diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-11 01:59:30 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-11 01:59:30 +0300 |
commit | c0d12d769299e1e08338988c7745009e0db2a4a0 (patch) | |
tree | 196e23330996b4094cd2f1b1c4aaaef09db1f44a /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
parent | ac347a0655dbc7d885e217c89dddd16e2800bd58 (diff) | |
parent | 03df0fc007ca4713fa1e716329af556f981807e4 (diff) | |
download | linux-c0d12d769299e1e08338988c7745009e0db2a4a0.tar.xz |
Merge tag 'drm-next-2023-11-10' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Daniel Vetter:
"Dave's VPN to the big machine died, so it's on me to do fixes pr this
and next week while everyone else is at plumbers.
- big pile of amd fixes, but mostly for hw support newly added in 6.7
- i915 fixes, mostly minor things
- qxl memory leak fix
- vc4 uaf fix in mock helpers
- syncobj fix for DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE"
* tag 'drm-next-2023-11-10' of git://anongit.freedesktop.org/drm/drm: (78 commits)
drm/amdgpu: fix error handling in amdgpu_vm_init
drm/amdgpu: Fix possible null pointer dereference
drm/amdgpu: move UVD and VCE sched entity init after sched init
drm/amdgpu: move kfd_resume before the ip late init
drm/amd: Explicitly check for GFXOFF to be enabled for s0ix
drm/amdgpu: Change WREG32_RLC to WREG32_SOC15_RLC where inst != 0 (v2)
drm/amdgpu: Use correct KIQ MEC engine for gfx9.4.3 (v5)
drm/amdgpu: add smu v13.0.6 pcs xgmi ras error query support
drm/amdgpu: fix software pci_unplug on some chips
drm/amd/display: remove duplicated argument
drm/amdgpu: correct mca debugfs dump reg list
drm/amdgpu: correct acclerator check architecutre dump
drm/amdgpu: add pcs xgmi v6.4.0 ras support
drm/amdgpu: Change extended-scope MTYPE on GC 9.4.3
drm/amdgpu: disable smu v13.0.6 mca debug mode by default
drm/amdgpu: Support multiple error query modes
drm/amdgpu: refine smu v13.0.6 mca dump driver
drm/amdgpu: Do not program PF-only regs in hdp_v4_0.c under SRIOV (v2)
drm/amdgpu: Skip PCTL0_MMHUB_DEEPSLEEP_IB write in jpegv4.0.3 under SRIOV
drm: amd: Resolve Sphinx unexpected indentation warning
...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 102 |
1 files changed, 76 insertions, 26 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index b7fe5951b166..84e5987b14e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1165,13 +1165,53 @@ static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, s } } -/* query/inject/cure begin */ -int amdgpu_ras_query_error_status(struct amdgpu_device *adev, - struct ras_query_if *info) +static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev, + struct ras_query_if *info, + struct ras_err_data *err_data, + unsigned int error_query_mode) { + enum amdgpu_ras_block blk = info ? info->head.block : AMDGPU_RAS_BLOCK_COUNT; struct amdgpu_ras_block_object *block_obj = NULL; + + if (error_query_mode == AMDGPU_RAS_INVALID_ERROR_QUERY) + return -EINVAL; + + if (error_query_mode == AMDGPU_RAS_DIRECT_ERROR_QUERY) { + if (info->head.block == AMDGPU_RAS_BLOCK__UMC) { + amdgpu_ras_get_ecc_info(adev, err_data); + } else { + block_obj = amdgpu_ras_get_ras_block(adev, info->head.block, 0); + if (!block_obj || !block_obj->hw_ops) { + dev_dbg_once(adev->dev, "%s doesn't config RAS function\n", + get_ras_block_str(&info->head)); + return -EINVAL; + } + + if (block_obj->hw_ops->query_ras_error_count) + block_obj->hw_ops->query_ras_error_count(adev, &err_data); + + if ((info->head.block == AMDGPU_RAS_BLOCK__SDMA) || + (info->head.block == AMDGPU_RAS_BLOCK__GFX) || + (info->head.block == AMDGPU_RAS_BLOCK__MMHUB)) { + if (block_obj->hw_ops->query_ras_error_status) + block_obj->hw_ops->query_ras_error_status(adev); + } + } + } else { + /* FIXME: add code to check return value later */ + amdgpu_mca_smu_log_ras_error(adev, blk, AMDGPU_MCA_ERROR_TYPE_UE, err_data); + amdgpu_mca_smu_log_ras_error(adev, blk, AMDGPU_MCA_ERROR_TYPE_CE, err_data); + } + + return 0; +} + +/* query/inject/cure begin */ +int amdgpu_ras_query_error_status(struct amdgpu_device *adev, struct ras_query_if *info) +{ struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); struct ras_err_data err_data; + unsigned int error_query_mode; int ret; if (!obj) @@ -1181,27 +1221,14 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, if (ret) return ret; - if (info->head.block == AMDGPU_RAS_BLOCK__UMC) { - amdgpu_ras_get_ecc_info(adev, &err_data); - } else { - block_obj = amdgpu_ras_get_ras_block(adev, info->head.block, 0); - if (!block_obj || !block_obj->hw_ops) { - dev_dbg_once(adev->dev, "%s doesn't config RAS function\n", - get_ras_block_str(&info->head)); - ret = -EINVAL; - goto out_fini_err_data; - } - - if (block_obj->hw_ops->query_ras_error_count) - block_obj->hw_ops->query_ras_error_count(adev, &err_data); + if (!amdgpu_ras_get_error_query_mode(adev, &error_query_mode)) + return -EINVAL; - if ((info->head.block == AMDGPU_RAS_BLOCK__SDMA) || - (info->head.block == AMDGPU_RAS_BLOCK__GFX) || - (info->head.block == AMDGPU_RAS_BLOCK__MMHUB)) { - if (block_obj->hw_ops->query_ras_error_status) - block_obj->hw_ops->query_ras_error_status(adev); - } - } + ret = amdgpu_ras_query_error_status_helper(adev, info, + &err_data, + error_query_mode); + if (ret) + goto out_fini_err_data; amdgpu_rasmgr_error_data_statistic_update(obj, &err_data); @@ -1537,7 +1564,8 @@ static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - sysfs_remove_file_from_group(&adev->dev->kobj, + if (adev->dev->kobj.sd) + sysfs_remove_file_from_group(&adev->dev->kobj, &con->badpages_attr.attr, RAS_FS_NAME); } @@ -1556,7 +1584,8 @@ static int amdgpu_ras_sysfs_remove_dev_attr_node(struct amdgpu_device *adev) .attrs = attrs, }; - sysfs_remove_group(&adev->dev->kobj, &group); + if (adev->dev->kobj.sd) + sysfs_remove_group(&adev->dev->kobj, &group); return 0; } @@ -1603,7 +1632,8 @@ int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev, if (!obj || !obj->attr_inuse) return -EINVAL; - sysfs_remove_file_from_group(&adev->dev->kobj, + if (adev->dev->kobj.sd) + sysfs_remove_file_from_group(&adev->dev->kobj, &obj->sysfs_attr.attr, RAS_FS_NAME); obj->attr_inuse = 0; @@ -3397,6 +3427,26 @@ bool amdgpu_ras_get_mca_debug_mode(struct amdgpu_device *adev) return true; } +bool amdgpu_ras_get_error_query_mode(struct amdgpu_device *adev, + unsigned int *error_query_mode) +{ + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs; + + if (!con) { + *error_query_mode = AMDGPU_RAS_INVALID_ERROR_QUERY; + return false; + } + + if (mca_funcs && mca_funcs->mca_set_debug_mode) + *error_query_mode = + (con->is_mca_debug_mode) ? AMDGPU_RAS_DIRECT_ERROR_QUERY : AMDGPU_RAS_FIRMWARE_ERROR_QUERY; + else + *error_query_mode = AMDGPU_RAS_DIRECT_ERROR_QUERY; + + return true; +} + /* Register each ip ras block into amdgpu ras */ int amdgpu_ras_register_ras_block(struct amdgpu_device *adev, struct amdgpu_ras_block_object *ras_block_obj) |