From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Andrea Arcangeli <aarcange@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>,
Hugh Dickins <hughd@google.com>,
Wu Fengguang <fengguang.wu@intel.com>, Jan Kara <jack@suse.cz>,
Mel Gorman <mgorman@suse.de>,
linux-mm@kvack.org, Andi Kleen <ak@linux.intel.com>,
Matthew Wilcox <willy@linux.intel.com>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
Hillf Danton <dhillf@gmail.com>, Dave Hansen <dave@sr71.net>,
Ning Qu <quning@google.com>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH 11/23] thp, mm: handle tail pages in page_cache_get_speculative()
Date: Sun, 4 Aug 2013 05:17:13 +0300 [thread overview]
Message-ID: <1375582645-29274-12-git-send-email-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <1375582645-29274-1-git-send-email-kirill.shutemov@linux.intel.com>
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
For tail pages we need to take two refcounters:
- ->_count for its head page;
- ->_mapcount for the tail page;
To protect against splitting we take compound lock and re-check that we
still have tail page before taking ->_mapcount reference.
If the page was split we drop ->_count reference from head page and
return 0 to indicate caller that it must retry.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
include/linux/pagemap.h | 26 ++++++++++++++++++++++----
1 file changed, 22 insertions(+), 4 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 47b5082..d459b38 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -161,6 +161,8 @@ void release_pages(struct page **pages, int nr, int cold);
*/
static inline int page_cache_get_speculative(struct page *page)
{
+ struct page *page_head = compound_trans_head(page);
+
VM_BUG_ON(in_interrupt());
#ifdef CONFIG_TINY_RCU
@@ -176,11 +178,11 @@ static inline int page_cache_get_speculative(struct page *page)
* disabling preempt, and hence no need for the "speculative get" that
* SMP requires.
*/
- VM_BUG_ON(page_count(page) == 0);
- atomic_inc(&page->_count);
+ VM_BUG_ON(page_count(page_head) == 0);
+ atomic_inc(&page_head->_count);
#else
- if (unlikely(!get_page_unless_zero(page))) {
+ if (unlikely(!get_page_unless_zero(page_head))) {
/*
* Either the page has been freed, or will be freed.
* In either case, retry here and the caller should
@@ -189,7 +191,23 @@ static inline int page_cache_get_speculative(struct page *page)
return 0;
}
#endif
- VM_BUG_ON(PageTail(page));
+
+ if (unlikely(PageTransTail(page))) {
+ unsigned long flags;
+ int got = 0;
+
+ flags = compound_lock_irqsave(page_head);
+ if (likely(PageTransTail(page))) {
+ atomic_inc(&page->_mapcount);
+ got = 1;
+ }
+ compound_unlock_irqrestore(page_head, flags);
+
+ if (unlikely(!got))
+ atomic_dec(&page_head->_count);
+
+ return got;
+ }
return 1;
}
--
1.8.3.2
--
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:[~2013-08-04 2:14 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-04 2:17 [PATCHv5 00/23] Transparent huge page cache: phase 1, everything but mmap() Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 01/23] radix-tree: implement preload for multiple contiguous elements Kirill A. Shutemov
2013-08-05 11:17 ` Jan Kara
2013-08-06 16:34 ` Matthew Wilcox
2013-08-06 20:17 ` Jan Kara
2013-08-07 16:32 ` Kirill A. Shutemov
2013-08-07 20:00 ` Jan Kara
2013-08-07 20:24 ` Kirill A. Shutemov
2013-08-07 20:36 ` Jan Kara
2013-08-07 21:37 ` Kirill A. Shutemov
2013-08-08 8:45 ` Kirill A. Shutemov
2013-08-08 10:04 ` Jan Kara
2013-08-09 11:13 ` Kirill A. Shutemov
2013-08-09 11:36 ` Jan Kara
2013-08-04 2:17 ` [PATCH 02/23] memcg, thp: charge huge cache pages Kirill A. Shutemov
2013-08-04 8:25 ` Michal Hocko
2013-08-04 2:17 ` [PATCH 03/23] thp: compile-time and sysfs knob for thp pagecache Kirill A. Shutemov
2013-09-05 21:53 ` Ning Qu
2013-09-06 11:33 ` Kirill A. Shutemov
2013-09-06 17:14 ` Ning Qu
2013-08-04 2:17 ` [PATCH 04/23] thp, mm: introduce mapping_can_have_hugepages() predicate Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 05/23] thp: represent file thp pages in meminfo and friends Kirill A. Shutemov
2013-08-30 22:16 ` Ning Qu
2013-09-02 11:36 ` Kirill A. Shutemov
2013-09-02 20:05 ` Ning Qu
2013-08-04 2:17 ` [PATCH 06/23] thp, mm: rewrite add_to_page_cache_locked() to support huge pages Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 07/23] mm: trace filemap: dump page order Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 08/23] block: implement add_bdi_stat() Kirill A. Shutemov
2013-08-05 11:21 ` Jan Kara
2013-08-04 2:17 ` [PATCH 09/23] thp, mm: rewrite delete_from_page_cache() to support huge pages Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 10/23] thp, mm: warn if we try to use replace_page_cache_page() with THP Kirill A. Shutemov
2013-08-04 2:17 ` Kirill A. Shutemov [this message]
2013-08-04 2:17 ` [PATCH 12/23] thp, mm: add event counters for huge page alloc on file write or read Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 13/23] thp, mm: allocate huge pages in grab_cache_page_write_begin() Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 14/23] thp, mm: naive support of thp in generic_perform_write Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 15/23] mm, fs: avoid page allocation beyond i_size on read Kirill A. Shutemov
2013-08-05 0:29 ` NeilBrown
2013-08-04 2:17 ` [PATCH 16/23] thp, mm: handle transhuge pages in do_generic_file_read() Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 17/23] thp, libfs: initial thp support Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 18/23] thp: libfs: introduce simple_thp_release() Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 19/23] truncate: support huge pages Kirill A. Shutemov
2013-08-05 13:29 ` Jan Kara
2013-08-06 20:23 ` Dave Hansen
2013-08-06 20:57 ` Kirill A. Shutemov
2013-08-06 21:55 ` Dave Hansen
2013-08-09 14:39 ` Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 20/23] thp: handle file pages in split_huge_page() Kirill A. Shutemov
2013-08-06 19:09 ` Ning Qu
2013-08-06 21:09 ` Ning Qu
2013-08-06 21:47 ` Ning Qu
2013-08-09 14:46 ` Kirill A. Shutemov
2013-08-09 14:49 ` Ning Qu
2013-08-09 21:24 ` Ning Qu
2013-08-04 2:17 ` [PATCH 21/23] thp: wait_split_huge_page(): serialize over i_mmap_mutex too Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 22/23] thp, mm: split huge page on mmap file page Kirill A. Shutemov
2013-08-08 20:49 ` Khalid Aziz
2013-08-09 14:50 ` Kirill A. Shutemov
2013-08-04 2:17 ` [PATCH 23/23] ramfs: enable transparent huge page cache 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=1375582645-29274-12-git-send-email-kirill.shutemov@linux.intel.com \
--to=kirill.shutemov@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=dave@sr71.net \
--cc=dhillf@gmail.com \
--cc=fengguang.wu@intel.com \
--cc=hughd@google.com \
--cc=jack@suse.cz \
--cc=kirill@shutemov.name \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=quning@google.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@linux.intel.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).