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

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (32 commits)
  [NET]: Fix more per-cpu typos
  [SECURITY]: Fix build with CONFIG_SECURITY disabled.
  [I/OAT]: Remove CPU hotplug lock from net_dma_rebalance
  [DECNET]: Fix for routing bug
  [AF_UNIX]: Kernel memory leak fix for af_unix datagram getpeersec patch
  [NET]: skb_queue_lock_key() is no longer used.
  [NET]: Remove lockdep_set_class() call from skb_queue_head_init().
  [IPV6]: SNMPv2 "ipv6IfStatsOutFragCreates" counter error
  [IPV6]: SNMPv2 "ipv6IfStatsInHdrErrors" counter error
  [NET]: Kill the WARN_ON() calls for checksum fixups.
  [NETFILTER]: xt_hashlimit/xt_string: missing string validation
  [NETFILTER]: SIP helper: expect RTP streams in both directions
  [E1000]: Convert to netdev_alloc_skb
  [TG3]: Convert to netdev_alloc_skb
  [NET]: Add netdev_alloc_skb().
  [TCP]: Process linger2 timeout consistently.
  [SECURITY] secmark: nul-terminate secdata
  [NET] infiniband: Cleanup ib_addr module to use the netevents
  [NET]: Core net changes to generate netevents
  [NET]: Network Event Notifier Mechanism.
  ...

drivers/infiniband/core/addr.c

@@ -35,6 +35,7 @@
 #include <net/arp.h>
 #include <net/neighbour.h>
 #include <net/route.h>
+#include <net/netevent.h>
 #include <rdma/ib_addr.h>
 
 MODULE_AUTHOR("Sean Hefty");
@@ -326,25 +327,22 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr)
 }
 EXPORT_SYMBOL(rdma_addr_cancel);
 
-static int addr_arp_recv(struct sk_buff *skb, struct net_device *dev,
-			 struct packet_type *pkt, struct net_device *orig_dev)
+static int netevent_callback(struct notifier_block *self, unsigned long event, 
+	void *ctx)
 {
-	struct arphdr *arp_hdr;
+	if (event == NETEVENT_NEIGH_UPDATE) {  
+		struct neighbour *neigh = ctx;
 
-	arp_hdr = (struct arphdr *) skb->nh.raw;
-
-	if (arp_hdr->ar_op == htons(ARPOP_REQUEST) ||
-	    arp_hdr->ar_op == htons(ARPOP_REPLY))
-		set_timeout(jiffies);
-
-	kfree_skb(skb);
+		if (neigh->dev->type == ARPHRD_INFINIBAND &&
+		    (neigh->nud_state & NUD_VALID)) {
+			set_timeout(jiffies);
+		}
+	}
 	return 0;
 }
 
-static struct packet_type addr_arp = {
-	.type           = __constant_htons(ETH_P_ARP),
-	.func           = addr_arp_recv,
-	.af_packet_priv = (void*) 1,
+static struct notifier_block nb = {
+	.notifier_call = netevent_callback
 };
 
 static int addr_init(void)
@@ -353,13 +351,13 @@ static int addr_init(void)
 	if (!addr_wq)
 		return -ENOMEM;
 
-	dev_add_pack(&addr_arp);
+	register_netevent_notifier(&nb);
 	return 0;
 }
 
 static void addr_cleanup(void)
 {
-	dev_remove_pack(&addr_arp);
+	unregister_netevent_notifier(&nb);
 	destroy_workqueue(addr_wq);
 }
 

drivers/net/appletalk/Kconfig

@@ -29,7 +29,7 @@ config ATALK
 	  even politically correct people are allowed to say Y here.
 
 config DEV_APPLETALK
-	bool "Appletalk interfaces support"
+	tristate "Appletalk interfaces support"
 	depends on ATALK
 	help
 	  AppleTalk is the protocol that Apple computers can use to communicate

drivers/net/e1000/e1000_main.c

@@ -3127,7 +3127,7 @@ e1000_change_mtu(struct net_device *netdev, int new_mtu)
 		break;
 	}
 
-	/* NOTE: dev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
+	/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
 	 * means we reserve 2 more, this pushes us to allocate from the next
 	 * larger slab size
 	 * i.e. RXBUFFER_2048 --> size-4096 slab */
@@ -3708,7 +3708,7 @@ e1000_clean_rx_irq(struct e1000_adapter *adapter,
 #define E1000_CB_LENGTH 256
 		if (length < E1000_CB_LENGTH) {
 			struct sk_buff *new_skb =
-			    dev_alloc_skb(length + NET_IP_ALIGN);
+			    netdev_alloc_skb(netdev, length + NET_IP_ALIGN);
 			if (new_skb) {
 				skb_reserve(new_skb, NET_IP_ALIGN);
 				new_skb->dev = netdev;
@@ -3979,7 +3979,7 @@ e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 
 	while (cleaned_count--) {
 		if (!(skb = buffer_info->skb))
-			skb = dev_alloc_skb(bufsz);
+			skb = netdev_alloc_skb(netdev, bufsz);
 		else {
 			skb_trim(skb, 0);
 			goto map_skb;
@@ -3997,7 +3997,7 @@ e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 			DPRINTK(RX_ERR, ERR, "skb align check failed: %u bytes "
 					     "at %p\n", bufsz, skb->data);
 			/* Try again, without freeing the previous */
-			skb = dev_alloc_skb(bufsz);
+			skb = netdev_alloc_skb(netdev, bufsz);
 			/* Failed allocation, critical failure */
 			if (!skb) {
 				dev_kfree_skb(oldskb);
@@ -4121,7 +4121,8 @@ e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter,
 				rx_desc->read.buffer_addr[j+1] = ~0;
 		}
 
-		skb = dev_alloc_skb(adapter->rx_ps_bsize0 + NET_IP_ALIGN);
+		skb = netdev_alloc_skb(netdev,
+				       adapter->rx_ps_bsize0 + NET_IP_ALIGN);
 
 		if (unlikely(!skb)) {
 			adapter->alloc_rx_buff_failed++;

drivers/net/tg3.c

@@ -68,8 +68,8 @@
 
 #define DRV_MODULE_NAME		"tg3"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"3.63"
-#define DRV_MODULE_RELDATE	"July 25, 2006"
+#define DRV_MODULE_VERSION	"3.64"
+#define DRV_MODULE_RELDATE	"July 31, 2006"
 
 #define TG3_DEF_MAC_MODE	0
 #define TG3_DEF_RX_MODE		0
@@ -3097,7 +3097,7 @@ static int tg3_alloc_rx_skb(struct tg3 *tp, u32 opaque_key,
 	 * Callers depend upon this behavior and assume that
 	 * we leave everything unchanged if we fail.
 	 */
-	skb = dev_alloc_skb(skb_size);
+	skb = netdev_alloc_skb(tp->dev, skb_size);
 	if (skb == NULL)
 		return -ENOMEM;
 
@@ -3270,7 +3270,7 @@ static int tg3_rx(struct tg3 *tp, int budget)
 			tg3_recycle_rx(tp, opaque_key,
 				       desc_idx, *post_ptr);
 
-			copy_skb = dev_alloc_skb(len + 2);
+			copy_skb = netdev_alloc_skb(tp->dev, len + 2);
 			if (copy_skb == NULL)
 				goto drop_it_no_recycle;
 
@@ -8618,7 +8618,7 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode)
 	err = -EIO;
 
 	tx_len = 1514;
-	skb = dev_alloc_skb(tx_len);
+	skb = netdev_alloc_skb(tp->dev, tx_len);
 	if (!skb)
 		return -ENOMEM;
 

include/linux/netfilter_bridge.h

@@ -6,7 +6,6 @@
 
 #include <linux/netfilter.h>
 #if defined(__KERNEL__) && defined(CONFIG_BRIDGE_NETFILTER)
-#include <asm/atomic.h>
 #include <linux/if_ether.h>
 #endif
 

include/linux/security.h

@@ -1109,6 +1109,16 @@ struct swap_info_struct;
  *	@name contains the name of the security module being unstacked.
  *	@ops contains a pointer to the struct security_operations of the module to unstack.
  * 
+ * @secid_to_secctx:
+ *	Convert secid to security context.
+ *	@secid contains the security ID.
+ *	@secdata contains the pointer that stores the converted security context.
+ *
+ * @release_secctx:
+ *	Release the security context.
+ *	@secdata contains the security context.
+ *	@seclen contains the length of the security context.
+ *
  * This is the main security structure.
  */
 struct security_operations {
@@ -1289,6 +1299,8 @@ struct security_operations {
 
  	int (*getprocattr)(struct task_struct *p, char *name, void *value, size_t size);
  	int (*setprocattr)(struct task_struct *p, char *name, void *value, size_t size);
+	int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen);
+	void (*release_secctx)(char *secdata, u32 seclen);
 
 #ifdef CONFIG_SECURITY_NETWORK
 	int (*unix_stream_connect) (struct socket * sock,
@@ -1317,7 +1329,7 @@ struct security_operations {
 	int (*socket_shutdown) (struct socket * sock, int how);
 	int (*socket_sock_rcv_skb) (struct sock * sk, struct sk_buff * skb);
 	int (*socket_getpeersec_stream) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len);
-	int (*socket_getpeersec_dgram) (struct sk_buff *skb, char **secdata, u32 *seclen);
+	int (*socket_getpeersec_dgram) (struct socket *sock, struct sk_buff *skb, u32 *secid);
 	int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority);
 	void (*sk_free_security) (struct sock *sk);
 	unsigned int (*sk_getsid) (struct sock *sk, struct flowi *fl, u8 dir);
@@ -2059,6 +2071,16 @@ static inline int security_netlink_recv(struct sk_buff * skb, int cap)
 	return security_ops->netlink_recv(skb, cap);
 }
 
+static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
+{
+	return security_ops->secid_to_secctx(secid, secdata, seclen);
+}
+
+static inline void security_release_secctx(char *secdata, u32 seclen)
+{
+	return security_ops->release_secctx(secdata, seclen);
+}
+
 /* prototypes */
 extern int security_init	(void);
 extern int register_security	(struct security_operations *ops);
@@ -2725,6 +2747,14 @@ static inline void securityfs_remove(struct dentry *dentry)
 {
 }
 
+static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void security_release_secctx(char *secdata, u32 seclen)
+{
+}
 #endif	/* CONFIG_SECURITY */
 
 #ifdef CONFIG_SECURITY_NETWORK
@@ -2840,10 +2870,9 @@ static inline int security_socket_getpeersec_stream(struct socket *sock, char __
 	return security_ops->socket_getpeersec_stream(sock, optval, optlen, len);
 }
 
-static inline int security_socket_getpeersec_dgram(struct sk_buff *skb, char **secdata,
-						   u32 *seclen)
+static inline int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid)
 {
-	return security_ops->socket_getpeersec_dgram(skb, secdata, seclen);
+	return security_ops->socket_getpeersec_dgram(sock, skb, secid);
 }
 
 static inline int security_sk_alloc(struct sock *sk, int family, gfp_t priority)
@@ -2968,8 +2997,7 @@ static inline int security_socket_getpeersec_stream(struct socket *sock, char __
 	return -ENOPROTOOPT;
 }
 
-static inline int security_socket_getpeersec_dgram(struct sk_buff *skb, char **secdata,
-						   u32 *seclen)
+static inline int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid)
 {
 	return -ENOPROTOOPT;
 }

include/linux/skbuff.h

@@ -604,12 +604,17 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_)
 	return list_->qlen;
 }
 
-extern struct lock_class_key skb_queue_lock_key;
-
+/*
+ * This function creates a split out lock class for each invocation;
+ * this is needed for now since a whole lot of users of the skb-queue
+ * infrastructure in drivers have different locking usage (in hardirq)
+ * than the networking core (in softirq only). In the long run either the
+ * network layer or drivers should need annotation to consolidate the
+ * main types of usage into 3 classes.
+ */
 static inline void skb_queue_head_init(struct sk_buff_head *list)
 {
 	spin_lock_init(&list->lock);
-	lockdep_set_class(&list->lock, &skb_queue_lock_key);
 	list->prev = list->next = (struct sk_buff *)list;
 	list->qlen = 0;
 }
@@ -1104,6 +1109,28 @@ static inline struct sk_buff *dev_alloc_skb(unsigned int length)
 	return __dev_alloc_skb(length, GFP_ATOMIC);
 }
 
+extern struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
+		unsigned int length, gfp_t gfp_mask);
+
+/**
+ *	netdev_alloc_skb - allocate an skbuff for rx on a specific device
+ *	@dev: network device to receive on
+ *	@length: length to allocate
+ *
+ *	Allocate a new &sk_buff and assign it a usage count of one. The
+ *	buffer has unspecified headroom built in. Users should allocate
+ *	the headroom they think they need without accounting for the
+ *	built in space. The built in space is used for optimisations.
+ *
+ *	%NULL is returned if there is no free memory. Although this function
+ *	allocates memory it can be called from an interrupt.
+ */
+static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev,
+		unsigned int length)
+{
+	return __netdev_alloc_skb(dev, length, GFP_ATOMIC);
+}
+
 /**
  *	skb_cow - copy header of skb when it is required
  *	@skb: buffer to cow

include/net/af_unix.h

@@ -54,15 +54,13 @@ struct unix_skb_parms {
 	struct ucred		creds;		/* Skb credentials	*/
 	struct scm_fp_list	*fp;		/* Passed files		*/
 #ifdef CONFIG_SECURITY_NETWORK
-	char			*secdata;	/* Security context	*/
-	u32			seclen;		/* Security length	*/
+	u32			secid;		/* Security ID		*/
 #endif
 };
 
 #define UNIXCB(skb) 	(*(struct unix_skb_parms*)&((skb)->cb))
 #define UNIXCREDS(skb)	(&UNIXCB((skb)).creds)
-#define UNIXSECDATA(skb)	(&UNIXCB((skb)).secdata)
-#define UNIXSECLEN(skb)		(&UNIXCB((skb)).seclen)
+#define UNIXSID(skb)	(&UNIXCB((skb)).secid)
 
 #define unix_state_rlock(s)	spin_lock(&unix_sk(s)->lock)
 #define unix_state_runlock(s)	spin_unlock(&unix_sk(s)->lock)

include/net/ip6_route.h

@@ -139,16 +139,22 @@ extern rwlock_t rt6_lock;
 /*
  *	Store a destination cache entry in a socket
  */
-static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
-				     struct in6_addr *daddr)
+static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst,
+				   struct in6_addr *daddr)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct rt6_info *rt = (struct rt6_info *) dst;
 
-	write_lock(&sk->sk_dst_lock);
 	sk_setup_caps(sk, dst);
 	np->daddr_cache = daddr;
 	np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+}
+
+static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
+				 struct in6_addr *daddr)
+{
+	write_lock(&sk->sk_dst_lock);
+	__ip6_dst_store(sk, dst, daddr);
 	write_unlock(&sk->sk_dst_lock);
 }
 

include/net/ipv6.h

@@ -468,6 +468,9 @@ extern void			ip6_flush_pending_frames(struct sock *sk);
 extern int			ip6_dst_lookup(struct sock *sk,
 					       struct dst_entry **dst,
 					       struct flowi *fl);
+extern int			ip6_sk_dst_lookup(struct sock *sk,
+						  struct dst_entry **dst,
+						  struct flowi *fl);
 
 /*
  *	skb processing functions

include/net/netdma.h

@@ -29,7 +29,7 @@ static inline struct dma_chan *get_softnet_dma(void)
 {
 	struct dma_chan *chan;
 	rcu_read_lock();
-	chan = rcu_dereference(__get_cpu_var(softnet_data.net_dma));
+	chan = rcu_dereference(__get_cpu_var(softnet_data).net_dma);
 	if (chan)
 		dma_chan_get(chan);
 	rcu_read_unlock();

include/net/netevent.h

@@ -0,0 +1,33 @@
+#ifndef _NET_EVENT_H
+#define _NET_EVENT_H
+
+/*
+ *	Generic netevent notifiers
+ *
+ *	Authors:
+ *      Tom Tucker              <tom@opengridcomputing.com>
+ *      Steve Wise              <swise@opengridcomputing.com>
+ *
+ * 	Changes:
+ */
+#ifdef __KERNEL__
+
+#include <net/dst.h>
+
+struct netevent_redirect {
+	struct dst_entry *old;
+	struct dst_entry *new;
+};
+
+enum netevent_notif_type {
+	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
+	NETEVENT_PMTU_UPDATE,	   /* arg is struct dst_entry ptr */
+	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
+};
+
+extern int register_netevent_notifier(struct notifier_block *nb);
+extern int unregister_netevent_notifier(struct notifier_block *nb);
+extern int call_netevent_notifiers(unsigned long val, void *v);
+
+#endif
+#endif