kernel/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c, branch linux-4.17.y

drm/amdkfd: Add dGPU support to kernel_queue_init

2018-01-04T22:17:46Z

Recognize dGPU ASIC families. Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay

drm/amdkfd: Hardware DWORD size is 4 bytes

2017-11-06T19:52:27Z

Don't use sizeof(uint32_t) or similar types for hardware or firmware DWORD size. The hardware and firmware don't care about Linux types. Signed-off-by: Felix Kuehling Reviewed-by: Alex Deucher Signed-off-by: Oded Gabbay

drm/amdkfd: Reuse CHIP_* from amdgpu v2

2017-09-20T22:10:19Z

There are already CHIP_* definitions under amd_shared.h file on amdgpu side, so KFD should reuse them rather than defining new ones. Using enum for asic type requires default cases on switch statements to prevent compiler warnings. WARN on unsupported ASICs. It should never get there because KFD should not be initialized on unsupported devices. v2: Replace BUG() with WARN and error return Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Signed-off-by: Oded Gabbay

drm/amdkfd: Adjust dequeue latencies and timeouts

2017-09-20T22:10:16Z

Adjust latencies and timeouts for dequeueing with HWS and consolidate them in one place. Make them longer to allow long running waves to complete without causing a timeout. The timeout is twice as long as the latency plus some buffer to make sure we don't detect a timeout prematurely. Change timeouts for dequeueing HQDs without HWS. KFD_UNMAP_LATENCY is more consistent with what the HWS does for user queues. Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay

drm/amdkfd: Fix kernel-queue wrapping bugs

2017-09-20T22:10:21Z

Avoid intermediate negative numbers when doing calculations with a mix of signed and unsigned variables where implicit conversions can lead to unexpected results. When kernel queue buffer wraps around to 0, we need to check that rptr won't be overwritten by the new packet. Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Signed-off-by: Oded Gabbay

drm/amdkfd: Fix incorrect destroy_mqd parameter

2017-09-20T22:10:17Z

When uninitializing a kernel queue. Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay

drm/amdkfd: pass queue's mqd when destroying mqd

2017-09-02T12:00:25Z

In VI, the destroy mqd function needs to inquire fields present in the mqd structure. That's why we need to pass it to that function instead of NULL. Signed-off-by: Oded Gabbay

drm/amd: Update MEC HQD loading code for KFD

2017-08-16T03:00:17Z

Various bug fixes and improvements that accumulated over the last two years. Signed-off-by: Felix Kuehling Acked-by: Oded Gabbay Signed-off-by: Oded Gabbay

drm/amdkfd: Handle remaining BUG_ONs more gracefully v2

2017-08-16T03:00:12Z

In most cases, BUG_ONs can be replaced with WARN_ON with an error return. In some void functions just turn them into a WARN_ON and possibly an early exit. v2: * Cleaned up error handling in pm_send_unmap_queue * Removed redundant WARN_ON in kfd_process_destroy_delayed Signed-off-by: Felix Kuehling Signed-off-by: Oded Gabbay

drm/amdkfd: Remove BUG_ONs for NULL pointer arguments

2017-08-16T03:00:09Z

Remove BUG_ONs that check for NULL pointer arguments that are dereferenced in the same function. Dereferencing the NULL pointer will generate a BUG anyway, so the explicit check is redundant and unnecessary overhead. Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay