From 53dd920c1f471a5763c660a7b94fe0aaf746d357 Mon Sep 17 00:00:00 2001 From: Asad Kamal Date: Thu, 5 Oct 2023 15:40:42 +0800 Subject: drm/amdgpu : Add hive ras recovery check If one of the devices in the hive detects a fatal error, need to send ras recovery reset message to PMFW of all devices in the hive. For that add a flag in hive to indicate that it's undergoing ras recovery Signed-off-by: Asad Kamal Reviewed-by: Hawking Zhang Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 973073e07b2a..c7f8dcb3b4d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2140,9 +2140,11 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) struct amdgpu_device *remote_adev = NULL; struct amdgpu_device *adev = ras->adev; struct list_head device_list, *device_list_handle = NULL; + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); + if (hive) + atomic_set(&hive->ras_recovery, 1); if (!ras->disable_ras_err_cnt_harvest) { - struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); /* Build list of devices to query RAS related errors */ if (hive && adev->gmc.xgmi.num_physical_nodes > 1) { @@ -2159,7 +2161,6 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) amdgpu_ras_log_on_err_counter(remote_adev); } - amdgpu_put_xgmi_hive(hive); } if (amdgpu_device_should_recover_gpu(ras->adev)) { @@ -2194,6 +2195,10 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context); } atomic_set(&ras->in_recovery, 0); + if (hive) { + atomic_set(&hive->ras_recovery, 0); + amdgpu_put_xgmi_hive(hive); + } } /* alloc/realloc bps array */ -- cgit v1.2.3-70-g09d2