netdev - Re: [PATCH v2 net-next] net: generalize skb freeing deferral to per-cpu lists

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 29 Apr 2022 09:23:13 -0700
From:   Eric Dumazet <edumazet@...gle.com>
To:     Qian Cai <quic_qiancai@...cinc.com>
Cc:     Eric Dumazet <eric.dumazet@...il.com>,
        "David S . Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        netdev <netdev@...r.kernel.org>
Subject: Re: [PATCH v2 net-next] net: generalize skb freeing deferral to
 per-cpu lists

On Fri, Apr 29, 2022 at 9:18 AM Qian Cai <quic_qiancai@...cinc.com> wrote:
>
> On Fri, Apr 22, 2022 at 01:12:37PM -0700, Eric Dumazet wrote:
> > From: Eric Dumazet <edumazet@...gle.com>
> >
> > Logic added in commit f35f821935d8 ("tcp: defer skb freeing after socket
> > lock is released") helped bulk TCP flows to move the cost of skbs
> > frees outside of critical section where socket lock was held.
> >
> > But for RPC traffic, or hosts with RFS enabled, the solution is far from
> > being ideal.
> >
> > For RPC traffic, recvmsg() has to return to user space right after
> > skb payload has been consumed, meaning that BH handler has no chance
> > to pick the skb before recvmsg() thread. This issue is more visible
> > with BIG TCP, as more RPC fit one skb.
> >
> > For RFS, even if BH handler picks the skbs, they are still picked
> > from the cpu on which user thread is running.
> >
> > Ideally, it is better to free the skbs (and associated page frags)
> > on the cpu that originally allocated them.
> >
> > This patch removes the per socket anchor (sk->defer_list) and
> > instead uses a per-cpu list, which will hold more skbs per round.
> >
> > This new per-cpu list is drained at the end of net_action_rx(),
> > after incoming packets have been processed, to lower latencies.
> >
> > In normal conditions, skbs are added to the per-cpu list with
> > no further action. In the (unlikely) cases where the cpu does not
> > run net_action_rx() handler fast enough, we use an IPI to raise
> > NET_RX_SOFTIRQ on the remote cpu.
> >
> > Also, we do not bother draining the per-cpu list from dev_cpu_dead()
> > This is because skbs in this list have no requirement on how fast
> > they should be freed.
> >
> > Note that we can add in the future a small per-cpu cache
> > if we see any contention on sd->defer_lock.
>
> Hmm, we started to see some memory leak reports from kmemleak that have
> been around for hours without being freed since yesterday's linux-next
> tree which included this commit. Any thoughts?
>
> unreferenced object 0xffff400610f55cc0 (size 216):
>   comm "git-remote-http", pid 781180, jiffies 4314091475 (age 4323.740s)
>   hex dump (first 32 bytes):
>     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>     00 c0 7e 87 ff 3f ff ff 00 00 00 00 00 00 00 00  ..~..?..........
>   backtrace:
>      kmem_cache_alloc_node
>      __alloc_skb
>      __tcp_send_ack.part.0
>      tcp_send_ack
>      tcp_cleanup_rbuf
>      tcp_recvmsg_locked
>      tcp_recvmsg
>      inet_recvmsg
>      __sys_recvfrom
>      __arm64_sys_recvfrom
>      invoke_syscall
>      el0_svc_common.constprop.0
>      do_el0_svc
>      el0_svc
>      el0t_64_sync_handler
>      el0t_64_sync
> unreferenced object 0xffff4001e58f0c40 (size 216):
>   comm "git-remote-http", pid 781180, jiffies 4314091483 (age 4323.968s)
>   hex dump (first 32 bytes):
>     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>     00 c0 7e 87 ff 3f ff ff 00 00 00 00 00 00 00 00  ..~..?..........
>   backtrace:
>      kmem_cache_alloc_node
>      __alloc_skb
>      __tcp_send_ack.part.0
>      tcp_send_ack
>      tcp_cleanup_rbuf
>      tcp_recvmsg_locked
>      tcp_recvmsg
>      inet_recvmsg
>      __sys_recvfrom
>      __arm64_sys_recvfrom
>      invoke_syscall
>      el0_svc_common.constprop.0
>      do_el0_svc
>      el0_svc
>      el0t_64_sync_handler
>      el0t_64_sync

Which tree are you using ?

Ido said the leak has been fixed in
https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=f3412b3879b4f7c4313b186b03940d4791345534