diff options
| author | Christian König <christian.koenig@amd.com> | 2016-10-04 13:39:43 +0200 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2016-10-06 12:39:04 -0400 |
| commit | 8036617e92e3fad49eef9bbe868b661c58249aff (patch) | |
| tree | a20f4830cf3efbfd4502c0845f3c2fe7ec805557 /drivers/gpu/drm | |
| parent | 2f9ba199daf32dded4ef0237cd12efac451ebf47 (diff) | |
| download | op-kernel-dev-8036617e92e3fad49eef9bbe868b661c58249aff.zip op-kernel-dev-8036617e92e3fad49eef9bbe868b661c58249aff.tar.gz | |
drm/amdgpu: revert "use more than 64KB fragment size if possible"
This reverts commit 1dcd32fb9c54334ec948a0f18174a748d6b14364.
The block size is indeed an equal match, so this can cause performance regressions.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Diffstat (limited to 'drivers/gpu/drm')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 |
1 files changed, 4 insertions, 8 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index bc4b22c..06f2432 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -878,13 +878,13 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params *params, * allocation size to the fragment size. */ - const uint64_t frag_align = 1 << AMDGPU_LOG2_PAGES_PER_FRAG; + /* SI and newer are optimized for 64KB */ + uint64_t frag_flags = AMDGPU_PTE_FRAG(AMDGPU_LOG2_PAGES_PER_FRAG); + uint64_t frag_align = 1 << AMDGPU_LOG2_PAGES_PER_FRAG; uint64_t frag_start = ALIGN(start, frag_align); uint64_t frag_end = end & ~(frag_align - 1); - uint32_t frag; - /* system pages are non continuously */ if (params->src || !(flags & AMDGPU_PTE_VALID) || (frag_start >= frag_end)) { @@ -893,10 +893,6 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params *params, return; } - /* use more than 64KB fragment size if possible */ - frag = lower_32_bits(frag_start | frag_end); - frag = likely(frag) ? __ffs(frag) : 31; - /* handle the 4K area at the beginning */ if (start != frag_start) { amdgpu_vm_update_ptes(params, vm, start, frag_start, @@ -906,7 +902,7 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params *params, /* handle the area in the middle */ amdgpu_vm_update_ptes(params, vm, frag_start, frag_end, dst, - flags | AMDGPU_PTE_FRAG(frag)); + flags | frag_flags); /* handle the 4K area at the end */ if (frag_end != end) { |
