From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:39 -0700
Subject: tcp: annotate tp->rcv_nxt lockless reads
Patch-mainline: v5.4-rc4
Git-commit: dba7d9b8c739df27ff3a234c81d6c6b23e3986fa
References: bsc#1154353
There are few places where we fetch tp->rcv_nxt 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->rcv_nxt)
syzbot reported :
BUG: KCSAN: data-race in tcp_poll / tcp_queue_rcv
write to 0xffff888120425770 of 4 bytes by interrupt on cpu 0:
tcp_rcv_nxt_update net/ipv4/tcp_input.c:3365 [inline]
tcp_queue_rcv+0x180/0x380 net/ipv4/tcp_input.c:4638
tcp_rcv_established+0xbf1/0xf50 net/ipv4/tcp_input.c:5616
tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1542
tcp_v4_rcv+0x1a03/0x1bf0 net/ipv4/tcp_ipv4.c:1923
ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204
ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231
NF_HOOK include/linux/netfilter.h:305 [inline]
NF_HOOK include/linux/netfilter.h:299 [inline]
ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252
dst_input include/net/dst.h:442 [inline]
ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413
NF_HOOK include/linux/netfilter.h:305 [inline]
NF_HOOK include/linux/netfilter.h:299 [inline]
ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523
__netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004
__netif_receive_skb+0x37/0xf0 net/core/dev.c:5118
netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208
napi_skb_finish net/core/dev.c:5671 [inline]
napi_gro_receive+0x28f/0x330 net/core/dev.c:5704
receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061
read to 0xffff888120425770 of 4 bytes by task 7254 on cpu 1:
tcp_stream_is_readable net/ipv4/tcp.c:480 [inline]
tcp_poll+0x204/0x6b0 net/ipv4/tcp.c:554
sock_poll+0xed/0x250 net/socket.c:1256
vfs_poll include/linux/poll.h:90 [inline]
ep_item_poll.isra.0+0x90/0x190 fs/eventpoll.c:892
ep_send_events_proc+0x113/0x5c0 fs/eventpoll.c:1749
ep_scan_ready_list.constprop.0+0x189/0x500 fs/eventpoll.c:704
ep_send_events fs/eventpoll.c:1793 [inline]
ep_poll+0xe3/0x900 fs/eventpoll.c:1930
do_epoll_wait+0x162/0x180 fs/eventpoll.c:2294
__do_sys_epoll_pwait fs/eventpoll.c:2325 [inline]
__se_sys_epoll_pwait fs/eventpoll.c:2311 [inline]
__x64_sys_epoll_pwait+0xcd/0x170 fs/eventpoll.c:2311
do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296
entry_SYSCALL_64_after_hwframe+0x44/0xa9
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 7254 Comm: syz-fuzzer Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
net/ipv4/tcp.c | 4 ++--
net/ipv4/tcp_diag.c | 2 +-
net/ipv4/tcp_input.c | 6 +++---
net/ipv4/tcp_ipv4.c | 3 ++-
net/ipv4/tcp_minisocks.c | 7 +++++--
net/ipv6/tcp_ipv6.c | 3 ++-
6 files changed, 15 insertions(+), 10 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 (tp->rcv_nxt - tp->copied_seq >= target) ||
+ return (READ_ONCE(tp->rcv_nxt) - tp->copied_seq >= target) ||
(sk->sk_prot->stream_memory_read ?
sk->sk_prot->stream_memory_read(sk) : false);
}
@@ -2934,7 +2934,7 @@ static int do_tcp_setsockopt(struct sock
else if (tp->repair_queue == TCP_SEND_QUEUE)
tp->write_seq = val;
else if (tp->repair_queue == TCP_RECV_QUEUE)
- tp->rcv_nxt = val;
+ WRITE_ONCE(tp->rcv_nxt, val);
else
err = -EINVAL;
break;
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,7 +26,7 @@ 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, tp->rcv_nxt - tp->copied_seq, 0);
+ r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - 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
@@ -3362,7 +3362,7 @@ static void tcp_rcv_nxt_update(struct tc
sock_owned_by_me((struct sock *)tp);
tp->bytes_received += delta;
- tp->rcv_nxt = seq;
+ WRITE_ONCE(tp->rcv_nxt, seq);
}
/* Update our send window.
@@ -5932,7 +5932,7 @@ static int tcp_rcv_synsent_state_process
/* Ok.. it's good. Set up sequence numbers and
* move to established.
*/
- tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6035,7 +6035,7 @@ discard:
tp->tcp_header_len = sizeof(struct tcphdr);
}
- tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
tp->copied_seq = tp->rcv_nxt;
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2451,7 +2451,8 @@ static void get_tcp4_sock(struct sock *s
/* Because we don't lock the socket,
* we might find a transient negative value.
*/
- rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+ 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
@@ -461,6 +461,7 @@ struct sock *tcp_create_openreq_child(co
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk;
struct tcp_sock *oldtp, *newtp;
+ u32 seq;
if (!newsk)
return NULL;
@@ -474,8 +475,10 @@ struct sock *tcp_create_openreq_child(co
/* Now setup tcp_sock */
newtp->pred_flags = 0;
- newtp->rcv_wup = newtp->copied_seq =
- newtp->rcv_nxt = treq->rcv_isn + 1;
+ seq = treq->rcv_isn + 1;
+ newtp->rcv_wup = seq;
+ newtp->copied_seq = seq;
+ WRITE_ONCE(newtp->rcv_nxt, seq);
newtp->segs_in = 1;
newtp->snd_sml = newtp->snd_una =
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1889,7 +1889,8 @@ static void get_tcp6_sock(struct seq_fil
/* Because we don't lock the socket,
* we might find a transient negative value.
*/
- rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+ tp->copied_seq, 0);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "