[V2] acpi: apei: call into AER handling regardless of severity
diff mbox series

Message ID 1508254115-27945-1-git-send-email-tbaicar@codeaurora.org
State New, archived
Headers show
Series
  • [V2] acpi: apei: call into AER handling regardless of severity
Related show

Commit Message

Tyler Baicar Oct. 17, 2017, 3:28 p.m. UTC
Currently the GHES code only calls into the AER driver for
recoverable type errors. This is incorrect because errors of
other severities do not get logged by the AER driver and do not
get exposed to user space via the AER trace event. So, call
into the AER driver for PCIe errors regardless of the severity.

Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
---
 drivers/acpi/apei/ghes.c | 76 +++++++++++++++++++++++++++++-------------------
 1 file changed, 46 insertions(+), 30 deletions(-)

Comments

Tyler Baicar Nov. 7, 2017, 11:21 p.m. UTC | #1
On 10/17/2017 11:28 AM, Tyler Baicar wrote:
> Currently the GHES code only calls into the AER driver for
> recoverable type errors. This is incorrect because errors of
> other severities do not get logged by the AER driver and do not
> get exposed to user space via the AER trace event. So, call
> into the AER driver for PCIe errors regardless of the severity.
>
> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Hello Boris,

Do you think this patch is good now?

Thanks,
Tyler
> ---
>   drivers/acpi/apei/ghes.c | 76 +++++++++++++++++++++++++++++-------------------
>   1 file changed, 46 insertions(+), 30 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 3c3a37b..d7801bc 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -458,6 +458,51 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
>   #endif
>   }
>   
> +/*
> + * PCIe AER errors need to be sent to the AER driver for reporting and
> + * recovery. The GHES severities map to the following AER severities and
> + * require the following handling:
> + *
> + * GHES_SEV_CORRECTABLE -> AER_CORRECTABLE
> + *	These need to be reported by the AER driver but no recovery is
> + *	necessary.
> + * GHES_SEV_RECOVERABLE -> AER_NONFATAL
> + * GHES_SEV_RECOVERABLE && CPER_SEC_RESET -> AER_FATAL
> + *	These both need to be reported and recovered from by the AER driver.
> + * GHES_SEV_PANIC does not make it to this handling since the kernel must
> + *	panic.
> + */
> +static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
> +{
> +#ifdef CONFIG_ACPI_APEI_PCIEAER
> +	struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
> +
> +	if (pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
> +	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
> +		unsigned int devfn;
> +		int aer_severity;
> +
> +		devfn = PCI_DEVFN(pcie_err->device_id.device,
> +				  pcie_err->device_id.function);
> +		aer_severity = cper_severity_to_aer(gdata->error_severity);
> +
> +		/*
> +		 * If firmware reset the component to contain
> +		 * the error, we must reinitialize it before
> +		 * use, so treat it as a fatal AER error.
> +		 */
> +		if (gdata->flags & CPER_SEC_RESET)
> +			aer_severity = AER_FATAL;
> +
> +		aer_recover_queue(pcie_err->device_id.segment,
> +				  pcie_err->device_id.bus,
> +				  devfn, aer_severity,
> +				  (struct aer_capability_regs *)
> +				  pcie_err->aer_info);
> +	}
> +#endif
> +}
> +
>   static void ghes_do_proc(struct ghes *ghes,
>   			 const struct acpi_hest_generic_status *estatus)
>   {
> @@ -485,38 +530,9 @@ static void ghes_do_proc(struct ghes *ghes,
>   			arch_apei_report_mem_error(sev, mem_err);
>   			ghes_handle_memory_failure(gdata, sev);
>   		}
> -#ifdef CONFIG_ACPI_APEI_PCIEAER
>   		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
> -			struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
> -
> -			if (sev == GHES_SEV_RECOVERABLE &&
> -			    sec_sev == GHES_SEV_RECOVERABLE &&
> -			    pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
> -			    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
> -				unsigned int devfn;
> -				int aer_severity;
> -
> -				devfn = PCI_DEVFN(pcie_err->device_id.device,
> -						  pcie_err->device_id.function);
> -				aer_severity = cper_severity_to_aer(gdata->error_severity);
> -
> -				/*
> -				 * If firmware reset the component to contain
> -				 * the error, we must reinitialize it before
> -				 * use, so treat it as a fatal AER error.
> -				 */
> -				if (gdata->flags & CPER_SEC_RESET)
> -					aer_severity = AER_FATAL;
> -
> -				aer_recover_queue(pcie_err->device_id.segment,
> -						  pcie_err->device_id.bus,
> -						  devfn, aer_severity,
> -						  (struct aer_capability_regs *)
> -						  pcie_err->aer_info);
> -			}
> -
> +			ghes_handle_aer(gdata);
>   		}
> -#endif
>   		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
>   			struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
>
Borislav Petkov Nov. 8, 2017, 10:59 a.m. UTC | #2
On Tue, Nov 07, 2017 at 06:21:31PM -0500, Tyler Baicar wrote:
> Do you think this patch is good now?

Yes, it looks ok to me but please split it in two patches:

1. Only code movement without any functional changes
2. Make the change to severity checking and add the comment.

This will make the git history clean and understandable.

Thx.

Patch
diff mbox series

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 3c3a37b..d7801bc 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -458,6 +458,51 @@  static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 #endif
 }
 
+/*
+ * PCIe AER errors need to be sent to the AER driver for reporting and
+ * recovery. The GHES severities map to the following AER severities and
+ * require the following handling:
+ *
+ * GHES_SEV_CORRECTABLE -> AER_CORRECTABLE
+ *	These need to be reported by the AER driver but no recovery is
+ *	necessary.
+ * GHES_SEV_RECOVERABLE -> AER_NONFATAL
+ * GHES_SEV_RECOVERABLE && CPER_SEC_RESET -> AER_FATAL
+ *	These both need to be reported and recovered from by the AER driver.
+ * GHES_SEV_PANIC does not make it to this handling since the kernel must
+ *	panic.
+ */
+static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
+{
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
+
+	if (pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
+	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
+		unsigned int devfn;
+		int aer_severity;
+
+		devfn = PCI_DEVFN(pcie_err->device_id.device,
+				  pcie_err->device_id.function);
+		aer_severity = cper_severity_to_aer(gdata->error_severity);
+
+		/*
+		 * If firmware reset the component to contain
+		 * the error, we must reinitialize it before
+		 * use, so treat it as a fatal AER error.
+		 */
+		if (gdata->flags & CPER_SEC_RESET)
+			aer_severity = AER_FATAL;
+
+		aer_recover_queue(pcie_err->device_id.segment,
+				  pcie_err->device_id.bus,
+				  devfn, aer_severity,
+				  (struct aer_capability_regs *)
+				  pcie_err->aer_info);
+	}
+#endif
+}
+
 static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -485,38 +530,9 @@  static void ghes_do_proc(struct ghes *ghes,
 			arch_apei_report_mem_error(sev, mem_err);
 			ghes_handle_memory_failure(gdata, sev);
 		}
-#ifdef CONFIG_ACPI_APEI_PCIEAER
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
-			struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
-
-			if (sev == GHES_SEV_RECOVERABLE &&
-			    sec_sev == GHES_SEV_RECOVERABLE &&
-			    pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
-			    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
-				unsigned int devfn;
-				int aer_severity;
-
-				devfn = PCI_DEVFN(pcie_err->device_id.device,
-						  pcie_err->device_id.function);
-				aer_severity = cper_severity_to_aer(gdata->error_severity);
-
-				/*
-				 * If firmware reset the component to contain
-				 * the error, we must reinitialize it before
-				 * use, so treat it as a fatal AER error.
-				 */
-				if (gdata->flags & CPER_SEC_RESET)
-					aer_severity = AER_FATAL;
-
-				aer_recover_queue(pcie_err->device_id.segment,
-						  pcie_err->device_id.bus,
-						  devfn, aer_severity,
-						  (struct aer_capability_regs *)
-						  pcie_err->aer_info);
-			}
-
+			ghes_handle_aer(gdata);
 		}
-#endif
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);