Skip to contentSkip to conversation

tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().

PATCH Superseded Dmitriy Privalov 1 participant 1 message Jan 16, 2025

Subsystems (4)

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().

From: Kuniyuki Iwashima <[email protected]>

commit e8c526f2bdf1845bedaf6a478816a3d06fa78b8f upstream.

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

---
Backport fix for CVE-2024-50154

---
v2: Fix patch applying

 net/ipv4/inet_connection_sock.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)
net/ipv4/inet_connection_sock.c +15 -4
index 1dfa561e8f981..d912894ad4adc 100644
@@ -700,21 +700,31 @@ static bool reqsk_queue_unlink(struct request_sock *req)
 		found = __sk_nulls_del_node_init_rcu(req_to_sk(req));
 		spin_unlock(lock);
 	}
-	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
-		reqsk_put(req);
+
 	return found;
 }
 
-bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+static bool __inet_csk_reqsk_queue_drop(struct sock *sk,
+					struct request_sock *req,
+					bool from_timer)
 {
 	bool unlinked = reqsk_queue_unlink(req);
 
+	if (!from_timer && del_timer_sync(&req->rsk_timer))
+		reqsk_put(req);
+
 	if (unlinked) {
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
 		reqsk_put(req);
 	}
+
 	return unlinked;
 }
+
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+{
+	return __inet_csk_reqsk_queue_drop(sk, req, false);
+}
 EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
 
 void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
@@ -781,7 +791,8 @@ static void reqsk_timer_handler(struct timer_list *t)
 		return;
 	}
 drop:
-	inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
+	__inet_csk_reqsk_queue_drop(sk_listener, req, true);
+	reqsk_put(req);
 }
 
 static void reqsk_queue_hash_req(struct request_sock *req,
Signature · 1 line
2.34.1