summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
diff options
context:
space:
mode:
authorJonathan Kim <jonathan.kim@amd.com>2022-05-09 11:10:32 -0400
committerAlex Deucher <alexander.deucher@amd.com>2023-06-09 12:36:51 -0400
commit5bc20c224bcb863571e8831cdbba23cd61b10ac3 (patch)
tree7df4a5ce30d60ce1b5c8c34f99e78319b60076f6 /drivers/gpu/drm/amd/amdkfd/kfd_debug.c
parent103d5f08ff42b666c61c350be2c3e724c1646918 (diff)
downloadlinux-5bc20c224bcb863571e8831cdbba23cd61b10ac3.tar.gz
linux-5bc20c224bcb863571e8831cdbba23cd61b10ac3.tar.bz2
linux-5bc20c224bcb863571e8831cdbba23cd61b10ac3.zip
drm/amdkfd: add debug query event operation
Allow the debugger to query a single queue, device and process exception. The KFD should also return the GPU or Queue id of the exception. The debugger also has the option of clearing exceptions after being queried. 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>
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_debug.c')
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_debug.c64
1 files changed, 64 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
index 43c3170998d3..e9530e682e85 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
@@ -27,6 +27,70 @@
#define MAX_WATCH_ADDRESSES 4
+int kfd_dbg_ev_query_debug_event(struct kfd_process *process,
+ unsigned int *queue_id,
+ unsigned int *gpu_id,
+ uint64_t exception_clear_mask,
+ uint64_t *event_status)
+{
+ struct process_queue_manager *pqm;
+ struct process_queue_node *pqn;
+ int i;
+
+ if (!(process && process->debug_trap_enabled))
+ return -ENODATA;
+
+ mutex_lock(&process->event_mutex);
+ *event_status = 0;
+ *queue_id = 0;
+ *gpu_id = 0;
+
+ /* find and report queue events */
+ pqm = &process->pqm;
+ list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
+ uint64_t tmp = process->exception_enable_mask;
+
+ if (!pqn->q)
+ continue;
+
+ tmp &= pqn->q->properties.exception_status;
+
+ if (!tmp)
+ continue;
+
+ *event_status = pqn->q->properties.exception_status;
+ *queue_id = pqn->q->properties.queue_id;
+ *gpu_id = pqn->q->device->id;
+ pqn->q->properties.exception_status &= ~exception_clear_mask;
+ goto out;
+ }
+
+ /* find and report device events */
+ for (i = 0; i < process->n_pdds; i++) {
+ struct kfd_process_device *pdd = process->pdds[i];
+ uint64_t tmp = process->exception_enable_mask
+ & pdd->exception_status;
+
+ if (!tmp)
+ continue;
+
+ *event_status = pdd->exception_status;
+ *gpu_id = pdd->dev->id;
+ pdd->exception_status &= ~exception_clear_mask;
+ goto out;
+ }
+
+ /* report process events */
+ if (process->exception_enable_mask & process->exception_status) {
+ *event_status = process->exception_status;
+ process->exception_status &= ~exception_clear_mask;
+ }
+
+out:
+ mutex_unlock(&process->event_mutex);
+ return *event_status ? 0 : -EAGAIN;
+}
+
void debug_event_write_work_handler(struct work_struct *work)
{
struct kfd_process *process;