From: Gioh Kim <gioh.kim@lge.com>
To: Vlastimil Babka <vbabka@suse.cz>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Rik van Riel <riel@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Mel Gorman <mgorman@suse.de>,
Johannes Weiner <hannes@cmpxchg.org>,
Minchan Kim <minchan@kernel.org>,
Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>,
Zhang Yanfei <zhangyanfei@cn.fujitsu.com>,
"Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>,
Tang Chen <tangchen@cn.fujitsu.com>,
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>,
Wen Congyang <wency@cn.fujitsu.com>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Michal Nazarewicz <mina86@mina86.com>,
Laura Abbott <lauraa@codeaurora.org>,
Heesub Shin <heesub.shin@samsung.com>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
Ritesh Harjani <ritesh.list@gmail.com>,
t.stanislaws@samsung.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 08/10] mm/page_alloc: use get_onbuddy_migratetype() to get buddy list type
Date: Tue, 08 Jul 2014 10:01:23 +0900 [thread overview]
Message-ID: <53BB42E3.4060005@lge.com> (raw)
In-Reply-To: <53BAC37D.3060703@suse.cz>
2014-07-08 i??i ? 12:57, Vlastimil Babka i?' e,?:
> On 07/04/2014 09:57 AM, Joonsoo Kim wrote:
>> When isolating free page, what we want to know is which list
>> the page is linked. If it is linked in isolate migratetype buddy list,
>> we can skip watermark check and freepage counting. And if it is linked
>> in CMA migratetype buddy list, we need to fixup freepage counting. For
>> this purpose, get_onbuddy_migratetype() is more fit and cheap than
>> get_pageblock_migratetype(). So use it.
>
> Hm but you made get_onbuddy_migratetype() work only with CONFIG_MEMORY_ISOLATION. And __isolate_free_page is (despite the name) not at all limited to CONFIG_MEMORY_ISOLATION.
>
Current __isolate_free_page is called by only split_free_page, and split_free_page by isolate_freepages_block.
split_free_page is called only for isolated pages now but It can be changed someday.
I think get_onbuddy_migratetype should work with any situation.
And I think the name of get_onbuddy_migratetype is confused.
Because of _onbuddy_, it might look like that the pages are buddy pages.
I think the original name _freepage_ is proper one.
>> Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
>> ---
>> mm/page_alloc.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>> index e1c4c3e..d9fb8bb 100644
>> --- a/mm/page_alloc.c
>> +++ b/mm/page_alloc.c
>> @@ -1597,7 +1597,7 @@ static int __isolate_free_page(struct page *page, unsigned int order)
>> BUG_ON(!PageBuddy(page));
>>
>> zone = page_zone(page);
>> - mt = get_pageblock_migratetype(page);
>> + mt = get_onbuddy_migratetype(page);
>>
>> if (!is_migrate_isolate(mt)) {
>> /* Obey watermarks as if the page was being allocated */
>>
>
>
--
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>
WARNING: multiple messages have this Message-ID (diff)
From: Gioh Kim <gioh.kim@lge.com>
To: Vlastimil Babka <vbabka@suse.cz>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Rik van Riel <riel@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Mel Gorman <mgorman@suse.de>,
Johannes Weiner <hannes@cmpxchg.org>,
Minchan Kim <minchan@kernel.org>,
Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>,
Zhang Yanfei <zhangyanfei@cn.fujitsu.com>,
"Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>,
Tang Chen <tangchen@cn.fujitsu.com>,
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>,
Wen Congyang <wency@cn.fujitsu.com>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Michal Nazarewicz <mina86@mina86.com>,
Laura Abbott <lauraa@codeaurora.org>,
Heesub Shin <heesub.shin@samsung.com>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
Ritesh Harjani <ritesh.list@gmail.com>,
t.stanislaws@samsung.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 08/10] mm/page_alloc: use get_onbuddy_migratetype() to get buddy list type
Date: Tue, 08 Jul 2014 10:01:23 +0900 [thread overview]
Message-ID: <53BB42E3.4060005@lge.com> (raw)
In-Reply-To: <53BAC37D.3060703@suse.cz>
2014-07-08 오전 12:57, Vlastimil Babka 쓴 글:
> On 07/04/2014 09:57 AM, Joonsoo Kim wrote:
>> When isolating free page, what we want to know is which list
>> the page is linked. If it is linked in isolate migratetype buddy list,
>> we can skip watermark check and freepage counting. And if it is linked
>> in CMA migratetype buddy list, we need to fixup freepage counting. For
>> this purpose, get_onbuddy_migratetype() is more fit and cheap than
>> get_pageblock_migratetype(). So use it.
>
> Hm but you made get_onbuddy_migratetype() work only with CONFIG_MEMORY_ISOLATION. And __isolate_free_page is (despite the name) not at all limited to CONFIG_MEMORY_ISOLATION.
>
Current __isolate_free_page is called by only split_free_page, and split_free_page by isolate_freepages_block.
split_free_page is called only for isolated pages now but It can be changed someday.
I think get_onbuddy_migratetype should work with any situation.
And I think the name of get_onbuddy_migratetype is confused.
Because of _onbuddy_, it might look like that the pages are buddy pages.
I think the original name _freepage_ is proper one.
>> Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
>> ---
>> mm/page_alloc.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>> index e1c4c3e..d9fb8bb 100644
>> --- a/mm/page_alloc.c
>> +++ b/mm/page_alloc.c
>> @@ -1597,7 +1597,7 @@ static int __isolate_free_page(struct page *page, unsigned int order)
>> BUG_ON(!PageBuddy(page));
>>
>> zone = page_zone(page);
>> - mt = get_pageblock_migratetype(page);
>> + mt = get_onbuddy_migratetype(page);
>>
>> if (!is_migrate_isolate(mt)) {
>> /* Obey watermarks as if the page was being allocated */
>>
>
>
next prev parent reply other threads:[~2014-07-08 1:01 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-04 7:57 [PATCH 00/10] fix freepage count problems due to memory isolation Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 01/10] mm/page_alloc: remove unlikely macro on free_one_page() Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-04 12:03 ` Vlastimil Babka
2014-07-04 12:03 ` Vlastimil Babka
2014-07-07 4:58 ` Joonsoo Kim
2014-07-07 4:58 ` Joonsoo Kim
2014-07-04 12:52 ` Michal Nazarewicz
2014-07-04 12:52 ` Michal Nazarewicz
2014-07-04 12:53 ` Michal Nazarewicz
2014-07-04 12:53 ` Michal Nazarewicz
2014-07-04 7:57 ` [PATCH 02/10] mm/page_alloc: correct to clear guard attribute in DEBUG_PAGEALLOC Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-07 14:50 ` Vlastimil Babka
2014-07-07 14:50 ` Vlastimil Babka
2014-07-04 7:57 ` [PATCH 03/10] mm/page_alloc: handle page on pcp correctly if it's pageblock is isolated Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-07 8:25 ` Gioh Kim
2014-07-07 8:25 ` Gioh Kim
2014-07-08 7:18 ` Vlastimil Babka
2014-07-08 7:18 ` Vlastimil Babka
2014-07-07 15:19 ` Vlastimil Babka
2014-07-07 15:19 ` Vlastimil Babka
2014-07-14 6:24 ` Joonsoo Kim
2014-07-14 6:24 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 04/10] mm/page_alloc: carefully free the page on isolate pageblock Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-07 15:43 ` Vlastimil Babka
2014-07-07 15:43 ` Vlastimil Babka
2014-07-04 7:57 ` [PATCH 05/10] mm/page_alloc: optimize and unify pageblock migratetype check in free path Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-07 15:50 ` Vlastimil Babka
2014-07-07 15:50 ` Vlastimil Babka
2014-07-14 6:28 ` Joonsoo Kim
2014-07-14 6:28 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 06/10] mm/page_alloc: separate freepage migratetype interface Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 07/10] mm/page_alloc: store migratetype of the buddy list into freepage correctly Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 08/10] mm/page_alloc: use get_onbuddy_migratetype() to get buddy list type Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-07 15:57 ` Vlastimil Babka
2014-07-07 15:57 ` Vlastimil Babka
2014-07-08 1:01 ` Gioh Kim [this message]
2014-07-08 1:01 ` Gioh Kim
2014-07-08 7:23 ` Vlastimil Babka
2014-07-08 7:23 ` Vlastimil Babka
2014-07-14 6:34 ` Joonsoo Kim
2014-07-14 6:34 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 09/10] mm/page_alloc: fix possible wrongly calculated freepage counter Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-04 7:57 ` [PATCH 10/10] mm/page_alloc: Stop merging pages on non-isolate and isolate buddy list Joonsoo Kim
2014-07-04 7:57 ` Joonsoo Kim
2014-07-04 15:33 ` [PATCH 00/10] fix freepage count problems due to memory isolation Vlastimil Babka
2014-07-04 15:33 ` Vlastimil Babka
2014-07-07 4:49 ` Joonsoo Kim
2014-07-07 4:49 ` Joonsoo Kim
2014-07-07 14:33 ` Vlastimil Babka
2014-07-07 14:33 ` Vlastimil Babka
2014-07-14 6:22 ` Joonsoo Kim
2014-07-14 6:22 ` Joonsoo Kim
2014-07-14 9:49 ` Vlastimil Babka
2014-07-14 9:49 ` Vlastimil Babka
2014-07-15 8:28 ` Joonsoo Kim
2014-07-15 8:28 ` Joonsoo Kim
2014-07-15 8:36 ` Vlastimil Babka
2014-07-15 8:36 ` Vlastimil Babka
2014-07-15 9:39 ` Joonsoo Kim
2014-07-15 10:00 ` Peter Zijlstra
2014-07-16 8:44 ` Joonsoo Kim
2014-07-16 8:43 ` Joonsoo Kim
2014-07-16 8:43 ` Joonsoo Kim
2014-07-16 11:14 ` Vlastimil Babka
2014-07-16 11:14 ` Vlastimil Babka
2014-07-17 6:12 ` Joonsoo Kim
2014-07-17 6:12 ` Joonsoo Kim
2014-07-17 9:14 ` Vlastimil Babka
2014-07-17 9:14 ` Vlastimil Babka
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=53BB42E3.4060005@lge.com \
--to=gioh.kim@lge.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=b.zolnierkie@samsung.com \
--cc=hannes@cmpxchg.org \
--cc=heesub.shin@samsung.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=isimatu.yasuaki@jp.fujitsu.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=lauraa@codeaurora.org \
--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=n-horiguchi@ah.jp.nec.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=ritesh.list@gmail.com \
--cc=srivatsa.bhat@linux.vnet.ibm.com \
--cc=t.stanislaws@samsung.com \
--cc=tangchen@cn.fujitsu.com \
--cc=vbabka@suse.cz \
--cc=wency@cn.fujitsu.com \
--cc=zhangyanfei@cn.fujitsu.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.