nvd-json-data-feeds/CVE-2021/CVE-2021-469xx/CVE-2021-46929.json

{
  "id": "CVE-2021-46929",
  "sourceIdentifier": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
  "published": "2024-02-27T10:15:07.573",
  "lastModified": "2024-02-27T14:20:06.637",
  "vulnStatus": "Awaiting Analysis",
  "descriptions": [
    {
      "lang": "en",
      "value": "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->base.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's 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->asoc->ep, 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->asoc->ep, 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't 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->base.sk in sctp_assocs_seq_show() and sctp_rcv().\n\nThanks Jones to bring this issue up.\n\nv1->v2:\n  - improve the changelog.\n  - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed."
    },
    {
      "lang": "es",
      "value": "En el kernel de Linux, se resolvi\u00f3 la siguiente vulnerabilidad: sctp: use call_rcu para liberar el endpoint. Este parche tiene como objetivo retrasar la liberaci\u00f3n del endpoint llamando a call_rcu() para solucionar otro problema de use-after-free en sctp_sock_dump(): ERROR: KASAN: use-after-free en __lock_acquire+0x36d9/0x4c20 Rastreo de llamadas: __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 [en l\u00ednea] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [en l\u00ednea] __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 [en l\u00ednea] 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+0x6 06/0x1080 neto/ netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [en l\u00ednea] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cm re neto /core/sock_diag.c:232 [en l\u00ednea] 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 Este problema ocurre cuando se quita asoc y se libera el sk antiguo despu\u00e9s de obtenerlo mediante asoc->base.sk y antes de llamar a lock_sock(sk). Para evitar que sk se libere, como titular de sk, ep debe estar activo al llamar a lock_sock(). Este parche usa call_rcu() y mueve sock_put y ep free a sctp_endpoint_destroy_rcu(), por lo que es seguro intentar mantener el ep bajo rcu_read_lock en sctp_transport_traverse_process(). Si sctp_endpoint_hold() devuelve verdadero, significa que este ep todav\u00eda est\u00e1 vivo, lo hemos retenido y podemos continuar descart\u00e1ndolo; Si devuelve falso, significa que este ep est\u00e1 muerto y puede liberarse despu\u00e9s de rcu_read_unlock, y debemos omitirlo. En sctp_sock_dump(), despu\u00e9s de bloquear el sk, si este ep es diferente de tsp->asoc->ep, significa que durante este volcado, este asoc se elimin\u00f3 antes de llamar a lock_sock(), y el sk debe omitirse; Si este ep es el mismo con tsp->asoc->ep, significa que no se produce ning\u00fan despegue en este asoc y, debido a lock_sock, tampoco se producir\u00e1 ning\u00fan despegue hasta que se libere_sock. Tenga en cuenta que retrasar la liberaci\u00f3n del endpoint  no retrasar\u00e1 la liberaci\u00f3n del puerto, ya que la liberaci\u00f3n del puerto ocurre en sctp_endpoint_destroy() antes de llamar a call_rcu(). Adem\u00e1s, liberar el endpoint mediante call_rcu() hace que sea seguro acceder a sk mediante asoc->base.sk en sctp_assocs_seq_show() y sctp_rcv(). Gracias Jones por plantear este problema. v1->v2: - mejorar el registro de cambios. - agregue kfree(ep) a sctp_endpoint_destroy_rcu(), como not\u00f3 Jakub."
    }
  ],
  "metrics": {},
  "references": [
    {
      "url": "https://git.kernel.org/stable/c/5ec7d18d1813a5bead0b495045606c93873aecbb",
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    },
    {
      "url": "https://git.kernel.org/stable/c/75799e71df1da11394740b43ae5686646179561d",
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    },
    {
      "url": "https://git.kernel.org/stable/c/769d14abd35e0e153b5149c3e1e989a9d719e3ff",
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    },
    {
      "url": "https://git.kernel.org/stable/c/831de271452b87657fcf8d715ee20519b79caef5",
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    },
    {
      "url": "https://git.kernel.org/stable/c/8873140f95d4977bf37e4cf0d5c5e3f6e34cdd3e",
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    },
    {
      "url": "https://git.kernel.org/stable/c/af6e6e58f7ebf86b4e7201694b1e4f3a62cbc3ec",
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    }
  ]
}