tcp: tcp_rtx_synack() can be called from process context
Subsystems (3)
PATCH 1/1 tcp: tcp_rtx_synack() can be called from process context
From: Eric Dumazet <[email protected]>
Laurent reported the enclosed report [1]
This bug triggers with following coditions:
0) Kernel built with CONFIG_DEBUG_PREEMPT=y
1) A new passive FastOpen TCP socket is created.
This FO socket waits for an ACK coming from client to be a complete ESTABLISHED one.
2) A socket operation on this socket goes through lock_sock() release_sock() dance.
3) While the socket is owned by the user in step 2),
a retransmit of the SYN is received and stored in socket backlog.
4) At release_sock() time, the socket backlog is processed while in process context.
5) A SYNACK packet is cooked in response of the SYN retransmit.
6) -> tcp_rtx_synack() is called in process context.
Before blamed commit, tcp_rtx_synack() was always called from BH handler, from a timer handler.
Fix this by using TCP_INC_STATS() & NET_INC_STATS() which do not assume caller is in non preemptible context.
[1]
BUG: using __this_cpu_add() in preemptible [00000000] code: epollpep/2180 caller is tcp_rtx_synack.part.0+0x36/0xc0 CPU: 10 PID: 2180 Comm: epollpep Tainted: G OE 5.16.0-0.bpo.4-amd64 #1 Debian 5.16.12-1~bpo11+1 Hardware name: Supermicro SYS-5039MC-H8TRF/X11SCD-F, BIOS 1.7 11/23/2021 Call Trace: <TASK> dump_stack_lvl+0x48/0x5e check_preemption_disabled+0xde/0xe0 tcp_rtx_synack.part.0+0x36/0xc0 tcp_rtx_synack+0x8d/0xa0 ? kmem_cache_alloc+0x2e0/0x3e0 ? apparmor_file_alloc_security+0x3b/0x1f0 inet_rtx_syn_ack+0x16/0x30 tcp_check_req+0x367/0x610 tcp_rcv_state_process+0x91/0xf60 ? get_nohz_timer_target+0x18/0x1a0 ? lock_timer_base+0x61/0x80 ? preempt_count_add+0x68/0xa0 tcp_v4_do_rcv+0xbd/0x270 __release_sock+0x6d/0xb0 release_sock+0x2b/0x90 sock_setsockopt+0x138/0x1140 ? __sys_getsockname+0x7e/0xc0 ? aa_sk_perm+0x3e/0x1a0 __sys_setsockopt+0x198/0x1e0 __x64_sys_setsockopt+0x21/0x30 do_syscall_64+0x38/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae
--- net/ipv4/tcp_output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/ipv4/tcp_output.c +2 -2
@@ -4115,8 +4115,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) res = af_ops->send_synack (sk,NULL , &fl, req,NULL ,TCP_SYNACK_NORMAL ,NULL );if (!res) { -__TCP_INC_STATS (sock_net (sk),TCP_MIB_RETRANSSEGS ); -__NET_INC_STATS (sock_net (sk),LINUX_MIB_TCPSYNRETRANS ); +TCP_INC_STATS (sock_net (sk),TCP_MIB_RETRANSSEGS ); +NET_INC_STATS (sock_net (sk),LINUX_MIB_TCPSYNRETRANS );if (unlikely (tcp_passive_fastopen (sk)))tcp_sk (sk)->total_retrans++;trace_tcp_retransmit_synack (sk, req);
Signature · 1 line
2.36.1.255.ge46751e96f-goog
Quoted 70 lines · Eric Dumazet
From: Eric Dumazet <[email protected]>
Laurent reported the enclosed report [1]
This bug triggers with following coditions:
0) Kernel built with
CONFIG_DEBUG_PREEMPT=y1) A new passive FastOpen TCP socket is created.
This FO socket waits for an ACK coming from client to be a complete ESTABLISHED one.
2) A socket operation on this socket goes throughlock_sock()release_sock()dance.
3) While the socket is owned by the user in step 2),
a retransmit of the SYN is received and stored in socket backlog.
4) Atrelease_sock()time, the socket backlog is processed while in process context.
5) A SYNACK packet is cooked in response of the SYN retransmit.
6) ->tcp_rtx_synack()is called in process context.Before blamed commit,
tcp_rtx_synack()was always called from BH handler, from a timer handler.Fix this by using
TCP_INC_STATS()&NET_INC_STATS()which do not assume caller is in non preemptible context.[1]
BUG: using __this_cpu_add() in preemptible [00000000] code: epollpep/2180 caller is tcp_rtx_synack.part.0+0x36/0xc0 CPU: 10 PID: 2180 Comm: epollpep Tainted: G OE 5.16.0-0.bpo.4-amd64 #1 Debian 5.16.12-1~bpo11+1 Hardware name: Supermicro SYS-5039MC-H8TRF/X11SCD-F, BIOS 1.7 11/23/2021 Call Trace: <TASK> dump_stack_lvl+0x48/0x5e check_preemption_disabled+0xde/0xe0 tcp_rtx_synack.part.0+0x36/0xc0 tcp_rtx_synack+0x8d/0xa0 ? kmem_cache_alloc+0x2e0/0x3e0 ? apparmor_file_alloc_security+0x3b/0x1f0 inet_rtx_syn_ack+0x16/0x30 tcp_check_req+0x367/0x610 tcp_rcv_state_process+0x91/0xf60 ? get_nohz_timer_target+0x18/0x1a0 ? lock_timer_base+0x61/0x80 ? preempt_count_add+0x68/0xa0 tcp_v4_do_rcv+0xbd/0x270 __release_sock+0x6d/0xb0 release_sock+0x2b/0x90 sock_setsockopt+0x138/0x1140 ? __sys_getsockname+0x7e/0xc0 ? aa_sk_perm+0x3e/0x1a0 __sys_setsockopt+0x198/0x1e0 __x64_sys_setsockopt+0x21/0x30 do_syscall_64+0x38/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xaeFixes 168a8f58059a ("tcp: TCP Fast Open Server - main code path")Signed-off-by Eric Dumazet <[email protected]>Reported-by Laurent Fasnacht <[email protected]>--- net/ipv4/tcp_output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)net/ipv4/tcp_output.c +0
-0@@ -4115,8 +4115,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
net/ipv4/tcp_output.c int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
Quoted 10 lines
net/ipv4/tcp_output.c +2
-3NULL);if (!res) { -__TCP_INC_STATS (sock_net (sk),TCP_MIB_RETRANSSEGS ); -__NET_INC_STATS (sock_net (sk),LINUX_MIB_TCPSYNRETRANS ); +TCP_INC_STATS (sock_net (sk),TCP_MIB_RETRANSSEGS ); +NET_INC_STATS (sock_net (sk),LINUX_MIB_TCPSYNRETRANS );if (unlikely (tcp_passive_fastopen (sk)))tcp_sk (sk)->total_retrans++;trace_tcp_retransmit_synack (sk, req); --
Nice diagnosis and fix! Thanks, Eric!
neal
This patch was applied to netdev/net.git (master) by Jakub Kicinski <[email protected]>:
Hello:
This patch was applied to netdev/net.git (master)
by Jakub Kicinski <[email protected]>:
Quoted 9 lines · On Mon, 30 May 2022 14:37:13 -0700 you wrote:
From: Eric Dumazet <[email protected]>
Laurent reported the enclosed report [1]
This bug triggers with following coditions:
0) Kernel built with
CONFIG_DEBUG_PREEMPT=y[...]
Here is the summary with links:
- [net] tcp: tcp_rtx_synack() can be called from process context
https://git.kernel.org/netdev/net/c/0a375c822497
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html