In kernel amdgpu driver, kfd_wait_on_events is used to support user space signal event wait function. For multiple threads waiting on same event scenery, race condition could occur since some threads after checking signal condition, before calling kfd_wait_on_events, the event interrupt could be fired and wake up other thread which are sleeping on this event. Then those threads could fall into sleep without waking up again. Adding event age tracking in both kernel and user mode, will help avoiding this race condition. The changes for The user space ROCT-Thunk-Interface/ROCR-Runtime are listed below for review togehter with kernel mode changes. ROCT-Thunk-Interface: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/efdbf6cfbc026bd68ac3c35d00dacf84370eb81e https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/910108272091d1ce61dbc48bd9519731e0e9cf52 ROCR-Runtime: https://github.com/RadeonOpenCompute/ROCR-Runtime/compare/master...zhums:ROCR-Runtime:new_event_wait_review https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/e1f5bdb88eb882ac798aeca2c00ea3fbb2dba459 https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/7d26afd14107b5c2a754c1a3f415d89f3aabb503 -v2: remove unnecessay link -v3: 1. update kfd test cases (910108272091d1ce61dbc48bd9519731e0e9cf52) 2. move event age match checking into init_event_waiter 3. move last event age update into copy_signaled_event_data James Zhu (5): drm/amdkfd: add event age tracking drm/amdkfd: add event_age tracking when receiving interrupt drm/amdkfd: set activated flag true when event age unmatchs drm/amdkfd: update user space last_event_age drm/amdkfd: bump kfd ioctl minor version for event age availability drivers/gpu/drm/amd/amdkfd/kfd_events.c | 44 ++++++++++++++++++------- drivers/gpu/drm/amd/amdkfd/kfd_events.h | 1 + include/uapi/linux/kfd_ioctl.h | 13 ++++++-- 3 files changed, 44 insertions(+), 14 deletions(-) -- 2.34.1
