On Thu, 23 Dec 2021, Xin Long wrote:
> This patch is to delay the endpoint free by calling call_rcu() to fix
> another use-after-free issue in sctp_sock_dump():
>
> BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20
> Call Trace:
> __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218
> lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844
> __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
> _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168
> spin_lock_bh include/linux/spinlock.h:334 [inline]
> __lock_sock+0x203/0x350 net/core/sock.c:2253
> lock_sock_nested+0xfe/0x120 net/core/sock.c:2774
> lock_sock include/net/sock.h:1492 [inline]
> sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324
> sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091
> sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527
> __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049
> inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065
> netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244
> __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352
> netlink_dump_start include/linux/netlink.h:216 [inline]
> inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170
> __sock_diag_cmd net/core/sock_diag.c:232 [inline]
> sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263
> netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477
> sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274
>
> This issue occurs when asoc is peeled off and the old sk is freed after
> getting it by asoc->base.sk and before calling lock_sock(sk).
>
> To prevent the sk free, as a holder of the sk, ep should be alive when
> calling lock_sock(). This patch uses call_rcu() and moves sock_put and
> ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to
> hold the ep under rcu_read_lock in sctp_transport_traverse_process().
>
> If sctp_endpoint_hold() returns true, it means this ep is still alive
> and we have held it and can continue to dump it; If it returns false,
> it means this ep is dead and can be freed after rcu_read_unlock, and
> we should skip it.
>
> In sctp_sock_dump(), after locking the sk, if this ep is different from
> tsp->asoc->ep, it means during this dumping, this asoc was peeled off
> before calling lock_sock(), and the sk should be skipped; If this ep is
> the same with tsp->asoc->ep, it means no peeloff happens on this asoc,
> and due to lock_sock, no peeloff will happen either until release_sock.
>
> Note that delaying endpoint free won't delay the port release, as the
> port release happens in sctp_endpoint_destroy() before calling call_rcu().
> Also, freeing endpoint by call_rcu() makes it safe to access the sk by
> asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv().
>
> Thanks Jones to bring this issue up.
>
> v1->v2:
> - improve the changelog.
> - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed.
>
> Reported-by: syzbot+9276d76e83e3bcde6c99@xxxxxxxxxxxxxxxxxxxxxxxxx
> Reported-by: Lee Jones <lee.jones@xxxxxxxxxx>
> Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump")
> Signed-off-by: Xin Long <lucien.xin@xxxxxxxxx>
> ---
> include/net/sctp/sctp.h | 6 +++---
> include/net/sctp/structs.h | 3 ++-
> net/sctp/diag.c | 12 ++++++------
> net/sctp/endpointola.c | 23 +++++++++++++++--------
> net/sctp/socket.c | 23 +++++++++++++++--------
> 5 files changed, 41 insertions(+), 26 deletions(-)
My test has been soaking for about an hour now with no crashes.
So far so good:
Tested-by: Lee Jones <lee.jones@xxxxxxxxxx>
--
Lee Jones [李琼斯]
Senior Technical Lead - Developer Services
Linaro.org │ Open source software for Arm SoCs
Follow Linaro: Facebook | Twitter | Blog
