net: socket ioctl to reset connections matching local address

Introduce a new socket ioctl, SIOCKILLADDR, that nukes all sockets
bound to the same local address. This is useful in situations with
dynamic IPs, to kill stuck connections.

Signed-off-by: Brian Swetland <swetland@google.com>

net: fix tcp_v4_nuke_addr

Signed-off-by: Dima Zavin <dima@android.com>

net: ipv4: Fix a spinlock recursion bug in tcp_v4_nuke.

We can't hold the lock while calling to tcp_done(), so we drop
it before calling. We then have to start at the top of the chain again.

Signed-off-by: Dima Zavin <dima@android.com>

net: ipv4: Fix race in tcp_v4_nuke_addr().

To fix a recursive deadlock in 2.6.29, we stopped holding the hash table lock
across tcp_done() calls. This fixed the deadlock, but introduced a race where
the socket could die or change state.

Fix: Before unlocking the hash table, we grab a reference to the socket. We
can then unlock the hash table without risk of the socket going away. We then
lock the socket, which is safe because it is pinned. We can then call
tcp_done() without recursive deadlock and without race. Upon return, we unlock
the socket and then unpin it, killing it.

Change-Id: Idcdae072b48238b01bdbc8823b60310f1976e045
Signed-off-by: Robert Love <rlove@google.com>
Acked-by: Dima Zavin <dima@android.com>

ipv4: disable bottom halves around call to tcp_done().

Signed-off-by: Robert Love <rlove@google.com>
Signed-off-by: Colin Cross <ccross@android.com>

ipv4: Move sk_error_report inside bh_lock_sock in tcp_v4_nuke_addr

When sk_error_report is called, it wakes up the user-space thread, which then
calls tcp_close.  When the tcp_close is interrupted by the tcp_v4_nuke_addr
ioctl thread running tcp_done, it leaks 392 bytes and triggers a WARN_ON.

This patch moves the call to sk_error_report inside the bh_lock_sock, which
matches the locking used in tcp_v4_err.

Signed-off-by: Colin Cross <ccross@android.com>

3 files changed, 52 insertions, 1 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index dac2c6b7c9e6..08b8f8f00636 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -908,6 +908,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCSIFPFLAGS:
 	case SIOCGIFPFLAGS:
 	case SIOCSIFFLAGS:
+	case SIOCKILLADDR:
 		err = devinet_ioctl(net, cmd, (void __user *)arg);
 		break;
 	default:
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index bc19bd06dd00..8d40ca19326b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -59,6 +59,7 @@
 
 #include <net/arp.h>
 #include <net/ip.h>
+#include <net/tcp.h>
 #include <net/route.h>
 #include <net/ip_fib.h>
 #include <net/rtnetlink.h>
@@ -735,6 +736,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSIFBRDADDR:	/* Set the broadcast address */
 	case SIOCSIFDSTADDR:	/* Set the destination address */
 	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
+	case SIOCKILLADDR:	/* Nuke all sockets on this address */
 		ret = -EACCES;
 		if (!capable(CAP_NET_ADMIN))
 			goto out;
@@ -786,7 +788,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	}
 
 	ret = -EADDRNOTAVAIL;
-	if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
+	if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS
+	    && cmd != SIOCKILLADDR)
 		goto done;
 
 	switch (cmd) {
@@ -912,6 +915,10 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 			inet_insert_ifa(ifa);
 		}
 		break;
+	case SIOCKILLADDR:	/* Nuke all connections on this address */
+		ret = 0;
+		tcp_v4_nuke_addr(sin->sin_addr.s_addr);
+		break;
 	}
 done:
 	rtnl_unlock();
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7963e03f1068..11b38565e368 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1971,6 +1971,49 @@ void tcp_v4_destroy_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 
+/*
+ * tcp_v4_nuke_addr - destroy all sockets on the given local address
+ */
+void tcp_v4_nuke_addr(__u32 saddr)
+{
+	unsigned int bucket;
+
+	for (bucket = 0; bucket < tcp_hashinfo.ehash_mask; bucket++) {
+		struct hlist_nulls_node *node;
+		struct sock *sk;
+		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, bucket);
+
+restart:
+		spin_lock_bh(lock);
+		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[bucket].chain) {
+			struct inet_sock *inet = inet_sk(sk);
+
+			if (inet->inet_rcv_saddr != saddr)
+				continue;
+			if (sysctl_ip_dynaddr && sk->sk_state == TCP_SYN_SENT)
+				continue;
+			if (sock_flag(sk, SOCK_DEAD))
+				continue;
+
+			sock_hold(sk);
+			spin_unlock_bh(lock);
+
+			local_bh_disable();
+			bh_lock_sock(sk);
+			sk->sk_err = ETIMEDOUT;
+			sk->sk_error_report(sk);
+
+			tcp_done(sk);
+			bh_unlock_sock(sk);
+			local_bh_enable();
+			sock_put(sk);
+
+			goto restart;
+		}
+		spin_unlock_bh(lock);
+	}
+}
+
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */