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

1 files changed, 43 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
index dccb27fc764b..61098975bb0e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
@@ -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};