6 files changed, 290 insertions, 178 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 42c9f8b09a6e..ae83da9cd18a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1267,6 +1267,48 @@ static u32 mlx4_en_get_priv_flags(struct net_device *dev)
         return priv->pflags;
 }
 
+static int mlx4_en_get_tunable(struct net_device *dev,
+                               const struct ethtool_tunable *tuna,
+                               void *data)
+{
+        const struct mlx4_en_priv *priv = netdev_priv(dev);
+        int ret = 0;
+
+        switch (tuna->id) {
+        case ETHTOOL_TX_COPYBREAK:
+                *(u32 *)data = priv->prof->inline_thold;
+                break;
+        default:
+                ret = -EINVAL;
+                break;
+        }
+
+        return ret;
+}
+
+static int mlx4_en_set_tunable(struct net_device *dev,
+                               const struct ethtool_tunable *tuna,
+                               const void *data)
+{
+        struct mlx4_en_priv *priv = netdev_priv(dev);
+        int val, ret = 0;
+
+        switch (tuna->id) {
+        case ETHTOOL_TX_COPYBREAK:
+                val = *(u32 *)data;
+                if (val < MIN_PKT_LEN || val > MAX_INLINE)
+                        ret = -EINVAL;
+                else
+                        priv->prof->inline_thold = val;
+                break;
+        default:
+                ret = -EINVAL;
+                break;
+        }
+
+        return ret;
+}
+
 
 const struct ethtool_ops mlx4_en_ethtool_ops = {
         .get_drvinfo = mlx4_en_get_drvinfo,
@@ -1297,6 +1339,8 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
         .get_ts_info = mlx4_en_get_ts_info,
         .set_priv_flags = mlx4_en_set_priv_flags,
         .get_priv_flags = mlx4_en_get_priv_flags,
+        .get_tunable            = mlx4_en_get_tunable,
+        .set_tunable            = mlx4_en_set_tunable,
 };
 
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0c501253fdab..92a7cf46d9af 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -37,6 +37,7 @@
 #include <linux/mlx4/qp.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
+#include <linux/prefetch.h>
 #include <linux/vmalloc.h>
 #include <linux/tcp.h>
 #include <linux/ip.h>
@@ -65,10 +66,9 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
         ring->size = size;
         ring->size_mask = size - 1;
         ring->stride = stride;
-        ring->inline_thold = priv->prof->inline_thold;
 
         tmp = size * sizeof(struct mlx4_en_tx_info);
-        ring->tx_info = vmalloc_node(tmp, node);
+        ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
         if (!ring->tx_info) {
                 ring->tx_info = vmalloc(tmp);
                 if (!ring->tx_info) {
@@ -151,7 +151,7 @@ err_bounce:
         kfree(ring->bounce_buf);
         ring->bounce_buf = NULL;
 err_info:
-        vfree(ring->tx_info);
+        kvfree(ring->tx_info);
         ring->tx_info = NULL;
 err_ring:
         kfree(ring);
@@ -174,7 +174,7 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
         mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
         kfree(ring->bounce_buf);
         ring->bounce_buf = NULL;
-        vfree(ring->tx_info);
+        kvfree(ring->tx_info);
         ring->tx_info = NULL;
         kfree(ring);
         *pring = NULL;
@@ -191,12 +191,12 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
         ring->prod = 0;
         ring->cons = 0xffffffff;
         ring->last_nr_txbb = 1;
-        ring->poll_cnt = 0;
         memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info));
         memset(ring->buf, 0, ring->buf_size);
 
         ring->qp_state = MLX4_QP_STATE_RST;
-        ring->doorbell_qpn = ring->qp.qpn << 8;
+        ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8);
+        ring->mr_key = cpu_to_be32(mdev->mr.key);
 
         mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
                                 ring->cqn, user_prio, &ring->context);
@@ -259,38 +259,45 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
                                 struct mlx4_en_tx_ring *ring,
                                 int index, u8 owner, u64 timestamp)
 {
-        struct mlx4_en_dev *mdev = priv->mdev;
         struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
         struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
         struct mlx4_wqe_data_seg *data = (void *) tx_desc + tx_info->data_offset;
-        struct sk_buff *skb = tx_info->skb;
-        struct skb_frag_struct *frag;
         void *end = ring->buf + ring->buf_size;
-        int frags = skb_shinfo(skb)->nr_frags;
+        struct sk_buff *skb = tx_info->skb;
+        int nr_maps = tx_info->nr_maps;
         int i;
-        struct skb_shared_hwtstamps hwts;
 
-        if (timestamp) {
-                mlx4_en_fill_hwtstamps(mdev, &hwts, timestamp);
+        /* We do not touch skb here, so prefetch skb->users location
+         * to speedup consume_skb()
+         */
+        prefetchw(&skb->users);
+
+        if (unlikely(timestamp)) {
+                struct skb_shared_hwtstamps hwts;
+
+                mlx4_en_fill_hwtstamps(priv->mdev, &hwts, timestamp);
                 skb_tstamp_tx(skb, &hwts);
         }
 
         /* Optimize the common case when there are no wraparounds */
         if (likely((void *) tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) {
                 if (!tx_info->inl) {
-                        if (tx_info->linear) {
+                        if (tx_info->linear)