Commit c2d2588c authored by Jonathan Kim's avatar Jonathan Kim Committed by Alex Deucher
Browse files

drm/amdkfd: add send exception operation 



Add a debug operation that allows the debugger to send an exception
directly to runtime through a payload address.

For memory violations, normal vmfault signals will be applied to
notify runtime instead after passing in the saved exception data
when a memory violation was raised to the debugger.

For runtime exceptions, this will unblock the runtime enable
function which will be explained and implemented in a follow up
patch.

Signed-off-by: default avatarJonathan Kim <jonathan.kim@amd.com>
Reviewed-by: default avatarFelix Kuehling <felix.kuehling@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 44b87bb0

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

+2 −2
Original line number Diff line number Diff line
@@ -118,9 +118,9 @@ static void cik_event_interrupt_wq(struct kfd_node *dev, 
			return;



		if (info.vmid == vmid)

			kfd_signal_vm_fault_event(dev, pasid, &info);

			kfd_signal_vm_fault_event(dev, pasid, &info, NULL);

		else

			kfd_signal_vm_fault_event(dev, pasid, NULL);

			kfd_signal_vm_fault_event(dev, pasid, NULL, NULL);

	}

}

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

+5 −0
Original line number Diff line number Diff line
@@ -2833,6 +2833,11 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v 
		r = kfd_dbg_trap_disable(target);

		break;

	case KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT:

		r = kfd_dbg_send_exception_to_runtime(target,

				args->send_runtime_event.gpu_id,

				args->send_runtime_event.queue_id,

				args->send_runtime_event.exception_mask);

		break;

	case KFD_IOC_DBG_TRAP_SET_EXCEPTIONS_ENABLED:

	case KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE:

	case KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE:

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

+43 −0
Original line number Diff line number Diff line
@@ -125,6 +125,49 @@ bool kfd_dbg_ev_raise(uint64_t event_mask, 
	return is_subscribed;

}



int kfd_dbg_send_exception_to_runtime(struct kfd_process *p,

					unsigned int dev_id,

					unsigned int queue_id,

					uint64_t error_reason)

{

	if (error_reason & KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION)) {

		struct kfd_process_device *pdd = NULL;

		struct kfd_hsa_memory_exception_data *data;

		int i;



		for (i = 0; i < p->n_pdds; i++) {

			if (p->pdds[i]->dev->id == dev_id) {

				pdd = p->pdds[i];

				break;

			}

		}



		if (!pdd)

			return -ENODEV;



		data = (struct kfd_hsa_memory_exception_data *)

						pdd->vm_fault_exc_data;



		kfd_dqm_evict_pasid(pdd->dev->dqm, p->pasid);

		kfd_signal_vm_fault_event(pdd->dev, p->pasid, NULL, data);

		error_reason &= ~KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION);

	}



	if (error_reason & (KFD_EC_MASK(EC_PROCESS_RUNTIME))) {

		/*

		 * block should only happen after the debugger receives runtime

		 * enable notice.

		 */

		up(&p->runtime_enable_sema);

		error_reason &= ~KFD_EC_MASK(EC_PROCESS_RUNTIME);

	}



	if (error_reason)

		return kfd_send_exception_to_runtime(p, queue_id, error_reason);



	return 0;

}



static int kfd_dbg_set_queue_workaround(struct queue *q, bool enable)

{

	struct mqd_update_info minfo = {0};

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

+6 −0
Original line number Diff line number Diff line
@@ -34,6 +34,12 @@ int kfd_dbg_trap_disable(struct kfd_process *target); 
int kfd_dbg_trap_enable(struct kfd_process *target, uint32_t fd,

			void __user *runtime_info,

			uint32_t *runtime_info_size);



int kfd_dbg_send_exception_to_runtime(struct kfd_process *p,

					unsigned int dev_id,

					unsigned int queue_id,

					uint64_t error_reason);



static inline bool kfd_dbg_is_per_vmid_supported(struct kfd_node *dev)

{

	return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||

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

+2 −1
Original line number Diff line number Diff line
@@ -1222,7 +1222,8 @@ void kfd_signal_hw_exception_event(u32 pasid) 
}



void kfd_signal_vm_fault_event(struct kfd_node *dev, u32 pasid,

			       struct kfd_vm_fault_info *info)

				struct kfd_vm_fault_info *info,

				struct kfd_hsa_memory_exception_data *data)

{

	struct kfd_event *ev;

	uint32_t id;