Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "A quick set of fixes, some to deal with fallout from yesterday's
  net-next merge.

   1) Fix compilation of bnx2x driver with CONFIG_BNX2X_SRIOV disabled,
      from Dmitry Kravkov.

   2) Fix a bnx2x regression caused by one of Dave Jones's mistaken
      braces changes, from Eilon Greenstein.

   3) Add some protective filtering in the netlink tap code, from Daniel
      Borkmann.

   4) Fix TCP congestion window growth regression after timeouts, from
      Yuchung Cheng.

   5) Correctly adjust TCP's rcv_ssthresh for out of order packets, from
      Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  tcp: properly increase rcv_ssthresh for ofo packets
  net: add documentation for BQL helpers
  mlx5: remove unused MLX5_DEBUG param in Kconfig
  bnx2x: Restore a call to config_init
  bnx2x: fix broken compilation with CONFIG_BNX2X_SRIOV is not set
  tcp: fix no cwnd growth after timeout
  net: netlink: filter particular protocols from analyzers

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 664568420c9bdd08869e33802ee8c208e307c082..d60a2ea3da192a203a18cda07251c3e2ee60ab42 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6501,13 +6501,10 @@ static int bnx2x_link_initialize(struct link_params *params,
                struct bnx2x_phy *phy = &params->phy[INT_PHY];
                if (vars->line_speed == SPEED_AUTO_NEG &&
                    (CHIP_IS_E1x(bp) ||
-                    CHIP_IS_E2(bp))) {
+                    CHIP_IS_E2(bp)))
                        bnx2x_set_parallel_detection(phy, params);
-                       if (params->phy[INT_PHY].config_init)
-                               params->phy[INT_PHY].config_init(phy,
-                                                                params,
-                                                                vars);
-               }
+               if (params->phy[INT_PHY].config_init)
+                       params->phy[INT_PHY].config_init(phy, params, vars);
        }
 
        /* Init external phy*/

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 2a8c1dc65d9cd6c3a0168bf1c5d12ee0b6b58bcc..059f0d460af2a249e631a913ec98da290d78f323 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -816,6 +816,8 @@ static inline int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp
 static inline int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx) {return 0; }
 static inline int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr,
                                        u8 vf_qid, bool set) {return 0; }
+static inline int bnx2x_vfpf_config_rss(struct bnx2x *bp,
+                                       struct bnx2x_config_rss_params *params) {return 0; }
 static inline int bnx2x_vfpf_set_mcast(struct net_device *dev) {return 0; }
 static inline int bnx2x_vfpf_storm_rx_mode(struct bnx2x *bp) {return 0; }
 static inline int bnx2x_iov_nic_init(struct bnx2x *bp) {return 0; }

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 21962828925a5224fc122f0761eca03954e58df5..157fe8df2c3ed5c105a5301219b281670ed70efd 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -6,13 +6,3 @@ config MLX5_CORE
        tristate
        depends on PCI && X86
        default n
-
-config MLX5_DEBUG
-       bool "Verbose debugging output" if (MLX5_CORE && EXPERT)
-       depends on MLX5_CORE
-       default y
-       ---help---
-         This option causes debugging code to be compiled into the
-         mlx5_core driver.  The output can be turned on via the
-         debug_mask module parameter (which can also be set after
-         the driver is loaded through sysfs).

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8ed4ae9430533a40b6701be6d9346b033f2f96fd..041b42a305f6a1817df51bfd46aa746a454e1a50 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2101,6 +2101,15 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 #endif
 }
 
+/**
+ *     netdev_sent_queue - report the number of bytes queued to hardware
+ *     @dev: network device
+ *     @bytes: number of bytes queued to the hardware device queue
+ *
+ *     Report the number of bytes queued for sending/completion to the network
+ *     device hardware queue. @bytes should be a good approximation and should
+ *     exactly match netdev_completed_queue() @bytes
+ */
 static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
 {
        netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
@@ -2130,6 +2139,16 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
 #endif
 }
 
+/**
+ *     netdev_completed_queue - report bytes and packets completed by device
+ *     @dev: network device
+ *     @pkts: actual number of packets sent over the medium
+ *     @bytes: actual number of bytes sent over the medium
+ *
+ *     Report the number of bytes and packets transmitted by the network device
+ *     hardware queue over the physical medium, @bytes must exactly match the
+ *     @bytes amount passed to netdev_sent_queue()
+ */
 static inline void netdev_completed_queue(struct net_device *dev,
                                          unsigned int pkts, unsigned int bytes)
 {
@@ -2144,6 +2163,13 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
 #endif
 }
 
+/**
+ *     netdev_reset_queue - reset the packets and bytes count of a network device
+ *     @dev_queue: network device
+ *
+ *     Reset the bytes and packet count of a network device and clear the
+ *     software flow control OFF bit for this network device
+ */
 static inline void netdev_reset_queue(struct net_device *dev_queue)
 {
        netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1969e16d936d9b5cd37c01309df27ef31c9b2437..25a89eaa669de9240036abc04f1385eb168f995e 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3162,16 +3162,14 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
 
        /* If reordering is high then always grow cwnd whenever data is
         * delivered regardless of its ordering. Otherwise stay conservative
-        * and only grow cwnd on in-order delivery in Open state, and retain
-        * cwnd in Disordered state (RFC5681). A stretched ACK with
+        * and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/
         * new SACK or ECE mark may first advance cwnd here and later reduce
         * cwnd in tcp_fastretrans_alert() based on more states.
         */
        if (tcp_sk(sk)->reordering > sysctl_tcp_reordering)
                return flag & FLAG_FORWARD_PROGRESS;
 
-       return inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
-              flag & FLAG_DATA_ACKED;
+       return flag & FLAG_DATA_ACKED;
 }
 
 /* Check that window update is acceptable.
@@ -4141,6 +4139,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
                if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) {
                        __skb_queue_after(&tp->out_of_order_queue, skb1, skb);
                } else {
+                       tcp_grow_window(sk, skb);
                        kfree_skb_partial(skb, fragstolen);
                        skb = NULL;
                }
@@ -4216,8 +4215,10 @@ add_sack:
        if (tcp_is_sack(tp))
                tcp_sack_new_ofo_skb(sk, seq, end_seq);
 end:
-       if (skb)
+       if (skb) {
+               tcp_grow_window(sk, skb);
                skb_set_owner_r(skb, sk);
+       }
 }
 
 static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen,

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a17dda1bbee0704935c92c7d265268fb73c724a1..8df7f64c6db35a0f538bef1fa0206f7826fd1a14 100644 (file)
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -168,16 +168,43 @@ int netlink_remove_tap(struct netlink_tap *nt)
 }
 EXPORT_SYMBOL_GPL(netlink_remove_tap);
 
+static bool netlink_filter_tap(const struct sk_buff *skb)
+{
+       struct sock *sk = skb->sk;
+       bool pass = false;
+
+       /* We take the more conservative approach and
+        * whitelist socket protocols that may pass.
+        */
+       switch (sk->sk_protocol) {
+       case NETLINK_ROUTE:
+       case NETLINK_USERSOCK:
+       case NETLINK_SOCK_DIAG:
+       case NETLINK_NFLOG:
+       case NETLINK_XFRM:
+       case NETLINK_FIB_LOOKUP:
+       case NETLINK_NETFILTER:
+       case NETLINK_GENERIC:
+               pass = true;
+               break;
+       }
+
+       return pass;
+}
+
 static int __netlink_deliver_tap_skb(struct sk_buff *skb,
                                     struct net_device *dev)
 {
        struct sk_buff *nskb;
+       struct sock *sk = skb->sk;
        int ret = -ENOMEM;
 
        dev_hold(dev);
        nskb = skb_clone(skb, GFP_ATOMIC);
        if (nskb) {
                nskb->dev = dev;
+               nskb->protocol = htons((u16) sk->sk_protocol);
+
                ret = dev_queue_xmit(nskb);
                if (unlikely(ret > 0))
                        ret = net_xmit_errno(ret);
@@ -192,6 +219,9 @@ static void __netlink_deliver_tap(struct sk_buff *skb)
        int ret;
        struct netlink_tap *tmp;
 
+       if (!netlink_filter_tap(skb))
+               return;
+
        list_for_each_entry_rcu(tmp, &netlink_tap_all, list) {
                ret = __netlink_deliver_tap_skb(skb, tmp->dev);
                if (unlikely(ret))