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 <matthew.r.wilcox@intel.com>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
Hillf Danton <dhillf@gmail.com>, Dave Hansen <dave@sr71.net>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv3, RFC 17/34] thp, mm: implement grab_thp_write_begin()
Date: Fri, 5 Apr 2013 14:59:41 +0300 [thread overview]
Message-ID: <1365163198-29726-18-git-send-email-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <1365163198-29726-1-git-send-email-kirill.shutemov@linux.intel.com>
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
The function is grab_cache_page_write_begin() twin but it tries to
allocate huge page at given position aligned to HPAGE_CACHE_NR.
If, for some reason, it's not possible allocate a huge page at this
possition, it returns NULL. Caller should take care of fallback to
small pages.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
include/linux/pagemap.h | 10 ++++++
mm/filemap.c | 89 +++++++++++++++++++++++++++++++++++++++--------
2 files changed, 85 insertions(+), 14 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bd07fc1..5a7dda9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -271,6 +271,16 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct page *grab_thp_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags);
+#else
+static inline struct page *grab_thp_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags)
+{
+ return NULL;
+}
+#endif
/*
* Returns locked page at given index in given cache, creating it if needed.
diff --git a/mm/filemap.c b/mm/filemap.c
index 7b4736c..bcb679c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2290,16 +2290,17 @@ out:
EXPORT_SYMBOL(generic_file_direct_write);
/*
- * Find or create a page at the given pagecache position. Return the locked
- * page. This function is specifically for buffered writes.
+ * Returns true if the page was found in page cache and
+ * false if it had to allocate a new page.
*/
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
- pgoff_t index, unsigned flags)
+static bool __grab_cache_page_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags, unsigned int order,
+ struct page **page)
{
int status;
gfp_t gfp_mask;
- struct page *page;
gfp_t gfp_notmask = 0;
+ int found = true;
gfp_mask = mapping_gfp_mask(mapping);
if (mapping_cap_account_dirty(mapping))
@@ -2307,27 +2308,87 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
if (flags & AOP_FLAG_NOFS)
gfp_notmask = __GFP_FS;
repeat:
- page = find_lock_page(mapping, index);
- if (page)
+ *page = find_lock_page(mapping, index);
+ if (*page)
goto found;
- page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
- if (!page)
- return NULL;
- status = add_to_page_cache_lru(page, mapping, index,
+ found = false;
+ if (order)
+ *page = alloc_pages(gfp_mask & ~gfp_notmask, order);
+ else
+ *page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
+ if (!*page)
+ return false;
+ status = add_to_page_cache_lru(*page, mapping, index,
GFP_KERNEL & ~gfp_notmask);
if (unlikely(status)) {
- page_cache_release(page);
+ page_cache_release(*page);
if (status == -EEXIST)
goto repeat;
- return NULL;
+ *page = NULL;
+ return false;
}
found:
- wait_for_stable_page(page);
+ wait_for_stable_page(*page);
+ return found;
+}
+
+/*
+ * Find or create a page at the given pagecache position. Return the locked
+ * page. This function is specifically for buffered writes.
+ */
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags)
+{
+ struct page *page;
+ __grab_cache_page_write_begin(mapping, index, flags, 0, &page);
return page;
}
EXPORT_SYMBOL(grab_cache_page_write_begin);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * Find or create a huge page at the given pagecache position, aligned to
+ * HPAGE_CACHE_NR. Return the locked huge page.
+ *
+ * If, for some reason, it's not possible allocate a huge page at this
+ * possition, it returns NULL. Caller should take care of fallback to small
+ * pages.
+ *
+ * This function is specifically for buffered writes.
+ */
+struct page *grab_thp_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags)
+{
+ gfp_t gfp_mask;
+ struct page *page;
+ bool found;
+
+ BUG_ON(index & HPAGE_CACHE_INDEX_MASK);
+ gfp_mask = mapping_gfp_mask(mapping);
+ BUG_ON(!(gfp_mask & __GFP_COMP));
+
+ found = __grab_cache_page_write_begin(mapping, index, flags,
+ HPAGE_PMD_ORDER, &page);
+ if (!page) {
+ if (!found)
+ count_vm_event(THP_WRITE_ALLOC_FAILED);
+ return NULL;
+ }
+
+ if (!found)
+ count_vm_event(THP_WRITE_ALLOC);
+
+ if (!PageTransHuge(page)) {
+ unlock_page(page);
+ page_cache_release(page);
+ return NULL;
+ }
+
+ return page;
+}
+#endif
+
static ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
--
1.7.10.4
next prev parent reply other threads:[~2013-04-05 11:59 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-05 11:59 [PATCHv3, RFC 00/34] Transparent huge page cache Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 01/34] mm: drop actor argument of do_generic_file_read() Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 02/34] block: implement add_bdi_stat() Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 03/34] mm: implement zero_huge_user_segment and friends Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 04/34] radix-tree: implement preload for multiple contiguous elements Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 05/34] memcg, thp: charge huge cache pages Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 06/34] thp, mm: avoid PageUnevictable on active/inactive lru lists Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 07/34] thp, mm: basic defines for transparent huge page cache Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 08/34] thp, mm: introduce mapping_can_have_hugepages() predicate Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 09/34] thp: represent file thp pages in meminfo and friends Kirill A. Shutemov
2013-04-08 19:38 ` Dave Hansen
2013-04-16 14:49 ` Kirill A. Shutemov
2013-04-16 15:11 ` Dave Hansen
2013-04-05 11:59 ` [PATCHv3, RFC 10/34] thp, mm: rewrite add_to_page_cache_locked() to support huge pages Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 11/34] mm: trace filemap: dump page order Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 12/34] thp, mm: rewrite delete_from_page_cache() to support huge pages Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 13/34] thp, mm: trigger bug in replace_page_cache_page() on THP Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 14/34] thp, mm: locking tail page is a bug Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 15/34] thp, mm: handle tail pages in page_cache_get_speculative() Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 16/34] thp, mm: add event counters for huge page alloc on write to a file Kirill A. Shutemov
2013-04-05 11:59 ` Kirill A. Shutemov [this message]
2013-04-05 11:59 ` [PATCHv3, RFC 18/34] thp, mm: naive support of thp in generic read/write routines Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 19/34] thp, libfs: initial support of thp in simple_read/write_begin/write_end Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 20/34] thp: handle file pages in split_huge_page() Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 21/34] thp: wait_split_huge_page(): serialize over i_mmap_mutex too Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 22/34] thp, mm: truncate support for transparent huge page cache Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 23/34] thp, mm: split huge page on mmap file page Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 24/34] ramfs: enable transparent huge page cache Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 25/34] x86-64, mm: proper alignment mappings with hugepages Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 26/34] mm: add huge_fault() callback to vm_operations_struct Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 27/34] thp: prepare zap_huge_pmd() to uncharge file pages Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 28/34] thp: move maybe_pmd_mkwrite() out of mk_huge_pmd() Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 29/34] thp, mm: basic huge_fault implementation for generic_file_vm_ops Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 30/34] thp: extract fallback path from do_huge_pmd_anonymous_page() to a function Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 31/34] thp: initial implementation of do_huge_linear_fault() Kirill A. Shutemov
2013-04-08 18:46 ` Dave Hansen
2013-04-08 18:52 ` Dave Hansen
2013-04-17 14:38 ` Kirill A. Shutemov
2013-04-17 22:07 ` Dave Hansen
2013-04-18 16:09 ` Kirill A. Shutemov
2013-04-18 16:19 ` Kirill A. Shutemov
2013-04-18 16:20 ` Dave Hansen
2013-04-18 16:38 ` Kirill A. Shutemov
2013-04-18 16:42 ` Dave Hansen
2013-04-05 11:59 ` [PATCHv3, RFC 32/34] thp: handle write-protect exception to file-backed huge pages Kirill A. Shutemov
2013-04-08 19:07 ` Dave Hansen
2013-04-26 15:31 ` Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 33/34] thp: call __vma_adjust_trans_huge() for file-backed VMA Kirill A. Shutemov
2013-04-05 11:59 ` [PATCHv3, RFC 34/34] thp: map file-backed huge pages on fault Kirill A. Shutemov
2013-04-07 0:40 ` [PATCHv3, RFC 00/34] Transparent huge page cache Ric Mason
2013-04-15 16:02 ` IOZone with transparent " Kirill A. Shutemov
2013-04-15 18:17 ` [RESEND] " Kirill A. Shutemov
2013-04-15 23:19 ` Dave Hansen
2013-04-16 5:57 ` Kirill A. Shutemov
2013-04-16 6:11 ` Dave Hansen
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=1365163198-29726-18-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=matthew.r.wilcox@intel.com \
--cc=mgorman@suse.de \
--cc=viro@zeniv.linux.org.uk \
/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).