===================================================================
@@ -4718,7 +4718,15 @@ int pcie_retrain_link(struct pci_dev *pd
pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL);
}
- return pcie_wait_for_link_status(pdev, use_lt, !use_lt);
+ rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt);
+
+ /*
+ * Clear LBMS after a manual retrain so that the bit can be used
+ * to track link speed or width changes made by hardware itself
+ * in attempt to correct unreliable link operation.
+ */
+ pcie_capability_write_word(pdev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+ return rc;
}
/**
The LBMS bit, where implemented, is set by hardware either in response to the completion of retraining caused by writing 1 to the Retrain Link bit or whenever hardware has changed the link speed or width in attempt to correct unreliable link operation. It is never cleared by hardware other than by software writing 1 to the bit position in the Link Status register and we never do such a write. We currently have two places, namely `apply_bad_link_workaround' and `pcie_failed_link_retrain' in drivers/pci/controller/dwc/pcie-tegra194.c and drivers/pci/quirks.c respectively where we check the state of the LBMS bit and neither is interested in the state of the bit resulting from the completion of retraining, both check for a link fault. And in particular `pcie_failed_link_retrain' causes issues consequently, by trying to retrain a link where there's no downstream device anymore and the state of 1 in the LBMS bit has been retained from when there was a device downstream that has since been removed. Clear the LBMS bit then at the conclusion of `pcie_retrain_link', so that we have a single place that controls it and that our code can track link speed or width changes resulting from unreliable link operation. Fixes: a89c82249c37 ("PCI: Work around PCIe link training failures") Reported-by: Matthew W Carlis <mattc@purestorage.com> Link: https://lore.kernel.org/r/20240806000659.30859-1-mattc@purestorage.com/ Link: https://lore.kernel.org/r/20240722193407.23255-1-mattc@purestorage.com/ Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk> Cc: stable@vger.kernel.org # v6.5+ --- No change from v2. New change in v2. --- drivers/pci/pci.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) linux-pcie-retrain-link-lbms-clear.diff