| Message ID | 20220202173154.3758970-1-matthew.auld@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | drm/i915: opportunistically apply ALLOC_CONTIGIOUS | expand |
On 2/2/22 18:31, Matthew Auld wrote: > It looks like this code was accidentally dropped at some point(in a > slightly different form), so add it back. The gist is that if we know > the allocation will be one single chunk, then we can just annotate the > BO with I915_BO_ALLOC_CONTIGUOUS, even if the user doesn't bother. In > the future this might prove to be potentially useful. Perhaps be more clear that this allows us to avoid using vmap in upcoming patches. > > Signed-off-by: Matthew Auld <matthew.auld@intel.com> > Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> > --- > drivers/gpu/drm/i915/gem/i915_gem_region.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c > index a4350227e9ae..dd414a2bcb06 100644 > --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c > +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c > @@ -57,6 +57,9 @@ i915_gem_object_create_region(struct intel_memory_region *mem, > > size = round_up(size, default_page_size); > > + if (default_page_size == size) > + flags |= I915_BO_ALLOC_CONTIGUOUS; > + > GEM_BUG_ON(!size); > GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_MIN_ALIGNMENT)); > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index a4350227e9ae..dd414a2bcb06 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -57,6 +57,9 @@ i915_gem_object_create_region(struct intel_memory_region *mem, size = round_up(size, default_page_size); + if (default_page_size == size) + flags |= I915_BO_ALLOC_CONTIGUOUS; + GEM_BUG_ON(!size); GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_MIN_ALIGNMENT));
It looks like this code was accidentally dropped at some point(in a slightly different form), so add it back. The gist is that if we know the allocation will be one single chunk, then we can just annotate the BO with I915_BO_ALLOC_CONTIGUOUS, even if the user doesn't bother. In the future this might prove to be potentially useful. Signed-off-by: Matthew Auld <matthew.auld@intel.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> --- drivers/gpu/drm/i915/gem/i915_gem_region.c | 3 +++ 1 file changed, 3 insertions(+)