// For flags

CVE-2021-46929

sctp: use call_rcu to free endpoint

Severity Score

5.5
*CVSS v3.1

Exploit Likelihood

*EPSS

Affected Versions

*CPE

Public Exploits

0
*Multiple Sources

Exploited in Wild

-
*KEV

Decision

Track
*SSVC
Descriptions

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.

En el kernel de Linux, se resolvió la siguiente vulnerabilidad: sctp: use call_rcu para liberar el endpoint. Este parche tiene como objetivo retrasar la liberación 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 línea] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [en línea] __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 línea] 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 línea] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cm re neto /core/sock_diag.c:232 [en línea] 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 después 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 todavía está vivo, lo hemos retenido y podemos continuar descartándolo; Si devuelve falso, significa que este ep está muerto y puede liberarse después de rcu_read_unlock, y debemos omitirlo. En sctp_sock_dump(), después de bloquear el sk, si este ep es diferente de tsp->asoc->ep, significa que durante este volcado, este asoc se eliminó 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 ningún despegue en este asoc y, debido a lock_sock, tampoco se producirá ningún despegue hasta que se libere_sock. Tenga en cuenta que retrasar la liberación del endpoint no retrasará la liberación del puerto, ya que la liberación del puerto ocurre en sctp_endpoint_destroy() antes de llamar a call_rcu(). Además, 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 notó Jakub.

*Credits: N/A
CVSS Scores
Attack Vector
Local
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High
* Common Vulnerability Scoring System
SSVC
  • Decision:Track
Exploitation
None
Automatable
No
Tech. Impact
Partial
* Organization's Worst-case Scenario
Timeline
  • 2024-02-25 CVE Reserved
  • 2024-02-27 CVE Published
  • 2024-04-21 EPSS Updated
  • 2024-09-11 CVE Updated
  • ---------- Exploited in Wild
  • ---------- KEV Due Date
  • ---------- First Exploit
CWE
  • CWE-416: Use After Free
CAPEC
Affected Vendors, Products, and Versions
Vendor Product Version Other Status
Vendor Product Version Other Status <-- --> Vendor Product Version Other Status
Linux
Search vendor "Linux"
Linux Kernel
Search vendor "Linux" for product "Linux Kernel"
>= 4.14 < 4.14.261
Search vendor "Linux" for product "Linux Kernel" and version " >= 4.14 < 4.14.261"
en
Affected
Linux
Search vendor "Linux"
Linux Kernel
Search vendor "Linux" for product "Linux Kernel"
>= 4.14 < 4.19.224
Search vendor "Linux" for product "Linux Kernel" and version " >= 4.14 < 4.19.224"
en
Affected
Linux
Search vendor "Linux"
Linux Kernel
Search vendor "Linux" for product "Linux Kernel"
>= 4.14 < 5.4.170
Search vendor "Linux" for product "Linux Kernel" and version " >= 4.14 < 5.4.170"
en
Affected
Linux
Search vendor "Linux"
Linux Kernel
Search vendor "Linux" for product "Linux Kernel"
>= 4.14 < 5.10.90
Search vendor "Linux" for product "Linux Kernel" and version " >= 4.14 < 5.10.90"
en
Affected
Linux
Search vendor "Linux"
Linux Kernel
Search vendor "Linux" for product "Linux Kernel"
>= 4.14 < 5.15.13
Search vendor "Linux" for product "Linux Kernel" and version " >= 4.14 < 5.15.13"
en
Affected
Linux
Search vendor "Linux"
Linux Kernel
Search vendor "Linux" for product "Linux Kernel"
>= 4.14 < 5.16
Search vendor "Linux" for product "Linux Kernel" and version " >= 4.14 < 5.16"
en
Affected