linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrea Arcangeli <aarcange@redhat.com>
To: linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
	Adam Litke <agl@us.ibm.com>, Avi Kivity <avi@redhat.com>,
	Izik Eidus <ieidus@redhat.com>,
	Hugh Dickins <hugh.dickins@tiscali.co.uk>,
	Nick Piggin <npiggin@suse.de>, Rik van Riel <riel@redhat.com>,
	Mel Gorman <mel@csn.ul.ie>, Dave Hansen <dave@linux.vnet.ibm.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Ingo Molnar <mingo@elte.hu>, Mike Travis <travis@sgi.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Christoph Lameter <cl@linux-foundation.org>,
	Chris Wright <chrisw@sous-sol.org>,
	bpicco@redhat.com,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	Arnd Bergmann <arnd@arndb.de>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
	Chris Mason <chris.mason@oracle.com>
Subject: [PATCH 51 of 67] Share the anon_vma ref counts between KSM and page migration
Date: Thu, 08 Apr 2010 03:51:34 +0200	[thread overview]
Message-ID: <9acd43df3ec98bdef70a.1270691494@v2.random> (raw)
In-Reply-To: <patchbomb.1270691443@v2.random>

From: Mel Gorman <mel@csn.ul.ie>

For clarity of review, KSM and page migration have separate refcounts on
the anon_vma. While clear, this is a waste of memory. This patch gets
KSM and page migration to share their toys in a spirit of harmony.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -26,11 +26,17 @@
  */
 struct anon_vma {
 	spinlock_t lock;	/* Serialize access to vma list */
-#ifdef CONFIG_KSM
-	atomic_t ksm_refcount;
-#endif
-#ifdef CONFIG_MIGRATION
-	atomic_t migrate_refcount;
+#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
+
+	/*
+	 * The external_refcount is taken by either KSM or page migration
+	 * to take a reference to an anon_vma when there is no
+	 * guarantee that the vma of page tables will exist for
+	 * the duration of the operation. A caller that takes
+	 * the reference is responsible for clearing up the
+	 * anon_vma if they are the last user on release
+	 */
+	atomic_t external_refcount;
 #endif
 	/*
 	 * NOTE: the LSB of the head.next is set by
@@ -64,46 +70,26 @@ struct anon_vma_chain {
 };
 
 #ifdef CONFIG_MMU
-#ifdef CONFIG_KSM
-static inline void ksm_refcount_init(struct anon_vma *anon_vma)
+#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
+static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma)
 {
-	atomic_set(&anon_vma->ksm_refcount, 0);
+	atomic_set(&anon_vma->external_refcount, 0);
 }
 
-static inline int ksm_refcount(struct anon_vma *anon_vma)
+static inline int anonvma_external_refcount(struct anon_vma *anon_vma)
 {
-	return atomic_read(&anon_vma->ksm_refcount);
+	return atomic_read(&anon_vma->external_refcount);
 }
 #else
-static inline void ksm_refcount_init(struct anon_vma *anon_vma)
+static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma)
 {
 }
 
-static inline int ksm_refcount(struct anon_vma *anon_vma)
+static inline int anonvma_external_refcount(struct anon_vma *anon_vma)
 {
 	return 0;
 }
 #endif /* CONFIG_KSM */
-#ifdef CONFIG_MIGRATION
-static inline void migrate_refcount_init(struct anon_vma *anon_vma)
-{
-	atomic_set(&anon_vma->migrate_refcount, 0);
-}
-
-static inline int migrate_refcount(struct anon_vma *anon_vma)
-{
-	return atomic_read(&anon_vma->migrate_refcount);
-}
-#else
-static inline void migrate_refcount_init(struct anon_vma *anon_vma)
-{
-}
-
-static inline int migrate_refcount(struct anon_vma *anon_vma)
-{
-	return 0;
-}
-#endif /* CONFIG_MIGRATE */
 
 static inline struct anon_vma *page_anon_vma(struct page *page)
 {
diff --git a/mm/ksm.c b/mm/ksm.c
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -318,14 +318,14 @@ static void hold_anon_vma(struct rmap_it
 			  struct anon_vma *anon_vma)
 {
 	rmap_item->anon_vma = anon_vma;
-	atomic_inc(&anon_vma->ksm_refcount);
+	atomic_inc(&anon_vma->external_refcount);
 }
 
 static void drop_anon_vma(struct rmap_item *rmap_item)
 {
 	struct anon_vma *anon_vma = rmap_item->anon_vma;
 
-	if (atomic_dec_and_lock(&anon_vma->ksm_refcount, &anon_vma->lock)) {
+	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
 		int empty = list_empty(&anon_vma->head);
 		spin_unlock(&anon_vma->lock);
 		if (empty)
diff --git a/mm/migrate.c b/mm/migrate.c
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -621,7 +621,7 @@ static int unmap_and_move(new_page_t get
 			goto rcu_unlock;
 
 		anon_vma = page_anon_vma(page);
-		atomic_inc(&anon_vma->migrate_refcount);
+		atomic_inc(&anon_vma->external_refcount);
 	}
 
 	/*
@@ -663,7 +663,7 @@ skip_unmap:
 rcu_unlock:
 
 	/* Drop an anon_vma reference if we took one */
-	if (anon_vma && atomic_dec_and_lock(&anon_vma->migrate_refcount, &anon_vma->lock)) {
+	if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
 		int empty = list_empty(&anon_vma->head);
 		spin_unlock(&anon_vma->lock);
 		if (empty)
diff --git a/mm/rmap.c b/mm/rmap.c
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -250,8 +250,7 @@ static void anon_vma_unlink(struct anon_
 	list_del(&anon_vma_chain->same_anon_vma);
 
 	/* We must garbage collect the anon_vma if it's empty */
-	empty = list_empty(&anon_vma->head) && !ksm_refcount(anon_vma) &&
-					!migrate_refcount(anon_vma);
+	empty = list_empty(&anon_vma->head) && !anonvma_external_refcount(anon_vma);
 	spin_unlock(&anon_vma->lock);
 
 	if (empty)
@@ -275,8 +274,7 @@ static void anon_vma_ctor(void *data)
 	struct anon_vma *anon_vma = data;
 
 	spin_lock_init(&anon_vma->lock);
-	ksm_refcount_init(anon_vma);
-	migrate_refcount_init(anon_vma);
+	anonvma_external_refcount_init(anon_vma);
 	INIT_LIST_HEAD(&anon_vma->head);
 }
 

--
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>

  parent reply	other threads:[~2010-04-08  2:57 UTC|newest]

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-04-08  1:50 [PATCH 00 of 67] Transparent Hugepage Support #18 Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 01 of 67] define MADV_HUGEPAGE Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 02 of 67] compound_lock Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 03 of 67] alter compound get_page/put_page Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 04 of 67] update futex compound knowledge Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 05 of 67] fix bad_page to show the real reason the page is bad Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 06 of 67] clear compound mapping Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 07 of 67] add native_set_pmd_at Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 08 of 67] add pmd paravirt ops Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 09 of 67] no paravirt version of pmd ops Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 10 of 67] export maybe_mkwrite Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 11 of 67] comment reminder in destroy_compound_page Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 12 of 67] config_transparent_hugepage Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 13 of 67] special pmd_trans_* functions Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 14 of 67] add pmd mangling generic functions Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 15 of 67] add pmd mangling functions to x86 Andrea Arcangeli
2010-04-08  1:50 ` [PATCH 16 of 67] bail out gup_fast on splitting pmd Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 17 of 67] pte alloc trans splitting Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 18 of 67] add pmd mmu_notifier helpers Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 19 of 67] clear page compound Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 20 of 67] add pmd_huge_pte to mm_struct Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 21 of 67] This fixes some minor issues that bugged me while going over the code: Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 22 of 67] Split out functions to handle hugetlb ranges, pte ranges and unmapped Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 23 of 67] Instead of passing a start address and a number of pages into the helper Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 24 of 67] Do page table walks with the well-known nested loops we use in several Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 25 of 67] split_huge_page_mm/vma Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 26 of 67] split_huge_page paging Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 27 of 67] clear_copy_huge_page Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 28 of 67] kvm mmu transparent hugepage support Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 29 of 67] _GFP_NO_KSWAPD Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 30 of 67] don't alloc harder for gfp nomemalloc even if nowait Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 31 of 67] transparent hugepage core Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 32 of 67] verify pmd_trans_huge isn't leaking Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 33 of 67] madvise(MADV_HUGEPAGE) Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 34 of 67] pmd_trans_huge migrate bugcheck Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 35 of 67] memcg compound Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 36 of 67] memcg huge memory Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 37 of 67] transparent hugepage vmstat Andrea Arcangeli
2010-04-08 11:53   ` Avi Kivity
2010-04-08  1:51 ` [PATCH 38 of 67] khugepaged Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 39 of 67] don't leave orhpaned swap cache after ksm merging Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 40 of 67] skip transhuge pages in ksm for now Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 41 of 67] remove PG_buddy Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 42 of 67] add x86 32bit support Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 43 of 67] mincore transparent hugepage support Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 44 of 67] add pmd_modify Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 45 of 67] mprotect: pass vma down to page table walkers Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 46 of 67] mprotect: transparent huge page support Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 47 of 67] set recommended min free kbytes Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 48 of 67] remove lumpy_reclaim Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 49 of 67] Take a reference to the anon_vma before migrating Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 50 of 67] Do not try to migrate unmapped anonymous pages Andrea Arcangeli
2010-04-08  1:51 ` Andrea Arcangeli [this message]
2010-04-08  1:51 ` [PATCH 52 of 67] Allow CONFIG_MIGRATION to be set without CONFIG_NUMA or memory hot-remove Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 53 of 67] Export unusable free space index via /proc/unusable_index Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 54 of 67] Export fragmentation index via /proc/extfrag_index Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 55 of 67] Move definition for LRU isolation modes to a header Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 56 of 67] Memory compaction core Andrea Arcangeli
2010-04-08 16:18   ` Johannes Weiner
2010-04-08 16:46     ` Andrea Arcangeli
2010-04-08 17:09       ` Andrea Arcangeli
2010-04-08 17:14         ` Andrea Arcangeli
2010-04-08 17:56           ` Johannes Weiner
2010-04-08 17:58             ` Andrea Arcangeli
2010-04-08 18:48               ` Johannes Weiner
2010-04-08 21:23                 ` Andrea Arcangeli
2010-04-08 21:32                   ` Andrea Arcangeli
2010-04-09 10:51                   ` Mel Gorman
2010-04-09 15:37                     ` Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 57 of 67] Add /proc trigger for memory compaction Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 58 of 67] Add /sys trigger for per-node " Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 59 of 67] Direct compact when a high-order allocation fails Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 60 of 67] Add a tunable that decides when memory should be compacted and when it should be reclaimed Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 61 of 67] Allow the migration of PageSwapCache pages Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 62 of 67] do not display compaction-related stats when !CONFIG_COMPACTION Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 63 of 67] disable migreate_prep() Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 64 of 67] page buddy can go away before reading page_order Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 65 of 67] select CONFIG_COMPACTION if TRANSPARENT_HUGEPAGE enabled Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 66 of 67] enable direct defrag Andrea Arcangeli
2010-04-08  1:51 ` [PATCH 67 of 67] memcg fix prepare migration Andrea Arcangeli
2010-04-08  3:57   ` Daisuke Nishimura
2010-04-13  1:29     ` Andrew Morton
2010-04-09  8:13   ` KAMEZAWA Hiroyuki
2010-04-08  9:39 ` [PATCH 00 of 67] Transparent Hugepage Support #18 Avi Kivity
2010-04-08 11:44   ` Avi Kivity
2010-04-08 15:23     ` Andrea Arcangeli
2010-04-08 15:27       ` Avi Kivity
2010-04-08 16:02         ` Andrea Arcangeli
2010-04-08 15:32       ` Christoph Lameter
2010-04-08 23:17         ` Andrea Arcangeli
2010-04-09  8:45     ` Avi Kivity
2010-04-09 15:50       ` Andrea Arcangeli
2010-04-09 17:44         ` Avi Kivity
2010-04-09  2:05 ` Transparent Hugepage Support #19 Andrea Arcangeli
2010-04-09 15:43   ` Andrea Arcangeli

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=9acd43df3ec98bdef70a.1270691494@v2.random \
    --to=aarcange@redhat.com \
    --cc=agl@us.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=avi@redhat.com \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=bpicco@redhat.com \
    --cc=chris.mason@oracle.com \
    --cc=chrisw@sous-sol.org \
    --cc=cl@linux-foundation.org \
    --cc=dave@linux.vnet.ibm.com \
    --cc=hannes@cmpxchg.org \
    --cc=hugh.dickins@tiscali.co.uk \
    --cc=ieidus@redhat.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=mingo@elte.hu \
    --cc=mst@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=nishimura@mxp.nes.nec.co.jp \
    --cc=npiggin@suse.de \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --cc=travis@sgi.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