LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: Joe Korty <joe.korty@ccur.com>
Cc: linux-kernel@vger.kernel.org, riel@redhat.com, andrea@suse.de
Subject: Re: mlockall and mmap of IO devices don't mix
Date: Fri, 3 Oct 2003 16:06:42 -0700	[thread overview]
Message-ID: <20031003160642.6173f13a.akpm@osdl.org> (raw)
In-Reply-To: <20031003225509.GA26590@rudolph.ccur.com>

Joe Korty <joe.korty@ccur.com> wrote:
>
> > Something like this?
> 
> 
> Sigh.  No go; it *looks* good but my app still locks up....

Oh crap, you're mapping /dev/mem rather than going through a device driver.
/dev/mem isn't setting VM_IO.

Does this little experiment make it go?


diff -puN drivers/char/mem.c~a drivers/char/mem.c
--- 25/drivers/char/mem.c~a	Fri Oct  3 16:04:04 2003
+++ 25-akpm/drivers/char/mem.c	Fri Oct  3 16:04:15 2003
@@ -176,7 +176,7 @@ static int mmap_mem(struct file * file, 
 	/*
 	 * Don't dump addresses that are not real memory to a core file.
 	 */
-	if (uncached)
+//	if (uncached)
 		vma->vm_flags |= VM_IO;
 
 	if (remap_page_range(vma, vma->vm_start, offset, vma->vm_end-vma->vm_start,

_

Course I could test it myself...


I wonder what to do.  Perhaps /dev/mam should set VM_IO if any of the
mapped pages are not valid mem_map-style pageframes.  Or maybe it should
just set VM_IO all the time.

  reply	other threads:[~2003-10-03 23:06 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-10-03 21:44 Joe Korty
2003-10-03 22:23 ` Andrew Morton
2003-10-03 22:55   ` Joe Korty
2003-10-03 23:06     ` Andrew Morton [this message]
2003-10-03 23:28       ` Joe Korty
2003-10-03 23:15     ` Andrew Morton
2003-10-03 23:54       ` Joe Korty
2003-10-04  0:27         ` Andrew Morton
2003-10-04  5:47           ` David S. Miller
2003-10-04  9:29             ` Ingo Oeser
2004-05-21 11:34 ` Mark Hounschell
2004-05-22  2:13   ` Andrew Morton
2004-05-22 10:47     ` Mark Hounschell
2004-05-23 12:58       ` Mark Hounschell
2004-05-25 14:27     ` Joe Korty
2004-05-25 19:47       ` Andrew Morton
2004-05-25 21:31         ` Joe Korty
2004-07-16 21:01         ` Mark Hounschell
     [not found] <CFYv.787.23@gated-at.bofh.it>
2003-10-04  7:02 ` Andi Kleen
2003-10-04  7:42   ` Andrew Morton
2003-10-04  8:29     ` Andi Kleen
2003-10-04  8:47   ` Ingo Oeser
2003-10-04  9:17     ` Andi Kleen
2003-10-04  9:22       ` Russell King
2003-10-04 10:02         ` Ingo Oeser
2003-10-04 10:13           ` Russell King
2003-10-04 14:19             ` Ingo Oeser
2003-10-04 14:32           ` Martin J. Bligh

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=20031003160642.6173f13a.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=andrea@suse.de \
    --cc=joe.korty@ccur.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=riel@redhat.com \
    --subject='Re: mlockall and mmap of IO devices don'\''t mix' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).