FEX-Emu/linux
1
0
Fork 0
mirror of https://github.com/FEX-Emu/linux.git synced 2024-12-23 09:56:00 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

drm/i915: Disable EXEC_OBJECT_ASYNC when doing relocations

Browse Source 
If we write a relocation into the buffer, we require our own implicit
synchronisation added after the start of the execbuf, outside of the
user's control. As we may end up clflushing, or doing the patch itself
on the GPU, asynchronously we need to look at the implicit serialisation
on obj->resv and hence need to disable EXEC_OBJECT_ASYNC for this
object.

If the user does trigger a stall for relocations, we make sure the stall
is complete enough so that the batch is not submitted before we complete
those relocations.

Fixes: 77ae995789 ("drm/i915: Enable userspace to opt-out of implicit fencing")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
(cherry picked from commit 071750e550)
[danvet: Resolve conflicts, resolution reviewed by Tvrtko on irc.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This commit is contained in:
Chris Wilson 2017-06-16 15:05:18 +01:00 committed by Daniel Vetter
parent 2c73676267
commit 611cdf3695
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
drivers/gpu/drm/i915/i915_gem_execbuffer.c
View File

@ -546,11 +546,12 @@ repeat:
}
static int
i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
i915_gem_execbuffer_relocate_entry(struct i915_vma *vma,
struct eb_vmas *eb,
struct drm_i915_gem_relocation_entry *reloc,
struct reloc_cache *cache)
{
struct drm_i915_gem_object *obj = vma->obj;
struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
struct drm_gem_object *target_obj;
struct drm_i915_gem_object *target_i915_obj;
@ -628,6 +629,16 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
return -EINVAL;
}
/*
* If we write into the object, we need to force the synchronisation
* barrier, either with an asynchronous clflush or if we executed the
* patching using the GPU (though that should be serialised by the
* timeline). To be completely sure, and since we are required to
* do relocations we are already stalling, disable the user's opt
* of our synchronisation.
*/
vma->exec_entry->flags &= ~EXEC_OBJECT_ASYNC;
ret = relocate_entry(obj, reloc, cache, target_offset);
if (ret)
return ret;
@ -678,7 +689,7 @@ i915_gem_execbuffer_relocate_vma(struct i915_vma *vma,
do {
u64 offset = r->presumed_offset;
ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r, &cache);
ret = i915_gem_execbuffer_relocate_entry(vma, eb, r, &cache);
if (ret)
goto out;
@ -726,7 +737,7 @@ i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma,
reloc_cache_init(&cache, eb->i915);
for (i = 0; i < entry->relocation_count; i++) {
ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i], &cache);
ret = i915_gem_execbuffer_relocate_entry(vma, eb, &relocs[i], &cache);
if (ret)
break;
}