Am 14.04.22 um 07:03 schrieb xinhui pan:
VM might already be freed when amdgpu_vm_tlb_seq_cb() is called.
We see the calltrace below.
Fix it by keeping the last flush fence around and wait for it to signal
BUG kmalloc-4k (Not tainted): Poison overwritten
0xffff9c88630414e8-0xffff9c88630414e8 @offset=5352. First byte 0x6c
instead of 0x6b Allocated in amdgpu_driver_open_kms+0x9d/0x360 [amdgpu]
age=44 cpu=0 pid=2343
__slab_alloc.isra.0+0x4f/0x90
kmem_cache_alloc_trace+0x6b8/0x7a0
amdgpu_driver_open_kms+0x9d/0x360 [amdgpu]
drm_file_alloc+0x222/0x3e0 [drm]
drm_open+0x11d/0x410 [drm]
Freed in amdgpu_driver_postclose_kms+0x3e9/0x550 [amdgpu] age=22 cpu=1
pid=2485
kfree+0x4a2/0x580
amdgpu_driver_postclose_kms+0x3e9/0x550 [amdgpu]
drm_file_free+0x24e/0x3c0 [drm]
drm_close_helper.isra.0+0x90/0xb0 [drm]
drm_release+0x97/0x1a0 [drm]
__fput+0xb6/0x280
____fput+0xe/0x10
task_work_run+0x64/0xb0
Suggested-by: Christian König <christian.koenig@xxxxxxx>
Signed-off-by: xinhui pan <xinhui.pan@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 17 ++++++++++++++---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 1 +
2 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 645ce28277c2..cd5aa7edd451 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -932,9 +932,12 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
if (flush_tlb || params.table_freed) {
tlb_cb->vm = vm;
- if (!fence || !*fence ||
- dma_fence_add_callback(*fence, &tlb_cb->cb,
- amdgpu_vm_tlb_seq_cb))
+ if (fence && *fence &&
+ !dma_fence_add_callback(*fence, &tlb_cb->cb,
+ amdgpu_vm_tlb_seq_cb)) {
+ dma_fence_put(vm->last_tlb_flush);
+ vm->last_tlb_flush = dma_fence_get(*fence);
+ } else
amdgpu_vm_tlb_seq_cb(NULL, &tlb_cb->cb);
One style nit pick here: When one side of an if/else has {}, the other
side should have {} as well.
Apart from that the patch is Reviewed-by: Christian König
<christian.koenig@xxxxxxx>
Thanks,
Christian.
tlb_cb = NULL;
}
@@ -2094,6 +2097,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
vm->update_funcs = &amdgpu_vm_sdma_funcs;
vm->last_update = NULL;
vm->last_unlocked = dma_fence_get_stub();
+ vm->last_tlb_flush = dma_fence_get_stub();
mutex_init(&vm->eviction_lock);
vm->evicting = false;
@@ -2132,6 +2136,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
vm->root.bo = NULL;
error_free_delayed:
+ dma_fence_put(vm->last_tlb_flush);
dma_fence_put(vm->last_unlocked);
drm_sched_entity_destroy(&vm->delayed);
@@ -2248,6 +2253,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
struct amdgpu_bo_va_mapping *mapping, *tmp;
bool prt_fini_needed = !!adev->gmc.gmc_funcs->set_prt;
struct amdgpu_bo *root;
+ unsigned long flags;
int i;
amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
@@ -2257,6 +2263,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
amdgpu_vm_set_pasid(adev, vm, 0);
dma_fence_wait(vm->last_unlocked, false);
dma_fence_put(vm->last_unlocked);
+ dma_fence_wait(vm->last_tlb_flush, false);
+ /* Make sure that all fence callbacks have completed */
+ spin_lock_irqsave(vm->last_tlb_flush->lock, flags);
+ spin_unlock_irqrestore(vm->last_tlb_flush->lock, flags);
+ dma_fence_put(vm->last_tlb_flush);
list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
if (mapping->flags & AMDGPU_PTE_PRT && prt_fini_needed) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 1a814fbffff8..6b06a214f05f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -286,6 +286,7 @@ struct amdgpu_vm {
/* Last finished delayed update */
atomic64_t tlb_seq;
+ struct dma_fence *last_tlb_flush;
/* Last unlocked submission to the scheduler entities */
struct dma_fence *last_unlocked;
