drm/amdgpu: Modify the count method of defer error

The number of newly added de counts and the number of newly added error addresses remain consistent Signed-off-by: Ce Sun <cesun102@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
mariux64 · May 13, 2025 · 533aa8b · 533aa8b
1 parent 085c997
commit 533aa8b
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 2 deletions.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -529,6 +529,7 @@ int amdgpu_umc_lookup_bad_pages_in_a_row(struct amdgpu_device *adev,
 		pfns[i] = err_data.err_addr[i].retired_page;
 	}
 	ret = i;
+	adev->umc.err_addr_cnt = err_data.err_addr_cnt;
 
 out:
 	kfree(err_data.err_addr);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -145,6 +145,8 @@ struct amdgpu_umc {
 	unsigned long active_mask;
 
 	struct amdgpu_umc_flip_bits flip_bits;
+
+	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
@@ -482,8 +482,12 @@ 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);
 }