On 5/6/2025 7:30 AM, Ce Sun wrote:
The number of newly added de counts and the number of
newly added error addresses remain consistent
You need to make sure you include a Signed-off-by: tag when you submit
patches.
https://www.kernel.org/doc/html/latest/process/submitting-patches.html#developer-s-certificate-of-origin-1-1
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h | 1 +
drivers/gpu/drm/amd/amdgpu/umc_v12_0.c | 11 +++++++++--
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index 857693bcd8d4..52fb71c4ce9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -130,6 +130,7 @@ struct amdgpu_umc {
/* active mask for umc node instance */
unsigned long active_mask;
+ unsigned long err_addr_cnt;
};
int amdgpu_umc_ras_sw_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index 0e404c074975..eb3f99dbbcd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -262,6 +262,9 @@ static int umc_v12_0_convert_error_address(struct
amdgpu_device *adev,
soc_pa, channel_index, umc_inst);
}
+ if (err_data)
+ adev->umc.err_addr_cnt = err_data->err_addr_cnt;
+
out:
return ret;
}
@@ -428,8 +431,12 @@ static int umc_v12_0_aca_bank_parser(struct aca_handle
*handle, struct aca_bank
bank->regs[ACA_REG_IDX_ADDR]);
ext_error_code = ACA_REG__STATUS__ERRORCODEEXT(status);
- count = ext_error_code == 0 ?
- ACA_REG__MISC0__ERRCNT(bank->regs[ACA_REG_IDX_MISC0]) : 1ULL;
+ if (umc_v12_0_is_deferred_error(adev, status))
+ count = ext_error_code == 0 ?
+ adev->umc.err_addr_cnt / adev->umc.retire_unit : 1ULL;
+ else
+ count = ext_error_code == 0 ?
+ ACA_REG__MISC0__ERRCNT(bank->regs[ACA_REG_IDX_MISC0]) :
1ULL;
return aca_error_cache_log_bank_error(handle, &info, err_type, count);
}
