From: Christian König <christian.koenig@xxxxxxx>
We align to 64KB, but when userspace aligns even more we can easily use more.
Signed-off-by: Christian König <christian.koenig at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index e6c030b..88f4109 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -817,13 +817,13 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params *params,
* allocation size to the fragment size.
*/
- /* 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;
+ const 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 || params->pages_addr || !(flags & AMDGPU_PTE_VALID) ||
(frag_start >= frag_end)) {
@@ -832,6 +832,10 @@ 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,
@@ -841,7 +845,7 @@ 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 | frag_flags);
+ flags | AMDGPU_PTE_FRAG(frag));
/* handle the 4K area at the end */
if (frag_end != end) {
--
2.5.0
