myri10ge: improve parity error detection and recovery

Improve myri10ge parity error detection and recovery:
1) Don't restore PCI config space to a rebooted NIC until AFTER the
   host is quiescent.
2) Let myri10ge_close() know the NIC is dead, so it won't waste time
   waiting for a dead nic to respond to MXGEFW_CMD_ETHERNET_DOWN
3) When the NIC is quiet (link down, or otherwise idle link) use
   a pci config space read to detect a rebooted NIC.  Otherwise
   we might never notice that a NIC rebooted

Signed-off-by: Andrew Gallatin <gallatin@myri.com>
Signed-off-by: Brice Goglin <brice@myri.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 1a34f7e..75deef3 100644 (file)
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -75,7 +75,7 @@
 #include "myri10ge_mcp.h"
 #include "myri10ge_mcp_gen_header.h"
 
-#define MYRI10GE_VERSION_STR "1.5.0-1.418"
+#define MYRI10GE_VERSION_STR "1.5.0-1.432"
 
 MODULE_DESCRIPTION("Myricom 10G driver (10GbE)");
 MODULE_AUTHOR("Maintainer: help@myri.com");
@@ -188,6 +188,7 @@ struct myri10ge_slice_state {
        dma_addr_t fw_stats_bus;
        int watchdog_tx_done;
        int watchdog_tx_req;
+       int watchdog_rx_done;
 #ifdef CONFIG_MYRI10GE_DCA
        int cached_dca_tag;
        int cpu;
@@ -256,6 +257,7 @@ struct myri10ge_priv {
        u32 link_changes;
        u32 msg_enable;
        unsigned int board_number;
+       int rebooted;
 };
 
 static char *myri10ge_fw_unaligned = "myri10ge_ethp_z8e.dat";
@@ -2552,17 +2554,22 @@ static int myri10ge_close(struct net_device *dev)
        netif_carrier_off(dev);
 
        netif_tx_stop_all_queues(dev);
-       old_down_cnt = mgp->down_cnt;
-       mb();
-       status = myri10ge_send_cmd(mgp, MXGEFW_CMD_ETHERNET_DOWN, &cmd, 0);
-       if (status)
-               printk(KERN_ERR "myri10ge: %s: Couldn't bring down link\n",
-                      dev->name);
-
-       wait_event_timeout(mgp->down_wq, old_down_cnt != mgp->down_cnt, HZ);
-       if (old_down_cnt == mgp->down_cnt)
-               printk(KERN_ERR "myri10ge: %s never got down irq\n", dev->name);
+       if (mgp->rebooted == 0) {
+               old_down_cnt = mgp->down_cnt;
+               mb();
+               status =
+                   myri10ge_send_cmd(mgp, MXGEFW_CMD_ETHERNET_DOWN, &cmd, 0);
+               if (status)
+                       printk(KERN_ERR
+                              "myri10ge: %s: Couldn't bring down link\n",
+                              dev->name);
 
+               wait_event_timeout(mgp->down_wq, old_down_cnt != mgp->down_cnt,
+                                  HZ);
+               if (old_down_cnt == mgp->down_cnt)
+                       printk(KERN_ERR "myri10ge: %s never got down irq\n",
+                              dev->name);
+       }
        netif_tx_disable(dev);
        myri10ge_free_irq(mgp);
        for (i = 0; i < mgp->num_slices; i++)
@@ -3427,12 +3434,13 @@ static void myri10ge_watchdog(struct work_struct *work)
            container_of(work, struct myri10ge_priv, watchdog_work);
        struct myri10ge_tx_buf *tx;
        u32 reboot;
-       int status;
+       int status, rebooted;
        int i;
        u16 cmd, vendor;
 
        mgp->watchdog_resets++;
        pci_read_config_word(mgp->pdev, PCI_COMMAND, &cmd);
+       rebooted = 0;
        if ((cmd & PCI_COMMAND_MASTER) == 0) {
                /* Bus master DMA disabled?  Check to see
                 * if the card rebooted due to a parity error
@@ -3444,9 +3452,12 @@ static void myri10ge_watchdog(struct work_struct *work)
                       myri10ge_reset_recover ? " " : " not");
                if (myri10ge_reset_recover == 0)
                        return;
-
+               rtnl_lock();
+               mgp->rebooted = 1;
+               rebooted = 1;
+               myri10ge_close(mgp->dev);
                myri10ge_reset_recover--;
-
+               mgp->rebooted = 0;
                /*
                 * A rebooted nic will come back with config space as
                 * it was after power was applied to PCIe bus.
@@ -3494,8 +3505,10 @@ static void myri10ge_watchdog(struct work_struct *work)
                }
        }
 
-       rtnl_lock();
-       myri10ge_close(mgp->dev);
+       if (!rebooted) {
+               rtnl_lock();
+               myri10ge_close(mgp->dev);
+       }
        status = myri10ge_load_firmware(mgp, 1);
        if (status != 0)
                printk(KERN_ERR "myri10ge: %s: failed to load firmware\n",
@@ -3516,12 +3529,14 @@ static void myri10ge_watchdog_timer(unsigned long arg)
 {
        struct myri10ge_priv *mgp;
        struct myri10ge_slice_state *ss;
-       int i, reset_needed;
+       int i, reset_needed, busy_slice_cnt;
        u32 rx_pause_cnt;
+       u16 cmd;
 
        mgp = (struct myri10ge_priv *)arg;
 
        rx_pause_cnt = ntohl(mgp->ss[0].fw_stats->dropped_pause);
+       busy_slice_cnt = 0;
        for (i = 0, reset_needed = 0;
             i < mgp->num_slices && reset_needed == 0; ++i) {
 
@@ -3559,8 +3574,22 @@ static void myri10ge_watchdog_timer(unsigned long arg)
                                reset_needed = 1;
                        }
                }
+               if (ss->watchdog_tx_done != ss->tx.done ||
+                   ss->watchdog_rx_done != ss->rx_done.cnt) {
+                       busy_slice_cnt++;
+               }
                ss->watchdog_tx_done = ss->tx.done;
                ss->watchdog_tx_req = ss->tx.req;
+               ss->watchdog_rx_done = ss->rx_done.cnt;
+       }
+       /* if we've sent or received no traffic, poll the NIC to
+        * ensure it is still there.  Otherwise, we risk not noticing
+        * an error in a timely fashion */
+       if (busy_slice_cnt == 0) {
+               pci_read_config_word(mgp->pdev, PCI_COMMAND, &cmd);
+               if ((cmd & PCI_COMMAND_MASTER) == 0) {
+                       reset_needed = 1;
+               }
        }
        mgp->watchdog_pause = rx_pause_cnt;