From: Simon Jeons <simon.jeons@gmail.com>
To: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@suse.cz>,
linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mel@csn.ul.ie>, Hugh Dickins <hughd@google.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Andi Kleen <andi@firstfloor.org>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 5/9] migrate: enable migrate_pages() to migrate hugepage
Date: Thu, 21 Mar 2013 08:06:06 +0800 [thread overview]
Message-ID: <514A4EEE.1080405@gmail.com> (raw)
In-Reply-To: <1363816793-7eq6pu0l-mutt-n-horiguchi@ah.jp.nec.com>
Hi Naoya,
On 03/21/2013 05:59 AM, Naoya Horiguchi wrote:
> On Wed, Mar 20, 2013 at 08:31:06AM +0800, Simon Jeons wrote:
> ...
>>>>> diff --git v3.8.orig/mm/mempolicy.c v3.8/mm/mempolicy.c
>>>>> index e2df1c1..8627135 100644
>>>>> --- v3.8.orig/mm/mempolicy.c
>>>>> +++ v3.8/mm/mempolicy.c
>>>>> @@ -525,6 +525,27 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
>>>>> return addr != end;
>>>>> }
>>>>>
>>>>> +static void check_hugetlb_pmd_range(struct vm_area_struct *vma, pmd_t *pmd,
>>>>> + const nodemask_t *nodes, unsigned long flags,
>>>>> + void *private)
>>>>> +{
>>>>> +#ifdef CONFIG_HUGETLB_PAGE
>>>>> + int nid;
>>>>> + struct page *page;
>>>>> +
>>>>> + spin_lock(&vma->vm_mm->page_table_lock);
>>>>> + page = pte_page(huge_ptep_get((pte_t *)pmd));
>>>>> + spin_unlock(&vma->vm_mm->page_table_lock);
>>>> I am a bit confused why page_table_lock is used here and why it doesn't
>>>> cover the page usage.
>>> I expected this function to do the same for pmd as check_pte_range() does
>>> for pte, but the above code didn't do it. I should've put spin_unlock
>>> below migrate_hugepage_add(). Sorry for the confusion.
>> I still confuse! Could you explain more in details?
> With the above code, check_hugetlb_pmd_range() checks page_mapcount
> outside the page table lock, but mapcount can be decremented by
> __unmap_hugepage_range(), so there's a race.
> __unmap_hugepage_range() calls page_remove_rmap() inside page table lock,
> so we can avoid this race by doing whole check_hugetlb_pmd_range()'s work
> inside the page table lock.
Why you use page_table_lock instead of split ptlock to protect 2MB?
>
> Thanks,
> Naoya
next prev parent reply other threads:[~2013-03-21 0:06 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-21 19:41 [RFC][PATCH 0/9] extend hugepage migration Naoya Horiguchi
2013-02-21 19:41 ` [PATCH 1/9] migrate: add migrate_entry_wait_huge() Naoya Horiguchi
2013-03-18 14:51 ` Michal Hocko
2013-03-19 0:06 ` Naoya Horiguchi
2013-03-19 23:57 ` Simon Jeons
2013-03-20 21:53 ` Naoya Horiguchi
2013-03-20 23:36 ` Simon Jeons
2013-04-04 4:57 ` Simon Jeons
2013-02-21 19:41 ` [PATCH 2/9] migrate: make core migration code aware of hugepage Naoya Horiguchi
2013-03-18 15:22 ` Michal Hocko
2013-03-18 15:33 ` Michal Hocko
2013-03-19 0:06 ` Naoya Horiguchi
2013-02-21 19:41 ` [PATCH 3/9] soft-offline: use migrate_pages() instead of migrate_huge_page() Naoya Horiguchi
2013-02-27 7:25 ` Chen Gong
2013-02-27 17:06 ` Naoya Horiguchi
2013-02-27 17:57 ` Naoya Horiguchi
2013-02-21 19:41 ` [PATCH 4/9] migrate: clean up migrate_huge_page() Naoya Horiguchi
2013-02-21 19:41 ` [PATCH 5/9] migrate: enable migrate_pages() to migrate hugepage Naoya Horiguchi
2013-03-18 15:40 ` Michal Hocko
2013-03-19 0:07 ` Naoya Horiguchi
2013-03-19 7:11 ` Michal Hocko
2013-03-20 6:12 ` Naoya Horiguchi
2013-03-20 7:41 ` Michal Hocko
2013-03-20 0:31 ` Simon Jeons
2013-03-20 21:59 ` Naoya Horiguchi
2013-03-21 0:06 ` Simon Jeons [this message]
2013-02-21 19:41 ` [PATCH 6/9] migrate: enable move_pages() " Naoya Horiguchi
2013-02-21 19:41 ` [PATCH 7/9] mbind: enable mbind() " Naoya Horiguchi
2013-02-21 19:41 ` [PATCH 8/9] memory-hotplug: enable memory hotplug to handle hugepage Naoya Horiguchi
2013-02-23 7:05 ` Hillf Danton
2013-02-25 16:57 ` Naoya Horiguchi
2013-02-27 7:36 ` Chen Gong
2013-02-27 17:16 ` Naoya Horiguchi
2013-03-18 16:07 ` Michal Hocko
2013-03-20 3:55 ` Naoya Horiguchi
2013-03-20 7:57 ` Michal Hocko
2013-03-20 1:03 ` Simon Jeons
2013-03-20 22:05 ` Naoya Horiguchi
2013-03-20 23:55 ` Simon Jeons
2013-02-21 19:41 ` [PATCH 9/9] remove /proc/sys/vm/hugepages_treat_as_movable Naoya Horiguchi
2013-02-28 6:02 ` KOSAKI Motohiro
2013-02-28 18:16 ` Naoya Horiguchi
2013-03-18 15:51 ` Michal Hocko
2013-03-19 0:07 ` Naoya Horiguchi
2013-03-19 23:43 ` [RFC][PATCH 0/9] extend hugepage migration Simon Jeons
2013-03-20 21:35 ` Naoya Horiguchi
2013-03-20 23:49 ` Simon Jeons
2013-03-21 12:56 ` Michal Hocko
2013-03-21 23:46 ` Simon Jeons
[not found] ` <20130322081532.GC31457@dhcp22.suse.cz>
2013-04-05 1:14 ` Simon Jeons
2013-04-05 8:08 ` Michal Hocko
2013-04-05 9:00 ` Simon Jeons
2013-04-05 9:30 ` Michal Hocko
2013-04-07 0:32 ` Simon Jeons
2013-04-07 14:05 ` KOSAKI Motohiro
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=514A4EEE.1080405@gmail.com \
--to=simon.jeons@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=hughd@google.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=mhocko@suse.cz \
--cc=n-horiguchi@ah.jp.nec.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;
as well as URLs for NNTP newsgroup(s).