Commit 86c2bc29 authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski
Browse files

tcp: use RCU lookup in __inet_hash_connect() 



When __inet_hash_connect() has to try many 4-tuples before
finding an available one, we see a high spinlock cost from
the many spin_lock_bh(&head->lock) performed in its loop.

This patch adds an RCU lookup to avoid the spinlock cost.

check_established() gets a new @rcu_lookup argument.
First reason is to not make any changes while head->lock
is not held.
Second reason is to not make this RCU lookup a second time
after the spinlock has been acquired.

Tested:

Server:

ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog

Client:

ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog -c -H server

Before series:

  utime_start=0.288582
  utime_end=1.548707
  stime_start=20.637138
  stime_end=2002.489845
  num_transactions=484453
  latency_min=0.156279245
  latency_max=20.922042756
  latency_mean=1.546521274
  latency_stddev=3.936005194
  num_samples=312537
  throughput=47426.00

perf top on the client:

 49.54%  [kernel]       [k] _raw_spin_lock
 25.87%  [kernel]       [k] _raw_spin_lock_bh
  5.97%  [kernel]       [k] queued_spin_lock_slowpath
  5.67%  [kernel]       [k] __inet_hash_connect
  3.53%  [kernel]       [k] __inet6_check_established
  3.48%  [kernel]       [k] inet6_ehashfn
  0.64%  [kernel]       [k] rcu_all_qs

After this series:

  utime_start=0.271607
  utime_end=3.847111
  stime_start=18.407684
  stime_end=1997.485557
  num_transactions=1350742
  latency_min=0.014131929
  latency_max=17.895073144
  latency_mean=0.505675853  # Nice reduction of latency metrics
  latency_stddev=2.125164772
  num_samples=307884
  throughput=139866.80      # 190 % increase

perf top on client:

 56.86%  [kernel]       [k] __inet6_check_established
 17.96%  [kernel]       [k] __inet_hash_connect
 13.88%  [kernel]       [k] inet6_ehashfn
  2.52%  [kernel]       [k] rcu_all_qs
  2.01%  [kernel]       [k] __cond_resched
  0.41%  [kernel]       [k] _raw_spin_lock

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarJason Xing <kerneljasonxing@gmail.com>
Tested-by: default avatarJason Xing <kerneljasonxing@gmail.com>
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250302124237.3913746-5-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent d186f405

include/net/inet_hashtables.h

+2 −1
Original line number Diff line number Diff line
@@ -529,7 +529,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 
			struct sock *sk, u64 port_offset,

			int (*check_established)(struct inet_timewait_death_row *,

						 struct sock *, __u16,

						 struct inet_timewait_sock **));

						 struct inet_timewait_sock **,

						 bool rcu_lookup));



int inet_hash_connect(struct inet_timewait_death_row *death_row,

		      struct sock *sk);

net/ipv4/inet_hashtables.c

+35 −17
Original line number Diff line number Diff line
@@ -537,7 +537,8 @@ EXPORT_SYMBOL_GPL(__inet_lookup_established); 
/* called with local bh disabled */

static int __inet_check_established(struct inet_timewait_death_row *death_row,

				    struct sock *sk, __u16 lport,

				    struct inet_timewait_sock **twp)

				    struct inet_timewait_sock **twp,

				    bool rcu_lookup)

{

	struct inet_hashinfo *hinfo = death_row->hashinfo;

	struct inet_sock *inet = inet_sk(sk);
@@ -556,17 +557,17 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, 
	struct sock *sk2;

	spinlock_t *lock;



	rcu_read_lock();

	if (rcu_lookup) {

		sk_nulls_for_each(sk2, node, &head->chain) {

			if (sk2->sk_hash != hash ||

			    !inet_match(net, sk2, acookie, ports, dif, sdif))

				continue;

			if (sk2->sk_state == TCP_TIME_WAIT)

				break;

		rcu_read_unlock();

			return -EADDRNOTAVAIL;

		}

	rcu_read_unlock();

		return 0;

	}



	lock = inet_ehash_lockp(hinfo, hash);

	spin_lock(lock);
@@ -1007,7 +1008,8 @@ static u32 *table_perturb; 
int __inet_hash_connect(struct inet_timewait_death_row *death_row,

		struct sock *sk, u64 port_offset,

		int (*check_established)(struct inet_timewait_death_row *,

			struct sock *, __u16, struct inet_timewait_sock **))

			struct sock *, __u16, struct inet_timewait_sock **,

			bool rcu_lookup))

{

	struct inet_hashinfo *hinfo = death_row->hashinfo;

	struct inet_bind_hashbucket *head, *head2;
@@ -1025,7 +1027,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 


	if (port) {

		local_bh_disable();

		ret = check_established(death_row, sk, port, NULL);

		ret = check_established(death_row, sk, port, NULL, false);

		local_bh_enable();

		return ret;

	}
@@ -1061,6 +1063,21 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 
			continue;

		head = &hinfo->bhash[inet_bhashfn(net, port,

						  hinfo->bhash_size)];

		rcu_read_lock();

		hlist_for_each_entry_rcu(tb, &head->chain, node) {

			if (!inet_bind_bucket_match(tb, net, port, l3mdev))

				continue;

			if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) {

				rcu_read_unlock();

				goto next_port;

			}

			if (!check_established(death_row, sk, port, &tw, true))

				break;

			rcu_read_unlock();

			goto next_port;

		}

		rcu_read_unlock();



		spin_lock_bh(&head->lock);



		/* Does not bother with rcv_saddr checks, because
@@ -1070,12 +1087,12 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 
			if (inet_bind_bucket_match(tb, net, port, l3mdev)) {

				if (tb->fastreuse >= 0 ||

				    tb->fastreuseport >= 0)

					goto next_port;

					goto next_port_unlock;

				WARN_ON(hlist_empty(&tb->bhash2));

				if (!check_established(death_row, sk,

						       port, &tw))

						       port, &tw, false))

					goto ok;

				goto next_port;

				goto next_port_unlock;

			}

		}
@@ -1089,8 +1106,9 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, 
		tb->fastreuse = -1;

		tb->fastreuseport = -1;

		goto ok;

next_port:

next_port_unlock:

		spin_unlock_bh(&head->lock);

next_port:

		cond_resched();

	}

net/ipv6/inet6_hashtables.c

+13 −11
Original line number Diff line number Diff line
@@ -263,7 +263,8 @@ EXPORT_SYMBOL_GPL(inet6_lookup); 


static int __inet6_check_established(struct inet_timewait_death_row *death_row,

				     struct sock *sk, const __u16 lport,

				     struct inet_timewait_sock **twp)

				     struct inet_timewait_sock **twp,

				     bool rcu_lookup)

{

	struct inet_hashinfo *hinfo = death_row->hashinfo;

	struct inet_sock *inet = inet_sk(sk);
@@ -281,17 +282,18 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, 
	struct sock *sk2;

	spinlock_t *lock;



	rcu_read_lock();

	if (rcu_lookup) {

		sk_nulls_for_each(sk2, node, &head->chain) {

			if (sk2->sk_hash != hash ||

		    !inet6_match(net, sk2, saddr, daddr, ports, dif, sdif))

			    !inet6_match(net, sk2, saddr, daddr,

					 ports, dif, sdif))

				continue;

			if (sk2->sk_state == TCP_TIME_WAIT)

				break;

		rcu_read_unlock();

			return -EADDRNOTAVAIL;

		}

	rcu_read_unlock();

		return 0;

	}



	lock = inet_ehash_lockp(hinfo, hash);

	spin_lock(lock);