lead to
- * infinite recursion! Until that back call path is removed, it is
- * necessary to do a manual _begin() outside.
*/
- intel_ring_reserved_space_reserve(req->ringbuf, MIN_SPACE_FOR_ADD_REQUEST);
+ if (i915.enable_execlists)
+ ret = intel_logical_ring_reserve_space(req);
+ else
+ ret = intel_ring_reserve_space(req);
+ if (ret) {
+ /*
+ * At this point, the request is fully allocated even if not
+ * fully prepared. Thus it can be cleaned up using the proper
+ * free code.
+ */
+ i915_gem_request_cancel(req);
+ return ret;
+ }
- *req_out = ring->outstanding_lazy_request = req;
+ *req_out = req;
return 0;
err:
i915_gem_request_retire(request);
}
-
- /* This may not have been flushed before the reset, so clean it now */
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
}
void i915_gem_restore_fences(struct drm_device *dev)
static int
i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
{
- int ret, i;
+ int i;
if (!obj->active)
return 0;
if (list_empty(&req->list))
goto retire;
- ret = i915_gem_check_olr(req);
- if (ret)
- return ret;
-
if (i915_gem_request_completed(req, true)) {
__i915_gem_request_retire__upto(req);
retire:
static int
__i915_gem_object_sync(struct drm_i915_gem_object *obj,
struct intel_engine_cs *to,
- struct drm_i915_gem_request *req)
+ struct drm_i915_gem_request *from_req,
+ struct drm_i915_gem_request **to_req)
{
struct intel_engine_cs *from;
int ret;
- from = i915_gem_request_get_ring(req);
+ from = i915_gem_request_get_ring(from_req);
if (to == from)
return 0;
- if (i915_gem_request_completed(req, true))
+ if (i915_gem_request_completed(from_req, true))
return 0;
- ret = i915_gem_check_olr(req);
- if (ret)
- return ret;
-
if (!i915_semaphore_is_enabled(obj->base.dev)) {
struct drm_i915_private *i915 = to_i915(obj->base.dev);
- ret = __i915_wait_request(req,
+ ret = __i915_wait_request(from_req,
atomic_read(&i915->gpu_error.reset_counter),
i915->mm.interruptible,
NULL,
if (ret)
return ret;
- i915_gem_object_retire_request(obj, req);
+ i915_gem_object_retire_request(obj, from_req);
} else {
int idx = intel_ring_sync_index(from, to);
- u32 seqno = i915_gem_request_get_seqno(req);
+ u32 seqno = i915_gem_request_get_seqno(from_req);
+
+ WARN_ON(!to_req);
if (seqno <= from->semaphore.sync_seqno[idx])
return 0;
- trace_i915_gem_ring_sync_to(from, to, req);
- ret = to->semaphore.sync_to(to, from, seqno);
+ if (*to_req == NULL) {
+ ret = i915_gem_request_alloc(to, to->default_context, to_req);
+ if (ret)
+ return ret;
+ }
+
+ trace_i915_gem_ring_sync_to(*to_req, from, from_req);
+ ret = to->semaphore.sync_to(*to_req, from, seqno);
if (ret)
return ret;
*
* @obj: object which may be in use on another ring.
* @to: ring we wish to use the object on. May be NULL.
+ * @to_req: request we wish to use the object for. See below.
+ * This will be allocated and returned if a request is
+ * required but not passed in.
*
* This code is meant to abstract object synchronization with the GPU.
* Calling with NULL implies synchronizing the object with the CPU
* rather than a particular GPU ring. Conceptually we serialise writes
- * between engines inside the GPU. We only allow on engine to write
+ * between engines inside the GPU. We only allow one engine to write
* into a buffer at any time, but multiple readers. To ensure each has
* a coherent view of memory, we must:
*
* - If we are a write request (pending_write_domain is set), the new
* request must wait for outstanding read requests to complete.
*
+ * For CPU synchronisation (NULL to) no request is required. For syncing with
+ * rings to_req must be non-NULL. However, a request does not have to be
+ * pre-allocated. If *to_req is NULL and sync commands will be emitted then a
+ * request will be allocated automatically and returned through *to_req. Note
+ * that it is not guaranteed that commands will be emitted (because the system
+ * might already be idle). Hence there is no need to create a request that
+ * might never have any work submitted. Note further that if a request is
+ * returned in *to_req, it is the responsibility of the caller to submit
+ * that request (after potentially adding more work to it).
+ *
* Returns 0 if successful, else propagates up the lower layer error.
*/
int
i915_gem_object_sync(struct drm_i915_gem_object *obj,
- struct intel_engine_cs *to)
+ struct intel_engine_cs *to,
+ struct drm_i915_gem_request **to_req)
{
const bool readonly = obj->base.pending_write_domain == 0;
struct drm_i915_gem_request *req[I915_NUM_RINGS];
req[n++] = obj->last_read_req[i];
}
for (i = 0; i < n; i++) {
- ret = __i915_gem_object_sync(obj, to, req[i]);
+ ret = __i915_gem_object_sync(obj, to, req[i], to_req);
if (ret)
return ret;
}
return ret;
}
- i915_add_request_no_flush(req->ring);
+ i915_add_request_no_flush(req);
}
- WARN_ON(ring->outstanding_lazy_request);
-
ret = intel_ring_idle(ring);
if (ret)
return ret;
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
u32 size, fence_size, fence_alignment, unfenced_alignment;
- unsigned long start =
+ u64 start =
flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
- unsigned long end =
+ u64 end =
flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total;
struct i915_vma *vma;
int ret;
* attempt to find space.
*/
if (size > end) {
- DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%lu\n",
+ DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%llu\n",
ggtt_view ? ggtt_view->type : 0,
size,
flags & PIN_MAPPABLE ? "mappable" : "total",
i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
u32 alignment,
struct intel_engine_cs *pipelined,
+ struct drm_i915_gem_request **pipelined_request,
const struct i915_ggtt_view *view)
{
u32 old_read_domains, old_write_domain;
int ret;
- ret = i915_gem_object_sync(obj, pipelined);
+ ret = i915_gem_object_sync(obj, pipelined, pipelined_request);
if (ret)
return ret;
if (time_after_eq(request->emitted_jiffies, recent_enough))
break;
+ /*
+ * Note that the request might not have been submitted yet.
+ * In which case emitted_jiffies will be zero.
+ */
+ if (!request->emitted_jiffies)
+ continue;
+
target = request;
}
reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
return ret;
}
-int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
if (!HAS_L3_DPF(dev) || !remap_info)
return 0;
- ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
+ ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
if (ret)
return ret;
if (ring->id == RCS) {
for (j = 0; j < NUM_L3_SLICES(dev); j++)
- i915_gem_l3_remap(ring, j);
+ i915_gem_l3_remap(req, j);
}
ret = i915_ppgtt_init_ring(req);
goto out;
}
- i915_add_request_no_flush(ring);
+ i915_add_request_no_flush(req);
}
out: