ixgb: add tx timeout counter

This adds a TX timeout counter to the ethtool stats, a tx timeout
debug message, and sets the timer to 5 seconds.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: John Ronciak <john.ronciak@intel.com>

3 files changed, 27 insertions, 4 deletions

diff --git a/drivers/net/ixgb/ixgb.h b/drivers/net/ixgb/ixgb.h
index a687f1210cb0..b9c37fdc8418 100644
--- a/drivers/net/ixgb/ixgb.h
+++ b/drivers/net/ixgb/ixgb.h
@@ -180,6 +180,7 @@ struct ixgb_adapter {
         uint64_t hw_csum_tx_good;
         uint64_t hw_csum_tx_error;
         uint32_t tx_int_delay;
+        uint32_t tx_timeout_count;
         boolean_t tx_int_delay_enable;
         boolean_t detect_tx_hung;
 
diff --git a/drivers/net/ixgb/ixgb_ethtool.c b/drivers/net/ixgb/ixgb_ethtool.c
index 560b4b6c79d0..6d8192f4314c 100644
--- a/drivers/net/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ixgb/ixgb_ethtool.c
@@ -78,6 +78,7 @@ static struct ixgb_stats ixgb_gstrings_stats[] = {
         {"tx_heartbeat_errors", IXGB_STAT(net_stats.tx_heartbeat_errors)},
         {"tx_window_errors", IXGB_STAT(net_stats.tx_window_errors)},
         {"tx_deferred_ok", IXGB_STAT(stats.dc)},
+        {"tx_timeout_count", IXGB_STAT(tx_timeout_count) },
         {"rx_long_length_errors", IXGB_STAT(stats.roc)},
         {"rx_short_length_errors", IXGB_STAT(stats.ruc)},
 #ifdef NETIF_F_TSO
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index 4115bf360d93..da0b91905ffc 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -428,7 +428,7 @@ ixgb_probe(struct pci_dev *pdev,
         netdev->change_mtu = &ixgb_change_mtu;
         ixgb_set_ethtool_ops(netdev);
         netdev->tx_timeout = &ixgb_tx_timeout;
-        netdev->watchdog_timeo = HZ;
+        netdev->watchdog_timeo = 5 * HZ;
 #ifdef CONFIG_IXGB_NAPI
         netdev->poll = &ixgb_clean;
         netdev->weight = 64;
@@ -1509,6 +1509,7 @@ ixgb_tx_timeout_task(struct net_device *netdev)
 {
         struct ixgb_adapter *adapter = netdev_priv(netdev);
 
+        adapter->tx_timeout_count++;
         ixgb_down(adapter, TRUE);
         ixgb_up(adapter);
 }
@@ -1838,11 +1839,31 @@ ixgb_clean_tx_irq(struct ixgb_adapter *adapter)
                 /* detect a transmit hang in hardware, this serializes the
                  * check with the clearing of time_stamp and movement of i */
                 adapter->detect_tx_hung = FALSE;
-                if(tx_ring->buffer_info[i].dma &&
-                   time_after(jiffies, tx_ring->buffer_info[i].time_stamp + HZ)
+                if (tx_ring->buffer_info[eop].dma &&
+                   time_after(jiffies, tx_ring->buffer_info[eop].time_stamp + HZ)
                    && !(IXGB_READ_REG(&adapter->hw, STATUS) &
-                        IXGB_STATUS_TXOFF))
+                        IXGB_STATUS_TXOFF)) {
+                        /* detected Tx unit hang */
+                        DPRINTK(DRV, ERR, "Detected Tx Unit Hang\n"
+                                        "  TDH                  <%x>\n"
+                                        "  TDT                  <%x>\n"
+                                        "  next_to_use          <%x>\n"
+                                        "  next_to_clean        <%x>\n"
+                                        "buffer_info[next_to_clean]\n"
+                                        "  time_stamp           <%lx>\n"
+                                        "  next_to_watch        <%x>\n"
+                                        "  jiffies              <%lx>\n"
+                                        "  next_to_watch.status <%x>\n",
+                                IXGB_READ_REG(&adapter->hw, TDH),
+                                IXGB_READ_REG(&adapter->hw, TDT),
+                                tx_ring->next_to_use,
+                                tx_ring->next_to_clean,
+                                tx_ring->buffer_info[eop].time_stamp,
+                                eop,
+                                jiffies,
+                                eop_desc->status);
                         netif_stop_queue(netdev);
+                }
         }
 
         return cleaned;