CVE-2024-50154
Linux Kernel: Use-After-Free in TCP<|reserved_special_token_230|><|start_header_id|><|start_header_id|>assistant<|end_header_id|> Linux Kernel: Use-After-Free in TCP
Description
In the Linux kernel, the following vulnerability has been resolved: tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink(). Martin KaFai Lau reported use-after-free [0] in reqsk_timer_handler(). """ We are seeing a use-after-free from a bpf prog attached to trace_tcp_retransmit_synack. The program passes the req->sk to the bpf_sk_storage_get_tracing kernel helper which does check for null before using it. """ The commit 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") added timer_pending() in reqsk_queue_unlink() not to call del_timer_sync() from reqsk_timer_handler(), but it introduced a small race window. Before the timer is called, expire_timers() calls detach_timer(timer, true) to clear timer->entry.pprev and marks it as not pending. If reqsk_queue_unlink() checks timer_pending() just after expire_timers() calls detach_timer(), TCP will miss del_timer_sync(); the reqsk timer will continue running and send multiple SYN+ACKs until it expires. The reported UAF could happen if req->sk is close()d earlier than the timer expiration, which is 63s by default. The scenario would be 1. inet_csk_complete_hashdance() calls inet_csk_reqsk_queue_drop(), but del_timer_sync() is missed 2. reqsk timer is executed and scheduled again 3. req->sk is accept()ed and reqsk_put() decrements rsk_refcnt, but reqsk timer still has another one, and inet_csk_accept() does not clear req->sk for non-TFO sockets 4. sk is close()d 5. reqsk timer is executed again, and BPF touches req->sk Let's not use timer_pending() by passing the caller context to __inet_csk_reqsk_queue_drop(). Note that reqsk timer is pinned, so the issue does not happen in most use cases. [1] [0] BUG: KFENCE: use-after-free read in bpf_sk_storage_get_tracing+0x2e/0x1b0 Use-after-free read at 0x00000000a891fb3a (in kfence-#1): bpf_sk_storage_get_tracing+0x2e/0x1b0 bpf_prog_5ea3e95db6da0438_tcp_retransmit_synack+0x1d20/0x1dda bpf_trace_run2+0x4c/0xc0 tcp_rtx_synack+0xf9/0x100 reqsk_timer_handler+0xda/0x3d0 run_timer_softirq+0x292/0x8a0 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 intel_idle_irq+0x5a/0xa0 cpuidle_enter_state+0x94/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb kfence-#1: 0x00000000a72cc7b6-0x00000000d97616d9, size=2376, cache=TCPv6 allocated by task 0 on cpu 9 at 260507.901592s: sk_prot_alloc+0x35/0x140 sk_clone_lock+0x1f/0x3f0 inet_csk_clone_lock+0x15/0x160 tcp_create_openreq_child+0x1f/0x410 tcp_v6_syn_recv_sock+0x1da/0x700 tcp_check_req+0x1fb/0x510 tcp_v6_rcv+0x98b/0x1420 ipv6_list_rcv+0x2258/0x26e0 napi_complete_done+0x5b1/0x2990 mlx5e_napi_poll+0x2ae/0x8d0 net_rx_action+0x13e/0x590 irq_exit_rcu+0xf5/0x320 common_interrupt+0x80/0x90 asm_common_interrupt+0x22/0x40 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb freed by task 0 on cpu 9 at 260507.927527s: rcu_core_si+0x4ff/0xf10 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb
INFO
Published Date :
Nov. 7, 2024, 10:15 a.m.
Last Modified :
Nov. 13, 2024, 4:17 p.m.
Source :
416baaa9-dc9f-4396-8d5f-8c081fb06d67
Remotely Exploitable :
No
Impact Score :
5.9
Exploitability Score :
1.0
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2024-50154.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2024-50154 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2024-50154 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Nov. 13, 2024
Action Type Old Value New Value Added CVSS V3.1 NIST AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H Changed Reference Type https://git.kernel.org/stable/c/5071beb59ee416e8ab456ac8647a4dabcda823b1 No Types Assigned https://git.kernel.org/stable/c/5071beb59ee416e8ab456ac8647a4dabcda823b1 Patch Changed Reference Type https://git.kernel.org/stable/c/51e34db64f4e43c7b055ccf881b7f3e0c31bb26d No Types Assigned https://git.kernel.org/stable/c/51e34db64f4e43c7b055ccf881b7f3e0c31bb26d Patch Changed Reference Type https://git.kernel.org/stable/c/8459d61fbf24967839a70235165673148c7c7f17 No Types Assigned https://git.kernel.org/stable/c/8459d61fbf24967839a70235165673148c7c7f17 Patch Changed Reference Type https://git.kernel.org/stable/c/997ae8da14f1639ce6fb66a063dab54031cd61b3 No Types Assigned https://git.kernel.org/stable/c/997ae8da14f1639ce6fb66a063dab54031cd61b3 Patch Changed Reference Type https://git.kernel.org/stable/c/e8c526f2bdf1845bedaf6a478816a3d06fa78b8f No Types Assigned https://git.kernel.org/stable/c/e8c526f2bdf1845bedaf6a478816a3d06fa78b8f Patch Added CWE NIST CWE-416 Added CPE Configuration OR *cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:* versions from (including) 4.1.11 up to (excluding) 4.2 *cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:* versions from (including) 4.2 up to (excluding) 5.15.170 *cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:* versions from (including) 5.16 up to (excluding) 6.1.115 *cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:* versions from (including) 6.2 up to (excluding) 6.6.59 *cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:* versions from (including) 6.7 up to (excluding) 6.11.6 *cpe:2.3:o:linux:linux_kernel:6.12:rc1:*:*:*:*:*:* *cpe:2.3:o:linux:linux_kernel:6.12:rc2:*:*:*:*:*:* *cpe:2.3:o:linux:linux_kernel:6.12:rc3:*:*:*:*:*:* -
CVE Received by 416baaa9-dc9f-4396-8d5f-8c081fb06d67
Nov. 07, 2024
Action Type Old Value New Value Added Description In the Linux kernel, the following vulnerability has been resolved: tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink(). Martin KaFai Lau reported use-after-free [0] in reqsk_timer_handler(). """ We are seeing a use-after-free from a bpf prog attached to trace_tcp_retransmit_synack. The program passes the req->sk to the bpf_sk_storage_get_tracing kernel helper which does check for null before using it. """ The commit 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") added timer_pending() in reqsk_queue_unlink() not to call del_timer_sync() from reqsk_timer_handler(), but it introduced a small race window. Before the timer is called, expire_timers() calls detach_timer(timer, true) to clear timer->entry.pprev and marks it as not pending. If reqsk_queue_unlink() checks timer_pending() just after expire_timers() calls detach_timer(), TCP will miss del_timer_sync(); the reqsk timer will continue running and send multiple SYN+ACKs until it expires. The reported UAF could happen if req->sk is close()d earlier than the timer expiration, which is 63s by default. The scenario would be 1. inet_csk_complete_hashdance() calls inet_csk_reqsk_queue_drop(), but del_timer_sync() is missed 2. reqsk timer is executed and scheduled again 3. req->sk is accept()ed and reqsk_put() decrements rsk_refcnt, but reqsk timer still has another one, and inet_csk_accept() does not clear req->sk for non-TFO sockets 4. sk is close()d 5. reqsk timer is executed again, and BPF touches req->sk Let's not use timer_pending() by passing the caller context to __inet_csk_reqsk_queue_drop(). Note that reqsk timer is pinned, so the issue does not happen in most use cases. [1] [0] BUG: KFENCE: use-after-free read in bpf_sk_storage_get_tracing+0x2e/0x1b0 Use-after-free read at 0x00000000a891fb3a (in kfence-#1): bpf_sk_storage_get_tracing+0x2e/0x1b0 bpf_prog_5ea3e95db6da0438_tcp_retransmit_synack+0x1d20/0x1dda bpf_trace_run2+0x4c/0xc0 tcp_rtx_synack+0xf9/0x100 reqsk_timer_handler+0xda/0x3d0 run_timer_softirq+0x292/0x8a0 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 intel_idle_irq+0x5a/0xa0 cpuidle_enter_state+0x94/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb kfence-#1: 0x00000000a72cc7b6-0x00000000d97616d9, size=2376, cache=TCPv6 allocated by task 0 on cpu 9 at 260507.901592s: sk_prot_alloc+0x35/0x140 sk_clone_lock+0x1f/0x3f0 inet_csk_clone_lock+0x15/0x160 tcp_create_openreq_child+0x1f/0x410 tcp_v6_syn_recv_sock+0x1da/0x700 tcp_check_req+0x1fb/0x510 tcp_v6_rcv+0x98b/0x1420 ipv6_list_rcv+0x2258/0x26e0 napi_complete_done+0x5b1/0x2990 mlx5e_napi_poll+0x2ae/0x8d0 net_rx_action+0x13e/0x590 irq_exit_rcu+0xf5/0x320 common_interrupt+0x80/0x90 asm_common_interrupt+0x22/0x40 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb freed by task 0 on cpu 9 at 260507.927527s: rcu_core_si+0x4ff/0xf10 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb Added Reference kernel.org https://git.kernel.org/stable/c/8459d61fbf24967839a70235165673148c7c7f17 [No types assigned] Added Reference kernel.org https://git.kernel.org/stable/c/5071beb59ee416e8ab456ac8647a4dabcda823b1 [No types assigned] Added Reference kernel.org https://git.kernel.org/stable/c/997ae8da14f1639ce6fb66a063dab54031cd61b3 [No types assigned] Added Reference kernel.org https://git.kernel.org/stable/c/51e34db64f4e43c7b055ccf881b7f3e0c31bb26d [No types assigned] Added Reference kernel.org https://git.kernel.org/stable/c/e8c526f2bdf1845bedaf6a478816a3d06fa78b8f [No types assigned]
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2024-50154 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2024-50154
weaknesses.