5.15-stable review patch. If anyone has any objections, please let me know.
------------------
From: Martin KaFai Lau <kafai@xxxxxx>
[ Upstream commit e8d0059000b20c4745c5b6a713f6adb269cff8ff ]
This patch folds lhash2 related functions into __inet_hash and
inet_unhash. This will make the removal of the listening_hash
in a latter patch easier to review.
First, this patch folds inet_hash2 into __inet_hash.
For unhash, the current call sequence is like
inet_unhash() => __inet_unhash() => inet_unhash2().
The specific testing cases in __inet_unhash() are mostly related
to TCP_LISTEN sk and its caller inet_unhash() already has
the TCP_LISTEN test, so this patch folds both __inet_unhash() and
inet_unhash2() into inet_unhash().
Note that all listening_hash users also have lhash2 initialized,
so the !h->lhash2 check is no longer needed.
Signed-off-by: Martin KaFai Lau <kafai@xxxxxx>
Reviewed-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Stable-dep-of: 871019b22d1b ("net: set SOCK_RCU_FREE before inserting socket into hashtable")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
net/ipv4/inet_hashtables.c | 88 ++++++++++++++------------------------
1 file changed, 33 insertions(+), 55 deletions(-)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 8e0451248fc05..637d806090b00 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -193,40 +193,6 @@ inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk)
return inet_lhash2_bucket(h, hash);
}
-static void inet_hash2(struct inet_hashinfo *h, struct sock *sk)
-{
- struct inet_listen_hashbucket *ilb2;
-
- if (!h->lhash2)
- return;
-
- ilb2 = inet_lhash2_bucket_sk(h, sk);
-
- spin_lock(&ilb2->lock);
- if (sk->sk_reuseport && sk->sk_family == AF_INET6)
- hlist_add_tail_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,
- &ilb2->head);
- else
- hlist_add_head_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,
- &ilb2->head);
- spin_unlock(&ilb2->lock);
-}
-
-static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk)
-{
- struct inet_listen_hashbucket *ilb2;
-
- if (!h->lhash2 ||
- WARN_ON_ONCE(hlist_unhashed(&inet_csk(sk)->icsk_listen_portaddr_node)))
- return;
-
- ilb2 = inet_lhash2_bucket_sk(h, sk);
-
- spin_lock(&ilb2->lock);
- hlist_del_init_rcu(&inet_csk(sk)->icsk_listen_portaddr_node);
- spin_unlock(&ilb2->lock);
-}
-
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum, const __be32 daddr,
const int dif, const int sdif)
@@ -626,6 +592,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
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;
@@ -637,22 +604,29 @@ int __inet_hash(struct sock *sk, struct sock *osk)
}
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);
if (err)
goto unlock;
}
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
- sk->sk_family == AF_INET6)
+ 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
+ } else {
+ hlist_add_head_rcu(&inet_csk(sk)->icsk_listen_portaddr_node,
+ &ilb2->head);
__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
- inet_hash2(hashinfo, sk);
+ }
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;
@@ -670,22 +644,6 @@ int inet_hash(struct sock *sk)
}
EXPORT_SYMBOL_GPL(inet_hash);
-static void __inet_unhash(struct sock *sk, struct inet_listen_hashbucket *ilb)
-{
- if (sk_unhashed(sk))
- return;
-
- if (rcu_access_pointer(sk->sk_reuseport_cb))
- reuseport_stop_listen_sock(sk);
- if (ilb) {
- struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-
- inet_unhash2(hashinfo, sk);
- }
- __sk_nulls_del_node_init_rcu(sk);
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-}
-
void inet_unhash(struct sock *sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
@@ -694,20 +652,40 @@ void inet_unhash(struct sock *sk)
return;
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);
- __inet_unhash(sk, ilb);
+ 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);
spin_lock_bh(lock);
- __inet_unhash(sk, NULL);
+ if (sk_unhashed(sk)) {
+ spin_unlock_bh(lock);
+ return;
+ }
+ __sk_nulls_del_node_init_rcu(sk);
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
spin_unlock_bh(lock);
}
}
--
2.42.0
