req->num_timeout counts the SYN-ACK timeouts of a request and is used as a shift amount: /* tcp_reqsk_timeout() */ u64 timeout = (u64)req->timeout << req->num_timeout; /* tcp_fastopen_synack_timer() */ req->timeout << req->num_timeout Once it climbs past the width of the shifted type the shift is UB. Seen with tcp_synack_retries=255 and a peer that never completes the handshake: UBSAN: shift-out-of-bounds in ./include/net/tcp.h:917:34 shift exponent 64 is too large for 64-bit type 'long long unsigned int' Call Trace: dump_stack_lvl+0xc1/0xf0 dump_stack+0x10/0x20 __ubsan_handle_shift_out_of_bounds+0x1d1/0x390 reqsk_timer_handler.cold+0x1c/0x5d call_timer_fn+0x17d/0x510 __run_timers+0x662/0xab0 run_timer_softirq+0xdf/0x260 handle_softirqs+0x204/0x9b0 __irq_exit_rcu+0x13c/0x220 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0x40/0xd0 asm_sysvec_apic_timer_interrupt+0x1b/0x20 The sysctl is not needed: TCP_SYNCNT=127 on the listener gets there too, and the TFO shift is 32-bit, so it is UB from num_timeout 32. The value can also wrap to 0 before the shift count is out of range, which arms a zero-length timer. E.g. with HZ=1000 and req->timeout == 1000, (u64)1000 << 61 and (u32)1000 << 29 are both 0. num_timeout is a 7-bit field. Once a retransmit limit is above 127 the "num_timeout >= limit" check can never be true, the request is never expired by that limit, and after the field wraps to 0 reqsk_timer_handler() decrements queue->young again on the next expiry. - split tcp_reqsk_timeout() into tcp_reqsk_timeout_sk() and cap the shift at 32 there, same as inet_csk_rto_backoff() in the next patch. req->timeout << 32 is already above tcp_rto_max(), so the clamped result does not change. - cap max_retries / max_syn_ack_retries at MAX_TCP_SYNCNT (127), the largest value the field can hold. The sysctl range is left alone: narrowing it would make setups that write 128..255 fail with -EINVAL, and the caps are needed anyway for TCP_DEFER_ACCEPT and the TFO "+ 1". 128..255 now act as 127. - cap the TCP_DEFER_ACCEPT conversion in secs_to_retrans() at 127 too; larger values kept an acked request from ever expiring. getsockopt() now reports at most 14527 instead of 29887 seconds. - route the TFO path through the same helper. - document that tcp_synack_retries values above 127 act as 127. Found by checking sysctl ranges against their users. Reproduced in a VM with UBSAN: tcp_synack_retries=255 and tcp_rto_max_ms=1000 on the server, and an iptables rule dropping the final ACK of the handshake. The splat shows up after about 64 seconds, and is gone with this patch. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: e6c022a4fa2d ("tcp: better retrans tracking for defer-accept") Cc: stable@vger.kernel.org Signed-off-by: Jiayuan Chen --- v2 -> v3: - drop READ_ONCE(req->timeout), cap the shift at 32, reuse MAX_TCP_SYNCNT, simplify the doc text (Neal) - changelog: mention TCP_SYNCNT, the wrap to 0, why the sysctl range is not narrowed, how it was found and tested (Neal) - add Fixes: 1da177e4c3f4, the shift was already there v1 -> v2: reworded the commit message, no code change. v2: https://lore.kernel.org/netdev/20261026123244.239766-1-jiayuan.chen@linux.dev/ v1: https://lore.kernel.org/netdev/20261023064915.401112-1-jiayuan.chen@linux.dev/ --- Documentation/networking/ip-sysctl.rst | 2 +- include/net/tcp.h | 14 ++++++++++---- net/ipv4/inet_connection_sock.c | 1 + net/ipv4/tcp.c | 2 +- net/ipv4/tcp_timer.c | 3 ++- 5 files changed, 15 insertions(+), 7 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 3cc80d9b024b..468d3df998a5 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -956,7 +956,7 @@ tcp_stdurg - BOOLEAN tcp_synack_retries - INTEGER Number of times SYNACKs for a passive TCP connection attempt will - be retransmitted. Should not be higher than 255. Default value + be retransmitted. Values above 127 are treated as 127. Default value is 5, which corresponds to 31seconds till the last retransmission with the current initial RTO of 1second. With this the final timeout for a passive TCP connection will happen after 63seconds. diff --git a/include/net/tcp.h b/include/net/tcp.h index 25d11fab1b03..39ee5c250bae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -920,12 +920,18 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } -static inline unsigned long tcp_reqsk_timeout(struct request_sock *req) +static inline unsigned long tcp_reqsk_timeout_sk(const struct sock *sk, + const struct request_sock *req) { - u64 timeout = (u64)req->timeout << req->num_timeout; + /* timeout << 32 is already above tcp_rto_max(). */ + u64 timeout = (u64)req->timeout << min_t(u8, req->num_timeout, 32); + + return (unsigned long)min_t(u64, timeout, tcp_rto_max(sk)); +} - return (unsigned long)min_t(u64, timeout, - tcp_rto_max(req->rsk_listener)); +static inline unsigned long tcp_reqsk_timeout(struct request_sock *req) +{ + return tcp_reqsk_timeout_sk(req->rsk_listener, req); } u32 tcp_delack_max(const struct sock *sk); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5807067083c9..02a472d44ea5 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1071,6 +1071,7 @@ static void reqsk_timer_handler(struct timer_list *t) net = sock_net(sk_listener); max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); + max_syn_ack_retries = min_t(int, max_syn_ack_retries, MAX_TCP_SYNCNT); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d510e982dcea..45ecc97e164f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -358,7 +358,7 @@ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) int period = timeout; res = 1; - while (seconds > period && res < 255) { + while (seconds > period && res < MAX_TCP_SYNCNT) { res++; timeout <<= 1; if (timeout > rto_max) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 00debcba122b..814fadb30749 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -468,6 +468,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) */ max_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; + max_retries = min_t(int, max_retries, MAX_TCP_SYNCNT); if (req->num_timeout >= max_retries) { tcp_write_err(sk); @@ -489,7 +490,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - req->timeout << req->num_timeout, false); + tcp_reqsk_timeout_sk(sk, req), false); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, -- 2.43.0