From e330af788998b0de4da4f5bd7ddd087507999800 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 15 Oct 2018 12:18:28 -0700 Subject: fm10k: ensure completer aborts are marked as non-fatal after a resume VF drivers can trigger PCIe completer aborts any time they read a queue that they don't own. Even in nominal circumstances, it is not possible to prevent the VF driver from reading queues it doesn't own. VF drivers may attempt to read queues it previously owned, but which it no longer does due to a PF reset. Normally these completer aborts aren't an issue. However, on some platforms these trigger machine check errors. This is true even if we lower their severity from fatal to non-fatal. Indeed, we already have code for lowering the severity. We could attempt to mask these errors conditionally around resets, which is the most common time they would occur. However this would essentially be a race between the PF and VF drivers, and we may still occasionally see machine check exceptions on these strictly configured platforms. Instead, mask the errors entirely any time we resume VFs. By doing so, we prevent the completer aborts from being sent to the parent PCIe device, and thus these strict platforms will not upgrade them into machine check errors. Additionally, we don't lose any information by masking these errors, because we'll still report VFs which attempt to access queues via the FUM_BAD_VF_QACCESS errors. Without this change, on platforms where completer aborts cause machine check exceptions, the VF reading queues it doesn't own could crash the host system. Masking the completer abort prevents this, so we should mask it for good, and not just around a PCIe reset. Otherwise malicious or misconfigured VFs could cause the host system to crash. Because we are masking the error entirely, there is little reason to also keep setting the severity bit, so that code is also removed. Signed-off-by: Jacob Keller Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 48 ++++++++++++++++------------ 1 file changed, 28 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 74160c2095ee..5d4f1761dc0c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -303,6 +303,28 @@ void fm10k_iov_suspend(struct pci_dev *pdev) } } +static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev) +{ + u32 err_mask; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + if (!pos) + return; + + /* Mask the completion abort bit in the ERR_UNCOR_MASK register, + * preventing the device from reporting these errors to the upstream + * PCIe root device. This avoids bringing down platforms which upgrade + * non-fatal completer aborts into machine check exceptions. Completer + * aborts can occur whenever a VF reads a queue it doesn't own. + */ + pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask); + err_mask |= PCI_ERR_UNC_COMP_ABORT; + pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask); + + mmiowb(); +} + int fm10k_iov_resume(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); @@ -318,6 +340,12 @@ int fm10k_iov_resume(struct pci_dev *pdev) if (!iov_data) return -ENOMEM; + /* Lower severity of completer abort error reporting as + * the VFs can trigger this any time they read a queue + * that they don't own. + */ + fm10k_mask_aer_comp_abort(pdev); + /* allocate hardware resources for the VFs */ hw->iov.ops.assign_resources(hw, num_vfs, num_vfs); @@ -461,20 +489,6 @@ void fm10k_iov_disable(struct pci_dev *pdev) fm10k_iov_free_data(pdev); } -static void fm10k_disable_aer_comp_abort(struct pci_dev *pdev) -{ - u32 err_sev; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - if (!pos) - return; - - pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &err_sev); - err_sev &= ~PCI_ERR_UNC_COMP_ABORT; - pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, err_sev); -} - int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) { int current_vfs = pci_num_vf(pdev); @@ -496,12 +510,6 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) /* allocate VFs if not already allocated */ if (num_vfs && num_vfs != current_vfs) { - /* Disable completer abort error reporting as - * the VFs can trigger this any time they read a queue - * that they don't own. - */ - fm10k_disable_aer_comp_abort(pdev); - err = pci_enable_sriov(pdev, num_vfs); if (err) { dev_err(&pdev->dev, -- cgit v1.2.3-59-g8ed1b