Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (27 commits)
  af_unix: limit recursion level
  pch_gbe driver: The wrong of initializer entry
  pch_gbe dreiver: chang author
  ucc_geth: fix ucc halt problem in half duplex mode
  inet: Fix __inet_inherit_port() to correctly increment bsockets and num_owners
  ehea: Add some info messages and fix an issue
  hso: fix disable_net
  NET: wan/x25_asy, move lapb_unregister to x25_asy_close_tty
  cxgb4vf: fix setting unicast/multicast addresses ...
  net, ppp: Report correct error code if unit allocation failed
  DECnet: don't leak uninitialized stack byte
  au1000_eth: fix invalid address accessing the MAC enable register
  dccp: fix error in updating the GAR
  tcp: restrict net.ipv4.tcp_adv_win_scale (#20312)
  netns: Don't leak others' openreq-s in proc
  Net: ceph: Makefile: Remove unnessary code
  vhost/net: fix rcu check usage
  econet: fix CVE-2010-3848
  econet: fix CVE-2010-3850
  econet: disallow NULL remote addr for sendmsg(), fixes CVE-2010-3849
  ...

10 files changed, 96 insertions, 83 deletions

diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index aab1cabb8035..5f19415ec9c0 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -1,9 +1,6 @@
 #
 # Makefile for CEPH filesystem.
 #
-
-ifneq ($(KERNELRELEASE),)
-
 obj-$(CONFIG_CEPH_LIB) += libceph.o
 
 libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
@@ -16,22 +13,3 @@ libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
 	ceph_fs.o ceph_strings.o ceph_hash.o \
 	pagevec.o
 
-else
-#Otherwise we were called directly from the command
-# line; invoke the kernel build system.
-
-KERNELDIR ?= /lib/modules/$(shell uname -r)/build
-PWD := $(shell pwd)
-
-default: all
-
-all:
-	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules
-
-modules_install:
-	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install
-
-clean:
-	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
-
-endif
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 265985370fa1..e424a09e83f6 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -239,7 +239,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
 		dccp_update_gsr(sk, seqno);
 
 		if (dh->dccph_type != DCCP_PKT_SYNC &&
-		    (ackno != DCCP_PKT_WITHOUT_ACK_SEQ))
+		    ackno != DCCP_PKT_WITHOUT_ACK_SEQ &&
+		    after48(ackno, dp->dccps_gar))
 			dp->dccps_gar = ackno;
 	} else {
 		unsigned long now = jiffies;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index a76b78de679f..6f97268ed85f 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1556,6 +1556,8 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us
 			if (r_len > sizeof(struct linkinfo_dn))
 				r_len = sizeof(struct linkinfo_dn);
 
+			memset(&link, 0, sizeof(link));
+
 			switch(sock->state) {
 				case SS_CONNECTING:
 					link.idn_linkstate = LL_CONNECTING;
diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c
index f8c1ae4b41f0..13992e1d2726 100644
--- a/net/econet/af_econet.c
+++ b/net/econet/af_econet.c
@@ -31,6 +31,7 @@
 #include <linux/skbuff.h>
 #include <linux/udp.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <net/sock.h>
 #include <net/inet_common.h>
 #include <linux/stat.h>
@@ -276,12 +277,12 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 #endif
 #ifdef CONFIG_ECONET_AUNUDP
 	struct msghdr udpmsg;
-	struct iovec iov[msg->msg_iovlen+1];
+	struct iovec iov[2];
 	struct aunhdr ah;
 	struct sockaddr_in udpdest;
 	__kernel_size_t size;
-	int i;
 	mm_segment_t oldfs;
+	char *userbuf;
 #endif
 
 	/*
@@ -297,23 +298,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	mutex_lock(&econet_mutex);
 
-	if (saddr == NULL) {
-		struct econet_sock *eo = ec_sk(sk);
-
-		addr.station = eo->station;
-		addr.net     = eo->net;
-		port	     = eo->port;
-		cb	     = eo->cb;
-	} else {
-		if (msg->msg_namelen < sizeof(struct sockaddr_ec)) {
-			mutex_unlock(&econet_mutex);
-			return -EINVAL;
-		}
-		addr.station = saddr->addr.station;
-		addr.net = saddr->addr.net;
-		port = saddr->port;
-		cb = saddr->cb;
-	}
+        if (saddr == NULL || msg->msg_namelen < sizeof(struct sockaddr_ec)) {
+                mutex_unlock(&econet_mutex);
+                return -EINVAL;
+        }
+        addr.station = saddr->addr.station;
+        addr.net = saddr->addr.net;
+        port = saddr->port;
+        cb = saddr->cb;
 
 	/* Look for a device with the right network number. */
 	dev = net2dev_map[addr.net];
@@ -328,17 +320,17 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 		}
 	}
 
-	if (len + 15 > dev->mtu) {
-		mutex_unlock(&econet_mutex);
-		return -EMSGSIZE;
-	}
-
 	if (dev->type == ARPHRD_ECONET) {
 		/* Real hardware Econet.  We're not worthy etc. */
 #ifdef CONFIG_ECONET_NATIVE
 		unsigned short proto = 0;
 		int res;
 
+		if (len + 15 > dev->mtu) {
+			mutex_unlock(&econet_mutex);
+			return -EMSGSIZE;
+		}
+
 		dev_hold(dev);
 
 		skb = sock_alloc_send_skb(sk, len+LL_ALLOCATED_SPACE(dev),
@@ -351,7 +343,6 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 		eb = (struct ec_cb *)&skb->cb;
 
-		/* BUG: saddr may be NULL */
 		eb->cookie = saddr->cookie;
 		eb->sec = *saddr;
 		eb->sent = ec_tx_done;
@@ -415,6 +406,11 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 		return -ENETDOWN;		/* No socket - can't send */
 	}
 
+	if (len > 32768) {
+		err = -E2BIG;
+		goto error;
+	}
+
 	/* Make up a UDP datagram and hand it off to some higher intellect. */
 
 	memset(&udpdest, 0, sizeof(udpdest));
@@ -446,36 +442,26 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	/* tack our header on the front of the iovec */
 	size = sizeof(struct aunhdr);
-	/*
-	 * XXX: that is b0rken.  We can't mix userland and kernel pointers
-	 * in iovec, since on a lot of platforms copy_from_user() will
-	 * *not* work with the kernel and userland ones at the same time,
-	 * regardless of what we do with set_fs().  And we are talking about
-	 * econet-over-ethernet here, so "it's only ARM anyway" doesn't
-	 * apply.  Any suggestions on fixing that code?		-- AV
-	 */
 	iov[0].iov_base = (void *)&ah;
 	iov[0].iov_len = size;
-	for (i = 0; i < msg->msg_iovlen; i++) {
-		void __user *base = msg->msg_iov[i].iov_base;
-		size_t iov_len = msg->msg_iov[i].iov_len;
-		/* Check it now since we switch to KERNEL_DS later. */
-		if (!access_ok(VERIFY_READ, base, iov_len)) {
-			mutex_unlock(&econet_mutex);
-			return -EFAULT;
-		}
-		iov[i+1].iov_base = base;
-		iov[i+1].iov_len = iov_len;
-		size += iov_len;
+
+	userbuf = vmalloc(len);
+	if (userbuf == NULL) {
+		err = -ENOMEM;
+		goto error;
 	}
 
+	iov[1].iov_base = userbuf;
+	iov[1].iov_len = len;
+	err = memcpy_fromiovec(userbuf, msg->msg_iov, len);
+	if (err)
+		goto error_free_buf;
+
 	/* Get a skbuff (no data, just holds our cb information) */
 	if ((skb = sock_alloc_send_skb(sk, 0,
 				       msg->msg_flags & MSG_DONTWAIT,
-				       &err)) == NULL) {
-		mutex_unlock(&econet_mutex);
-		return err;
-	}
+				       &err)) == NULL)
+		goto error_free_buf;
 
 	eb = (struct ec_cb *)&skb->cb;
 
@@ -491,7 +477,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 	udpmsg.msg_name = (void *)&udpdest;
 	udpmsg.msg_namelen = sizeof(udpdest);
 	udpmsg.msg_iov = &iov[0];
-	udpmsg.msg_iovlen = msg->msg_iovlen + 1;
+	udpmsg.msg_iovlen = 2;
 	udpmsg.msg_control = NULL;
 	udpmsg.msg_controllen = 0;
 	udpmsg.msg_flags=0;
@@ -499,9 +485,13 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 	oldfs = get_fs(); set_fs(KERNEL_DS);	/* More privs :-) */
 	err = sock_sendmsg(udpsock, &udpmsg, size);
 	set_fs(oldfs);
+
+error_free_buf:
+	vfree(userbuf);
 #else
 	err = -EPROTOTYPE;
 #endif
+	error:
 	mutex_unlock(&econet_mutex);
 
 	return err;
@@ -671,6 +661,9 @@ static int ec_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg)
 	err = 0;
 	switch (cmd) {
 	case SIOCSIFADDR:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+
 		edev = dev->ec_ptr;
 		if (edev == NULL) {
 			/* Magic up a new one. */
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 1b344f30b463..3c0369a3a663 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -133,8 +133,7 @@ int __inet_inherit_port(struct sock *sk, struct sock *child)
 			}
 		}
 	}
-	sk_add_bind_node(child, &tb->owners);
-	inet_csk(child)->icsk_bind_hash = tb;
+	inet_bind_hash(child, tb, port);
 	spin_unlock(&head->lock);
 
 	return 0;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e91911d7aae2..1b4ec21497a4 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -26,6 +26,8 @@ static int zero;
 static int tcp_retr1_max = 255;
 static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
+static int tcp_adv_win_scale_min = -31;
+static int tcp_adv_win_scale_max = 31;
 
 /* Update system visible IP port range */
 static void set_local_port_range(int range[2])
@@ -426,7 +428,9 @@ static struct ctl_table ipv4_table[] = {
 		.data		= &sysctl_tcp_adv_win_scale,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_adv_win_scale_min,
+		.extra2		= &tcp_adv_win_scale_max,
 	},
 	{
 		.procname	= "tcp_tw_reuse",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 081419969485..f15c36a706ec 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2246,7 +2246,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		/* Values greater than interface MTU won't take effect. However
 		 * at the point when this call is done we typically don't yet
 		 * know which interface is going to be used */
-		if (val < 64 || val > MAX_TCP_WINDOW) {
+		if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
 			err = -EINVAL;
 			break;
 		}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 69ccbc1dde9c..e13da6de1fc7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2043,7 +2043,9 @@ get_req:
 	}
 get_sk:
 	sk_nulls_for_each_from(sk, node) {
-		if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		if (sk->sk_family == st->family) {
 			cur = sk;
 			goto out;
 		}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3c95304a0817..2268e6798124 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1343,9 +1343,25 @@ static void unix_destruct_scm(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+#define MAX_RECURSION_LEVEL 4
+
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
 	int i;
+	unsigned char max_level = 0;
+	int unix_sock_count = 0;
+
+	for (i = scm->fp->count - 1; i >= 0; i--) {
+		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
+
+		if (sk) {
+			unix_sock_count++;
+			max_level = max(max_level,
+					unix_sk(sk)->recursion_level);
+		}
+	}
+	if (unlikely(max_level > MAX_RECURSION_LEVEL))
+		return -ETOOMANYREFS;
 
 	/*
 	 * Need to duplicate file references for the sake of garbage
@@ -1356,9 +1372,11 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	if (!UNIXCB(skb).fp)
 		return -ENOMEM;
 
-	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_inflight(scm->fp->fp[i]);
-	return 0;
+	if (unix_sock_count) {
+		for (i = scm->fp->count - 1; i >= 0; i--)
+			unix_inflight(scm->fp->fp[i]);
+	}
+	return max_level;
 }
 
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
@@ -1393,6 +1411,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sk_buff *skb;
 	long timeo;
 	struct scm_cookie tmp_scm;
+	int max_level;
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1431,8 +1450,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		goto out;
 
 	err = unix_scm_to_skb(siocb->scm, skb, true);
-	if (err)
+	if (err < 0)
 		goto out_free;
+	max_level = err + 1;
 	unix_get_secdata(siocb->scm, skb);
 
 	skb_reset_transport_header(skb);
@@ -1514,6 +1534,8 @@ restart:
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
+	if (max_level > unix_sk(other)->recursion_level)
+		unix_sk(other)->recursion_level = max_level;
 	unix_state_unlock(other);
 	other->sk_data_ready(other, len);
 	sock_put(other);
@@ -1544,6 +1566,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	int sent = 0;
 	struct scm_cookie tmp_scm;
 	bool fds_sent = false;
+	int max_level;
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1607,10 +1630,11 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 		/* Only send the fds in the first buffer */
 		err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
-		if (err) {
+		if (err < 0) {
 			kfree_skb(skb);
 			goto out_err;
 		}
+		max_level = err + 1;
 		fds_sent = true;
 
 		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
@@ -1626,6 +1650,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto pipe_err_free;
 
 		skb_queue_tail(&other->sk_receive_queue, skb);
+		if (max_level > unix_sk(other)->recursion_level)
+			unix_sk(other)->recursion_level = max_level;
 		unix_state_unlock(other);
 		other->sk_data_ready(other, size);
 		sent += size;
@@ -1845,6 +1871,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		unix_state_lock(sk);
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		if (skb == NULL) {
+			unix_sk(sk)->recursion_level = 0;
 			if (copied >= target)
 				goto unlock;
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index c8df6fda0b1f..f89f83bf828e 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -96,7 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
 unsigned int unix_tot_inflight;
 
 
-static struct sock *unix_get_socket(struct file *filp)
+struct sock *unix_get_socket(struct file *filp)
 {
 	struct sock *u_sock = NULL;
 	struct inode *inode = filp->f_path.dentry->d_inode;
@@ -259,9 +259,16 @@ static void inc_inflight_move_tail(struct unix_sock *u)
 }
 
 static bool gc_in_progress = false;
+#define UNIX_INFLIGHT_TRIGGER_GC 16000
 
 void wait_for_unix_gc(void)
 {
+	/*
+	 * If number of inflight sockets is insane,
+	 * force a garbage collect right now.
+	 */
+	if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
+		unix_gc();
 	wait_event(unix_gc_wait, gc_in_progress == false);
 }