diff options
| author | Michel Dänzer <michel.daenzer@amd.com> | 2014-08-28 15:56:00 +0900 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2014-09-10 11:29:45 -0400 |
| commit | c858403943886a92eece9d0413aa65c48bbe6fa7 (patch) | |
| tree | a259ede5ad9d773075b868e9bd28fbd4e2ae75cb /drivers/gpu/drm/radeon/radeon_object.c | |
| parent | fdcaa1dbb7c6ed419b10fb8cdb5001ab0a00538f (diff) | |
| download | linux-stable-c858403943886a92eece9d0413aa65c48bbe6fa7.tar.gz linux-stable-c858403943886a92eece9d0413aa65c48bbe6fa7.tar.bz2 linux-stable-c858403943886a92eece9d0413aa65c48bbe6fa7.zip | |
drm/radeon: Add RADEON_GEM_CPU_ACCESS BO creation flag
This flag is a hint that userspace expects the BO to be accessed by the
CPU. We can use that hint to prevent such BOs from ever being stored in
the CPU inaccessible part of VRAM.
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/radeon/radeon_object.c')
| -rw-r--r-- | drivers/gpu/drm/radeon/radeon_object.c | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index aadbd36e64b9..eef60aaf4e64 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -144,7 +144,12 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) for (i = 0; i < c; ++i) { rbo->placements[i].fpfn = 0; - rbo->placements[i].lpfn = 0; + if ((rbo->flags & RADEON_GEM_CPU_ACCESS) && + (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) + rbo->placements[i].lpfn = + rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT; + else + rbo->placements[i].lpfn = 0; } /* @@ -152,7 +157,9 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) * improve fragmentation quality. * 512kb was measured as the most optimal number. */ - if (rbo->tbo.mem.size > 512 * 1024) { + if (!((rbo->flags & RADEON_GEM_CPU_ACCESS) && + (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) && + rbo->tbo.mem.size > 512 * 1024) { for (i = 0; i < c; i++) { rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN; } |