From 348b81b68b13ebd489a3e6a46aa1c384c731c919 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:47 +0000 Subject: tcp: annotate data-races around tp->tcp_tx_delay do_tcp_getsockopt() reads tp->tcp_tx_delay while another cpu might change its value. Fixes: a842fe1425cb ("tcp: add optional per socket transmit delay") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03e08745308..bd6400e1ae9f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3674,7 +3674,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -4154,7 +4154,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: -- cgit From dd23c9f1e8d5c1d2e3d29393412385ccb9c7a948 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:48 +0000 Subject: tcp: annotate data-races around tp->tsoffset do_tcp_getsockopt() reads tp->tsoffset while another cpu might change its value. Fixes: 93be6ce0e91b ("tcp: set and get per-socket timestamp") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bd6400e1ae9f..03ae6554c78d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3656,7 +3656,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp_raw(); + WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -4158,7 +4158,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + tp->tsoffset; + val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; -- cgit From 4164245c76ff906c9086758e1c3f87082a7f5ef5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:49 +0000 Subject: tcp: annotate data-races around tp->keepalive_time do_tcp_getsockopt() reads tp->keepalive_time while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 03ae6554c78d..b4f7856dfb16 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3312,7 +3312,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); -- cgit From 5ecf9d4f52ff2f1d4d44c9b68bc75688e82f13b4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:50 +0000 Subject: tcp: annotate data-races around tp->keepalive_intvl do_tcp_getsockopt() reads tp->keepalive_intvl while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-5-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b4f7856dfb16..d55fe014e7c9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3345,7 +3345,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3559,7 +3559,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) -- cgit From 6e5e1de616bf5f3df1769abc9292191dfad9110a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:51 +0000 Subject: tcp: annotate data-races around tp->keepalive_probes do_tcp_getsockopt() reads tp->keepalive_probes while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-6-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d55fe014e7c9..574fd0da1673 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3357,7 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3565,7 +3566,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) -- cgit From 3a037f0f3c4bfe44518f2fbb478aa2f99a9cd8bb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:52 +0000 Subject: tcp: annotate data-races around icsk->icsk_syn_retries do_tcp_getsockopt() and reqsk_timer_handler() read icsk->icsk_syn_retries while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-7-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 574fd0da1673..9f74ac16f1c1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3291,7 +3291,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3572,7 +3572,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3993,7 +3993,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: -- cgit From 9df5335ca974e688389c875546e5819778a80d59 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:53 +0000 Subject: tcp: annotate data-races around tp->linger2 do_tcp_getsockopt() reads tp->linger2 while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-8-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9f74ac16f1c1..2cf129a0c00b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3585,11 +3585,11 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: @@ -3997,7 +3997,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; -- cgit From ae488c74422fb1dcd807c0201804b3b5e8a322a3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:54 +0000 Subject: tcp: annotate data-races around rskq_defer_accept do_tcp_getsockopt() reads rskq_defer_accept while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-9-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2cf129a0c00b..5beec71a5c41 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3594,9 +3594,9 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -4002,8 +4002,9 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; -- cgit From 1aeb87bc1440c5447a7fa2d6e3c2cca52cbd206b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:55 +0000 Subject: tcp: annotate data-races around tp->notsent_lowat tp->notsent_lowat can be read locklessly from do_tcp_getsockopt() and tcp_poll(). Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-10-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5beec71a5c41..2b2241e9b492 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3664,7 +3664,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -4164,7 +4164,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; -- cgit From 26023e91e12c68669db416b97234328a03d8e499 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:56 +0000 Subject: tcp: annotate data-races around icsk->icsk_user_timeout This field can be read locklessly from do_tcp_getsockopt() Fixes: dca43c75e7e5 ("tcp: Add TCP_USER_TIMEOUT socket option.") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-11-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2b2241e9b492..3e137e9a18f5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3300,7 +3300,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3620,7 +3620,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -4141,7 +4141,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: -- cgit From 70f360dd7042cb843635ece9d28335a4addff9eb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:57 +0000 Subject: tcp: annotate data-races around fastopenq.max_qlen This field can be read locklessly. Fixes: 1536e2857bd3 ("tcp: Add a TCP_FASTOPEN socket option to get a max backlog on its listner") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-12-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3e137e9a18f5..8ed52e1e3c99 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4145,7 +4145,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: -- cgit