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

Documentation/networking/ip-sysctl.txt

@@ -46,6 +46,29 @@ ipfrag_secret_interval - INTEGER
 	for the hash secret) for IP fragments.
 	Default: 600
 
+ipfrag_max_dist - INTEGER
+	ipfrag_max_dist is a non-negative integer value which defines the 
+	maximum "disorder" which is allowed among fragments which share a 
+	common IP source address. Note that reordering of packets is 
+	not unusual, but if a large number of fragments arrive from a source 
+	IP address while a particular fragment queue remains incomplete, it 
+	probably indicates that one or more fragments belonging to that queue 
+	have been lost. When ipfrag_max_dist is positive, an additional check 
+	is done on fragments before they are added to a reassembly queue - if 
+	ipfrag_max_dist (or more) fragments have arrived from a particular IP 
+	address between additions to any IP fragment queue using that source 
+	address, it's presumed that one or more fragments in the queue are 
+	lost. The existing fragment queue will be dropped, and a new one 
+	started. An ipfrag_max_dist value of zero disables this check.
+
+	Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can
+	result in unnecessarily dropping fragment queues when normal
+	reordering of packets occurs, which could lead to poor application 
+	performance. Using a very large value, e.g. 50000, increases the 
+	likelihood of incorrectly reassembling IP fragments that originate 
+	from different IP datagrams, which could result in data corruption.
+	Default: 64
+
 INET peer storage:
 
 inet_peer_threshold - INTEGER

drivers/char/random.c

@@ -1554,10 +1554,8 @@ __u32 secure_tcp_sequence_number(__u32 saddr, __u32 daddr,
 
 EXPORT_SYMBOL(secure_tcp_sequence_number);
 
-
-
-/* Generate secure starting point for ephemeral TCP port search */
-u32 secure_tcp_port_ephemeral(__u32 saddr, __u32 daddr, __u16 dport)
+/* Generate secure starting point for ephemeral IPV4 transport port search */
+u32 secure_ipv4_port_ephemeral(__u32 saddr, __u32 daddr, __u16 dport)
 {
 	struct keydata *keyptr = get_keyptr();
 	u32 hash[4];
@@ -1575,7 +1573,7 @@ u32 secure_tcp_port_ephemeral(__u32 saddr, __u32 daddr, __u16 dport)
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-u32 secure_tcpv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, __u16 dport)
+u32 secure_ipv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, __u16 dport)
 {
 	struct keydata *keyptr = get_keyptr();
 	u32 hash[12];
@@ -1586,7 +1584,7 @@ u32 secure_tcpv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, __u16 dp
 
 	return twothirdsMD4Transform(daddr, hash);
 }
-EXPORT_SYMBOL(secure_tcpv6_port_ephemeral);
+EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -47,6 +47,8 @@
 #include <linux/ip.h>
 #include <linux/in.h>
 
+#include <net/dst.h>
+
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("IP-over-InfiniBand net driver");
 MODULE_LICENSE("Dual BSD/GPL");

drivers/infiniband/ulp/ipoib/ipoib_multicast.c

@@ -43,6 +43,8 @@
 #include <linux/delay.h>
 #include <linux/completion.h>
 
+#include <net/dst.h>
+
 #include "ipoib.h"
 
 #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG

drivers/net/ns83820.c

@@ -115,6 +115,7 @@
 #include <linux/ethtool.h>
 #include <linux/timer.h>
 #include <linux/if_vlan.h>
+#include <linux/rtnetlink.h>
 
 #include <asm/io.h>
 #include <asm/uaccess.h>

drivers/net/pppoe.c

@@ -85,7 +85,7 @@ static int pppoe_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb);
 static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb);
 
-static struct proto_ops pppoe_ops;
+static const struct proto_ops pppoe_ops;
 static DEFINE_RWLOCK(pppoe_hash_lock);
 
 static struct ppp_channel_ops pppoe_chan_ops;
@@ -383,8 +383,6 @@ static int pppoe_rcv(struct sk_buff *skb,
 {
 	struct pppoe_hdr *ph;
 	struct pppox_sock *po;
-	struct sock *sk;
-	int ret;
 
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto drop;
@@ -395,24 +393,8 @@ static int pppoe_rcv(struct sk_buff *skb,
 	ph = (struct pppoe_hdr *) skb->nh.raw;
 
 	po = get_item((unsigned long) ph->sid, eth_hdr(skb)->h_source);
-	if (!po) 
-		goto drop;
-
-	sk = sk_pppox(po);
-	bh_lock_sock(sk);
-
-	/* Socket state is unknown, must put skb into backlog. */
-	if (sock_owned_by_user(sk) != 0) {
-		sk_add_backlog(sk, skb);
-		ret = NET_RX_SUCCESS;
-	} else {
-		ret = pppoe_rcv_core(sk, skb);
-	}
-
-	bh_unlock_sock(sk);
-	sock_put(sk);
-
-	return ret;
+	if (po != NULL) 
+		return sk_receive_skb(sk_pppox(po), skb);
 drop:
 	kfree_skb(skb);
 out:
@@ -1081,9 +1063,7 @@ static int __init pppoe_proc_init(void)
 static inline int pppoe_proc_init(void) { return 0; }
 #endif /* CONFIG_PROC_FS */
 
-/* ->ioctl are set at pppox_create */
-
-static struct proto_ops pppoe_ops = {
+static const struct proto_ops pppoe_ops = {
     .family		= AF_PPPOX,
     .owner		= THIS_MODULE,
     .release		= pppoe_release,
@@ -1099,7 +1079,8 @@ static struct proto_ops pppoe_ops = {
     .getsockopt		= sock_no_getsockopt,
     .sendmsg		= pppoe_sendmsg,
     .recvmsg		= pppoe_recvmsg,
-    .mmap		= sock_no_mmap
+    .mmap		= sock_no_mmap,
+    .ioctl		= pppox_ioctl,
 };
 
 static struct pppox_proto pppoe_proto = {

drivers/net/pppox.c

@@ -68,8 +68,7 @@ EXPORT_SYMBOL(register_pppox_proto);
 EXPORT_SYMBOL(unregister_pppox_proto);
 EXPORT_SYMBOL(pppox_unbind_sock);
 
-static int pppox_ioctl(struct socket* sock, unsigned int cmd, 
-		       unsigned long arg)
+int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	struct sock *sk = sock->sk;
 	struct pppox_sock *po = pppox_sk(sk);
@@ -105,6 +104,7 @@ static int pppox_ioctl(struct socket* sock, unsigned int cmd,
 	return rc;
 }
 
+EXPORT_SYMBOL(pppox_ioctl);
 
 static int pppox_create(struct socket *sock, int protocol)
 {
@@ -119,11 +119,7 @@ static int pppox_create(struct socket *sock, int protocol)
 		goto out;
 
 	rc = pppox_protos[protocol]->create(sock);
-	if (!rc) {
-		/* We get to set the ioctl handler. */
-		/* For everything else, pppox is just a shell. */
-		sock->ops->ioctl = pppox_ioctl;
-	}
+
 	module_put(pppox_protos[protocol]->owner);
 out:
 	return rc;

drivers/net/sk98lin/skge.c

@@ -107,6 +107,7 @@
 
 #include	"h/skversion.h"
 
+#include	<linux/in.h>
 #include	<linux/module.h>
 #include	<linux/moduleparam.h>
 #include	<linux/init.h>

drivers/net/skge.c

@@ -25,6 +25,7 @@
  */
 
 #include <linux/config.h>
+#include <linux/in.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>

drivers/net/tg3.c

@@ -24,6 +24,7 @@
 #include <linux/compiler.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/in.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
@@ -3650,7 +3651,7 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			       TXD_FLAG_CPU_POST_DMA);
 
 		skb->nh.iph->check = 0;
-		skb->nh.iph->tot_len = ntohs(mss + ip_tcp_len + tcp_opt_len);
+		skb->nh.iph->tot_len = htons(mss + ip_tcp_len + tcp_opt_len);
 		if (tp->tg3_flags2 & TG3_FLG2_HW_TSO) {
 			skb->h.th->check = 0;
 			base_flags &= ~TXD_FLAG_TCPUDP_CSUM;

drivers/net/wireless/ipw2200.c

@@ -7456,8 +7456,7 @@ static void ipw_handle_data_packet(struct ipw_priv *priv,
 	/* HW decrypt will not clear the WEP bit, MIC, PN, etc. */
 	hdr = (struct ieee80211_hdr_4addr *)rxb->skb->data;
 	if (priv->ieee->iw_mode != IW_MODE_MONITOR &&
-	    ((is_multicast_ether_addr(hdr->addr1) ||
-	      is_broadcast_ether_addr(hdr->addr1)) ?
+	    (is_multicast_ether_addr(hdr->addr1) ?
 	     !priv->ieee->host_mc_decrypt : !priv->ieee->host_decrypt))
 		ipw_rebuild_decrypted_skb(priv, rxb->skb);
 
@@ -7648,8 +7647,7 @@ static inline int is_network_packet(struct ipw_priv *priv,
 			return 0;
 
 		/* {broad,multi}cast packets to our BSSID go through */
-		if (is_multicast_ether_addr(header->addr1) ||
-		    is_broadcast_ether_addr(header->addr1))
+		if (is_multicast_ether_addr(header->addr1))
 			return !memcmp(header->addr3, priv->bssid, ETH_ALEN);
 
 		/* packets to our adapter go through */
@@ -7662,8 +7660,7 @@ static inline int is_network_packet(struct ipw_priv *priv,
 			return 0;
 
 		/* {broad,multi}cast packets to our BSS go through */
-		if (is_multicast_ether_addr(header->addr1) ||
-		    is_broadcast_ether_addr(header->addr1))
+		if (is_multicast_ether_addr(header->addr1))
 			return !memcmp(header->addr2, priv->bssid, ETH_ALEN);
 
 		/* packets to our adapter go through */
@@ -9657,8 +9654,7 @@ static inline int ipw_tx_skb(struct ipw_priv *priv, struct ieee80211_txb *txb,
 	switch (priv->ieee->iw_mode) {
 	case IW_MODE_ADHOC:
 		hdr_len = IEEE80211_3ADDR_LEN;
-		unicast = !(is_multicast_ether_addr(hdr->addr1) ||
-			    is_broadcast_ether_addr(hdr->addr1));
+		unicast = !is_multicast_ether_addr(hdr->addr1);
 		id = ipw_find_station(priv, hdr->addr1);
 		if (id == IPW_INVALID_STATION) {
 			id = ipw_add_station(priv, hdr->addr1);
@@ -9673,8 +9669,7 @@ static inline int ipw_tx_skb(struct ipw_priv *priv, struct ieee80211_txb *txb,
 
 	case IW_MODE_INFRA:
 	default:
-		unicast = !(is_multicast_ether_addr(hdr->addr3) ||
-			    is_broadcast_ether_addr(hdr->addr3));
+		unicast = !is_multicast_ether_addr(hdr->addr3);
 		hdr_len = IEEE80211_3ADDR_LEN;
 		id = 0;
 		break;

fs/9p/trans_sock.c

@@ -26,6 +26,7 @@
  */
 
 #include <linux/config.h>
+#include <linux/in.h>
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/ipv6.h>

fs/nfs/callback.c

@@ -14,6 +14,9 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
+
+#include <net/inet_sock.h>
+
 #include "nfs4_fs.h"
 #include "callback.h"
 

include/asm-alpha/bitops.h

@@ -321,6 +321,7 @@ static inline int fls(int word)
 #else
 #define fls	generic_fls
 #endif
+#define fls64   generic_fls64
 
 /* Compute powers of two for the given integer.  */
 static inline long floor_log2(unsigned long word)

include/asm-arm/bitops.h

@@ -332,6 +332,7 @@ static inline unsigned long __ffs(unsigned long word)
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 /*
  * ffs: find first bit set. This is defined the same way as
@@ -351,6 +352,7 @@ static inline unsigned long __ffs(unsigned long word)
 #define fls(x) \
 	( __builtin_constant_p(x) ? generic_fls(x) : \
 	  ({ int __r; asm("clz\t%0, %1" : "=r"(__r) : "r"(x) : "cc"); 32-__r; }) )
+#define fls64(x)   generic_fls64(x)
 #define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
 #define __ffs(x) (ffs(x) - 1)
 #define ffz(x) __ffs( ~(x) )

include/asm-arm26/bitops.h

@@ -259,6 +259,7 @@ static inline unsigned long __ffs(unsigned long word)
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 /*
  * ffs: find first bit set. This is defined the same way as

include/asm-cris/bitops.h

@@ -240,6 +240,7 @@ static inline int test_bit(int nr, const volatile unsigned long *addr)
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 /*
  * hweightN - returns the hamming weight of a N-bit word

include/asm-frv/bitops.h

@@ -228,6 +228,7 @@ found_middle:
 							\
 	bit ? 33 - bit : bit;				\
 })
+#define fls64(x)   generic_fls64(x)
 
 /*
  * Every architecture must define this function. It's the fastest

include/asm-generic/bitops.h

@@ -56,6 +56,7 @@ extern __inline__ int test_bit(int nr, const unsigned long * addr)
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #ifdef __KERNEL__
 

include/asm-h8300/bitops.h

@@ -406,5 +406,6 @@ found_middle:
 #endif /* __KERNEL__ */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #endif /* _H8300_BITOPS_H */

include/asm-i386/bitops.h

@@ -372,6 +372,7 @@ static inline unsigned long ffz(unsigned long word)
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #ifdef __KERNEL__
 

include/asm-ia64/bitops.h

@@ -345,6 +345,7 @@ fls (int t)
 	x |= x >> 16;
 	return ia64_popcnt(x);
 }
+#define fls64(x)   generic_fls64(x)
 
 /*
  * ffs: find first bit set. This is defined the same way as the libc and compiler builtin

include/asm-m32r/bitops.h

@@ -465,6 +465,7 @@ static __inline__ unsigned long __ffs(unsigned long word)
  * fls: find last bit set.
  */
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #ifdef __KERNEL__
 

include/asm-m68k/bitops.h

@@ -310,6 +310,7 @@ static inline int fls(int x)
 
 	return 32 - cnt;
 }
+#define fls64(x)   generic_fls64(x)
 
 /*
  * Every architecture must define this function. It's the fastest

include/asm-m68knommu/bitops.h

@@ -499,5 +499,6 @@ found_middle:
  * fls: find last bit set.
  */
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #endif /* _M68KNOMMU_BITOPS_H */

include/asm-mips/bitops.h

@@ -695,7 +695,7 @@ static inline unsigned long fls(unsigned long word)
 
 	return flz(~word) + 1;
 }
-
+#define fls64(x)   generic_fls64(x)
 
 /*
  * find_next_zero_bit - find the first zero bit in a memory region

include/asm-parisc/bitops.h

@@ -263,6 +263,7 @@ static __inline__ int fls(int x)
 
 	return ret;
 }
+#define fls64(x)   generic_fls64(x)
 
 /*
  * hweightN: returns the hamming weight (i.e. the number

include/asm-powerpc/bitops.h

@@ -310,6 +310,7 @@ static __inline__ int fls(unsigned int x)
 	asm ("cntlzw %0,%1" : "=r" (lz) : "r" (x));
 	return 32 - lz;
 }
+#define fls64(x)   generic_fls64(x)
 
 /*
  * hweightN: returns the hamming weight (i.e. the number

include/asm-s390/bitops.h

@@ -839,6 +839,7 @@ static inline int sched_find_first_bit(unsigned long *b)
  * fls: find last bit set.
  */
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 /*
  * hweightN: returns the hamming weight (i.e. the number

include/asm-sh/bitops.h

@@ -470,6 +470,7 @@ found_middle:
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #endif /* __KERNEL__ */
 

include/asm-sh64/bitops.h

@@ -510,6 +510,7 @@ found_middle:
 
 #define ffs(x)	generic_ffs(x)
 #define fls(x)	generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #endif /* __KERNEL__ */
 

include/asm-sparc/bitops.h

@@ -298,6 +298,7 @@ static inline int ffs(int x)
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 /*
  * hweightN: returns the hamming weight (i.e. the number

include/asm-sparc64/bitops.h

@@ -119,6 +119,7 @@ static inline unsigned long __ffs(unsigned long word)
  */
 
 #define fls(x) generic_fls(x)
+#define fls64(x)   generic_fls64(x)
 
 #ifdef __KERNEL__
 

include/asm-v850/bitops.h

@@ -276,6 +276,7 @@ found_middle:
 
 #define ffs(x) generic_ffs (x)
 #define fls(x) generic_fls (x)
+#define fls64(x) generic_fls64(x)
 #define __ffs(x) ffs(x)
 
 

include/asm-x86_64/bitops.h

@@ -340,6 +340,20 @@ static __inline__ unsigned long __ffs(unsigned long word)
 	return word;
 }
 
+/*
+ * __fls: find last bit set.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static __inline__ unsigned long __fls(unsigned long word)
+{
+	__asm__("bsrq %1,%0"
+		:"=r" (word)
+		:"rm" (word));
+	return word;
+}
+
 #ifdef __KERNEL__
 
 static inline int sched_find_first_bit(const unsigned long *b)
@@ -369,6 +383,19 @@ static __inline__ int ffs(int x)
 	return r+1;
 }
 
+/**
+ * fls64 - find last bit set in 64 bit word
+ * @x: the word to search
+ *
+ * This is defined the same way as fls.
+ */
+static __inline__ int fls64(__u64 x)
+{
+	if (x == 0)
+		return 0;
+	return __fls(x) + 1;
+}
+
 /**
  * hweightN - returns the hamming weight of a N-bit word
  * @x: the word to weigh

include/asm-xtensa/bitops.h

@@ -245,6 +245,7 @@ static __inline__ int fls (unsigned int x)
 {
 	return __cntlz(x);
 }
+#define fls64(x)   generic_fls64(x)
 
 static __inline__ int
 find_next_bit(const unsigned long *addr, int size, int offset)

include/linux/bitops.h

@@ -76,6 +76,15 @@ static __inline__ int generic_fls(int x)
  */
 #include <asm/bitops.h>
 
+
+static inline int generic_fls64(__u64 x)
+{
+	__u32 h = x >> 32;
+	if (h)
+		return fls(x) + 32;
+	return fls(x);
+}
+
 static __inline__ int get_bitmask_order(unsigned int count)
 {
 	int order;

include/linux/dccp.h

@@ -192,10 +192,9 @@ enum {
 #include <linux/workqueue.h>
 
 #include <net/inet_connection_sock.h>
+#include <net/inet_sock.h>
 #include <net/inet_timewait_sock.h>
-#include <net/sock.h>
 #include <net/tcp_states.h>
-#include <net/tcp.h>
 
 enum dccp_state {
 	DCCP_OPEN	= TCP_ESTABLISHED,
@@ -408,8 +407,6 @@ struct dccp_ackvec;
  * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss
  * @dccps_timestamp_time - time of latest TIMESTAMP option
  * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option
- * @dccps_ext_header_len - network protocol overhead (IP/IPv6 options)
- * @dccps_pmtu_cookie - Last pmtu seen by socket
  * @dccps_packet_size - Set thru setsockopt
  * @dccps_role - Role of this sock, one of %dccp_role
  * @dccps_ndp_count - number of Non Data Packets since last data packet
@@ -434,8 +431,6 @@ struct dccp_sock {
 	__u32				dccps_timestamp_echo;
 	__u32				dccps_packet_size;
 	unsigned long			dccps_ndp_count;
-	__u16				dccps_ext_header_len;
-	__u32				dccps_pmtu_cookie;
 	__u32				dccps_mss_cache;
 	struct dccp_options		dccps_options;
 	struct dccp_ackvec		*dccps_hc_rx_ackvec;

include/linux/etherdevice.h

@@ -63,10 +63,11 @@ static inline int is_zero_ether_addr(const u8 *addr)
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
  * Return true if the address is a multicast address.
+ * By definition the broadcast address is also a multicast address.
  */
 static inline int is_multicast_ether_addr(const u8 *addr)
 {
-	return ((addr[0] != 0xff) && (0x01 & addr[0]));
+	return (0x01 & addr[0]);
 }
 
 /**

include/linux/if_pppox.h

@@ -157,8 +157,7 @@ struct pppox_proto {
 extern int register_pppox_proto(int proto_num, struct pppox_proto *pp);
 extern void unregister_pppox_proto(int proto_num);
 extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */
-extern int pppox_channel_ioctl(struct ppp_channel *pc, unsigned int cmd,
-			       unsigned long arg);
+extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 
 /* PPPoX socket states */
 enum {

include/linux/ip.h

@@ -16,6 +16,7 @@
  */
 #ifndef _LINUX_IP_H
 #define _LINUX_IP_H
+#include <linux/types.h>
 #include <asm/byteorder.h>
 
 #define IPTOS_TOS_MASK		0x1E
@@ -78,126 +79,6 @@
 #define	IPOPT_TS_TSANDADDR	1		/* timestamps and addresses */
 #define	IPOPT_TS_PRESPEC	3		/* specified modules only */
 
-#ifdef __KERNEL__
-#include <linux/config.h>
-#include <linux/types.h>
-#include <net/request_sock.h>
-#include <net/sock.h>
-#include <linux/igmp.h>
-#include <net/flow.h>
-
-struct ip_options {
-  __u32		faddr;				/* Saved first hop address */
-  unsigned char	optlen;
-  unsigned char srr;
-  unsigned char rr;
-  unsigned char ts;
-  unsigned char is_setbyuser:1,			/* Set by setsockopt?			*/
-                is_data:1,			/* Options in __data, rather than skb	*/
-                is_strictroute:1,		/* Strict source route			*/
-                srr_is_hit:1,			/* Packet destination addr was our one	*/
-                is_changed:1,			/* IP checksum more not valid		*/	
-                rr_needaddr:1,			/* Need to record addr of outgoing dev	*/
-                ts_needtime:1,			/* Need to record timestamp		*/
-                ts_needaddr:1;			/* Need to record addr of outgoing dev  */
-  unsigned char router_alert;
-  unsigned char __pad1;
-  unsigned char __pad2;
-  unsigned char __data[0];
-};
-
-#define optlength(opt) (sizeof(struct ip_options) + opt->optlen)
-
-struct inet_request_sock {
-	struct request_sock	req;
-	u32			loc_addr;
-	u32			rmt_addr;
-	u16			rmt_port;
-	u16			snd_wscale : 4, 
-				rcv_wscale : 4, 
-				tstamp_ok  : 1,
-				sack_ok	   : 1,
-				wscale_ok  : 1,
-				ecn_ok	   : 1,
-				acked	   : 1;
-	struct ip_options	*opt;
-};
-
-static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
-{
-	return (struct inet_request_sock *)sk;
-}
-
-struct ipv6_pinfo;
-
-struct inet_sock {
-	/* sk and pinet6 has to be the first two members of inet_sock */
-	struct sock		sk;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	struct ipv6_pinfo	*pinet6;
-#endif
-	/* Socket demultiplex comparisons on incoming packets. */
-	__u32			daddr;		/* Foreign IPv4 addr */
-	__u32			rcv_saddr;	/* Bound local IPv4 addr */
-	__u16			dport;		/* Destination port */
-	__u16			num;		/* Local port */
-	__u32			saddr;		/* Sending source */
-	__s16			uc_ttl;		/* Unicast TTL */
-	__u16			cmsg_flags;
-	struct ip_options	*opt;
-	__u16			sport;		/* Source port */
-	__u16			id;		/* ID counter for DF pkts */
-	__u8			tos;		/* TOS */
-	__u8			mc_ttl;		/* Multicasting TTL */
-	__u8			pmtudisc;
-	unsigned		recverr : 1,
-				freebind : 1,
-				hdrincl : 1,
-				mc_loop : 1;
-	int			mc_index;	/* Multicast device index */
-	__u32			mc_addr;
-	struct ip_mc_socklist	*mc_list;	/* Group array */
-	/*
-	 * Following members are used to retain the infomation to build
-	 * an ip header on each ip fragmentation while the socket is corked.
-	 */
-	struct {
-		unsigned int		flags;
-		unsigned int		fragsize;
-		struct ip_options	*opt;
-		struct rtable		*rt;
-		int			length; /* Total length of all frames */
-		u32			addr;
-		struct flowi		fl;
-	} cork;
-};
-
-#define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
-#define IPCORK_ALLFRAG	2	/* always fragment (for ipv6 for now) */
-
-static inline struct inet_sock *inet_sk(const struct sock *sk)
-{
-	return (struct inet_sock *)sk;
-}
-
-static inline void __inet_sk_copy_descendant(struct sock *sk_to,
-					     const struct sock *sk_from,
-					     const int ancestor_size)
-{
-	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
-	       sk_from->sk_prot->obj_size - ancestor_size);
-}
-#if !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE))
-static inline void inet_sk_copy_descendant(struct sock *sk_to,
-					   const struct sock *sk_from)
-{
-	__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
-}
-#endif
-#endif
-
-extern int inet_sk_rebuild_header(struct sock *sk);
-
 struct iphdr {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
 	__u8	ihl:4,

include/linux/ipv6.h

@@ -171,12 +171,13 @@ enum {
 };
 
 #ifdef __KERNEL__
-#include <linux/in6.h>          /* struct sockaddr_in6 */
 #include <linux/icmpv6.h>
-#include <net/if_inet6.h>       /* struct ipv6_mc_socklist */
 #include <linux/tcp.h>
 #include <linux/udp.h>
 
+#include <net/if_inet6.h>       /* struct ipv6_mc_socklist */
+#include <net/inet_sock.h>
+
 /* 
    This structure contains results of exthdrs parsing
    as offsets from skb->nh.
@@ -199,18 +200,17 @@ static inline int inet6_iif(const struct sk_buff *skb)
 	return IP6CB(skb)->iif;
 }
 
-struct tcp6_request_sock {
-	struct tcp_request_sock	req;
+struct inet6_request_sock {
 	struct in6_addr		loc_addr;
 	struct in6_addr		rmt_addr;
 	struct sk_buff		*pktopts;
 	int			iif;
 };
 
-static inline struct tcp6_request_sock *tcp6_rsk(const struct request_sock *sk)
-{
-	return (struct tcp6_request_sock *)sk;
-}
+struct tcp6_request_sock {
+	struct tcp_request_sock	  tcp6rsk_tcp;
+	struct inet6_request_sock tcp6rsk_inet6;
+};
 
 /**
  * struct ipv6_pinfo - ipv6 private area
@@ -298,12 +298,36 @@ struct tcp6_sock {
 	struct ipv6_pinfo inet6;
 };
 
+extern int inet6_sk_rebuild_header(struct sock *sk);
+
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 {
 	return inet_sk(__sk)->pinet6;
 }
 
+static inline struct inet6_request_sock *
+			inet6_rsk(const struct request_sock *rsk)
+{
+	return (struct inet6_request_sock *)(((u8 *)rsk) +
+					     inet_rsk(rsk)->inet6_rsk_offset);
+}
+
+static inline u32 inet6_rsk_offset(struct request_sock *rsk)
+{
+	return rsk->rsk_ops->obj_size - sizeof(struct inet6_request_sock);
+}
+
+static inline struct request_sock *inet6_reqsk_alloc(struct request_sock_ops *ops)
+{
+	struct request_sock *req = reqsk_alloc(ops);
+
+	if (req != NULL)
+		inet_rsk(req)->inet6_rsk_offset = inet6_rsk_offset(req);
+
+	return req;
+}
+
 static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 {
 	return (struct raw6_sock *)sk;
@@ -323,28 +347,37 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 #define __ipv6_only_sock(sk)	(inet6_sk(sk)->ipv6only)
 #define ipv6_only_sock(sk)	((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk))
 
-#include <linux/tcp.h>
+struct inet6_timewait_sock {
+	struct in6_addr tw_v6_daddr;
+	struct in6_addr	tw_v6_rcv_saddr;
+};
 
 struct tcp6_timewait_sock {
-	struct tcp_timewait_sock tw_v6_sk;
-	struct in6_addr		 tw_v6_daddr;
-	struct in6_addr		 tw_v6_rcv_saddr;
+	struct tcp_timewait_sock   tcp6tw_tcp;
+	struct inet6_timewait_sock tcp6tw_inet6;
 };
 
-static inline struct tcp6_timewait_sock *tcp6_twsk(const struct sock *sk)
+static inline u16 inet6_tw_offset(const struct proto *prot)
 {
-	return (struct tcp6_timewait_sock *)sk;
+	return prot->twsk_prot->twsk_obj_size -
+			sizeof(struct inet6_timewait_sock);
 }
 
-static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk)
+static inline struct inet6_timewait_sock *inet6_twsk(const struct sock *sk)
+{
+	return (struct inet6_timewait_sock *)(((u8 *)sk) +
+					      inet_twsk(sk)->tw_ipv6_offset);
+}
+
+static inline struct in6_addr *__inet6_rcv_saddr(const struct sock *sk)
 {
 	return likely(sk->sk_state != TCP_TIME_WAIT) ?
-		&inet6_sk(sk)->rcv_saddr : &tcp6_twsk(sk)->tw_v6_rcv_saddr;
+		&inet6_sk(sk)->rcv_saddr : &inet6_twsk(sk)->tw_v6_rcv_saddr;
 }
 
-static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk)
+static inline struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
 {
-	return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL;
+	return sk->sk_family == AF_INET6 ? __inet6_rcv_saddr(sk) : NULL;
 }
 
 static inline int inet_v6_ipv6only(const struct sock *sk)
@@ -361,13 +394,19 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 	return NULL;
 }
 
+static inline struct inet6_request_sock *
+			inet6_rsk(const struct request_sock *rsk)
+{
+	return NULL;
+}
+
 static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 {
 	return NULL;
 }
 
-#define __tcp_v6_rcv_saddr(__sk)	NULL
-#define tcp_v6_rcv_saddr(__sk)		NULL
+#define __inet6_rcv_saddr(__sk)	NULL
+#define inet6_rcv_saddr(__sk)	NULL
 #define tcp_twsk_ipv6only(__sk)		0
 #define inet_v6_ipv6only(__sk)		0
 #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */

include/linux/net.h

@@ -107,7 +107,7 @@ enum sock_type {
 struct socket {
 	socket_state		state;
 	unsigned long		flags;
-	struct proto_ops	*ops;
+	const struct proto_ops	*ops;
 	struct fasync_struct	*fasync_list;
 	struct file		*file;
 	struct sock		*sk;
@@ -260,7 +260,7 @@ SOCKCALL_WRAP(name, recvmsg, (struct kiocb *iocb, struct socket *sock, struct ms
 SOCKCALL_WRAP(name, mmap, (struct file *file, struct socket *sock, struct vm_area_struct *vma), \
 	      (file, sock, vma)) \
 	      \
-static struct proto_ops name##_ops = {			\
+static const struct proto_ops name##_ops = {			\
 	.family		= fam,				\
 	.owner		= THIS_MODULE,			\
 	.release	= __lock_##name##_release,	\

include/linux/pfkeyv2.h

@@ -216,6 +216,16 @@ struct sadb_x_nat_t_port {
 } __attribute__((packed));
 /* sizeof(struct sadb_x_nat_t_port) == 8 */
 
+/* Generic LSM security context */
+struct sadb_x_sec_ctx {
+	uint16_t	sadb_x_sec_len;
+	uint16_t	sadb_x_sec_exttype;
+	uint8_t		sadb_x_ctx_alg;  /* LSMs: e.g., selinux == 1 */
+	uint8_t		sadb_x_ctx_doi;
+	uint16_t	sadb_x_ctx_len;
+} __attribute__((packed));
+/* sizeof(struct sadb_sec_ctx) = 8 */
+
 /* Message types */
 #define SADB_RESERVED		0
 #define SADB_GETSPI		1
@@ -325,7 +335,8 @@ struct sadb_x_nat_t_port {
 #define SADB_X_EXT_NAT_T_SPORT		21
 #define SADB_X_EXT_NAT_T_DPORT		22
 #define SADB_X_EXT_NAT_T_OA		23
-#define SADB_EXT_MAX			23
+#define SADB_X_EXT_SEC_CTX		24
+#define SADB_EXT_MAX			24
 
 /* Identity Extension values */
 #define SADB_IDENTTYPE_RESERVED	0

include/linux/pkt_sched.h

@@ -429,6 +429,7 @@ enum
 	TCA_NETEM_CORR,
 	TCA_NETEM_DELAY_DIST,
 	TCA_NETEM_REORDER,
+	TCA_NETEM_CORRUPT,
 	__TCA_NETEM_MAX,
 };
 
@@ -457,6 +458,12 @@ struct tc_netem_reorder
 	__u32	correlation;
 };
 
+struct tc_netem_corrupt
+{
+	__u32	probability;
+	__u32	correlation;
+};
+
 #define NETEM_DIST_SCALE	8192
 
 #endif

include/linux/random.h

@@ -52,9 +52,9 @@ extern void get_random_bytes(void *buf, int nbytes);
 void generate_random_uuid(unsigned char uuid_out[16]);
 
 extern __u32 secure_ip_id(__u32 daddr);
-extern u32 secure_tcp_port_ephemeral(__u32 saddr, __u32 daddr, __u16 dport);
-extern u32 secure_tcpv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, 
-				       __u16 dport);
+extern u32 secure_ipv4_port_ephemeral(__u32 saddr, __u32 daddr, __u16 dport);
+extern u32 secure_ipv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, 
+				      __u16 dport);
 extern __u32 secure_tcp_sequence_number(__u32 saddr, __u32 daddr,
 					__u16 sport, __u16 dport);
 extern __u32 secure_tcpv6_sequence_number(__u32 *saddr, __u32 *daddr,

include/linux/security.h

@@ -59,6 +59,12 @@ struct sk_buff;
 struct sock;
 struct sockaddr;
 struct socket;
+struct flowi;
+struct dst_entry;
+struct xfrm_selector;
+struct xfrm_policy;
+struct xfrm_state;
+struct xfrm_user_sec_ctx;
 
 extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb);
 extern int cap_netlink_recv(struct sk_buff *skb);
@@ -788,6 +794,52 @@ struct swap_info_struct;
  *      which is used to copy security attributes between local stream sockets.
  * @sk_free_security:
  *	Deallocate security structure.
+ * @sk_getsid:
+ *	Retrieve the LSM-specific sid for the sock to enable caching of network
+ *	authorizations.
+ *
+ * Security hooks for XFRM operations.
+ *
+ * @xfrm_policy_alloc_security:
+ *	@xp contains the xfrm_policy being added to Security Policy Database
+ *	used by the XFRM system.
+ *	@sec_ctx contains the security context information being provided by
+ *	the user-level policy update program (e.g., setkey).
+ *	Allocate a security structure to the xp->selector.security field.
+ *	The security field is initialized to NULL when the xfrm_policy is
+ *	allocated.
+ *	Return 0 if operation was successful (memory to allocate, legal context)
+ * @xfrm_policy_clone_security:
+ *	@old contains an existing xfrm_policy in the SPD.
+ *	@new contains a new xfrm_policy being cloned from old.
+ *	Allocate a security structure to the new->selector.security field
+ *	that contains the information from the old->selector.security field.
+ *	Return 0 if operation was successful (memory to allocate).
+ * @xfrm_policy_free_security:
+ *	@xp contains the xfrm_policy
+ *	Deallocate xp->selector.security.
+ * @xfrm_state_alloc_security:
+ *	@x contains the xfrm_state being added to the Security Association
+ *	Database by the XFRM system.
+ *	@sec_ctx contains the security context information being provided by
+ *	the user-level SA generation program (e.g., setkey or racoon).
+ *	Allocate a security structure to the x->sel.security field.  The
+ *	security field is initialized to NULL when the xfrm_state is
+ *	allocated.
+ *	Return 0 if operation was successful (memory to allocate, legal context).
+ * @xfrm_state_free_security:
+ *	@x contains the xfrm_state.
+ *	Deallocate x>sel.security.
+ * @xfrm_policy_lookup:
+ *	@xp contains the xfrm_policy for which the access control is being
+ *	checked.
+ *	@sk_sid contains the sock security label that is used to authorize
+ *	access to the policy xp.
+ *	@dir contains the direction of the flow (input or output).
+ *	Check permission when a sock selects a xfrm_policy for processing
+ *	XFRMs on a packet.  The hook is called when selecting either a
+ *	per-socket policy or a generic xfrm policy.
+ *	Return 0 if permission is granted.
  *
  * Security hooks affecting all Key Management operations
  *
@@ -1237,8 +1289,18 @@ struct security_operations {
 	int (*socket_getpeersec) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len);
 	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);
 #endif	/* CONFIG_SECURITY_NETWORK */
 
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+	int (*xfrm_policy_alloc_security) (struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx);
+	int (*xfrm_policy_clone_security) (struct xfrm_policy *old, struct xfrm_policy *new);
+	void (*xfrm_policy_free_security) (struct xfrm_policy *xp);
+	int (*xfrm_state_alloc_security) (struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx);
+	void (*xfrm_state_free_security) (struct xfrm_state *x);
+	int (*xfrm_policy_lookup)(struct xfrm_policy *xp, u32 sk_sid, u8 dir);
+#endif	/* CONFIG_SECURITY_NETWORK_XFRM */
+
 	/* key management security hooks */
 #ifdef CONFIG_KEYS
 	int (*key_alloc)(struct key *key);
@@ -2679,6 +2741,11 @@ static inline void security_sk_free(struct sock *sk)
 {
 	return security_ops->sk_free_security(sk);
 }
+
+static inline unsigned int security_sk_sid(struct sock *sk, struct flowi *fl, u8 dir)
+{
+	return security_ops->sk_getsid(sk, fl, dir);
+}
 #else	/* CONFIG_SECURITY_NETWORK */
 static inline int security_unix_stream_connect(struct socket * sock,
 					       struct socket * other, 
@@ -2795,8 +2862,73 @@ static inline int security_sk_alloc(struct sock *sk, int family, gfp_t priority)
 static inline void security_sk_free(struct sock *sk)
 {
 }
+
+static inline unsigned int security_sk_sid(struct sock *sk, struct flowi *fl, u8 dir)
+{
+	return 0;
+}
 #endif	/* CONFIG_SECURITY_NETWORK */
 
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx)
+{
+	return security_ops->xfrm_policy_alloc_security(xp, sec_ctx);
+}
+
+static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new)
+{
+	return security_ops->xfrm_policy_clone_security(old, new);
+}
+
+static inline void security_xfrm_policy_free(struct xfrm_policy *xp)
+{
+	security_ops->xfrm_policy_free_security(xp);
+}
+
+static inline int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx)
+{
+	return security_ops->xfrm_state_alloc_security(x, sec_ctx);
+}
+
+static inline void security_xfrm_state_free(struct xfrm_state *x)
+{
+	security_ops->xfrm_state_free_security(x);
+}
+
+static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir)
+{
+	return security_ops->xfrm_policy_lookup(xp, sk_sid, dir);
+}
+#else	/* CONFIG_SECURITY_NETWORK_XFRM */
+static inline int security_xfrm_policy_alloc(struct xfrm_policy *xp, struct xfrm_user_sec_ctx *sec_ctx)
+{
+	return 0;
+}
+
+static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new)
+{
+	return 0;
+}
+
+static inline void security_xfrm_policy_free(struct xfrm_policy *xp)
+{
+}
+
+static inline int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx)
+{
+	return 0;
+}
+
+static inline void security_xfrm_state_free(struct xfrm_state *x)
+{
+}
+
+static inline int security_xfrm_policy_lookup(struct xfrm_policy *xp, u32 sk_sid, u8 dir)
+{
+	return 0;
+}
+#endif	/* CONFIG_SECURITY_NETWORK_XFRM */
+
 #ifdef CONFIG_KEYS
 #ifdef CONFIG_SECURITY
 static inline int security_key_alloc(struct key *key)

include/linux/skbuff.h

@@ -32,7 +32,6 @@
 
 #define HAVE_ALLOC_SKB		/* For the drivers to know */
 #define HAVE_ALIGNABLE_SKB	/* Ditto 8)		   */
-#define SLAB_SKB 		/* Slabified skbuffs 	   */
 
 #define CHECKSUM_NONE 0
 #define CHECKSUM_HW 1
@@ -134,7 +133,7 @@ struct skb_frag_struct {
  */
 struct skb_shared_info {
 	atomic_t	dataref;
-	unsigned int	nr_frags;
+	unsigned short	nr_frags;
 	unsigned short	tso_size;
 	unsigned short	tso_segs;
 	unsigned short  ufo_size;
@@ -1239,6 +1238,8 @@ extern int	       skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
 							int hlen,
 							struct iovec *iov);
 extern void	       skb_free_datagram(struct sock *sk, struct sk_buff *skb);
+extern void	       skb_kill_datagram(struct sock *sk, struct sk_buff *skb,
+					 unsigned int flags);
 extern unsigned int    skb_checksum(const struct sk_buff *skb, int offset,
 				    int len, unsigned int csum);
 extern int	       skb_copy_bits(const struct sk_buff *skb, int offset,

include/linux/socket.h

@@ -27,7 +27,6 @@ struct __kernel_sockaddr_storage {
 #include <linux/compiler.h>		/* __user			*/
 
 extern int sysctl_somaxconn;
-extern void sock_init(void);
 #ifdef CONFIG_PROC_FS
 struct seq_file;
 extern void socket_seq_show(struct seq_file *seq);

include/linux/sysctl.h

@@ -390,6 +390,7 @@ enum
 	NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR=109,
 	NET_TCP_CONG_CONTROL=110,
 	NET_TCP_ABC=111,
+	NET_IPV4_IPFRAG_MAX_DIST=112,
 };
 
 enum {

include/linux/tcp.h

@@ -55,22 +55,6 @@ struct tcphdr {
 	__u16	urg_ptr;
 };
 
-#define TCP_ACTION_FIN	(1 << 7)
-
-enum {
-  TCPF_ESTABLISHED = (1 << 1),
-  TCPF_SYN_SENT  = (1 << 2),
-  TCPF_SYN_RECV  = (1 << 3),
-  TCPF_FIN_WAIT1 = (1 << 4),
-  TCPF_FIN_WAIT2 = (1 << 5),
-  TCPF_TIME_WAIT = (1 << 6),
-  TCPF_CLOSE     = (1 << 7),
-  TCPF_CLOSE_WAIT = (1 << 8),
-  TCPF_LAST_ACK  = (1 << 9),
-  TCPF_LISTEN    = (1 << 10),
-  TCPF_CLOSING   = (1 << 11) 
-};
-
 /*
  *	The union cast uses a gcc extension to avoid aliasing problems
  *  (union is compatible to any of its members)
@@ -254,10 +238,9 @@ struct tcp_sock {
 	__u32	snd_wl1;	/* Sequence for window update		*/
 	__u32	snd_wnd;	/* The window we expect to receive	*/
 	__u32	max_window;	/* Maximal window ever seen from peer	*/
-	__u32	pmtu_cookie;	/* Last pmtu seen by socket		*/
 	__u32	mss_cache;	/* Cached effective mss, not including SACKS */
 	__u16	xmit_size_goal;	/* Goal for segmenting output packets	*/
-	__u16	ext_header_len;	/* Network protocol overhead (IP/IPv6 options) */
+	/* XXX Two bytes hole, try to pack */
 
 	__u32	window_clamp;	/* Maximal window to advertise		*/
 	__u32	rcv_ssthresh;	/* Current window clamp			*/
@@ -295,8 +278,6 @@ struct tcp_sock {
 
 	struct sk_buff_head	out_of_order_queue; /* Out of order segments go here */
 
-	struct tcp_func		*af_specific;	/* Operations which are AF_INET{4,6} specific	*/
-
  	__u32	rcv_wnd;	/* Current receiver window		*/
 	__u32	rcv_wup;	/* rcv_nxt on last window update sent	*/
 	__u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */

include/linux/udp.h

@@ -35,10 +35,10 @@ struct udphdr {
 #define UDP_ENCAP_ESPINUDP	2 /* draft-ietf-ipsec-udp-encaps-06 */
 
 #ifdef __KERNEL__
-
 #include <linux/config.h>
-#include <net/sock.h>
-#include <linux/ip.h>
+#include <linux/types.h>
+
+#include <net/inet_sock.h>
 
 struct udp_sock {
 	/* inet_sock has to be the first member */

include/linux/xfrm.h

@@ -27,6 +27,22 @@ struct xfrm_id
 	__u8		proto;
 };
 
+struct xfrm_sec_ctx {
+	__u8	ctx_doi;
+	__u8	ctx_alg;
+	__u16	ctx_len;
+	__u32	ctx_sid;
+	char	ctx_str[0];
+};
+
+/* Security Context Domains of Interpretation */
+#define XFRM_SC_DOI_RESERVED 0
+#define XFRM_SC_DOI_LSM 1
+
+/* Security Context Algorithms */
+#define XFRM_SC_ALG_RESERVED 0
+#define XFRM_SC_ALG_SELINUX 1
+
 /* Selector, used as selector both on policy rules (SPD) and SAs. */
 
 struct xfrm_selector
@@ -146,6 +162,18 @@ enum {
 
 #define XFRM_NR_MSGTYPES (XFRM_MSG_MAX + 1 - XFRM_MSG_BASE)
 
+/*
+ * Generic LSM security context for comunicating to user space
+ * NOTE: Same format as sadb_x_sec_ctx
+ */
+struct xfrm_user_sec_ctx {
+	__u16			len;
+	__u16			exttype;
+	__u8			ctx_alg;  /* LSMs: e.g., selinux == 1 */
+	__u8			ctx_doi;
+	__u16			ctx_len;
+};
+
 struct xfrm_user_tmpl {
 	struct xfrm_id		id;
 	__u16			family;
@@ -176,6 +204,7 @@ enum xfrm_attr_type_t {
 	XFRMA_TMPL,		/* 1 or more struct xfrm_user_tmpl */
 	XFRMA_SA,
 	XFRMA_POLICY,
+	XFRMA_SEC_CTX,		/* struct xfrm_sec_ctx */
 	__XFRMA_MAX
 
 #define XFRMA_MAX (__XFRMA_MAX - 1)

include/net/af_unix.h

@@ -13,7 +13,7 @@ extern void unix_gc(void);
 #define UNIX_HASH_SIZE	256
 
 extern struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
-extern rwlock_t unix_table_lock;
+extern spinlock_t unix_table_lock;
 
 extern atomic_t unix_tot_inflight;
 
@@ -58,10 +58,10 @@ struct unix_skb_parms {
 #define UNIXCB(skb) 	(*(struct unix_skb_parms*)&((skb)->cb))
 #define UNIXCREDS(skb)	(&UNIXCB((skb)).creds)
 
-#define unix_state_rlock(s)	read_lock(&unix_sk(s)->lock)
-#define unix_state_runlock(s)	read_unlock(&unix_sk(s)->lock)
-#define unix_state_wlock(s)	write_lock(&unix_sk(s)->lock)
-#define unix_state_wunlock(s)	write_unlock(&unix_sk(s)->lock)
+#define unix_state_rlock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_runlock(s)	spin_unlock(&unix_sk(s)->lock)
+#define unix_state_wlock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_wunlock(s)	spin_unlock(&unix_sk(s)->lock)
 
 #ifdef __KERNEL__
 /* The AF_UNIX socket */
@@ -76,7 +76,7 @@ struct unix_sock {
         struct sock		*other;
         struct sock		*gc_tree;
         atomic_t                inflight;
-        rwlock_t                lock;
+        spinlock_t		lock;
         wait_queue_head_t       peer_wait;
 };
 #define unix_sk(__sk) ((struct unix_sock *)__sk)

include/net/atmclip.h

@@ -7,7 +7,6 @@
 #define _ATMCLIP_H
 
 #include <linux/netdevice.h>
-#include <linux/skbuff.h>
 #include <linux/atm.h>
 #include <linux/atmdev.h>
 #include <linux/atmarp.h>
@@ -18,6 +17,7 @@
 #define CLIP_VCC(vcc) ((struct clip_vcc *) ((vcc)->user_back))
 #define NEIGH2ENTRY(neigh) ((struct atmarp_entry *) (neigh)->primary_key)
 
+struct sk_buff;
 
 struct clip_vcc {
 	struct atm_vcc	*vcc;		/* VCC descriptor */

include/net/dst.h

@@ -9,6 +9,7 @@
 #define _NET_DST_H
 
 #include <linux/config.h>
+#include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/rcupdate.h>
 #include <linux/jiffies.h>

include/net/flow.h

@@ -84,11 +84,12 @@ struct flowi {
 #define FLOW_DIR_OUT	1
 #define FLOW_DIR_FWD	2
 
-typedef void (*flow_resolve_t)(struct flowi *key, u16 family, u8 dir,
+struct sock;
+typedef void (*flow_resolve_t)(struct flowi *key, u32 sk_sid, u16 family, u8 dir,
 			       void **objp, atomic_t **obj_refp);
 
-extern void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
-			       flow_resolve_t resolver);
+extern void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir,
+	 		       flow_resolve_t resolver);
 extern void flow_cache_flush(void);
 extern atomic_t flow_cache_genid;
 

include/net/genetlink.h

@@ -60,7 +60,7 @@ struct genl_info
  */
 struct genl_ops
 {
-	unsigned int		cmd;
+	u8			cmd;
 	unsigned int		flags;
 	struct nla_policy	*policy;
 	int		       (*doit)(struct sk_buff *skb,

include/net/icmp.h

@@ -20,12 +20,9 @@
 
 #include <linux/config.h>
 #include <linux/icmp.h>
-#include <linux/skbuff.h>
 
-#include <net/sock.h>
-#include <net/protocol.h>
+#include <net/inet_sock.h>
 #include <net/snmp.h>
-#include <linux/ip.h>
 
 struct icmp_err {
   int		errno;
@@ -38,6 +35,10 @@ DECLARE_SNMP_STAT(struct icmp_mib, icmp_statistics);
 #define ICMP_INC_STATS_BH(field)	SNMP_INC_STATS_BH(icmp_statistics, field)
 #define ICMP_INC_STATS_USER(field) 	SNMP_INC_STATS_USER(icmp_statistics, field)
 
+struct dst_entry;
+struct net_proto_family;
+struct sk_buff;
+
 extern void	icmp_send(struct sk_buff *skb_in,  int type, int code, u32 info);
 extern int	icmp_rcv(struct sk_buff *skb);
 extern int	icmp_ioctl(struct sock *sk, int cmd, unsigned long arg);

include/net/ieee80211_crypt.h

@@ -23,12 +23,17 @@
 #ifndef IEEE80211_CRYPT_H
 #define IEEE80211_CRYPT_H
 
-#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <asm/atomic.h>
 
 enum {
 	IEEE80211_CRYPTO_TKIP_COUNTERMEASURES = (1 << 0),
 };
 
+struct sk_buff;
+struct module;
+
 struct ieee80211_crypto_ops {
 	const char *name;
 	struct list_head list;
@@ -87,6 +92,8 @@ struct ieee80211_crypt_data {
 	atomic_t refcnt;
 };
 
+struct ieee80211_device;
+
 int ieee80211_register_crypto_ops(struct ieee80211_crypto_ops *ops);
 int ieee80211_unregister_crypto_ops(struct ieee80211_crypto_ops *ops);
 struct ieee80211_crypto_ops *ieee80211_get_crypto_ops(const char *name);

include/net/inet6_connection_sock.h

@@ -0,0 +1,42 @@
+/*
+ * NET		Generic infrastructure for INET6 connection oriented protocols.
+ *
+ * Authors:	Many people, see the TCPv6 sources
+ *
+ * 		From code originally in TCPv6
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _INET6_CONNECTION_SOCK_H
+#define _INET6_CONNECTION_SOCK_H
+
+#include <linux/types.h>
+
+struct in6_addr;
+struct inet_bind_bucket;
+struct request_sock;
+struct sk_buff;
+struct sock;
+struct sockaddr;
+
+extern int inet6_csk_bind_conflict(const struct sock *sk,
+				   const struct inet_bind_bucket *tb);
+
+extern struct request_sock *inet6_csk_search_req(const struct sock *sk,
+						 struct request_sock ***prevp,
+						 const __u16 rport,
+						 const struct in6_addr *raddr,
+						 const struct in6_addr *laddr,
+						 const int iif);
+
+extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
+					   struct request_sock *req,
+					   const unsigned long timeout);
+
+extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
+
+extern int inet6_csk_xmit(struct sk_buff *skb, int ipfragok);
+#endif /* _INET6_CONNECTION_SOCK_H */

include/net/inet6_hashtables.h

@@ -48,6 +48,32 @@ static inline int inet6_sk_ehashfn(const struct sock *sk)
 	return inet6_ehashfn(laddr, lport, faddr, fport);
 }
 
+static inline void __inet6_hash(struct inet_hashinfo *hashinfo,
+				struct sock *sk)
+{
+	struct hlist_head *list;
+	rwlock_t *lock;
+
+	BUG_TRAP(sk_unhashed(sk));
+
+	if (sk->sk_state == TCP_LISTEN) {
+		list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+		lock = &hashinfo->lhash_lock;
+		inet_listen_wlock(hashinfo);
+	} else {
+		unsigned int hash;
+		sk->sk_hash = hash = inet6_sk_ehashfn(sk);
+		hash &= (hashinfo->ehash_size - 1);
+		list = &hashinfo->ehash[hash].chain;
+		lock = &hashinfo->ehash[hash].lock;
+		write_lock(lock);
+	}
+
+	__sk_add_node(sk, list);
+	sock_prot_inc_use(sk->sk_prot);
+	write_unlock(lock);
+}
+
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
  * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
@@ -84,10 +110,10 @@ static inline struct sock *
 
 		if(*((__u32 *)&(tw->tw_dport))	== ports	&&
 		   sk->sk_family		== PF_INET6) {
-			const struct tcp6_timewait_sock *tcp6tw = tcp6_twsk(sk);
+			const struct inet6_timewait_sock *tw6 = inet6_twsk(sk);
 
-			if (ipv6_addr_equal(&tcp6tw->tw_v6_daddr, saddr)	&&
-			    ipv6_addr_equal(&tcp6tw->tw_v6_rcv_saddr, daddr)	&&
+			if (ipv6_addr_equal(&tw6->tw_v6_daddr, saddr)	&&
+			    ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr)	&&
 			    (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif))
 				goto hit;
 		}

include/net/inet_common.h

@@ -1,8 +1,8 @@
 #ifndef _INET_COMMON_H
 #define _INET_COMMON_H
 
-extern struct proto_ops		inet_stream_ops;
-extern struct proto_ops		inet_dgram_ops;
+extern const struct proto_ops		inet_stream_ops;
+extern const struct proto_ops		inet_dgram_ops;
 
 /*
  *	INET4 prototypes used by INET6

include/net/inet_connection_sock.h

@@ -15,9 +15,11 @@
 #ifndef _INET_CONNECTION_SOCK_H
 #define _INET_CONNECTION_SOCK_H
 
-#include <linux/ip.h>
+#include <linux/compiler.h>
 #include <linux/string.h>
 #include <linux/timer.h>
+
+#include <net/inet_sock.h>
 #include <net/request_sock.h>
 
 #define INET_CSK_DEBUG 1
@@ -29,6 +31,29 @@ struct inet_bind_bucket;
 struct inet_hashinfo;
 struct tcp_congestion_ops;
 
+/*
+ * Pointers to address related TCP functions
+ * (i.e. things that depend on the address family)
+ */
+struct inet_connection_sock_af_ops {
+	int	    (*queue_xmit)(struct sk_buff *skb, int ipfragok);
+	void	    (*send_check)(struct sock *sk, int len,
+				  struct sk_buff *skb);
+	int	    (*rebuild_header)(struct sock *sk);
+	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb);
+	struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb,
+				      struct request_sock *req,
+				      struct dst_entry *dst);
+	int	    (*remember_stamp)(struct sock *sk);
+	__u16	    net_header_len;
+	int	    (*setsockopt)(struct sock *sk, int level, int optname, 
+				  char __user *optval, int optlen);
+	int	    (*getsockopt)(struct sock *sk, int level, int optname, 
+				  char __user *optval, int __user *optlen);
+	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
+	int sockaddr_len;
+};
+
 /** inet_connection_sock - INET connection oriented sock
  *
  * @icsk_accept_queue:	   FIFO of established children 
@@ -36,13 +61,16 @@ struct tcp_congestion_ops;
  * @icsk_timeout:	   Timeout
  * @icsk_retransmit_timer: Resend (no ack)
  * @icsk_rto:		   Retransmit timeout
+ * @icsk_pmtu_cookie	   Last pmtu seen by socket
  * @icsk_ca_ops		   Pluggable congestion control hook
+ * @icsk_af_ops		   Operations which are AF_INET{4,6} specific
  * @icsk_ca_state:	   Congestion control state
  * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts
  * @icsk_pending:	   Scheduled timer event
  * @icsk_backoff:	   Backoff
  * @icsk_syn_retries:      Number of allowed SYN (or equivalent) retries
  * @icsk_probes_out:	   unanswered 0 window probes
+ * @icsk_ext_hdr_len:	   Network protocol overhead (IP/IPv6 options)
  * @icsk_ack:		   Delayed ACK control data
  */
 struct inet_connection_sock {
@@ -54,14 +82,17 @@ struct inet_connection_sock {
  	struct timer_list	  icsk_retransmit_timer;
  	struct timer_list	  icsk_delack_timer;
 	__u32			  icsk_rto;
+	__u32			  icsk_pmtu_cookie;
 	struct tcp_congestion_ops *icsk_ca_ops;
+	struct inet_connection_sock_af_ops *icsk_af_ops;
+	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
 	__u8			  icsk_ca_state;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
 	__u8			  icsk_backoff;
 	__u8			  icsk_syn_retries;
 	__u8			  icsk_probes_out;
-	/* 2 BYTES HOLE, TRY TO PACK! */
+	__u16			  icsk_ext_hdr_len;
 	struct {
 		__u8		  pending;	 /* ACK is pending			   */
 		__u8		  quick;	 /* Scheduled number of quick acks	   */
@@ -192,8 +223,12 @@ extern struct request_sock *inet_csk_search_req(const struct sock *sk,
 						const __u16 rport,
 						const __u32 raddr,
 						const __u32 laddr);
+extern int inet_csk_bind_conflict(const struct sock *sk,
+				  const struct inet_bind_bucket *tb);
 extern int inet_csk_get_port(struct inet_hashinfo *hashinfo,
-			     struct sock *sk, unsigned short snum);
+			     struct sock *sk, unsigned short snum,
+			     int (*bind_conflict)(const struct sock *sk,
+						  const struct inet_bind_bucket *tb));
 
 extern struct dst_entry* inet_csk_route_req(struct sock *sk,
 					    const struct request_sock *req);
@@ -207,7 +242,7 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk,
 
 extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
 					  struct request_sock *req,
-					  const unsigned timeout);
+					  unsigned long timeout);
 
 static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
 						struct request_sock *req)
@@ -273,4 +308,6 @@ static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
 extern int  inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
 extern void inet_csk_listen_stop(struct sock *sk);
 
+extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
+
 #endif /* _INET_CONNECTION_SOCK_H */

include/net/inet_ecn.h

@@ -3,6 +3,8 @@
 
 #include <linux/ip.h>
 #include <linux/skbuff.h>
+
+#include <net/inet_sock.h>
 #include <net/dsfield.h>
 
 enum {

include/net/inet_hashtables.h

@@ -26,6 +26,7 @@
 #include <linux/wait.h>
 
 #include <net/inet_connection_sock.h>
+#include <net/inet_sock.h>
 #include <net/route.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
@@ -128,26 +129,6 @@ struct inet_hashinfo {
 	kmem_cache_t			*bind_bucket_cachep;
 };
 
-static inline unsigned int inet_ehashfn(const __u32 laddr, const __u16 lport,
-			       const __u32 faddr, const __u16 fport)
-{
-	unsigned int h = (laddr ^ lport) ^ (faddr ^ fport);
-	h ^= h >> 16;
-	h ^= h >> 8;
-	return h;
-}
-
-static inline int inet_sk_ehashfn(const struct sock *sk)
-{
-	const struct inet_sock *inet = inet_sk(sk);
-	const __u32 laddr = inet->rcv_saddr;
-	const __u16 lport = inet->num;
-	const __u32 faddr = inet->daddr;
-	const __u16 fport = inet->dport;
-
-	return inet_ehashfn(laddr, lport, faddr, fport);
-}
-
 static inline struct inet_ehash_bucket *inet_ehash_bucket(
 	struct inet_hashinfo *hashinfo,
 	unsigned int hash)
@@ -434,4 +415,7 @@ static inline struct sock *inet_lookup(struct inet_hashinfo *hashinfo,
 
 	return sk;
 }
+
+extern int inet_hash_connect(struct inet_timewait_death_row *death_row,
+			     struct sock *sk);
 #endif /* _INET_HASHTABLES_H */

include/net/inet_sock.h

@@ -0,0 +1,193 @@
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions for inet_sock
+ *
+ * Authors:	Many, reorganised here by
+ * 		Arnaldo Carvalho de Melo <acme@mandriva.com>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _INET_SOCK_H
+#define _INET_SOCK_H
+
+#include <linux/config.h>
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <net/flow.h>
+#include <net/sock.h>
+#include <net/request_sock.h>
+
+/** struct ip_options - IP Options
+ *
+ * @faddr - Saved first hop address
+ * @is_setbyuser - Set by setsockopt?
+ * @is_data - Options in __data, rather than skb
+ * @is_strictroute - Strict source route
+ * @srr_is_hit - Packet destination addr was our one
+ * @is_changed - IP checksum more not valid
+ * @rr_needaddr - Need to record addr of outgoing dev
+ * @ts_needtime - Need to record timestamp
+ * @ts_needaddr - Need to record addr of outgoing dev
+ */
+struct ip_options {
+	__u32		faddr;
+	unsigned char	optlen;
+	unsigned char	srr;
+	unsigned char	rr;
+	unsigned char	ts;
+	unsigned char	is_setbyuser:1,
+			is_data:1,
+			is_strictroute:1,
+			srr_is_hit:1,
+			is_changed:1,
+			rr_needaddr:1,
+			ts_needtime:1,
+			ts_needaddr:1;
+	unsigned char	router_alert;
+	unsigned char	__pad1;
+	unsigned char	__pad2;
+	unsigned char	__data[0];
+};
+
+#define optlength(opt) (sizeof(struct ip_options) + opt->optlen)
+
+struct inet_request_sock {
+	struct request_sock	req;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	u16			inet6_rsk_offset;
+	/* 2 bytes hole, try to pack */
+#endif
+	u32			loc_addr;
+	u32			rmt_addr;
+	u16			rmt_port;
+	u16			snd_wscale : 4, 
+				rcv_wscale : 4, 
+				tstamp_ok  : 1,
+				sack_ok	   : 1,
+				wscale_ok  : 1,
+				ecn_ok	   : 1,
+				acked	   : 1;
+	struct ip_options	*opt;
+};
+
+static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
+{
+	return (struct inet_request_sock *)sk;
+}
+
+struct ip_mc_socklist;
+struct ipv6_pinfo;
+struct rtable;
+
+/** struct inet_sock - representation of INET sockets
+ *
+ * @sk - ancestor class
+ * @pinet6 - pointer to IPv6 control block
+ * @daddr - Foreign IPv4 addr
+ * @rcv_saddr - Bound local IPv4 addr
+ * @dport - Destination port
+ * @num - Local port
+ * @saddr - Sending source
+ * @uc_ttl - Unicast TTL
+ * @sport - Source port
+ * @id - ID counter for DF pkts
+ * @tos - TOS
+ * @mc_ttl - Multicasting TTL
+ * @is_icsk - is this an inet_connection_sock?
+ * @mc_index - Multicast device index
+ * @mc_list - Group array
+ * @cork - info to build ip hdr on each ip frag while socket is corked
+ */
+struct inet_sock {
+	/* sk and pinet6 has to be the first two members of inet_sock */
+	struct sock		sk;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	struct ipv6_pinfo	*pinet6;
+#endif
+	/* Socket demultiplex comparisons on incoming packets. */
+	__u32			daddr;
+	__u32			rcv_saddr;
+	__u16			dport;
+	__u16			num;
+	__u32			saddr;
+	__s16			uc_ttl;
+	__u16			cmsg_flags;
+	struct ip_options	*opt;
+	__u16			sport;
+	__u16			id;
+	__u8			tos;
+	__u8			mc_ttl;
+	__u8			pmtudisc;
+	__u8			recverr:1,
+				is_icsk:1,
+				freebind:1,
+				hdrincl:1,
+				mc_loop:1;
+	int			mc_index;
+	__u32			mc_addr;
+	struct ip_mc_socklist	*mc_list;
+	struct {
+		unsigned int		flags;
+		unsigned int		fragsize;
+		struct ip_options	*opt;
+		struct rtable		*rt;
+		int			length; /* Total length of all frames */
+		u32			addr;
+		struct flowi		fl;
+	} cork;
+};
+
+#define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
+#define IPCORK_ALLFRAG	2	/* always fragment (for ipv6 for now) */
+
+static inline struct inet_sock *inet_sk(const struct sock *sk)
+{
+	return (struct inet_sock *)sk;
+}
+
+static inline void __inet_sk_copy_descendant(struct sock *sk_to,
+					     const struct sock *sk_from,
+					     const int ancestor_size)
+{
+	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
+	       sk_from->sk_prot->obj_size - ancestor_size);
+}
+#if !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE))
+static inline void inet_sk_copy_descendant(struct sock *sk_to,
+					   const struct sock *sk_from)
+{
+	__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
+}
+#endif
+
+extern int inet_sk_rebuild_header(struct sock *sk);
+
+static inline unsigned int inet_ehashfn(const __u32 laddr, const __u16 lport,
+					const __u32 faddr, const __u16 fport)
+{
+	unsigned int h = (laddr ^ lport) ^ (faddr ^ fport);
+	h ^= h >> 16;
+	h ^= h >> 8;
+	return h;
+}
+
+static inline int inet_sk_ehashfn(const struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const __u32 laddr = inet->rcv_saddr;
+	const __u16 lport = inet->num;
+	const __u32 faddr = inet->daddr;
+	const __u16 fport = inet->dport;
+
+	return inet_ehashfn(laddr, lport, faddr, fport);
+}
+
+#endif	/* _INET_SOCK_H */

include/net/inet_timewait_sock.h

@@ -17,15 +17,16 @@
 
 #include <linux/config.h>
 
-#include <linux/ip.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+#include <net/inet_sock.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
+#include <net/timewait_sock.h>
 
 #include <asm/atomic.h>
 
@@ -127,7 +128,8 @@ struct inet_timewait_sock {
 	__u16			tw_num;
 	/* And these are ours. */
 	__u8			tw_ipv6only:1;
-	/* 31 bits hole, try to pack */
+	/* 15 bits hole, try to pack */
+	__u16			tw_ipv6_offset;
 	int			tw_timeout;
 	unsigned long		tw_ttd;
 	struct inet_bind_bucket	*tw_tb;
@@ -199,7 +201,7 @@ static inline void inet_twsk_put(struct inet_timewait_sock *tw)
 		printk(KERN_DEBUG "%s timewait_sock %p released\n",
 		       tw->tw_prot->name, tw);
 #endif
-		kmem_cache_free(tw->tw_prot->twsk_slab, tw);
+		kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
 		module_put(owner);
 	}
 }

include/net/inetpeer.h

@@ -25,6 +25,7 @@ struct inet_peer
 	__u32			v4daddr;	/* peer's address */
 	__u16			avl_height;
 	__u16			ip_id_count;	/* IP ID for the next packet */
+	atomic_t		rid;		/* Frag reception counter */
 	__u32			tcp_ts;
 	unsigned long		tcp_ts_stamp;
 };

include/net/ip.h

@@ -24,14 +24,10 @@
 
 #include <linux/config.h>
 #include <linux/types.h>
-#include <linux/socket.h>
 #include <linux/ip.h>
 #include <linux/in.h>
-#include <linux/netdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/in_route.h>
-#include <net/route.h>
-#include <net/arp.h>
+
+#include <net/inet_sock.h>
 #include <net/snmp.h>
 
 struct sock;
@@ -45,6 +41,7 @@ struct inet_skb_parm
 #define IPSKB_TRANSLATED	2
 #define IPSKB_FORWARDED		4
 #define IPSKB_XFRM_TUNNEL_SIZE	8
+#define IPSKB_FRAG_COMPLETE	16
 };
 
 struct ipcm_cookie
@@ -74,6 +71,13 @@ extern rwlock_t ip_ra_lock;
 
 #define IP_FRAG_TIME	(30 * HZ)		/* fragment lifetime	*/
 
+struct msghdr;
+struct net_device;
+struct packet_type;
+struct rtable;
+struct sk_buff;
+struct sockaddr;
+
 extern void		ip_mc_dropsocket(struct sock *);
 extern void		ip_mc_dropdevice(struct net_device *dev);
 extern int		igmp_mc_proc_init(void);
@@ -168,6 +172,7 @@ extern int sysctl_ipfrag_high_thresh;
 extern int sysctl_ipfrag_low_thresh;
 extern int sysctl_ipfrag_time;
 extern int sysctl_ipfrag_secret_interval;
+extern int sysctl_ipfrag_max_dist;
 
 /* From inetpeer.c */
 extern int inet_peer_threshold;
@@ -182,6 +187,8 @@ extern int sysctl_ip_dynaddr;
 extern void ipfrag_init(void);
 
 #ifdef CONFIG_INET
+#include <net/dst.h>
+
 /* The function in 2.2 was invalid, producing wrong result for
  * check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */
 static inline

include/net/ip_fib.h

@@ -238,6 +238,8 @@ extern int fib_validate_source(u32 src, u32 dst, u8 tos, int oif,
 			       struct net_device *dev, u32 *spec_dst, u32 *itag);
 extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res);
 
+struct rtentry;
+
 /* Exported by fib_semantics.c */
 extern int ip_fib_check_default(u32 gw, struct net_device *dev);
 extern int fib_sync_down(u32 local, struct net_device *dev, int force);

include/net/ip_vs.h

@@ -251,16 +251,15 @@ struct ip_vs_daemon_user {
 #include <linux/config.h>
 #include <linux/list.h>                 /* for struct list_head */
 #include <linux/spinlock.h>             /* for struct rwlock_t */
-#include <linux/skbuff.h>               /* for struct sk_buff */
-#include <linux/ip.h>                   /* for struct iphdr */
 #include <asm/atomic.h>                 /* for struct atomic_t */
-#include <linux/netdevice.h>		/* for struct neighbour */
-#include <net/dst.h>			/* for struct dst_entry */
-#include <net/udp.h>
 #include <linux/compiler.h>
+#include <linux/timer.h>
 
+#include <net/checksum.h>
 
 #ifdef CONFIG_IP_VS_DEBUG
+#include <linux/net.h>
+
 extern int ip_vs_get_debug_level(void);
 #define IP_VS_DBG(level, msg...)			\
     do {						\
@@ -429,8 +428,11 @@ struct ip_vs_stats
 	spinlock_t              lock;           /* spin lock */
 };
 
+struct dst_entry;
+struct iphdr;
 struct ip_vs_conn;
 struct ip_vs_app;
+struct sk_buff;
 
 struct ip_vs_protocol {
 	struct ip_vs_protocol	*next;

include/net/ipv6.h

@@ -240,6 +240,8 @@ extern struct ipv6_txoptions *	ipv6_renew_options(struct sock *sk, struct ipv6_t
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 					  struct ipv6_txoptions *opt);
 
+extern int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb);
+
 extern int ip6_frag_nqueues;
 extern atomic_t ip6_frag_mem;
 
@@ -525,6 +527,9 @@ extern int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 extern int inet6_ioctl(struct socket *sock, unsigned int cmd, 
 		       unsigned long arg);
 
+extern int inet6_hash_connect(struct inet_timewait_death_row *death_row,
+			      struct sock *sk);
+
 /*
  * reassembly.c
  */
@@ -533,8 +538,11 @@ extern int sysctl_ip6frag_low_thresh;
 extern int sysctl_ip6frag_time;
 extern int sysctl_ip6frag_secret_interval;
 
-extern struct proto_ops inet6_stream_ops;
-extern struct proto_ops inet6_dgram_ops;
+extern const struct proto_ops inet6_stream_ops;
+extern const struct proto_ops inet6_dgram_ops;
+
+struct group_source_req;
+struct group_filter;
 
 extern int ip6_mc_source(int add, int omode, struct sock *sk,
 			 struct group_source_req *pgsr);

include/net/ndisc.h

@@ -35,11 +35,20 @@ enum {
 
 #ifdef __KERNEL__
 
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
+#include <linux/config.h>
+#include <linux/compiler.h>
 #include <linux/icmpv6.h>
+#include <linux/in6.h>
+#include <linux/types.h>
+
 #include <net/neighbour.h>
-#include <asm/atomic.h>
+
+struct ctl_table;
+struct file;
+struct inet6_dev;
+struct net_device;
+struct net_proto_family;
+struct sk_buff;
 
 extern struct neigh_table nd_tbl;
 
@@ -108,7 +117,7 @@ extern int			igmp6_event_report(struct sk_buff *skb);
 extern void			igmp6_cleanup(void);
 
 #ifdef CONFIG_SYSCTL
-extern int 			ndisc_ifinfo_sysctl_change(ctl_table *ctl,
+extern int 			ndisc_ifinfo_sysctl_change(struct ctl_table *ctl,
 							   int write,
 							   struct file * filp,
 							   void __user *buffer,

include/net/neighbour.h

@@ -49,8 +49,8 @@
 #ifdef __KERNEL__
 
 #include <asm/atomic.h>
-#include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <linux/skbuff.h>
 #include <linux/rcupdate.h>
 #include <linux/seq_file.h>
 

include/net/pkt_act.h

@@ -15,7 +15,6 @@
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
-#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/module.h>

include/net/protocol.h

@@ -65,7 +65,7 @@ struct inet_protosw {
 	int		 protocol; /* This is the L4 protocol number.  */
 
 	struct proto	 *prot;
-	struct proto_ops *ops;
+	const struct proto_ops *ops;
   
 	int              capability; /* Which (if any) capability do
 				      * we need to use this socket
@@ -76,6 +76,7 @@ struct inet_protosw {
 };
 #define INET_PROTOSW_REUSE 0x01	     /* Are ports automatically reusable? */
 #define INET_PROTOSW_PERMANENT 0x02  /* Permanent protocols are unremovable. */
+#define INET_PROTOSW_ICSK      0x04  /* Is this an inet_connection_sock? */
 
 extern struct net_protocol *inet_protocol_base;
 extern struct net_protocol *inet_protos[MAX_INET_PROTOS];

include/net/raw.h

@@ -19,6 +19,8 @@
 
 #include <linux/config.h>
 
+#include <net/protocol.h>
+
 extern struct proto raw_prot;
 
 extern void 	raw_err(struct sock *, struct sk_buff *, u32 info);

include/net/request_sock.h

@@ -244,7 +244,7 @@ static inline int reqsk_queue_is_full(const struct request_sock_queue *queue)
 
 static inline void reqsk_queue_hash_req(struct request_sock_queue *queue,
 					u32 hash, struct request_sock *req,
-					unsigned timeout)
+					unsigned long timeout)
 {
 	struct listen_sock *lopt = queue->listen_opt;
 

include/net/sctp/structs.h

@@ -277,6 +277,24 @@ struct sctp_sock {
 	__u32 default_context;
 	__u32 default_timetolive;
 
+	/* Heartbeat interval: The endpoint sends out a Heartbeat chunk to
+	 * the destination address every heartbeat interval. This value
+	 * will be inherited by all new associations.
+	 */
+	__u32 hbinterval;
+
+	/* This is the max_retrans value for new associations. */
+	__u16 pathmaxrxt;
+
+	/* The initial Path MTU to use for new associations. */
+	__u32 pathmtu;
+
+	/* The default SACK delay timeout for new associations. */
+	__u32 sackdelay;
+
+	/* Flags controling Heartbeat, SACK delay, and Path MTU Discovery. */
+	__u32 param_flags;
+
 	struct sctp_initmsg initmsg;
 	struct sctp_rtoinfo rtoinfo;
 	struct sctp_paddrparams paddrparam;
@@ -845,9 +863,6 @@ struct sctp_transport {
 	/* Data that has been sent, but not acknowledged. */
 	__u32 flight_size;
 
-	/* PMTU	      : The current known path MTU.  */
-	__u32 pmtu;
-
 	/* Destination */
 	struct dst_entry *dst;
 	/* Source address. */
@@ -862,7 +877,22 @@ struct sctp_transport {
 	/* Heartbeat interval: The endpoint sends out a Heartbeat chunk to
 	 * the destination address every heartbeat interval.
 	 */
-	int hb_interval;
+	__u32 hbinterval;
+
+	/* This is the max_retrans value for the transport and will
+	 * be initialized from the assocs value.  This can be changed
+	 * using SCTP_SET_PEER_ADDR_PARAMS socket option.
+	 */
+	__u16 pathmaxrxt;
+
+	/* PMTU	      : The current known path MTU.  */
+	__u32 pathmtu;
+
+	/* SACK delay timeout */
+	__u32 sackdelay;
+
+	/* Flags controling Heartbeat, SACK delay, and Path MTU Discovery. */
+	__u32 param_flags;
 
 	/* When was the last time (in jiffies) that we heard from this
 	 * transport?  We use this to pick new active and retran paths.
@@ -882,22 +912,11 @@ struct sctp_transport {
 	 */
 	int state;
 
-	/* hb_allowed  : The current heartbeat state of this destination,
-	 *	       :  i.e. ALLOW-HB, NO-HEARTBEAT, etc.
-	 */
-	int hb_allowed;
-
 	/* These are the error stats for this destination.  */
 
 	/* Error count : The current error count for this destination.	*/
 	unsigned short error_count;
 
-	/* This is the max_retrans value for the transport and will
-	 * be initialized to proto.max_retrans.path.  This can be changed
-	 * using SCTP_SET_PEER_ADDR_PARAMS socket option.
-	 */
-	int max_retrans;
-
 	/* Per	       : A timer used by each destination.
 	 * Destination :
 	 * Timer       :
@@ -1502,6 +1521,28 @@ struct sctp_association {
 	/* The largest timeout or RTO value to use in attempting an INIT */
 	__u16 max_init_timeo;
 
+	/* Heartbeat interval: The endpoint sends out a Heartbeat chunk to
+	 * the destination address every heartbeat interval. This value
+	 * will be inherited by all new transports.
+	 */
+	__u32 hbinterval;
+
+	/* This is the max_retrans value for new transports in the
+	 * association.
+	 */
+	__u16 pathmaxrxt;
+
+	/* Association : The smallest PMTU discovered for all of the
+	 * PMTU	       : peer's transport addresses.
+	 */
+	__u32 pathmtu;
+
+	/* SACK delay timeout */
+	__u32 sackdelay;
+
+	/* Flags controling Heartbeat, SACK delay, and Path MTU Discovery. */
+	__u32 param_flags;
+
 	int timeouts[SCTP_NUM_TIMEOUT_TYPES];
 	struct timer_list timers[SCTP_NUM_TIMEOUT_TYPES];
 
@@ -1571,11 +1612,6 @@ struct sctp_association {
 	 */
 	wait_queue_head_t	wait;
 
-	/* Association : The smallest PMTU discovered for all of the
-	 * PMTU	       : peer's transport addresses.
-	 */
-	__u32 pmtu;
-
 	/* The message size at which SCTP fragmentation will occur. */
 	__u32 frag_point;
 

include/net/sctp/user.h

@@ -93,6 +93,8 @@ enum sctp_optname {
 #define SCTP_STATUS SCTP_STATUS
 	SCTP_GET_PEER_ADDR_INFO,
 #define SCTP_GET_PEER_ADDR_INFO SCTP_GET_PEER_ADDR_INFO
+	SCTP_DELAYED_ACK_TIME,
+#define SCTP_DELAYED_ACK_TIME SCTP_DELAYED_ACK_TIME
 
 	/* Internal Socket Options. Some of the sctp library functions are 
 	 * implemented using these socket options.
@@ -503,13 +505,41 @@ struct sctp_setadaption {
  *   unreachable. The following structure is used to access and modify an
  *   address's parameters:
  */
+enum  sctp_spp_flags {
+	SPP_HB_ENABLE = 1,		/*Enable heartbeats*/
+	SPP_HB_DISABLE = 2,		/*Disable heartbeats*/
+	SPP_HB = SPP_HB_ENABLE | SPP_HB_DISABLE,
+	SPP_HB_DEMAND = 4,		/*Send heartbeat immediately*/
+	SPP_PMTUD_ENABLE = 8,		/*Enable PMTU discovery*/
+	SPP_PMTUD_DISABLE = 16,		/*Disable PMTU discovery*/
+	SPP_PMTUD = SPP_PMTUD_ENABLE | SPP_PMTUD_DISABLE,
+	SPP_SACKDELAY_ENABLE = 32,	/*Enable SACK*/
+	SPP_SACKDELAY_DISABLE = 64,	/*Disable SACK*/
+	SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE,
+};
+
 struct sctp_paddrparams {
 	sctp_assoc_t		spp_assoc_id;
 	struct sockaddr_storage	spp_address;
 	__u32			spp_hbinterval;
 	__u16			spp_pathmaxrxt;
+	__u32			spp_pathmtu;
+	__u32			spp_sackdelay;
+	__u32			spp_flags;
 } __attribute__((packed, aligned(4)));
 
+/* 7.1.24. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME)
+ *
+ *   This options will get or set the delayed ack timer.  The time is set
+ *   in milliseconds.  If the assoc_id is 0, then this sets or gets the
+ *   endpoints default delayed ack timer value.  If the assoc_id field is
+ *   non-zero, then the set or get effects the specified association.
+ */
+struct sctp_assoc_value {
+    sctp_assoc_t            assoc_id;
+    uint32_t                assoc_value;
+};
+
 /*
  * 7.2.2 Peer Address Information
  *

include/net/sock.h

@@ -493,6 +493,7 @@ extern void sk_stream_kill_queues(struct sock *sk);
 extern int sk_wait_data(struct sock *sk, long *timeo);
 
 struct request_sock_ops;
+struct timewait_sock_ops;
 
 /* Networking protocol blocks we attach to sockets.
  * socket layer -> transport layer interface
@@ -557,11 +558,10 @@ struct proto {
 	kmem_cache_t		*slab;
 	unsigned int		obj_size;
 
-	kmem_cache_t		*twsk_slab;
-	unsigned int		twsk_obj_size;
 	atomic_t		*orphan_count;
 
 	struct request_sock_ops	*rsk_prot;
+	struct timewait_sock_ops *twsk_prot;
 
 	struct module		*owner;
 
@@ -926,6 +926,29 @@ static inline void sock_put(struct sock *sk)
 		sk_free(sk);
 }
 
+static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb)
+{
+	int rc = NET_RX_SUCCESS;
+
+	if (sk_filter(sk, skb, 0))
+		goto discard_and_relse;
+
+	skb->dev = NULL;
+
+	bh_lock_sock(sk);
+	if (!sock_owned_by_user(sk))
+		rc = sk->sk_backlog_rcv(sk, skb);
+	else
+		sk_add_backlog(sk, skb);
+	bh_unlock_sock(sk);
+out:
+	sock_put(sk);
+	return rc;
+discard_and_relse:
+	kfree_skb(skb);
+	goto out;
+}
+
 /* Detach socket from process context.
  * Announce socket dead, detach it from wait queue and inode.
  * Note that parent inode held reference count on this struct sock,
@@ -1166,7 +1189,10 @@ static inline int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
  
 static inline int sock_error(struct sock *sk)
 {
-	int err = xchg(&sk->sk_err, 0);
+	int err;
+	if (likely(!sk->sk_err))
+		return 0;
+	err = xchg(&sk->sk_err, 0);
 	return -err;
 }
 

include/net/tcp.h

@@ -224,53 +224,6 @@ extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
 extern int tcp_memory_pressure;
 
-/*
- *	Pointers to address related TCP functions
- *	(i.e. things that depend on the address family)
- */
-
-struct tcp_func {
-	int			(*queue_xmit)		(struct sk_buff *skb,
-							 int ipfragok);
-
-	void			(*send_check)		(struct sock *sk,
-							 struct tcphdr *th,
-							 int len,
-							 struct sk_buff *skb);
-
-	int			(*rebuild_header)	(struct sock *sk);
-
-	int			(*conn_request)		(struct sock *sk,
-							 struct sk_buff *skb);
-
-	struct sock *		(*syn_recv_sock)	(struct sock *sk,
-							 struct sk_buff *skb,
-							 struct request_sock *req,
-							 struct dst_entry *dst);
-    
-	int			(*remember_stamp)	(struct sock *sk);
-
-	__u16			net_header_len;
-
-	int			(*setsockopt)		(struct sock *sk, 
-							 int level, 
-							 int optname, 
-							 char __user *optval, 
-							 int optlen);
-
-	int			(*getsockopt)		(struct sock *sk, 
-							 int level, 
-							 int optname, 
-							 char __user *optval, 
-							 int __user *optlen);
-
-
-	void			(*addr2sockaddr)	(struct sock *sk,
-							 struct sockaddr *);
-
-	int sockaddr_len;
-};
-
 /*
  * The next routines deal with comparing 32 bit unsigned ints
  * and worry about wraparound (automatic with unsigned arithmetic).
@@ -334,6 +287,9 @@ extern int			tcp_rcv_established(struct sock *sk,
 
 extern void			tcp_rcv_space_adjust(struct sock *sk);
 
+extern int			tcp_twsk_unique(struct sock *sk,
+						struct sock *sktw, void *twp);
+
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
@@ -405,8 +361,7 @@ extern void			tcp_parse_options(struct sk_buff *skb,
  *	TCP v4 functions exported for the inet6 API
  */
 
-extern void		       	tcp_v4_send_check(struct sock *sk, 
-						  struct tcphdr *th, int len, 
+extern void		       	tcp_v4_send_check(struct sock *sk, int len,
 						  struct sk_buff *skb);
 
 extern int			tcp_v4_conn_request(struct sock *sk,
@@ -490,34 +445,16 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 			 sk_read_actor_t recv_actor);
 
-/* Initialize RCV_MSS value.
- * RCV_MSS is an our guess about MSS used by the peer.
- * We haven't any direct information about the MSS.
- * It's better to underestimate the RCV_MSS rather than overestimate.
- * Overestimations make us ACKing less frequently than needed.
- * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
- */
+extern void tcp_initialize_rcv_mss(struct sock *sk);
 
-static inline void tcp_initialize_rcv_mss(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
-
-	hint = min(hint, tp->rcv_wnd/2);
-	hint = min(hint, TCP_MIN_RCVMSS);
-	hint = max(hint, TCP_MIN_MSS);
-
-	inet_csk(sk)->icsk_ack.rcv_mss = hint;
-}
-
-static __inline__ void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
+static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 {
 	tp->pred_flags = htonl((tp->tcp_header_len << 26) |
 			       ntohl(TCP_FLAG_ACK) |
 			       snd_wnd);
 }
 
-static __inline__ void tcp_fast_path_on(struct tcp_sock *tp)
+static inline void tcp_fast_path_on(struct tcp_sock *tp)
 {
 	__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
 }
@@ -535,7 +472,7 @@ static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp)
  * Rcv_nxt can be after the window if our peer push more data
  * than the offered window.
  */
-static __inline__ u32 tcp_receive_window(const struct tcp_sock *tp)
+static inline u32 tcp_receive_window(const struct tcp_sock *tp)
 {
 	s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;
 
@@ -707,6 +644,7 @@ extern void tcp_cleanup_congestion_control(struct sock *sk);
 extern int tcp_set_default_congestion_control(const char *name);
 extern void tcp_get_default_congestion_control(char *name);
 extern int tcp_set_congestion_control(struct sock *sk, const char *name);
+extern void tcp_slow_start(struct tcp_sock *tp);
 
 extern struct tcp_congestion_ops tcp_init_congestion_ops;
 extern u32 tcp_reno_ssthresh(struct sock *sk);
@@ -746,7 +684,7 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
  *	"Packets left network, but not honestly ACKed yet" PLUS
  *	"Packets fast retransmitted"
  */
-static __inline__ unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
+static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
 {
 	return (tp->packets_out - tp->left_out + tp->retrans_out);
 }
@@ -766,33 +704,6 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 			    (tp->snd_cwnd >> 2)));
 }
 
-/*
- * Linear increase during slow start
- */
-static inline void tcp_slow_start(struct tcp_sock *tp)
-{
-	if (sysctl_tcp_abc) {
-		/* RFC3465: Slow Start
-		 * TCP sender SHOULD increase cwnd by the number of
-		 * previously unacknowledged bytes ACKed by each incoming
-		 * acknowledgment, provided the increase is not more than L
-		 */
-		if (tp->bytes_acked < tp->mss_cache)
-			return;
-
-		/* We MAY increase by 2 if discovered delayed ack */
-		if (sysctl_tcp_abc > 1 && tp->bytes_acked > 2*tp->mss_cache) {
-			if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-				tp->snd_cwnd++;
-		}
-	}
-	tp->bytes_acked = 0;
-
-	if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-		tp->snd_cwnd++;
-}
-
-
 static inline void tcp_sync_left_out(struct tcp_sock *tp)
 {
 	if (tp->rx_opt.sack_ok &&
@@ -801,34 +712,7 @@ static inline void tcp_sync_left_out(struct tcp_sock *tp)
 	tp->left_out = tp->sacked_out + tp->lost_out;
 }
 
-/* Set slow start threshold and cwnd not falling to slow start */
-static inline void __tcp_enter_cwr(struct sock *sk)
-{
-	const struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	tp->undo_marker = 0;
-	tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
-	tp->snd_cwnd = min(tp->snd_cwnd,
-			   tcp_packets_in_flight(tp) + 1U);
-	tp->snd_cwnd_cnt = 0;
-	tp->high_seq = tp->snd_nxt;
-	tp->snd_cwnd_stamp = tcp_time_stamp;
-	TCP_ECN_queue_cwr(tp);
-}
-
-static inline void tcp_enter_cwr(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	tp->prior_ssthresh = 0;
-	tp->bytes_acked = 0;
-	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
-		__tcp_enter_cwr(sk);
-		tcp_set_ca_state(sk, TCP_CA_CWR);
-	}
-}
-
+extern void tcp_enter_cwr(struct sock *sk);
 extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
 
 /* Slow start with delack produces 3 packets of burst, so that
@@ -860,14 +744,14 @@ static inline int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
 		return left <= tcp_max_burst(tp);
 }
 
-static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, 
-					   const struct sk_buff *skb)
+static inline void tcp_minshall_update(struct tcp_sock *tp, int mss,
+				       const struct sk_buff *skb)
 {
 	if (skb->len < mss)
 		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
 }
 
-static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	if (!tp->packets_out && !icsk->icsk_pending)
@@ -875,18 +759,18 @@ static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *t
 					  icsk->icsk_rto, TCP_RTO_MAX);
 }
 
-static __inline__ void tcp_push_pending_frames(struct sock *sk,
-					       struct tcp_sock *tp)
+static inline void tcp_push_pending_frames(struct sock *sk,
+					   struct tcp_sock *tp)
 {
 	__tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle);
 }
 
-static __inline__ void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
+static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
 {
 	tp->snd_wl1 = seq;
 }
 
-static __inline__ void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
+static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
 {
 	tp->snd_wl1 = seq;
 }
@@ -894,19 +778,19 @@ static __inline__ void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
 /*
  * Calculate(/check) TCP checksum
  */
-static __inline__ u16 tcp_v4_check(struct tcphdr *th, int len,
-				   unsigned long saddr, unsigned long daddr, 
-				   unsigned long base)
+static inline u16 tcp_v4_check(struct tcphdr *th, int len,
+			       unsigned long saddr, unsigned long daddr, 
+			       unsigned long base)
 {
 	return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
 }
 
-static __inline__ int __tcp_checksum_complete(struct sk_buff *skb)
+static inline int __tcp_checksum_complete(struct sk_buff *skb)
 {
 	return __skb_checksum_complete(skb);
 }
 
-static __inline__ int tcp_checksum_complete(struct sk_buff *skb)
+static inline int tcp_checksum_complete(struct sk_buff *skb)
 {
 	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
 		__tcp_checksum_complete(skb);
@@ -914,7 +798,7 @@ static __inline__ int tcp_checksum_complete(struct sk_buff *skb)
 
 /* Prequeue for VJ style copy to user, combined with checksumming. */
 
-static __inline__ void tcp_prequeue_init(struct tcp_sock *tp)
+static inline void tcp_prequeue_init(struct tcp_sock *tp)
 {
 	tp->ucopy.task = NULL;
 	tp->ucopy.len = 0;
@@ -930,7 +814,7 @@ static __inline__ void tcp_prequeue_init(struct tcp_sock *tp)
  *
  * NOTE: is this not too big to inline?
  */
-static __inline__ int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
+static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -971,7 +855,7 @@ static const char *statename[]={
 };
 #endif
 
-static __inline__ void tcp_set_state(struct sock *sk, int state)
+static inline void tcp_set_state(struct sock *sk, int state)
 {
 	int oldstate = sk->sk_state;
 
@@ -1005,7 +889,7 @@ static __inline__ void tcp_set_state(struct sock *sk, int state)
 #endif	
 }
 
-static __inline__ void tcp_done(struct sock *sk)
+static inline void tcp_done(struct sock *sk)
 {
 	tcp_set_state(sk, TCP_CLOSE);
 	tcp_clear_xmit_timers(sk);
@@ -1018,81 +902,13 @@ static __inline__ void tcp_done(struct sock *sk)
 		inet_csk_destroy_sock(sk);
 }
 
-static __inline__ void tcp_sack_reset(struct tcp_options_received *rx_opt)
+static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 {
 	rx_opt->dsack = 0;
 	rx_opt->eff_sacks = 0;
 	rx_opt->num_sacks = 0;
 }
 
-static __inline__ void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp, __u32 tstamp)
-{
-	if (tp->rx_opt.tstamp_ok) {
-		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
-					  (TCPOPT_NOP << 16) |
-					  (TCPOPT_TIMESTAMP << 8) |
-					  TCPOLEN_TIMESTAMP);
-		*ptr++ = htonl(tstamp);
-		*ptr++ = htonl(tp->rx_opt.ts_recent);
-	}
-	if (tp->rx_opt.eff_sacks) {
-		struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
-		int this_sack;
-
-		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
-					  (TCPOPT_NOP << 16) |
-					  (TCPOPT_SACK << 8) |
-					  (TCPOLEN_SACK_BASE +
-					   (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK)));
-		for(this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
-			*ptr++ = htonl(sp[this_sack].start_seq);
-			*ptr++ = htonl(sp[this_sack].end_seq);
-		}
-		if (tp->rx_opt.dsack) {
-			tp->rx_opt.dsack = 0;
-			tp->rx_opt.eff_sacks--;
-		}
-	}
-}
-
-/* Construct a tcp options header for a SYN or SYN_ACK packet.
- * If this is every changed make sure to change the definition of
- * MAX_SYN_SIZE to match the new maximum number of options that you
- * can generate.
- */
-static inline void tcp_syn_build_options(__u32 *ptr, int mss, int ts, int sack,
-					     int offer_wscale, int wscale, __u32 tstamp, __u32 ts_recent)
-{
-	/* We always get an MSS option.
-	 * The option bytes which will be seen in normal data
-	 * packets should timestamps be used, must be in the MSS
-	 * advertised.  But we subtract them from tp->mss_cache so
-	 * that calculations in tcp_sendmsg are simpler etc.
-	 * So account for this fact here if necessary.  If we
-	 * don't do this correctly, as a receiver we won't
-	 * recognize data packets as being full sized when we
-	 * should, and thus we won't abide by the delayed ACK
-	 * rules correctly.
-	 * SACKs don't matter, we never delay an ACK when we
-	 * have any of those going out.
-	 */
-	*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
-	if (ts) {
-		if(sack)
-			*ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) |
-						  (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
-		else
-			*ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
-						  (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
-		*ptr++ = htonl(tstamp);		/* TSVAL */
-		*ptr++ = htonl(ts_recent);	/* TSECR */
-	} else if(sack)
-		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
-					  (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM);
-	if (offer_wscale)
-		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale));
-}
-
 /* Determine a window scaling and initial window to offer. */
 extern void tcp_select_initial_window(int __space, __u32 mss,
 				      __u32 *rcv_wnd, __u32 *window_clamp,
@@ -1117,9 +933,9 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk->sk_rcvbuf); 
 }
 
-static __inline__ void tcp_openreq_init(struct request_sock *req,
-					struct tcp_options_received *rx_opt,
-					struct sk_buff *skb)
+static inline void tcp_openreq_init(struct request_sock *req,
+				    struct tcp_options_received *rx_opt,
+				    struct sk_buff *skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 

include/net/tcp_states.h

@@ -31,4 +31,20 @@ enum {
 
 #define TCP_STATE_MASK	0xF
 
+#define TCP_ACTION_FIN	(1 << 7)
+
+enum {
+	TCPF_ESTABLISHED = (1 << 1),
+	TCPF_SYN_SENT	 = (1 << 2),
+	TCPF_SYN_RECV	 = (1 << 3),
+	TCPF_FIN_WAIT1	 = (1 << 4),
+	TCPF_FIN_WAIT2	 = (1 << 5),
+	TCPF_TIME_WAIT	 = (1 << 6),
+	TCPF_CLOSE	 = (1 << 7),
+	TCPF_CLOSE_WAIT	 = (1 << 8),
+	TCPF_LAST_ACK	 = (1 << 9),
+	TCPF_LISTEN	 = (1 << 10),
+	TCPF_CLOSING	 = (1 << 11) 
+};
+
 #endif	/* _LINUX_TCP_STATES_H */

include/net/timewait_sock.h

@@ -0,0 +1,31 @@
+/*
+ * NET		Generic infrastructure for Network protocols.
+ *
+ * Authors:	Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _TIMEWAIT_SOCK_H
+#define _TIMEWAIT_SOCK_H
+
+#include <linux/slab.h>
+#include <net/sock.h>
+
+struct timewait_sock_ops {
+	kmem_cache_t	*twsk_slab;
+	unsigned int	twsk_obj_size;
+	int		(*twsk_unique)(struct sock *sk,
+				       struct sock *sktw, void *twp);
+};
+
+static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
+{
+	if (sk->sk_prot->twsk_prot->twsk_unique != NULL)
+		return sk->sk_prot->twsk_prot->twsk_unique(sk, sktw, twp);
+	return 0;
+}
+
+#endif /* _TIMEWAIT_SOCK_H */

include/net/transp_v6.h

@@ -44,7 +44,7 @@ extern int			datagram_send_ctl(struct msghdr *msg,
 /*
  *	address family specific functions
  */
-extern struct tcp_func	ipv4_specific;
+extern struct inet_connection_sock_af_ops ipv4_specific;
 
 extern int inet6_destroy_sock(struct sock *sk);
 

include/net/udp.h

@@ -22,9 +22,8 @@
 #ifndef _UDP_H
 #define _UDP_H
 
-#include <linux/udp.h>
-#include <linux/ip.h>
 #include <linux/list.h>
+#include <net/inet_sock.h>
 #include <net/sock.h>
 #include <net/snmp.h>
 #include <linux/seq_file.h>
@@ -62,6 +61,7 @@ static inline int udp_lport_inuse(u16 num)
 
 extern struct proto udp_prot;
 
+struct sk_buff;
 
 extern void	udp_err(struct sk_buff *, u32);
 

include/net/xfrm.h

@@ -2,11 +2,12 @@
 #define _NET_XFRM_H
 
 #include <linux/compiler.h>
+#include <linux/in.h>
 #include <linux/xfrm.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/skbuff.h>
-#include <linux/netdevice.h>
+#include <linux/socket.h>
 #include <linux/crypto.h>
 #include <linux/pfkeyv2.h>
 #include <linux/in6.h>
@@ -144,6 +145,9 @@ struct xfrm_state
 	 * transformer. */
 	struct xfrm_type	*type;
 
+	/* Security context */
+	struct xfrm_sec_ctx	*security;
+
 	/* Private data of this transformer, format is opaque,
 	 * interpreted by xfrm_type methods. */
 	void			*data;
@@ -298,6 +302,7 @@ struct xfrm_policy
 	__u8			flags;
 	__u8			dead;
 	__u8			xfrm_nr;
+	struct xfrm_sec_ctx	*security;
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
 };
 
@@ -510,6 +515,25 @@ xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl,
 	return 0;
 }
 
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+/*	If neither has a context --> match
+ * 	Otherwise, both must have a context and the sids, doi, alg must match
+ */
+static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2)
+{
+	return ((!s1 && !s2) ||
+		(s1 && s2 &&
+		 (s1->ctx_sid == s2->ctx_sid) &&
+		 (s1->ctx_doi == s2->ctx_doi) &&
+		 (s1->ctx_alg == s2->ctx_alg)));
+}
+#else
+static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2)
+{
+	return 1;
+}
+#endif
+
 /* A struct encoding bundle of transformations to apply to some set of flow.
  *
  * dst->child points to the next element of bundle.
@@ -878,8 +902,8 @@ static inline int xfrm_dst_lookup(struct xfrm_dst **dst, struct flowi *fl, unsig
 struct xfrm_policy *xfrm_policy_alloc(gfp_t gfp);
 extern int xfrm_policy_walk(int (*func)(struct xfrm_policy *, int, int, void*), void *);
 int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
-struct xfrm_policy *xfrm_policy_bysel(int dir, struct xfrm_selector *sel,
-				      int delete);
+struct xfrm_policy *xfrm_policy_bysel_ctx(int dir, struct xfrm_selector *sel,
+					  struct xfrm_sec_ctx *ctx, int delete);
 struct xfrm_policy *xfrm_policy_byid(int dir, u32 id, int delete);
 void xfrm_policy_flush(void);
 u32 xfrm_get_acqseq(void);

init/main.c

@@ -47,7 +47,6 @@
 #include <linux/rmap.h>
 #include <linux/mempolicy.h>
 #include <linux/key.h>
-#include <net/sock.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -614,9 +613,6 @@ static void __init do_basic_setup(void)
 	sysctl_init();
 #endif
 
-	/* Networking initialization needs a process context */ 
-	sock_init();
-
 	do_initcalls();
 }
 

net/appletalk/ddp.c

@@ -63,7 +63,7 @@
 #include <linux/atalk.h>
 
 struct datalink_proto *ddp_dl, *aarp_dl;
-static struct proto_ops atalk_dgram_ops;
+static const struct proto_ops atalk_dgram_ops;
 
 /**************************************************************************\
 *                                                                          *
@@ -1763,7 +1763,7 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
  */
 static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
-	int rc = -EINVAL;
+	int rc = -ENOIOCTLCMD;
 	struct sock *sk = sock->sk;
 	void __user *argp = (void __user *)arg;
 
@@ -1813,23 +1813,6 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			rc = atif_ioctl(cmd, argp);
 			rtnl_unlock();
 			break;
-		/* Physical layer ioctl calls */
-		case SIOCSIFLINK:
-		case SIOCGIFHWADDR:
-		case SIOCSIFHWADDR:
-		case SIOCGIFFLAGS:
-		case SIOCSIFFLAGS:
-		case SIOCGIFTXQLEN:
-		case SIOCSIFTXQLEN:
-		case SIOCGIFMTU:
-		case SIOCGIFCONF:
-		case SIOCADDMULTI:
-		case SIOCDELMULTI:
-		case SIOCGIFCOUNT:
-		case SIOCGIFINDEX:
-		case SIOCGIFNAME:
-			rc = dev_ioctl(cmd, argp);
-			break;
 	}
 
 	return rc;
@@ -1841,7 +1824,7 @@ static struct net_proto_family atalk_family_ops = {
 	.owner		= THIS_MODULE,
 };
 
-static struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = {
+static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = {
 	.family		= PF_APPLETALK,
 	.owner		= THIS_MODULE,
 	.release	= atalk_release,

net/atm/pvc.c

@@ -102,7 +102,7 @@ static int pvc_getname(struct socket *sock,struct sockaddr *sockaddr,
 }
 
 
-static struct proto_ops pvc_proto_ops = {
+static const struct proto_ops pvc_proto_ops = {
 	.family =	PF_ATMPVC,
 	.owner =	THIS_MODULE,
 

net/atm/svc.c

@@ -613,7 +613,7 @@ static int svc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	return error;
 }
 
-static struct proto_ops svc_proto_ops = {
+static const struct proto_ops svc_proto_ops = {
 	.family =	PF_ATMSVC,
 	.owner =	THIS_MODULE,
 

net/ax25/af_ax25.c

@@ -54,7 +54,7 @@
 HLIST_HEAD(ax25_list);
 DEFINE_SPINLOCK(ax25_list_lock);
 
-static struct proto_ops ax25_proto_ops;
+static const struct proto_ops ax25_proto_ops;
 
 static void ax25_free_sock(struct sock *sk)
 {
@@ -1827,7 +1827,7 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 
 	default:
-		res = dev_ioctl(cmd, argp);
+		res = -ENOIOCTLCMD;
 		break;
 	}
 	release_sock(sk);
@@ -1944,7 +1944,7 @@ static struct net_proto_family ax25_family_ops = {
 	.owner	=	THIS_MODULE,
 };
 
-static struct proto_ops ax25_proto_ops = {
+static const struct proto_ops ax25_proto_ops = {
 	.family		= PF_AX25,
 	.owner		= THIS_MODULE,
 	.release	= ax25_release,

net/bluetooth/af_bluetooth.c

@@ -287,10 +287,9 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo)
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
 
-		if (sk->sk_err) {
-			err = sock_error(sk);
+		err = sock_error(sk);
+		if (err)
 			break;
-		}
 	}
 	set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk->sk_sleep, &wait);

net/bluetooth/bnep/sock.c

@@ -146,7 +146,7 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long
 	return 0;
 }
 
-static struct proto_ops bnep_sock_ops = {
+static const struct proto_ops bnep_sock_ops = {
 	.family     = PF_BLUETOOTH,
 	.owner      = THIS_MODULE,
 	.release    = bnep_sock_release,

net/bluetooth/cmtp/sock.c

@@ -137,7 +137,7 @@ static int cmtp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long
 	return -EINVAL;
 }
 
-static struct proto_ops cmtp_sock_ops = {
+static const struct proto_ops cmtp_sock_ops = {
 	.family		= PF_BLUETOOTH,
 	.owner		= THIS_MODULE,
 	.release	= cmtp_sock_release,

net/bluetooth/hci_sock.c

@@ -575,7 +575,7 @@ static int hci_sock_getsockopt(struct socket *sock, int level, int optname, char
 	return 0;
 }
 
-static struct proto_ops hci_sock_ops = {
+static const struct proto_ops hci_sock_ops = {
 	.family		= PF_BLUETOOTH,
 	.owner		= THIS_MODULE,
 	.release	= hci_sock_release,

net/bluetooth/hidp/sock.c

@@ -143,7 +143,7 @@ static int hidp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long
 	return -EINVAL;
 }
 
-static struct proto_ops hidp_sock_ops = {
+static const struct proto_ops hidp_sock_ops = {
 	.family		= PF_BLUETOOTH,
 	.owner		= THIS_MODULE,
 	.release	= hidp_sock_release,

net/bluetooth/l2cap.c

@@ -57,7 +57,7 @@
 
 #define VERSION "2.8"
 
-static struct proto_ops l2cap_sock_ops;
+static const struct proto_ops l2cap_sock_ops;
 
 static struct bt_sock_list l2cap_sk_list = {
 	.lock = RW_LOCK_UNLOCKED
@@ -767,8 +767,9 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
-	if (sk->sk_err)
-		return sock_error(sk);
+	err = sock_error(sk);
+	if (err)
+		return err;
 
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2160,7 +2161,7 @@ static ssize_t l2cap_sysfs_show(struct class *dev, char *buf)
 
 static CLASS_ATTR(l2cap, S_IRUGO, l2cap_sysfs_show, NULL);
 
-static struct proto_ops l2cap_sock_ops = {
+static const struct proto_ops l2cap_sock_ops = {
 	.family		= PF_BLUETOOTH,
 	.owner		= THIS_MODULE,
 	.release	= l2cap_sock_release,

net/bluetooth/rfcomm/sock.c

@@ -58,7 +58,7 @@
 #define BT_DBG(D...)
 #endif
 
-static struct proto_ops rfcomm_sock_ops;
+static const struct proto_ops rfcomm_sock_ops;
 
 static struct bt_sock_list rfcomm_sk_list = {
 	.lock = RW_LOCK_UNLOCKED
@@ -907,7 +907,7 @@ static ssize_t rfcomm_sock_sysfs_show(struct class *dev, char *buf)
 
 static CLASS_ATTR(rfcomm, S_IRUGO, rfcomm_sock_sysfs_show, NULL);
 
-static struct proto_ops rfcomm_sock_ops = {
+static const struct proto_ops rfcomm_sock_ops = {
 	.family		= PF_BLUETOOTH,
 	.owner		= THIS_MODULE,
 	.release	= rfcomm_sock_release,