public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Anton Blanchard <anton@samba.org>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Juergen Doelle <jdoelle@de.ibm.com>,
	Linus Torvalds <torvalds@transmeta.com>,
	linux-kernel@vger.kernel.org
Subject: Re: Pls apply this spinlock patch to the kernel
Date: Wed, 31 Oct 2001 00:14:09 +1100	[thread overview]
Message-ID: <20011031001409.A22589@krispykreme> (raw)
In-Reply-To: <3BDD8241.8002B946@de.ibm.com> <E15yG7P-0003Kb-00@the-village.bc.nu>
In-Reply-To: <E15yG7P-0003Kb-00@the-village.bc.nu>


Hi,

> spinlock_t pagecache_lock ____cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
> cache_line_pad;
> 
> where cache_line_pad is an asm(".align") - I would assume that is
> sufficient - Linus ?

In include/asm-ppc64/cache.h I ended up redefining ____cacheline_aligned_in_smp
to avoid the problem of things sharing a cacheline: 

#ifdef CONFIG_SMP
#define ____cacheline_aligned_in_smp __cacheline_aligned
#else
#define ____cacheline_aligned_in_smp
#endif /* CONFIG_SMP */

so that these things end up in the cacheline_aligned section and no variables
share a cacheline. Maybe there are some places where we want to group
variables in the same cacheline, but for consistency I think we should
have:

__cacheline_aligned{,_in_smp}
	variable goes into cacheline_aligned section

____cacheline_aligned{,_in_smp}
	just align to a cacheline

Anton

      parent reply	other threads:[~2001-10-30 13:19 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-10-29 16:22 Pls apply this spinlock patch to the kernel Juergen Doelle
2001-10-29 17:13 ` Linus Torvalds
2001-10-29 17:22 ` Alan Cox
2001-10-29 17:32   ` Linus Torvalds
2001-11-03 19:55     ` Richard Henderson
2001-11-03 20:20       ` Linus Torvalds
2001-11-03 21:01         ` Richard Henderson
2001-11-04  0:43           ` Linus Torvalds
2001-10-30 13:14   ` Anton Blanchard [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=20011031001409.A22589@krispykreme \
    --to=anton@samba.org \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=jdoelle@de.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@transmeta.com \
    /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