diff options
author | Hawking Zhang <Hawking.Zhang@amd.com> | 2025-02-11 19:54:05 +0800 |
---|---|---|
committer | Alex Deucher <alexander.deucher@amd.com> | 2025-02-17 14:09:29 -0500 |
commit | 652e09023029b79b4490e824d4ebe8eaea92cc8e (patch) | |
tree | 8a32f43e4aa90a1a0c1cd1e4c5671c1ff9a96723 /drivers | |
parent | e7a477735f1771b9a9346a5fbd09d7ff0641723a (diff) |
drm/amdgpu: Generate cper records
Encode the error information in CPER format and commit
to the cper ring
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Yang Wang <keivnyang.wang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c index ed1c20bd8114..c0da9096a7fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c @@ -384,6 +384,36 @@ static bool aca_bank_should_update(struct amdgpu_device *adev, enum aca_smu_type return ret; } +static void aca_banks_generate_cper(struct amdgpu_device *adev, + enum aca_smu_type type, + struct aca_banks *banks, + int count) +{ + struct aca_bank_node *node; + struct aca_bank *bank; + + if (!adev || !banks || !count) { + dev_warn(adev->dev, "fail to generate cper records\n"); + return; + } + + /* UEs must be encoded into separate CPER entries */ + if (type == ACA_SMU_TYPE_UE) { + list_for_each_entry(node, &banks->list, node) { + bank = &node->bank; + if (amdgpu_cper_generate_ue_record(adev, bank)) + dev_warn(adev->dev, "fail to generate ue cper records\n"); + } + } else { + /* + * SMU_TYPE_CE banks are combined into 1 CPER entries, + * they could be CEs or DEs or both + */ + if (amdgpu_cper_generate_ce_records(adev, banks, count)) + dev_warn(adev->dev, "fail to generate ce cper records\n"); + } +} + static int aca_banks_update(struct amdgpu_device *adev, enum aca_smu_type type, bank_handler_t handler, struct ras_query_context *qctx, void *data) { @@ -421,6 +451,8 @@ static int aca_banks_update(struct amdgpu_device *adev, enum aca_smu_type type, if (ret) goto err_release_banks; + aca_banks_generate_cper(adev, type, &banks, count); + err_release_banks: aca_banks_release(&banks); |