From: Alexey Bogoslavsky <mailto:Alexey.Bogoslavsky@xxxxxxx> A bug was found in SN730 WD SSD that causes occasional false AER reporting of correctable errors. While functionally harmless, this causes error messages to appear in the system log (dmesg) which, in turn, causes problems in automated platform validation tests. Since the issue can not be fixed by FW, customers asked for correctable error reporting to be quirked out in the kernel for this particular device. The patch was manually verified. It was checked that correctable errors are still detected but ignored for the target device (SN730), and are both detected and reported for devices not affected by this quirk. Signed-off-by: Alexey Bogoslavsky mailto:alexey.bogoslavsky@xxxxxxx --- drivers/pci/pcie/aer.c | 3 +++ drivers/pci/quirks.c | 6 ++++++ include/linux/pci.h | 1 + include/linux/pci_ids.h | 4 ++++ 4 files changed, 14 insertions(+) diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index d7ee79d7b192..5cc24d28b76d 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -721,6 +721,9 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) goto out; } + if ((info->severity == AER_CORRECTABLE) && dev->ignore_correctable_errors) + return; + layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 285acc4aaccc..21e4972fb242 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5911,6 +5911,12 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1536, rom_bar_overlap_defect); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1537, rom_bar_overlap_defect); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1538, rom_bar_overlap_defect); +static void wd_ignore_correctable_errors(struct pci_dev *pdev) +{ + pdev->ignore_correctable_errors = true; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_WESTERN_DIGITAL, PCI_DEVICE_ID_WESTERN_DIGITAL_SN730, wd_ignore_correctable_errors); + #ifdef CONFIG_PCIEASPM /* * Several Intel DG2 graphics devices advertise that they can only tolerate diff --git a/include/linux/pci.h b/include/linux/pci.h index adffd65e84b4..1e002be07255 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -463,6 +463,7 @@ struct pci_dev { unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ + unsigned int ignore_correctable_errors:1; /* Ignore correctable errors reported */ unsigned int rom_bar_overlap:1; /* ROM BAR disable broken */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b362d90eb9b0..b5a08a4cf047 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2299,9 +2299,13 @@ #define PCI_VENDOR_ID_QUICKNET 0x15e2 #define PCI_DEVICE_ID_QUICKNET_XJ 0x0500 +#define PCI_VENDOR_ID_WESTERN_DIGITAL 0x15B7 +#define PCI_DEVICE_ID_WESTERN_DIGITAL_SN730 0x5006 + /* * ADDI-DATA GmbH communication cards mailto:info@xxxxxxxxxxxxx */ + #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 -- 2.17.1
