Commit 43566ded authored by Chris Wilson's avatar Chris Wilson Committed by Daniel Vetter

drm/i915: Broaden application of set-domain(GTT)

Previously, this was restricted to only operate on bound objects - to
make pointer access through the GTT to the object coherent with writes
to and from the GPU. A second usecase is drm_intel_bo_wait_rendering()
which at present does not function unless the object also happens to
be bound into the GGTT (on current systems that is becoming increasingly
rare, especially for the typical requests from mesa). A third usecase is
a future patch wishing to extend the coverage of the GTT domain to
include objects not bound into the GGTT but still in its coherent cache
domain. For the latter pair of requests, we need to operate on the
object regardless of its bind state.

v2: After discussion with Akash, we came to the conclusion that the
get-pages was required in order for accurate domain tracking in the
corner cases (like the shrinker) and also useful for ensuring memory
coherency with earlier cached CPU mmaps in case userspace uses exotic
cache bypass (non-temporal) instructions.

v3: Fix the inactive object check.

v4: Rebase to latest drm-intel-nightly codebase
Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: default avatarAkash Goel <akash.goel@intel.com>
Signed-off-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
parent b9b5dce5
...@@ -153,12 +153,6 @@ int i915_mutex_lock_interruptible(struct drm_device *dev) ...@@ -153,12 +153,6 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
return 0; return 0;
} }
static inline bool
i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
{
return i915_gem_obj_bound_any(obj) && !obj->active;
}
int int
i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
struct drm_file *file) struct drm_file *file)
...@@ -1472,18 +1466,10 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, ...@@ -1472,18 +1466,10 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
if (ret) if (ret)
goto unref; goto unref;
if (read_domains & I915_GEM_DOMAIN_GTT) { if (read_domains & I915_GEM_DOMAIN_GTT)
ret = i915_gem_object_set_to_gtt_domain(obj, write_domain != 0); ret = i915_gem_object_set_to_gtt_domain(obj, write_domain != 0);
else
/* Silently promote "you're not bound, there was nothing to do"
* to success, since the client was just asking us to
* make sure everything was done.
*/
if (ret == -EINVAL)
ret = 0;
} else {
ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0); ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0);
}
unref: unref:
drm_gem_object_unreference(&obj->base); drm_gem_object_unreference(&obj->base);
...@@ -3699,15 +3685,10 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj, ...@@ -3699,15 +3685,10 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
int int
i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
{ {
struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
uint32_t old_write_domain, old_read_domains; uint32_t old_write_domain, old_read_domains;
struct i915_vma *vma;
int ret; int ret;
/* Not valid to be called on unbound objects. */
if (vma == NULL)
return -EINVAL;
if (obj->base.write_domain == I915_GEM_DOMAIN_GTT) if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
return 0; return 0;
...@@ -3716,6 +3697,19 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) ...@@ -3716,6 +3697,19 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
return ret; return ret;
i915_gem_object_retire(obj); i915_gem_object_retire(obj);
/* Flush and acquire obj->pages so that we are coherent through
* direct access in memory with previous cached writes through
* shmemfs and that our cache domain tracking remains valid.
* For example, if the obj->filp was moved to swap without us
* being notified and releasing the pages, we would mistakenly
* continue to assume that the obj remained out of the CPU cached
* domain.
*/
ret = i915_gem_object_get_pages(obj);
if (ret)
return ret;
i915_gem_object_flush_cpu_write_domain(obj, false); i915_gem_object_flush_cpu_write_domain(obj, false);
/* Serialise direct access to this object with the barriers for /* Serialise direct access to this object with the barriers for
...@@ -3747,9 +3741,10 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) ...@@ -3747,9 +3741,10 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
old_write_domain); old_write_domain);
/* And bump the LRU for this access */ /* And bump the LRU for this access */
if (i915_gem_object_is_inactive(obj)) vma = i915_gem_obj_to_ggtt(obj);
if (vma && drm_mm_node_allocated(&vma->node) && !obj->active)
list_move_tail(&vma->mm_list, list_move_tail(&vma->mm_list,
&dev_priv->gtt.base.inactive_list); &to_i915(obj->base.dev)->gtt.base.inactive_list);
return 0; return 0;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment