From: Ingo Molnar <mingo@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
linux-mm <linux-mm@kvack.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Paul Turner <pjt@google.com>,
Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
Christoph Lameter <cl@linux.com>, Rik van Riel <riel@redhat.com>,
Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Johannes Weiner <hannes@cmpxchg.org>,
Hugh Dickins <hughd@google.com>
Subject: [PATCH 1/2] mm/rmap: Convert the struct anon_vma::mutex to an rwsem
Date: Sat, 1 Dec 2012 21:10:30 +0100 [thread overview]
Message-ID: <20121201201030.GA2704@gmail.com> (raw)
In-Reply-To: <CA+55aFyq7OaUxcEHXvJhp0T57KN14o-RGxqPmA+ks8ge6zJh5w@mail.gmail.com>
Convert the struct anon_vma::mutex to an rwsem, which will help
in solving a page-migration scalability problem. (Addressed in
a separate patch.)
The conversion is simple and straightforward: in every case
where we mutex_lock()ed we'll now down_write().
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/linux/rmap.h | 16 ++++++++--------
mm/huge_memory.c | 4 ++--
mm/mmap.c | 8 ++++----
mm/rmap.c | 22 +++++++++++-----------
4 files changed, 25 insertions(+), 25 deletions(-)
Index: linux/include/linux/rmap.h
===================================================================
--- linux.orig/include/linux/rmap.h
+++ linux/include/linux/rmap.h
@@ -7,7 +7,7 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/mm.h>
-#include <linux/mutex.h>
+#include <linux/rwsem.h>
#include <linux/memcontrol.h>
/*
@@ -25,8 +25,8 @@
* pointing to this anon_vma once its vma list is empty.
*/
struct anon_vma {
- struct anon_vma *root; /* Root of this anon_vma tree */
- struct mutex mutex; /* Serialize access to vma list */
+ struct anon_vma *root; /* Root of this anon_vma tree */
+ struct rw_semaphore rwsem; /* W: modification, R: walking the list */
/*
* The refcount is taken on an anon_vma when there is no
* guarantee that the vma of page tables will exist for
@@ -64,7 +64,7 @@ struct anon_vma_chain {
struct vm_area_struct *vma;
struct anon_vma *anon_vma;
struct list_head same_vma; /* locked by mmap_sem & page_table_lock */
- struct rb_node rb; /* locked by anon_vma->mutex */
+ struct rb_node rb; /* locked by anon_vma->rwsem */
unsigned long rb_subtree_last;
#ifdef CONFIG_DEBUG_VM_RB
unsigned long cached_vma_start, cached_vma_last;
@@ -108,24 +108,24 @@ static inline void vma_lock_anon_vma(str
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma)
- mutex_lock(&anon_vma->root->mutex);
+ down_write(&anon_vma->root->rwsem);
}
static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma)
- mutex_unlock(&anon_vma->root->mutex);
+ up_write(&anon_vma->root->rwsem);
}
static inline void anon_vma_lock(struct anon_vma *anon_vma)
{
- mutex_lock(&anon_vma->root->mutex);
+ down_write(&anon_vma->root->rwsem);
}
static inline void anon_vma_unlock(struct anon_vma *anon_vma)
{
- mutex_unlock(&anon_vma->root->mutex);
+ up_write(&anon_vma->root->rwsem);
}
/*
Index: linux/mm/huge_memory.c
===================================================================
--- linux.orig/mm/huge_memory.c
+++ linux/mm/huge_memory.c
@@ -1388,7 +1388,7 @@ static int __split_huge_page_splitting(s
* We can't temporarily set the pmd to null in order
* to split it, the pmd must remain marked huge at all
* times or the VM won't take the pmd_trans_huge paths
- * and it won't wait on the anon_vma->root->mutex to
+ * and it won't wait on the anon_vma->root->rwsem to
* serialize against split_huge_page*.
*/
pmdp_splitting_flush(vma, address, pmd);
@@ -1591,7 +1591,7 @@ static int __split_huge_page_map(struct
return ret;
}
-/* must be called with anon_vma->root->mutex hold */
+/* must be called with anon_vma->root->rwsem held */
static void __split_huge_page(struct page *page,
struct anon_vma *anon_vma)
{
Index: linux/mm/mmap.c
===================================================================
--- linux.orig/mm/mmap.c
+++ linux/mm/mmap.c
@@ -2561,15 +2561,15 @@ static void vm_lock_anon_vma(struct mm_s
* The LSB of head.next can't change from under us
* because we hold the mm_all_locks_mutex.
*/
- mutex_lock_nest_lock(&anon_vma->root->mutex, &mm->mmap_sem);
+ down_write(&anon_vma->root->rwsem);
/*
* We can safely modify head.next after taking the
- * anon_vma->root->mutex. If some other vma in this mm shares
+ * anon_vma->root->rwsem. If some other vma in this mm shares
* the same anon_vma we won't take it again.
*
* No need of atomic instructions here, head.next
* can't change from under us thanks to the
- * anon_vma->root->mutex.
+ * anon_vma->root->rwsem.
*/
if (__test_and_set_bit(0, (unsigned long *)
&anon_vma->root->rb_root.rb_node))
@@ -2671,7 +2671,7 @@ static void vm_unlock_anon_vma(struct an
*
* No need of atomic instructions here, head.next
* can't change from under us until we release the
- * anon_vma->root->mutex.
+ * anon_vma->root->rwsem.
*/
if (!__test_and_clear_bit(0, (unsigned long *)
&anon_vma->root->rb_root.rb_node))
Index: linux/mm/rmap.c
===================================================================
--- linux.orig/mm/rmap.c
+++ linux/mm/rmap.c
@@ -24,7 +24,7 @@
* mm->mmap_sem
* page->flags PG_locked (lock_page)
* mapping->i_mmap_mutex
- * anon_vma->mutex
+ * anon_vma->rwsem
* mm->page_table_lock or pte_lock
* zone->lru_lock (in mark_page_accessed, isolate_lru_page)
* swap_lock (in swap_duplicate, swap_info_get)
@@ -37,7 +37,7 @@
* in arch-dependent flush_dcache_mmap_lock,
* within bdi.wb->list_lock in __sync_single_inode)
*
- * anon_vma->mutex,mapping->i_mutex (memory_failure, collect_procs_anon)
+ * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon)
* ->tasklist_lock
* pte map lock
*/
@@ -103,7 +103,7 @@ static inline void anon_vma_free(struct
* LOCK should suffice since the actual taking of the lock must
* happen _before_ what follows.
*/
- if (mutex_is_locked(&anon_vma->root->mutex)) {
+ if (rwsem_is_locked(&anon_vma->root->rwsem)) {
anon_vma_lock(anon_vma);
anon_vma_unlock(anon_vma);
}
@@ -219,9 +219,9 @@ static inline struct anon_vma *lock_anon
struct anon_vma *new_root = anon_vma->root;
if (new_root != root) {
if (WARN_ON_ONCE(root))
- mutex_unlock(&root->mutex);
+ up_write(&root->rwsem);
root = new_root;
- mutex_lock(&root->mutex);
+ down_write(&root->rwsem);
}
return root;
}
@@ -229,7 +229,7 @@ static inline struct anon_vma *lock_anon
static inline void unlock_anon_vma_root(struct anon_vma *root)
{
if (root)
- mutex_unlock(&root->mutex);
+ up_write(&root->rwsem);
}
/*
@@ -349,7 +349,7 @@ void unlink_anon_vmas(struct vm_area_str
/*
* Iterate the list once more, it now only contains empty and unlinked
* anon_vmas, destroy them. Could not do before due to __put_anon_vma()
- * needing to acquire the anon_vma->root->mutex.
+ * needing to write-acquire the anon_vma->root->rwsem.
*/
list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
struct anon_vma *anon_vma = avc->anon_vma;
@@ -365,7 +365,7 @@ static void anon_vma_ctor(void *data)
{
struct anon_vma *anon_vma = data;
- mutex_init(&anon_vma->mutex);
+ init_rwsem(&anon_vma->rwsem);
atomic_set(&anon_vma->refcount, 0);
anon_vma->rb_root = RB_ROOT;
}
@@ -457,14 +457,14 @@ struct anon_vma *page_lock_anon_vma(stru
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
root_anon_vma = ACCESS_ONCE(anon_vma->root);
- if (mutex_trylock(&root_anon_vma->mutex)) {
+ if (down_write_trylock(&root_anon_vma->rwsem)) {
/*
* If the page is still mapped, then this anon_vma is still
* its anon_vma, and holding the mutex ensures that it will
* not go away, see anon_vma_free().
*/
if (!page_mapped(page)) {
- mutex_unlock(&root_anon_vma->mutex);
+ up_write(&root_anon_vma->rwsem);
anon_vma = NULL;
}
goto out;
@@ -1299,7 +1299,7 @@ out_mlock:
/*
* We need mmap_sem locking, Otherwise VM_LOCKED check makes
* unstable result and race. Plus, We can't wait here because
- * we now hold anon_vma->mutex or mapping->i_mmap_mutex.
+ * we now hold anon_vma->rwsem or mapping->i_mmap_mutex.
* if trylock failed, the page remain in evictable lru and later
* vmscan could retry to move the page to unevictable lru if the
* page is actually mlocked.
--
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>
next prev parent reply other threads:[~2012-12-01 20:10 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-30 19:58 [PATCH 00/10] Latest numa/core release, v18 Ingo Molnar
2012-11-30 19:58 ` [PATCH 01/10] sched: Add "task flipping" support Ingo Molnar
2012-11-30 19:58 ` [PATCH 02/10] sched: Move the NUMA placement logic to a worklet Ingo Molnar
2012-11-30 19:58 ` [PATCH 03/10] numa, mempolicy: Improve CONFIG_NUMA_BALANCING=y OOM behavior Ingo Molnar
2012-11-30 19:58 ` [PATCH 04/10] mm, numa: Turn 4K pte NUMA faults into effective hugepage ones Ingo Molnar
2012-11-30 19:58 ` [PATCH 05/10] sched: Introduce directed NUMA convergence Ingo Molnar
2012-11-30 19:58 ` [PATCH 06/10] sched: Remove statistical NUMA scheduling Ingo Molnar
2012-11-30 19:58 ` [PATCH 07/10] sched: Track quality and strength of convergence Ingo Molnar
2012-11-30 19:58 ` [PATCH 08/10] sched: Converge NUMA migrations Ingo Molnar
2012-11-30 19:58 ` [PATCH 09/10] sched: Add convergence strength based adaptive NUMA page fault rate Ingo Molnar
2012-11-30 19:58 ` [PATCH 10/10] sched: Refine the 'shared tasks' memory interleaving logic Ingo Molnar
2012-11-30 20:37 ` [PATCH 00/10] Latest numa/core release, v18 Linus Torvalds
2012-12-01 9:49 ` [RFC PATCH] mm/migration: Don't lock anon vmas in rmap_walk_anon() Ingo Molnar
2012-12-01 12:26 ` [RFC PATCH] mm/migration: Remove anon vma locking from try_to_unmap() use Ingo Molnar
2012-12-01 18:38 ` Linus Torvalds
2012-12-01 18:41 ` Ingo Molnar
2012-12-01 18:50 ` Linus Torvalds
2012-12-01 20:10 ` Ingo Molnar [this message]
2012-12-01 20:19 ` [PATCH 1/2] mm/rmap: Convert the struct anon_vma::mutex to an rwsem Rik van Riel
2012-12-02 15:10 ` Ingo Molnar
2012-12-03 13:59 ` Mel Gorman
2012-12-01 20:15 ` [PATCH 2/2] mm/migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable Ingo Molnar
2012-12-01 20:33 ` Rik van Riel
2012-12-02 15:12 ` [PATCH 2/2, v2] " Ingo Molnar
2012-12-02 17:53 ` Rik van Riel
2012-12-04 14:42 ` Michel Lespinasse
2012-12-05 2:59 ` Michel Lespinasse
2012-12-03 14:17 ` [PATCH 2/2] " Mel Gorman
2012-12-04 14:37 ` Michel Lespinasse
2012-12-04 18:17 ` Mel Gorman
2012-12-01 18:55 ` [RFC PATCH] mm/migration: Remove anon vma locking from try_to_unmap() use Rik van Riel
2012-12-01 16:19 ` [RFC PATCH] mm/migration: Don't lock anon vmas in rmap_walk_anon() Rik van Riel
2012-12-01 17:55 ` Linus Torvalds
2012-12-01 18:30 ` Ingo Molnar
2012-12-03 13:41 ` [PATCH 00/10] Latest numa/core release, v18 Mel Gorman
2012-12-04 17:30 ` Thomas Gleixner
2012-12-03 10:43 ` Mel Gorman
2012-12-03 11:32 ` Mel Gorman
2012-12-04 22:49 ` Mel Gorman
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=20121201201030.GA2704@gmail.com \
--to=mingo@kernel.org \
--cc=Lee.Schermerhorn@hp.com \
--cc=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=pjt@google.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