Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 24 Oct 2019 13:31:55 +0200
From:   Andrea Parri <parri.andrea@gmail.com>
To:     Dmitry Vyukov <dvyukov@google.com>
Cc:     Christian Brauner <christian.brauner@ubuntu.com>,
        Will Deacon <will@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>, bsingharora@gmail.com,
        Marco Elver <elver@google.com>,
        stable <stable@vger.kernel.org>,
        syzbot <syzbot+c5d03165a1bd1dead0c1@syzkaller.appspotmail.com>,
        syzkaller-bugs <syzkaller-bugs@googlegroups.com>
Subject: Re: [PATCH v6] taskstats: fix data-race
Message-ID: <20191024113155.GA7406@andrea.guest.corp.microsoft.com>
References: <20191009114809.8643-1-christian.brauner@ubuntu.com>
 <20191021113327.22365-1-christian.brauner@ubuntu.com>
 <20191023121603.GA16344@andrea.guest.corp.microsoft.com>
 <CACT4Y+Y86HFnQGHyxv+f32tKDJXnRxmL7jQ3tGxVcksvtK3L7Q@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CACT4Y+Y86HFnQGHyxv+f32tKDJXnRxmL7jQ3tGxVcksvtK3L7Q@mail.gmail.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

> How these later loads can be completely independent of the pointer
> value? They need to obtain the pointer value from somewhere. And this
> can only be done by loaded it. And if a thread loads a pointer and
> then dereferences that pointer, that's a data/address dependency and
> we assume this is now covered by READ_ONCE.

The "dependency" I was considering here is a dependency _between the
load of sig->stats in taskstats_tgid_alloc() and the (program-order)
later loads of *(sig->stats) in taskstats_exit().  Roughly speaking,
such a dependency should correspond to a dependency chain at the asm
or registers level from the first load to the later loads; e.g., in:

  Thread [register r0 contains the address of sig->stats]

  A: LOAD r1,[r0]	// LOAD_ACQUIRE sig->stats
     ...
  B: LOAD r2,[r0]	// LOAD *(sig->stats)
  C: LOAD r3,[r2]

there would be no such dependency from A to C.  Compare, e.g., with:

  Thread [register r0 contains the address of sig->stats]

  A: LOAD r1,[r0]	// LOAD_ACQUIRE sig->stats
     ...
  C: LOAD r3,[r1]	// LOAD *(sig->stats)

AFAICT, there's no guarantee that the compilers will generate such a
dependency from the code under discussion.


> Or these later loads of the pointer can also race with the store? If
> so, I think they also need to use READ_ONCE (rather than turn this earlier
> pointer load into acquire).

AFAICT, _if the LOAD_ACQUIRE reads from the mentioned STORE_RELEASE,
then the former must induce enough synchronization to eliminate data
races (as well as any undesired re-ordering).

TBH, I am not familiar enough with the underlying logic of this code
to say whether that "if .. reads from .." pre-condition holds by the
time those *(sig->stats) execute.

Thanks,
  Andrea