[PATCH v3 net-next 06/15] net/ipv4: Use nested-BH locking for ipv4_tcp_sk.

From: Sebastian Andrzej Siewior
Date: Wed May 29 2024 - 12:31:10 EST


ipv4_tcp_sk is a per-CPU variable and relies on disabled BH for its
locking. Without per-CPU locking in local_bh_disable() on PREEMPT_RT
this data structure requires explicit locking.

Make a struct with a sock member (original ipv4_tcp_sk) and a
local_lock_t and use local_lock_nested_bh() for locking. This change
adds only lockdep coverage and does not alter the functional behaviour
for !PREEMPT_RT.

Cc: David Ahern <dsahern@xxxxxxxxxx>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
include/net/sock.h | 5 +++++
net/ipv4/tcp_ipv4.c | 15 +++++++++++----
2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 5f4d0629348f3..365bf676023f8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -544,6 +544,11 @@ struct sock {
netns_tracker ns_tracker;
};

+struct sock_bh_locked {
+ struct sock *sock;
+ local_lock_t bh_lock;
+};
+
enum sk_pacing {
SK_PACING_NONE = 0,
SK_PACING_NEEDED = 1,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f70b8d1d1e56..34c852a4e202d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -93,7 +93,9 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);

-static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
+ .bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};

static u32 tcp_v4_init_seq(const struct sk_buff *skb)
{
@@ -885,7 +887,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
arg.tos = ip_hdr(skb)->tos;
arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ctl_sk = this_cpu_read(ipv4_tcp_sk);
+ local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+ ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
+
sock_net_set(ctl_sk, net);
if (sk) {
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
@@ -910,6 +914,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
+ local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
local_bh_enable();

#ifdef CONFIG_TCP_MD5SIG
@@ -1005,7 +1010,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
arg.tos = tos;
arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ctl_sk = this_cpu_read(ipv4_tcp_sk);
+ local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+ ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
sock_net_set(ctl_sk, net);
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
@@ -1020,6 +1026,7 @@ static void tcp_v4_send_ack(const struct sock *sk,

sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
+ local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
local_bh_enable();
}

@@ -3627,7 +3634,7 @@ void __init tcp_v4_init(void)

sk->sk_clockid = CLOCK_MONOTONIC;

- per_cpu(ipv4_tcp_sk, cpu) = sk;
+ per_cpu(ipv4_tcp_sk.sock, cpu) = sk;
}
if (register_pernet_subsys(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
--
2.45.1