This series fixes some memory leaks and data races caused in the
same scenario where one thread converts an IPv6 socket into IPv4
with IPV6_ADDRFORM and another accesses the socket concurrently.
Note patch 1 and 5 conflict with these commits in net-next, respectively.
* 24426654ed3a ("bpf: net: Avoid sk_setsockopt() taking sk lock when called from bpf")
* 34704ef024ae ("bpf: net: Change do_tcp_getsockopt() to take the sockptr_t argument")
Changes:
v4:
* Patch 3:
* Change UDPv6 Lite's sk->sk_prot->init() and sk->destruct() as well.
* Move udplite_sk_init() from udplite.h to udplite.c.
v3 (Resend): https://lore.kernel.org/netdev/[email protected]/
* CC blamed commits' EHOSTUNREACH authors to make patchwork happy
v3: https://lore.kernel.org/netdev/[email protected]/
* Patch 2:
* Add comment for np->rxopt.all = 0
* Add inet6_cleanup_sock()
* Patch 3:
* Call inet6_cleanup_sock() instead of inet6_destroy_sock()
v2: https://lore.kernel.org/netdev/[email protected]/
* Patch 3:
* Move inet6_destroy_sock() from sk_prot->destroy()
to sk->sk_destruct() and fix CONFIG_IPV6=m build failure
* Patch 5:
* Add WRITE_ONCE()s in tcp_v6_connect()
* Add Reported-by tags and KCSAN log in changelog
v1: https://lore.kernel.org/netdev/[email protected]/
Kuniyuki Iwashima (5):
tcp/udp: Fix memory leak in ipv6_renew_options().
udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM).
tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct().
ipv6: Fix data races around sk->sk_prot.
tcp: Fix data races around icsk->icsk_af_ops.
include/net/ipv6.h | 2 ++
include/net/udp.h | 2 +-
include/net/udplite.h | 8 --------
net/core/sock.c | 6 ++++--
net/ipv4/af_inet.c | 23 ++++++++++++++++-------
net/ipv4/tcp.c | 10 ++++++----
net/ipv4/udp.c | 9 ++++++---
net/ipv4/udplite.c | 8 ++++++++
net/ipv6/af_inet6.c | 15 ++++++++++++++-
net/ipv6/ipv6_sockglue.c | 34 +++++++++++++++++++---------------
net/ipv6/tcp_ipv6.c | 6 ++++--
net/ipv6/udp.c | 15 ++++++++++++++-
net/ipv6/udp_impl.h | 1 +
net/ipv6/udplite.c | 9 ++++++++-
14 files changed, 103 insertions(+), 45 deletions(-)
--
2.30.2
syzbot reported a memory leak [0] related to IPV6_ADDRFORM.
The scenario is that while one thread is converting an IPv6 socket into
IPv4 with IPV6_ADDRFORM, another thread calls do_ipv6_setsockopt() and
allocates memory to inet6_sk(sk)->XXX after conversion.
Then, the converted sk with (tcp|udp)_prot never frees the IPv6 resources,
which inet6_destroy_sock() should have cleaned up.
setsockopt(IPV6_ADDRFORM) setsockopt(IPV6_DSTOPTS)
+-----------------------+ +----------------------+
- do_ipv6_setsockopt(sk, ...)
- lock_sock(sk) - do_ipv6_setsockopt(sk, ...)
- WRITE_ONCE(sk->sk_prot, &tcp_prot) ^._ called via tcpv6_prot
- xchg(&np->opt, NULL) before WRITE_ONCE()
- txopt_put(opt)
- release_sock(sk)
- lock_sock(sk)
- ipv6_set_opt_hdr(sk, ...)
- ipv6_update_options(sk, opt)
- xchg(&inet6_sk(sk)->opt, opt)
^._ opt is never freed.
- release_sock(sk)
Since IPV6_DSTOPTS allocates options under lock_sock(), we can avoid this
memory leak by testing whether sk_family is changed by IPV6_ADDRFORM after
acquiring the lock.
This issue exists from the initial commit between IPV6_ADDRFORM and
IPV6_PKTOPTIONS.
[0]:
BUG: memory leak
unreferenced object 0xffff888009ab9f80 (size 96):
comm "syz-executor583", pid 328, jiffies 4294916198 (age 13.034s)
hex dump (first 32 bytes):
01 00 00 00 48 00 00 00 08 00 00 00 00 00 00 00 ....H...........
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<000000002ee98ae1>] kmalloc include/linux/slab.h:605 [inline]
[<000000002ee98ae1>] sock_kmalloc+0xb3/0x100 net/core/sock.c:2566
[<0000000065d7b698>] ipv6_renew_options+0x21e/0x10b0 net/ipv6/exthdrs.c:1318
[<00000000a8c756d7>] ipv6_set_opt_hdr net/ipv6/ipv6_sockglue.c:354 [inline]
[<00000000a8c756d7>] do_ipv6_setsockopt.constprop.0+0x28b7/0x4350 net/ipv6/ipv6_sockglue.c:668
[<000000002854d204>] ipv6_setsockopt+0xdf/0x190 net/ipv6/ipv6_sockglue.c:1021
[<00000000e69fdcf8>] tcp_setsockopt+0x13b/0x2620 net/ipv4/tcp.c:3789
[<0000000090da4b9b>] __sys_setsockopt+0x239/0x620 net/socket.c:2252
[<00000000b10d192f>] __do_sys_setsockopt net/socket.c:2263 [inline]
[<00000000b10d192f>] __se_sys_setsockopt net/socket.c:2260 [inline]
[<00000000b10d192f>] __x64_sys_setsockopt+0xbe/0x160 net/socket.c:2260
[<000000000a80d7aa>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
[<000000000a80d7aa>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80
[<000000004562b5c6>] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot <[email protected]>
Signed-off-by: Kuniyuki Iwashima <[email protected]>
---
net/ipv6/ipv6_sockglue.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index e0dcc7a193df..b61066ac8648 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -419,6 +419,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
rtnl_lock();
lock_sock(sk);
+ /* Another thread has converted the socket into IPv4 with
+ * IPV6_ADDRFORM concurrently.
+ */
+ if (unlikely(sk->sk_family != AF_INET6))
+ goto unlock;
+
switch (optname) {
case IPV6_ADDRFORM:
@@ -994,6 +1000,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
}
+unlock:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
--
2.30.2
setsockopt(IPV6_ADDRFORM) and tcp_v6_connect() change icsk->icsk_af_ops
under lock_sock(), but tcp_(get|set)sockopt() read it locklessly. To
avoid load/store tearing, we need to add READ_ONCE() and WRITE_ONCE()
for the reads and writes.
Thanks to Eric Dumazet for providing the syzbot report:
BUG: KCSAN: data-race in tcp_setsockopt / tcp_v6_connect
write to 0xffff88813c624518 of 8 bytes by task 23936 on cpu 0:
tcp_v6_connect+0x5b3/0xce0 net/ipv6/tcp_ipv6.c:240
__inet_stream_connect+0x159/0x6d0 net/ipv4/af_inet.c:660
inet_stream_connect+0x44/0x70 net/ipv4/af_inet.c:724
__sys_connect_file net/socket.c:1976 [inline]
__sys_connect+0x197/0x1b0 net/socket.c:1993
__do_sys_connect net/socket.c:2003 [inline]
__se_sys_connect net/socket.c:2000 [inline]
__x64_sys_connect+0x3d/0x50 net/socket.c:2000
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
read to 0xffff88813c624518 of 8 bytes by task 23937 on cpu 1:
tcp_setsockopt+0x147/0x1c80 net/ipv4/tcp.c:3789
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3585
__sys_setsockopt+0x212/0x2b0 net/socket.c:2252
__do_sys_setsockopt net/socket.c:2263 [inline]
__se_sys_setsockopt net/socket.c:2260 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2260
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0xffffffff8539af68 -> 0xffffffff8539aff8
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 23937 Comm: syz-executor.5 Not tainted
6.0.0-rc4-syzkaller-00331-g4ed9c1e971b1-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 08/26/2022
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot <[email protected]>
Reported-by: Eric Dumazet <[email protected]>
Signed-off-by: Kuniyuki Iwashima <[email protected]>
---
net/ipv4/tcp.c | 10 ++++++----
net/ipv6/ipv6_sockglue.c | 3 ++-
net/ipv6/tcp_ipv6.c | 6 ++++--
3 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 997a80ce1e13..08db82c05a4a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3797,8 +3797,9 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
const struct inet_connection_sock *icsk = inet_csk(sk);
if (level != SOL_TCP)
- return icsk->icsk_af_ops->setsockopt(sk, level, optname,
- optval, optlen);
+ /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */
+ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname,
+ optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(tcp_setsockopt);
@@ -4396,8 +4397,9 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
struct inet_connection_sock *icsk = inet_csk(sk);
if (level != SOL_TCP)
- return icsk->icsk_af_ops->getsockopt(sk, level, optname,
- optval, optlen);
+ /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */
+ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname,
+ optval, optlen);
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(tcp_getsockopt);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 2fb9ee413c53..19ac75c2cd54 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -479,7 +479,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
/* Paired with READ_ONCE(sk->sk_prot) in inet6_stream_ops */
WRITE_ONCE(sk->sk_prot, &tcp_prot);
- icsk->icsk_af_ops = &ipv4_specific;
+ /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
+ WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific);
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e54eee80ce5f..8680aa83f0b9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -237,7 +237,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
- icsk->icsk_af_ops = &ipv6_mapped;
+ /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
+ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped);
if (sk_is_mptcp(sk))
mptcpv6_handle_mapped(sk, true);
sk->sk_backlog_rcv = tcp_v4_do_rcv;
@@ -249,7 +250,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
- icsk->icsk_af_ops = &ipv6_specific;
+ /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
+ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific);
if (sk_is_mptcp(sk))
mptcpv6_handle_mapped(sk, false);
sk->sk_backlog_rcv = tcp_v6_do_rcv;
--
2.30.2