diff options
| author | Amber Lin <Amber.Lin@amd.com> | 2025-08-15 14:04:15 -0400 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2025-08-27 13:57:49 -0400 |
| commit | f3820e9d356132e18405cd7606e22dc87ccfa6d1 (patch) | |
| tree | 1e3acac15abdcb4d93189e449dff6664b523aa46 | |
| parent | drm/amd/pm: Update SMU v13.0.6 PPT caps initialization (diff) | |
| download | linux-f3820e9d356132e18405cd7606e22dc87ccfa6d1.tar.gz linux-f3820e9d356132e18405cd7606e22dc87ccfa6d1.zip | |
drm/amdkfd: Tie UNMAP_LATENCY to queue_preemption
When KFD asks CP to preempt queues, other than preempt CP queues, CP
also requests SDMA to preempt SDMA queues with UNMAP_LATENCY timeout.
Currently queue_preemption_timeout_ms is 9000 ms by default but can be
configured via module parameter. KFD_UNMAP_LATENCY_MS is hard coded as
4000 ms though. This patch ties KFD_UNMAP_LATENCY_MS to
queue_preemption_timeout_ms so in a slow system such as emulator, both
CP and SDMA slowness are taken into account.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 67694bcd9464..d01ef5ac0766 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -111,7 +111,14 @@ #define KFD_KERNEL_QUEUE_SIZE 2048 -#define KFD_UNMAP_LATENCY_MS (4000) +/* KFD_UNMAP_LATENCY_MS is the timeout CP waiting for SDMA preemption. One XCC + * can be associated to 2 SDMA engines. queue_preemption_timeout_ms is the time + * driver waiting for CP returning the UNMAP_QUEUE fence. Thus the math is + * queue_preemption_timeout_ms = sdma_preemption_time * 2 + cp workload + * The format here makes CP workload 10% of total timeout + */ +#define KFD_UNMAP_LATENCY_MS \ + ((queue_preemption_timeout_ms - queue_preemption_timeout_ms / 10) >> 1) #define KFD_MAX_SDMA_QUEUES 128 |