Commit cae3873c authored by Martin KaFai Lau's avatar Martin KaFai Lau Committed by Jakub Kicinski
Browse files

net: inet: Retire port only listening_hash 



The listen sk is currently stored in two hash tables,
listening_hash (hashed by port) and lhash2 (hashed by port and address).

After commit 0ee58dad ("net: tcp6: prefer listeners bound to an address")
and commit d9fbc7f6 ("net: tcp: prefer listeners bound to an address"),
the TCP-SYN lookup fast path does not use listening_hash.

The commit 05c0b357 ("tcp: seq_file: Replace listening_hash with lhash2")
also moved the seq_file (/proc/net/tcp) iteration usage from
listening_hash to lhash2.

There are still a few listening_hash usages left.
One of them is inet_reuseport_add_sock() which uses the listening_hash
to search a listen sk during the listen() system call.  This turns
out to be very slow on use cases that listen on many different
VIPs at a popular port (e.g. 443).  [ On top of the slowness in
adding to the tail in the IPv6 case ].  The latter patch has a
selftest to demonstrate this case.

This patch takes this chance to move all remaining listening_hash
usages to lhash2 and then retire listening_hash.

Since most changes need to be done together, it is hard to cut
the listening_hash to lhash2 switch into small patches.  The
changes in this patch is highlighted here for the review
purpose.

1. Because of the listening_hash removal, lhash2 can use the
   sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node.
   This will also keep the sk_unhashed() check to work as is
   after stop adding sk to listening_hash.

   The union is removed from inet_listen_hashbucket because
   only nulls_head is needed.

2. icsk->icsk_listen_portaddr_node and its helpers are removed.

3. The current lhash2 users needs to iterate with sk_nulls_node
   instead of icsk_listen_portaddr_node.

   One case is in the inet[6]_lhash2_lookup().

   Another case is the seq_file iterator in tcp_ipv4.c.
   One thing to note is sk_nulls_next() is needed
   because the old inet_lhash2_for_each_icsk_continue()
   does a "next" first before iterating.

4. Move the remaining listening_hash usage to lhash2

   inet_reuseport_add_sock() which this series is
   trying to improve.

   inet_diag.c and mptcp_diag.c are the final two
   remaining use cases and is moved to lhash2 now also.

Signed-off-by: default avatarMartin KaFai Lau <kafai@fb.com>
Reviewed-by: default avatarEric Dumazet <edumazet@google.com>
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent e8d00590

include/net/inet_connection_sock.h

+0 −2
Original line number Diff line number Diff line
@@ -66,7 +66,6 @@ struct inet_connection_sock_af_ops { 
 * @icsk_ulp_ops	   Pluggable ULP control hook

 * @icsk_ulp_data	   ULP private data

 * @icsk_clean_acked	   Clean acked data hook

 * @icsk_listen_portaddr_node	hash to the portaddr listener hashtable

 * @icsk_ca_state:	   Congestion control state

 * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts

 * @icsk_pending:	   Scheduled timer event
@@ -96,7 +95,6 @@ struct inet_connection_sock { 
	const struct tcp_ulp_ops  *icsk_ulp_ops;

	void __rcu		  *icsk_ulp_data;

	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);

	struct hlist_node         icsk_listen_portaddr_node;

	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);

	__u8			  icsk_ca_state:5,

				  icsk_ca_initialized:1,

include/net/inet_hashtables.h

+1 −40
Original line number Diff line number Diff line
@@ -111,11 +111,8 @@ struct inet_bind_hashbucket { 
#define LISTENING_NULLS_BASE (1U << 29)

struct inet_listen_hashbucket {

	spinlock_t		lock;

	union {

		struct hlist_head	head;

	struct hlist_nulls_head	nulls_head;

};

};



/* This is for listening sockets, thus all sockets which possess wildcards. */

#define INET_LHTABLE_SIZE	32	/* Yes, really, this is all you need. */
@@ -142,32 +139,8 @@ struct inet_hashinfo { 
	/* 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;

};



#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_listen_hashbucket *

inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash)

{
@@ -229,23 +202,11 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, 
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)

{

	return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1);

}



static inline int inet_sk_listen_hashfn(const struct sock *sk)

{

	return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num);

}



/* 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,

net/dccp/proto.c

+0 −1
Original line number Diff line number Diff line
@@ -1110,7 +1110,6 @@ static int __init dccp_init(void) 


	BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >

		     sizeof_field(struct sk_buff, cb));

	inet_hashinfo_init(&dccp_hashinfo);

	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);

	if (rc)

		goto out_fail;

net/ipv4/inet_diag.c

+3 −2
Original line number Diff line number Diff line
@@ -1028,12 +1028,13 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, 
		if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport)

			goto skip_listen_ht;



		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {

		for (i = s_i; i <= hashinfo->lhash2_mask; i++) {

			struct inet_listen_hashbucket *ilb;

			struct hlist_nulls_node *node;



			num = 0;

			ilb = &hashinfo->listening_hash[i];

			ilb = &hashinfo->lhash2[i];



			spin_lock(&ilb->lock);

			sk_nulls_for_each(sk, node, &ilb->nulls_head) {

				struct inet_sock *inet = inet_sk(sk);

net/ipv4/inet_hashtables.c

+9 −38
Original line number Diff line number Diff line
@@ -246,12 +246,11 @@ static struct sock *inet_lhash2_lookup(struct net *net, 
				const __be32 daddr, const unsigned short hnum,

				const int dif, const int sdif)

{

	struct inet_connection_sock *icsk;

	struct sock *sk, *result = NULL;

	struct hlist_nulls_node *node;

	int score, hiscore = 0;



	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {

		sk = (struct sock *)icsk;

	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {

		score = compute_score(sk, net, hnum, daddr, dif, sdif);

		if (score > hiscore) {

			result = lookup_reuseport(net, sk, skb, doff,
@@ -598,7 +597,6 @@ int __inet_hash(struct sock *sk, struct sock *osk) 
{

	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;

	struct inet_listen_hashbucket *ilb2;

	struct inet_listen_hashbucket *ilb;

	int err = 0;



	if (sk->sk_state != TCP_LISTEN) {
@@ -608,31 +606,23 @@ int __inet_hash(struct sock *sk, struct sock *osk) 
		return 0;

	}

	WARN_ON(!sk_unhashed(sk));

	ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];

	ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);



	spin_lock(&ilb->lock);

	spin_lock(&ilb2->lock);

	if (sk->sk_reuseport) {

		err = inet_reuseport_add_sock(sk, ilb);

		err = inet_reuseport_add_sock(sk, ilb2);

		if (err)

			goto unlock;

	}

	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&

		sk->sk_family == AF_INET6) {

		hlist_add_tail_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,

				   &ilb2->head);

		__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);

	} else {

		hlist_add_head_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,

				   &ilb2->head);

		__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);

	}

		sk->sk_family == AF_INET6)

		__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);

	else

		__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);

	sock_set_flag(sk, SOCK_RCU_FREE);

	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);

unlock:

	spin_unlock(&ilb2->lock);

	spin_unlock(&ilb->lock);



	return err;

}
@@ -658,29 +648,23 @@ void inet_unhash(struct sock *sk) 


	if (sk->sk_state == TCP_LISTEN) {

		struct inet_listen_hashbucket *ilb2;

		struct inet_listen_hashbucket *ilb;



		ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];

		ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);

		/* Don't disable bottom halves while acquiring the lock to

		 * avoid circular locking dependency on PREEMPT_RT.

		 */

		spin_lock(&ilb->lock);

		spin_lock(&ilb2->lock);

		if (sk_unhashed(sk)) {

			spin_unlock(&ilb2->lock);

			spin_unlock(&ilb->lock);

			return;

		}



		if (rcu_access_pointer(sk->sk_reuseport_cb))

			reuseport_stop_listen_sock(sk);



		hlist_del_init_rcu(&inet_csk(sk)->icsk_listen_portaddr_node);

		__sk_nulls_del_node_init_rcu(sk);

		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);

		spin_unlock(&ilb2->lock);

		spin_unlock(&ilb->lock);

	} else {

		spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
@@ -848,27 +832,14 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row, 
}

EXPORT_SYMBOL_GPL(inet_hash_connect);



void inet_hashinfo_init(struct inet_hashinfo *h)

{

	int i;



	for (i = 0; i < INET_LHTABLE_SIZE; i++) {

		spin_lock_init(&h->listening_hash[i].lock);

		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,

				      i + LISTENING_NULLS_BASE);

	}



	h->lhash2 = NULL;

}

EXPORT_SYMBOL_GPL(inet_hashinfo_init);



static void init_hashinfo_lhash2(struct inet_hashinfo *h)

{

	int i;



	for (i = 0; i <= h->lhash2_mask; i++) {

		spin_lock_init(&h->lhash2[i].lock);

		INIT_HLIST_HEAD(&h->lhash2[i].head);

		INIT_HLIST_NULLS_HEAD(&h->lhash2[i].nulls_head,

				      i + LISTENING_NULLS_BASE);

	}

}