4 files changed, 55 insertions, 7 deletions

diff --git a/drivers/net/ixgb/ixgb.h b/drivers/net/ixgb/ixgb.h
index 50ffe90488ff..f4aba4355b19 100644
--- a/drivers/net/ixgb/ixgb.h
+++ b/drivers/net/ixgb/ixgb.h
@@ -171,6 +171,7 @@ struct ixgb_adapter {
 
         /* TX */
         struct ixgb_desc_ring tx_ring ____cacheline_aligned_in_smp;
+        unsigned int restart_queue;
         unsigned long timeo_start;
         uint32_t tx_cmd_type;
         uint64_t hw_csum_tx_good;
diff --git a/drivers/net/ixgb/ixgb_ethtool.c b/drivers/net/ixgb/ixgb_ethtool.c
index cd22523fb035..82c044d6e08a 100644
--- a/drivers/net/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ixgb/ixgb_ethtool.c
@@ -79,6 +79,7 @@ static struct ixgb_stats ixgb_gstrings_stats[] = {
         {"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) },
+        {"tx_restart_queue", IXGB_STAT(restart_queue) },
         {"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_hw.c b/drivers/net/ixgb/ixgb_hw.c
index 02089b64e42c..ecbf45861c68 100644
--- a/drivers/net/ixgb/ixgb_hw.c
+++ b/drivers/net/ixgb/ixgb_hw.c
@@ -399,8 +399,9 @@ ixgb_init_rx_addrs(struct ixgb_hw *hw)
         /* Zero out the other 15 receive addresses. */
         DEBUGOUT("Clearing RAR[1-15]\n");
         for(i = 1; i < IXGB_RAR_ENTRIES; i++) {
-                IXGB_WRITE_REG_ARRAY(hw, RA, (i << 1), 0);
+                /* Write high reg first to disable the AV bit first */
                 IXGB_WRITE_REG_ARRAY(hw, RA, ((i << 1) + 1), 0);
+                IXGB_WRITE_REG_ARRAY(hw, RA, (i << 1), 0);
         }
 
         return;
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index e628126c9c49..a083a9189230 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -36,7 +36,7 @@ static char ixgb_driver_string[] = "Intel(R) PRO/10GbE Network Driver";
 #else
 #define DRIVERNAPI "-NAPI"
 #endif
-#define DRV_VERSION             "1.0.117-k2"DRIVERNAPI
+#define DRV_VERSION             "1.0.126-k2"DRIVERNAPI
 char ixgb_driver_version[] = DRV_VERSION;
 static char ixgb_copyright[] = "Copyright (c) 1999-2006 Intel Corporation.";
 
@@ -1287,6 +1287,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb,
         struct ixgb_buffer *buffer_info;
         int len = skb->len;
         unsigned int offset = 0, size, count = 0, i;
+        unsigned int mss = skb_shinfo(skb)->gso_size;
 
         unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
         unsigned int f;
@@ -1298,6 +1299,11 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb,
         while(len) {
                 buffer_info = &tx_ring->buffer_info[i];
                 size = min(len, IXGB_MAX_DATA_PER_TXD);
+                /* Workaround for premature desc write-backs
+                 * in TSO mode.  Append 4-byte sentinel desc */
+                if (unlikely(mss && !nr_frags && size == len && size > 8))
+                        size -= 4;
+
                 buffer_info->length = size;
                 WARN_ON(buffer_info->dma != 0);
                 buffer_info->dma =
@@ -1324,6 +1330,13 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb,
                 while(len) {
                         buffer_info = &tx_ring->buffer_info[i];
                         size = min(len, IXGB_MAX_DATA_PER_TXD);
+
+                        /* Workaround for premature desc write-backs
+                         * in TSO mode.  Append 4-byte sentinel desc */
+                        if (unlikely(mss && !nr_frags && size == len
+                                     && size > 8))
+                                size -= 4;
+
                         buffer_info->length = size;
                         buffer_info->dma =
                                 pci_map_page(adapter->pdev,
@@ -1398,11 +1411,43 @@ ixgb_tx_queue(struct ixgb_adapter *adapter, int count, int vlan_id,int tx_flags)
         IXGB_WRITE_REG(&adapter->hw, TDT, i);
 }
 
+static int __ixgb_maybe_stop_tx(struct net_device *netdev, int size)
+{
+        struct ixgb_adapter *adapter = netdev_priv(netdev);
+        struct ixgb_desc_ring *tx_ring = &adapter->tx_ring;
+
+        netif_stop_queue(netdev);
+        /* Herbert's original patch had:
+         *  smp_mb__after_netif_stop_queue();
+         * but since that doesn't exist yet, just open code it. */
+        smp_mb();
+
+        /* We need to check again in a case another CPU has just
+         * made room available. */
+        if (likely(IXGB_DESC_UNUSED(tx_ring) < size))
+                return -EBUSY;
+
+        /* A reprieve! */
+        netif_start_queue(netdev);
+        ++adapter->restart_queue;
+        return 0;
+}
+
+static int ixgb_maybe_stop_tx(struct net_device *netdev,
+                              struct ixgb_desc_ring *tx_ring, int size)
+{
+        if (likely(IXGB_DESC_UNUSED(tx_ring) >= size))
+                return 0;
+        return __ixgb_maybe_stop_tx(netdev, size);
+}
+
+
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S) (((S) >> IXGB_MAX_TXD_PWR) + \
                          (((S) & (IXGB_MAX_DATA_PER_TXD - 1)) ? 1 : 0))
-#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) + \
-        MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1
+#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) /* skb->date */ + \
+        MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1 /* for context */ \
+        + 1 /* one more needed for sentinel TSO workaround */
 
 static int
 ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
@@ -1430,7 +1475,8 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
         spin_lock_irqsave(&adapter->tx_lock, flags);
 #endif
 
-        if(unlikely(IXGB_DESC_UNUSED(&adapter->tx_ring) < DESC_NEEDED)) {
+        if (unlikely(ixgb_maybe_stop_tx(netdev, &adapter->tx_ring,
+                     DESC_NEEDED))) {
                 netif_stop_queue(netdev);
                 spin_unlock_irqrestore(&adapter->tx_lock, flags);
                 return NETDEV_TX_BUSY;
@@ -1468,8 +1514,7 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 #ifdef NETIF_F_LLTX
         /* Make sure there is space in the ring for the next send. */
-        if(unlikely(IXGB_DESC_UNUSED(&adapter->tx_ring) < DESC_NEEDED))
-                netif_stop_queue(netdev);
+        ixgb_maybe_stop_tx(netdev, &adapter->tx_ring, DESC_NEEDED);
 
         spin_unlock_irqrestore(&adapter->tx_lock, flags);