All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Cc: "Xuan Zhuo" <xuanzhuo@linux.alibaba.com>,
	netdev@vger.kernel.org, linyunsheng@huawei.com,
	"David S. Miller" <davem@davemloft.net>,
	"Eric Dumazet" <edumazet@google.com>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Antoine Tenart" <atenart@kernel.org>,
	"Alexander Lobakin" <alobakin@pm.me>,
	"Wei Wang" <weiwan@google.com>, "Taehee Yoo" <ap420073@gmail.com>,
	"Björn Töpel" <bjorn@kernel.org>, "Arnd Bergmann" <arnd@arndb.de>,
	"Kumar Kartikeya Dwivedi" <memxor@gmail.com>,
	"Neil Horman" <nhorman@redhat.com>,
	"Dust Li" <dust.li@linux.alibaba.com>
Subject: Re: [PATCH net v2] napi: fix race inside napi_enable
Date: Mon, 18 Oct 2021 15:55:03 -0700	[thread overview]
Message-ID: <20211018155503.74aeaba9@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com> (raw)
In-Reply-To: <YW3t8AGxW6p261hw@us.ibm.com>

On Mon, 18 Oct 2021 14:58:08 -0700 Sukadev Bhattiprolu wrote:
> >                       CPU0       |                   CPU1       | napi.state
> > ===============================================================================
> > napi_disable()                   |                              | SCHED | NPSVC
> > napi_enable()                    |                              |
> > {                                |                              |
> >     smp_mb__before_atomic();     |                              |
> >     clear_bit(SCHED, &n->state); |                              | NPSVC
> >                                  | napi_schedule_prep()         | SCHED | NPSVC
> >                                  | napi_poll()                  |
> >                                  |   napi_complete_done()       |
> >                                  |   {                          |
> >                                  |      if (n->state & (NPSVC | | (1)
> >                                  |               _BUSY_POLL)))  |
> >                                  |           return false;      |
> >                                  |     ................         |
> >                                  |   }                          | SCHED | NPSVC
> >                                  |                              |
> >     clear_bit(NPSVC, &n->state); |                              | SCHED
> > }                                |                              |  
> 
> So its possible that after cpu0 cleared SCHED, cpu1 could have set it
> back and we are going to use cmpxchg() to detect and retry right? If so,

This is a state diagram before the change. There's no cmpxchg() here.
        
> > napi_schedule_prep()             |                              | SCHED | MISSED (2)
> > 
> > (1) Here return direct. Because of NAPI_STATE_NPSVC exists.
> > (2) NAPI_STATE_SCHED exists. So not add napi.poll_list to sd->poll_list
> > 
> > Since NAPI_STATE_SCHED already exists and napi is not in the
> > sd->poll_list queue, NAPI_STATE_SCHED cannot be cleared and will always
> > exist.
> > 
> > 1. This will cause this queue to no longer receive packets.
> > 2. If you encounter napi_disable under the protection of rtnl_lock, it
> >    will cause the entire rtnl_lock to be locked, affecting the overall
> >    system.
> > 
> > This patch uses cmpxchg to implement napi_enable(), which ensures that
> > there will be no race due to the separation of clear two bits.
> > 
> > Fixes: 2d8bff12699abc ("netpoll: Close race condition between poll_one_napi and napi_disable")
> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> > Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
> > ---
> >  net/core/dev.c | 16 ++++++++++------
> >  1 file changed, 10 insertions(+), 6 deletions(-)
> > 
> > diff --git a/net/core/dev.c b/net/core/dev.c
> > index 74fd402d26dd..7ee9fecd3aff 100644
> > --- a/net/core/dev.c
> > +++ b/net/core/dev.c
> > @@ -6923,12 +6923,16 @@ EXPORT_SYMBOL(napi_disable);
> >   */
> >  void napi_enable(struct napi_struct *n)
> >  {
> > -	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
> > -	smp_mb__before_atomic();
> > -	clear_bit(NAPI_STATE_SCHED, &n->state);
> > -	clear_bit(NAPI_STATE_NPSVC, &n->state);
> > -	if (n->dev->threaded && n->thread)
> > -		set_bit(NAPI_STATE_THREADED, &n->state);
> > +	unsigned long val, new;
> > +
> > +	do {
> > +		val = READ_ONCE(n->state);
> > +		BUG_ON(!test_bit(NAPI_STATE_SCHED, &val));  
> 
> is this BUG_ON valid/needed? We could have lost the cmpxchg() and
> the other thread could have set NAPI_STATE_SCHED?

The BUG_ON() is here to make sure that when napi_enable() is called the
napi instance was dormant, i.e. disabled. We have "STATE_SCHED" bit set
on disabled NAPIs because that bit means ownership. Whoever disabled
the NAPI owns it.

That BUG_ON() could have been taken outside of the loop, there's no
point re-checking on every try. 

Are you seeing NAPI-related failures? We had at least 3 reports in the
last two weeks of strange failures which look like NAPI state getting
corrupted on net-next...

  reply	other threads:[~2021-10-18 22:55 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-18  8:52 Xuan Zhuo
2021-09-20  8:50 ` patchwork-bot+netdevbpf
2021-09-20 19:20 ` Jakub Kicinski
2021-09-22  6:47   ` Xuan Zhuo
2021-09-23 13:14     ` Jakub Kicinski
     [not found]       ` <1632404456.506512-1-xuanzhuo@linux.alibaba.com>
2021-09-23 14:54         ` Jakub Kicinski
2021-10-18 21:58 ` Sukadev Bhattiprolu
2021-10-18 22:55   ` Jakub Kicinski [this message]
2021-10-18 23:36     ` Dany Madden
2021-10-18 23:47       ` Jakub Kicinski
2021-10-19  0:01         ` Sukadev Bhattiprolu
2021-10-22  3:16       ` Sukadev Bhattiprolu
2021-10-25 17:36         ` Jakub Kicinski

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211018155503.74aeaba9@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com \
    --to=kuba@kernel.org \
    --cc=alobakin@pm.me \
    --cc=ap420073@gmail.com \
    --cc=arnd@arndb.de \
    --cc=atenart@kernel.org \
    --cc=bjorn@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dust.li@linux.alibaba.com \
    --cc=edumazet@google.com \
    --cc=linyunsheng@huawei.com \
    --cc=memxor@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=nhorman@redhat.com \
    --cc=sukadev@linux.ibm.com \
    --cc=weiwan@google.com \
    --cc=xuanzhuo@linux.alibaba.com \
    --subject='Re: [PATCH net v2] napi: fix race inside napi_enable' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.