Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [VLAN]: Fix net_device leak.
  [PPP] generic: Fix receive path data clobbering & non-linear handling
  [PPP] generic: Call skb_cow_head before scribbling over skb
  [NET] skbuff: Add skb_cow_head
  [BRIDGE]: Kill clone argument to br_flood_*
  [PPP] pppoe: Fill in header directly in __pppoe_xmit
  [PPP] pppoe: Fix data clobbering in __pppoe_xmit and return value
  [PPP] pppoe: Fix skb_unshare_check call position
  [SCTP]: Convert bind_addr_list locking to RCU
  [SCTP]: Add RCU synchronization around sctp_localaddr_list
  [PKT_SCHED]: sch_cbq.c: Shut up uninitialized variable warning
  [PKTGEN]: srcmac fix
  [IPV6]: Fix source address selection.
  [IPV4]: Just increment OutDatagrams once per a datagram.
  [IPV6]: Just increment OutDatagrams once per a datagram.
  [IPV6]: Fix unbalanced socket reference with MSG_CONFIRM.
  [NET_SCHED] protect action config/dump from irqs
  [NET]: Fix two issues wrt. SO_BINDTODEVICE.

drivers/net/ppp_generic.c

@@ -899,17 +899,9 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Put the 2-byte PPP protocol number on the front,
 	   making sure there is room for the address and control fields. */
-	if (skb_headroom(skb) < PPP_HDRLEN) {
+	if (skb_cow_head(skb, PPP_HDRLEN))
-		struct sk_buff *ns;
+		goto outf;
 
-		ns = alloc_skb(skb->len + dev->hard_header_len, GFP_ATOMIC);
-		if (ns == 0)
-			goto outf;
-		skb_reserve(ns, dev->hard_header_len);
-		skb_copy_bits(skb, 0, skb_put(ns, skb->len), skb->len);
-		kfree_skb(skb);
-		skb = ns;
-	}
 	pp = skb_push(skb, 2);
 	proto = npindex_to_proto[npi];
 	pp[0] = proto >> 8;
@@ -1533,7 +1525,7 @@ ppp_input_error(struct ppp_channel *chan, int code)
 static void
 ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 {
-	if (skb->len >= 2) {
+	if (pskb_may_pull(skb, 2)) {
 #ifdef CONFIG_PPP_MULTILINK
 		/* XXX do channel-level decompression here */
 		if (PPP_PROTO(skb) == PPP_MP)
@@ -1585,7 +1577,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 		if (ppp->vj == 0 || (ppp->flags & SC_REJ_COMP_TCP))
 			goto err;
 
-		if (skb_tailroom(skb) < 124) {
+		if (skb_tailroom(skb) < 124 || skb_cloned(skb)) {
 			/* copy to a new sk_buff with more tailroom */
 			ns = dev_alloc_skb(skb->len + 128);
 			if (ns == 0) {
@@ -1656,23 +1648,29 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 		/* check if the packet passes the pass and active filters */
 		/* the filter instructions are constructed assuming
 		   a four-byte PPP header on each packet */
-		*skb_push(skb, 2) = 0;
+		if (ppp->pass_filter || ppp->active_filter) {
-		if (ppp->pass_filter
+			if (skb_cloned(skb) &&
-		    && sk_run_filter(skb, ppp->pass_filter,
+			    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
-				     ppp->pass_len) == 0) {
+				goto err;
-			if (ppp->debug & 1)
+
-				printk(KERN_DEBUG "PPP: inbound frame not passed\n");
+			*skb_push(skb, 2) = 0;
-			kfree_skb(skb);
+			if (ppp->pass_filter
-			return;
+			    && sk_run_filter(skb, ppp->pass_filter,
-		}
+					     ppp->pass_len) == 0) {
-		if (!(ppp->active_filter
+				if (ppp->debug & 1)
-		      && sk_run_filter(skb, ppp->active_filter,
+					printk(KERN_DEBUG "PPP: inbound frame "
-				       ppp->active_len) == 0))
+					       "not passed\n");
-			ppp->last_recv = jiffies;
+				kfree_skb(skb);
-		skb_pull(skb, 2);
+				return;
-#else
+			}
-		ppp->last_recv = jiffies;
+			if (!(ppp->active_filter
+			      && sk_run_filter(skb, ppp->active_filter,
+					       ppp->active_len) == 0))
+				ppp->last_recv = jiffies;
+			__skb_pull(skb, 2);
+		} else
 #endif /* CONFIG_PPP_FILTER */
+			ppp->last_recv = jiffies;
 
 		if ((ppp->dev->flags & IFF_UP) == 0
 		    || ppp->npmode[npi] != NPMODE_PASS) {
@@ -1770,7 +1768,7 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 	struct channel *ch;
 	int mphdrlen = (ppp->flags & SC_MP_SHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN;
 
-	if (!pskb_may_pull(skb, mphdrlen) || ppp->mrru == 0)
+	if (!pskb_may_pull(skb, mphdrlen + 1) || ppp->mrru == 0)
 		goto err;		/* no good, throw it away */
 
 	/* Decode sequence number and begin/end bits */

drivers/net/pppoe.c

@@ -385,12 +385,12 @@ static int pppoe_rcv(struct sk_buff *skb,
 	struct pppoe_hdr *ph;
 	struct pppox_sock *po;
 
-	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
-		goto drop;
-
 	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
 		goto out;
 
+	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
+		goto drop;
+
 	ph = pppoe_hdr(skb);
 
 	po = get_item((unsigned long) ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
@@ -848,71 +848,45 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	struct pppox_sock *po = pppox_sk(sk);
 	struct net_device *dev = po->pppoe_dev;
-	struct pppoe_hdr hdr;
 	struct pppoe_hdr *ph;
-	int headroom = skb_headroom(skb);
 	int data_len = skb->len;
-	struct sk_buff *skb2;
 
 	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
 		goto abort;
 
-	hdr.ver	= 1;
-	hdr.type = 1;
-	hdr.code = 0;
-	hdr.sid	= po->num;
-	hdr.length = htons(skb->len);
-
 	if (!dev)
 		goto abort;
 
-	/* Copy the skb if there is no space for the header. */
+	/* Copy the data if there is no space for the header or if it's
-	if (headroom < (sizeof(struct pppoe_hdr) + dev->hard_header_len)) {
+	 * read-only.
-		skb2 = dev_alloc_skb(32+skb->len +
-				     sizeof(struct pppoe_hdr) +
-				     dev->hard_header_len);
-
-		if (skb2 == NULL)
-			goto abort;
-
-		skb_reserve(skb2, dev->hard_header_len + sizeof(struct pppoe_hdr));
-		skb_copy_from_linear_data(skb, skb_put(skb2, skb->len),
-					  skb->len);
-	} else {
-		/* Make a clone so as to not disturb the original skb,
-		 * give dev_queue_xmit something it can free.
-		 */
-		skb2 = skb_clone(skb, GFP_ATOMIC);
-
-		if (skb2 == NULL)
-			goto abort;
-	}
-
-	ph = (struct pppoe_hdr *) skb_push(skb2, sizeof(struct pppoe_hdr));
-	memcpy(ph, &hdr, sizeof(struct pppoe_hdr));
-	skb2->protocol = __constant_htons(ETH_P_PPP_SES);
-
-	skb_reset_network_header(skb2);
-
-	skb2->dev = dev;
-
-	dev->hard_header(skb2, dev, ETH_P_PPP_SES,
-			 po->pppoe_pa.remote, NULL, data_len);
-
-	/* We're transmitting skb2, and assuming that dev_queue_xmit
-	 * will free it.  The generic ppp layer however, is expecting
-	 * that we give back 'skb' (not 'skb2') in case of failure,
-	 * but free it in case of success.
 	 */
-
+	if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
-	if (dev_queue_xmit(skb2) < 0)
+		goto abort;
+
+	__skb_push(skb, sizeof(*ph));
+	skb_reset_network_header(skb);
+
+	ph = pppoe_hdr(skb);
+	ph->ver	= 1;
+	ph->type = 1;
+	ph->code = 0;
+	ph->sid	= po->num;
+	ph->length = htons(data_len);
+
+	skb->protocol = __constant_htons(ETH_P_PPP_SES);
+	skb->dev = dev;
+
+	dev->hard_header(skb, dev, ETH_P_PPP_SES,
+			 po->pppoe_pa.remote, NULL, data_len);
+
+	if (dev_queue_xmit(skb) < 0)
 		goto abort;
 
-	kfree_skb(skb);
 	return 1;
 
 abort:
-	return 0;
+	kfree_skb(skb);
+	return 1;
 }
 
 

include/linux/skbuff.h

@@ -1352,6 +1352,22 @@ static inline int skb_clone_writable(struct sk_buff *skb, int len)
 	       skb_headroom(skb) + len <= skb->hdr_len;
 }
 
+static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
+			    int cloned)
+{
+	int delta = 0;
+
+	if (headroom < NET_SKB_PAD)
+		headroom = NET_SKB_PAD;
+	if (headroom > skb_headroom(skb))
+		delta = headroom - skb_headroom(skb);
+
+	if (delta || cloned)
+		return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0,
+					GFP_ATOMIC);
+	return 0;
+}
+
 /**
  *	skb_cow - copy header of skb when it is required
  *	@skb: buffer to cow
@@ -1366,16 +1382,22 @@ static inline int skb_clone_writable(struct sk_buff *skb, int len)
  */
 static inline int skb_cow(struct sk_buff *skb, unsigned int headroom)
 {
-	int delta = (headroom > NET_SKB_PAD ? headroom : NET_SKB_PAD) -
+	return __skb_cow(skb, headroom, skb_cloned(skb));
-			skb_headroom(skb);
+}
 
-	if (delta < 0)
+/**
-		delta = 0;
+ *	skb_cow_head - skb_cow but only making the head writable
-
+ *	@skb: buffer to cow
-	if (delta || skb_cloned(skb))
+ *	@headroom: needed headroom
-		return pskb_expand_head(skb, (delta + (NET_SKB_PAD-1)) &
+ *
-				~(NET_SKB_PAD-1), 0, GFP_ATOMIC);
+ *	This function is identical to skb_cow except that we replace the
-	return 0;
+ *	skb_cloned check by skb_header_cloned.  It should be used when
+ *	you only need to push on some header and do not need to modify
+ *	the data.
+ */
+static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom)
+{
+	return __skb_cow(skb, headroom, skb_header_cloned(skb));
 }
 
 /**

include/net/sctp/sctp.h

@@ -123,6 +123,7 @@
  * sctp/protocol.c
  */
 extern struct sock *sctp_get_ctl_sock(void);
+extern void sctp_local_addr_free(struct rcu_head *head);
 extern int sctp_copy_local_addr_list(struct sctp_bind_addr *,
 				     sctp_scope_t, gfp_t gfp,
 				     int flags);

include/net/sctp/structs.h

@@ -208,6 +208,9 @@ extern struct sctp_globals {
 	 */
 	struct list_head local_addr_list;
 
+	/* Lock that protects the local_addr_list writers */
+	spinlock_t addr_list_lock;
+	
 	/* Flag to indicate if addip is enabled. */
 	int addip_enable;
 
@@ -242,6 +245,7 @@ extern struct sctp_globals {
 #define sctp_port_alloc_lock		(sctp_globals.port_alloc_lock)
 #define sctp_port_hashtable		(sctp_globals.port_hashtable)
 #define sctp_local_addr_list		(sctp_globals.local_addr_list)
+#define sctp_local_addr_lock		(sctp_globals.addr_list_lock)
 #define sctp_addip_enable		(sctp_globals.addip_enable)
 #define sctp_prsctp_enable		(sctp_globals.prsctp_enable)
 
@@ -737,8 +741,10 @@ const union sctp_addr *sctp_source(const struct sctp_chunk *chunk);
 /* This is a structure for holding either an IPv6 or an IPv4 address.  */
 struct sctp_sockaddr_entry {
 	struct list_head list;
+	struct rcu_head	rcu;
 	union sctp_addr a;
 	__u8 use_as_src;
+	__u8 valid;
 };
 
 typedef struct sctp_chunk *(sctp_packet_phandler_t)(struct sctp_association *);
@@ -1149,7 +1155,9 @@ int sctp_bind_addr_copy(struct sctp_bind_addr *dest,
 			int flags);
 int sctp_add_bind_addr(struct sctp_bind_addr *, union sctp_addr *,
 		       __u8 use_as_src, gfp_t gfp);
-int sctp_del_bind_addr(struct sctp_bind_addr *, union sctp_addr *);
+int sctp_del_bind_addr(struct sctp_bind_addr *, union sctp_addr *,
+			void (*rcu_call)(struct rcu_head *,
+					  void (*func)(struct rcu_head *)));
 int sctp_bind_addr_match(struct sctp_bind_addr *, const union sctp_addr *,
 			 struct sctp_sock *);
 union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr	*bp,
@@ -1220,9 +1228,6 @@ struct sctp_ep_common {
 	 * bind_addr.address_list is our set of local IP addresses.
 	 */
 	struct sctp_bind_addr bind_addr;
-
-	/* Protection during address list comparisons. */
-	rwlock_t   addr_lock;
 };
 
 

net/8021q/vlan.c

@@ -562,8 +562,6 @@ static int register_vlan_device(struct net_device *real_dev,
 	if (err < 0)
 		goto out_free_newdev;
 
-	/* Account for reference in struct vlan_dev_info */
-	dev_hold(real_dev);
 #ifdef VLAN_DEBUG
 	printk(VLAN_DBG "Allocated new device successfully, returning.\n");
 #endif

net/bridge/br_device.c

@@ -41,11 +41,11 @@ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_pull(skb, ETH_HLEN);
 
 	if (dest[0] & 1)
-		br_flood_deliver(br, skb, 0);
+		br_flood_deliver(br, skb);
 	else if ((dst = __br_fdb_get(br, dest)) != NULL)
 		br_deliver(dst->dst, skb);
 	else
-		br_flood_deliver(br, skb, 0);
+		br_flood_deliver(br, skb);
 
 	return 0;
 }

net/bridge/br_forward.c

@@ -100,24 +100,13 @@ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 }
 
 /* called under bridge lock */
-static void br_flood(struct net_bridge *br, struct sk_buff *skb, int clone,
+static void br_flood(struct net_bridge *br, struct sk_buff *skb,
 	void (*__packet_hook)(const struct net_bridge_port *p,
 			      struct sk_buff *skb))
 {
 	struct net_bridge_port *p;
 	struct net_bridge_port *prev;
 
-	if (clone) {
-		struct sk_buff *skb2;
-
-		if ((skb2 = skb_clone(skb, GFP_ATOMIC)) == NULL) {
-			br->statistics.tx_dropped++;
-			return;
-		}
-
-		skb = skb2;
-	}
-
 	prev = NULL;
 
 	list_for_each_entry_rcu(p, &br->port_list, list) {
@@ -148,13 +137,13 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb, int clone,
 
 
 /* called with rcu_read_lock */
-void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, int clone)
+void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb)
 {
-	br_flood(br, skb, clone, __br_deliver);
+	br_flood(br, skb, __br_deliver);
 }
 
 /* called under bridge lock */
-void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, int clone)
+void br_flood_forward(struct net_bridge *br, struct sk_buff *skb)
 {
-	br_flood(br, skb, clone, __br_forward);
+	br_flood(br, skb, __br_forward);
 }

net/bridge/br_input.c

@@ -43,7 +43,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
 	struct net_bridge_port *p = rcu_dereference(skb->dev->br_port);
 	struct net_bridge *br;
 	struct net_bridge_fdb_entry *dst;
-	int passedup = 0;
+	struct sk_buff *skb2;
 
 	if (!p || p->state == BR_STATE_DISABLED)
 		goto drop;
@@ -55,40 +55,36 @@ int br_handle_frame_finish(struct sk_buff *skb)
 	if (p->state == BR_STATE_LEARNING)
 		goto drop;
 
-	if (br->dev->flags & IFF_PROMISC) {
+	/* The packet skb2 goes to the local host (NULL to skip). */
-		struct sk_buff *skb2;
+	skb2 = NULL;
 
-		skb2 = skb_clone(skb, GFP_ATOMIC);
+	if (br->dev->flags & IFF_PROMISC)
-		if (skb2 != NULL) {
+		skb2 = skb;
-			passedup = 1;
+
-			br_pass_frame_up(br, skb2);
+	dst = NULL;
-		}
-	}
 
 	if (is_multicast_ether_addr(dest)) {
 		br->statistics.multicast++;
-		br_flood_forward(br, skb, !passedup);
+		skb2 = skb;
-		if (!passedup)
+	} else if ((dst = __br_fdb_get(br, dest)) && dst->is_local) {
-			br_pass_frame_up(br, skb);
+		skb2 = skb;
-		goto out;
+		/* Do not forward the packet since it's local. */
+		skb = NULL;
 	}
 
-	dst = __br_fdb_get(br, dest);
+	if (skb2 == skb)
-	if (dst != NULL && dst->is_local) {
+		skb2 = skb_clone(skb, GFP_ATOMIC);
-		if (!passedup)
+
-			br_pass_frame_up(br, skb);
+	if (skb2)
+		br_pass_frame_up(br, skb2);
+
+	if (skb) {
+		if (dst)
+			br_forward(dst->dst, skb);
 		else
-			kfree_skb(skb);
+			br_flood_forward(br, skb);
-		goto out;
 	}
 
-	if (dst != NULL) {
-		br_forward(dst->dst, skb);
-		goto out;
-	}
-
-	br_flood_forward(br, skb, 0);
-
 out:
 	return 0;
 drop:

net/bridge/br_netfilter.c

@@ -183,7 +183,7 @@ int nf_bridge_copy_header(struct sk_buff *skb)
 	int err;
 	int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
 
-	err = skb_cow(skb, header_size);
+	err = skb_cow_head(skb, header_size);
 	if (err)
 		return err;
 

net/bridge/br_private.h

@@ -170,12 +170,8 @@ extern int br_dev_queue_push_xmit(struct sk_buff *skb);
 extern void br_forward(const struct net_bridge_port *to,
 		struct sk_buff *skb);
 extern int br_forward_finish(struct sk_buff *skb);
-extern void br_flood_deliver(struct net_bridge *br,
+extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb);
-		      struct sk_buff *skb,
+extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb);
-		      int clone);
-extern void br_flood_forward(struct net_bridge *br,
-		      struct sk_buff *skb,
-		      int clone);
 
 /* br_if.c */
 extern void br_port_carrier_check(struct net_bridge_port *p);

net/core/pktgen.c

@@ -111,6 +111,9 @@
  *
  * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com>
  *
+ * Fixed src_mac command to set source mac of packet to value specified in
+ * command by Adit Ranadive <adit.262@gmail.com>
+ *
  */
 #include <linux/sys.h>
 #include <linux/types.h>
@@ -1451,8 +1454,11 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 	if (!strcmp(name, "src_mac")) {
 		char *v = valstr;
+		unsigned char old_smac[ETH_ALEN];
 		unsigned char *m = pkt_dev->src_mac;
 
+		memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN);
+
 		len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
 		if (len < 0) {
 			return len;
@@ -1481,6 +1487,10 @@ static ssize_t pktgen_if_write(struct file *file,
 			}
 		}
 
+		/* Set up Src MAC */
+		if (compare_ether_addr(old_smac, pkt_dev->src_mac))
+			memcpy(&(pkt_dev->hh[6]), pkt_dev->src_mac, ETH_ALEN);
+
 		sprintf(pg_result, "OK: srcmac");
 		return count;
 	}

net/core/sock.c

@@ -362,6 +362,61 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
 }
 EXPORT_SYMBOL(sk_dst_check);
 
+static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen)
+{
+	int ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+	char devname[IFNAMSIZ];
+	int index;
+
+	/* Sorry... */
+	ret = -EPERM;
+	if (!capable(CAP_NET_RAW))
+		goto out;
+
+	ret = -EINVAL;
+	if (optlen < 0)
+		goto out;
+
+	/* Bind this socket to a particular device like "eth0",
+	 * as specified in the passed interface name. If the
+	 * name is "" or the option length is zero the socket
+	 * is not bound.
+	 */
+	if (optlen > IFNAMSIZ - 1)
+		optlen = IFNAMSIZ - 1;
+	memset(devname, 0, sizeof(devname));
+
+	ret = -EFAULT;
+	if (copy_from_user(devname, optval, optlen))
+		goto out;
+
+	if (devname[0] == '\0') {
+		index = 0;
+	} else {
+		struct net_device *dev = dev_get_by_name(devname);
+
+		ret = -ENODEV;
+		if (!dev)
+			goto out;
+
+		index = dev->ifindex;
+		dev_put(dev);
+	}
+
+	lock_sock(sk);
+	sk->sk_bound_dev_if = index;
+	sk_dst_reset(sk);
+	release_sock(sk);
+
+	ret = 0;
+
+out:
+#endif
+
+	return ret;
+}
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -390,6 +445,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 	}
 #endif
 
+	if (optname == SO_BINDTODEVICE)
+		return sock_bindtodevice(sk, optval, optlen);
+
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
@@ -578,54 +636,6 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
 		break;
 
-#ifdef CONFIG_NETDEVICES
-	case SO_BINDTODEVICE:
-	{
-		char devname[IFNAMSIZ];
-
-		/* Sorry... */
-		if (!capable(CAP_NET_RAW)) {
-			ret = -EPERM;
-			break;
-		}
-
-		/* Bind this socket to a particular device like "eth0",
-		 * as specified in the passed interface name. If the
-		 * name is "" or the option length is zero the socket
-		 * is not bound.
-		 */
-
-		if (!valbool) {
-			sk->sk_bound_dev_if = 0;
-		} else {
-			if (optlen > IFNAMSIZ - 1)
-				optlen = IFNAMSIZ - 1;
-			memset(devname, 0, sizeof(devname));
-			if (copy_from_user(devname, optval, optlen)) {
-				ret = -EFAULT;
-				break;
-			}
-
-			/* Remove any cached route for this socket. */
-			sk_dst_reset(sk);
-
-			if (devname[0] == '\0') {
-				sk->sk_bound_dev_if = 0;
-			} else {
-				struct net_device *dev = dev_get_by_name(devname);
-				if (!dev) {
-					ret = -ENODEV;
-					break;
-				}
-				sk->sk_bound_dev_if = dev->ifindex;
-				dev_put(dev);
-			}
-		}
-		break;
-	}
-#endif
-
-
 	case SO_ATTACH_FILTER:
 		ret = -EINVAL;
 		if (optlen == sizeof(struct sock_fprog)) {

net/ipv4/udp.c

@@ -505,6 +505,8 @@ static int udp_push_pending_frames(struct sock *sk)
 out:
 	up->len = 0;
 	up->pending = 0;
+	if (!err)
+		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag);
 	return err;
 }
 
@@ -693,10 +695,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	ip_rt_put(rt);
 	if (free)
 		kfree(ipc.opt);
-	if (!err) {
+	if (!err)
-		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
 		return len;
-	}
 	/*
 	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
 	 * ENOBUFS might not be good (it's not tunable per se), but otherwise

net/ipv6/addrconf.c

@@ -1021,7 +1021,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
 				hiscore.rule++;
 			}
 			if (ipv6_saddr_preferred(score.addr_type) ||
-			   (((ifa_result->flags &
+			   (((ifa->flags &
 			    (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) {
 				score.attrs |= IPV6_SADDR_SCORE_PREFERRED;
 				if (!(hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)) {

net/ipv6/raw.c

@@ -882,11 +882,10 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			ip6_flush_pending_frames(sk);
 		else if (!(msg->msg_flags & MSG_MORE))
 			err = rawv6_push_pending_frames(sk, &fl, rp);
+		release_sock(sk);
 	}
 done:
 	dst_release(dst);
-	if (!inet->hdrincl)
-		release_sock(sk);
 out:
 	fl6_sock_release(flowlabel);
 	return err<0?err:len;

net/ipv6/udp.c

@@ -555,6 +555,8 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 out:
 	up->len = 0;
 	up->pending = 0;
+	if (!err)
+		UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag);
 	return err;
 }
 
@@ -823,10 +825,8 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	release_sock(sk);
 out:
 	fl6_sock_release(flowlabel);
-	if (!err) {
+	if (!err)
-		UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
 		return len;
-	}
 	/*
 	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
 	 * ENOBUFS might not be good (it's not tunable per se), but otherwise

net/sched/act_api.c

@@ -68,7 +68,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 	int err = 0, index = -1,i = 0, s_i = 0, n_i = 0;
 	struct rtattr *r ;
 
-	read_lock(hinfo->lock);
+	read_lock_bh(hinfo->lock);
 
 	s_i = cb->args[0];
 
@@ -96,7 +96,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 		}
 	}
 done:
-	read_unlock(hinfo->lock);
+	read_unlock_bh(hinfo->lock);
 	if (n_i)
 		cb->args[0] += n_i;
 	return n_i;
@@ -156,13 +156,13 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo)
 {
 	struct tcf_common *p;
 
-	read_lock(hinfo->lock);
+	read_lock_bh(hinfo->lock);
 	for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p;
 	     p = p->tcfc_next) {
 		if (p->tcfc_index == index)
 			break;
 	}
-	read_unlock(hinfo->lock);
+	read_unlock_bh(hinfo->lock);
 
 	return p;
 }

net/sched/act_police.c

@@ -56,7 +56,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c
 	int err = 0, index = -1, i = 0, s_i = 0, n_i = 0;
 	struct rtattr *r;
 
-	read_lock(&police_lock);
+	read_lock_bh(&police_lock);
 
 	s_i = cb->args[0];
 
@@ -85,7 +85,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c
 		}
 	}
 done:
-	read_unlock(&police_lock);
+	read_unlock_bh(&police_lock);
 	if (n_i)
 		cb->args[0] += n_i;
 	return n_i;

net/sched/sch_cbq.c

@@ -380,7 +380,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	int len = skb->len;
-	int ret;
+	int uninitialized_var(ret);
 	struct cbq_class *cl = cbq_classify(skb, sch, &ret);
 
 #ifdef CONFIG_NET_CLS_ACT

net/sctp/associola.c

@@ -99,7 +99,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 
 	/* Initialize the bind addr area.  */
 	sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port);
-	rwlock_init(&asoc->base.addr_lock);
 
 	asoc->state = SCTP_STATE_CLOSED;
 
@@ -937,8 +936,6 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
 {
 	struct sctp_transport *transport;
 
-	sctp_read_lock(&asoc->base.addr_lock);
-
 	if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) &&
 	    (htons(asoc->peer.port) == paddr->v4.sin_port)) {
 		transport = sctp_assoc_lookup_paddr(asoc, paddr);
@@ -952,7 +949,6 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
 	transport = NULL;
 
 out:
-	sctp_read_unlock(&asoc->base.addr_lock);
 	return transport;
 }
 
@@ -1376,19 +1372,13 @@ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc,
 int sctp_assoc_lookup_laddr(struct sctp_association *asoc,
 			    const union sctp_addr *laddr)
 {
-	int found;
+	int found = 0;
 
-	sctp_read_lock(&asoc->base.addr_lock);
 	if ((asoc->base.bind_addr.port == ntohs(laddr->v4.sin_port)) &&
 	    sctp_bind_addr_match(&asoc->base.bind_addr, laddr,
-				 sctp_sk(asoc->base.sk))) {
+				 sctp_sk(asoc->base.sk)))
 		found = 1;
-		goto out;
-	}
 
-	found = 0;
-out:
-	sctp_read_unlock(&asoc->base.addr_lock);
 	return found;
 }
 

net/sctp/bind_addr.c

@@ -163,9 +163,15 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new,
 		addr->a.v4.sin_port = htons(bp->port);
 
 	addr->use_as_src = use_as_src;
+	addr->valid = 1;
 
 	INIT_LIST_HEAD(&addr->list);
-	list_add_tail(&addr->list, &bp->address_list);
+	INIT_RCU_HEAD(&addr->rcu);
+
+	/* We always hold a socket lock when calling this function,
+	 * and that acts as a writer synchronizing lock.
+	 */
+	list_add_tail_rcu(&addr->list, &bp->address_list);
 	SCTP_DBG_OBJCNT_INC(addr);
 
 	return 0;
@@ -174,23 +180,35 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new,
 /* Delete an address from the bind address list in the SCTP_bind_addr
  * structure.
  */
-int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr)
+int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr,
+			void (*rcu_call)(struct rcu_head *head,
+					 void (*func)(struct rcu_head *head)))
 {
-	struct list_head *pos, *temp;
+	struct sctp_sockaddr_entry *addr, *temp;
-	struct sctp_sockaddr_entry *addr;
 
-	list_for_each_safe(pos, temp, &bp->address_list) {
+	/* We hold the socket lock when calling this function,
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	 * and that acts as a writer synchronizing lock.
+	 */
+	list_for_each_entry_safe(addr, temp, &bp->address_list, list) {
 		if (sctp_cmp_addr_exact(&addr->a, del_addr)) {
 			/* Found the exact match. */
-			list_del(pos);
+			addr->valid = 0;
-			kfree(addr);
+			list_del_rcu(&addr->list);
-			SCTP_DBG_OBJCNT_DEC(addr);
+			break;
-
-			return 0;
 		}
 	}
 
+	/* Call the rcu callback provided in the args.  This function is
+	 * called by both BH packet processing and user side socket option
+	 * processing, but it works on different lists in those 2 contexts.
+	 * Each context provides it's own callback, whether call_rcu_bh()
+	 * or call_rcu(), to make sure that we wait for an appropriate time.
+	 */
+	if (addr && !addr->valid) {
+		rcu_call(&addr->rcu, sctp_local_addr_free);
+		SCTP_DBG_OBJCNT_DEC(addr);
+	}
+
 	return -EINVAL;
 }
 
@@ -300,15 +318,20 @@ int sctp_bind_addr_match(struct sctp_bind_addr *bp,
 			 struct sctp_sock *opt)
 {
 	struct sctp_sockaddr_entry *laddr;
-	struct list_head *pos;
+	int match = 0;
 
-	list_for_each(pos, &bp->address_list) {
+	rcu_read_lock();
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		if (opt->pf->cmp_addr(&laddr->a, addr, opt))
+		if (!laddr->valid)
-			return 1;
+			continue;
+		if (opt->pf->cmp_addr(&laddr->a, addr, opt)) {
+			match = 1;
+			break;
+		}
 	}
+	rcu_read_unlock();
 
-	return 0;
+	return match;
 }
 
 /* Find the first address in the bind address list that is not present in
@@ -323,18 +346,19 @@ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr	*bp,
 	union sctp_addr			*addr;
 	void 				*addr_buf;
 	struct sctp_af			*af;
-	struct list_head		*pos;
 	int				i;
 
-	list_for_each(pos, &bp->address_list) {
+	/* This is only called sctp_send_asconf_del_ip() and we hold
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	 * the socket lock in that code patch, so that address list
-
+	 * can't change.
+	 */
+	list_for_each_entry(laddr, &bp->address_list, list) {
 		addr_buf = (union sctp_addr *)addrs;
 		for (i = 0; i < addrcnt; i++) {
 			addr = (union sctp_addr *)addr_buf;
 			af = sctp_get_af_specific(addr->v4.sin_family);
 			if (!af)
-				return NULL;
+				break;
 
 			if (opt->pf->cmp_addr(&laddr->a, addr, opt))
 				break;

net/sctp/endpointola.c

@@ -92,7 +92,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 
 	/* Initialize the bind addr area */
 	sctp_bind_addr_init(&ep->base.bind_addr, 0);
-	rwlock_init(&ep->base.addr_lock);
 
 	/* Remember who we are attached to.  */
 	ep->base.sk = sk;
@@ -225,21 +224,14 @@ void sctp_endpoint_put(struct sctp_endpoint *ep)
 struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep,
 					       const union sctp_addr *laddr)
 {
-	struct sctp_endpoint *retval;
+	struct sctp_endpoint *retval = NULL;
 
-	sctp_read_lock(&ep->base.addr_lock);
 	if (htons(ep->base.bind_addr.port) == laddr->v4.sin_port) {
 		if (sctp_bind_addr_match(&ep->base.bind_addr, laddr,
-					 sctp_sk(ep->base.sk))) {
+					 sctp_sk(ep->base.sk)))
 			retval = ep;
-			goto out;
-		}
 	}
 
-	retval = NULL;
-
-out:
-	sctp_read_unlock(&ep->base.addr_lock);
 	return retval;
 }
 
@@ -261,9 +253,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc(
 	list_for_each(pos, &ep->asocs) {
 		asoc = list_entry(pos, struct sctp_association, asocs);
 		if (rport == asoc->peer.port) {
-			sctp_read_lock(&asoc->base.addr_lock);
 			*transport = sctp_assoc_lookup_paddr(asoc, paddr);
-			sctp_read_unlock(&asoc->base.addr_lock);
 
 			if (*transport)
 				return asoc;
@@ -295,20 +285,17 @@ struct sctp_association *sctp_endpoint_lookup_assoc(
 int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
 				const union sctp_addr *paddr)
 {
-	struct list_head *pos;
 	struct sctp_sockaddr_entry *addr;
 	struct sctp_bind_addr *bp;
 
-	sctp_read_lock(&ep->base.addr_lock);
 	bp = &ep->base.bind_addr;
-	list_for_each(pos, &bp->address_list) {
+	/* This function is called with the socket lock held,
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	 * so the address_list can not change.
-		if (sctp_has_association(&addr->a, paddr)) {
+	 */
-			sctp_read_unlock(&ep->base.addr_lock);
+	list_for_each_entry(addr, &bp->address_list, list) {
+		if (sctp_has_association(&addr->a, paddr))
 			return 1;
-		}
 	}
-	sctp_read_unlock(&ep->base.addr_lock);
 
 	return 0;
 }

net/sctp/ipv6.c

@@ -77,13 +77,18 @@
 
 #include <asm/uaccess.h>
 
-/* Event handler for inet6 address addition/deletion events.  */
+/* Event handler for inet6 address addition/deletion events.
+ * The sctp_local_addr_list needs to be protocted by a spin lock since
+ * multiple notifiers (say IPv4 and IPv6) may be running at the same
+ * time and thus corrupt the list.
+ * The reader side is protected with RCU.
+ */
 static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 				void *ptr)
 {
 	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
-	struct sctp_sockaddr_entry *addr;
+	struct sctp_sockaddr_entry *addr = NULL;
-	struct list_head *pos, *temp;
+	struct sctp_sockaddr_entry *temp;
 
 	switch (ev) {
 	case NETDEV_UP:
@@ -94,19 +99,26 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 			memcpy(&addr->a.v6.sin6_addr, &ifa->addr,
 				 sizeof(struct in6_addr));
 			addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
-			list_add_tail(&addr->list, &sctp_local_addr_list);
+			addr->valid = 1;
+			spin_lock_bh(&sctp_local_addr_lock);
+			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
+			spin_unlock_bh(&sctp_local_addr_lock);
 		}
 		break;
 	case NETDEV_DOWN:
-		list_for_each_safe(pos, temp, &sctp_local_addr_list) {
+		spin_lock_bh(&sctp_local_addr_lock);
-			addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		list_for_each_entry_safe(addr, temp,
-			if (ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr)) {
+					&sctp_local_addr_list, list) {
-				list_del(pos);
+			if (ipv6_addr_equal(&addr->a.v6.sin6_addr,
-				kfree(addr);
+					     &ifa->addr)) {
+				addr->valid = 0;
+				list_del_rcu(&addr->list);
 				break;
 			}
 		}
-
+		spin_unlock_bh(&sctp_local_addr_lock);
+		if (addr && !addr->valid)
+			call_rcu(&addr->rcu, sctp_local_addr_free);
 		break;
 	}
 
@@ -290,9 +302,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
 			      union sctp_addr *saddr)
 {
 	struct sctp_bind_addr *bp;
-	rwlock_t *addr_lock;
 	struct sctp_sockaddr_entry *laddr;
-	struct list_head *pos;
 	sctp_scope_t scope;
 	union sctp_addr *baddr = NULL;
 	__u8 matchlen = 0;
@@ -312,14 +322,14 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
 	scope = sctp_scope(daddr);
 
 	bp = &asoc->base.bind_addr;
-	addr_lock = &asoc->base.addr_lock;
 
 	/* Go through the bind address list and find the best source address
 	 * that matches the scope of the destination address.
 	 */
-	sctp_read_lock(addr_lock);
+	rcu_read_lock();
-	list_for_each(pos, &bp->address_list) {
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		if (!laddr->valid)
+			continue;
 		if ((laddr->use_as_src) &&
 		    (laddr->a.sa.sa_family == AF_INET6) &&
 		    (scope <= sctp_scope(&laddr->a))) {
@@ -341,7 +351,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
 		       __FUNCTION__, asoc, NIP6(daddr->v6.sin6_addr));
 	}
 
-	sctp_read_unlock(addr_lock);
+	rcu_read_unlock();
 }
 
 /* Make a copy of all potential local addresses. */
@@ -367,7 +377,9 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
 			addr->a.v6.sin6_port = 0;
 			addr->a.v6.sin6_addr = ifp->addr;
 			addr->a.v6.sin6_scope_id = dev->ifindex;
+			addr->valid = 1;
 			INIT_LIST_HEAD(&addr->list);
+			INIT_RCU_HEAD(&addr->rcu);
 			list_add_tail(&addr->list, addrlist);
 		}
 	}

net/sctp/protocol.c

@@ -153,6 +153,9 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist,
 			addr->a.v4.sin_family = AF_INET;
 			addr->a.v4.sin_port = 0;
 			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
+			addr->valid = 1;
+			INIT_LIST_HEAD(&addr->list);
+			INIT_RCU_HEAD(&addr->rcu);
 			list_add_tail(&addr->list, addrlist);
 		}
 	}
@@ -192,16 +195,24 @@ static void sctp_free_local_addr_list(void)
 	}
 }
 
+void sctp_local_addr_free(struct rcu_head *head)
+{
+	struct sctp_sockaddr_entry *e = container_of(head,
+				struct sctp_sockaddr_entry, rcu);
+	kfree(e);
+}
+
 /* Copy the local addresses which are valid for 'scope' into 'bp'.  */
 int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
 			      gfp_t gfp, int copy_flags)
 {
 	struct sctp_sockaddr_entry *addr;
 	int error = 0;
-	struct list_head *pos, *temp;
 
-	list_for_each_safe(pos, temp, &sctp_local_addr_list) {
+	rcu_read_lock();
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) {
+		if (!addr->valid)
+			continue;
 		if (sctp_in_scope(&addr->a, scope)) {
 			/* Now that the address is in scope, check to see if
 			 * the address type is really supported by the local
@@ -213,7 +224,7 @@ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
 			      (copy_flags & SCTP_ADDR6_ALLOWED) &&
 			      (copy_flags & SCTP_ADDR6_PEERSUPP)))) {
 				error = sctp_add_bind_addr(bp, &addr->a, 1,
-							   GFP_ATOMIC);
+						    GFP_ATOMIC);
 				if (error)
 					goto end_copy;
 			}
@@ -221,6 +232,7 @@ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
 	}
 
 end_copy:
+	rcu_read_unlock();
 	return error;
 }
 
@@ -416,9 +428,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 	struct rtable *rt;
 	struct flowi fl;
 	struct sctp_bind_addr *bp;
-	rwlock_t *addr_lock;
 	struct sctp_sockaddr_entry *laddr;
-	struct list_head *pos;
 	struct dst_entry *dst = NULL;
 	union sctp_addr dst_saddr;
 
@@ -447,23 +457,20 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 		goto out;
 
 	bp = &asoc->base.bind_addr;
-	addr_lock = &asoc->base.addr_lock;
 
 	if (dst) {
 		/* Walk through the bind address list and look for a bind
 		 * address that matches the source address of the returned dst.
 		 */
-		sctp_read_lock(addr_lock);
+		rcu_read_lock();
-		list_for_each(pos, &bp->address_list) {
+		list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-			laddr = list_entry(pos, struct sctp_sockaddr_entry,
+			if (!laddr->valid || !laddr->use_as_src)
-					   list);
-			if (!laddr->use_as_src)
 				continue;
 			sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
 			if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
 				goto out_unlock;
 		}
-		sctp_read_unlock(addr_lock);
+		rcu_read_unlock();
 
 		/* None of the bound addresses match the source address of the
 		 * dst. So release it.
@@ -475,10 +482,10 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 	/* Walk through the bind address list and try to get a dst that
 	 * matches a bind address as the source address.
 	 */
-	sctp_read_lock(addr_lock);
+	rcu_read_lock();
-	list_for_each(pos, &bp->address_list) {
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		if (!laddr->valid)
-
+			continue;
 		if ((laddr->use_as_src) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
 			fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
@@ -490,7 +497,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 	}
 
 out_unlock:
-	sctp_read_unlock(addr_lock);
+	rcu_read_unlock();
 out:
 	if (dst)
 		SCTP_DEBUG_PRINTK("rt_dst:%u.%u.%u.%u, rt_src:%u.%u.%u.%u\n",
@@ -600,13 +607,18 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
 	seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr));
 }
 
-/* Event handler for inet address addition/deletion events.  */
+/* Event handler for inet address addition/deletion events.
+ * The sctp_local_addr_list needs to be protocted by a spin lock since
+ * multiple notifiers (say IPv4 and IPv6) may be running at the same
+ * time and thus corrupt the list.
+ * The reader side is protected with RCU.
+ */
 static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
 			       void *ptr)
 {
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
-	struct sctp_sockaddr_entry *addr;
+	struct sctp_sockaddr_entry *addr = NULL;
-	struct list_head *pos, *temp;
+	struct sctp_sockaddr_entry *temp;
 
 	switch (ev) {
 	case NETDEV_UP:
@@ -615,19 +627,25 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
 			addr->a.v4.sin_family = AF_INET;
 			addr->a.v4.sin_port = 0;
 			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
-			list_add_tail(&addr->list, &sctp_local_addr_list);
+			addr->valid = 1;
+			spin_lock_bh(&sctp_local_addr_lock);
+			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
+			spin_unlock_bh(&sctp_local_addr_lock);
 		}
 		break;
 	case NETDEV_DOWN:
-		list_for_each_safe(pos, temp, &sctp_local_addr_list) {
+		spin_lock_bh(&sctp_local_addr_lock);
-			addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		list_for_each_entry_safe(addr, temp,
+					&sctp_local_addr_list, list) {
 			if (addr->a.v4.sin_addr.s_addr == ifa->ifa_local) {
-				list_del(pos);
+				addr->valid = 0;
-				kfree(addr);
+				list_del_rcu(&addr->list);
 				break;
 			}
 		}
-
+		spin_unlock_bh(&sctp_local_addr_lock);
+		if (addr && !addr->valid)
+			call_rcu(&addr->rcu, sctp_local_addr_free);
 		break;
 	}
 
@@ -1160,6 +1178,7 @@ SCTP_STATIC __init int sctp_init(void)
 
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&sctp_local_addr_list);
+	spin_lock_init(&sctp_local_addr_lock);
 	sctp_get_local_addr_list();
 
 	/* Register notifier for inet address additions/deletions. */
@@ -1227,6 +1246,9 @@ SCTP_STATIC __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
 
+	/* Unregister notifier for inet address additions/deletions. */
+	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
+
 	/* Free the local address list.  */
 	sctp_free_local_addr_list();
 
@@ -1240,9 +1262,6 @@ SCTP_STATIC __exit void sctp_exit(void)
 	inet_unregister_protosw(&sctp_stream_protosw);
 	inet_unregister_protosw(&sctp_seqpacket_protosw);
 
-	/* Unregister notifier for inet address additions/deletions. */
-	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
-
 	sctp_sysctl_unregister();
 	list_del(&sctp_ipv4_specific.list);
 

net/sctp/sm_make_chunk.c

@@ -1531,7 +1531,7 @@ struct sctp_association *sctp_unpack_cookie(
 	/* Also, add the destination address. */
 	if (list_empty(&retval->base.bind_addr.address_list)) {
 		sctp_add_bind_addr(&retval->base.bind_addr, &chunk->dest, 1,
-				   GFP_ATOMIC);
+				GFP_ATOMIC);
 	}
 
 	retval->next_tsn = retval->c.initial_tsn;
@@ -2613,22 +2613,16 @@ static int sctp_asconf_param_success(struct sctp_association *asoc,
 
 	switch (asconf_param->param_hdr.type) {
 	case SCTP_PARAM_ADD_IP:
-		sctp_local_bh_disable();
+		/* This is always done in BH context with a socket lock
-		sctp_write_lock(&asoc->base.addr_lock);
+		 * held, so the list can not change.
-		list_for_each(pos, &bp->address_list) {
+		 */
-			saddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		list_for_each_entry(saddr, &bp->address_list, list) {
 			if (sctp_cmp_addr_exact(&saddr->a, &addr))
 				saddr->use_as_src = 1;
 		}
-		sctp_write_unlock(&asoc->base.addr_lock);
-		sctp_local_bh_enable();
 		break;
 	case SCTP_PARAM_DEL_IP:
-		sctp_local_bh_disable();
+		retval = sctp_del_bind_addr(bp, &addr, call_rcu_bh);
-		sctp_write_lock(&asoc->base.addr_lock);
-		retval = sctp_del_bind_addr(bp, &addr);
-		sctp_write_unlock(&asoc->base.addr_lock);
-		sctp_local_bh_enable();
 		list_for_each(pos, &asoc->peer.transport_addr_list) {
 			transport = list_entry(pos, struct sctp_transport,
 						 transports);

net/sctp/socket.c

@@ -367,14 +367,10 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len)
 	if (!bp->port)
 		bp->port = inet_sk(sk)->num;
 
-	/* Add the address to the bind address list.  */
+	/* Add the address to the bind address list.
-	sctp_local_bh_disable();
+	 * Use GFP_ATOMIC since BHs will be disabled.
-	sctp_write_lock(&ep->base.addr_lock);
+	 */
-
-	/* Use GFP_ATOMIC since BHs are disabled.  */
 	ret = sctp_add_bind_addr(bp, addr, 1, GFP_ATOMIC);
-	sctp_write_unlock(&ep->base.addr_lock);
-	sctp_local_bh_enable();
 
 	/* Copy back into socket for getsockname() use. */
 	if (!ret) {
@@ -544,15 +540,12 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
 		if (i < addrcnt)
 			continue;
 
-		/* Use the first address in bind addr list of association as
+		/* Use the first valid address in bind addr list of
-		 * Address Parameter of ASCONF CHUNK.
+		 * association as Address Parameter of ASCONF CHUNK.
 		 */
-		sctp_read_lock(&asoc->base.addr_lock);
 		bp = &asoc->base.bind_addr;
 		p = bp->address_list.next;
 		laddr = list_entry(p, struct sctp_sockaddr_entry, list);
-		sctp_read_unlock(&asoc->base.addr_lock);
-
 		chunk = sctp_make_asconf_update_ip(asoc, &laddr->a, addrs,
 						   addrcnt, SCTP_PARAM_ADD_IP);
 		if (!chunk) {
@@ -567,8 +560,6 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
 		/* Add the new addresses to the bind address list with
 		 * use_as_src set to 0.
 		 */
-		sctp_local_bh_disable();
-		sctp_write_lock(&asoc->base.addr_lock);
 		addr_buf = addrs;
 		for (i = 0; i < addrcnt; i++) {
 			addr = (union sctp_addr *)addr_buf;
@@ -578,8 +569,6 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
 						    GFP_ATOMIC);
 			addr_buf += af->sockaddr_len;
 		}
-		sctp_write_unlock(&asoc->base.addr_lock);
-		sctp_local_bh_enable();
 	}
 
 out:
@@ -651,13 +640,7 @@ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt)
 		 * socket routing and failover schemes. Refer to comments in
 		 * sctp_do_bind(). -daisy
 		 */
-		sctp_local_bh_disable();
+		retval = sctp_del_bind_addr(bp, sa_addr, call_rcu);
-		sctp_write_lock(&ep->base.addr_lock);
-
-		retval = sctp_del_bind_addr(bp, sa_addr);
-
-		sctp_write_unlock(&ep->base.addr_lock);
-		sctp_local_bh_enable();
 
 		addr_buf += af->sockaddr_len;
 err_bindx_rem:
@@ -748,14 +731,16 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
 		 * make sure that we do not delete all the addresses in the
 		 * association.
 		 */
-		sctp_read_lock(&asoc->base.addr_lock);
 		bp = &asoc->base.bind_addr;
 		laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs,
 					       addrcnt, sp);
-		sctp_read_unlock(&asoc->base.addr_lock);
 		if (!laddr)
 			continue;
 
+		/* We do not need RCU protection throughout this loop
+		 * because this is done under a socket lock from the
+		 * setsockopt call.
+		 */
 		chunk = sctp_make_asconf_update_ip(asoc, laddr, addrs, addrcnt,
 						   SCTP_PARAM_DEL_IP);
 		if (!chunk) {
@@ -766,23 +751,16 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
 		/* Reset use_as_src flag for the addresses in the bind address
 		 * list that are to be deleted.
 		 */
-		sctp_local_bh_disable();
-		sctp_write_lock(&asoc->base.addr_lock);
 		addr_buf = addrs;
 		for (i = 0; i < addrcnt; i++) {
 			laddr = (union sctp_addr *)addr_buf;
 			af = sctp_get_af_specific(laddr->v4.sin_family);
-			list_for_each(pos1, &bp->address_list) {
+			list_for_each_entry(saddr, &bp->address_list, list) {
-				saddr = list_entry(pos1,
-						   struct sctp_sockaddr_entry,
-						   list);
 				if (sctp_cmp_addr_exact(&saddr->a, laddr))
 					saddr->use_as_src = 0;
 			}
 			addr_buf += af->sockaddr_len;
 		}
-		sctp_write_unlock(&asoc->base.addr_lock);
-		sctp_local_bh_enable();
 
 		/* Update the route and saddr entries for all the transports
 		 * as some of the addresses in the bind address list are
@@ -4059,9 +4037,7 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len,
 	sctp_assoc_t id;
 	struct sctp_bind_addr *bp;
 	struct sctp_association *asoc;
-	struct list_head *pos, *temp;
 	struct sctp_sockaddr_entry *addr;
-	rwlock_t *addr_lock;
 	int cnt = 0;
 
 	if (len < sizeof(sctp_assoc_t))
@@ -4078,17 +4054,13 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len,
 	 */
 	if (0 == id) {
 		bp = &sctp_sk(sk)->ep->base.bind_addr;
-		addr_lock = &sctp_sk(sk)->ep->base.addr_lock;
 	} else {
 		asoc = sctp_id2assoc(sk, id);
 		if (!asoc)
 			return -EINVAL;
 		bp = &asoc->base.bind_addr;
-		addr_lock = &asoc->base.addr_lock;
 	}
 
-	sctp_read_lock(addr_lock);
-
 	/* If the endpoint is bound to 0.0.0.0 or ::0, count the valid
 	 * addresses from the global local address list.
 	 */
@@ -4096,27 +4068,33 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len,
 		addr = list_entry(bp->address_list.next,
 				  struct sctp_sockaddr_entry, list);
 		if (sctp_is_any(&addr->a)) {
-			list_for_each_safe(pos, temp, &sctp_local_addr_list) {
+			rcu_read_lock();
-				addr = list_entry(pos,
+			list_for_each_entry_rcu(addr,
-						  struct sctp_sockaddr_entry,
+						&sctp_local_addr_list, list) {
-						  list);
+				if (!addr->valid)
+					continue;
+
 				if ((PF_INET == sk->sk_family) &&
 				    (AF_INET6 == addr->a.sa.sa_family))
 					continue;
+
 				cnt++;
 			}
+			rcu_read_unlock();
 		} else {
 			cnt = 1;
 		}
 		goto done;
 	}
 
-	list_for_each(pos, &bp->address_list) {
+	/* Protection on the bound address list is not needed,
+	 * since in the socket option context we hold the socket lock,
+	 * so there is no way that the bound address list can change.
+	 */
+	list_for_each_entry(addr, &bp->address_list, list) {
 		cnt ++;
 	}
-
 done:
-	sctp_read_unlock(addr_lock);
 	return cnt;
 }
 
@@ -4127,14 +4105,16 @@ static int sctp_copy_laddrs_old(struct sock *sk, __u16 port,
 					int max_addrs, void *to,
 					int *bytes_copied)
 {
-	struct list_head *pos, *next;
 	struct sctp_sockaddr_entry *addr;
 	union sctp_addr temp;
 	int cnt = 0;
 	int addrlen;
 
-	list_for_each_safe(pos, next, &sctp_local_addr_list) {
+	rcu_read_lock();
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) {
+		if (!addr->valid)
+			continue;
+
 		if ((PF_INET == sk->sk_family) &&
 		    (AF_INET6 == addr->a.sa.sa_family))
 			continue;
@@ -4149,6 +4129,7 @@ static int sctp_copy_laddrs_old(struct sock *sk, __u16 port,
 		cnt ++;
 		if (cnt >= max_addrs) break;
 	}
+	rcu_read_unlock();
 
 	return cnt;
 }
@@ -4156,14 +4137,16 @@ static int sctp_copy_laddrs_old(struct sock *sk, __u16 port,
 static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to,
 			    size_t space_left, int *bytes_copied)
 {
-	struct list_head *pos, *next;
 	struct sctp_sockaddr_entry *addr;
 	union sctp_addr temp;
 	int cnt = 0;
 	int addrlen;
 
-	list_for_each_safe(pos, next, &sctp_local_addr_list) {
+	rcu_read_lock();
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) {
+		if (!addr->valid)
+			continue;
+
 		if ((PF_INET == sk->sk_family) &&
 		    (AF_INET6 == addr->a.sa.sa_family))
 			continue;
@@ -4171,8 +4154,10 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to,
 		sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk),
 								&temp);
 		addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
-		if (space_left < addrlen)
+		if (space_left < addrlen) {
-			return -ENOMEM;
+			cnt =  -ENOMEM;
+			break;
+		}
 		memcpy(to, &temp, addrlen);
 
 		to += addrlen;
@@ -4180,6 +4165,7 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to,
 		space_left -= addrlen;
 		*bytes_copied += addrlen;
 	}
+	rcu_read_unlock();
 
 	return cnt;
 }
@@ -4192,7 +4178,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
 {
 	struct sctp_bind_addr *bp;
 	struct sctp_association *asoc;
-	struct list_head *pos;
 	int cnt = 0;
 	struct sctp_getaddrs_old getaddrs;
 	struct sctp_sockaddr_entry *addr;
@@ -4200,7 +4185,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
 	union sctp_addr temp;
 	struct sctp_sock *sp = sctp_sk(sk);
 	int addrlen;
-	rwlock_t *addr_lock;
 	int err = 0;
 	void *addrs;
 	void *buf;
@@ -4222,13 +4206,11 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
 	 */
 	if (0 == getaddrs.assoc_id) {
 		bp = &sctp_sk(sk)->ep->base.bind_addr;
-		addr_lock = &sctp_sk(sk)->ep->base.addr_lock;
 	} else {
 		asoc = sctp_id2assoc(sk, getaddrs.assoc_id);
 		if (!asoc)
 			return -EINVAL;
 		bp = &asoc->base.bind_addr;
-		addr_lock = &asoc->base.addr_lock;
 	}
 
 	to = getaddrs.addrs;
@@ -4242,8 +4224,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
 	if (!addrs)
 		return -ENOMEM;
 
-	sctp_read_lock(addr_lock);
-
 	/* If the endpoint is bound to 0.0.0.0 or ::0, get the valid
 	 * addresses from the global local address list.
 	 */
@@ -4259,8 +4239,11 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
 	}
 
 	buf = addrs;
-	list_for_each(pos, &bp->address_list) {
+	/* Protection on the bound address list is not needed since
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	 * in the socket option context we hold a socket lock and
+	 * thus the bound address list can't change.
+	 */
+	list_for_each_entry(addr, &bp->address_list, list) {
 		memcpy(&temp, &addr->a, sizeof(temp));
 		sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
 		addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
@@ -4272,8 +4255,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len,
 	}
 
 copy_getaddrs:
-	sctp_read_unlock(addr_lock);
-
 	/* copy the entire address list into the user provided space */
 	if (copy_to_user(to, addrs, bytes_copied)) {
 		err = -EFAULT;
@@ -4295,7 +4276,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 {
 	struct sctp_bind_addr *bp;
 	struct sctp_association *asoc;
-	struct list_head *pos;
 	int cnt = 0;
 	struct sctp_getaddrs getaddrs;
 	struct sctp_sockaddr_entry *addr;
@@ -4303,7 +4283,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 	union sctp_addr temp;
 	struct sctp_sock *sp = sctp_sk(sk);
 	int addrlen;
-	rwlock_t *addr_lock;
 	int err = 0;
 	size_t space_left;
 	int bytes_copied = 0;
@@ -4324,13 +4303,11 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 	 */
 	if (0 == getaddrs.assoc_id) {
 		bp = &sctp_sk(sk)->ep->base.bind_addr;
-		addr_lock = &sctp_sk(sk)->ep->base.addr_lock;
 	} else {
 		asoc = sctp_id2assoc(sk, getaddrs.assoc_id);
 		if (!asoc)
 			return -EINVAL;
 		bp = &asoc->base.bind_addr;
-		addr_lock = &asoc->base.addr_lock;
 	}
 
 	to = optval + offsetof(struct sctp_getaddrs,addrs);
@@ -4340,8 +4317,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 	if (!addrs)
 		return -ENOMEM;
 
-	sctp_read_lock(addr_lock);
-
 	/* If the endpoint is bound to 0.0.0.0 or ::0, get the valid
 	 * addresses from the global local address list.
 	 */
@@ -4353,21 +4328,24 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 						space_left, &bytes_copied);
 			if (cnt < 0) {
 				err = cnt;
-				goto error_lock;
+				goto out;
 			}
 			goto copy_getaddrs;
 		}
 	}
 
 	buf = addrs;
-	list_for_each(pos, &bp->address_list) {
+	/* Protection on the bound address list is not needed since
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	 * in the socket option context we hold a socket lock and
+	 * thus the bound address list can't change.
+	 */
+	list_for_each_entry(addr, &bp->address_list, list) {
 		memcpy(&temp, &addr->a, sizeof(temp));
 		sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
 		addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
 		if (space_left < addrlen) {
 			err =  -ENOMEM; /*fixme: right error?*/
-			goto error_lock;
+			goto out;
 		}
 		memcpy(buf, &temp, addrlen);
 		buf += addrlen;
@@ -4377,8 +4355,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 	}
 
 copy_getaddrs:
-	sctp_read_unlock(addr_lock);
-
 	if (copy_to_user(to, addrs, bytes_copied)) {
 		err = -EFAULT;
 		goto out;
@@ -4389,12 +4365,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 	}
 	if (put_user(bytes_copied, optlen))
 		err = -EFAULT;
-
-	goto out;
-
-error_lock:
-	sctp_read_unlock(addr_lock);
-
 out:
 	kfree(addrs);
 	return err;