[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241002173042.917928-2-edumazet@google.com>
Date: Wed, 2 Oct 2024 17:30:40 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>
Cc: Neal Cardwell <ncardwell@...gle.com>, netdev@...r.kernel.org, eric.dumazet@...il.com,
Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 1/3] tcp: annotate data-races around icsk->icsk_pending
icsk->icsk_pending can be read locklessly already.
Following patch in the series will add another lockless read.
Add smp_load_acquire() and smp_store_release() annotations
because following patch will add a test in tcp_write_timer(),
and READ_ONCE()/WRITE_ONCE() alone would possibly lead to races.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
include/net/inet_connection_sock.h | 4 ++--
net/ipv4/inet_connection_sock.c | 6 ++++--
net/ipv4/inet_diag.c | 10 ++++++----
net/ipv4/tcp_ipv4.c | 10 ++++++----
net/ipv4/tcp_output.c | 4 ++--
net/ipv4/tcp_timer.c | 4 ++--
net/ipv6/tcp_ipv6.c | 10 ++++++----
7 files changed, 28 insertions(+), 20 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c0deaafebfdc0bc5b7f9e1b2a881f797a1a82ace..914d1977270449241f6fc6da2055f3af02a75f99 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -197,7 +197,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
struct inet_connection_sock *icsk = inet_csk(sk);
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
- icsk->icsk_pending = 0;
+ smp_store_release(&icsk->icsk_pending, 0);
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
@@ -229,7 +229,7 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) {
- icsk->icsk_pending = what;
+ smp_store_release(&icsk->icsk_pending, what);
icsk->icsk_timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
} else if (what == ICSK_TIME_DACK) {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2c5632d4fddbe8ad96f6c35b9ed770d09126eb5d..8c53385cc808c61097898514fd91a322e3a08d31 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -775,7 +775,8 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
- icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+ smp_store_release(&icsk->icsk_pending, 0);
+ icsk->icsk_ack.pending = 0;
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
sk_stop_timer(sk, &icsk->icsk_delack_timer);
@@ -790,7 +791,8 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk)
/* ongoing timer handlers need to acquire socket lock. */
sock_not_owned_by_me(sk);
- icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+ smp_store_release(&icsk->icsk_pending, 0);
+ icsk->icsk_ack.pending = 0;
sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 67639309163d05c034fad80fc9a6096c3b79d42f..321acc8abf17e8c7d6a4e3326615123fff19deab 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -247,6 +247,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
+ u8 icsk_pending;
int protocol;
cb_data = cb->data;
@@ -307,14 +308,15 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
goto out;
}
- if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
- icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
- icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+ icsk_pending = smp_load_acquire(&icsk->icsk_pending);
+ if (icsk_pending == ICSK_TIME_RETRANS ||
+ icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+ icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires =
jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
- } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+ } else if (icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5afe5e57c89b5c28dfada2bf2e01fa7b3afa61f0..985028434f644c399e51d12ba8d9c2c5740dc6e1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2900,15 +2900,17 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
__be32 src = inet->inet_rcv_saddr;
__u16 destp = ntohs(inet->inet_dport);
__u16 srcp = ntohs(inet->inet_sport);
+ u8 icsk_pending;
int rx_queue;
int state;
- if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
- icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
- icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+ icsk_pending = smp_load_acquire(&icsk->icsk_pending);
+ if (icsk_pending == ICSK_TIME_RETRANS ||
+ icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+ icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
- } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+ } else if (icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
timer_expires = icsk->icsk_timeout;
} else if (timer_pending(&sk->sk_timer)) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4fd746bd4d54f621601b20c3821e71370a4a615a..4d04073016035dcf62ba5e0ad23aac86e54e65c7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2960,7 +2960,7 @@ void tcp_send_loss_probe(struct sock *sk)
WARN_ONCE(tp->packets_out,
"invalid inflight: %u state %u cwnd %u mss %d\n",
tp->packets_out, sk->sk_state, tcp_snd_cwnd(tp), mss);
- inet_csk(sk)->icsk_pending = 0;
+ smp_store_release(&inet_csk(sk)->icsk_pending, 0);
return;
}
@@ -2993,7 +2993,7 @@ void tcp_send_loss_probe(struct sock *sk)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
/* Reset s.t. tcp_rearm_rto will restart timer from now */
- inet_csk(sk)->icsk_pending = 0;
+ smp_store_release(&inet_csk(sk)->icsk_pending, 0);
rearm_timer:
tcp_rearm_rto(sk);
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 79064580c8c0d55daa2ab4dc6d27a5ab8802e599..56c597e763ac7a8cebeba324f84e57b1eeeae977 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -701,11 +701,11 @@ void tcp_write_timer_handler(struct sock *sk)
tcp_send_loss_probe(sk);
break;
case ICSK_TIME_RETRANS:
- icsk->icsk_pending = 0;
+ smp_store_release(&icsk->icsk_pending, 0);
tcp_retransmit_timer(sk);
break;
case ICSK_TIME_PROBE0:
- icsk->icsk_pending = 0;
+ smp_store_release(&icsk->icsk_pending, 0);
tcp_probe_timer(sk);
break;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d71ab4e1efe1c6598cf3d3e4334adf0881064ce9..7634c0be6acbdb67bb378cc81bdbf184552d2afc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2177,6 +2177,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
const struct tcp_sock *tp = tcp_sk(sp);
const struct inet_connection_sock *icsk = inet_csk(sp);
const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
+ u8 icsk_pending;
int rx_queue;
int state;
@@ -2185,12 +2186,13 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
destp = ntohs(inet->inet_dport);
srcp = ntohs(inet->inet_sport);
- if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
- icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
- icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+ icsk_pending = smp_load_acquire(&icsk->icsk_pending);
+ if (icsk_pending == ICSK_TIME_RETRANS ||
+ icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+ icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
- } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+ } else if (icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
timer_expires = icsk->icsk_timeout;
} else if (timer_pending(&sp->sk_timer)) {
--
2.47.0.rc0.187.ge670bccf7e-goog
Powered by blists - more mailing lists