return 0;
}
+void *i915_gem_object_alloc(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ return kmem_cache_alloc(dev_priv->slab, GFP_KERNEL | __GFP_ZERO);
+}
+
+void i915_gem_object_free(struct drm_i915_gem_object *obj)
+{
+ struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+ kmem_cache_free(dev_priv->slab, obj);
+}
+
static int
i915_gem_create(struct drm_file *file,
struct drm_device *dev,
if (ret) {
drm_gem_object_release(&obj->base);
i915_gem_info_remove_obj(dev->dev_private, obj->base.size);
- kfree(obj);
+ i915_gem_object_free(obj);
return ret;
}
args->size, &args->handle);
}
-static int i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
-{
- drm_i915_private_t *dev_priv = obj->base.dev->dev_private;
-
- return dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 &&
- obj->tiling_mode != I915_TILING_NONE;
-}
-
static inline int
__copy_to_user_swizzled(char __user *cpu_vaddr,
const char *gpu_vaddr, int gpu_offset,
loff_t offset;
int shmem_page_offset, page_length, ret = 0;
int obj_do_bit17_swizzling, page_do_bit17_swizzling;
- int hit_slowpath = 0;
int prefaulted = 0;
int needs_clflush = 0;
struct scatterlist *sg;
if (ret == 0)
goto next_page;
- hit_slowpath = 1;
mutex_unlock(&dev->struct_mutex);
if (!prefaulted) {
out:
i915_gem_object_unpin_pages(obj);
- if (hit_slowpath) {
- /* Fixup: Kill any reinstated backing storage pages */
- if (obj->madv == __I915_MADV_PURGED)
- i915_gem_object_truncate(obj);
- }
-
return ret;
}
i915_gem_object_unpin_pages(obj);
if (hit_slowpath) {
- /* Fixup: Kill any reinstated backing storage pages */
- if (obj->madv == __I915_MADV_PURGED)
- i915_gem_object_truncate(obj);
- /* and flush dirty cachelines in case the object isn't in the cpu write
- * domain anymore. */
- if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+ /*
+ * Fixup: Flush cpu caches in case we didn't flush the dirty
+ * cachelines in-line while writing and the object moved
+ * out of the cpu write domain while we've dropped the lock.
+ */
+ if (!needs_clflush_after &&
+ obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
i915_gem_clflush_object(obj);
i915_gem_chipset_flush(dev);
}
void
i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
- struct intel_ring_buffer *ring,
- u32 seqno)
+ struct intel_ring_buffer *ring)
{
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 seqno = intel_ring_get_seqno(ring);
BUG_ON(ring == NULL);
obj->ring = ring;
WARN_ON(i915_verify_lists(dev));
}
-static u32
-i915_gem_get_seqno(struct drm_device *dev)
+static int
+i915_gem_handle_seqno_wrap(struct drm_device *dev)
{
- drm_i915_private_t *dev_priv = dev->dev_private;
- u32 seqno = dev_priv->next_seqno;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_ring_buffer *ring;
+ int ret, i, j;
- /* reserve 0 for non-seqno */
- if (++dev_priv->next_seqno == 0)
- dev_priv->next_seqno = 1;
+ /* The hardware uses various monotonic 32-bit counters, if we
+ * detect that they will wraparound we need to idle the GPU
+ * and reset those counters.
+ */
+ ret = 0;
+ for_each_ring(ring, dev_priv, i) {
+ for (j = 0; j < ARRAY_SIZE(ring->sync_seqno); j++)
+ ret |= ring->sync_seqno[j] != 0;
+ }
+ if (ret == 0)
+ return ret;
- return seqno;
+ ret = i915_gpu_idle(dev);
+ if (ret)
+ return ret;
+
+ i915_gem_retire_requests(dev);
+ for_each_ring(ring, dev_priv, i) {
+ ret = intel_ring_handle_seqno_wrap(ring);
+ if (ret)
+ return ret;
+
+ for (j = 0; j < ARRAY_SIZE(ring->sync_seqno); j++)
+ ring->sync_seqno[j] = 0;
+ }
+
+ return 0;
}
-u32
-i915_gem_next_request_seqno(struct intel_ring_buffer *ring)
+int
+i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
{
- if (ring->outstanding_lazy_request == 0)
- ring->outstanding_lazy_request = i915_gem_get_seqno(ring->dev);
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ /* reserve 0 for non-seqno */
+ if (dev_priv->next_seqno == 0) {
+ int ret = i915_gem_handle_seqno_wrap(dev);
+ if (ret)
+ return ret;
- return ring->outstanding_lazy_request;
+ dev_priv->next_seqno = 1;
+ }
+
+ *seqno = dev_priv->last_seqno = dev_priv->next_seqno++;
+ return 0;
}
int
drm_i915_private_t *dev_priv = ring->dev->dev_private;
struct drm_i915_gem_request *request;
u32 request_ring_position;
- u32 seqno;
int was_empty;
int ret;
if (request == NULL)
return -ENOMEM;
- seqno = i915_gem_next_request_seqno(ring);
/* Record the position of the start of the request so that
* should we detect the updated seqno part-way through the
*/
request_ring_position = intel_ring_get_tail(ring);
- ret = ring->add_request(ring, &seqno);
+ ret = ring->add_request(ring);
if (ret) {
kfree(request);
return ret;
}
- trace_i915_gem_request_add(ring, seqno);
-
- request->seqno = seqno;
+ request->seqno = intel_ring_get_seqno(ring);
request->ring = ring;
request->tail = request_ring_position;
request->emitted_jiffies = jiffies;
spin_unlock(&file_priv->mm.lock);
}
+ trace_i915_gem_request_add(ring, request->seqno);
ring->outstanding_lazy_request = 0;
if (!dev_priv->mm.suspended) {
}
if (out_seqno)
- *out_seqno = seqno;
+ *out_seqno = request->seqno;
return 0;
}
i915_gem_retire_requests_ring(struct intel_ring_buffer *ring)
{
uint32_t seqno;
- int i;
if (list_empty(&ring->request_list))
return;
seqno = ring->get_seqno(ring, true);
- for (i = 0; i < ARRAY_SIZE(ring->sync_seqno); i++)
- if (seqno >= ring->sync_seqno[i])
- ring->sync_seqno[i] = 0;
-
while (!list_empty(&ring->request_list)) {
struct drm_i915_gem_request *request;
ret = to->sync_to(to, from, seqno);
if (!ret)
- from->sync_seqno[idx] = seqno;
+ /* We use last_read_seqno because sync_to()
+ * might have just caused seqno wrap under
+ * the radar.
+ */
+ from->sync_seqno[idx] = obj->last_read_seqno;
return ret;
}
return 0;
}
-static int i915_ring_idle(struct intel_ring_buffer *ring)
-{
- if (list_empty(&ring->active_list))
- return 0;
-
- return i915_wait_seqno(ring, i915_gem_next_request_seqno(ring));
-}
-
int i915_gpu_idle(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
if (ret)
return ret;
- ret = i915_ring_idle(ring);
+ ret = intel_ring_idle(ring);
if (ret)
return ret;
}
/* On non-LLC machines we have to be careful when putting differing
* types of snoopable memory together to avoid the prefetcher
- * crossing memory domains and dieing.
+ * crossing memory domains and dying.
*/
if (HAS_LLC(dev))
return true;
{
struct drm_i915_gem_object *obj;
struct address_space *mapping;
- u32 mask;
+ gfp_t mask;
- obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+ obj = i915_gem_object_alloc(dev);
if (obj == NULL)
return NULL;
if (drm_gem_object_init(dev, &obj->base, size) != 0) {
- kfree(obj);
+ i915_gem_object_free(obj);
return NULL;
}
obj->pages_pin_count = 0;
i915_gem_object_put_pages(obj);
i915_gem_object_free_mmap_offset(obj);
+ i915_gem_object_release_stolen(obj);
BUG_ON(obj->pages);
i915_gem_info_remove_obj(dev_priv, obj->base.size);
kfree(obj->bit_17);
- kfree(obj);
+ i915_gem_object_free(obj);
}
int
void
i915_gem_load(struct drm_device *dev)
{
- int i;
drm_i915_private_t *dev_priv = dev->dev_private;
+ int i;
+
+ dev_priv->slab =
+ kmem_cache_create("i915_gem_object",
+ sizeof(struct drm_i915_gem_object), 0,
+ SLAB_HWCACHE_ALIGN,
+ NULL);
INIT_LIST_HEAD(&dev_priv->mm.active_list);
INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
projects / firefly-linux-kernel-4.4.55.git / blobdiff