drm/amdgpu: Fix missing drain retry fault the last entry

While the entry get in svm_range_unmap_from_cpu is the last entry, and
the entry is page fault, it also need to be dropped. So for equal case,
it also need to be dropped.

v2:
Only modify the svm_range_restore_pages.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Xiaogang Chen<xiaogang.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Emily Deng 2025-03-03 15:10:22 +08:00 committed by Alex Deucher
parent 94b0908b85
commit fe2fa3be3d
2 changed files with 4 additions and 1 deletions

View file

@ -78,6 +78,9 @@ struct amdgpu_ih_ring {
#define amdgpu_ih_ts_after(t1, t2) \ #define amdgpu_ih_ts_after(t1, t2) \
(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL) (((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL)
#define amdgpu_ih_ts_after_or_equal(t1, t2) \
(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) >= 0LL)
/* provided by the ih block */ /* provided by the ih block */
struct amdgpu_ih_funcs { struct amdgpu_ih_funcs {
/* ring read/write ptr handling, called from interrupt context */ /* ring read/write ptr handling, called from interrupt context */

View file

@ -3011,7 +3011,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
/* check if this page fault time stamp is before svms->checkpoint_ts */ /* check if this page fault time stamp is before svms->checkpoint_ts */
if (svms->checkpoint_ts[gpuidx] != 0) { if (svms->checkpoint_ts[gpuidx] != 0) {
if (amdgpu_ih_ts_after(ts, svms->checkpoint_ts[gpuidx])) { if (amdgpu_ih_ts_after_or_equal(ts, svms->checkpoint_ts[gpuidx])) {
pr_debug("draining retry fault, drop fault 0x%llx\n", addr); pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
r = 0; r = 0;
goto out; goto out;