From: Peter Ujfalusi <peter.ujfalusi@ti.com>
To: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Thierry Reding <thierry.reding@avionic-design.de>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Michal Nazarewicz <mina86@mina86.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>,
Kyungmin Park <kyungmin.park@samsung.com>,
Mark Brown <broonie@opensource.wolfsonmicro.com>
Subject: Re: CMA broken in next-20120926
Date: Fri, 28 Sep 2012 11:48:25 +0300 [thread overview]
Message-ID: <50656459.70309@ti.com> (raw)
In-Reply-To: <20120928083722.GM3429@suse.de>
Hi,
On 09/28/2012 11:37 AM, Mel Gorman wrote:
>> I hope this patch fixes the bug. If this patch fixes the problem
>> but has some problem about description or someone has better idea,
>> feel free to modify and resend to akpm, Please.
>>
>
> A full revert is overkill. Can the following patch be tested as a
> potential replacement please?
>
> ---8<---
> mm: compaction: Iron out isolate_freepages_block() and isolate_freepages_range() -fix1
>
> CMA is reported to be broken in next-20120926. Minchan Kim pointed out
> that this was due to nr_scanned != total_isolated in the case of CMA
> because PageBuddy pages are one scan but many isolations in CMA. This
> patch should address the problem.
>
> This patch is a fix for
> mm-compaction-acquire-the-zone-lock-as-late-as-possible-fix-2.patch
>
> Signed-off-by: Mel Gorman <mgorman@suse.de>
linux-next + this patch alone also works for me.
Tested-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
> ---
> mm/compaction.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 8250b69..d6e260a 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -282,6 +282,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
> {
> int nr_scanned = 0, total_isolated = 0;
> struct page *cursor, *valid_page = NULL;
> + unsigned long nr_strict_required = end_pfn - blockpfn;
> unsigned long flags;
> bool locked = false;
>
> @@ -343,10 +344,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
>
> /*
> * If strict isolation is requested by CMA then check that all the
> - * pages scanned were isolated. If there were any failures, 0 is
> + * pages requested were isolated. If there were any failures, 0 is
> * returned and CMA will fail.
> */
> - if (strict && nr_scanned != total_isolated)
> + if (strict && nr_strict_required != total_isolated)
> total_isolated = 0;
>
> if (locked)
>
--
Peter
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-09-28 8:47 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20120927112911.GA25959@avionic-0098.mockup.avionic-design.de>
2012-09-27 22:11 ` CMA broken in next-20120926 Andrew Morton
2012-09-28 5:43 ` Minchan Kim
2012-09-28 6:10 ` Thierry Reding
2012-09-28 7:44 ` Peter Ujfalusi
2012-09-28 7:56 ` Mel Gorman
2012-09-28 8:09 ` Mel Gorman
2012-09-28 8:37 ` Mel Gorman
2012-09-28 8:48 ` Peter Ujfalusi [this message]
2012-09-28 10:27 ` Mel Gorman
2012-09-28 10:32 ` Thierry Reding
2012-09-28 10:38 ` Thierry Reding
2012-09-28 10:51 ` Thierry Reding
2012-09-28 11:07 ` Mel Gorman
2012-09-28 11:39 ` Thierry Reding
2012-09-28 12:43 ` Mel Gorman
2012-10-01 14:24 ` Thierry Reding
2012-10-02 12:48 ` Thierry Reding
2012-10-02 14:41 ` Mel Gorman
2012-10-02 15:03 ` Thierry Reding
2012-10-02 15:12 ` Mel Gorman
2012-10-08 8:06 ` Minchan Kim
2012-10-08 8:48 ` Mel Gorman
2012-10-09 8:40 ` Bartlomiej Zolnierkiewicz
2012-10-09 10:11 ` Mel Gorman
2012-10-09 11:02 ` Thierry Reding
2012-10-09 11:08 ` Bartlomiej Zolnierkiewicz
2012-10-09 11:32 ` Mel Gorman
2012-10-09 11:38 ` Thierry Reding
2012-09-28 10:52 ` Mel Gorman
2012-10-04 14:00 ` [PATCH] mm: compaction: Iron out isolate_freepages_block() and isolate_freepages_range() -fix1 Mel Gorman
2012-10-05 9:59 ` [PATCH] mm: compaction: Iron out isolate_freepages_block() and isolate_freepages_range() -fix2 Mel Gorman
2012-10-08 6:50 ` Minchan Kim
2012-10-08 6:53 ` [PATCH] mm: compaction: Iron out isolate_freepages_block() and isolate_freepages_range() -fix1 Minchan Kim
2012-10-04 14:03 ` [PATCH] mm: compaction: Cache if a pageblock was scanned and no pages were isolated -fix3 Mel Gorman
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=50656459.70309@ti.com \
--to=peter.ujfalusi@ti.com \
--cc=akpm@linux-foundation.org \
--cc=b.zolnierkie@samsung.com \
--cc=broonie@opensource.wolfsonmicro.com \
--cc=kyungmin.park@samsung.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=m.szyprowski@samsung.com \
--cc=mgorman@suse.de \
--cc=mina86@mina86.com \
--cc=minchan@kernel.org \
--cc=thierry.reding@avionic-design.de \
/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;
as well as URLs for NNTP newsgroup(s).