From 6d2c89441571ea534d6240f7724f518936c44f8d Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Mon, 23 Mar 2020 17:25:58 -0700 Subject: PCI/ERR: Update error status after reset_link() Commit bdb5ac85777d ("PCI/ERR: Handle fatal error recovery") uses reset_link() to recover from fatal errors. But during fatal error recovery, if the initial value of error status is PCI_ERS_RESULT_DISCONNECT or PCI_ERS_RESULT_NO_AER_DRIVER then even after successful recovery (using reset_link()) pcie_do_recovery() will report the recovery result as failure. Update the status of error after reset_link(). You can reproduce this issue by triggering a SW DPC using "DPC Software Trigger" bit in "DPC Control Register". You should see recovery failed dmesg log as below: pcieport 0000:00:16.0: DPC: containment event, status:0x1f27 source:0x0000 pcieport 0000:00:16.0: DPC: software trigger detected pci 0000:04:00.0: AER: can't recover (no error_detected callback) pcieport 0000:00:16.0: AER: device recovery failed Fixes: bdb5ac85777d ("PCI/ERR: Handle fatal error recovery") Link: https://lore.kernel.org/r/a255fcb3a3fdebcd90f84e08b555f1786eb8eba2.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com [bhelgaas: split pci_channel_io_frozen simplification to separate patch] Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Acked-by: Keith Busch Cc: Ashok Raj --- drivers/pci/pcie/err.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/pci') diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index cf97e068e12a..1ac57e9e1e71 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -205,7 +205,8 @@ void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state, pci_dbg(dev, "broadcast error_detected message\n"); if (state == pci_channel_io_frozen) { pci_walk_bus(bus, report_frozen_detected, &status); - if (reset_link(dev, service) != PCI_ERS_RESULT_RECOVERED) + status = reset_link(dev, service); + if (status != PCI_ERS_RESULT_RECOVERED) goto failed; } else { pci_walk_bus(bus, report_normal_detected, &status); -- cgit v1.2.3