linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
To: "David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Eric Dumazet <edumazet@google.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>,
	Martin KaFai Lau <kafai@fb.com>
Cc: Benjamin Herrenschmidt <benh@amazon.com>,
	Kuniyuki Iwashima <kuniyu@amazon.co.jp>,
	Kuniyuki Iwashima <kuni1840@gmail.com>, <bpf@vger.kernel.org>,
	<netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: [PATCH v6 bpf-next 02/11] tcp: Add num_closed_socks to struct sock_reuseport.
Date: Mon, 17 May 2021 09:22:49 +0900	[thread overview]
Message-ID: <20210517002258.75019-3-kuniyu@amazon.co.jp> (raw)
In-Reply-To: <20210517002258.75019-1-kuniyu@amazon.co.jp>

As noted in the following commit, a closed listener has to hold the
reference to the reuseport group for socket migration. This patch adds a
field (num_closed_socks) to struct sock_reuseport to manage closed sockets
within the same reuseport group. Moreover, this and the following commits
introduce some helper functions to split socks[] into two sections and keep
TCP_LISTEN and TCP_CLOSE sockets in each section. Like a double-ended
queue, we will place TCP_LISTEN sockets from the front and TCP_CLOSE
sockets from the end.

  TCP_LISTEN---------->       <-------TCP_CLOSE
  +---+---+  ---  +---+  ---  +---+  ---  +---+
  | 0 | 1 |  ...  | i |  ...  | j |  ...  | k |
  +---+---+  ---  +---+  ---  +---+  ---  +---+

  i = num_socks - 1
  j = max_socks - num_closed_socks
  k = max_socks - 1

This patch also extends reuseport_add_sock() and reuseport_grow() to
support num_closed_socks.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
 include/net/sock_reuseport.h |  5 ++-
 net/core/sock_reuseport.c    | 76 +++++++++++++++++++++++++++---------
 2 files changed, 60 insertions(+), 21 deletions(-)

diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 505f1e18e9bf..0e558ca7afbf 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -13,8 +13,9 @@ extern spinlock_t reuseport_lock;
 struct sock_reuseport {
 	struct rcu_head		rcu;
 
-	u16			max_socks;	/* length of socks */
-	u16			num_socks;	/* elements in socks */
+	u16			max_socks;		/* length of socks */
+	u16			num_socks;		/* elements in socks */
+	u16			num_closed_socks;	/* closed elements in socks */
 	/* The last synq overflow event timestamp of this
 	 * reuse->socks[] group.
 	 */
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index b065f0a103ed..079bd1aca0e7 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -18,6 +18,49 @@ DEFINE_SPINLOCK(reuseport_lock);
 
 static DEFINE_IDA(reuseport_ida);
 
+static int reuseport_sock_index(struct sock *sk,
+				struct sock_reuseport *reuse,
+				bool closed)
+{
+	int left, right;
+
+	if (!closed) {
+		left = 0;
+		right = reuse->num_socks;
+	} else {
+		left = reuse->max_socks - reuse->num_closed_socks;
+		right = reuse->max_socks;
+	}
+
+	for (; left < right; left++)
+		if (reuse->socks[left] == sk)
+			return left;
+	return -1;
+}
+
+static void __reuseport_add_sock(struct sock *sk,
+				 struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->num_socks] = sk;
+	/* paired with smp_rmb() in reuseport_select_sock() */
+	smp_wmb();
+	reuse->num_socks++;
+}
+
+static bool __reuseport_detach_sock(struct sock *sk,
+				    struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, false);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
+	reuse->num_socks--;
+
+	return true;
+}
+
 static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
 	unsigned int size = sizeof(struct sock_reuseport) +
@@ -72,9 +115,8 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
 	}
 
 	reuse->reuseport_id = id;
-	reuse->socks[0] = sk;
-	reuse->num_socks = 1;
 	reuse->bind_inany = bind_inany;
+	__reuseport_add_sock(sk, reuse);
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 out:
@@ -98,6 +140,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 		return NULL;
 
 	more_reuse->num_socks = reuse->num_socks;
+	more_reuse->num_closed_socks = reuse->num_closed_socks;
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
 	more_reuse->bind_inany = reuse->bind_inany;
@@ -105,9 +148,13 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
+	memcpy(more_reuse->socks +
+	       (more_reuse->max_socks - more_reuse->num_closed_socks),
+	       reuse->socks + reuse->num_socks,
+	       reuse->num_closed_socks * sizeof(struct sock *));
 	more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts);
 
-	for (i = 0; i < reuse->num_socks; ++i)
+	for (i = 0; i < reuse->max_socks; ++i)
 		rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
 				   more_reuse);
 
@@ -158,7 +205,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 		return -EBUSY;
 	}
 
-	if (reuse->num_socks == reuse->max_socks) {
+	if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
 		reuse = reuseport_grow(reuse);
 		if (!reuse) {
 			spin_unlock_bh(&reuseport_lock);
@@ -166,10 +213,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 		}
 	}
 
-	reuse->socks[reuse->num_socks] = sk;
-	/* paired with smp_rmb() in reuseport_select_sock() */
-	smp_wmb();
-	reuse->num_socks++;
+	__reuseport_add_sock(sk, reuse);
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 	spin_unlock_bh(&reuseport_lock);
@@ -183,7 +227,6 @@ EXPORT_SYMBOL(reuseport_add_sock);
 void reuseport_detach_sock(struct sock *sk)
 {
 	struct sock_reuseport *reuse;
-	int i;
 
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
@@ -200,16 +243,11 @@ void reuseport_detach_sock(struct sock *sk)
 	bpf_sk_reuseport_detach(sk);
 
 	rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
+	__reuseport_detach_sock(sk, reuse);
+
+	if (reuse->num_socks + reuse->num_closed_socks == 0)
+		call_rcu(&reuse->rcu, reuseport_free_rcu);
 
-	for (i = 0; i < reuse->num_socks; i++) {
-		if (reuse->socks[i] == sk) {
-			reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
-			reuse->num_socks--;
-			if (reuse->num_socks == 0)
-				call_rcu(&reuse->rcu, reuseport_free_rcu);
-			break;
-		}
-	}
 	spin_unlock_bh(&reuseport_lock);
 }
 EXPORT_SYMBOL(reuseport_detach_sock);
@@ -274,7 +312,7 @@ struct sock *reuseport_select_sock(struct sock *sk,
 	prog = rcu_dereference(reuse->prog);
 	socks = READ_ONCE(reuse->num_socks);
 	if (likely(socks)) {
-		/* paired with smp_wmb() in reuseport_add_sock() */
+		/* paired with smp_wmb() in __reuseport_add_sock() */
 		smp_rmb();
 
 		if (!prog || !skb)
-- 
2.30.2


  parent reply	other threads:[~2021-05-17  0:23 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-17  0:22 [PATCH v6 bpf-next 00/11] Socket migration for SO_REUSEPORT Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 01/11] net: Introduce net.ipv4.tcp_migrate_req Kuniyuki Iwashima
2021-05-17  0:22 ` Kuniyuki Iwashima [this message]
2021-05-17  0:22 ` [PATCH v6 bpf-next 03/11] tcp: Keep TCP_CLOSE sockets in the reuseport group Kuniyuki Iwashima
2021-05-20  6:26   ` Martin KaFai Lau
2021-05-20  8:51     ` Kuniyuki Iwashima
2021-05-20 21:22       ` Martin KaFai Lau
2021-05-20 22:54         ` Kuniyuki Iwashima
2021-05-20 23:39           ` Martin KaFai Lau
2021-05-21  0:26             ` Kuniyuki Iwashima
2021-05-21  4:47               ` Martin KaFai Lau
2021-05-21  5:15                 ` Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 04/11] tcp: Add reuseport_migrate_sock() to select a new listener Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 05/11] tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 06/11] tcp: Migrate TCP_NEW_SYN_RECV requests at retransmitting SYN+ACKs Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 07/11] tcp: Migrate TCP_NEW_SYN_RECV requests at receiving the final ACK Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 08/11] bpf: Support BPF_FUNC_get_socket_cookie() for BPF_PROG_TYPE_SK_REUSEPORT Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 09/11] bpf: Support socket migration by eBPF Kuniyuki Iwashima
2021-05-20  6:27   ` Martin KaFai Lau
2021-05-20  8:54     ` Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 10/11] libbpf: Set expected_attach_type for BPF_PROG_TYPE_SK_REUSEPORT Kuniyuki Iwashima
2021-05-17  0:22 ` [PATCH v6 bpf-next 11/11] bpf: Test BPF_SK_REUSEPORT_SELECT_OR_MIGRATE Kuniyuki Iwashima
2021-05-20  6:30 ` [PATCH v6 bpf-next 00/11] Socket migration for SO_REUSEPORT Martin KaFai Lau
2021-05-20  8:58   ` 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=20210517002258.75019-3-kuniyu@amazon.co.jp \
    --to=kuniyu@amazon.co.jp \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=benh@amazon.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kafai@fb.com \
    --cc=kuba@kernel.org \
    --cc=kuni1840@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    /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).