| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20191011031746.16220-3-edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:39 -0700
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>,
Jakub Kicinski <jakub.kicinski@...ronome.com>,
syzbot <syzkaller@...glegroups.com>
Subject: [PATCH net 2/9] tcp: annotate tp->rcv_nxt lockless reads
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@...gle.com>
Reported-by: syzbot <syzkaller@...glegroups.com>
---
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(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c59d0bd29c5c6fcbe38edb12b37c47ba4ed68899..883ee863db434b90096cdb4a597ae43c95711ad7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
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);
}
@@ -2935,7 +2935,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
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;
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 81a8221d650a94be53d17354c60ddd0c655eaccf..cd219161f1061cf2625a3ee476410ab95fd2ccec 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,7 +26,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
} 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)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5f9b102c3b55c5a40bceb945d0f5d288f682824c..5b7c8768ed5f63ec7e8b3bdd335ce437ce716799 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3362,7 +3362,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
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(struct sock *sk, struct sk_buff *skb,
/* 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 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
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;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ffa366099eb29145c37341ca00976844cd1185dc..5089dd6bee0ffaef22a5f1cd9a4bbcf4d68d4f3d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2455,7 +2455,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
/* 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",
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 5401dbd39c8fd34d147e0202a410dfc7cefafc26..adc6ce486a383caad502db05f51cdc7205fe009c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -462,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk;
struct tcp_sock *oldtp, *newtp;
+ u32 seq;
if (!newsk)
return NULL;
@@ -475,8 +476,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
/* 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 =
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 45a95e032bdfe8ffb05309bed8a967ee08690293..89ea0a7018b567aacefba9e8570607629d1185a8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1895,7 +1895,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
/* 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 "
--
2.23.0.700.g56cf767bdb-goog
Powered by blists - more mailing lists