netdev - [PATCH v1 net] net: Fix sk->sk_stamp race in sock_recv

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
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230506022325.99106-1-kuniyu@amazon.com>
Date: Fri, 5 May 2023 19:23:25 -0700
From: Kuniyuki Iwashima <kuniyu@...zon.com>
To: "David S. Miller" <davem@...emloft.net>, Eric Dumazet
	<edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni
	<pabeni@...hat.com>
CC: Kuniyuki Iwashima <kuniyu@...zon.com>, Kuniyuki Iwashima
	<kuni1840@...il.com>, <netdev@...r.kernel.org>, syzbot
	<syzkaller@...glegroups.com>
Subject: [PATCH v1 net] net: Fix sk->sk_stamp race in sock_recv_cmsgs().

KCSAN found a data race in sock_recv_cmsgs() [0] where the read access
to sk->sk_stamp needs READ_ONCE().

Also, there is another race below.  If the torn load of the high 32-bits
precedes WRITE_ONCE(sk, skb->tstamp) and later the written lower 32-bits
happens to match with SK_DEFAULT_STAMP, the final result of sk->sk_stamp
could be 0.

  sock_recv_cmsgs()  ioctl(SIOCGSTAMP)      sock_recv_cmsgs()
  |                  |                      |
  |- if (sock_flag(sk, SOCK_TIMESTAMP))     |
  |                  |                      |
  |                  `- sock_set_flag(sk, SOCK_TIMESTAMP)
  |                                         |
  |                                          `- if (sock_flag(sk, SOCK_TIMESTAMP))
  `- if (sk->sk_stamp == SK_DEFAULT_STAMP)      `- sock_write_timestamp(sk, skb->tstamp)
      `- sock_write_timestamp(sk, 0)

Even with READ_ONCE(), we could get the same result if READ_ONCE() precedes
WRITE_ONCE() because the SK_DEFAULT_STAMP check and WRITE_ONCE(sk_stamp, 0)
are not atomic.

Let's avoid the race by cmpxchg() on 64-bits architecture or seqlock on
32-bits machines.

[0]:
BUG: KCSAN: data-race in packet_recvmsg / packet_recvmsg

write (marked) to 0xffff88803c81f258 of 8 bytes by task 19171 on cpu 0:
 sock_write_timestamp include/net/sock.h:2670 [inline]
 sock_recv_cmsgs include/net/sock.h:2722 [inline]
 packet_recvmsg+0xb97/0xd00 net/packet/af_packet.c:3489
 sock_recvmsg_nosec net/socket.c:1019 [inline]
 sock_recvmsg+0x11a/0x130 net/socket.c:1040
 sock_read_iter+0x176/0x220 net/socket.c:1118
 call_read_iter include/linux/fs.h:1845 [inline]
 new_sync_read fs/read_write.c:389 [inline]
 vfs_read+0x5e0/0x630 fs/read_write.c:470
 ksys_read+0x163/0x1a0 fs/read_write.c:613
 __do_sys_read fs/read_write.c:623 [inline]
 __se_sys_read fs/read_write.c:621 [inline]
 __x64_sys_read+0x41/0x50 fs/read_write.c:621
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x72/0xdc

read to 0xffff88803c81f258 of 8 bytes by task 19183 on cpu 1:
 sock_recv_cmsgs include/net/sock.h:2721 [inline]
 packet_recvmsg+0xb64/0xd00 net/packet/af_packet.c:3489
 sock_recvmsg_nosec net/socket.c:1019 [inline]
 sock_recvmsg+0x11a/0x130 net/socket.c:1040
 sock_read_iter+0x176/0x220 net/socket.c:1118
 call_read_iter include/linux/fs.h:1845 [inline]
 new_sync_read fs/read_write.c:389 [inline]
 vfs_read+0x5e0/0x630 fs/read_write.c:470
 ksys_read+0x163/0x1a0 fs/read_write.c:613
 __do_sys_read fs/read_write.c:623 [inline]
 __se_sys_read fs/read_write.c:621 [inline]
 __x64_sys_read+0x41/0x50 fs/read_write.c:621
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x72/0xdc

value changed: 0xffffffffc4653600 -> 0x0000000000000000

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 19183 Comm: syz-executor.5 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Reported-by: syzbot <syzkaller@...glegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@...zon.com>
---
 include/net/sock.h | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 8b7ed7167243..c2a8b799283e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2671,6 +2671,20 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
 #endif
 }
 
+#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
+
+static inline void sock_zero_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+	write_seqlock(&sk->sk_stamp_seq);
+	if (sk->sk_stamp == SK_DEFAULT_STAMP)
+		sk->sk_stamp = 0;
+	write_sequnlock(&sk->sk_stamp_seq);
+#else
+	cmpxchg(&sk->sk_stamp, SK_DEFAULT_STAMP, 0);
+#endif
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2704,7 +2718,6 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 		       struct sk_buff *skb);
 
-#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
 static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 				   struct sk_buff *skb)
 {
@@ -2718,8 +2731,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 		__sock_recv_cmsgs(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sock_write_timestamp(sk, skb->tstamp);
-	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
-		sock_write_timestamp(sk, 0);
+	else
+		sock_zero_timestamp(sk);
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
-- 
2.30.2