Commit 8265792b authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski

net: silence KCSAN warnings around sk_add_backlog() calls

sk_add_backlog() callers usually read sk->sk_rcvbuf without
owning the socket lock. This means sk_rcvbuf value can
be changed by other cpus, and KCSAN complains.

Add READ_ONCE() annotations to document the lockless nature
of these reads.

Note that writes over sk_rcvbuf should also use WRITE_ONCE(),
but this will be done in separate patches to ease stable
backports (if we decide this is relevant for stable trees).

BUG: KCSAN: data-race in tcp_add_backlog / tcp_recvmsg

write to 0xffff88812ab369f8 of 8 bytes by interrupt on cpu 1:
 __sk_add_backlog include/net/sock.h:902 [inline]
 sk_add_backlog include/net/sock.h:933 [inline]
 tcp_add_backlog+0x45a/0xcc0 net/ipv4/tcp_ipv4.c:1737
 tcp_v4_rcv+0x1aba/0x1bf0 net/ipv4/tcp_ipv4.c:1925
 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
 virtnet_receive drivers/net/virtio_net.c:1323 [inline]
 virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428
 napi_poll net/core/dev.c:6352 [inline]
 net_rx_action+0x3ae/0xa50 net/core/dev.c:6418

read to 0xffff88812ab369f8 of 8 bytes by task 7271 on cpu 0:
 tcp_recvmsg+0x470/0x1a30 net/ipv4/tcp.c:2047
 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838
 sock_recvmsg_nosec net/socket.c:871 [inline]
 sock_recvmsg net/socket.c:889 [inline]
 sock_recvmsg+0x92/0xb0 net/socket.c:885
 sock_read_iter+0x15f/0x1e0 net/socket.c:967
 call_read_iter include/linux/fs.h:1864 [inline]
 new_sync_read+0x389/0x4f0 fs/read_write.c:414
 __vfs_read+0xb1/0xc0 fs/read_write.c:427
 vfs_read fs/read_write.c:461 [inline]
 vfs_read+0x143/0x2c0 fs/read_write.c:446
 ksys_read+0xd5/0x1b0 fs/read_write.c:587
 __do_sys_read fs/read_write.c:597 [inline]
 __se_sys_read fs/read_write.c:595 [inline]
 __x64_sys_read+0x4c/0x60 fs/read_write.c:595
 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: 0 PID: 7271 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: default avatarEric Dumazet <edumazet@google.com>
Reported-by: default avatarsyzbot <syzkaller@googlegroups.com>
Signed-off-by: default avatarJakub Kicinski <jakub.kicinski@netronome.com>
parent 1f142c17
...@@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, ...@@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
rc = sk_backlog_rcv(sk, skb); rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
} else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
bh_unlock_sock(sk); bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops); atomic_inc(&sk->sk_drops);
goto discard_and_relse; goto discard_and_relse;
......
...@@ -1644,7 +1644,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) ...@@ -1644,7 +1644,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
{ {
u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
struct skb_shared_info *shinfo; struct skb_shared_info *shinfo;
const struct tcphdr *th; const struct tcphdr *th;
struct tcphdr *thtail; struct tcphdr *thtail;
......
...@@ -813,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) ...@@ -813,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
else { else {
dprintk("%s: adding to backlog...\n", __func__); dprintk("%s: adding to backlog...\n", __func__);
llc_set_backlog_type(skb, LLC_PACKET); llc_set_backlog_type(skb, LLC_PACKET);
if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
goto drop_unlock; goto drop_unlock;
} }
out: out:
......
...@@ -322,7 +322,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) ...@@ -322,7 +322,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
bh_lock_sock(sk); bh_lock_sock(sk);
if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
sctp_chunk_free(chunk); sctp_chunk_free(chunk);
else else
backloged = 1; backloged = 1;
...@@ -337,7 +337,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) ...@@ -337,7 +337,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
return 0; return 0;
} else { } else {
if (!sctp_newsk_ready(sk)) { if (!sctp_newsk_ready(sk)) {
if (!sk_add_backlog(sk, skb, sk->sk_rcvbuf)) if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
return 0; return 0;
sctp_chunk_free(chunk); sctp_chunk_free(chunk);
} else { } else {
...@@ -364,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) ...@@ -364,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
struct sctp_ep_common *rcvr = chunk->rcvr; struct sctp_ep_common *rcvr = chunk->rcvr;
int ret; int ret;
ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf); ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
if (!ret) { if (!ret) {
/* Hold the assoc/ep while hanging on the backlog queue. /* Hold the assoc/ep while hanging on the backlog queue.
* This way, we know structures we need will not disappear * This way, we know structures we need will not disappear
......
...@@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) ...@@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
struct tipc_msg *hdr = buf_msg(skb); struct tipc_msg *hdr = buf_msg(skb);
if (unlikely(msg_in_group(hdr))) if (unlikely(msg_in_group(hdr)))
return sk->sk_rcvbuf; return READ_ONCE(sk->sk_rcvbuf);
if (unlikely(!msg_connected(hdr))) if (unlikely(!msg_connected(hdr)))
return sk->sk_rcvbuf << msg_importance(hdr); return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr);
if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL)) if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
return sk->sk_rcvbuf; return READ_ONCE(sk->sk_rcvbuf);
return FLOWCTL_MSG_LIM; return FLOWCTL_MSG_LIM;
} }
......
...@@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) ...@@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb)
if (!sock_owned_by_user(sk)) { if (!sock_owned_by_user(sk)) {
queued = x25_process_rx_frame(sk, skb); queued = x25_process_rx_frame(sk, skb);
} else { } else {
queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf); queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
} }
bh_unlock_sock(sk); bh_unlock_sock(sk);
sock_put(sk); sock_put(sk);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment