From: Zhigang Luo Date: Wed, 20 Mar 2024 14:40:27 +0000 (-0400) Subject: amd/amdgpu: improve VF recover time X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=d1999b4017d485a3168b4ba1316937c82454165a;p=linux.git amd/amdgpu: improve VF recover time 1. change AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT from 30 to 5. 2. set fatel error detected flag. Signed-off-by: Zhigang Luo Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f830024cffca7..170da4551ed52 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4994,6 +4994,7 @@ retry: r = amdgpu_virt_reset_gpu(adev); if (r) return r; + amdgpu_ras_set_fed(adev, false); amdgpu_irq_gpu_reset_resume_helper(adev); /* some sw clean up VF needs to do before recover */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 461753904dea5..54ab51a4ada77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -598,6 +598,7 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work) adev->virt.vf2pf_update_retry_cnt++; if ((adev->virt.vf2pf_update_retry_cnt >= AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT) && amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev)) { + amdgpu_ras_set_fed(adev, true); if (amdgpu_reset_domain_schedule(adev->reset_domain, &adev->virt.flr_work)) return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index a9f2f0c4f7991..642f1fd287d83 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -52,7 +52,7 @@ /* tonga/fiji use this offset */ #define mmBIF_IOV_FUNC_IDENTIFIER 0x1503 -#define AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT 30 +#define AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT 5 enum amdgpu_sriov_vf_mode { SRIOV_VF_MODE_BARE_METAL = 0,