drm/amdkfd: add debug query exception info operation

Allow the debugger to query additional info based on an exception code.
For device exceptions, it's currently only memory violation information.
For process exceptions, it's currently only runtime information.
Queue exception only report the queue exception status.

The debugger has the option of clearing the target exception on query.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

3 files changed, 133 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 498859259b55..b7ee79b5220a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -3045,6 +3045,13 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v
 				&args->query_debug_event.exception_mask);
 		break;
 	case KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO:
+		r = kfd_dbg_trap_query_exception_info(target,
+				args->query_exception_info.source_id,
+				args->query_exception_info.exception_code,
+				args->query_exception_info.clear_exception,
+				(void __user *)args->query_exception_info.info_ptr,
+				&args->query_exception_info.info_size);
+		break;
 	case KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT:
 	case KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT:
 		pr_warn("Debug op %i not supported yet\n", args->op);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
index e9530e682e85..24e2b285448a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
@@ -890,6 +890,126 @@ int kfd_dbg_trap_set_wave_launch_mode(struct kfd_process *target,
 	return r;
 }
 
+int kfd_dbg_trap_query_exception_info(struct kfd_process *target,
+		uint32_t source_id,
+		uint32_t exception_code,
+		bool clear_exception,
+		void __user *info,
+		uint32_t *info_size)
+{
+	bool found = false;
+	int r = 0;
+	uint32_t copy_size, actual_info_size = 0;
+	uint64_t *exception_status_ptr = NULL;
+
+	if (!target)
+		return -EINVAL;
+
+	if (!info || !info_size)
+		return -EINVAL;
+
+	mutex_lock(&target->event_mutex);
+
+	if (KFD_DBG_EC_TYPE_IS_QUEUE(exception_code)) {
+		/* Per queue exceptions */
+		struct queue *queue = NULL;
+		int i;
+
+		for (i = 0; i < target->n_pdds; i++) {
+			struct kfd_process_device *pdd = target->pdds[i];
+			struct qcm_process_device *qpd = &pdd->qpd;
+
+			list_for_each_entry(queue, &qpd->queues_list, list) {
+				if (!found && queue->properties.queue_id == source_id) {
+					found = true;
+					break;
+				}
+			}
+			if (found)
+				break;
+		}
+
+		if (!found) {
+			r = -EINVAL;
+			goto out;
+		}
+
+		if (!(queue->properties.exception_status & KFD_EC_MASK(exception_code))) {
+			r = -ENODATA;
+			goto out;
+		}
+		exception_status_ptr = &queue->properties.exception_status;
+	} else if (KFD_DBG_EC_TYPE_IS_DEVICE(exception_code)) {
+		/* Per device exceptions */
+		struct kfd_process_device *pdd = NULL;
+		int i;
+
+		for (i = 0; i < target->n_pdds; i++) {
+			pdd = target->pdds[i];
+			if (pdd->dev->id == source_id) {
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			r = -EINVAL;
+			goto out;
+		}
+
+		if (!(pdd->exception_status & KFD_EC_MASK(exception_code))) {
+			r = -ENODATA;
+			goto out;
+		}
+
+		if (exception_code == EC_DEVICE_MEMORY_VIOLATION) {
+			copy_size = min((size_t)(*info_size), pdd->vm_fault_exc_data_size);
+
+			if (copy_to_user(info, pdd->vm_fault_exc_data, copy_size)) {
+				r = -EFAULT;
+				goto out;
+			}
+			actual_info_size = pdd->vm_fault_exc_data_size;
+			if (clear_exception) {
+				kfree(pdd->vm_fault_exc_data);
+				pdd->vm_fault_exc_data = NULL;
+				pdd->vm_fault_exc_data_size = 0;
+			}
+		}
+		exception_status_ptr = &pdd->exception_status;
+	} else if (KFD_DBG_EC_TYPE_IS_PROCESS(exception_code)) {
+		/* Per process exceptions */
+		if (!(target->exception_status & KFD_EC_MASK(exception_code))) {
+			r = -ENODATA;
+			goto out;
+		}
+
+		if (exception_code == EC_PROCESS_RUNTIME) {
+			copy_size = min((size_t)(*info_size), sizeof(target->runtime_info));
+
+			if (copy_to_user(info, (void *)&target->runtime_info, copy_size)) {
+				r = -EFAULT;
+				goto out;
+			}
+
+			actual_info_size = sizeof(target->runtime_info);
+		}
+
+		exception_status_ptr = &target->exception_status;
+	} else {
+		pr_debug("Bad exception type [%i]\n", exception_code);
+		r = -EINVAL;
+		goto out;
+	}
+
+	*info_size = actual_info_size;
+	if (clear_exception)
+		*exception_status_ptr &= ~KFD_EC_MASK(exception_code);
+out:
+	mutex_unlock(&target->event_mutex);
+	return r;
+}
+
 void kfd_dbg_set_enabled_debug_exception_mask(struct kfd_process *target,
 					uint64_t exception_set_mask)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
index e78f954c0684..234e2ccafa87 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
@@ -63,6 +63,12 @@ int kfd_dbg_trap_set_dev_address_watch(struct kfd_process_device *pdd,
 					uint32_t *watch_id,
 					uint32_t watch_mode);
 int kfd_dbg_trap_set_flags(struct kfd_process *target, uint32_t *flags);
+int kfd_dbg_trap_query_exception_info(struct kfd_process *target,
+		uint32_t source_id,
+		uint32_t exception_code,
+		bool clear_exception,
+		void __user *info,
+		uint32_t *info_size);
 int kfd_dbg_send_exception_to_runtime(struct kfd_process *p,
 					unsigned int dev_id,
 					unsigned int queue_id,