net: Add a bhash2 table hashed by port and address

The current bind hashtable (bhash) is hashed by port only.
In the socket bind path, we have to check for bind conflicts by
traversing the specified port's inet_bind_bucket while holding the
hashbucket's spinlock (see inet_csk_get_port() and
inet_csk_bind_conflict()). In instances where there are tons of
sockets hashed to the same port at different addresses, the bind
conflict check is time-intensive and can cause softirq cpu lockups,
as well as stops new tcp connections since __inet_inherit_port()
also contests for the spinlock.

This patch adds a second bind table, bhash2, that hashes by
port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6).
Searching the bhash2 table leads to significantly faster conflict
resolution and less time holding the hashbucket spinlock.

Please note a few things:
* There can be the case where the a socket's address changes after it
has been bound. There are two cases where this happens:

  1) The case where there is a bind() call on INADDR_ANY (ipv4) or
  IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will
  assign the socket an address when it handles the connect()

  2) In inet_sk_reselect_saddr(), which is called when rebuilding the
  sk header and a few pre-conditions are met (eg rerouting fails).

In these two cases, we need to update the bhash2 table by removing the
entry for the old address, and add a new entry reflecting the updated
address.

* The bhash2 table must have its own lock, even though concurrent
accesses on the same port are protected by the bhash lock. Bhash2 must
have its own lock to protect against cases where sockets on different
ports hash to different bhash hashbuckets but to the same bhash2
hashbucket.

This brings up a few stipulations:
  1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock
  will always be acquired after the bhash lock and released before the
  bhash lock is released.

  2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always
  acquired+released before another bhash2 lock is acquired+released.

* The bhash table cannot be superseded by the bhash2 table because for
bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket
bound to that port must be checked for a potential conflict. The bhash
table is the only source of port->socket associations.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 95 insertions, 2 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index ee88f0f1350f..c2b15f7e5516 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -25,6 +25,7 @@
 #undef INET_CSK_CLEAR_TIMERS
 
 struct inet_bind_bucket;
+struct inet_bind2_bucket;
 struct tcp_congestion_ops;
 
 /*
@@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops {
  *
  * @icsk_accept_queue:	   FIFO of established children
  * @icsk_bind_hash:	   Bind node
+ * @icsk_bind2_hash:	   Bind node in the bhash2 table
  * @icsk_timeout:	   Timeout
  * @icsk_retransmit_timer: Resend (no ack)
  * @icsk_rto:		   Retransmit timeout
@@ -83,6 +85,7 @@ struct inet_connection_sock {
 	struct inet_sock	  icsk_inet;
 	struct request_sock_queue icsk_accept_queue;
 	struct inet_bind_bucket	  *icsk_bind_hash;
+	struct inet_bind2_bucket  *icsk_bind2_hash;
 	unsigned long		  icsk_timeout;
  	struct timer_list	  icsk_retransmit_timer;
  	struct timer_list	  icsk_delack_timer;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index e9cf2157ed8a..44a419b9e3d5 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 +91,28 @@ 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;
+	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);
 }
@@ -133,7 +155,14 @@ 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 */
@@ -182,14 +211,61 @@ 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);
 }
 
+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)
+{
+	u32 hash;
+
+#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,
-		    const unsigned short snum);
+		    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);
diff --git a/include/net/sock.h b/include/net/sock.h
index d08cfe190a78..ca469980e006 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -348,6 +348,7 @@ struct sk_filter;
   *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   *	@ns_tracker: tracker for netns reference
+  *	@sk_bind2_node: bind node in the bhash2 table
   */
 struct sock {
 	/*
@@ -537,6 +538,7 @@ struct sock {
 #endif
 	struct rcu_head		sk_rcu;
 	netns_tracker		ns_tracker;
+	struct hlist_node	sk_bind2_node;
 };
 
 enum sk_pacing {
@@ -870,6 +872,16 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_add_head(&sk->sk_bind_node, list);
 }
 
+static inline void __sk_del_bind2_node(struct sock *sk)
+{
+	__hlist_del(&sk->sk_bind2_node);
+}
+
+static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list)
+{
+	hlist_add_head(&sk->sk_bind2_node, list);
+}
+
 #define sk_for_each(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_node)
 #define sk_for_each_rcu(__sk, list) \
@@ -887,6 +899,8 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
 #define sk_for_each_bound(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_bind_node)
+#define sk_for_each_bound_bhash2(__sk, list) \
+	hlist_for_each_entry(__sk, list, sk_bind2_node)
 
 /**
  * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset