6.8-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vikas Gupta vikas.gupta@broadcom.com
[ Upstream commit a1acdc226baec331512f815d6ac9dd6f8435cc7f ]
We do not support two simultaneous recoveries so check for reset flag, BNXT_STATE_IN_FW_RESET, and do not proceed with AER further. When the pci channel state is pci_channel_io_frozen, the PCIe link can not be trusted so we disable the traffic immediately and stop BAR access by calling bnxt_fw_fatal_close(). BAR access after AER fatal error can cause an NMI.
Fixes: f75d9a0aa967 ("bnxt_en: Re-write PCI BARs after PCI fatal error.") Signed-off-by: Vikas Gupta vikas.gupta@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 260ffd71e2a89..6bdd8c2607898 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -15045,6 +15045,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, { struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); + bool abort = false;
netdev_info(netdev, "PCI I/O error detected\n");
@@ -15053,16 +15054,27 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
bnxt_ulp_stop(bp);
- if (state == pci_channel_io_perm_failure) { + if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + netdev_err(bp->dev, "Firmware reset already in progress\n"); + abort = true; + } + + if (abort || state == pci_channel_io_perm_failure) { rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; }
- if (state == pci_channel_io_frozen) + /* Link is not reliable anymore if state is pci_channel_io_frozen + * so we disable bus master to prevent any potential bad DMAs before + * freeing kernel memory. + */ + if (state == pci_channel_io_frozen) { set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state); + bnxt_fw_fatal_close(bp); + }
if (netif_running(netdev)) - bnxt_close(netdev); + __bnxt_close_nic(bp, true, true);
if (pci_is_enabled(pdev)) pci_disable_device(pdev); @@ -15146,6 +15158,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) }
reset_exit: + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_clear_reservations(bp, true); rtnl_unlock();