[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20221012185243.88948-1-kuniyu@amazon.com>
Date: Wed, 12 Oct 2022 11:52:43 -0700
From: Kuniyuki Iwashima <kuniyu@...zon.com>
To: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
David Ahern <dsahern@...nel.org>,
Martin KaFai Lau <martin.lau@...nel.org>
CC: Craig Gallek <kraig@...gle.com>,
Willem de Bruijn <willemb@...gle.com>,
Kuniyuki Iwashima <kuniyu@...zon.com>,
Kuniyuki Iwashima <kuni1840@...il.com>,
<netdev@...r.kernel.org>
Subject: [PATCH v2 net] udp: Update reuse->has_conns under reuseport_lock.
When we call connect() for a UDP socket in a reuseport group, we have
to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel
could select a unconnected socket wrongly for packets sent to the
connected socket.
However, the current way to set has_conns is illegal and possible to
trigger that problem. reuseport_has_conns() changes has_conns under
rcu_read_lock(), which upgrades the RCU reader to the updater. Then,
it must do the update under the updater's lock, reuseport_lock, but
it doesn't for now.
For this reason, there is a race below where we fail to set has_conns
resulting in the wrong socket selection. To avoid the race, let's split
the reader and updater with proper locking.
cpu1 cpu2
+----+ +----+
__ip[46]_datagram_connect() reuseport_grow()
. .
|- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size)
| . |
| |- rcu_read_lock()
| |- reuse = rcu_dereference(sk->sk_reuseport_cb)
| |
| | | /* reuse->has_conns == 0 here */
| | |- more_reuse->has_conns = reuse->has_conns
| |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */
| | |
| | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
| | | more_reuse)
| `- rcu_read_unlock() `- kfree_rcu(reuse, rcu)
|
|- sk->sk_state = TCP_ESTABLISHED
Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets")
Signed-off-by: Kuniyuki Iwashima <kuniyu@...zon.com>
---
v2:
* Fix build failure for CONFIG_IPV6=m
* Drop SO_INCOMING_CPU fix, which will be sent for net-next
after the v6.1 merge window
v1: https://lore.kernel.org/netdev/20221010174351.11024-1-kuniyu@amazon.com/
---
include/net/sock_reuseport.h | 11 +++++------
net/core/sock_reuseport.c | 15 +++++++++++++++
net/ipv4/datagram.c | 2 +-
net/ipv4/udp.c | 2 +-
net/ipv6/datagram.c | 2 +-
net/ipv6/udp.c | 2 +-
6 files changed, 24 insertions(+), 10 deletions(-)
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 473b0b0fa4ab..efc9085c6892 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
extern int reuseport_detach_prog(struct sock *sk);
-static inline bool reuseport_has_conns(struct sock *sk, bool set)
+static inline bool reuseport_has_conns(struct sock *sk)
{
struct sock_reuseport *reuse;
bool ret = false;
rcu_read_lock();
reuse = rcu_dereference(sk->sk_reuseport_cb);
- if (reuse) {
- if (set)
- reuse->has_conns = 1;
- ret = reuse->has_conns;
- }
+ if (reuse && reuse->has_conns)
+ ret = true;
rcu_read_unlock();
return ret;
}
+void reuseport_has_conns_set(struct sock *sk);
+
#endif /* _SOCK_REUSEPORT_H */
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 5daa1fa54249..abb414ed4aa7 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -21,6 +21,21 @@ static DEFINE_IDA(reuseport_ida);
static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
struct sock_reuseport *reuse, bool bind_inany);
+void reuseport_has_conns_set(struct sock *sk)
+{
+ struct sock_reuseport *reuse;
+
+ if (!rcu_access_pointer(sk->sk_reuseport_cb))
+ return;
+
+ spin_lock(&reuseport_lock);
+ reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+ lockdep_is_held(&reuseport_lock));
+ reuse->has_conns = 1;
+ spin_unlock(&reuseport_lock);
+}
+EXPORT_SYMBOL(reuseport_has_conns_set);
+
static int reuseport_sock_index(struct sock *sk,
const struct sock_reuseport *reuse,
bool closed)
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 405a8c2aea64..5e66add7befa 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
}
inet->inet_daddr = fl4->daddr;
inet->inet_dport = usin->sin_port;
- reuseport_has_conns(sk, true);
+ reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
inet->inet_id = prandom_u32();
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d63118ce5900..29228231b058 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk, false))
+ if (result && !reuseport_has_conns(sk))
return result;
result = result ? : sk;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index df665d4e8f0f..5ecb56522f9d 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
goto out;
}
- reuseport_has_conns(sk, true);
+ reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
out:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 91e795bb9ade..56e4523a3004 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -182,7 +182,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk, false))
+ if (result && !reuseport_has_conns(sk))
return result;
result = result ? : sk;
--
2.30.2
Powered by blists - more mailing lists