Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.26

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.26: (1090 commits)
  [NET]: Fix and allocate less memory for ->priv'less netdevices
  [IPV6]: Fix dangling references on error in fib6_add().
  [NETLABEL]: Fix NULL deref in netlbl_unlabel_staticlist_gen() if ifindex not found
  [PKT_SCHED]: Fix datalen check in tcf_simp_init().
  [INET]: Uninline the __inet_inherit_port call.
  [INET]: Drop the inet_inherit_port() call.
  SCTP: Initialize partial_bytes_acked to 0, when all of the data is acked.
  [netdrvr] forcedeth: internal simplifications; changelog removal
  phylib: factor out get_phy_id from within get_phy_device
  PHY: add BCM5464 support to broadcom PHY driver
  cxgb3: Fix __must_check warning with dev_dbg.
  tc35815: Statistics cleanup
  natsemi: fix MMIO for PPC 44x platforms
  [TIPC]: Cleanup of TIPC reference table code
  [TIPC]: Optimized initialization of TIPC reference table
  [TIPC]: Remove inlining of reference table locking routines
  e1000: convert uint16_t style integers to u16
  ixgb: convert uint16_t style integers to u16
  sb1000.c: make const arrays static
  sb1000.c: stop inlining largish static functions
  ...

1 files changed, 186 insertions, 179 deletions

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index bf2a686aa13d..06de9d0e1f6b 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -16,7 +16,6 @@
  *
  *	FIXME: Make the setsockopt code POSIX compliant: That is
  *
- *	o	Return -EINVAL for setsockopt of short lengths
  *	o	Truncate getsockopt returns
  *	o	Return an optlen of the truncated length if need be
  *
@@ -33,6 +32,7 @@
 #include <linux/sockios.h>
 #include <linux/net.h>
 #include <linux/in6.h>
+#include <linux/mroute6.h>
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
 #include <linux/init.h>
@@ -57,118 +57,6 @@
 
 DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics) __read_mostly;
 
-static struct inet6_protocol *ipv6_gso_pull_exthdrs(struct sk_buff *skb,
-						    int proto)
-{
-	struct inet6_protocol *ops = NULL;
-
-	for (;;) {
-		struct ipv6_opt_hdr *opth;
-		int len;
-
-		if (proto != NEXTHDR_HOP) {
-			ops = rcu_dereference(inet6_protos[proto]);
-
-			if (unlikely(!ops))
-				break;
-
-			if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
-				break;
-		}
-
-		if (unlikely(!pskb_may_pull(skb, 8)))
-			break;
-
-		opth = (void *)skb->data;
-		len = opth->hdrlen * 8 + 8;
-
-		if (unlikely(!pskb_may_pull(skb, len)))
-			break;
-
-		proto = opth->nexthdr;
-		__skb_pull(skb, len);
-	}
-
-	return ops;
-}
-
-static int ipv6_gso_send_check(struct sk_buff *skb)
-{
-	struct ipv6hdr *ipv6h;
-	struct inet6_protocol *ops;
-	int err = -EINVAL;
-
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		goto out;
-
-	ipv6h = ipv6_hdr(skb);
-	__skb_pull(skb, sizeof(*ipv6h));
-	err = -EPROTONOSUPPORT;
-
-	rcu_read_lock();
-	ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
-	if (likely(ops && ops->gso_send_check)) {
-		skb_reset_transport_header(skb);
-		err = ops->gso_send_check(skb);
-	}
-	rcu_read_unlock();
-
-out:
-	return err;
-}
-
-static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
-{
-	struct sk_buff *segs = ERR_PTR(-EINVAL);
-	struct ipv6hdr *ipv6h;
-	struct inet6_protocol *ops;
-
-	if (!(features & NETIF_F_V6_CSUM))
-		features &= ~NETIF_F_SG;
-
-	if (unlikely(skb_shinfo(skb)->gso_type &
-		     ~(SKB_GSO_UDP |
-		       SKB_GSO_DODGY |
-		       SKB_GSO_TCP_ECN |
-		       SKB_GSO_TCPV6 |
-		       0)))
-		goto out;
-
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		goto out;
-
-	ipv6h = ipv6_hdr(skb);
-	__skb_pull(skb, sizeof(*ipv6h));
-	segs = ERR_PTR(-EPROTONOSUPPORT);
-
-	rcu_read_lock();
-	ops = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
-	if (likely(ops && ops->gso_segment)) {
-		skb_reset_transport_header(skb);
-		segs = ops->gso_segment(skb, features);
-	}
-	rcu_read_unlock();
-
-	if (unlikely(IS_ERR(segs)))
-		goto out;
-
-	for (skb = segs; skb; skb = skb->next) {
-		ipv6h = ipv6_hdr(skb);
-		ipv6h->payload_len = htons(skb->len - skb->mac_len -
-					   sizeof(*ipv6h));
-	}
-
-out:
-	return segs;
-}
-
-static struct packet_type ipv6_packet_type = {
-	.type = __constant_htons(ETH_P_IPV6),
-	.func = ipv6_rcv,
-	.gso_send_check = ipv6_gso_send_check,
-	.gso_segment = ipv6_gso_segment,
-};
-
 struct ip6_ra_chain *ip6_ra_chain;
 DEFINE_RWLOCK(ip6_ra_lock);
 
@@ -215,25 +103,59 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *))
 	return 0;
 }
 
+static
+struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
+					   struct ipv6_txoptions *opt)
+{
+	if (inet_sk(sk)->is_icsk) {
+		if (opt &&
+		    !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
+		    inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
+			struct inet_connection_sock *icsk = inet_csk(sk);
+			icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
+			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
+		}
+		opt = xchg(&inet6_sk(sk)->opt, opt);
+	} else {
+		write_lock(&sk->sk_dst_lock);
+		opt = xchg(&inet6_sk(sk)->opt, opt);
+		write_unlock(&sk->sk_dst_lock);
+	}
+	sk_dst_reset(sk);
+
+	return opt;
+}
+
 static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, int optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net *net = sock_net(sk);
 	int val, valbool;
 	int retv = -ENOPROTOOPT;
 
 	if (optval == NULL)
 		val=0;
-	else if (get_user(val, (int __user *) optval))
-		return -EFAULT;
+	else {
+		if (optlen >= sizeof(int)) {
+			if (get_user(val, (int __user *) optval))
+				return -EFAULT;
+		} else
+			val = 0;
+	}
 
 	valbool = (val!=0);
 
+	if (ip6_mroute_opt(optname))
+		return ip6_mroute_setsockopt(sk, optname, optval, optlen);
+
 	lock_sock(sk);
 
 	switch (optname) {
 
 	case IPV6_ADDRFORM:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		if (val == PF_INET) {
 			struct ipv6_txoptions *opt;
 			struct sk_buff *pktopt;
@@ -266,10 +188,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 			if (sk->sk_protocol == IPPROTO_TCP) {
 				struct inet_connection_sock *icsk = inet_csk(sk);
-
 				local_bh_disable();
-				sock_prot_inuse_add(sk->sk_prot, -1);
-				sock_prot_inuse_add(&tcp_prot, 1);
+				sock_prot_inuse_add(net, sk->sk_prot, -1);
+				sock_prot_inuse_add(net, &tcp_prot, 1);
 				local_bh_enable();
 				sk->sk_prot = &tcp_prot;
 				icsk->icsk_af_ops = &ipv4_specific;
@@ -282,8 +203,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				if (sk->sk_protocol == IPPROTO_UDPLITE)
 					prot = &udplite_prot;
 				local_bh_disable();
-				sock_prot_inuse_add(sk->sk_prot, -1);
-				sock_prot_inuse_add(prot, 1);
+				sock_prot_inuse_add(net, sk->sk_prot, -1);
+				sock_prot_inuse_add(net, prot, 1);
 				local_bh_enable();
 				sk->sk_prot = prot;
 				sk->sk_socket->ops = &inet_dgram_ops;
@@ -309,63 +230,86 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		goto e_inval;
 
 	case IPV6_V6ONLY:
-		if (inet_sk(sk)->num)
+		if (optlen < sizeof(int) ||
+		    inet_sk(sk)->num)
 			goto e_inval;
 		np->ipv6only = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_RECVPKTINFO:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.rxinfo = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_2292PKTINFO:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.rxoinfo = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_RECVHOPLIMIT:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.rxhlim = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_2292HOPLIMIT:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.rxohlim = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_RECVRTHDR:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.srcrt = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_2292RTHDR:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.osrcrt = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_RECVHOPOPTS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.hopopts = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_2292HOPOPTS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.ohopopts = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_RECVDSTOPTS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.dstopts = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_2292DSTOPTS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.odstopts = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_TCLASS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		if (val < -1 || val > 0xff)
 			goto e_inval;
 		np->tclass = val;
@@ -373,11 +317,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_RECVTCLASS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.rxtclass = valbool;
 		retv = 0;
 		break;
 
 	case IPV6_FLOWINFO:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->rxopt.bits.rxflow = valbool;
 		retv = 0;
 		break;
@@ -396,9 +344,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW))
 			break;
 
-		retv = -EINVAL;
-		if (optlen & 0x7 || optlen > 8 * 255)
-			break;
+		if (optlen < sizeof(struct ipv6_opt_hdr) ||
+		    optlen & 0x7 || optlen > 8 * 255)
+			goto e_inval;
 
 		opt = ipv6_renew_options(sk, np->opt, optname,
 					 (struct ipv6_opt_hdr __user *)optval,
@@ -426,25 +374,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		}
 
 		retv = 0;
-		if (inet_sk(sk)->is_icsk) {
-			if (opt) {
-				struct inet_connection_sock *icsk = inet_csk(sk);
-				if (!((1 << sk->sk_state) &
-				      (TCPF_LISTEN | TCPF_CLOSE))
-				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
-					icsk->icsk_ext_hdr_len =
-						opt->opt_flen + opt->opt_nflen;
-					icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
-				}
-			}
-			opt = xchg(&np->opt, opt);
-			sk_dst_reset(sk);
-		} else {
-			write_lock(&sk->sk_dst_lock);
-			opt = xchg(&np->opt, opt);
-			write_unlock(&sk->sk_dst_lock);
-			sk_dst_reset(sk);
-		}
+		opt = ipv6_update_options(sk, opt);
 sticky_done:
 		if (opt)
 			sock_kfree_s(sk, opt, opt->tot_len);
@@ -490,32 +420,15 @@ sticky_done:
 			goto done;
 update:
 		retv = 0;
-		if (inet_sk(sk)->is_icsk) {
-			if (opt) {
-				struct inet_connection_sock *icsk = inet_csk(sk);
-				if (!((1 << sk->sk_state) &
-				      (TCPF_LISTEN | TCPF_CLOSE))
-				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
-					icsk->icsk_ext_hdr_len =
-						opt->opt_flen + opt->opt_nflen;
-					icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
-				}
-			}
-			opt = xchg(&np->opt, opt);
-			sk_dst_reset(sk);
-		} else {
-			write_lock(&sk->sk_dst_lock);
-			opt = xchg(&np->opt, opt);
-			write_unlock(&sk->sk_dst_lock);
-			sk_dst_reset(sk);
-		}
-
+		opt = ipv6_update_options(sk, opt);
 done:
 		if (opt)
 			sock_kfree_s(sk, opt, opt->tot_len);
 		break;
 	}
 	case IPV6_UNICAST_HOPS:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		if (val > 255 || val < -1)
 			goto e_inval;
 		np->hop_limit = val;
@@ -525,6 +438,8 @@ done:
 	case IPV6_MULTICAST_HOPS:
 		if (sk->sk_type == SOCK_STREAM)
 			goto e_inval;
+		if (optlen < sizeof(int))
+			goto e_inval;
 		if (val > 255 || val < -1)
 			goto e_inval;
 		np->mcast_hops = val;
@@ -532,6 +447,8 @@ done:
 		break;
 
 	case IPV6_MULTICAST_LOOP:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->mc_loop = valbool;
 		retv = 0;
 		break;
@@ -539,12 +456,14 @@ done:
 	case IPV6_MULTICAST_IF:
 		if (sk->sk_type == SOCK_STREAM)
 			goto e_inval;
+		if (optlen < sizeof(int))
+			goto e_inval;
 
 		if (val) {
 			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
 				goto e_inval;
 
-			if (__dev_get_by_index(&init_net, val) == NULL) {
+			if (__dev_get_by_index(net, val) == NULL) {
 				retv = -ENODEV;
 				break;
 			}
@@ -557,6 +476,9 @@ done:
 	{
 		struct ipv6_mreq mreq;
 
+		if (optlen < sizeof(struct ipv6_mreq))
+			goto e_inval;
+
 		retv = -EPROTO;
 		if (inet_sk(sk)->is_icsk)
 			break;
@@ -576,7 +498,7 @@ done:
 	{
 		struct ipv6_mreq mreq;
 
-		if (optlen != sizeof(struct ipv6_mreq))
+		if (optlen < sizeof(struct ipv6_mreq))
 			goto e_inval;
 
 		retv = -EFAULT;
@@ -595,6 +517,9 @@ done:
 		struct group_req greq;
 		struct sockaddr_in6 *psin6;
 
+		if (optlen < sizeof(struct group_req))
+			goto e_inval;
+
 		retv = -EFAULT;
 		if (copy_from_user(&greq, optval, sizeof(struct group_req)))
 			break;
@@ -619,7 +544,7 @@ done:
 		struct group_source_req greqs;
 		int omode, add;
 
-		if (optlen != sizeof(struct group_source_req))
+		if (optlen < sizeof(struct group_source_req))
 			goto e_inval;
 		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
 			retv = -EFAULT;
@@ -693,27 +618,37 @@ done:
 		break;
 	}
 	case IPV6_ROUTER_ALERT:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		retv = ip6_ra_control(sk, val, NULL);
 		break;
 	case IPV6_MTU_DISCOVER:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		if (val<0 || val>3)
 			goto e_inval;
 		np->pmtudisc = val;
 		retv = 0;
 		break;
 	case IPV6_MTU:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		if (val && val < IPV6_MIN_MTU)
 			goto e_inval;
 		np->frag_size = val;
 		retv = 0;
 		break;
 	case IPV6_RECVERR:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->recverr = valbool;
 		if (!val)
 			skb_queue_purge(&sk->sk_error_queue);
 		retv = 0;
 		break;
 	case IPV6_FLOWINFO_SEND:
+		if (optlen < sizeof(int))
+			goto e_inval;
 		np->sndflow = valbool;
 		retv = 0;
 		break;
@@ -728,7 +663,70 @@ done:
 		retv = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
+	case IPV6_ADDR_PREFERENCES:
+	    {
+		unsigned int pref = 0;
+		unsigned int prefmask = ~0;
+
+		if (optlen < sizeof(int))
+			goto e_inval;
+
+		retv = -EINVAL;
+
+		/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
+		switch (val & (IPV6_PREFER_SRC_PUBLIC|
+			       IPV6_PREFER_SRC_TMP|
+			       IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
+		case IPV6_PREFER_SRC_PUBLIC:
+			pref |= IPV6_PREFER_SRC_PUBLIC;
+			break;
+		case IPV6_PREFER_SRC_TMP:
+			pref |= IPV6_PREFER_SRC_TMP;
+			break;
+		case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
+			break;
+		case 0:
+			goto pref_skip_pubtmp;
+		default:
+			goto e_inval;
+		}
+
+		prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
+			      IPV6_PREFER_SRC_TMP);
+pref_skip_pubtmp:
+
+		/* check HOME/COA conflicts */
+		switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
+		case IPV6_PREFER_SRC_HOME:
+			break;
+		case IPV6_PREFER_SRC_COA:
+			pref |= IPV6_PREFER_SRC_COA;
+		case 0:
+			goto pref_skip_coa;
+		default:
+			goto e_inval;
+		}
+
+		prefmask &= ~IPV6_PREFER_SRC_COA;
+pref_skip_coa:
+
+		/* check CGA/NONCGA conflicts */
+		switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
+		case IPV6_PREFER_SRC_CGA:
+		case IPV6_PREFER_SRC_NONCGA:
+		case 0:
+			break;
+		default:
+			goto e_inval;
+		}
+
+		np->srcprefs = (np->srcprefs & prefmask) | pref;
+		retv = 0;
+
+		break;
+	    }
 	}
+
 	release_sock(sk);
 
 	return retv;
@@ -839,6 +837,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	int len;
 	int val;
 
+	if (ip6_mroute_opt(optname))
+		return ip6_mroute_getsockopt(sk, optname, optval, optlen);
+
 	if (get_user(len, optlen))
 		return -EFAULT;
 	switch (optname) {
@@ -1015,9 +1016,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		dst = sk_dst_get(sk);
 		if (dst) {
 			if (val < 0)
-				val = dst_metric(dst, RTAX_HOPLIMIT);
-			if (val < 0)
-				val = ipv6_get_hoplimit(dst->dev);
+				val = ip6_dst_hoplimit(dst);
 			dst_release(dst);
 		}
 		if (val < 0)
@@ -1045,6 +1044,24 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		val = np->sndflow;
 		break;
 
+	case IPV6_ADDR_PREFERENCES:
+		val = 0;
+
+		if (np->srcprefs & IPV6_PREFER_SRC_TMP)
+			val |= IPV6_PREFER_SRC_TMP;
+		else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC)
+			val |= IPV6_PREFER_SRC_PUBLIC;
+		else {
+			/* XXX: should we return system default? */
+			val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT;
+		}
+
+		if (np->srcprefs & IPV6_PREFER_SRC_COA)
+			val |= IPV6_PREFER_SRC_COA;
+		else
+			val |= IPV6_PREFER_SRC_HOME;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -1128,13 +1145,3 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_ipv6_getsockopt);
 #endif
 
-int __init ipv6_packet_init(void)
-{
-	dev_add_pack(&ipv6_packet_type);
-	return 0;
-}
-
-void ipv6_packet_cleanup(void)
-{
-	dev_remove_pack(&ipv6_packet_type);
-}