AER info of PCIe fatal error is not printed in the current driver.
Because APEI driver will panic directly for fatal error, and can't
run to the place of printing AER info.
An example log is as following:
{763}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 11
{763}[Hardware Error]: event severity: fatal
{763}[Hardware Error]: Error 0, type: fatal
{763}[Hardware Error]: section_type: PCIe error
{763}[Hardware Error]: port_type: 0, PCIe end point
{763}[Hardware Error]: version: 4.0
{763}[Hardware Error]: command: 0x0000, status: 0x0010
{763}[Hardware Error]: device_id: 0000:82:00.0
{763}[Hardware Error]: slot: 0
{763}[Hardware Error]: secondary_bus: 0x00
{763}[Hardware Error]: vendor_id: 0x8086, device_id: 0x10fb
{763}[Hardware Error]: class_code: 000002
Kernel panic - not syncing: Fatal hardware error!
This issue was imported by the patch, '37448adfc7ce ("aerdrv: Move
cper_print_aer() call out of interrupt context")'. To fix this issue,
this patch adds print of AER info in cper_print_pcie() for fatal error.
Here is the example log after this patch applied:
{24}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 10
{24}[Hardware Error]: event severity: fatal
{24}[Hardware Error]: Error 0, type: fatal
{24}[Hardware Error]: section_type: PCIe error
{24}[Hardware Error]: port_type: 0, PCIe end point
{24}[Hardware Error]: version: 4.0
{24}[Hardware Error]: command: 0x0546, status: 0x4010
{24}[Hardware Error]: device_id: 0000:01:00.0
{24}[Hardware Error]: slot: 0
{24}[Hardware Error]: secondary_bus: 0x00
{24}[Hardware Error]: vendor_id: 0x15b3, device_id: 0x1019
{24}[Hardware Error]: class_code: 000002
{24}[Hardware Error]: aer_uncor_status: 0x00040000, aer_uncor_mask: 0x00000000
{24}[Hardware Error]: aer_uncor_severity: 0x00062010
{24}[Hardware Error]: TLP Header: 000000c0 01010000 00000001 00000000
Kernel panic - not syncing: Fatal hardware error!
Fixes: 37448adfc7ce ("aerdrv: Move cper_print_aer() call out of interrupt context")
Signed-off-by: Xiaofei Tan <[email protected]>
Reviewed-by: James Morse <[email protected]>
---
drivers/firmware/efi/cper.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 8fa977c..78b8922 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -390,6 +390,21 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
printk(
"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
pfx, pcie->bridge.secondary_status, pcie->bridge.control);
+
+ /* Fatal errors call __ghes_panic() before AER handler prints this */
+ if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO &&
+ gdata->error_severity & CPER_SEV_FATAL) {
+ struct aer_capability_regs *aer;
+
+ aer = (struct aer_capability_regs *)pcie->aer_info;
+ printk("%saer_uncor_status: 0x%08x, aer_uncor_mask: 0x%08x\n",
+ pfx, aer->uncor_status, aer->uncor_mask);
+ printk("%saer_uncor_severity: 0x%08x\n",
+ pfx, aer->uncor_severity);
+ printk("%sTLP Header: %08x %08x %08x %08x\n", pfx,
+ aer->header_log.dw0, aer->header_log.dw1,
+ aer->header_log.dw2, aer->header_log.dw3);
+ }
}
static void cper_print_tstamp(const char *pfx,
--
2.8.1
ping...
On 2019/7/26 9:43, Xiaofei Tan wrote:
> AER info of PCIe fatal error is not printed in the current driver.
> Because APEI driver will panic directly for fatal error, and can't
> run to the place of printing AER info.
>
> An example log is as following:
> {763}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 11
> {763}[Hardware Error]: event severity: fatal
> {763}[Hardware Error]: Error 0, type: fatal
> {763}[Hardware Error]: section_type: PCIe error
> {763}[Hardware Error]: port_type: 0, PCIe end point
> {763}[Hardware Error]: version: 4.0
> {763}[Hardware Error]: command: 0x0000, status: 0x0010
> {763}[Hardware Error]: device_id: 0000:82:00.0
> {763}[Hardware Error]: slot: 0
> {763}[Hardware Error]: secondary_bus: 0x00
> {763}[Hardware Error]: vendor_id: 0x8086, device_id: 0x10fb
> {763}[Hardware Error]: class_code: 000002
> Kernel panic - not syncing: Fatal hardware error!
>
> This issue was imported by the patch, '37448adfc7ce ("aerdrv: Move
> cper_print_aer() call out of interrupt context")'. To fix this issue,
> this patch adds print of AER info in cper_print_pcie() for fatal error.
>
> Here is the example log after this patch applied:
> {24}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 10
> {24}[Hardware Error]: event severity: fatal
> {24}[Hardware Error]: Error 0, type: fatal
> {24}[Hardware Error]: section_type: PCIe error
> {24}[Hardware Error]: port_type: 0, PCIe end point
> {24}[Hardware Error]: version: 4.0
> {24}[Hardware Error]: command: 0x0546, status: 0x4010
> {24}[Hardware Error]: device_id: 0000:01:00.0
> {24}[Hardware Error]: slot: 0
> {24}[Hardware Error]: secondary_bus: 0x00
> {24}[Hardware Error]: vendor_id: 0x15b3, device_id: 0x1019
> {24}[Hardware Error]: class_code: 000002
> {24}[Hardware Error]: aer_uncor_status: 0x00040000, aer_uncor_mask: 0x00000000
> {24}[Hardware Error]: aer_uncor_severity: 0x00062010
> {24}[Hardware Error]: TLP Header: 000000c0 01010000 00000001 00000000
> Kernel panic - not syncing: Fatal hardware error!
>
> Fixes: 37448adfc7ce ("aerdrv: Move cper_print_aer() call out of interrupt context")
> Signed-off-by: Xiaofei Tan <[email protected]>
> Reviewed-by: James Morse <[email protected]>
> ---
> drivers/firmware/efi/cper.c | 15 +++++++++++++++
> 1 file changed, 15 insertions(+)
>
> diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
> index 8fa977c..78b8922 100644
> --- a/drivers/firmware/efi/cper.c
> +++ b/drivers/firmware/efi/cper.c
> @@ -390,6 +390,21 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
> printk(
> "%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
> pfx, pcie->bridge.secondary_status, pcie->bridge.control);
> +
> + /* Fatal errors call __ghes_panic() before AER handler prints this */
> + if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO &&
> + gdata->error_severity & CPER_SEV_FATAL) {
> + struct aer_capability_regs *aer;
> +
> + aer = (struct aer_capability_regs *)pcie->aer_info;
> + printk("%saer_uncor_status: 0x%08x, aer_uncor_mask: 0x%08x\n",
> + pfx, aer->uncor_status, aer->uncor_mask);
> + printk("%saer_uncor_severity: 0x%08x\n",
> + pfx, aer->uncor_severity);
> + printk("%sTLP Header: %08x %08x %08x %08x\n", pfx,
> + aer->header_log.dw0, aer->header_log.dw1,
> + aer->header_log.dw2, aer->header_log.dw3);
> + }
> }
>
> static void cper_print_tstamp(const char *pfx,
>
--
thanks
tanxiaofei