diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 9e0f57cfa3bf..5fa156e89a73 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -476,15 +476,27 @@ int kfd_criu_checkpoint_events(struct kfd_process *p, int ret = 0; struct kfd_event *ev; uint32_t ev_id; + uint32_t num_events; - uint32_t num_events = kfd_get_num_events(p); + /* Serialize the count and the walk below against concurrent event + * create/destroy. Those paths take only p->event_mutex, not the + * p->mutex held by the CRIU checkpoint caller, so without this the + * event_idr can grow between kfd_get_num_events() and the loop and the + * walk writes past the ev_privs allocation. + */ + mutex_lock(&p->event_mutex); - if (!num_events) + num_events = kfd_get_num_events(p); + if (!num_events) { + mutex_unlock(&p->event_mutex); return 0; + } ev_privs = kvzalloc(num_events * sizeof(*ev_privs), GFP_KERNEL); - if (!ev_privs) + if (!ev_privs) { + mutex_unlock(&p->event_mutex); return -ENOMEM; + } idr_for_each_entry(&p->event_idr, ev, ev_id) { @@ -525,6 +537,8 @@ int kfd_criu_checkpoint_events(struct kfd_process *p, i++; } + mutex_unlock(&p->event_mutex); + ret = copy_to_user(user_priv_data + *priv_data_offset, ev_privs, num_events * sizeof(*ev_privs)); if (ret) {