[PATCH 26/29] drm/amdkfd: add debug query exception info operation

[Jonathan Kim]

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 at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c |   7 ++
 drivers/gpu/drm/amd/amdkfd/kfd_debug.c   | 120 +++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_debug.h   |   6 ++
 3 files changed, 133 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 042cb0f6426b..1017bf076e1f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2922,6 +2922,13 @@ 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 3b15159421cc..8590f7b21aa7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
@@ -742,6 +742,126 @@ 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 c64ffd3efc46..58a5f14d1258 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,
-- 
2.25.1