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) {
-		struct sk_buff *ns;
-
-		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;
-	}
+	if (skb_cow_head(skb, PPP_HDRLEN))
+		goto outf;
+
 	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
-		    && sk_run_filter(skb, ppp->pass_filter,
-				     ppp->pass_len) == 0) {
-			if (ppp->debug & 1)
-				printk(KERN_DEBUG "PPP: inbound frame not passed\n");
-			kfree_skb(skb);
-			return;
-		}
-		if (!(ppp->active_filter
-		      && sk_run_filter(skb, ppp->active_filter,
-				       ppp->active_len) == 0))
-			ppp->last_recv = jiffies;
-		skb_pull(skb, 2);
-#else
-		ppp->last_recv = jiffies;
+		if (ppp->pass_filter || ppp->active_filter) {
+			if (skb_cloned(skb) &&
+			    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+				goto err;
+
+			*skb_push(skb, 2) = 0;
+			if (ppp->pass_filter
+			    && sk_run_filter(skb, ppp->pass_filter,
+					     ppp->pass_len) == 0) {
+				if (ppp->debug & 1)
+					printk(KERN_DEBUG "PPP: inbound frame "
+					       "not passed\n");
+				kfree_skb(skb);
+				return;
+			}
+			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. */
-	if (headroom < (sizeof(struct pppoe_hdr) + dev->hard_header_len)) {
-		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;
-	}
+	/* Copy the data if there is no space for the header or if it's
+	 * read-only.
+	 */
+	if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
+		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_push(skb, sizeof(*ph));
+	skb_reset_network_header(skb);
 
-	skb_reset_network_header(skb2);
+	ph = pppoe_hdr(skb);
+	ph->ver	= 1;
+	ph->type = 1;
+	ph->code = 0;
+	ph->sid	= po->num;
+	ph->length = htons(data_len);
 
-	skb2->dev = dev;
+	skb->protocol = __constant_htons(ETH_P_PPP_SES);
+	skb->dev = dev;
 
-	dev->hard_header(skb2, dev, ETH_P_PPP_SES,
+	dev->hard_header(skb, 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 (dev_queue_xmit(skb2) < 0)
+	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) -
-			skb_headroom(skb);
-
-	if (delta < 0)
-		delta = 0;
+	return __skb_cow(skb, headroom, skb_cloned(skb));
+}
 
-	if (delta || skb_cloned(skb))
-		return pskb_expand_head(skb, (delta + (NET_SKB_PAD-1)) &
-				~(NET_SKB_PAD-1), 0, GFP_ATOMIC);
-	return 0;
+/**
+ *	skb_cow_head - skb_cow but only making the head writable
+ *	@skb: buffer to cow
+ *	@headroom: needed headroom
+ *
+ *	This function is identical to skb_cow except that we replace the
+ *	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

@@ -207,6 +207,9 @@ extern struct sctp_globals {
 	 * It is a list of sctp_sockaddr_entry.
 	 */
 	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);
 }