1 files changed, 107 insertions, 68 deletions

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index f72ec113ae56..3af1e927247d 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -23,6 +23,7 @@
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_sock.h>
+#include <net/ip.h>
 #include <net/sock.h>
 #include <net/route.h>
 #include <net/tcp_states.h>
@@ -90,7 +91,31 @@ struct inet_bind_bucket {
 	struct hlist_head	owners;
 };
 
-static inline struct net *ib_net(struct inet_bind_bucket *ib)
+struct inet_bind2_bucket {
+	possible_net_t		ib_net;
+	int			l3mdev;
+	unsigned short		port;
+#if IS_ENABLED(CONFIG_IPV6)
+	unsigned short		family;
+#endif
+	union {
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr		v6_rcv_saddr;
+#endif
+		__be32			rcv_saddr;
+	};
+	/* Node in the bhash2 inet_bind_hashbucket chain */
+	struct hlist_node	node;
+	/* List of sockets hashed to this bucket */
+	struct hlist_head	owners;
+};
+
+static inline struct net *ib_net(const struct inet_bind_bucket *ib)
+{
+	return read_pnet(&ib->ib_net);
+}
+
+static inline struct net *ib2_net(const struct inet_bind2_bucket *ib)
 {
 	return read_pnet(&ib->ib_net);
 }
@@ -111,11 +136,7 @@ struct inet_bind_hashbucket {
 #define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
-	unsigned int		count;
-	union {
-		struct hlist_head	head;
-		struct hlist_nulls_head	nulls_head;
-	};
+	struct hlist_nulls_head	nulls_head;
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */
@@ -137,37 +158,32 @@ struct inet_hashinfo {
 	 * TCP hash as well as the others for fast bind/connect.
 	 */
 	struct kmem_cache		*bind_bucket_cachep;
+	/* This bind table is hashed by local port */
 	struct inet_bind_hashbucket	*bhash;
+	struct kmem_cache		*bind2_bucket_cachep;
+	/* This bind table is hashed by local port and sk->sk_rcv_saddr (ipv4)
+	 * or sk->sk_v6_rcv_saddr (ipv6). This 2nd bind table is used
+	 * primarily for expediting bind conflict resolution.
+	 */
+	struct inet_bind_hashbucket	*bhash2;
 	unsigned int			bhash_size;
 
 	/* The 2nd listener table hashed by local port and address */
 	unsigned int			lhash2_mask;
 	struct inet_listen_hashbucket	*lhash2;
 
-	/* 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
-	 * might be often dirty.
-	 */
-	/* All sockets in TCP_LISTEN state will be in listening_hash.
-	 * This is the only table where wildcard'd TCP sockets can
-	 * exist.  listening_hash is only hashed by local port number.
-	 * If lhash2 is initialized, the same socket will also be hashed
-	 * to lhash2 by port and address.
-	 */
-	struct inet_listen_hashbucket	listening_hash[INET_LHTABLE_SIZE]
-					____cacheline_aligned_in_smp;
+	bool				pernet;
 };
 
-#define inet_lhash2_for_each_icsk_continue(__icsk) \
-	hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node)
-
-#define inet_lhash2_for_each_icsk(__icsk, list) \
-	hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node)
-
-#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \
-	hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node)
+static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IP_DCCP)
+	return sk->sk_prot->h.hashinfo ? :
+		sock_net(sk)->ipv4.tcp_death_row.hashinfo;
+#else
+	return sock_net(sk)->ipv4.tcp_death_row.hashinfo;
+#endif
+}
 
 static inline struct inet_listen_hashbucket *
 inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash)
@@ -203,16 +219,9 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	hashinfo->ehash_locks = NULL;
 }
 
-static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
-					int dif, int sdif)
-{
-#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept,
-				 bound_dev_if, dif, sdif);
-#else
-	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
-#endif
-}
+struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo,
+						 unsigned int ehash_entries);
+void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo);
 
 struct inet_bind_bucket *
 inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
@@ -221,32 +230,67 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
 void inet_bind_bucket_destroy(struct kmem_cache *cachep,
 			      struct inet_bind_bucket *tb);
 
+bool inet_bind_bucket_match(const struct inet_bind_bucket *tb,
+			    const struct net *net, unsigned short port,
+			    int l3mdev);
+
+struct inet_bind2_bucket *
+inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net,
+			 struct inet_bind_hashbucket *head,
+			 unsigned short port, int l3mdev,
+			 const struct sock *sk);
+
+void inet_bind2_bucket_destroy(struct kmem_cache *cachep,
+			       struct inet_bind2_bucket *tb);
+
+struct inet_bind2_bucket *
+inet_bind2_bucket_find(const struct inet_bind_hashbucket *head,
+		       const struct net *net,
+		       unsigned short port, int l3mdev,
+		       const struct sock *sk);
+
+bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb,
+				      const struct net *net, unsigned short port,
+				      int l3mdev, const struct sock *sk);
+
 static inline u32 inet_bhashfn(const struct net *net, const __u16 lport,
 			       const u32 bhash_size)
 {
 	return (lport + net_hash_mix(net)) & (bhash_size - 1);
 }
 
-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 u32 inet_lhashfn(const struct net *net, const unsigned short num)
+static inline struct inet_bind_hashbucket *
+inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk,
+		      const struct net *net, unsigned short port)
 {
-	return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1);
-}
+	u32 hash;
 
-static inline int inet_sk_listen_hashfn(const struct sock *sk)
-{
-	return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		hash = ipv6_portaddr_hash(net, &sk->sk_v6_rcv_saddr, port);
+	else
+#endif
+		hash = ipv4_portaddr_hash(net, sk->sk_rcv_saddr, port);
+	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
 }
 
+struct inet_bind_hashbucket *
+inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port);
+
+/* This should be called whenever a socket's sk_rcv_saddr (ipv4) or
+ * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's
+ * rcv_saddr field should already have been updated when this is called.
+ */
+int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk);
+
+void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
+		    struct inet_bind2_bucket *tb2, unsigned short port);
+
 /* Caller must disable local BH processing. */
 int __inet_inherit_port(const struct sock *sk, struct sock *child);
 
 void inet_put_port(struct sock *sk);
 
-void inet_hashinfo_init(struct inet_hashinfo *h);
 void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 			 unsigned long numentries, int scale,
 			 unsigned long low_limit,
@@ -295,7 +339,6 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 	((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport)))
 #endif
 
-#if (BITS_PER_LONG == 64)
 #ifdef __BIG_ENDIAN
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
@@ -307,24 +350,20 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 				   (((__force __u64)(__be32)(__daddr)) << 32) | \
 				   ((__force __u64)(__be32)(__saddr)))
 #endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
-	(((__sk)->sk_portpair == (__ports))			&&	\
-	 ((__sk)->sk_addrpair == (__cookie))			&&	\
-	 (((__sk)->sk_bound_dev_if == (__dif))			||	\
-	  ((__sk)->sk_bound_dev_if == (__sdif)))		&&	\
-	 net_eq(sock_net(__sk), (__net)))
-#else /* 32-bit arch */
-#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
-	const int __name __deprecated __attribute__((unused))
 
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
-	(((__sk)->sk_portpair == (__ports))		&&		\
-	 ((__sk)->sk_daddr	== (__saddr))		&&		\
-	 ((__sk)->sk_rcv_saddr	== (__daddr))		&&		\
-	 (((__sk)->sk_bound_dev_if == (__dif))		||		\
-	  ((__sk)->sk_bound_dev_if == (__sdif)))	&&		\
-	 net_eq(sock_net(__sk), (__net)))
-#endif /* 64-bit arch */
+static inline bool inet_match(struct net *net, const struct sock *sk,
+			      const __addrpair cookie, const __portpair ports,
+			      int dif, int sdif)
+{
+	if (!net_eq(sock_net(sk), net) ||
+	    sk->sk_portpair != ports ||
+	    sk->sk_addrpair != cookie)
+	        return false;
+
+	/* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */
+	return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif,
+				    sdif);
+}
 
 /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
  * not check it for lookups anymore, thanks Alexey. -DaveM
@@ -425,7 +464,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr)
 }
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
-			struct sock *sk, u32 port_offset,
+			struct sock *sk, u64 port_offset,
 			int (*check_established)(struct inet_timewait_death_row *,
 						 struct sock *, __u16,
 						 struct inet_timewait_sock **));