diff options
| author | Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> | 2026-01-09 23:26:36 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2026-02-04 01:24:21 +0300 |
| commit | 6b61a54e684006ca0d92d684a1d3c3a00f077d8f (patch) | |
| tree | 4127f442c5eda13f15fe4c4297c914ae4f08039e /drivers | |
| parent | 84962445cd8a83dc5bed4c8ad5bbb2c1cdb249a0 (diff) | |
| download | linux-6b61a54e684006ca0d92d684a1d3c3a00f077d8f.tar.xz | |
drm/amdgpu: Fix double deletion of validate_list
If amdgpu_amdkfd_gpuvm_free_memory_of_gpu() fails after kgd_mem is
removed from validate_list, the mem handle still lingers in the KFD idr.
This means when process is terminated,
kfd_process_free_outstanding_kfd_bos() will call
amdgpu_amdkfd_gpuvm_free_memory_of_gpu() again resulting in double
deletion.
To avoid this -
(a) Check if list is empty before deleting it
(b) Rearragne amdgpu_amdkfd_gpuvm_free_memory_of_gpu() such that it can
be safely called again if it returns failure the first time.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6ba60345f45eaf7cb4f89105d26083a4b9fd1cba)
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index b1c24c8fa686..a51e76623bad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1920,21 +1920,21 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( /* Make sure restore workers don't access the BO any more */ mutex_lock(&process_info->lock); - list_del(&mem->validate_list); + if (!list_empty(&mem->validate_list)) + list_del_init(&mem->validate_list); mutex_unlock(&process_info->lock); + ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx); + if (unlikely(ret)) + return ret; + /* Cleanup user pages and MMU notifiers */ if (amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm)) { amdgpu_hmm_unregister(mem->bo); - mutex_lock(&process_info->notifier_lock); amdgpu_hmm_range_free(mem->range); - mutex_unlock(&process_info->notifier_lock); + mem->range = NULL; } - ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx); - if (unlikely(ret)) - return ret; - amdgpu_amdkfd_remove_eviction_fence(mem->bo, process_info->eviction_fence); pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va, |