ghsa-j525-244m-q96j
Vulnerability from github
In the Linux kernel, the following vulnerability has been resolved:
sctp: use call_rcu to free endpoint
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.
{
"affected": [],
"aliases": [
"CVE-2021-46929"
],
"database_specific": {
"cwe_ids": [
"CWE-416"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-02-27T10:15:07Z",
"severity": "MODERATE"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nsctp: use call_rcu to free endpoint\n\nThis patch is to delay the endpoint free by calling call_rcu() to fix\nanother use-after-free issue in sctp_sock_dump():\n\n BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20\n Call Trace:\n __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218\n lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844\n __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]\n _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168\n spin_lock_bh include/linux/spinlock.h:334 [inline]\n __lock_sock+0x203/0x350 net/core/sock.c:2253\n lock_sock_nested+0xfe/0x120 net/core/sock.c:2774\n lock_sock include/net/sock.h:1492 [inline]\n sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324\n sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091\n sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527\n __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049\n inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065\n netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244\n __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352\n netlink_dump_start include/linux/netlink.h:216 [inline]\n inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170\n __sock_diag_cmd net/core/sock_diag.c:232 [inline]\n sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263\n netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477\n sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274\n\nThis issue occurs when asoc is peeled off and the old sk is freed after\ngetting it by asoc-\u003ebase.sk and before calling lock_sock(sk).\n\nTo prevent the sk free, as a holder of the sk, ep should be alive when\ncalling lock_sock(). This patch uses call_rcu() and moves sock_put and\nep free into sctp_endpoint_destroy_rcu(), so that it\u0027s safe to try to\nhold the ep under rcu_read_lock in sctp_transport_traverse_process().\n\nIf sctp_endpoint_hold() returns true, it means this ep is still alive\nand we have held it and can continue to dump it; If it returns false,\nit means this ep is dead and can be freed after rcu_read_unlock, and\nwe should skip it.\n\nIn sctp_sock_dump(), after locking the sk, if this ep is different from\ntsp-\u003easoc-\u003eep, it means during this dumping, this asoc was peeled off\nbefore calling lock_sock(), and the sk should be skipped; If this ep is\nthe same with tsp-\u003easoc-\u003eep, it means no peeloff happens on this asoc,\nand due to lock_sock, no peeloff will happen either until release_sock.\n\nNote that delaying endpoint free won\u0027t delay the port release, as the\nport release happens in sctp_endpoint_destroy() before calling call_rcu().\nAlso, freeing endpoint by call_rcu() makes it safe to access the sk by\nasoc-\u003ebase.sk in sctp_assocs_seq_show() and sctp_rcv().\n\nThanks Jones to bring this issue up.\n\nv1-\u003ev2:\n - improve the changelog.\n - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed.",
"id": "GHSA-j525-244m-q96j",
"modified": "2024-04-10T18:30:46Z",
"published": "2024-02-27T12:31:10Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2021-46929"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/5ec7d18d1813a5bead0b495045606c93873aecbb"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/75799e71df1da11394740b43ae5686646179561d"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/769d14abd35e0e153b5149c3e1e989a9d719e3ff"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/831de271452b87657fcf8d715ee20519b79caef5"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/8873140f95d4977bf37e4cf0d5c5e3f6e34cdd3e"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/af6e6e58f7ebf86b4e7201694b1e4f3a62cbc3ec"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
]
}