drm/amdgpu: extend lock range for race condition when gpu reset

to cover below case:
1. A task gart bind/unbind but not add to adev->gtt_list yet
2. at this time gpu reset, gtt only recover those gtt in adev->gtt_list

Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Roger.He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 14 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 5db0230e45c6..fcf617c237ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -745,6 +745,7 @@ int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem)
                 return r;
         }
 
+        spin_lock(&gtt->adev->gtt_list_lock);
         flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem);
         gtt->offset = (u64)bo_mem->start << PAGE_SHIFT;
         r = amdgpu_gart_bind(gtt->adev, gtt->offset, ttm->num_pages,
@@ -753,12 +754,13 @@ int amdgpu_ttm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *bo_mem)
         if (r) {
                 DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
                           ttm->num_pages, gtt->offset);
-                return r;
+                goto error_gart_bind;
         }
-        spin_lock(&gtt->adev->gtt_list_lock);
+
         list_add_tail(&gtt->list, &gtt->adev->gtt_list);
+error_gart_bind:
         spin_unlock(&gtt->adev->gtt_list_lock);
-        return 0;
+        return r;
 }
 
 int amdgpu_ttm_recover_gart(struct amdgpu_device *adev)
@@ -789,6 +791,7 @@ int amdgpu_ttm_recover_gart(struct amdgpu_device *adev)
 static int amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
 {
         struct amdgpu_ttm_tt *gtt = (void *)ttm;
+        int r;
 
         if (gtt->userptr)
                 amdgpu_ttm_tt_unpin_userptr(ttm);
@@ -797,14 +800,17 @@ static int amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
                 return 0;
 
         /* unbind shouldn't be done for GDS/GWS/OA in ttm_bo_clean_mm */
-        if (gtt->adev->gart.ready)
-                amdgpu_gart_unbind(gtt->adev, gtt->offset, ttm->num_pages);
-
         spin_lock(&gtt->adev->gtt_list_lock);
+        r = amdgpu_gart_unbind(gtt->adev, gtt->offset, ttm->num_pages);
+        if (r) {
+                DRM_ERROR("failed to unbind %lu pages at 0x%08llX\n",
+                          gtt->ttm.ttm.num_pages, gtt->offset);
+                goto error_unbind;
+        }
         list_del_init(&gtt->list);
+error_unbind:
         spin_unlock(&gtt->adev->gtt_list_lock);
-
-        return 0;
+        return r;
 }
 
 static void amdgpu_ttm_backend_destroy(struct ttm_tt *ttm)