From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Hugh Dickins <hughd@google.com>,
Dave Hansen <dave.hansen@intel.com>, Mel Gorman <mgorman@suse.de>,
Rik van Riel <riel@redhat.com>, Christoph Lameter <cl@gentwo.org>,
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
Steve Capper <steve.capper@linaro.org>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@suse.cz>,
Jerome Marchand <jmarchan@redhat.com>,
Sasha Levin <sasha.levin@oracle.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCHv5 22/28] thp: implement split_huge_pmd()
Date: Wed, 20 May 2015 17:38:43 +0300 [thread overview]
Message-ID: <20150520143843.GB13921@node.dhcp.inet.fi> (raw)
In-Reply-To: <555AF37A.2060709@suse.cz>
On Tue, May 19, 2015 at 10:25:30AM +0200, Vlastimil Babka wrote:
> On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote:
> >Original split_huge_page() combined two operations: splitting PMDs into
> >tables of PTEs and splitting underlying compound page. This patch
> >implements split_huge_pmd() which split given PMD without splitting
> >other PMDs this page mapped with or underlying compound page.
> >
> >Without tail page refcounting, implementation of split_huge_pmd() is
> >pretty straight-forward.
> >
> >Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> >Tested-by: Sasha Levin <sasha.levin@oracle.com>
> >---
> > include/linux/huge_mm.h | 11 ++++-
> > mm/huge_memory.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++++
> > 2 files changed, 118 insertions(+), 1 deletion(-)
> >
> >diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> >index 0382230b490f..b7844c73b7db 100644
> >--- a/include/linux/huge_mm.h
> >+++ b/include/linux/huge_mm.h
> >@@ -94,7 +94,16 @@ extern unsigned long transparent_hugepage_flags;
> >
> > #define split_huge_page_to_list(page, list) BUILD_BUG()
> > #define split_huge_page(page) BUILD_BUG()
> >-#define split_huge_pmd(__vma, __pmd, __address) BUILD_BUG()
> >+
> >+void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
> >+ unsigned long address);
> >+
> >+#define split_huge_pmd(__vma, __pmd, __address) \
> >+ do { \
> >+ pmd_t *____pmd = (__pmd); \
> >+ if (unlikely(pmd_trans_huge(*____pmd))) \
>
> Given that most of calls to split_huge_pmd() appear to be in
> if (pmd_trans_huge(...)) branches, this unlikely() seems counter-productive.
Fair enough.
> >+void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
> >+ unsigned long address)
> >+{
> >+ spinlock_t *ptl;
> >+ struct mm_struct *mm = vma->vm_mm;
> >+ unsigned long haddr = address & HPAGE_PMD_MASK;
> >+
> >+ mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
> >+ ptl = pmd_lock(mm, pmd);
> >+ if (likely(pmd_trans_huge(*pmd)))
>
> This likely is likely useless :)
No, it's not. We check the pmd with pmd_trans_huge() under ptl for the
first time. And __split_huge_pmd_locked() assumes pmd is huge.
> >+ __split_huge_pmd_locked(vma, pmd, haddr);
> >+ spin_unlock(ptl);
> >+ mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
> >+}
> >+
--
Kirill A. Shutemov
--
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:[~2015-05-20 14:38 UTC|newest]
Thread overview: 100+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-04-23 21:03 [PATCHv5 00/28] THP refcounting redesign Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 01/28] mm, proc: adjust PSS calculation Kirill A. Shutemov
2015-04-29 15:49 ` Jerome Marchand
2015-05-14 14:12 ` Vlastimil Babka
2015-05-15 10:56 ` Kirill A. Shutemov
2015-05-15 11:33 ` Vlastimil Babka
2015-05-15 11:43 ` Kirill A. Shutemov
2015-05-15 12:37 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 02/28] rmap: add argument to charge compound page Kirill A. Shutemov
2015-04-29 15:53 ` Jerome Marchand
2015-04-30 11:52 ` Kirill A. Shutemov
2015-05-14 16:07 ` Vlastimil Babka
2015-05-15 11:14 ` Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 03/28] memcg: adjust to support new THP refcounting Kirill A. Shutemov
2015-05-15 7:44 ` Vlastimil Babka
2015-05-15 11:18 ` Kirill A. Shutemov
2015-05-15 14:57 ` Dave Hansen
2015-05-16 23:17 ` Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 04/28] mm, thp: adjust conditions when we can reuse the page on WP fault Kirill A. Shutemov
2015-04-29 15:54 ` Jerome Marchand
2015-05-15 9:15 ` Vlastimil Babka
2015-05-15 11:21 ` Kirill A. Shutemov
2015-05-15 11:35 ` Vlastimil Babka
2015-05-15 13:29 ` Kirill A. Shutemov
2015-05-19 13:00 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 05/28] mm: adjust FOLL_SPLIT for new refcounting Kirill A. Shutemov
2015-05-15 11:05 ` Vlastimil Babka
2015-05-15 11:36 ` Kirill A. Shutemov
2015-05-15 12:01 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 06/28] mm: handle PTE-mapped tail pages in gerneric fast gup implementaiton Kirill A. Shutemov
2015-04-29 15:56 ` Jerome Marchand
2015-05-15 12:46 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 07/28] thp, mlock: do not allow huge pages in mlocked area Kirill A. Shutemov
2015-04-29 15:58 ` Jerome Marchand
2015-05-15 12:56 ` Vlastimil Babka
2015-05-15 13:41 ` Kirill A. Shutemov
2015-05-19 14:37 ` Vlastimil Babka
2015-05-20 12:10 ` Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 08/28] khugepaged: ignore pmd tables with THP mapped with ptes Kirill A. Shutemov
2015-04-29 15:59 ` Jerome Marchand
2015-05-15 12:59 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 09/28] thp: rename split_huge_page_pmd() to split_huge_pmd() Kirill A. Shutemov
2015-04-29 16:00 ` Jerome Marchand
2015-05-15 13:08 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 10/28] mm, vmstats: new THP splitting event Kirill A. Shutemov
2015-04-29 16:02 ` Jerome Marchand
2015-05-15 13:10 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 11/28] mm: temporally mark THP broken Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 12/28] thp: drop all split_huge_page()-related code Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 13/28] mm: drop tail page refcounting Kirill A. Shutemov
2015-05-18 9:48 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 14/28] futex, thp: remove special case for THP in get_futex_key Kirill A. Shutemov
2015-05-18 11:49 ` Vlastimil Babka
2015-05-18 12:13 ` Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 15/28] ksm: prepare to new THP semantics Kirill A. Shutemov
2015-05-18 12:41 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 16/28] mm, thp: remove compound_lock Kirill A. Shutemov
2015-04-29 16:11 ` Jerome Marchand
2015-04-30 11:58 ` Kirill A. Shutemov
2015-05-18 12:57 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 17/28] mm, thp: remove infrastructure for handling splitting PMDs Kirill A. Shutemov
2015-04-29 16:14 ` Jerome Marchand
2015-04-30 12:03 ` Kirill A. Shutemov
2015-05-18 13:40 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 18/28] x86, " Kirill A. Shutemov
2015-04-29 9:13 ` Aneesh Kumar K.V
2015-04-23 21:03 ` [PATCHv5 19/28] mm: store mapcount for compound page separately Kirill A. Shutemov
2015-05-18 14:32 ` Vlastimil Babka
2015-05-19 3:55 ` Kirill A. Shutemov
2015-05-19 9:01 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 20/28] mm: differentiate page_mapped() from page_mapcount() for compound pages Kirill A. Shutemov
2015-04-29 16:20 ` Jerome Marchand
2015-04-30 12:06 ` Kirill A. Shutemov
2015-05-18 15:35 ` Vlastimil Babka
2015-05-19 4:00 ` Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 21/28] mm, numa: skip PTE-mapped THP on numa fault Kirill A. Shutemov
2015-04-23 21:03 ` [PATCHv5 22/28] thp: implement split_huge_pmd() Kirill A. Shutemov
2015-05-19 8:25 ` Vlastimil Babka
2015-05-20 14:38 ` Kirill A. Shutemov [this message]
2015-04-23 21:03 ` [PATCHv5 23/28] thp: add option to setup migration entiries during PMD split Kirill A. Shutemov
2015-05-19 13:55 ` Vlastimil Babka
2015-04-23 21:03 ` [PATCHv5 24/28] thp, mm: split_huge_page(): caller need to lock page Kirill A. Shutemov
2015-05-19 13:55 ` Vlastimil Babka
2015-04-23 21:04 ` [PATCHv5 25/28] thp: reintroduce split_huge_page() Kirill A. Shutemov
2015-05-19 12:43 ` Vlastimil Babka
2015-04-23 21:04 ` [PATCHv5 26/28] thp: introduce deferred_split_huge_page() Kirill A. Shutemov
2015-05-19 13:54 ` Vlastimil Babka
2015-04-23 21:04 ` [PATCHv5 27/28] mm: re-enable THP Kirill A. Shutemov
2015-04-23 21:04 ` [PATCHv5 28/28] thp: update documentation Kirill A. Shutemov
2015-04-27 23:03 ` [PATCHv5 00/28] THP refcounting redesign Andrew Morton
2015-04-27 23:33 ` Kirill A. Shutemov
2015-04-30 8:25 ` [RFC PATCH 0/3] Remove _PAGE_SPLITTING from ppc64 Aneesh Kumar K.V
2015-04-30 8:25 ` [RFC PATCH 1/3] mm/thp: Use pmdp_splitting_flush_notify to clear pmd on splitting Aneesh Kumar K.V
2015-04-30 13:30 ` Kirill A. Shutemov
2015-04-30 15:59 ` Aneesh Kumar K.V
2015-04-30 16:47 ` Aneesh Kumar K.V
2015-04-30 8:25 ` [RFC PATCH 2/3] powerpc/thp: Remove _PAGE_SPLITTING and related code Aneesh Kumar K.V
2015-04-30 8:25 ` [RFC PATCH 3/3] mm/thp: Add new function to clear pmd on collapse Aneesh Kumar K.V
2015-05-15 8:55 ` [PATCHv5 00/28] THP refcounting redesign Vlastimil Babka
2015-05-15 13:31 ` Kirill A. Shutemov
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=20150520143843.GB13921@node.dhcp.inet.fi \
--to=kirill@shutemov.name \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=cl@gentwo.org \
--cc=dave.hansen@intel.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jmarchan@redhat.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.cz \
--cc=n-horiguchi@ah.jp.nec.com \
--cc=riel@redhat.com \
--cc=sasha.levin@oracle.com \
--cc=steve.capper@linaro.org \
--cc=vbabka@suse.cz \
/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).