Commit b4672c8a authored Nov 18, 2019 by Alex Sierra Committed by Alex Deucher Nov 22, 2019

amd/amdgpu: force to trigger a no-retry-fault after a retry-fault



Only for the debugger use case.

[why]
Avoid endless translation retries, after an invalid address access has
been issued to the GPU. Instead, the trap handler is forced to enter by
generating a no-retry-fault.
A s_trap instruction is inserted in the debugger case to let the wave to
enter trap handler to save context.

[how]
Intentionally using an invalid flag combination (F and P set at the same
time) to trigger a no-retry-fault, after a retry-fault happens. This is
only valid under compute context.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

parent f43ef951

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

+10 −1

Original line number	Diff line number	Diff line
		@@ -3197,11 +3197,20 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
		flags = AMDGPU_PTE_VALID \| AMDGPU_PTE_SNOOPED \|
		AMDGPU_PTE_SYSTEM;

		if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
		if (vm->is_compute_context) {
		/* Intentionally setting invalid PTE flag
		* combination to force a no-retry-fault
		*/
		flags = AMDGPU_PTE_EXECUTABLE \| AMDGPU_PDE_PTE \|
		AMDGPU_PTE_TF;
		value = 0;

		} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
		/* Redirect the access to the dummy page */
		value = adev->dummy_page_addr;
		flags \|= AMDGPU_PTE_EXECUTABLE \| AMDGPU_PTE_READABLE \|
		AMDGPU_PTE_WRITEABLE;

		} else {
		/* Let the hw retry silently on the PTE */
		value = 0;

Admin message