linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH 10/28] mm: Make use of the anon_vma ref count
Date: Mon, 07 Jun 2010 13:07:04 +0200	[thread overview]
Message-ID: <20100607111407.309924253@chello.nl> (raw)
In-Reply-To: 20100607110654.606530953@chello.nl

[-- Attachment #1: mm-use-anon_vma-ref.patch --]
[-- Type: text/plain, Size: 6872 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 convert page_lock_anon_vma() over to use refcounts. This 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 |   11 ++++-
 mm/ksm.c             |    4 --
 mm/rmap.c            |   94 ++++++++++++++++++++++-----------------------------
 3 files changed, 52 insertions(+), 57 deletions(-)

Index: linux-2.6/include/linux/rmap.h
===================================================================
--- linux-2.6.orig/include/linux/rmap.h
+++ linux-2.6/include/linux/rmap.h
@@ -73,7 +73,13 @@ static inline void get_anon_vma(struct a
 	atomic_inc(&anon_vma->refcount);
 }
 
-void put_anon_vma(struct anon_vma *);
+void __put_anon_vma(struct anon_vma *anon_vma);
+
+static inline void put_anon_vma(struct anon_vma *anon_vma)
+{
+	if (atomic_dec_and_test(&anon_vma->refcount))
+		__put_anon_vma(anon_vma);
+}
 
 static inline struct anon_vma *page_anon_vma(struct page *page)
 {
@@ -116,7 +122,6 @@ void unlink_anon_vmas(struct vm_area_str
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 void __anon_vma_link(struct vm_area_struct *);
-void anon_vma_free(struct anon_vma *);
 
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)
@@ -125,6 +130,8 @@ static inline void anon_vma_merge(struct
 	unlink_anon_vmas(next);
 }
 
+struct anon_vma *page_get_anon_vma(struct page *page);
+
 /*
  * 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
@@ -323,9 +323,7 @@ static void hold_anon_vma(struct rmap_it
 
 static void ksm_put_anon_vma(struct rmap_item *rmap_item)
 {
-	struct anon_vma *anon_vma = rmap_item->anon_vma;
-
-	put_anon_vma(anon_vma);
+	put_anon_vma(rmap_item->anon_vma);
 }
 
 /*
Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -66,11 +66,24 @@ 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->refcount, 1);
+		/*
+		 * This VMA had no anon_vma yet.  This anon_vma is
+		 * the root of any anon_vma tree that might form.
+		 */
+		anon_vma->root = anon_vma;
+	}
+
+	return anon_vma;
 }
 
-void anon_vma_free(struct anon_vma *anon_vma)
+static inline void anon_vma_free(struct anon_vma *anon_vma)
 {
+	VM_BUG_ON(atomic_read(&anon_vma->refcount));
 	kmem_cache_free(anon_vma_cachep, anon_vma);
 }
 
@@ -132,11 +145,6 @@ int anon_vma_prepare(struct vm_area_stru
 			if (unlikely(!anon_vma))
 				goto out_enomem_free_avc;
 			allocated = anon_vma;
-			/*
-			 * This VMA had no anon_vma yet.  This anon_vma is
-			 * the root of any anon_vma tree that might form.
-			 */
-			anon_vma->root = anon_vma;
 		}
 
 		anon_vma_lock(anon_vma);
@@ -155,7 +163,7 @@ int anon_vma_prepare(struct vm_area_stru
 		anon_vma_unlock(anon_vma);
 
 		if (unlikely(allocated))
-			anon_vma_free(allocated);
+			put_anon_vma(allocated);
 		if (unlikely(avc))
 			anon_vma_chain_free(avc);
 	}
@@ -248,7 +256,7 @@ int anon_vma_fork(struct vm_area_struct 
 	return 0;
 
  out_error_free_anon_vma:
-	anon_vma_free(anon_vma);
+	put_anon_vma(anon_vma);
  out_error:
 	unlink_anon_vmas(vma);
 	return -ENOMEM;
@@ -265,16 +273,12 @@ static void anon_vma_unlink(struct anon_
 
 	anon_vma_lock(anon_vma);
 	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->refcount);
+	empty = list_empty(&anon_vma->head);
 	anon_vma_unlock(anon_vma);
 
-	if (empty) {
-		/* We no longer need the root anon_vma */
-		put_anon_vma(anon_vma->root);
-		anon_vma_free(anon_vma);
-	}
+	if (empty)
+		put_anon_vma(anon_vma);
 }
 
 void unlink_anon_vmas(struct vm_area_struct *vma)
@@ -326,9 +330,9 @@ void __init anon_vma_init(void)
  * that the anon_vma pointer from page->mapping is valid if there is a
  * mapcount, we can dereference the anon_vma after observing those.
  */
-struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_get_anon_vma(struct page *page)
 {
-	struct anon_vma *anon_vma;
+	struct anon_vma *anon_vma = NULL;
 	unsigned long anon_mapping;
 
 	rcu_read_lock();
@@ -339,17 +343,28 @@ struct anon_vma *page_lock_anon_vma(stru
 		goto out;
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-	anon_vma_lock(anon_vma);
-	return anon_vma;
+	if (!atomic_inc_not_zero(&anon_vma->refcount))
+		anon_vma = NULL;
 out:
 	rcu_read_unlock();
-	return NULL;
+
+	return anon_vma;
+}
+
+struct anon_vma *page_lock_anon_vma(struct page *page)
+{
+	struct anon_vma *anon_vma = page_get_anon_vma(page);
+
+	if (anon_vma)
+		anon_vma_lock(anon_vma);
+
+	return anon_vma;
 }
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
 	anon_vma_unlock(anon_vma);
-	rcu_read_unlock();
+	put_anon_vma(anon_vma);
 }
 
 /*
@@ -1405,36 +1420,11 @@ int try_to_munlock(struct page *page)
 		return try_to_unmap_file(page, TTU_MUNLOCK);
 }
 
-/*
- * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root
- * if necessary.  Be careful to do all the tests under the lock.  Once
- * we know we are the last user, nobody else can get a reference and we
- * can do the freeing without the lock.
- */
-void put_anon_vma(struct anon_vma *anon_vma)
-{
-	if (atomic_dec_and_lock(&anon_vma->refcount, &anon_vma->root->lock)) {
-		struct anon_vma *root = anon_vma->root;
-		int empty = list_empty(&anon_vma->head);
-		int last_root_user = 0;
-		int root_empty = 0;
-
-		/*
-		 * The refcount on a non-root anon_vma got dropped.  Drop
-		 * the refcount on the root and check if we need to free it.
-		 */
-		if (empty && anon_vma != root) {
-			last_root_user = atomic_dec_and_test(&root->refcount);
-			root_empty = list_empty(&root->head);
-		}
-		anon_vma_unlock(anon_vma);
-
-		if (empty) {
-			anon_vma_free(anon_vma);
-			if (root_empty && last_root_user)
-				anon_vma_free(root);
-		}
-	}
+void __put_anon_vma(struct anon_vma *anon_vma)
+{
+	if (anon_vma->root != anon_vma)
+		put_anon_vma(anon_vma->root);
+	anon_vma_free(anon_vma);
 }
 
 #ifdef CONFIG_MIGRATION



  parent reply	other threads:[~2010-06-07 11:26 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-06-07 11:06 [PATCH 00/28] mm: preemptibility -v3 Peter Zijlstra
2010-06-07 11:06 ` [PATCH 01/28] powerpc: Use call_rcu_sched() for pagetables Peter Zijlstra
2010-06-07 11:06 ` [PATCH 02/28] mm: Improve page_lock_anon_vma() comment Peter Zijlstra
2010-06-09 10:50   ` Mel Gorman
2010-06-07 11:06 ` [PATCH 03/28] rename anon_vma_lock to vma_lock_anon_vma Peter Zijlstra
2010-06-07 15:01   ` Peter Zijlstra
2010-06-09 10:59   ` Mel Gorman
2010-06-07 11:06 ` [PATCH 04/28] change direct call of spin_lock(anon_vma->lock) to inline function Peter Zijlstra
2010-06-07 11:06 ` [PATCH 05/28] track the root (oldest) anon_vma Peter Zijlstra
2010-06-07 11:07 ` [PATCH 06/28] always lock " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 07/28] extend KSM refcounts to the anon_vma root Peter Zijlstra
2010-06-09 10:55   ` Mel Gorman
2010-06-07 11:07 ` [PATCH 08/28] mm: Rename drop_anon_vma to put_anon_vma Peter Zijlstra
2010-06-07 11:07 ` [PATCH 09/28] mm: Move anon_vma ref out from under CONFIG_KSM Peter Zijlstra
2010-06-09 11:05   ` Mel Gorman
2010-06-07 11:07 ` Peter Zijlstra [this message]
2010-06-09 13:22   ` [PATCH 10/28] mm: Make use of the anon_vma ref count Mel Gorman
2010-06-09 13:32     ` Peter Zijlstra
2010-06-07 11:07 ` [PATCH 11/28] mm: Preemptible mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 12/28] powerpc: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 13/28] sparc: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 14/28] s390: preemptible mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 15/28] arm: Preemptible mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 16/28] sh: " Peter Zijlstra
2010-06-07 11:38   ` Peter Zijlstra
2010-06-07 11:07 ` [PATCH 17/28] um: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 18/28] ia64: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 19/28] mm, powerpc: Move the RCU page-table freeing into generic code Peter Zijlstra
2010-06-07 11:07 ` [PATCH 20/28] sparc64: Kill page table quicklists Peter Zijlstra
2010-06-07 11:07 ` [PATCH 21/28] sparc64: Use RCU page table freeing Peter Zijlstra
2010-06-07 11:07 ` [PATCH 22/28] sparc64: Add support for _PAGE_SPECIAL Peter Zijlstra
2010-06-07 11:07 ` [PATCH 23/28] sparc64: Implement get_user_pages_fast() Peter Zijlstra
2010-06-07 11:07 ` [PATCH 24/28] lockdep, mutex: Provide mutex_lock_nest_lock Peter Zijlstra
2010-06-07 11:07 ` [PATCH 25/28] mutex: Provide mutex_is_contended Peter Zijlstra
2010-06-07 11:07 ` [PATCH 26/28] mm: Convert i_mmap_lock and anon_vma->lock to mutexes Peter Zijlstra
2010-06-07 11:07 ` [PATCH 27/28] mm: Extended batches for generic mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 28/28] mm: Optimize page_lock_anon_vma() fast-path Peter Zijlstra
2010-06-07 13:57 ` [PATCH 00/28] mm: preemptibility -v3 Sam Ravnborg
2010-06-07 15:02   ` Peter Zijlstra
2010-06-07 16:36 ` Andi Kleen
2010-06-07 16:39   ` Peter Zijlstra
2010-06-10  1:45 ` Zhang, Yanmin
2010-06-10  6:52   ` Peter Zijlstra
2010-06-10  6:59     ` Zhang, Yanmin
2010-06-21 10:21       ` Peter Zijlstra
2010-06-24  9:55         ` Peter Zijlstra
2010-06-29  7:40           ` Zhang, Yanmin
2010-06-29  7:48             ` 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=20100607111407.309924253@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=paulmck@linux.vnet.ibm.com \
    --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).