Here's the corresponding patch for the ixgb.
--linas
> Hi,
>
> The following patch to the e100 device driver is in the current
> 2.6.15-mm1 tree, and is being pushed to the mainline 2.6.15 tree.
>
> I wrote this patch, and I believe I've cc'ed you on previous
> versions, but certainly not recently. Please review, comment,
> ACK or NAK as appropriate.
>
> Background: Newer PCI controllers can detect and respond to
> serious PCI bus errors, typically by isolating the PCI slot
> (cutting off i/o to the failing card). An arch-specific
> framework can report these errors back to the device driver,
> and coordinate the recovery of the card. Detailed documentation
> for this is in the kernel tree, at Documentation/pci-error-recovery.txt
>
> This patch adds the detection and recovery callbacks to the
> e100 driver. A version of this patch has been shipping as
> a part of SUSE SLES9 for about a year, and so has been
> tested in the field.
>
> Similar patches to follow for the e1000 and the ixgb.
>
> --linas
>
----- Forwarded message from Greg KH <[EMAIL PROTECTED]> -----
Subject: [PATCH] PCI Error Recovery: ixgb network device driver
To: [EMAIL PROTECTED]
From: Greg KH <[EMAIL PROTECTED]>
[PATCH] PCI Error Recovery: ixgb network device driver
Various PCI bus errors can be signaled by newer PCI controllers. This
patch adds the PCI error recovery callbacks to the intel ten-gigabit
ethernet ixgb device driver. The patch has been tested, and appears
to work well.
Signed-off-by: Linas Vepstas <[EMAIL PROTECTED]>
Signed-off-by: Greg Kroah-Hartman <[EMAIL PROTECTED]>
---
commit 3c0006afdd8ade574257c88df81c93b0bb71b544
tree 4cc697ccc74b8d67a9f08e68f71584f9d538e90e
parent d78cde68ab78766c3a175466aa8adcbdc5520963
author linas <[EMAIL PROTECTED]> Fri, 18 Nov 2005 16:24:20 -0600
committer Greg Kroah-Hartman <[EMAIL PROTECTED]> Thu, 05 Jan 2006 21:54:55 -0800
drivers/net/ixgb/ixgb_main.c | 86 ++++++++++++++++++++++++++++++++++++++++++
1 files changed, 86 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index f9f77e4..166832c 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -132,6 +132,16 @@ static void ixgb_restore_vlan(struct ixg
static void ixgb_netpoll(struct net_device *dev);
#endif
+static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev,
pci_channel_state_t state);
+static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev);
+static void ixgb_io_resume (struct pci_dev *pdev);
+
+static struct pci_error_handlers ixgb_err_handler = {
+ .error_detected = ixgb_io_error_detected,
+ .slot_reset = ixgb_io_slot_reset,
+ .resume = ixgb_io_resume,
+};
+
/* Exported from other modules */
extern void ixgb_check_options(struct ixgb_adapter *adapter);
@@ -141,6 +151,8 @@ static struct pci_driver ixgb_driver = {
.id_table = ixgb_pci_tbl,
.probe = ixgb_probe,
.remove = __devexit_p(ixgb_remove),
+ .err_handler = &ixgb_err_handler,
+
};
MODULE_AUTHOR("Intel Corporation, <[EMAIL PROTECTED]>");
@@ -1654,8 +1666,16 @@ ixgb_intr(int irq, void *data, struct pt
unsigned int i;
#endif
+#ifdef XXX_CONFIG_IXGB_EEH_RECOVERY
+ if(unlikely(icr==EEH_IO_ERROR_VALUE(4))) {
+ if (eeh_slot_is_isolated (adapter->pdev))
+ // disable_irq_nosync (adapter->pdev->irq);
+ return IRQ_NONE; /* Not our interrupt */
+ }
+#else
if(unlikely(!icr))
return IRQ_NONE; /* Not our interrupt */
+#endif /* CONFIG_IXGB_EEH_RECOVERY */
if(unlikely(icr & (IXGB_INT_RXSEQ | IXGB_INT_LSC))) {
mod_timer(&adapter->watchdog_timer, jiffies);
@@ -2125,4 +2145,70 @@ static void ixgb_netpoll(struct net_devi
}
#endif
+/* -------------- PCI Error Recovery infrastructure ---------------- */
+/** ixgb_io_error_detected() is called when PCI error is detected */
+static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev,
pci_channel_state_t state)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct ixgb_adapter *adapter = netdev->priv;
+
+ if(netif_running(netdev))
+ ixgb_down(adapter, TRUE);
+
+ /* Request a slot reset. */
+ return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/** ixgb_io_slot_reset is called after the pci bus has been reset.
+ * Restart the card from scratch.
+ * Implementation resembles the first-half of the
+ * ixgb_resume routine.
+ */
+static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct ixgb_adapter *adapter = netdev->priv;
+
+ if(pci_enable_device(pdev)) {
+ printk(KERN_ERR "ixgb: Cannot re-enable PCI device after
reset.\n");
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+ pci_set_master(pdev);
+
+ /* Perform card reset only on one instance of the card */
+ if (0 != PCI_FUNC (pdev->devfn))
+ return PCI_ERS_RESULT_RECOVERED;
+
+ ixgb_reset(adapter);
+
+ return PCI_ERS_RESULT_RECOVERED;
+}
+
+/** ixgb_io_resume is called when the error recovery driver
+ * tells us that its OK to resume normal operation.
+ * Implementation resembles the second-half of the
+ * ixgb_resume routine.
+ */
+static void ixgb_io_resume (struct pci_dev *pdev)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct ixgb_adapter *adapter = netdev->priv;
+
+ if(netif_running(netdev)) {
+ if(ixgb_up(adapter)) {
+ printk ("ixgb: can't bring device back up after
reset\n");
+ return;
+ }
+ }
+
+ netif_device_attach(netdev);
+ if(netif_running(netdev))
+ mod_timer(&adapter->watchdog_timer, jiffies);
+
+ /* Reading all-ff's from the adapter will completely hose
+ * the counts and statistics. So just clear them out */
+ memset(&adapter->stats, 0, sizeof(struct ixgb_hw_stats));
+ ixgb_update_stats(adapter);
+}
+
/* ixgb_main.c */
----- End forwarded message -----
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
