From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:40 -0700
Subject: tcp: annotate tp->copied_seq lockless reads
Patch-mainline: v5.4-rc4
Git-commit: 7db48e983930285b765743ebd665aecf9850582b
References: bsc#1154353
There are few places where we fetch tp->copied_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.
Note that tcp_inq_hint() was already using READ_ONCE(tp->copied_seq)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
net/ipv4/tcp.c | 20 ++++++++++----------
net/ipv4/tcp_diag.c | 3 ++-
net/ipv4/tcp_input.c | 6 +++---
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv4/tcp_output.c | 2 +-
net/ipv6/tcp_ipv6.c | 2 +-
7 files changed, 19 insertions(+), 18 deletions(-)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock
static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
int target, struct sock *sk)
{
- return (READ_ONCE(tp->rcv_nxt) - tp->copied_seq >= target) ||
+ return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
(sk->sk_prot->stream_memory_read ?
sk->sk_prot->stream_memory_read(sk) : false);
}
@@ -546,7 +546,7 @@ __poll_t tcp_poll(struct file *file, str
(state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
int target = sock_rcvlowat(sk, 0, INT_MAX);
- if (tp->urg_seq == tp->copied_seq &&
+ if (tp->urg_seq == READ_ONCE(tp->copied_seq) &&
!sock_flag(sk, SOCK_URGINLINE) &&
tp->urg_data)
target++;
@@ -607,7 +607,7 @@ int tcp_ioctl(struct sock *sk, int cmd,
unlock_sock_fast(sk, slow);
break;
case SIOCATMARK:
- answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
+ answ = tp->urg_data && tp->urg_seq == READ_ONCE(tp->copied_seq);
break;
case SIOCOUTQ:
if (sk->sk_state == TCP_LISTEN)
@@ -1667,9 +1667,9 @@ int tcp_read_sock(struct sock *sk, read_
sk_eat_skb(sk, skb);
if (!desc->count)
break;
- tp->copied_seq = seq;
+ WRITE_ONCE(tp->copied_seq, seq);
}
- tp->copied_seq = seq;
+ WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
@@ -1818,7 +1818,7 @@ static int tcp_zerocopy_receive(struct s
out:
up_read(¤t->mm->mmap_sem);
if (length) {
- tp->copied_seq = seq;
+ WRITE_ONCE(tp->copied_seq, seq);
tcp_rcv_space_adjust(sk);
/* Clean up data we have read: This will do ACK frames. */
@@ -2116,7 +2116,7 @@ found_ok_skb:
if (urg_offset < used) {
if (!urg_offset) {
if (!sock_flag(sk, SOCK_URGINLINE)) {
- ++*seq;
+ WRITE_ONCE(*seq, *seq + 1);
urg_hole++;
offset++;
used--;
@@ -2138,7 +2138,7 @@ found_ok_skb:
}
}
- *seq += used;
+ WRITE_ONCE(*seq, *seq + used);
copied += used;
len -= used;
@@ -2165,7 +2165,7 @@ skip_copy:
found_fin_ok:
/* Process the FIN. */
- ++*seq;
+ WRITE_ONCE(*seq, *seq + 1);
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb);
break;
@@ -2587,7 +2587,7 @@ int tcp_disconnect(struct sock *sk, int
__kfree_skb(sk->sk_rx_skb_cache);
sk->sk_rx_skb_cache = NULL;
}
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
tp->urg_data = 0;
tcp_write_queue_purge(sk);
tcp_fastopen_active_disable_ofo_check(sk);
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,7 +26,8 @@ static void tcp_diag_get_info(struct soc
} else if (sk->sk_type == SOCK_STREAM) {
const struct tcp_sock *tp = tcp_sk(sk);
- r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - tp->copied_seq, 0);
+ 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;
}
if (info)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5961,7 +5961,7 @@ static int tcp_rcv_synsent_state_process
/* Remember, tcp_poll() does not lock socket!
* Change state from SYN-SENT only after copied_seq
* is initialized. */
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
smc_check_reset_syn(tp);
@@ -6036,7 +6036,7 @@ discard:
}
WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6216,7 +6216,7 @@ int tcp_rcv_state_process(struct sock *s
tcp_try_undo_spurious_syn(sk);
tp->retrans_stamp = 0;
tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
}
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2452,7 +2452,7 @@ static void get_tcp4_sock(struct sock *s
* we might find a transient negative value.
*/
rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
- tp->copied_seq, 0);
+ READ_ONCE(tp->copied_seq), 0);
seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -477,7 +477,7 @@ struct sock *tcp_create_openreq_child(co
seq = treq->rcv_isn + 1;
newtp->rcv_wup = seq;
- newtp->copied_seq = seq;
+ WRITE_ONCE(newtp->copied_seq, seq);
WRITE_ONCE(newtp->rcv_nxt, seq);
newtp->segs_in = 1;
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3422,7 +3422,7 @@ static void tcp_connect_init(struct sock
else
tp->rcv_tstamp = tcp_jiffies32;
tp->rcv_wup = tp->rcv_nxt;
- tp->copied_seq = tp->rcv_nxt;
+ WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
inet_csk(sk)->icsk_retransmits = 0;
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1890,7 +1890,7 @@ static void get_tcp6_sock(struct seq_fil
* we might find a transient negative value.
*/
rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
- tp->copied_seq, 0);
+ READ_ONCE(tp->copied_seq), 0);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "