[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
re-generation token.
v2: Check vm->generation instead of calling drm_sched_entity_error
in amdgpu_vm_validate.
Signed-off-by: ZhenGuo Yin <zhenguo.yin@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 3abfa66d72a2..9e2f84c166e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -434,7 +434,7 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
if (!vm)
return result;
- result += vm->generation;
+ result += (vm->generation & 0xFFFFFFFF);
/* Add one if the page tables will be re-generated on next CS */
if (drm_sched_entity_error(&vm->delayed))
++result;
@@ -467,9 +467,12 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
struct amdgpu_bo *shadow;
struct amdgpu_bo *bo;
int r;
+ uint32_t vram_lost_counter = atomic_read(&adev->vram_lost_counter);
- if (drm_sched_entity_error(&vm->delayed)) {
- ++vm->generation;
+ if (vm->generation != amdgpu_vm_generation(adev, vm)) {
+ if (drm_sched_entity_error(&vm->delayed))
+ ++vm->generation;
+ vm->generation = (u64)vram_lost_counter << 32 | (vm->generation & 0xFFFFFFFF);
amdgpu_vm_bo_reset_state_machine(vm);
amdgpu_vm_fini_entities(vm);
r = amdgpu_vm_init_entities(adev, vm);
@@ -2439,7 +2442,7 @@ 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 = (u64)atomic_read(&adev->vram_lost_counter) << 32;
mutex_init(&vm->eviction_lock);
vm->evicting = false;
--
2.35.1
