All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
To: Anthony Liguori <anthony@codemonkey.ws>
Cc: linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
	mbligh@google.com
Subject: Re: Problem with global_flush_tlb() on i386 in 2.6.22-rc4-mm2
Date: Tue, 19 Jun 2007 21:49:24 -0400	[thread overview]
Message-ID: <20070620014924.GA19080@Krystal> (raw)
In-Reply-To: <46788188.1040403@codemonkey.ws>

* Anthony Liguori (anthony@codemonkey.ws) wrote:
 
> This is actually very conservative seeing as how disabling CR4.PGE 
> should be sufficient to flush global pages on modern processors.  I 
> suspect you're getting preempted while it's running.
> 

Sorry, I just realized that I rejected your preemption explanation
without explaining why:

1 - In my "Text Section" lock code, which is the original place where I
triggered the problem, I take a spinlock around these operations, which
disables preemption.

2 - My sample module plays alone in its own data structures: there is
only one thread accessing the data at a given time (because I do only
one file open at a given time, which I control).

Regards,

Mathieu


-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

      parent reply	other threads:[~2007-06-20  1:59 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-06-19 17:09 Problem with global_flush_tlb() on i386 in 2.6.22-rc4-mm2 Mathieu Desnoyers
2007-06-19 20:01 ` Problem with global_flush_tlb() on i386 (x86_64? too) " Mathieu Desnoyers
2007-06-19 21:10   ` [PATCH] Workaround change_page_attr() and global_flush_tlb() df_list inconsistency on i386 Mathieu Desnoyers
2007-06-20  9:01   ` Problem with global_flush_tlb() on i386 (x86_64? too) in 2.6.22-rc4-mm2 Andi Kleen
2007-06-20 16:46     ` Mathieu Desnoyers
2007-06-20 17:53       ` Andi Kleen
2007-06-20 18:14         ` Mathieu Desnoyers
2007-06-20 19:39         ` [PATCH] fix x86_64-mm-cpa-cache-flush.patch " Mathieu Desnoyers
     [not found]           ` <20070625212553.ec2caba9.akpm@linux-foundation.org>
2007-06-29  4:20             ` Mathieu Desnoyers
2007-06-20  1:23 ` Problem with global_flush_tlb() on i386 " Anthony Liguori
2007-06-20  1:32   ` Mathieu Desnoyers
2007-06-20  1:49   ` Mathieu Desnoyers [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=20070620014924.GA19080@Krystal \
    --to=mathieu.desnoyers@polymtl.ca \
    --cc=akpm@linux-foundation.org \
    --cc=anthony@codemonkey.ws \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mbligh@google.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 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.