8 files changed, 89 insertions, 34 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 70491d9035eb..0c94a1ac2946 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -166,7 +166,7 @@ config IP_PNP_DHCP
 
           If unsure, say Y. Note that if you want to use DHCP, a DHCP server
           must be operating on your network.  Read
-          <file:Documentation/filesystems/nfsroot.txt> for details.
+          <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
 
 config IP_PNP_BOOTP
         bool "IP: BOOTP support"
@@ -181,7 +181,7 @@ config IP_PNP_BOOTP
           does BOOTP itself, providing all necessary information on the kernel
           command line, you can say N here. If unsure, say Y. Note that if you
           want to use BOOTP, a BOOTP server must be operating on your network.
-          Read <file:Documentation/filesystems/nfsroot.txt> for details.
+          Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
 
 config IP_PNP_RARP
         bool "IP: RARP support"
@@ -194,7 +194,7 @@ config IP_PNP_RARP
           older protocol which is being obsoleted by BOOTP and DHCP), say Y
           here. Note that if you want to use RARP, a RARP server must be
           operating on your network. Read
-          <file:Documentation/filesystems/nfsroot.txt> for details.
+          <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
 
 # not yet ready..
 #   bool '    IP: ARP support' CONFIG_IP_PNP_ARP
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index c95cd93acf29..078709233bc4 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -70,6 +70,7 @@
  *                                      bonding can change the skb before
  *                                      sending (e.g. insert 8021q tag).
  *              Harald Welte    :       convert to make use of jenkins hash
+ *              Jesper D. Brouer:       Proxy ARP PVLAN RFC 3069 support.
  */
 
 #include <linux/module.h>
@@ -524,12 +525,15 @@ int arp_bind_neighbour(struct dst_entry *dst)
 /*
  * Check if we can use proxy ARP for this path
  */
-
-static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt)
+static inline int arp_fwd_proxy(struct in_device *in_dev,
+                                struct net_device *dev, struct rtable *rt)
 {
         struct in_device *out_dev;
         int imi, omi = -1;
 
+        if (rt->u.dst.dev == dev)
+                return 0;
+
         if (!IN_DEV_PROXY_ARP(in_dev))
                 return 0;
 
@@ -548,6 +552,43 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt)
 }
 
 /*
+ * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev)
+ *
+ * RFC3069 supports proxy arp replies back to the same interface.  This
+ * is done to support (ethernet) switch features, like RFC 3069, where
+ * the individual ports are not allowed to communicate with each
+ * other, BUT they are allowed to talk to the upstream router.  As
+ * described in RFC 3069, it is possible to allow these hosts to
+ * communicate through the upstream router, by proxy_arp'ing.
+ *
+ * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation"
+ *
+ *  This technology is known by different names:
+ *    In RFC 3069 it is called VLAN Aggregation.
+ *    Cisco and Allied Telesyn call it Private VLAN.
+ *    Hewlett-Packard call it Source-Port filtering or port-isolation.
+ *    Ericsson call it MAC-Forced Forwarding (RFC Draft).
+ *
+ */
+static inline int arp_fwd_pvlan(struct in_device *in_dev,
+                                struct net_device *dev, struct rtable *rt,
+                                __be32 sip, __be32 tip)
+{
+        /* Private VLAN is only concerned about the same ethernet segment */
+        if (rt->u.dst.dev != dev)
+                return 0;
+
+        /* Don't reply on self probes (often done by windowz boxes)*/
+        if (sip == tip)
+                return 0;
+
+        if (IN_DEV_PROXY_ARP_PVLAN(in_dev))
+                return 1;
+        else
+                return 0;
+}
+
+/*
  *      Interface to link layer: send routine and receive handler.
  */
 
@@ -833,8 +874,11 @@ static int arp_process(struct sk_buff *skb)
                         }
                         goto out;
                 } else if (IN_DEV_FORWARD(in_dev)) {
-                            if (addr_type == RTN_UNICAST  && rt->u.dst.dev != dev &&
-                             (arp_fwd_proxy(in_dev, rt) || pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
+                        if (addr_type == RTN_UNICAST  &&
+                            (arp_fwd_proxy(in_dev, dev, rt) ||
+                             arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
+                             pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))
+                        {
                                 n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
                                 if (n)
                                         neigh_release(n);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 040c4f05b653..cd71a3908391 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1408,6 +1408,7 @@ static struct devinet_sysctl_table {
                 DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
                 DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
                 DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
+                DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),
 
                 DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
                 DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 4e08b7f2331c..10a6a604bf32 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1446,7 +1446,7 @@ late_initcall(ip_auto_config);
 
 /*
  *  Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel
- *  command line parameter.  See Documentation/filesystems/nfsroot.txt.
+ *  command line parameter.  See Documentation/filesystems/nfs/nfsroot.txt.
  */
 static int __init ic_proto_name(char *name)
 {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e446496f564f..1cc339441e7d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1988,8 +1988,13 @@ static int __mkroute_input(struct sk_buff *skb,
         if (skb->protocol != htons(ETH_P_IP)) {
                 /* Not IP (i.e. ARP). Do not create route, if it is
                  * invalid for proxy arp. DNAT routes are always valid.
+                 *
+                 * Proxy arp feature have been extended to allow, ARP
+                 * replies back to the same interface, to support
+                 * Private VLAN switch technologies. See arp.c.
                  */
-                if (out_dev == in_dev) {
+                if (out_dev == in_dev &&
+                    IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
                         err = -EINVAL;
                         goto cleanup;
                 }
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 66fd80ef2473..5c24db4a3c91 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -358,7 +358,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
         tcp_select_initial_window(tcp_full_space(sk), req->mss,
                                   &req->rcv_wnd, &req->window_clamp,
-                                  ireq->wscale_ok, &rcv_wscale);
+                                  ireq->wscale_ok, &rcv_wscale,
+                                  dst_metric(&rt->u.dst, RTAX_INITRWND));
 
         ireq->rcv_wscale  = rcv_wscale;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b0a26bb25e2e..d5d69ea8f249 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -536,8 +536,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
                 tp->nonagle &= ~TCP_NAGLE_PUSH;
 }
 
-static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
-                                struct sk_buff *skb)
+static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
 {
         if (flags & MSG_OOB)
                 tp->snd_up = tp->write_seq;
@@ -546,13 +545,13 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
 static inline void tcp_push(struct sock *sk, int flags, int mss_now,
                             int nonagle)
 {
-        struct tcp_sock *tp = tcp_sk(sk);
-
         if (tcp_send_head(sk)) {
-                struct sk_buff *skb = tcp_write_queue_tail(sk);
+                struct tcp_sock *tp = tcp_sk(sk);
+
                 if (!(flags & MSG_MORE) || forced_push(tp))
-                        tcp_mark_push(tp, skb);
-                tcp_mark_urg(tp, flags, skb);
+                        tcp_mark_push(tp, tcp_write_queue_tail(sk));
+
+                tcp_mark_urg(tp, flags);
                 __tcp_push_pending_frames(sk, mss_now,
                                           (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
         }
@@ -877,12 +876,12 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
 #define TCP_PAGE(sk)    (sk->sk_sndmsg_page)
 #define TCP_OFF(sk)     (sk->sk_sndmsg_off)
 
-static inline int select_size(struct sock *sk)
+static inline int select_size(struct sock *sk, int sg)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         int tmp = tp->mss_cache;
 
-        if (sk->sk_route_caps & NETIF_F_SG) {
+        if (sg) {
                 if (sk_can_gso(sk))
                         tmp = 0;
                 else {
@@ -906,7 +905,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
         struct sk_buff *skb;
         int iovlen, flags;
         int mss_now, size_goal;
-        int err, copied;
+        int sg, err, copied;
         long timeo;
 
         lock_sock(sk);
@@ -934,6 +933,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
         if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
                 goto out_err;
 
+        sg = sk->sk_route_caps & NETIF_F_SG;
+
         while (--iovlen >= 0) {
                 int seglen = iov->iov_len;
                 unsigned char __user *from = iov->iov_base;
@@ -959,8 +960,9 @@ new_segment:
                                 if (!sk_stream_memory_free(sk))
                                         goto wait_for_sndbuf;
 
-                                skb = sk_stream_alloc_skb(sk, select_size(sk),
-                                                sk->sk_allocation);
+                                skb = sk_stream_alloc_skb(sk,
+                                                          select_size(sk, sg),
+                                                          sk->sk_allocation);
                                 if (!skb)
                                         goto wait_for_memory;
 
@@ -997,9 +999,7 @@ new_segment:
                                         /* We can extend the last page
                                          * fragment. */
                                         merge = 1;
-                                } else if (i == MAX_SKB_FRAGS ||
-                                           (!i &&
-                                           !(sk->sk_route_caps & NETIF_F_SG))) {
+                                } else if (i == MAX_SKB_FRAGS || !sg) {
                                         /* Need to add new fragment and cannot
                                          * do this because interface is non-SG,
                                          * or because all the page slots are
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 383ce237640f..4a1605d3f909 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -183,7 +183,8 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
  */
 void tcp_select_initial_window(int __space, __u32 mss,
                                __u32 *rcv_wnd, __u32 *window_clamp,
-                               int wscale_ok, __u8 *rcv_wscale)
+                               int wscale_ok, __u8 *rcv_wscale,
+                               __u32 init_rcv_wnd)
 {
         unsigned int space = (__space < 0 ? 0 : __space);
 
@@ -232,7 +233,13 @@ void tcp_select_initial_window(int __space, __u32 mss,
                         init_cwnd = 2;
                 else if (mss > 1460)
                         init_cwnd = 3;
-                if (*rcv_wnd > init_cwnd * mss)
+                /* when initializing use the value from init_rcv_wnd
+                 * rather than the default from above
+                 */
+                if (init_rcv_wnd &&
+                    (*rcv_wnd > init_rcv_wnd * mss))
+                        *rcv_wnd = init_rcv_wnd * mss;
+                else if (*rcv_wnd > init_cwnd * mss)
                         *rcv_wnd = init_cwnd * mss;
         }
 
@@ -1794,11 +1801,6 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
                                int nonagle)
 {
-        struct sk_buff *skb = tcp_send_head(sk);
-
-        if (!skb)
-                return;
-
         /* If we are closed, the bytes will have to remain here.
          * In time closedown will finish, we empty the write queue and
          * all will be happy.
@@ -2422,7 +2424,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
                         &req->rcv_wnd,
                         &req->window_clamp,
                         ireq->wscale_ok,
-                        &rcv_wscale);
+                        &rcv_wscale,
+                        dst_metric(dst, RTAX_INITRWND));
                 ireq->rcv_wscale = rcv_wscale;
         }
 
@@ -2549,7 +2552,8 @@ static void tcp_connect_init(struct sock *sk)
                                   &tp->rcv_wnd,
                                   &tp->window_clamp,
                                   sysctl_tcp_window_scaling,
-                                  &rcv_wscale);
+                                  &rcv_wscale,
+                                  dst_metric(dst, RTAX_INITRWND));
 
         tp->rx_opt.rcv_wscale = rcv_wscale;
         tp->rcv_ssthresh = tp->rcv_wnd;