linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: LKML <linux-kernel@vger.kernel.org>
Cc: kosaki.motohiro@jp.fujitsu.com, linux-mm <linux-mm@kvack.org>,
	Rik van Riel <riel@redhat.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Larry Woodman <lwoodman@redhat.com>
Subject: [PATCH 1/7] Replace page_mapping_inuse() with page_mapped()
Date: Fri,  4 Dec 2009 17:41:35 +0900 (JST)	[thread overview]
Message-ID: <20091204174016.5894.A69D9226@jp.fujitsu.com> (raw)
In-Reply-To: <20091204173233.5891.A69D9226@jp.fujitsu.com>

From c0cd3ee2bb13567a36728600a86f43abac3125b5 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Wed, 2 Dec 2009 12:05:26 +0900
Subject: [PATCH 1/7] Replace page_mapping_inuse() with page_mapped()

page reclaim logic need to distingish mapped and unmapped pages.
However page_mapping_inuse() don't provide proper test way. it test
the address space (i.e. file) is mmpad(). Why `page' reclaim need
care unrelated page's mapped state? it's unrelated.

Thus, This patch replace page_mapping_inuse() with page_mapped()

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 mm/vmscan.c |   25 ++-----------------------
 1 files changed, 2 insertions(+), 23 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index da6cf42..4ba08da 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -262,27 +262,6 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 	return ret;
 }
 
-/* Called without lock on whether page is mapped, so answer is unstable */
-static inline int page_mapping_inuse(struct page *page)
-{
-	struct address_space *mapping;
-
-	/* Page is in somebody's page tables. */
-	if (page_mapped(page))
-		return 1;
-
-	/* Be more reluctant to reclaim swapcache than pagecache */
-	if (PageSwapCache(page))
-		return 1;
-
-	mapping = page_mapping(page);
-	if (!mapping)
-		return 0;
-
-	/* File is mmap'd by somebody? */
-	return mapping_mapped(mapping);
-}
-
 static inline int is_page_cache_freeable(struct page *page)
 {
 	/*
@@ -649,7 +628,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * try_to_unmap moves it to unevictable list
 		 */
 		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
-					referenced && page_mapping_inuse(page)
+					referenced && page_mapped(page)
 					&& !(vm_flags & VM_LOCKED))
 			goto activate_locked;
 
@@ -1356,7 +1335,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		}
 
 		/* page_referenced clears PageReferenced */
-		if (page_mapping_inuse(page) &&
+		if (page_mapped(page) &&
 		    page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
 			nr_rotated++;
 			/*
-- 
1.6.5.2



--
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>

  reply	other threads:[~2009-12-04  8:41 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-12-04  8:40 [RFC][PATCH 0/7] some page_referenced() improvement KOSAKI Motohiro
2009-12-04  8:41 ` KOSAKI Motohiro [this message]
2009-12-07 11:27   ` [PATCH 1/7] Replace page_mapping_inuse() with page_mapped() Johannes Weiner
2009-12-04  8:42 ` [PATCH 2/7] Introduce __page_check_address KOSAKI Motohiro
2009-12-06 14:55   ` Rik van Riel
2009-12-04  8:42 ` [PATCH 3/7] VM_LOCKED check don't need pte lock KOSAKI Motohiro
2009-12-06 19:41   ` Rik van Riel
2009-12-04  8:43 ` [PATCH 4/7] Replace page_referenced() with wipe_page_reference() KOSAKI Motohiro
2009-12-06 20:31   ` Rik van Riel
2009-12-04  8:44 ` [PATCH 5/7] Don't deactivate the page if trylock_page() is failed KOSAKI Motohiro
2009-12-06 20:34   ` Rik van Riel
2009-12-04  8:45 ` [PATCH 6/7] wipe_page_reference return SWAP_AGAIN if VM pressulre is low and lock contention is detected KOSAKI Motohiro
2009-12-06 21:01   ` Rik van Riel
2009-12-04  8:46 ` [PATCH 7/7] Try to mark PG_mlocked if wipe_page_reference find VM_LOCKED vma KOSAKI Motohiro
2009-12-06 21:03   ` Rik van Riel
2009-12-07  9:25 ` [RFC][PATCH 0/7] some page_referenced() improvement KOSAKI Motohiro
2009-12-07 11:36 ` [early RFC][PATCH 8/7] vmscan: Don't deactivate many touched page KOSAKI Motohiro
2009-12-07 18:10   ` Rik van Riel
2009-12-08  6:27     ` 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=20091204174016.5894.A69D9226@jp.fujitsu.com \
    --to=kosaki.motohiro@jp.fujitsu.com \
    --cc=aarcange@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lwoodman@redhat.com \
    --cc=riel@redhat.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