dri-devel Archive on lore.kernel.org
 help / color / Atom feed
From: "Paul E. McKenney" <paulmck@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Juri Lelli <juri.lelli@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Lai Jiangshan <jiangshanlai@gmail.com>,
	dri-devel <dri-devel@lists.freedesktop.org>,
	Ben Segall <bsegall@google.com>, Linux-MM <linux-mm@kvack.org>,
	"open list:KERNEL SELFTEST FRAMEWORK"
	<linux-kselftest@vger.kernel.org>,
	linux-hexagon@vger.kernel.org, Will Deacon <will@kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Anton Ivanov <anton.ivanov@cambridgegreys.com>,
	linux-arch <linux-arch@vger.kernel.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Brian Cain <bcain@codeaurora.org>,
	Richard Weinberger <richard@nod.at>,
	Russell King <linux@armlinux.org.uk>,
	David Airlie <airlied@linux.ie>, Ingo Molnar <mingo@redhat.com>,
	Geert Uytterhoeven <geert@linux-m68k.org>,
	Mel Gorman <mgorman@suse.de>,
	intel-gfx <intel-gfx@lists.freedesktop.org>,
	Matt Turner <mattst88@gmail.com>,
	Valentin Schneider <valentin.schneider@arm.com>,
	linux-xtensa@linux-xtensa.org, Shuah Khan <shuah@kernel.org>,
	Jeff Dike <jdike@addtoit.com>,
	linux-um <linux-um@lists.infradead.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	rcu@vger.kernel.org, linux-m68k <linux-m68k@lists.linux-m68k.org>,
	Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
	Rodrigo Vivi <rodrigo.vivi@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>,
	Richard Henderson <rth@twiddle.net>,
	Chris Zankel <chris@zankel.net>,
	Max Filippov <jcmvbkbc@gmail.com>,
	LKML <linux-kernel@vger.kernel.org>,
	alpha <linux-alpha@vger.kernel.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Daniel Bristot de Oliveira <bristot@redhat.com>
Subject: Re: [patch 00/13] preempt: Make preempt count unconditional
Date: Tue, 15 Sep 2020 10:25:50 -0700
Message-ID: <20200915172550.GO29330@paulmck-ThinkPad-P72> (raw)
In-Reply-To: <CAHk-=win80rdof8Pb=5k6gT9j_v+hz-TQzKPVastZDvBe9RimQ@mail.gmail.com>

On Mon, Sep 14, 2020 at 01:59:15PM -0700, Linus Torvalds wrote:
> On Mon, Sep 14, 2020 at 1:45 PM Thomas Gleixner <tglx@linutronix.de> wrote:
> >
> > Recently merged code does:
> >
> >          gfp = preemptible() ? GFP_KERNEL : GFP_ATOMIC;
> >
> > Looks obviously correct, except for the fact that preemptible() is
> > unconditionally false for CONFIF_PREEMPT_COUNT=n, i.e. all allocations in
> > that code use GFP_ATOMIC on such kernels.
> 
> I don't think this is a good reason to entirely get rid of the no-preempt thing.
> 
> The above is just garbage. It's bogus. You can't do it.
> 
> Blaming the no-preempt code for this bug is extremely unfair, imho.
> 
> And the no-preempt code does help make for much better code generation
> for simple spinlocks.
> 
> Where is that horribly buggy recent code? It's not in that exact
> format, certainly, since 'grep' doesn't find it.

It would be convenient for that "gfp =" code to work, as this would
allow better cache locality while invoking RCU callbacks, and would
further provide better robustness to callback floods.  The full story
is quite long, but here are alternatives have not yet been proven to be
abject failures:

1.	Use workqueues to do the allocations in a clean context.
	While waiting for the allocations, the callbacks are queued
	in the old cache-busting manner.  This functions correctly,
	but in the meantime (which on busy systems can be some time)
	the cache locality and robustness are lost.

2.	Provide the ability to allocate memory in raw atomic context.
	This is extremely effective, especially when used in combination
	with #1 above, but as you might suspect, the MM guys don't like
	it much.

In contrast, with Thomas's patch series, call_rcu() and kvfree_rcu()
could just look at preemptible() to see whether or not it was safe to
allocate memory, even in !PREEMPT kernels -- and in the common case,
it almost always would be safe.  It is quite possible that this approach
would work in isolation, or failing that, that adding #1 above would do
the trick.

I understand that this is all very hand-wavy, and I do apologize for that.
If you really want the full sad story with performance numbers and the
works, let me know!

							Thanx, Paul
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

      parent reply index

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-14 20:42 Thomas Gleixner
2020-09-14 20:42 ` [patch 01/13] lib/debug: Remove pointless ARCH_NO_PREEMPT dependencies Thomas Gleixner
2020-09-14 20:42 ` [patch 02/13] preempt: Make preempt count unconditional Thomas Gleixner
2020-09-14 20:42 ` [patch 03/13] preempt: Clenaup PREEMPT_COUNT leftovers Thomas Gleixner
2020-09-14 20:42 ` [patch 04/13] lockdep: " Thomas Gleixner
2020-09-15 16:11   ` Will Deacon
2020-09-14 20:42 ` [patch 05/13] mm/pagemap: " Thomas Gleixner
2020-09-14 20:42 ` [patch 06/13] locking/bitspinlock: " Thomas Gleixner
2020-09-15 16:10   ` Will Deacon
2020-09-14 20:42 ` [patch 07/13] uaccess: " Thomas Gleixner
2020-09-14 20:42 ` [patch 08/13] sched: " Thomas Gleixner
2020-09-14 20:42 ` [patch 09/13] ARM: " Thomas Gleixner
2020-09-14 20:42 ` [patch 10/13] xtensa: " Thomas Gleixner
2020-09-14 20:42 ` [patch 11/13] drm/i915: " Thomas Gleixner
2020-09-14 20:42 ` [patch 12/13] rcutorture: " Thomas Gleixner
2020-09-14 20:42 ` [patch 13/13] preempt: Remove PREEMPT_COUNT from Kconfig Thomas Gleixner
2020-09-14 20:54 ` [patch 00/13] preempt: Make preempt count unconditional Steven Rostedt
2020-09-14 20:59 ` Linus Torvalds
2020-09-14 21:55   ` Thomas Gleixner
2020-09-14 22:24     ` Linus Torvalds
2020-09-14 22:37       ` Linus Torvalds
2020-09-15  3:21         ` [PATCH] crypto: lib/chacha20poly1305 - Set SG_MITER_ATOMIC unconditionally Herbert Xu
2020-09-15  6:20         ` [patch 00/13] preempt: Make preempt count unconditional Ard Biesheuvel
2020-09-15  6:22           ` Herbert Xu
2020-09-15  6:39             ` Linus Torvalds
     [not found]               ` <87een35woz.fsf@nanos.tec.linutronix.de>
2020-09-15 17:29                 ` Linus Torvalds
     [not found]       ` <87bli75t7v.fsf@nanos.tec.linutronix.de>
2020-09-15 17:35         ` Linus Torvalds
2020-09-15 19:57           ` Thomas Gleixner
2020-09-16 18:34             ` Linus Torvalds
2020-09-16  7:37           ` Daniel Vetter
2020-09-16 15:29             ` Paul E. McKenney
2020-09-16 18:32               ` Linus Torvalds
2020-09-16 20:43                 ` Paul E. McKenney
2020-09-17  6:38                 ` Ard Biesheuvel
2020-09-16 20:29               ` Daniel Vetter
2020-09-16 20:58                 ` Paul E. McKenney
2020-09-16 21:43                   ` Daniel Vetter
2020-09-16 22:39                     ` Paul E. McKenney
2020-09-17  7:52                       ` Daniel Vetter
2020-09-17 16:28                         ` Paul E. McKenney
2020-09-29  8:19                     ` Michal Hocko
2020-09-29  8:19                       ` Michal Hocko
2020-09-29  8:20                       ` Michal Hocko
2020-09-29  8:21                       ` Michal Hocko
2020-09-29  8:23                       ` Michal Hocko
2020-09-29  9:00                       ` Daniel Vetter
2020-09-29 14:54                         ` Michal Hocko
2020-09-16 19:23     ` Matthew Wilcox
2020-09-16 20:48       ` Paul E. McKenney
2020-09-15 17:25   ` Paul E. McKenney [this message]

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=20200915172550.GO29330@paulmck-ThinkPad-P72 \
    --to=paulmck@kernel.org \
    --cc=airlied@linux.ie \
    --cc=akpm@linux-foundation.org \
    --cc=anton.ivanov@cambridgegreys.com \
    --cc=bcain@codeaurora.org \
    --cc=bigeasy@linutronix.de \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=chris@zankel.net \
    --cc=dietmar.eggemann@arm.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=geert@linux-m68k.org \
    --cc=ink@jurassic.park.msu.ru \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=jcmvbkbc@gmail.com \
    --cc=jdike@addtoit.com \
    --cc=jiangshanlai@gmail.com \
    --cc=josh@joshtriplett.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-alpha@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-hexagon@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-m68k@lists.linux-m68k.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-um@lists.infradead.org \
    --cc=linux-xtensa@linux-xtensa.org \
    --cc=linux@armlinux.org.uk \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mattst88@gmail.com \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rcu@vger.kernel.org \
    --cc=richard@nod.at \
    --cc=rodrigo.vivi@intel.com \
    --cc=rostedt@goodmis.org \
    --cc=rth@twiddle.net \
    --cc=shuah@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.org \
    --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

dri-devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/dri-devel/0 dri-devel/git/0.git
	git clone --mirror https://lore.kernel.org/dri-devel/1 dri-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dri-devel dri-devel/ https://lore.kernel.org/dri-devel \
		dri-devel@lists.freedesktop.org
	public-inbox-index dri-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.freedesktop.lists.dri-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git