From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Andrea Arcangeli <aarcange@redhat.com>,
Avi Kivity <avi@redhat.com>, Thomas Gleixner <tglx@linutronix.de>,
Rik van Riel <riel@redhat.com>, Ingo Molnar <mingo@elte.hu>,
akpm@linux-foundation.org,
Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
David Miller <davem@davemloft.net>,
Hugh Dickins <hugh.dickins@tiscali.co.uk>,
Mel Gorman <mel@csn.ul.ie>, Nick Piggin <npiggin@suse.de>,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 05/13] mm: Make use of the anon_vma ref count
Date: Thu, 08 Apr 2010 21:17:42 +0200 [thread overview]
Message-ID: <20100408192722.815377075@chello.nl> (raw)
In-Reply-To: 20100408191737.296180458@chello.nl
[-- Attachment #1: mm-use-anon_vma-ref.patch --]
[-- Type: text/plain, Size: 6267 bytes --]
This patch changes the anon_vma refcount to be 0 when the object is
free. It does this by adding 1 ref to being in use in the anon_vma
structure (iow. the anon_vma->head list is not empty).
This allows a simpler release scheme without having to check both the
refcount and the list as well as avoids taking a ref for each entry
on the list.
We then use this new refcount in the migration code to avoid a long
RCU read side section and convert page_lock_anon_vma() over to use
refcounts.
This later is done for each of convertion of anon_vma from spinlock
to mutex.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/rmap.h | 7 +++++++
mm/ksm.c | 9 +--------
mm/migrate.c | 17 ++++++-----------
mm/rmap.c | 45 ++++++++++++++++++++++++++++++---------------
4 files changed, 44 insertions(+), 34 deletions(-)
Index: linux-2.6/include/linux/rmap.h
===================================================================
--- linux-2.6.orig/include/linux/rmap.h
+++ linux-2.6/include/linux/rmap.h
@@ -100,6 +100,13 @@ static inline void anon_vma_merge(struct
unlink_anon_vmas(next);
}
+struct anon_vma *anon_vma_get(struct page *page);
+static inline void anon_vma_put(struct anon_vma *anon_vma)
+{
+ if (atomic_dec_and_test(&anon_vma->ref))
+ anon_vma_free(anon_vma);
+}
+
/*
* rmap interfaces called when adding or removing pte of page
*/
Index: linux-2.6/mm/ksm.c
===================================================================
--- linux-2.6.orig/mm/ksm.c
+++ linux-2.6/mm/ksm.c
@@ -323,14 +323,7 @@ static void hold_anon_vma(struct rmap_it
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->ref, &anon_vma->lock)) {
- int empty = list_empty(&anon_vma->head);
- spin_unlock(&anon_vma->lock);
- if (empty)
- anon_vma_free(anon_vma);
- }
+ anon_vma_put(rmap_item->anon_vma);
}
/*
Index: linux-2.6/mm/migrate.c
===================================================================
--- linux-2.6.orig/mm/migrate.c
+++ linux-2.6/mm/migrate.c
@@ -545,7 +545,7 @@ static int unmap_and_move(new_page_t get
int rc = 0;
int *result = NULL;
struct page *newpage = get_new_page(page, private, &result);
- int rcu_locked = 0;
+ struct anon_vma *anon_vma = NULL;
int charge = 0;
struct mem_cgroup *mem = NULL;
@@ -601,10 +601,8 @@ static int unmap_and_move(new_page_t get
* File Caches may use write_page() or lock_page() in migration, then,
* just care Anon page here.
*/
- if (PageAnon(page)) {
- rcu_read_lock();
- rcu_locked = 1;
- }
+ if (PageAnon(page))
+ anon_vma = anon_vma_get(page);
/*
* Corner case handling:
@@ -622,10 +620,7 @@ static int unmap_and_move(new_page_t get
if (!PageAnon(page) && page_has_private(page)) {
/*
* Go direct to try_to_free_buffers() here because
- * a) that's what try_to_release_page() would do anyway
- * b) we may be under rcu_read_lock() here, so we can't
- * use GFP_KERNEL which is what try_to_release_page()
- * needs to be effective.
+ * that's what try_to_release_page() would do anyway
*/
try_to_free_buffers(page);
goto rcu_unlock;
@@ -643,8 +638,8 @@ skip_unmap:
if (rc)
remove_migration_ptes(page, page);
rcu_unlock:
- if (rcu_locked)
- rcu_read_unlock();
+ if (anon_vma)
+ anon_vma_put(anon_vma);
uncharge:
if (!charge)
mem_cgroup_end_migration(mem, page, newpage);
Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -66,11 +66,18 @@ static struct kmem_cache *anon_vma_chain
static inline struct anon_vma *anon_vma_alloc(void)
{
- return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+ struct anon_vma *anon_vma;
+
+ anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+ if (anon_vma)
+ atomic_set(&anon_vma->ref, 1);
+
+ return anon_vma;
}
void anon_vma_free(struct anon_vma *anon_vma)
{
+ VM_BUG_ON(atomic_read(&anon_vma->ref));
kmem_cache_free(anon_vma_cachep, anon_vma);
}
@@ -149,7 +156,7 @@ int anon_vma_prepare(struct vm_area_stru
spin_unlock(&anon_vma->lock);
if (unlikely(allocated)) {
- anon_vma_free(allocated);
+ anon_vma_put(allocated);
anon_vma_chain_free(avc);
}
}
@@ -230,7 +237,7 @@ int anon_vma_fork(struct vm_area_struct
return 0;
out_error_free_anon_vma:
- anon_vma_free(anon_vma);
+ anon_vma_put(anon_vma);
out_error:
unlink_anon_vmas(vma);
return -ENOMEM;
@@ -247,13 +254,11 @@ static void anon_vma_unlink(struct anon_
spin_lock(&anon_vma->lock);
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) && !atomic_read(&anon_vma->ref);
+ empty = list_empty(&anon_vma->head);
spin_unlock(&anon_vma->lock);
if (empty)
- anon_vma_free(anon_vma);
+ anon_vma_put(anon_vma);
}
void unlink_anon_vmas(struct vm_area_struct *vma)
@@ -286,11 +291,11 @@ void __init anon_vma_init(void)
/*
* Getting a lock on a stable anon_vma from a page off the LRU is
- * tricky: page_lock_anon_vma rely on RCU to guard against the races.
+ * tricky: page_lock_anon_vma relies on RCU to guard against the races.
*/
-struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *anon_vma_get(struct page *page)
{
- struct anon_vma *anon_vma;
+ struct anon_vma *anon_vma = NULL;
unsigned long anon_mapping;
rcu_read_lock();
@@ -302,23 +307,33 @@ again:
goto out;
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
- spin_lock(&anon_vma->lock);
+ if (!atomic_inc_not_zero(&anon_vma->ref))
+ anon_vma = NULL;
if (page_rmapping(page) != anon_vma) {
- spin_unlock(&anon_vma->lock);
+ anon_vma_put(anon_vma);
goto again;
}
- return anon_vma;
out:
rcu_read_unlock();
- return NULL;
+ return anon_vma;
+}
+
+struct anon_vma *page_lock_anon_vma(struct page *page)
+{
+ struct anon_vma *anon_vma = anon_vma_get(page);
+
+ if (anon_vma)
+ spin_lock(&anon_vma->lock);
+
+ return anon_vma;
}
void page_unlock_anon_vma(struct anon_vma *anon_vma)
{
spin_unlock(&anon_vma->lock);
- rcu_read_unlock();
+ anon_vma_put(anon_vma);
}
/*
next prev parent reply other threads:[~2010-04-08 19:31 UTC|newest]
Thread overview: 96+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-08 19:17 [PATCH 00/13] mm: preemptibility -v2 Peter Zijlstra
2010-04-08 19:17 ` [PATCH 01/13] powerpc: Add rcu_read_lock() to gup_fast() implementation Peter Zijlstra
2010-04-08 20:31 ` Rik van Riel
2010-04-09 3:11 ` Nick Piggin
2010-04-13 1:05 ` Benjamin Herrenschmidt
2010-04-13 3:43 ` Paul E. McKenney
2010-04-14 13:51 ` Peter Zijlstra
2010-04-15 14:28 ` Paul E. McKenney
2010-04-16 6:54 ` Benjamin Herrenschmidt
2010-04-16 13:43 ` Paul E. McKenney
2010-04-16 23:25 ` Benjamin Herrenschmidt
2010-04-16 13:51 ` Peter Zijlstra
2010-04-16 14:17 ` Paul E. McKenney
2010-04-16 14:23 ` Peter Zijlstra
2010-04-16 14:32 ` Paul E. McKenney
2010-04-16 14:56 ` Peter Zijlstra
2010-04-16 15:09 ` Paul E. McKenney
2010-04-16 15:14 ` Peter Zijlstra
2010-04-16 16:45 ` Paul E. McKenney
2010-04-16 19:37 ` Peter Zijlstra
2010-04-16 20:28 ` Paul E. McKenney
2010-04-18 3:06 ` James Bottomley
2010-04-18 13:55 ` Paul E. McKenney
2010-04-18 18:55 ` James Bottomley
2010-04-16 6:51 ` Benjamin Herrenschmidt
2010-04-16 8:18 ` Nick Piggin
2010-04-16 8:29 ` Benjamin Herrenschmidt
2010-04-16 9:22 ` Nick Piggin
2010-04-08 19:17 ` [PATCH 02/13] mm: Revalidate anon_vma in page_lock_anon_vma() Peter Zijlstra
2010-04-08 20:50 ` Rik van Riel
2010-04-08 21:20 ` Andrew Morton
2010-04-08 21:54 ` Peter Zijlstra
2010-04-09 2:19 ` KOSAKI Motohiro
2010-04-09 2:19 ` Minchan Kim
2010-04-09 3:16 ` Nick Piggin
2010-04-09 4:56 ` KAMEZAWA Hiroyuki
2010-04-09 6:34 ` KOSAKI Motohiro
2010-04-09 6:47 ` KAMEZAWA Hiroyuki
2010-04-09 7:29 ` KOSAKI Motohiro
2010-04-09 7:57 ` KAMEZAWA Hiroyuki
2010-04-09 8:03 ` KAMEZAWA Hiroyuki
2010-04-09 8:24 ` KAMEZAWA Hiroyuki
2010-04-09 8:01 ` Minchan Kim
2010-04-09 8:17 ` KOSAKI Motohiro
2010-04-09 14:41 ` mlock and pageout race? Minchan Kim
2010-04-09 8:44 ` [PATCH 02/13] mm: Revalidate anon_vma in page_lock_anon_vma() Peter Zijlstra
2010-05-24 19:32 ` Andrew Morton
2010-05-25 9:01 ` Peter Zijlstra
2010-04-09 12:57 ` Peter Zijlstra
2010-04-08 19:17 ` [PATCH 03/13] x86: Remove last traces of quicklist usage Peter Zijlstra
2010-04-08 20:51 ` Rik van Riel
2010-04-08 19:17 ` [PATCH 04/13] mm: Move anon_vma ref out from under CONFIG_KSM Peter Zijlstra
2010-04-09 12:35 ` Rik van Riel
2010-04-08 19:17 ` Peter Zijlstra [this message]
2010-04-09 7:04 ` [PATCH 05/13] mm: Make use of the anon_vma ref count Christian Ehrhardt
2010-04-09 9:57 ` Peter Zijlstra
2010-04-08 19:17 ` [PATCH 06/13] mm: Preemptible mmu_gather Peter Zijlstra
2010-04-09 3:25 ` Nick Piggin
2010-04-09 8:18 ` Peter Zijlstra
2010-04-09 20:36 ` Peter Zijlstra
2010-04-19 19:16 ` Peter Zijlstra
2010-04-08 19:17 ` [PATCH 07/13] powerpc: " Peter Zijlstra
2010-04-09 4:07 ` Nick Piggin
2010-04-09 8:14 ` Peter Zijlstra
2010-04-09 8:46 ` Nick Piggin
2010-04-09 9:22 ` Peter Zijlstra
2010-04-13 2:06 ` Benjamin Herrenschmidt
2010-04-13 1:56 ` Benjamin Herrenschmidt
2010-04-13 1:23 ` Benjamin Herrenschmidt
2010-04-13 10:22 ` Peter Zijlstra
2010-04-14 13:34 ` Peter Zijlstra
2010-04-14 13:51 ` Peter Zijlstra
2010-04-08 19:17 ` [PATCH 08/13] sparc: " Peter Zijlstra
2010-04-08 19:17 ` [PATCH 09/13] mm, powerpc: Move the RCU page-table freeing into generic code Peter Zijlstra
2010-04-09 3:35 ` Nick Piggin
2010-04-09 8:08 ` Peter Zijlstra
2010-04-08 19:17 ` [PATCH 10/13] lockdep, mutex: Provide mutex_lock_nest_lock Peter Zijlstra
2010-04-09 15:36 ` Rik van Riel
2010-04-08 19:17 ` [PATCH 11/13] mutex: Provide mutex_is_contended Peter Zijlstra
2010-04-09 15:37 ` Rik van Riel
2010-04-08 19:17 ` [PATCH 12/13] mm: Convert i_mmap_lock and anon_vma->lock to mutexes Peter Zijlstra
2010-04-08 19:17 ` [PATCH 13/13] mm: Optimize page_lock_anon_vma Peter Zijlstra
2010-04-08 22:18 ` Paul E. McKenney
2010-04-09 8:35 ` Peter Zijlstra
2010-04-09 19:22 ` Paul E. McKenney
2010-04-08 20:29 ` [PATCH 00/13] mm: preemptibility -v2 David Miller
2010-04-08 20:35 ` Peter Zijlstra
2010-04-09 1:00 ` David Miller
2010-04-09 4:14 ` Nick Piggin
2010-04-09 8:35 ` Peter Zijlstra
2010-04-09 8:50 ` Nick Piggin
2010-04-09 8:58 ` Peter Zijlstra
2010-04-09 8:58 ` Martin Schwidefsky
2010-04-09 9:53 ` Peter Zijlstra
2010-04-09 9:03 ` David Howells
2010-04-09 9:22 ` Peter Zijlstra
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=20100408192722.815377075@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=avi@redhat.com \
--cc=benh@kernel.crashing.org \
--cc=davem@davemloft.net \
--cc=hugh.dickins@tiscali.co.uk \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mel@csn.ul.ie \
--cc=mingo@elte.hu \
--cc=npiggin@suse.de \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/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).