github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-26 08:02:27 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdkfd: fix the clean up when amdgpu_hmm_range_alloc fails

Browse Source 
we need to unreserve the bo's too during clean up along
with freeing the memory of context.

Fixes: 7bb02a34c2 ("drm/amdkfd: add missing return value check for range")
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Sunil Khatri 2025-10-24 22:29:00 +05:30 committed by Alex Deucher
parent a0559012a1
commit 1017e393ad
1 changed files with 4 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
drivers/gpu/drm/amd/amdkfd/kfd_svm.c
View File

@ -1738,14 +1738,11 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
WRITE_ONCE(p->svms.faulting_task, current);
range = amdgpu_hmm_range_alloc(NULL);
if (unlikely(!range)) {
if (likely(range))
r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages,
readonly, owner, range);
else
r = -ENOMEM;
goto free_ctx;
}
r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages,
readonly, owner,
range);
WRITE_ONCE(p->svms.faulting_task, NULL);
if (r) {
amdgpu_hmm_range_free(range);