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
| ||
|
Message-ID: <CANn89iLNpxXJMyDM-xLE_=N5jZ4jw6tfu+U++LSduUmnX7UE+g@mail.gmail.com> 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
Powered by blists - more mailing lists