From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <owner-linux-mm@kvack.org>
Received: from mail-io0-f200.google.com (mail-io0-f200.google.com [209.85.223.200])
	by kanga.kvack.org (Postfix) with ESMTP id DEE616B0038
	for <linux-mm@kvack.org>; Sun, 25 Dec 2016 16:51:18 -0500 (EST)
Received: by mail-io0-f200.google.com with SMTP id j76so126516074ioe.3
        for <linux-mm@kvack.org>; Sun, 25 Dec 2016 13:51:18 -0800 (PST)
Received: from mail-it0-x244.google.com (mail-it0-x244.google.com. [2607:f8b0:4001:c0b::244])
        by mx.google.com with ESMTPS id l195si28969216ioe.182.2016.12.25.13.51.18
        for <linux-mm@kvack.org>
        (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128);
        Sun, 25 Dec 2016 13:51:18 -0800 (PST)
Received: by mail-it0-x244.google.com with SMTP id 75so29648882ite.1
        for <linux-mm@kvack.org>; Sun, 25 Dec 2016 13:51:18 -0800 (PST)
MIME-Version: 1.0
In-Reply-To: <20161225030030.23219-3-npiggin@gmail.com>
References: <20161225030030.23219-1-npiggin@gmail.com> <20161225030030.23219-3-npiggin@gmail.com>
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 25 Dec 2016 13:51:17 -0800
Message-ID: <CA+55aFzqgtz-782MmLOjQ2A2nB5YVyLAvveo6G_c85jqqGDA0Q@mail.gmail.com>
Subject: Re: [PATCH 2/2] mm: add PageWaiters indicating tasks are waiting for
 a page bit
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Sender: owner-linux-mm@kvack.org
List-ID: <linux-mm.kvack.org>
To: Nicholas Piggin <npiggin@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>, Bob Peterson <rpeterso@redhat.com>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org>, Steven Whitehouse <swhiteho@redhat.com>, Andrew Lutomirski <luto@kernel.org>, Andreas Gruenbacher <agruenba@redhat.com>, Peter Zijlstra <peterz@infradead.org>, linux-mm <linux-mm@kvack.org>, Mel Gorman <mgorman@techsingularity.net>

On Sat, Dec 24, 2016 at 7:00 PM, Nicholas Piggin <npiggin@gmail.com> wrote:
> Add a new page flag, PageWaiters, to indicate the page waitqueue has
> tasks waiting. This can be tested rather than testing waitqueue_active
> which requires another cacheline load.

Ok, I applied this one too. I think there's room for improvement, but
I don't think it's going to help to just wait another release cycle
and hope something happens.

Example room for improvement from a profile of unlock_page():

   46.44 =E2=94=82      lock   andb $0xfe,(%rdi)
   34.22 =E2=94=82      mov    (%rdi),%rax

this has the old "do atomic op on a byte, then load the whole word"
issue that we used to have with the nasty zone lookup code too. And it
causes a horrible pipeline hickup because the load will not forward
the data from the (partial) store.

 Its' really a misfeature of our asm optimizations of the atomic bit
ops. Using "andb" is slightly smaller, but in this case in particular,
an "andq" would be a ton faster, and the mask still fits in an imm8,
so it's not even hugely larger.

But it might also be a good idea to simply use a "cmpxchg" loop here.
That also gives atomicity guarantees that we don't have with the
"clear bit and then load the value".

Regardless, I think this is worth more people looking at and testing.
And merging it is probably the best way for that to happen.

                Linus

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>