torvalds/linux
torvalds/linux
2
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
Code

drm/amdgpu: make compute timeouts consistent

Browse Source 
For kernel compute queues, align the timeout with
other kernel queues (10 sec).  This had previously
been set higher for OpenCL when it used kernel
queues, but now OpenCL uses KFD user queues which
don't have a timeout limitation. This also aligns
with SR-IOV which already used a shorter timeout.

Additionally the longer timeout negatively impacts
the user experience with kernel queues for interactive
applications.

Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher 2025-06-18 09:49:05 -04:00
parent 991f2e0c63
commit ec8fbb44b5
2 changed files with 7 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
View File

@ -4220,18 +4220,10 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
int ret = 0;
/*
* By default timeout for non compute jobs is 10000
* and 60000 for compute jobs.
* In SR-IOV or passthrough mode, timeout for compute
* jobs are 60000 by default.
* By default timeout for jobs is 10 sec
*/
adev->gfx_timeout = msecs_to_jiffies(10000);
adev->compute_timeout = adev->gfx_timeout = msecs_to_jiffies(10000);
adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
if (amdgpu_sriov_vf(adev))
adev->compute_timeout = amdgpu_sriov_is_pp_one_vf(adev) ?
msecs_to_jiffies(60000) : msecs_to_jiffies(10000);
else
adev->compute_timeout = msecs_to_jiffies(60000);
if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
while ((timeout_setting = strsep(&input, ",")) &&

10
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
View File

@ -362,12 +362,12 @@ module_param_named(svm_default_granularity, amdgpu_svm_default_granularity, uint
* The second one is for Compute. The third and fourth ones are
* for SDMA and Video.
*
* By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
* jobs is 10000. The timeout for compute is 60000.
* By default(with no lockup_timeout settings), the timeout for all jobs is 10000.
*/
MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and 60000 for compute jobs; "
"for passthrough or sriov, 10000 for all jobs. 0: keep default value. negative: infinity timeout), format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
"for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
MODULE_PARM_DESC(lockup_timeout,
"GPU lockup timeout in ms (default: 10000 for all jobs. "
"0: keep default value. negative: infinity timeout), format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
"for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
module_param_string(lockup_timeout, amdgpu_lockup_timeout, sizeof(amdgpu_lockup_timeout), 0444);
/**