drm/amdgpu: reset vm state machine after gpu reset(vram lost)
commit 5659b0c93a1ea02c662a030b322093203f299185 upstream. [Why] Page table of compute VM in the VRAM will lost after gpu reset. VRAM won't be restored since compute VM has no shadows. [How] Use higher 32-bit of vm->generation to record a vram_lost_counter. Reset the VM state machine when vm->genertaion is not equal to the new generation token. v2: Check vm->generation instead of calling drm_sched_entity_error in amdgpu_vm_validate. v3: Use new generation token instead of vram_lost_counter for check. Signed-off-by: ZhenGuo Yin <zhenguo.yin@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org (cherry picked from commit 47c0388b0589cb481c294dcb857d25a214c46eb3) Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
parent
e290feb8b7
commit
3237905352
|
@ -418,7 +418,7 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
|
|||
if (!vm)
|
||||
return result;
|
||||
|
||||
result += vm->generation;
|
||||
result += lower_32_bits(vm->generation);
|
||||
/* Add one if the page tables will be re-generated on next CS */
|
||||
if (drm_sched_entity_error(&vm->delayed))
|
||||
++result;
|
||||
|
@ -443,13 +443,14 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
|
|||
int (*validate)(void *p, struct amdgpu_bo *bo),
|
||||
void *param)
|
||||
{
|
||||
uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm);
|
||||
struct amdgpu_vm_bo_base *bo_base;
|
||||
struct amdgpu_bo *shadow;
|
||||
struct amdgpu_bo *bo;
|
||||
int r;
|
||||
|
||||
if (drm_sched_entity_error(&vm->delayed)) {
|
||||
++vm->generation;
|
||||
if (vm->generation != new_vm_generation) {
|
||||
vm->generation = new_vm_generation;
|
||||
amdgpu_vm_bo_reset_state_machine(vm);
|
||||
amdgpu_vm_fini_entities(vm);
|
||||
r = amdgpu_vm_init_entities(adev, vm);
|
||||
|
@ -2192,7 +2193,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
|
|||
vm->last_update = dma_fence_get_stub();
|
||||
vm->last_unlocked = dma_fence_get_stub();
|
||||
vm->last_tlb_flush = dma_fence_get_stub();
|
||||
vm->generation = 0;
|
||||
vm->generation = amdgpu_vm_generation(adev, NULL);
|
||||
|
||||
mutex_init(&vm->eviction_lock);
|
||||
vm->evicting = false;
|
||||
|
|
Loading…
Reference in New Issue