kernel/net/ipv4/tcp_output.c, branch linux-6.2.y

tcp: tcp_make_synack() can be called from process context

2023-03-22T12:37:45Z

[ Upstream commit bced3f7db95ff2e6ca29dc4d1c9751ab5e736a09 ] tcp_rtx_synack() now could be called in process context as explained in 0a375c822497 ("tcp: tcp_rtx_synack() can be called from process context"). tcp_rtx_synack() might call tcp_make_synack(), which will touch per-CPU variables with preemption enabled. This causes the following BUG: BUG: using __this_cpu_add() in preemptible [00000000] code: ThriftIO1/5464 caller is tcp_make_synack+0x841/0xac0 Call Trace: dump_stack_lvl+0x10d/0x1a0 check_preemption_disabled+0x104/0x110 tcp_make_synack+0x841/0xac0 tcp_v6_send_synack+0x5c/0x450 tcp_rtx_synack+0xeb/0x1f0 inet_rtx_syn_ack+0x34/0x60 tcp_check_req+0x3af/0x9e0 tcp_rcv_state_process+0x59b/0x2030 tcp_v6_do_rcv+0x5f5/0x700 release_sock+0x3a/0xf0 tcp_sendmsg+0x33/0x40 ____sys_sendmsg+0x2f2/0x490 __sys_sendmsg+0x184/0x230 do_syscall_64+0x3d/0x90 Avoid calling __TCP_INC_STATS() with will touch per-cpu variables. Use TCP_INC_STATS() which is safe to be called from context switch. Fixes: 8336886f786f ("tcp: TCP Fast Open Server - support TFO listeners") Signed-off-by: Breno Leitao Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230308190745.780221-1-leitao@debian.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin

net/tcp: Disable TCP-MD5 static key on tcp_md5sig_info destruction

2022-12-01T23:53:05Z

To do that, separate two scenarios: - where it's the first MD5 key on the system, which means that enabling of the static key may need to sleep; - copying of an existing key from a listening socket to the request socket upon receiving a signed TCP segment, where static key was already enabled (when the key was added to the listening socket). Now the life-time of the static branch for TCP-MD5 is until: - last tcp_md5sig_info is destroyed - last socket in time-wait state with MD5 key is closed. Which means that after all sockets with TCP-MD5 keys are gone, the system gets back the performance of disabled md5-key static branch. While at here, provide static_key_fast_inc() helper that does ref counter increment in atomic fashion (without grabbing cpus_read_lock() on CONFIG_JUMP_LABEL=y). This is needed to add a new user for a static_key when the caller controls the lifetime of another user. Signed-off-by: Dmitry Safonov Acked-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski

tcp: tcp_wfree() refactoring

2022-11-12T05:38:03Z

Use try_cmpxchg() (instead of cmpxchg()) in a more readable way. oval = smp_load_acquire(&sk->sk_tsq_flags); do { ... } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); Reduce indentation level. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20221110190239.3531280-1-edumazet@google.com Signed-off-by: Jakub Kicinski

tcp: adopt try_cmpxchg() in tcp_release_cb()

2022-11-12T05:37:49Z

try_cmpxchg() is slighly more efficient (at least on x86), and smp_load_acquire(&sk->sk_tsq_flags) could avoid a KCSAN report. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20221110174829.3403442-1-edumazet@google.com Signed-off-by: Jakub Kicinski

tcp: fix tcp_cwnd_validate() to not forget is_cwnd_limited

2022-09-30T11:37:45Z

This commit fixes a bug in the tracking of max_packets_out and is_cwnd_limited. This bug can cause the connection to fail to remember that is_cwnd_limited is true, causing the connection to fail to grow cwnd when it should, causing throughput to be lower than it should be. The following event sequence is an example that triggers the bug: (a) The connection is cwnd_limited, but packets_out is not at its peak due to TSO deferral deciding not to send another skb yet. In such cases the connection can advance max_packets_seq and set tp->is_cwnd_limited to true and max_packets_out to a small number. (b) Then later in the round trip the connection is pacing-limited (not cwnd-limited), and packets_out is larger. In such cases the connection would raise max_packets_out to a bigger number but (unexpectedly) flip tp->is_cwnd_limited from true to false. This commit fixes that bug. One straightforward fix would be to separately track (a) the next window after max_packets_out reaches a maximum, and (b) the next window after tp->is_cwnd_limited is set to true. But this would require consuming an extra u32 sequence number. Instead, to save space we track only the most important information. Specifically, we track the strongest available signal of the degree to which the cwnd is fully utilized: (1) If the connection is cwnd-limited then we remember that fact for the current window. (2) If the connection not cwnd-limited then we track the maximum number of outstanding packets in the current window. In particular, note that the new logic cannot trigger the buggy (a)/(b) sequence above because with the new logic a condition where tp->packets_out > tp->max_packets_out can only trigger an update of tp->is_cwnd_limited if tp->is_cwnd_limited is false. This first showed up in a testing of a BBRv2 dev branch, but this buggy behavior highlighted a general issue with the tcp_cwnd_validate() logic that can cause cwnd to fail to increase at the proper rate for any TCP congestion control, including Reno or CUBIC. Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement-based, and gentler") Signed-off-by: Neal Cardwell Signed-off-by: Kevin(Yudong) Yang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller

net: Fix data-races around sysctl_[rw]mem_(max|default).

2022-08-24T12:46:57Z

While reading sysctl_[rw]mem_(max|default), they can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2022-07-29T01:21:16Z

No conflicts. Signed-off-by: Jakub Kicinski

net: Fix data-races around sysctl_[rw]mem(_offset)?.

2022-07-25T11:42:09Z

While reading these sysctl variables, they can be changed concurrently. Thus, we need to add READ_ONCE() to their readers. - .sysctl_rmem - .sysctl_rwmem - .sysctl_rmem_offset - .sysctl_wmem_offset - sysctl_tcp_rmem[1, 2] - sysctl_tcp_wmem[1, 2] - sysctl_decnet_rmem[1] - sysctl_decnet_wmem[1] - sysctl_tipc_rmem[1] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller

Revert "tcp: change pingpong threshold to 3"

2022-07-22T22:09:10Z

This reverts commit 4a41f453bedfd5e9cd040bad509d9da49feb3e2c. This to-be-reverted commit was meant to apply a stricter rule for the stack to enter pingpong mode. However, the condition used to check for interactive session "before(tp->lsndtime, icsk->icsk_ack.lrcvtime)" is jiffy based and might be too coarse, which delays the stack entering pingpong mode. We revert this patch so that we no longer use the above condition to determine interactive session, and also reduce pingpong threshold to 1. Fixes: 4a41f453bedf ("tcp: change pingpong threshold to 3") Reported-by: LemmyHuang Suggested-by: Neal Cardwell Signed-off-by: Wei Wang Acked-by: Neal Cardwell Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220721204404.388396-1-weiwan@google.com Signed-off-by: Jakub Kicinski

tcp: Fix a data-race around sysctl_tcp_tso_rtt_log.

2022-07-22T11:06:17Z

While reading sysctl_tcp_tso_rtt_log, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 65466904b015 ("tcp: adjust TSO packet sizes based on min_rtt") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller