netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kuniyuki Iwashima <kuniyu@amazon.com>
To: "David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>,
	Kuniyuki Iwashima <kuni1840@gmail.com>, <netdev@vger.kernel.org>
Subject: [PATCH v3 net-next 2/5] tcp: Set NULL to sk->sk_prot->h.hashinfo.
Date: Tue, 30 Aug 2022 12:15:15 -0700	[thread overview]
Message-ID: <20220830191518.77083-3-kuniyu@amazon.com> (raw)
In-Reply-To: <20220830191518.77083-1-kuniyu@amazon.com>

We will soon introduce an optional per-netns ehash.

This means we cannot use the global sk->sk_prot->h.hashinfo
to fetch a TCP hashinfo.

Instead, set NULL to sk->sk_prot->h.hashinfo for TCP and get
a proper hashinfo from net->ipv4.tcp_death_row->hashinfo.

Note that we need not use sk->sk_prot->h.hashinfo if DCCP is
disabled.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
 include/net/inet_hashtables.h   | 10 ++++++++++
 net/ipv4/af_inet.c              |  2 +-
 net/ipv4/inet_connection_sock.c |  9 ++++-----
 net/ipv4/inet_hashtables.c      | 14 +++++++-------
 net/ipv4/tcp_ipv4.c             |  2 +-
 net/ipv6/tcp_ipv6.c             |  2 +-
 6 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 44a419b9e3d5..1ff5603cddff 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -170,6 +170,16 @@ struct inet_hashinfo {
 	struct inet_listen_hashbucket	*lhash2;
 };
 
+static inline struct inet_hashinfo *tcp_or_dccp_get_hashinfo(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IP_DCCP)
+	return sk->sk_prot->h.hashinfo ? :
+		sock_net(sk)->ipv4.tcp_death_row->hashinfo;
+#else
+	return sock_net(sk)->ipv4.tcp_death_row->hashinfo;
+#endif
+}
+
 static inline struct inet_listen_hashbucket *
 inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d3ab1ae32ef5..e2c219382345 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1250,7 +1250,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	}
 
 	prev_addr_hashbucket =
-		inet_bhashfn_portaddr(sk->sk_prot->h.hashinfo, sk,
+		inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk,
 				      sock_net(sk), inet->inet_num);
 
 	inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8e71d65cfad4..ebca860e113f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -285,7 +285,7 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret,
 			struct inet_bind2_bucket **tb2_ret,
 			struct inet_bind_hashbucket **head2_ret, int *port_ret)
 {
-	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	int i, low, high, attempt_half, port, l3mdev;
 	struct inet_bind_hashbucket *head, *head2;
 	struct net *net = sock_net(sk);
@@ -467,8 +467,8 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
  */
 int inet_csk_get_port(struct sock *sk, unsigned short snum)
 {
+	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
-	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
 	bool found_port = false, check_bind_conflict = true;
 	bool bhash_created = false, bhash2_created = false;
 	struct inet_bind_hashbucket *head, *head2;
@@ -910,10 +910,9 @@ static bool reqsk_queue_unlink(struct request_sock *req)
 	bool found = false;
 
 	if (sk_hashed(sk)) {
-		struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-		spinlock_t *lock;
+		struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
+		spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
 
-		lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
 		spin_lock(lock);
 		found = __sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 29dce78de179..bdb5427a7a3d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -168,7 +168,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
  */
 static void __inet_put_port(struct sock *sk)
 {
-	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
 	struct inet_bind_hashbucket *head, *head2;
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb;
@@ -208,7 +208,7 @@ EXPORT_SYMBOL(inet_put_port);
 
 int __inet_inherit_port(const struct sock *sk, struct sock *child)
 {
-	struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk);
 	unsigned short port = inet_sk(child)->inet_num;
 	struct inet_bind_hashbucket *head, *head2;
 	bool created_inet_bind_bucket = false;
@@ -629,7 +629,7 @@ static bool inet_ehash_lookup_by_sk(struct sock *sk,
  */
 bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 {
-	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
 	struct inet_ehash_bucket *head;
 	struct hlist_nulls_head *list;
 	spinlock_t *lock;
@@ -701,7 +701,7 @@ 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_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
 	struct inet_listen_hashbucket *ilb2;
 	int err = 0;
 
@@ -747,7 +747,7 @@ EXPORT_SYMBOL_GPL(inet_hash);
 
 void inet_unhash(struct sock *sk)
 {
-	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
 
 	if (sk_unhashed(sk))
 		return;
@@ -834,7 +834,7 @@ inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net
 struct inet_bind_hashbucket *
 inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port)
 {
-	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	u32 hash;
 #if IS_ENABLED(CONFIG_IPV6)
 	struct in6_addr addr_any = {};
@@ -850,7 +850,7 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in
 
 int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk)
 {
-	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
+	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	struct inet_bind2_bucket *tb2, *new_tb2;
 	int l3mdev = inet_sk_bound_l3mdev(sk);
 	struct inet_bind_hashbucket *head2;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 61a9bf661814..7c3b3ce85a5e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3083,7 +3083,7 @@ struct proto tcp_prot = {
 	.slab_flags		= SLAB_TYPESAFE_BY_RCU,
 	.twsk_prot		= &tcp_timewait_sock_ops,
 	.rsk_prot		= &tcp_request_sock_ops,
-	.h.hashinfo		= &tcp_hashinfo,
+	.h.hashinfo		= NULL,
 	.no_autobind		= true,
 	.diag_destroy		= tcp_abort,
 };
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ff5c4fc135fc..791f24da9212 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2193,7 +2193,7 @@ struct proto tcpv6_prot = {
 	.slab_flags		= SLAB_TYPESAFE_BY_RCU,
 	.twsk_prot		= &tcp6_timewait_sock_ops,
 	.rsk_prot		= &tcp6_request_sock_ops,
-	.h.hashinfo		= &tcp_hashinfo,
+	.h.hashinfo		= NULL,
 	.no_autobind		= true,
 	.diag_destroy		= tcp_abort,
 };
-- 
2.30.2


  parent reply	other threads:[~2022-08-30 19:16 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-30 19:15 [PATCH v3 net-next 0/5] tcp: Introduce optional per-netns ehash Kuniyuki Iwashima
2022-08-30 19:15 ` [PATCH v3 net-next 1/5] tcp: Clean up some functions Kuniyuki Iwashima
2022-08-30 19:15 ` Kuniyuki Iwashima [this message]
2022-08-30 19:15 ` [PATCH v3 net-next 3/5] tcp: Access &tcp_hashinfo via net Kuniyuki Iwashima
2022-09-01 10:57   ` Paolo Abeni
2022-09-01 21:25     ` Kuniyuki Iwashima
2022-09-01 21:30       ` Eric Dumazet
2022-09-01 22:12         ` Kuniyuki Iwashima
2022-09-03  0:44           ` Kuniyuki Iwashima
2022-09-03  0:53             ` Eric Dumazet
2022-09-03  1:12               ` Kuniyuki Iwashima
2022-09-03  1:44                 ` Kuniyuki Iwashima
2022-09-03  2:30                   ` Eric Dumazet
2022-09-03  2:50                     ` Kuniyuki Iwashima
2022-09-03  3:16                       ` Eric Dumazet
2022-09-03  3:25                         ` Kuniyuki Iwashima
2022-09-01 21:49       ` Jakub Kicinski
2022-09-01 22:19         ` Kuniyuki Iwashima
2022-08-30 19:15 ` [PATCH v3 net-next 4/5] tcp: Save unnecessary inet_twsk_purge() calls Kuniyuki Iwashima
2022-08-30 19:15 ` [PATCH v3 net-next 5/5] tcp: Introduce optional per-netns ehash Kuniyuki Iwashima

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220830191518.77083-3-kuniyu@amazon.com \
    --to=kuniyu@amazon.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=kuni1840@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).