drm/amdgpu: Align amdgpu_gtt_mgr entries to TLB size on Tahiti (v2)

The TLB is organized in groups of 8 entries, each one is 4K.
On Tahiti, the HW requires these GART entries to be 32K-aligned.

This fixes a VCE 1 firmware validation failure that can happen
after suspend/resume since we use amdgpu_gtt_mgr for VCE 1.

v2:
- Change variable declaration order
- Add comment about "V bit HW bug"

Fixes: 698fa62f56 ("drm/amdgpu: Add helper to alloc GART entries")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Timur Kristóf 2026-05-13 22:04:08 +02:00 committed by Alex Deucher
parent 7ef144458f
commit 530411b465

View File

@ -199,11 +199,18 @@ int amdgpu_gtt_mgr_alloc_entries(struct amdgpu_gtt_mgr *mgr,
enum drm_mm_insert_mode mode)
{
struct amdgpu_device *adev = container_of(mgr, typeof(*adev), mman.gtt_mgr);
u32 alignment = 0;
int r;
/* Align to TLB L2 cache entry size to work around "V bit HW bug" */
if (adev->asic_type == CHIP_TAHITI) {
alignment = 32 * 1024 / AMDGPU_GPU_PAGE_SIZE;
num_pages = ALIGN(num_pages, alignment);
}
spin_lock(&mgr->lock);
r = drm_mm_insert_node_in_range(&mgr->mm, mm_node, num_pages,
0, GART_ENTRY_WITHOUT_BO_COLOR, 0,
alignment, GART_ENTRY_WITHOUT_BO_COLOR, 0,
adev->gmc.gart_size >> PAGE_SHIFT,
mode);
spin_unlock(&mgr->lock);