3.3 KiB
CVE-2021-46929
Description
In the Linux kernel, the following vulnerability has been resolved:sctp: use call_rcu to free endpointThis patch is to delay the endpoint free by calling call_rcu() to fixanother 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:274This issue occurs when asoc is peeled off and the old sk is freed aftergetting 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 whencalling lock_sock(). This patch uses call_rcu() and moves sock_put andep free into sctp_endpoint_destroy_rcu(), so that it's safe to try tohold the ep under rcu_read_lock in sctp_transport_traverse_process().If sctp_endpoint_hold() returns true, it means this ep is still aliveand 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, andwe should skip it.In sctp_sock_dump(), after locking the sk, if this ep is different fromtsp->asoc->ep, it means during this dumping, this asoc was peeled offbefore calling lock_sock(), and the sk should be skipped; If this ep isthe 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 theport release happens in sctp_endpoint_destroy() before calling call_rcu().Also, freeing endpoint by call_rcu() makes it safe to access the sk byasoc->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.
POC
Reference
No PoCs from references.