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 PHC | |
Open Source and information security mailing list archives
| ||
|
Date: Mon, 1 Aug 2022 21:45:13 +0300 From: Kirill Tkhai <tkhai@...ru> To: Eric Dumazet <edumazet@...gle.com> Cc: Paolo Abeni <pabeni@...hat.com>, "David S. Miller" <davem@...emloft.net>, Linux Kernel Network Developers <netdev@...r.kernel.org> Subject: Re: [PATCH] net: skb content must be visible for lockless skb_peek() and its variations On 01.08.2022 10:39, Eric Dumazet wrote: > On Mon, Aug 1, 2022 at 9:00 AM Kirill Tkhai <tkhai@...ru> wrote: >> >> On 01.08.2022 09:52, Paolo Abeni wrote: >>> On Sun, 2022-07-31 at 23:39 +0300, Kirill Tkhai wrote: >>>> From: Kirill Tkhai <tkhai@...ru> >>>> >>>> Currently, there are no barriers, and skb->xxx update may become invisible on cpu2. >>>> In the below example var2 may point to intial_val0 instead of expected var1: >>>> >>>> [cpu1] [cpu2] >>>> skb->xxx = initial_val0; >>>> ... >>>> skb->xxx = var1; skb = READ_ONCE(prev_skb->next); >>>> <no barrier> <no barrier> >>>> WRITE_ONCE(prev_skb->next, skb); var2 = skb->xxx; >>>> >>>> This patch adds barriers and fixes the problem. Note, that __skb_peek() is not patched, >>>> since it's a lowlevel function, and a caller has to understand the things it does (and >>>> also __skb_peek() is used under queue lock in some places). >>>> >>>> Signed-off-by: Kirill Tkhai <tkhai@...ru> >>>> --- >>>> Hi, David, Eric and other developers, >>>> >>>> picking unix sockets code I found this problem, >>> >>> Could you please report exactly how/where the problem maifests (e.g. >>> the involved call paths/time sequence)? >> >> I didn't get why call paths in the patch description are not enough for you. Please, explain >> what you want. >> >>>> and for me it looks like it exists. If there >>>> are arguments that everything is OK and it's expected, please, explain. >>> >>> I don't see why such barriers are needed for the locked peek/tail >>> variants, as the spin_lock pair implies a full memory barrier. >> >> This is for lockless skb_peek() calls and the patch is called in that way :). For locked skb_peek() >> this is not needed. I'm not sure we need separate skb_peek() and skb_peek_lockless(). Do we? > > We prefer explicit _lockless variants to document the precise points > they are needed. > > A new helper (and its initial usage) will clearly point to the problem > you saw in af_unix. The problem is: unix_stream_sendmsg() unix_stream_read_generic() skb->len = size; skb = skb_peek(); skb_queue_tail(skb); unix_skb_len(skb); <- here we read wrong len > BTW, smp_mb__after_spinlock() in your patch does not really make sense to me. > Please add in your changelog the precise issue you are seeing. What is about queue part, do you recommend to have a separate helper for that? skb_queue_tail_for_lockless()?
Powered by blists - more mailing lists