[PATCH] igc: Mask replay rollover/timeout errors in I225_LMVP

From: Rajat Khandelwal
Date: Thu Dec 29 2022 - 07:26:44 EST


The CPU logs get flooded with replay rollover/timeout AER errors in
the system with i225_lmvp connected, usually inside thunderbolt devices.

One of the prominent TBT4 docks we use is HP G4 Hook2, which incorporates
an Intel Foxville chipset, which uses the igc driver.
On connecting ethernet, CPU logs get inundated with these errors. The point
is we shouldn't be spamming the logs with such correctible errors as it
confuses other kernel developers less familiar with PCI errors, support
staff, and users who happen to look at the logs.

Signed-off-by: Rajat Khandelwal <rajat.khandelwal@xxxxxxxxxxxxxxx>
---
drivers/net/ethernet/intel/igc/igc_main.c | 28 +++++++++++++++++++++--
1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ebff0e04045d..a3a6e8086c8d 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6201,6 +6201,26 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
return value;
}

+#ifdef CONFIG_PCIEAER
+static void igc_mask_aer_replay_correctible(struct igc_adapter *adapter)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ u32 aer_pos, corr_mask;
+
+ if (pdev->device != IGC_DEV_ID_I225_LMVP)
+ return;
+
+ aer_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+ if (!aer_pos)
+ return;
+
+ pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_MASK, &corr_mask);
+
+ corr_mask |= PCI_ERR_COR_REP_ROLL | PCI_ERR_COR_REP_TIMER;
+ pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_MASK, corr_mask);
+}
+#endif
+
/**
* igc_probe - Device Initialization Routine
* @pdev: PCI device information struct
@@ -6236,8 +6256,6 @@ static int igc_probe(struct pci_dev *pdev,
if (err)
goto err_pci_reg;

- pci_enable_pcie_error_reporting(pdev);
-
err = pci_enable_ptm(pdev, NULL);
if (err < 0)
dev_info(&pdev->dev, "PCIe PTM not supported by PCIe bus/controller\n");
@@ -6272,6 +6290,12 @@ static int igc_probe(struct pci_dev *pdev,
if (!adapter->io_addr)
goto err_ioremap;

+#ifdef CONFIG_PCIEAER
+ igc_mask_aer_replay_correctible(adapter);
+#endif
+
+ pci_enable_pcie_error_reporting(pdev);
+
/* hw->hw_addr can be zeroed, so use adapter->io_addr for unmap */
hw->hw_addr = adapter->io_addr;

--
2.34.1