From: Eric Dumazet <edumazet@google.com> mainline inclusion from mainline-v6.15-rc1 commit ae9d5b19b322d4b557efda684da2f4df21670ef8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICA4Z5 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- When __inet_hash_connect() has to try many 4-tuples before finding an available one, we see a high spinlock cost from __inet_check_established() and/or __inet6_check_established(). This patch adds an RCU lookup to avoid the spinlock acquisition when the 4-tuple is found in the hash table. Note that there are still spin_lock_bh() calls in __inet_hash_connect() to protect inet_bind_hashbucket, this will be fixed later in this series. Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Jason Xing <kerneljasonxing@gmail.com> Tested-by: Jason Xing <kerneljasonxing@gmail.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://patch.msgid.link/20250302124237.3913746-2-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2@huawei.com> --- net/ipv4/inet_hashtables.c | 19 ++++++++++++++++--- net/ipv6/inet6_hashtables.c | 19 ++++++++++++++++--- 2 files changed, 32 insertions(+), 6 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9ecabf87b474..7a1092529a8e 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -559,11 +559,24 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); - spinlock_t *lock = inet_ehash_lockp(hinfo, hash); - struct sock *sk2; - const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; + const struct hlist_nulls_node *node; + struct sock *sk2; + spinlock_t *lock; + + rcu_read_lock(); + 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(); + lock = inet_ehash_lockp(hinfo, hash); spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b0e8d278e8a9..8c133f6f21b9 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -276,11 +276,24 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); - spinlock_t *lock = inet_ehash_lockp(hinfo, hash); - struct sock *sk2; - const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; + const struct hlist_nulls_node *node; + struct sock *sk2; + spinlock_t *lock; + + rcu_read_lock(); + sk_nulls_for_each(sk2, node, &head->chain) { + if (sk2->sk_hash != hash || + !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(); + lock = inet_ehash_lockp(hinfo, hash); spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { -- 2.25.1