diff options
| author | Shaoyun Liu <Shaoyun.Liu@amd.com> | 2018-07-11 22:32:56 -0400 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2018-07-11 22:32:56 -0400 |
| commit | e42051d2133b7912db99bd3a307c9219a88fe7c2 (patch) | |
| tree | 2c5a8c8149af2b94af15aa1316ea43d6b98da349 /drivers/gpu/drm/amd/amdkfd/kfd_events.c | |
| parent | 5c6dd71e597f33d517710affe3b8d8de253bc86d (diff) | |
drm/amdkfd: Implement GPU reset handlers in KFD
Lock KFD and evict existing queues on reset. Notify user mode by
signaling hw_exception events.
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_events.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_events.c | 27 |
1 files changed, 27 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index b58a0e665ebc..820133cdef83 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -1000,3 +1000,30 @@ void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, mutex_unlock(&p->event_mutex); kfd_unref_process(p); } + +void kfd_signal_reset_event(struct kfd_dev *dev) +{ + struct kfd_hsa_hw_exception_data hw_exception_data; + struct kfd_process *p; + struct kfd_event *ev; + unsigned int temp; + uint32_t id, idx; + + /* Whole gpu reset caused by GPU hang and memory is lost */ + memset(&hw_exception_data, 0, sizeof(hw_exception_data)); + hw_exception_data.gpu_id = dev->id; + hw_exception_data.memory_lost = 1; + + idx = srcu_read_lock(&kfd_processes_srcu); + hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) { + mutex_lock(&p->event_mutex); + id = KFD_FIRST_NONSIGNAL_EVENT_ID; + idr_for_each_entry_continue(&p->event_idr, ev, id) + if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) { + ev->hw_exception_data = hw_exception_data; + set_event(ev); + } + mutex_unlock(&p->event_mutex); + } + srcu_read_unlock(&kfd_processes_srcu, idx); +} |