linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: David Laight <david.laight.linux@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	linux-kernel@vger.kernel.org, Nicholas Piggin <npiggin@gmail.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Will Deacon <will@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Alan Stern <stern@rowland.harvard.edu>,
	John Stultz <jstultz@google.com>,
	Neeraj Upadhyay <Neeraj.Upadhyay@amd.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Frederic Weisbecker <frederic@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Uladzislau Rezki <urezki@gmail.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Lai Jiangshan <jiangshanlai@gmail.com>,
	Zqiang <qiang.zhang1211@gmail.com>,
	Ingo Molnar <mingo@redhat.com>, Waiman Long <longman@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Vlastimil Babka <vbabka@suse.cz>,
	maged.michael@gmail.com, Mateusz Guzik <mjguzik@gmail.com>,
	Jonas Oberhauser <jonas.oberhauser@huaweicloud.com>,
	rcu@vger.kernel.org, linux-mm@kvack.org, lkmm@lists.linux.dev,
	Gary Guo <gary@garyguo.net>, Nikita Popov <github@npopov.com>,
	llvm@lists.linux.dev
Subject: Re: [RFC PATCH v4 1/4] compiler.h: Introduce ptr_eq() to preserve address dependency
Date: Thu, 18 Dec 2025 08:51:02 -0500	[thread overview]
Message-ID: <cb55e583-395f-4b83-925f-c341c95903c1@efficios.com> (raw)
In-Reply-To: <20251218090313.33923750@pumpkin>

On 2025-12-18 04:03, David Laight wrote:
[...]
>> + *
>> + * The compiler barrier() is ineffective at fixing this issue. It does
>> + * not prevent the compiler CSE from losing the address dependency:
>> + *
>> + * int fct_2_volatile_barriers(void)
>> + * {
>> + *     int *a, *b;
>> + *
>> + *     do {
>> + *         a = READ_ONCE(p);
>> + *         asm volatile ("" : : : "memory");
>> + *         b = READ_ONCE(p);
>> + *     } while (a != b);
>> + *     asm volatile ("" : : : "memory");  <-- barrier()
>> + *     return *b;
>> + * }
>> + *
>> + * With gcc 14.2 (arm64):
>> + *
>> + * fct_2_volatile_barriers:
>> + *         adrp    x0, .LANCHOR0
>> + *         add     x0, x0, :lo12:.LANCHOR0
>> + * .L2:
>> + *         ldr     x1, [x0]  <-- x1 populated by first load.
>> + *         ldr     x2, [x0]
>> + *         cmp     x1, x2
>> + *         bne     .L2
>> + *         ldr     w0, [x1]  <-- x1 is used for access which should depend on b.
>> + *         ret
>> + *
>> + * On weakly-ordered architectures, this lets CPU speculation use the
>> + * result from the first load to speculate "ldr w0, [x1]" before
>> + * "ldr x2, [x0]".
>> + * Based on the RCU documentation, the control dependency does not
>> + * prevent the CPU from speculating loads.
> 
> I'm not sure that example (of something that doesn't work) is really necessary.
> The simple example of, given:
> 	return a == b ? *a : 0;
> the generated code might speculatively dereference 'b' (not a) before returning
> zero when the pointers are different.

In the past discussion that led to this new API, AFAIU, Linus made it
clear that this counter example needs to be in a comment:

https://lore.kernel.org/lkml/CAHk-=wgBgh5U+dyNaN=+XCdcm2OmgSRbcH4Vbtk8i5ZDGwStSA@mail.gmail.com/

This counter-example is what convinced him that this addresses a real
issue.

Thanks,

Mathieu


-- 
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com


  reply	other threads:[~2025-12-18 13:51 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-18  1:45 [RFC PATCH v4 0/4] Hazard Pointers Mathieu Desnoyers
2025-12-18  1:45 ` [RFC PATCH v4 1/4] compiler.h: Introduce ptr_eq() to preserve address dependency Mathieu Desnoyers
2025-12-18  9:03   ` David Laight
2025-12-18 13:51     ` Mathieu Desnoyers [this message]
2025-12-18 15:54       ` David Laight
2025-12-18 14:27     ` Gary Guo
2025-12-18 16:12       ` David Laight
2025-12-18  1:45 ` [RFC PATCH v4 2/4] Documentation: RCU: Refer to ptr_eq() Mathieu Desnoyers
2025-12-18  1:45 ` [RFC PATCH v4 3/4] hazptr: Implement Hazard Pointers Mathieu Desnoyers
2025-12-18  8:36   ` Boqun Feng
2025-12-18 17:35     ` Mathieu Desnoyers
2025-12-18 20:22       ` Boqun Feng
2025-12-18 23:36         ` Mathieu Desnoyers
2025-12-19  0:25           ` Boqun Feng
2025-12-19  6:06             ` Joel Fernandes
2025-12-19 15:14             ` Mathieu Desnoyers
2025-12-19 15:42               ` Joel Fernandes
2025-12-19 22:19                 ` Mathieu Desnoyers
2025-12-19 22:39                   ` Joel Fernandes
2025-12-21  9:59                     ` Boqun Feng
2025-12-19  0:43       ` Boqun Feng
2025-12-19 14:22         ` Mathieu Desnoyers
2025-12-19  1:22   ` Joel Fernandes
2025-12-18  1:45 ` [RFC PATCH v4 4/4] hazptr: Migrate per-CPU slots to backup slot on context switch Mathieu Desnoyers
2025-12-18 16:20   ` Mathieu Desnoyers
2025-12-18 22:16   ` Boqun Feng
2025-12-19  0:21     ` Mathieu Desnoyers
2025-12-18 10:33 ` [RFC PATCH v4 0/4] Hazard Pointers Joel Fernandes
2025-12-18 17:54   ` Mathieu Desnoyers

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=cb55e583-395f-4b83-925f-c341c95903c1@efficios.com \
    --to=mathieu.desnoyers@efficios.com \
    --cc=Neeraj.Upadhyay@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=bigeasy@linutronix.de \
    --cc=boqun.feng@gmail.com \
    --cc=david.laight.linux@gmail.com \
    --cc=frederic@kernel.org \
    --cc=gary@garyguo.net \
    --cc=github@npopov.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=jiangshanlai@gmail.com \
    --cc=joel@joelfernandes.org \
    --cc=jonas.oberhauser@huaweicloud.com \
    --cc=josh@joshtriplett.org \
    --cc=jstultz@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkmm@lists.linux.dev \
    --cc=llvm@lists.linux.dev \
    --cc=longman@redhat.com \
    --cc=maged.michael@gmail.com \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=mjguzik@gmail.com \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=qiang.zhang1211@gmail.com \
    --cc=rcu@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=stern@rowland.harvard.edu \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=urezki@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=will@kernel.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox