Commit e2b1f9f5 authored by Dennis Li's avatar Dennis Li Committed by Alex Deucher
Browse files

drm/amdkfd: refine the poison data consumption handling 



The user applications maybe register the KFD_EVENT_TYPE_HW_EXCEPTION and
KFD_EVENT_TYPE_MEMORY events, driver could notify them when poison data
consumed. Beside that, some applications maybe register SIGBUS signal
hander. These applications will handle poison data by themselves, exit
or re-create context to re-dispatch works.

Signed-off-by: default avatarDennis Li <Dennis.Li@amd.com>
Reviewed-by: default avatarFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 2bb5b5f6

drivers/gpu/drm/amd/amdkfd/kfd_events.c

+39 −0
Original line number Diff line number Diff line
@@ -1050,3 +1050,42 @@ void kfd_signal_reset_event(struct kfd_dev *dev) 
	}

	srcu_read_unlock(&kfd_processes_srcu, idx);

}



void kfd_signal_poison_consumed_event(struct kfd_dev *dev, u32 pasid)

{

	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);

	struct kfd_hsa_memory_exception_data memory_exception_data;

	struct kfd_hsa_hw_exception_data hw_exception_data;

	struct kfd_event *ev;

	uint32_t id = KFD_FIRST_NONSIGNAL_EVENT_ID;



	if (!p)

		return; /* Presumably process exited. */



	memset(&hw_exception_data, 0, sizeof(hw_exception_data));

	hw_exception_data.gpu_id = dev->id;

	hw_exception_data.memory_lost = 1;

	hw_exception_data.reset_cause = KFD_HW_EXCEPTION_ECC;



	memset(&memory_exception_data, 0, sizeof(memory_exception_data));

	memory_exception_data.ErrorType = KFD_MEM_ERR_POISON_CONSUMED;

	memory_exception_data.gpu_id = dev->id;

	memory_exception_data.failure.imprecise = true;



	mutex_lock(&p->event_mutex);

	idr_for_each_entry_continue(&p->event_idr, ev, id) {

		if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {

			ev->hw_exception_data = hw_exception_data;

			set_event(ev);

		}



		if (ev->type == KFD_EVENT_TYPE_MEMORY) {

			ev->memory_exception_data = memory_exception_data;

			set_event(ev);

		}

	}

	mutex_unlock(&p->event_mutex);



	/* user application will handle SIGBUS signal */

	send_sig(SIGBUS, p->lead_thread, 0);

}

drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c

+1 −1
Original line number Diff line number Diff line
@@ -230,7 +230,7 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev, 
					sq_intr_err);

				if (sq_intr_err != SQ_INTERRUPT_ERROR_TYPE_ILLEGAL_INST &&

					sq_intr_err != SQ_INTERRUPT_ERROR_TYPE_MEMVIOL) {

					kfd_signal_hw_exception_event(pasid);

					kfd_signal_poison_consumed_event(dev, pasid);

					amdgpu_amdkfd_gpu_reset(dev->kgd);

					return;

				}

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

+2 −0
Original line number Diff line number Diff line
@@ -1144,6 +1144,8 @@ void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid, 


void kfd_signal_reset_event(struct kfd_dev *dev);



void kfd_signal_poison_consumed_event(struct kfd_dev *dev, u32 pasid);



void kfd_flush_tlb(struct kfd_process_device *pdd);



int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);