All of lore.kernel.org
 help / color / mirror / Atom feed
From: Valentin Schneider <valentin.schneider@arm.com>
To: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Linus Torvalds <torvalds@linux-foundation.org>
Cc: paulmck <paulmck@linux.ibm.com>,
	"Joel Fernandes, Google" <joel@joelfernandes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Alan Stern <stern@rowland.harvard.edu>,
	rostedt <rostedt@goodmis.org>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	Will Deacon <will.deacon@arm.com>,
	David Howells <dhowells@redhat.com>
Subject: Re: [PATCH 1/1] Fix: trace sched switch start/stop racy updates
Date: Sat, 17 Aug 2019 21:03:30 +0100	[thread overview]
Message-ID: <600fd72f-11a0-ff1a-c87a-b26349f6f54a@arm.com> (raw)
In-Reply-To: <1065930957.23914.1566054178444.JavaMail.zimbra@efficios.com>

Apologies to Steve for continuing this thread when all he wanted was moving
an operation inside a mutex...

On 17/08/2019 16:02, Mathieu Desnoyers wrote:
[...]
> However, if the state of "x" can be any pointer value, or a reference
> count value, then not using "WRITE_ONCE()" to store a constant leaves
> the compiler free to perform that store in more than one memory access.
> Based on [1], section "Store tearing", there are situations where this
> happens on x86 in the wild today when storing 64-bit constants: the
> compiler is then free to decide to use two 32-bit immediate store
> instructions.
> 

That's also how I understand things, and it's also one of the points raised
in the compiler barrier section of memory-barriers.txt

Taking this store tearing, or the invented stores - e.g. the branch
optimization pointed out by Linus:

>    if (a)
>       global_var = 1
>    else
>       global_var = 0
> 
> then the compiler had better not turn that into
> 
>      global_var = 0
>      if (a)
>          global_var = 1

AFAICT nothing prevents this from happening inside a critical section (where
the locking primitives provide the right barriers, but that's it). That's
all fine when data is never accessed locklessly, but in the case of locked
writes vs lockless reads, couldn't there be "leaks" of these transient
states? In those cases we would want WRITE_ONCE() for the writes.

So going back to:

> But the reverse is not really true. All a READ_ONCE() says is "I want
> either the old or the new value", and it can get that _without_ being
> paired with a WRITE_ONCE().

AFAIU it's not always the case, since a lone READ_ONCE() could get transient
values.

I'll be honest, it's not 100% clear to me when those optimizations can
actually be done (maybe the branch thingy but the others are dubious), and
it's even less clear when compilers *actually* do it - only that they have
been reported to do it (so it's not made up).

> Thanks,
> 
> Mathieu
> 
> [1] https://lwn.net/Articles/793253/
> 

  reply	other threads:[~2019-08-17 20:04 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-18 10:29 WARNING in tracepoint_probe_register_prio (3) syzbot
2019-08-16  0:11 ` syzbot
2019-08-16 14:26   ` [PATCH 1/1] Fix: trace sched switch start/stop racy updates Mathieu Desnoyers
2019-08-16 16:25     ` Steven Rostedt
2019-08-16 16:48       ` Valentin Schneider
2019-08-16 17:04         ` Steven Rostedt
2019-08-16 17:41           ` Mathieu Desnoyers
2019-08-16 19:18             ` Steven Rostedt
2019-08-16 19:19             ` Alan Stern
2019-08-16 20:44               ` Joel Fernandes
2019-08-16 20:49                 ` Thomas Gleixner
2019-08-16 20:57                   ` Joel Fernandes
2019-08-16 22:27                     ` Valentin Schneider
2019-08-16 22:57                       ` Linus Torvalds
2019-08-17  1:41                         ` Mathieu Desnoyers
2019-08-17  4:52                         ` Paul E. McKenney
2019-08-17  8:28                           ` Linus Torvalds
2019-08-17  8:44                             ` Linus Torvalds
2019-08-17 15:02                               ` Mathieu Desnoyers
2019-08-17 20:03                                 ` Valentin Schneider [this message]
2019-08-17 23:00                                   ` Paul E. McKenney
2019-08-19 10:34                                     ` Valentin Schneider
2019-08-17 22:28                             ` Paul E. McKenney
2019-08-20 14:01                           ` Peter Zijlstra
2019-08-20 20:31                             ` Paul E. McKenney
2019-08-20 20:39                               ` Peter Zijlstra
2019-08-20 20:52                                 ` Paul E. McKenney
2019-08-16 21:04                   ` Linus Torvalds
2019-08-17  1:36                     ` Mathieu Desnoyers
2019-08-17  2:13                       ` Steven Rostedt
2019-08-17 14:40                         ` Mathieu Desnoyers
2019-08-17 15:26                           ` Steven Rostedt
2019-08-17 15:55                             ` Mathieu Desnoyers
2019-08-17 16:40                               ` Steven Rostedt
2019-08-17 22:06                                 ` Paul E. McKenney
2019-08-17  8:08                       ` Linus Torvalds
2019-08-20 13:56                         ` Peter Zijlstra
2019-08-20 20:29                           ` Paul E. McKenney
2019-08-21 10:32                             ` Will Deacon
2019-08-21 13:23                               ` Paul E. McKenney
2019-08-21 13:32                                 ` Will Deacon
2019-08-21 13:56                                   ` Paul E. McKenney
2019-08-21 16:22                                     ` Will Deacon
2019-08-21 15:33                                 ` Peter Zijlstra
2019-08-21 15:48                                   ` Mathieu Desnoyers
2019-08-21 16:14                                     ` Paul E. McKenney
2019-08-21 19:03                                     ` Joel Fernandes
2019-09-09  6:21                           ` Herbert Xu
2019-08-16 20:49                 ` Steven Rostedt
2019-08-16 20:59                   ` Joel Fernandes
2019-08-17  1:25                   ` Mathieu Desnoyers
2019-08-18  9:15                   ` stable markup was " Pavel Machek
2019-08-16 17:19       ` Mathieu Desnoyers
2019-08-16 19:15         ` Steven Rostedt
2019-08-17 14:27           ` Mathieu Desnoyers
2019-08-17 15:42             ` Steven Rostedt
2019-08-17 15:53               ` Mathieu Desnoyers
2019-08-17 16:43                 ` Steven Rostedt
2019-08-16 12:32 ` WARNING in tracepoint_probe_register_prio (3) syzbot
2019-08-16 12:41   ` Sebastian Andrzej Siewior

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=600fd72f-11a0-ff1a-c87a-b26349f6f54a@arm.com \
    --to=valentin.schneider@arm.com \
    --cc=boqun.feng@gmail.com \
    --cc=dhowells@redhat.com \
    --cc=joel@joelfernandes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=paulmck@linux.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=stern@rowland.harvard.edu \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    --subject='Re: [PATCH 1/1] Fix: trace sched switch start/stop racy updates' \
    /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.