Skip to main content

Browse the archive

Revision 3ad33b2436b545cbe8b28e53f3710432cad457ab authored by Lee Schermerhorn on 15 November 2007, 00:59:10 UTC, committed by Linus Torvalds on 15 November 2007, 02:45:38 UTC 
Migration: find correct vma in new_vma_page()
 
We hit the BUG_ON() in mm/rmap.c:vma_address() when trying to migrate via
mbind(MPOL_MF_MOVE) a non-anon region that spans multiple vmas.  For
anon-regions, we just fail to migrate any pages beyond the 1st vma in the
range.

This occurs because do_mbind() collects a list of pages to migrate by
calling check_range().  check_range() walks the task's mm, spanning vmas as
necessary, to collect the migratable pages into a list.  Then, do_mbind()
calls migrate_pages() passing the list of pages, a function to allocate new
pages based on vma policy [new_vma_page()], and a pointer to the first vma
of the range.

For each page in the list, new_vma_page() calls page_address_in_vma()
passing the page and the vma [first in range] to obtain the address to get
for alloc_page_vma().  The page address is needed to get interleaving
policy correct.  If the pages in the list come from multiple vmas,
eventually, new_page_address() will pass that page to page_address_in_vma()
with the incorrect vma.  For !PageAnon pages, this will result in a bug
check in rmap.c:vma_address().  For anon pages, vma_address() will just
return EFAULT and fail the migration.

This patch modifies new_vma_page() to check the return value from
page_address_in_vma().  If the return value is EFAULT, new_vma_page()
searchs forward via vm_next for the vma that maps the page--i.e., that does
not return EFAULT.  This assumes that the pages in the list handed to
migrate_pages() is in address order.  This is currently case.  The patch
documents this assumption in a new comment block for new_vma_page().

If new_vma_page() cannot locate the vma mapping the page in a forward
search in the mm, it will pass a NULL vma to alloc_page_vma().  This will
result in the allocation using the task policy, if any, else system default
policy.  This situation is unlikely, but the patch documents this behavior
with a comment.

Note, this patch results in restarting from the first vma in a multi-vma
range each time new_vma_page() is called.  If this is not acceptable, we
can make the vma argument a pointer, both in new_vma_page() and it's caller
unmap_and_move() so that the value held by the loop in migrate_pages()
always passes down the last vma in which a page was found.  This will
require changes to all new_page_t functions passed to migrate_pages().  Is
this necessary?

For this patch to work, we can't bug check in vma_address() for pages
outside the argument vma.  This patch removes the BUG_ON().  All other
callers [besides new_vma_page()] already check the return status.

Tested on x86_64, 4 node NUMA platform.

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent e1a1c99
Raw File
semaphore.h 
/*
 * linux/include/asm-xtensa/semaphore.h
 *
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 2001 - 2005 Tensilica Inc.
 */

#ifndef _XTENSA_SEMAPHORE_H
#define _XTENSA_SEMAPHORE_H

#include <asm/atomic.h>
#include <asm/system.h>
#include <linux/wait.h>
#include <linux/rwsem.h>

struct semaphore {
	atomic_t count;
	int sleepers;
	wait_queue_head_t wait;
};

#define __SEMAPHORE_INITIALIZER(name,n)					\
{									\
	.count		= ATOMIC_INIT(n),				\
	.sleepers	= 0,						\
	.wait		= __WAIT_QUEUE_HEAD_INITIALIZER((name).wait)	\
}

#define __DECLARE_SEMAPHORE_GENERIC(name,count) 			\
	struct semaphore name = __SEMAPHORE_INITIALIZER(name,count)

#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name,1)

static inline void sema_init (struct semaphore *sem, int val)
{
	atomic_set(&sem->count, val);
	sem->sleepers = 0;
	init_waitqueue_head(&sem->wait);
}

static inline void init_MUTEX (struct semaphore *sem)
{
	sema_init(sem, 1);
}

static inline void init_MUTEX_LOCKED (struct semaphore *sem)
{
	sema_init(sem, 0);
}

asmlinkage void __down(struct semaphore * sem);
asmlinkage int  __down_interruptible(struct semaphore * sem);
asmlinkage int  __down_trylock(struct semaphore * sem);
asmlinkage void __up(struct semaphore * sem);

extern spinlock_t semaphore_wake_lock;

static inline void down(struct semaphore * sem)
{
	might_sleep();

	if (atomic_sub_return(1, &sem->count) < 0)
		__down(sem);
}

static inline int down_interruptible(struct semaphore * sem)
{
	int ret = 0;

	might_sleep();

	if (atomic_sub_return(1, &sem->count) < 0)
		ret = __down_interruptible(sem);
	return ret;
}

static inline int down_trylock(struct semaphore * sem)
{
	int ret = 0;

	if (atomic_sub_return(1, &sem->count) < 0)
		ret = __down_trylock(sem);
	return ret;
}

/*
 * Note! This is subtle. We jump to wake people up only if
 * the semaphore was negative (== somebody was waiting on it).
 */
static inline void up(struct semaphore * sem)
{
	if (atomic_add_return(1, &sem->count) <= 0)
		__up(sem);
}

#endif /* _XTENSA_SEMAPHORE_H */
back to top