From 361187e04733eee19778ea9b01cb95a977c14c10 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 15:11:21 -0700 Subject: [PATCH] PCI/AER: Add optional logging callback for correctable error Some new devices such as CXL devices may want to record additional error information on a corrected error. Add a callback to allow the PCI device driver to do additional logging such as providing additional stats for user space RAS monitoring. For CXL device, this is actually a need due to CXL needing to write to the CXL RAS capability structure correctable error status register in order to clear the unmasked correctable errors. See CXL spec rev3.0 8.2.4.16. Suggested-by: Jonathan Cameron Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166984619233.2804404.3966368388544312674.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- Documentation/PCI/pci-error-recovery.rst | 7 +++++++ drivers/pci/pcie/aer.c | 8 +++++++- include/linux/pci.h | 3 +++ 3 files changed, 17 insertions(+), 1 deletion(-) diff --git a/Documentation/PCI/pci-error-recovery.rst b/Documentation/PCI/pci-error-recovery.rst index 187f43a03200..bdafeb4b66dc 100644 --- a/Documentation/PCI/pci-error-recovery.rst +++ b/Documentation/PCI/pci-error-recovery.rst @@ -83,6 +83,7 @@ This structure has the form:: int (*mmio_enabled)(struct pci_dev *dev); int (*slot_reset)(struct pci_dev *dev); void (*resume)(struct pci_dev *dev); + void (*cor_error_detected)(struct pci_dev *dev); }; The possible channel states are:: @@ -422,5 +423,11 @@ That is, the recovery API only requires that: - drivers/net/cxgb3 - drivers/net/s2io.c + The cor_error_detected() callback is invoked in handle_error_source() when + the error severity is "correctable". The callback is optional and allows + additional logging to be done if desired. See example: + + - drivers/cxl/pci.c + The End ------- diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index e2d8a74f83c3..625f7b2cafe4 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -961,8 +961,14 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) if (aer) pci_write_config_dword(dev, aer + PCI_ERR_COR_STATUS, info->status); - if (pcie_aer_is_native(dev)) + if (pcie_aer_is_native(dev)) { + struct pci_driver *pdrv = dev->driver; + + if (pdrv && pdrv->err_handler && + pdrv->err_handler->cor_error_detected) + pdrv->err_handler->cor_error_detected(dev); pcie_clear_device_status(dev); + } } else if (info->severity == AER_NONFATAL) pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset); else if (info->severity == AER_FATAL) diff --git a/include/linux/pci.h b/include/linux/pci.h index 2bda4a4e47e8..2119a16ecb10 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -843,6 +843,9 @@ struct pci_error_handlers { /* Device driver may resume normal operations */ void (*resume)(struct pci_dev *dev); + + /* Allow device driver to record more details of a correctable error */ + void (*cor_error_detected)(struct pci_dev *dev); };