On Fri, 2009-08-21 at 12:48 +0900, Hidetoshi Seto wrote:
> ERR_{,UN}CORRECTABLE_ERROR_MASK are set of error bits which linux know,
> set of PCI_ERR_COR_* and PCI_ERR_UNC_* defined in linux/pci_regs.h.
> This masks make aerdrv not to report errors of unknown bit, while aerdrv
> have ability to report such undefined errors as "Unknown Error Bit %2d".
>
> OTOH aerdrv_errprint does not have any check of setting in mask register.
> So it could report masked wrong error by finding bit in status without
> knowing that the bit is masked in the mask register.
>
> This patch changes aerdrv to use mask state in mask register properly
> instead of defined/hardcoded ERR_{,UN}CORRECTABLE_ERROR_MASK.
> This change prevents aerdrv from reporting masked error, and also enable
> reporting unknown errors.
>
> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@xxxxxxxxxxxxxx>
> ---
> drivers/pci/pcie/aer/aerdrv.h | 4 +---
> drivers/pci/pcie/aer/aerdrv_core.c | 28 ++++++++++++----------------
> drivers/pci/pcie/aer/aerdrv_errprint.c | 6 ++++--
> 3 files changed, 17 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
> index 820ea73..0db530d 100644
> --- a/drivers/pci/pcie/aer/aerdrv.h
> +++ b/drivers/pci/pcie/aer/aerdrv.h
> @@ -47,9 +47,6 @@
> #define AER_TLP_HEADER_VALID_FLAG 0x00000001
> #define AER_MULTI_ERROR_VALID_FLAG 0x00000002
>
> -#define ERR_CORRECTABLE_ERROR_MASK 0x000031c1
> -#define ERR_UNCORRECTABLE_ERROR_MASK 0x001ff010
> -
> struct header_log_regs {
> unsigned int dw0;
> unsigned int dw1;
> @@ -65,6 +62,7 @@ struct aer_err_info {
> int severity; /* 0:NONFATAL | 1:FATAL | 2:COR */
> int flags;
> unsigned int status; /* COR/UNCOR Error Status */
> + unsigned int mask; /* COR/UNCOR Error Mask */
> struct header_log_regs tlp; /* TLP Header */
> };
>
> diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
> index 4d67db8..38b3933 100644
> --- a/drivers/pci/pcie/aer/aerdrv_core.c
> +++ b/drivers/pci/pcie/aer/aerdrv_core.c
> @@ -236,24 +236,16 @@ static int find_device_iter(struct pci_dev *dev, void *data)
> status = 0;
> mask = 0;
> if (e_info->severity == AER_CORRECTABLE) {
> - pci_read_config_dword(dev,
> - pos + PCI_ERR_COR_STATUS,
> - &status);
> - pci_read_config_dword(dev,
> - pos + PCI_ERR_COR_MASK,
> - &mask);
> - if (status & ERR_CORRECTABLE_ERROR_MASK & ~mask) {
> + pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
> + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask);
> + if (status & ~mask) {
> add_error_device(e_info, dev);
> goto added;
> }
> } else {
> - pci_read_config_dword(dev,
> - pos + PCI_ERR_UNCOR_STATUS,
> - &status);
> - pci_read_config_dword(dev,
> - pos + PCI_ERR_UNCOR_MASK,
> - &mask);
> - if (status & ERR_UNCORRECTABLE_ERROR_MASK & ~mask) {
> + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
> + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
> + if (status & ~mask) {
> add_error_device(e_info, dev);
> goto added;
> }
> @@ -720,7 +712,9 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
> if (info->severity == AER_CORRECTABLE) {
> pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
> &info->status);
> - if (!(info->status & ERR_CORRECTABLE_ERROR_MASK))
> + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK,
> + &info->mask);
> + if (!(info->status & ~info->mask))
> return AER_UNSUCCESS;
> } else if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE ||
> info->severity == AER_NONFATAL) {
> @@ -728,7 +722,9 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
> /* Link is still healthy for IO reads */
> pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
> &info->status);
> - if (!(info->status & ERR_UNCORRECTABLE_ERROR_MASK))
> + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK,
> + &info->mask);
> + if (!(info->status & ~info->mask))
> return AER_UNSUCCESS;
>
> if (info->status & AER_LOG_TLP_MASKS) {
> diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
> index 5fd1178..919c2c0 100644
> --- a/drivers/pci/pcie/aer/aerdrv_errprint.c
> +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
> @@ -154,11 +154,13 @@ static char *aer_agent_string[] = {
>
> static void aer_print_error_source(struct aer_err_info *info)
> {
> - int i;
> + int i, status;
> char *errmsg = NULL;
>
> + status = (info->status & ~info->mask);
> +
> for (i = 0; i < 32; i++) {
> - if (!(info->status & (1 << i)))
> + if (!(status & (1 << i)))
> continue;
>
> if (info->severity == AER_CORRECTABLE)
Reviewed-by: Andrew Patterson <andrew.patterson@xxxxxx>
--
Andrew Patterson
Hewlett-Packard
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
