From 660261df61fb7fd972aae0f09b17c2b899f1e282 Mon Sep 17 00:00:00 2001 From: ganglxie Date: Wed, 2 Jul 2025 16:56:22 +0800 Subject: drm/amdgpu: refine eeprom data check add eeprom data checksum check before driver unload. reset eeprom and save correct data to eeprom when check failed Signed-off-by: ganglxie Reviewed-by: Tao Zhou Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 1c54b2e5a225..648a829559e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2512,6 +2512,7 @@ amdgpu_pci_remove(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); struct amdgpu_device *adev = drm_to_adev(dev); + amdgpu_ras_eeprom_check_and_recover(adev); amdgpu_xcp_dev_unplug(adev); amdgpu_gmc_prepare_nps_mode_change(adev); drm_dev_unplug(dev); -- cgit v1.2.3 From ec8fbb44b51ef5cf82ef09043387879276e9ba6b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 18 Jun 2025 09:49:05 -0400 Subject: drm/amdgpu: make compute timeouts consistent 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 Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 ++---------- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 10 +++++----- 2 files changed, 7 insertions(+), 15 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 45b44dec0d7f..79d0ff0bda29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -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, ",")) && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 648a829559e1..3bb9b25cd121 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -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); /** -- cgit v1.2.3