blob: 7055dd9eeb383752d8ea5d61ada5dcc286e0e394 [file] [log] [blame]
From 32e2858d1a12f223facf58371a8e4d269d0c5896 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:41 -0700
Subject: [PATCH] tcp: annotate tp->write_seq lockless reads
commit 0f31746452e6793ad6271337438af8f4defb8940 upstream.
There are few places where we fetch tp->write_seq while
this field can change from IRQ or other cpu.
We need to add READ_ONCE() annotations, and also make
sure write sides use corresponding WRITE_ONCE() to avoid
store-tearing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9eea14060456..2c57e0b79e1a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1885,7 +1885,7 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
{
const struct tcp_sock *tp = tcp_sk(sk);
- u32 notsent_bytes = tp->write_seq - tp->snd_nxt;
+ u32 notsent_bytes = READ_ONCE(tp->write_seq) - tp->snd_nxt;
return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d55ff2f83dc3..5822b426c4d7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -616,7 +616,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
answ = 0;
else
- answ = tp->write_seq - tp->snd_una;
+ answ = READ_ONCE(tp->write_seq) - tp->snd_una;
break;
case SIOCOUTQNSD:
if (sk->sk_state == TCP_LISTEN)
@@ -625,7 +625,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
answ = 0;
else
- answ = tp->write_seq - tp->snd_nxt;
+ answ = READ_ONCE(tp->write_seq) - tp->snd_nxt;
break;
default:
return -ENOIOCTLCMD;
@@ -1035,7 +1035,7 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
sk->sk_wmem_queued += copy;
sk_mem_charge(sk, copy);
skb->ip_summed = CHECKSUM_PARTIAL;
- tp->write_seq += copy;
+ WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
TCP_SKB_CB(skb)->end_seq += copy;
tcp_skb_pcount_set(skb, 0);
@@ -1360,7 +1360,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
if (!copied)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
- tp->write_seq += copy;
+ WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
TCP_SKB_CB(skb)->end_seq += copy;
tcp_skb_pcount_set(skb, 0);
@@ -2558,6 +2558,7 @@ int tcp_disconnect(struct sock *sk, int flags)
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int old_state = sk->sk_state;
+ u32 seq;
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
@@ -2600,9 +2601,12 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->srtt_us = 0;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
tp->rcv_rtt_last_tsecr = 0;
- tp->write_seq += tp->max_window + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
+
+ seq = tp->write_seq + tp->max_window + 2;
+ if (!seq)
+ seq = 1;
+ WRITE_ONCE(tp->write_seq, seq);
+
icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
@@ -2911,7 +2915,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
if (sk->sk_state != TCP_CLOSE)
err = -EPERM;
else if (tp->repair_queue == TCP_SEND_QUEUE)
- tp->write_seq = val;
+ WRITE_ONCE(tp->write_seq, val);
else if (tp->repair_queue == TCP_RECV_QUEUE)
WRITE_ONCE(tp->rcv_nxt, val);
else
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 035c549f623c..89b8de350b10 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -28,7 +28,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) -
READ_ONCE(tp->copied_seq), 0);
- r->idiag_wqueue = tp->write_seq - tp->snd_una;
+ r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una;
}
if (info)
tcp_get_info(sk, info);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b900ce920f51..16591cccbeff 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
* without appearing to create any others.
*/
if (likely(!tp->repair)) {
- tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
- if (tp->write_seq == 0)
- tp->write_seq = 1;
+ u32 seq = tcptw->tw_snd_nxt + 65535 + 2;
+
+ if (!seq)
+ seq = 1;
+ WRITE_ONCE(tp->write_seq, seq);
tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
}
@@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
if (likely(!tp->repair))
- tp->write_seq = 0;
+ WRITE_ONCE(tp->write_seq, 0);
}
inet->inet_dport = usin->sin_port;
@@ -291,10 +293,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (likely(!tp->repair)) {
if (!tp->write_seq)
- tp->write_seq = secure_tcp_seq(inet->inet_saddr,
- inet->inet_daddr,
- inet->inet_sport,
- usin->sin_port);
+ WRITE_ONCE(tp->write_seq,
+ secure_tcp_seq(inet->inet_saddr,
+ inet->inet_daddr,
+ inet->inet_sport,
+ usin->sin_port));
tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
inet->inet_saddr,
inet->inet_daddr);
@@ -2437,7 +2440,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
i, src, srcp, dest, destp, state,
- tp->write_seq - tp->snd_una,
+ READ_ONCE(tp->write_seq) - tp->snd_una,
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2775a5be74bc..9a91d4dfe493 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -496,7 +496,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->total_retrans = req->num_retrans;
tcp_init_xmit_timers(newsk);
- newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
+ WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
if (sock_flag(newsk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(newsk,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 87ce98a1022b..f70920f5bb7f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1187,7 +1187,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
/* Advance write_seq and place onto the write_queue. */
- tp->write_seq = TCP_SKB_CB(skb)->end_seq;
+ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
__skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
sk->sk_wmem_queued += skb->truesize;
@@ -3434,7 +3434,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
__skb_header_release(skb);
sk->sk_wmem_queued += skb->truesize;
sk_mem_charge(sk, skb->truesize);
- tp->write_seq = tcb->end_seq;
+ WRITE_ONCE(tp->write_seq, tcb->end_seq);
tp->packets_out += tcp_skb_pcount(skb);
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 41d616a8a967..70b36dc26f62 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
!ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
- tp->write_seq = 0;
+ WRITE_ONCE(tp->write_seq, 0);
}
sk->sk_v6_daddr = usin->sin6_addr;
@@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (likely(!tp->repair)) {
if (!tp->write_seq)
- tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
- sk->sk_v6_daddr.s6_addr32,
- inet->inet_sport,
- inet->inet_dport);
+ WRITE_ONCE(tp->write_seq,
+ secure_tcpv6_seq(np->saddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32,
+ inet->inet_sport,
+ inet->inet_dport));
tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk),
np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32);
@@ -1864,7 +1865,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
state,
- tp->write_seq - tp->snd_una,
+ READ_ONCE(tp->write_seq) - tp->snd_una,
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
--
2.7.4