bnxt_en: Re-write PCI BARs after PCI fatal error.

When a PCIe fatal error occurs, the internal latched BAR addresses
in the chip get reset even though the BAR register values in config
space are retained.

pci_restore_state() will not rewrite the BAR addresses if the
BAR address values are valid, causing the chip's internal BAR addresses
to stay invalid.  So we need to zero the BAR registers during PCIe fatal
error to force pci_restore_state() to restore the BAR addresses.  These
write cycles to the BAR registers will cause the proper BAR addresses to
latch internally.

Fixes: 6316ea6db93d ("bnxt_en: Enable AER support.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7be23201801523206611a60e36682fd2ba0d4377..8012386b4a0f1d5a72fcd576771d6f1a41cacc15 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12852,6 +12852,9 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
                return PCI_ERS_RESULT_DISCONNECT;
        }
 
+       if (state == pci_channel_io_frozen)
+               set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state);
+
        if (netif_running(netdev))
                bnxt_close(netdev);
 
@@ -12878,7 +12881,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 {
        struct net_device *netdev = pci_get_drvdata(pdev);
        struct bnxt *bp = netdev_priv(netdev);
-       int err = 0;
+       int err = 0, off;
        pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
 
        netdev_info(bp->dev, "PCI Slot Reset\n");
@@ -12890,6 +12893,20 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
                        "Cannot re-enable PCI device after reset.\n");
        } else {
                pci_set_master(pdev);
+               /* Upon fatal error, our device internal logic that latches to
+                * BAR value is getting reset and will restore only upon
+                * rewritting the BARs.
+                *
+                * As pci_restore_state() does not re-write the BARs if the
+                * value is same as saved value earlier, driver needs to
+                * write the BARs to 0 to force restore, in case of fatal error.
+                */
+               if (test_and_clear_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN,
+                                      &bp->state)) {
+                       for (off = PCI_BASE_ADDRESS_0;
+                            off <= PCI_BASE_ADDRESS_5; off += 4)
+                               pci_write_config_dword(bp->pdev, off, 0);
+               }
                pci_restore_state(pdev);
                pci_save_state(pdev);
 

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 21ef1c21f602acdd444437a33b91bcf0be5ff14d..47b3c31278798b1b076f15fdd45d1e9d5a05311a 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1781,6 +1781,7 @@ struct bnxt {
 #define BNXT_STATE_ABORT_ERR   5
 #define BNXT_STATE_FW_FATAL_COND       6
 #define BNXT_STATE_DRV_REGISTERED      7
+#define BNXT_STATE_PCI_CHANNEL_IO_FROZEN       8
 
 #define BNXT_NO_FW_ACCESS(bp)                                  \
        (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) ||    \