All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@gentwo.de>,
	linux-kernel@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <peterz@infradead.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Matthew Wilcox <willy@infradead.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Rientjes <rientjes@google.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Pekka Enberg <penberg@kernel.org>,
	linux-mm@kvack.org
Subject: Re: [PATCH 1/9] slub: Make PREEMPT_RT support less convoluted
Date: Thu, 18 Aug 2022 17:22:53 +0200	[thread overview]
Message-ID: <Yv5ZTXMmk9LupRae@linutronix.de> (raw)
In-Reply-To: <5679405a-b3c3-6dc5-783f-7ebeda7c9bf0@suse.cz>

On 2022-08-18 16:37:06 [+0200], Vlastimil Babka wrote:
> > The slub fastpath does not interfere with slow path operations and the
> 
> That's true on !PREEMPT_RT because a slowpath operation under
> local_lock_irqsave() will disable interrupts, so there can't be a
> fastpath operation in an interrupt handler appearing in the middle of a
> slowpath operation.
> 
> On PREEMPT_RT local_lock_irqsave() doesn't actually disable interrupts,
> so that can happen. IIRC we learned that the hard way when Mike
> Galbraith was testing early versions of my PREEMPT_RT changes for SLUB.

I think the point is that local_lock_irqsave() does not disable
preemption. So the lock owner (within the local_lock_irqsave() section)
can be preempted and another task can use the fast path which does not
involve the lock and things go boom from here.

Sebastian

  reply	other threads:[~2022-08-18 15:23 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-17 16:26 [PATCH 0/9] Replace PREEMPT_RT ifdefs with preempt_[dis|en]able_nested() Sebastian Andrzej Siewior
2022-08-17 16:26 ` [PATCH 1/9] slub: Make PREEMPT_RT support less convoluted Sebastian Andrzej Siewior
2022-08-18  9:42   ` Christoph Lameter
2022-08-18 14:37     ` Vlastimil Babka
2022-08-18 15:22       ` Sebastian Andrzej Siewior [this message]
2022-08-19 15:04       ` Christoph Lameter
2022-08-25  5:15         ` Hyeonggon Yoo
2022-08-18 17:34   ` Linus Torvalds
2022-08-23 17:15   ` Vlastimil Babka
2022-08-24 13:25     ` Sebastian Andrzej Siewior
2022-08-24 13:54       ` Vlastimil Babka
2022-08-24 13:57         ` Sebastian Andrzej Siewior
2022-08-17 16:26 ` [PATCH 2/9] preempt: Provide preempt_[dis|en]able_nested() Sebastian Andrzej Siewior
2022-08-17 16:26 ` [PATCH 3/9] dentry: Use preempt_[dis|en]able_nested() Sebastian Andrzej Siewior
2022-08-17 16:26 ` [PATCH 4/9] mm/vmstat: " Sebastian Andrzej Siewior
2022-08-17 16:26 ` [PATCH 5/9] mm/debug: Provide VM_WARN_ON_IRQS_ENABLED() Sebastian Andrzej Siewior
2022-08-17 16:27 ` [PATCH 6/9] mm/memcontrol: Replace the PREEMPT_RT conditionals Sebastian Andrzej Siewior
2022-08-17 16:27   ` Sebastian Andrzej Siewior
2022-08-17 16:59   ` Johannes Weiner
2022-08-17 16:59     ` Johannes Weiner
2022-08-18  2:45   ` Muchun Song
2022-08-18  2:45     ` Muchun Song
2022-08-17 16:27 ` [PATCH 7/9] mm/compaction: Get rid of RT ifdeffery Sebastian Andrzej Siewior
2022-08-18  8:55   ` Rasmus Villemoes
2022-08-18 15:51     ` Sebastian Andrzej Siewior
2022-08-24 13:50     ` Thomas Gleixner
2022-08-17 16:27 ` [PATCH 8/9] u64_stats: Streamline the implementation Sebastian Andrzej Siewior
2022-08-17 16:27 ` [PATCH 9/9] u64_stat: Remove the obsolete fetch_irq() variants Sebastian Andrzej Siewior
2022-08-17 18:27   ` Jakub Kicinski
2022-08-18 15:27     ` Sebastian Andrzej Siewior
2022-08-18 16:02       ` Jakub Kicinski
2022-08-18 16:59         ` Sebastian Andrzej Siewior
2022-08-18 17:45           ` Jakub Kicinski
2022-08-22 15:17             ` Sebastian Andrzej Siewior
2022-08-22 18:05               ` Jakub Kicinski
2022-08-25 16:45                 ` Sebastian Andrzej Siewior
2022-08-25 17:30                   ` Jakub Kicinski
2022-08-18  8:20 ` [PATCH 0/9] Replace PREEMPT_RT ifdefs with preempt_[dis|en]able_nested() Peter Zijlstra
2022-08-18 17:41 ` Linus Torvalds

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=Yv5ZTXMmk9LupRae@linutronix.de \
    --to=bigeasy@linutronix.de \
    --cc=akpm@linux-foundation.org \
    --cc=cl@gentwo.de \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=penberg@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.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 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.