1 files changed, 133 insertions, 114 deletions

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 735b926a349..dd1950a7e27 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -16,6 +16,7 @@
 
 
 #include <linux/interrupt.h>
+#include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/list.h>
 #include <linux/slab.h>
@@ -28,18 +29,19 @@
 #include <net/inet_connection_sock.h>
 #include <net/inet_sock.h>
 #include <net/sock.h>
+#include <net/route.h>
 #include <net/tcp_states.h>
+#include <net/netns/hash.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/byteorder.h>
 
 /* This is for all connections with a full identity, no wildcards.
- * One chain is dedicated to TIME_WAIT sockets.
- * I'll experiment with dynamic table growth later.
+ * The 'e' prefix stands for Establish, but we really put all sockets
+ * but LISTEN ones.
  */
 struct inet_ehash_bucket {
-	struct hlist_head chain;
-	struct hlist_head twchain;
+	struct hlist_nulls_head chain;
 };
 
 /* There are a few simple rules, which allow for local port reuse by
@@ -74,21 +76,43 @@ struct inet_ehash_bucket {
  * ports are created in O(1) time?  I thought so. ;-)	-DaveM
  */
 struct inet_bind_bucket {
+#ifdef CONFIG_NET_NS
 	struct net		*ib_net;
+#endif
 	unsigned short		port;
-	signed short		fastreuse;
+	signed char		fastreuse;
+	signed char		fastreuseport;
+	kuid_t			fastuid;
+	int			num_owners;
 	struct hlist_node	node;
 	struct hlist_head	owners;
 };
 
-#define inet_bind_bucket_for_each(tb, node, head) \
-	hlist_for_each_entry(tb, node, head, node)
+static inline struct net *ib_net(struct inet_bind_bucket *ib)
+{
+	return read_pnet(&ib->ib_net);
+}
+
+#define inet_bind_bucket_for_each(tb, head) \
+	hlist_for_each_entry(tb, head, node)
 
 struct inet_bind_hashbucket {
 	spinlock_t		lock;
 	struct hlist_head	chain;
 };
 
+/*
+ * Sockets can be hashed in established or listening table
+ * We must use different 'nulls' end-of-chain value for listening
+ * hash table, or we might find a socket that was closed and
+ * reallocated/inserted into established hash table
+ */
+#define LISTENING_NULLS_BASE (1U << 29)
+struct inet_listen_hashbucket {
+	spinlock_t		lock;
+	struct hlist_nulls_head	head;
+};
+
 /* This is for listening sockets, thus all sockets which possess wildcards. */
 #define INET_LHTABLE_SIZE	32	/* Yes, really, this is all you need. */
 
@@ -98,11 +122,10 @@ struct inet_hashinfo {
 	 *
 	 *          TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
 	 *
-	 * TIME_WAIT sockets use a separate chain (twchain).
 	 */
 	struct inet_ehash_bucket	*ehash;
-	rwlock_t			*ehash_locks;
-	unsigned int			ehash_size;
+	spinlock_t			*ehash_locks;
+	unsigned int			ehash_mask;
 	unsigned int			ehash_locks_mask;
 
 	/* Ok, let's try this, I give up, we do need a local binding
@@ -111,34 +134,34 @@ struct inet_hashinfo {
 	struct inet_bind_hashbucket	*bhash;
 
 	unsigned int			bhash_size;
-	/* Note : 4 bytes padding on 64 bit arches */
+	/* 4 bytes hole on 64 bit */
 
-	/* All sockets in TCP_LISTEN state will be in here.  This is the only
-	 * table where wildcard'd TCP sockets can exist.  Hash function here
-	 * is just local port number.
-	 */
-	struct hlist_head		listening_hash[INET_LHTABLE_SIZE];
+	struct kmem_cache		*bind_bucket_cachep;
 
 	/* All the above members are written once at bootup and
 	 * never written again _or_ are predominantly read-access.
 	 *
 	 * Now align to a new cache line as all the following members
-	 * are often dirty.
+	 * might be often dirty.
+	 */
+	/* All sockets in TCP_LISTEN state will be in here.  This is the only
+	 * table where wildcard'd TCP sockets can exist.  Hash function here
+	 * is just local port number.
 	 */
-	rwlock_t			lhash_lock ____cacheline_aligned;
-	atomic_t			lhash_users;
-	wait_queue_head_t		lhash_wait;
-	struct kmem_cache			*bind_bucket_cachep;
+	struct inet_listen_hashbucket	listening_hash[INET_LHTABLE_SIZE]
+					____cacheline_aligned_in_smp;
+
+	atomic_t			bsockets;
 };
 
 static inline struct inet_ehash_bucket *inet_ehash_bucket(
 	struct inet_hashinfo *hashinfo,
 	unsigned int hash)
 {
-	return &hashinfo->ehash[hash & (hashinfo->ehash_size - 1)];
+	return &hashinfo->ehash[hash & hashinfo->ehash_mask];
 }
 
-static inline rwlock_t *inet_ehash_lockp(
+static inline spinlock_t *inet_ehash_lockp(
 	struct inet_hashinfo *hashinfo,
 	unsigned int hash)
 {
@@ -161,18 +184,18 @@ static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 		size = 2048;
 	if (nr_pcpus >= 32)
 		size = 4096;
-	if (sizeof(rwlock_t) != 0) {
+	if (sizeof(spinlock_t) != 0) {
 #ifdef CONFIG_NUMA
-		if (size * sizeof(rwlock_t) > PAGE_SIZE)
-			hashinfo->ehash_locks = vmalloc(size * sizeof(rwlock_t));
+		if (size * sizeof(spinlock_t) > PAGE_SIZE)
+			hashinfo->ehash_locks = vmalloc(size * sizeof(spinlock_t));
 		else
 #endif
-		hashinfo->ehash_locks =	kmalloc(size * sizeof(rwlock_t),
+		hashinfo->ehash_locks =	kmalloc(size * sizeof(spinlock_t),
 						GFP_KERNEL);
 		if (!hashinfo->ehash_locks)
 			return ENOMEM;
 		for (i = 0; i < size; i++)
-			rwlock_init(&hashinfo->ehash_locks[i]);
+			spin_lock_init(&hashinfo->ehash_locks[i]);
 	}
 	hashinfo->ehash_locks_mask = size - 1;
 	return 0;
@@ -183,7 +206,7 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	if (hashinfo->ehash_locks) {
 #ifdef CONFIG_NUMA
 		unsigned int size = (hashinfo->ehash_locks_mask + 1) *
-							sizeof(rwlock_t);
+							sizeof(spinlock_t);
 		if (size > PAGE_SIZE)
 			vfree(hashinfo->ehash_locks);
 		else
@@ -193,74 +216,58 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	}
 }
 
-extern struct inet_bind_bucket *
-		    inet_bind_bucket_create(struct kmem_cache *cachep,
-					    struct net *net,
-					    struct inet_bind_hashbucket *head,
-					    const unsigned short snum);
-extern void inet_bind_bucket_destroy(struct kmem_cache *cachep,
-				     struct inet_bind_bucket *tb);
+struct inet_bind_bucket *
+inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
+			struct inet_bind_hashbucket *head,
+			const unsigned short snum);
+void inet_bind_bucket_destroy(struct kmem_cache *cachep,
+			      struct inet_bind_bucket *tb);
 
-static inline int inet_bhashfn(const __u16 lport, const int bhash_size)
+static inline int inet_bhashfn(struct net *net, const __u16 lport,
+			       const int bhash_size)
 {
-	return lport & (bhash_size - 1);
+	return (lport + net_hash_mix(net)) & (bhash_size - 1);
 }
 
-extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
-			   const unsigned short snum);
+void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
+		    const unsigned short snum);
 
 /* These can have wildcards, don't try too hard. */
-static inline int inet_lhashfn(const unsigned short num)
+static inline int inet_lhashfn(struct net *net, const unsigned short num)
 {
-	return num & (INET_LHTABLE_SIZE - 1);
+	return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1);
 }
 
 static inline int inet_sk_listen_hashfn(const struct sock *sk)
 {
-	return inet_lhashfn(inet_sk(sk)->num);
+	return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num);
 }
 
 /* Caller must disable local BH processing. */
-extern void __inet_inherit_port(struct sock *sk, struct sock *child);
-
-extern void inet_put_port(struct sock *sk);
+int __inet_inherit_port(struct sock *sk, struct sock *child);
 
-extern void inet_listen_wlock(struct inet_hashinfo *hashinfo);
+void inet_put_port(struct sock *sk);
 
-/*
- * - We may sleep inside this lock.
- * - If sleeping is not required (or called from BH),
- *   use plain read_(un)lock(&inet_hashinfo.lhash_lock).
- */
-static inline void inet_listen_lock(struct inet_hashinfo *hashinfo)
-{
-	/* read_lock synchronizes to candidates to writers */
-	read_lock(&hashinfo->lhash_lock);
-	atomic_inc(&hashinfo->lhash_users);
-	read_unlock(&hashinfo->lhash_lock);
-}
-
-static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo)
-{
-	if (atomic_dec_and_test(&hashinfo->lhash_users))
-		wake_up(&hashinfo->lhash_wait);
-}
+void inet_hashinfo_init(struct inet_hashinfo *h);
 
-extern void __inet_hash_nolisten(struct sock *sk);
-extern void inet_hash(struct sock *sk);
-extern void inet_unhash(struct sock *sk);
+int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw);
+void inet_hash(struct sock *sk);
+void inet_unhash(struct sock *sk);
 
-extern struct sock *__inet_lookup_listener(struct net *net,
-					   struct inet_hashinfo *hashinfo,
-					   const __be32 daddr,
-					   const unsigned short hnum,
-					   const int dif);
+struct sock *__inet_lookup_listener(struct net *net,
+				    struct inet_hashinfo *hashinfo,
+				    const __be32 saddr, const __be16 sport,
+				    const __be32 daddr,
+				    const unsigned short hnum,
+				    const int dif);
 
 static inline struct sock *inet_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
+		__be32 saddr, __be16 sport,
 		__be32 daddr, __be16 dport, int dif)
 {
-	return __inet_lookup_listener(net, hashinfo, daddr, ntohs(dport), dif);
+	return __inet_lookup_listener(net, hashinfo, saddr, sport,
+				      daddr, ntohs(dport), dif);
 }
 
 /* Socket demux engine toys. */
@@ -272,7 +279,6 @@ static inline struct sock *inet_lookup_listener(struct net *net,
    On 64bit targets we combine comparisons with pair of adjacent __be32
    fields in the same way.
 */
-typedef __u32 __bitwise __portpair;
 #ifdef __BIG_ENDIAN
 #define INET_COMBINED_PORTS(__sport, __dport) \
 	((__force __portpair)(((__force __u32)(__be16)(__sport) << 16) | (__u32)(__dport)))
@@ -282,42 +288,34 @@ typedef __u32 __bitwise __portpair;
 #endif
 
 #if (BITS_PER_LONG == 64)
-typedef __u64 __bitwise __addrpair;
 #ifdef __BIG_ENDIAN
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
 				   (((__force __u64)(__be32)(__saddr)) << 32) | \
-				   ((__force __u64)(__be32)(__daddr)));
+				   ((__force __u64)(__be32)(__daddr)))
 #else /* __LITTLE_ENDIAN */
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
 				   (((__force __u64)(__be32)(__daddr)) << 32) | \
-				   ((__force __u64)(__be32)(__saddr)));
+				   ((__force __u64)(__be32)(__saddr)))
 #endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
-	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&&	\
-	 ((*((__addrpair *)&(inet_sk(__sk)->daddr))) == (__cookie))	&&	\
-	 ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports))	&&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#define INET_TW_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
-	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&&	\
-	 ((*((__addrpair *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) &&	\
-	 ((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) &&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)	\
+	(((__sk)->sk_portpair == (__ports))			&&	\
+	 ((__sk)->sk_addrpair == (__cookie))			&&	\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 		&& 	\
+	 net_eq(sock_net(__sk), (__net)))
 #else /* 32-bit arch */
-#define INET_ADDR_COOKIE(__name, __saddr, __daddr)
-#define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)	\
-	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&&	\
-	 (inet_sk(__sk)->daddr		== (__saddr))		&&	\
-	 (inet_sk(__sk)->rcv_saddr	== (__daddr))		&&	\
-	 ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports))	&&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#define INET_TW_MATCH(__sk, __net, __hash,__cookie, __saddr, __daddr, __ports, __dif)	\
-	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&&	\
-	 (inet_twsk(__sk)->tw_daddr	== (__saddr))		&&	\
-	 (inet_twsk(__sk)->tw_rcv_saddr	== (__daddr))		&&	\
-	 ((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) &&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+	const int __name __deprecated __attribute__((unused))
+
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
+	(((__sk)->sk_portpair == (__ports))		&&		\
+	 ((__sk)->sk_daddr	== (__saddr))		&&		\
+	 ((__sk)->sk_rcv_saddr	== (__daddr))		&&		\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 	&&		\
+	 net_eq(sock_net(__sk), (__net)))
 #endif /* 64-bit arch */
 
 /*
@@ -326,10 +324,11 @@ typedef __u64 __bitwise __addrpair;
  *
  * Local BH must be disabled here.
  */
-extern struct sock * __inet_lookup_established(struct net *net,
-		struct inet_hashinfo *hashinfo,
-		const __be32 saddr, const __be16 sport,
-		const __be32 daddr, const u16 hnum, const int dif);
+struct sock *__inet_lookup_established(struct net *net,
+				       struct inet_hashinfo *hashinfo,
+				       const __be32 saddr, const __be16 sport,
+				       const __be32 daddr, const u16 hnum,
+				       const int dif);
 
 static inline struct sock *
 	inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
@@ -351,7 +350,8 @@ static inline struct sock *__inet_lookup(struct net *net,
 	struct sock *sk = __inet_lookup_established(net, hashinfo,
 				saddr, sport, daddr, hnum, dif);
 
-	return sk ? : __inet_lookup_listener(net, hashinfo, daddr, hnum, dif);
+	return sk ? : __inet_lookup_listener(net, hashinfo, saddr, sport,
+					     daddr, hnum, dif);
 }
 
 static inline struct sock *inet_lookup(struct net *net,
@@ -369,11 +369,30 @@ static inline struct sock *inet_lookup(struct net *net,
 	return sk;
 }
 
-extern int __inet_hash_connect(struct inet_timewait_death_row *death_row,
-		struct sock *sk, u32 port_offset,
-		int (*check_established)(struct inet_timewait_death_row *,
-			struct sock *, __u16, struct inet_timewait_sock **),
-			       void (*hash)(struct sock *sk));
-extern int inet_hash_connect(struct inet_timewait_death_row *death_row,
-			     struct sock *sk);
+static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
+					     struct sk_buff *skb,
+					     const __be16 sport,
+					     const __be16 dport)
+{
+	struct sock *sk = skb_steal_sock(skb);
+	const struct iphdr *iph = ip_hdr(skb);
+
+	if (sk)
+		return sk;
+	else
+		return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
+				     iph->saddr, sport,
+				     iph->daddr, dport, inet_iif(skb));
+}
+
+int __inet_hash_connect(struct inet_timewait_death_row *death_row,
+			struct sock *sk, u32 port_offset,
+			int (*check_established)(struct inet_timewait_death_row *,
+						 struct sock *, __u16,
+						 struct inet_timewait_sock **),
+			int (*hash)(struct sock *sk,
+				    struct inet_timewait_sock *twp));
+
+int inet_hash_connect(struct inet_timewait_death_row *death_row,
+		      struct sock *sk);
 #endif /* _INET_HASHTABLES_H */