Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 6ce3c4c0 authored by Christoph Lameter's avatar Christoph Lameter Committed by Linus Torvalds
Browse files

[PATCH] Move page migration related functions near do_migrate_pages() 



Group page migration functions in mempolicy.c

Add a forward declaration for migrate_page_add (like gather_stats()) and use
our new found mobility to group all page migration related function around
do_migrate_pages().

Signed-off-by: default avatarChristoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent 48fce342

mm/mempolicy.c

+138 −132
Original line number Diff line number Diff line
@@ -183,55 +183,9 @@ static struct mempolicy *mpol_new(int mode, nodemask_t *nodes) 
	return policy;

}



/* Check if we are the only process mapping the page in question */

static inline int single_mm_mapping(struct mm_struct *mm,

			struct address_space *mapping)

{

	struct vm_area_struct *vma;

	struct prio_tree_iter iter;

	int rc = 1;



	spin_lock(&mapping->i_mmap_lock);

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)

		if (mm != vma->vm_mm) {

			rc = 0;

			goto out;

		}

	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)

		if (mm != vma->vm_mm) {

			rc = 0;

			goto out;

		}

out:

	spin_unlock(&mapping->i_mmap_lock);

	return rc;

}



/*

 * Add a page to be migrated to the pagelist

 */

static void migrate_page_add(struct vm_area_struct *vma,

	struct page *page, struct list_head *pagelist, unsigned long flags)

{

	/*

	 * Avoid migrating a page that is shared by others and not writable.

	 */

	if ((flags & MPOL_MF_MOVE_ALL) || !page->mapping || PageAnon(page) ||

	    mapping_writably_mapped(page->mapping) ||

	    single_mm_mapping(vma->vm_mm, page->mapping)) {

		int rc = isolate_lru_page(page);



		if (rc == 1)

			list_add(&page->lru, pagelist);

		/*

		 * If the isolate attempt was not successful then we just

		 * encountered an unswappable page. Something must be wrong.

	 	 */

		WARN_ON(rc == 0);

	}

}



static void gather_stats(struct page *, void *);

static void migrate_page_add(struct vm_area_struct *vma,

	struct page *page, struct list_head *pagelist, unsigned long flags);



/* Scan through pages checking if pages follow certain conditions. */

static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
@@ -440,90 +394,6 @@ static int contextualize_policy(int mode, nodemask_t *nodes) 
	return mpol_check_policy(mode, nodes);

}



static int swap_pages(struct list_head *pagelist)

{

	LIST_HEAD(moved);

	LIST_HEAD(failed);

	int n;



	n = migrate_pages(pagelist, NULL, &moved, &failed);

	putback_lru_pages(&failed);

	putback_lru_pages(&moved);



	return n;

}



long do_mbind(unsigned long start, unsigned long len,

		unsigned long mode, nodemask_t *nmask, unsigned long flags)

{

	struct vm_area_struct *vma;

	struct mm_struct *mm = current->mm;

	struct mempolicy *new;

	unsigned long end;

	int err;

	LIST_HEAD(pagelist);



	if ((flags & ~(unsigned long)(MPOL_MF_STRICT |

				      MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))

	    || mode > MPOL_MAX)

		return -EINVAL;

	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_RESOURCE))

		return -EPERM;



	if (start & ~PAGE_MASK)

		return -EINVAL;



	if (mode == MPOL_DEFAULT)

		flags &= ~MPOL_MF_STRICT;



	len = (len + PAGE_SIZE - 1) & PAGE_MASK;

	end = start + len;



	if (end < start)

		return -EINVAL;

	if (end == start)

		return 0;



	if (mpol_check_policy(mode, nmask))

		return -EINVAL;



	new = mpol_new(mode, nmask);

	if (IS_ERR(new))

		return PTR_ERR(new);



	/*

	 * If we are using the default policy then operation

	 * on discontinuous address spaces is okay after all

	 */

	if (!new)

		flags |= MPOL_MF_DISCONTIG_OK;



	PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,

			mode,nodes_addr(nodes)[0]);



	down_write(&mm->mmap_sem);

	vma = check_range(mm, start, end, nmask,

			  flags | MPOL_MF_INVERT, &pagelist);



	err = PTR_ERR(vma);

	if (!IS_ERR(vma)) {

		int nr_failed = 0;



		err = mbind_range(vma, start, end, new);

		if (!list_empty(&pagelist))

			nr_failed = swap_pages(&pagelist);



		if (!err && nr_failed && (flags & MPOL_MF_STRICT))

			err = -EIO;

	}

	if (!list_empty(&pagelist))

		putback_lru_pages(&pagelist);



	up_write(&mm->mmap_sem);

	mpol_free(new);

	return err;

}



/* Set the process memory policy */

long do_set_mempolicy(int mode, nodemask_t *nodes)

{
@@ -643,6 +513,71 @@ long do_get_mempolicy(int *policy, nodemask_t *nmask, 
	return err;

}



/*

 * page migration

 */



/* Check if we are the only process mapping the page in question */

static inline int single_mm_mapping(struct mm_struct *mm,

			struct address_space *mapping)

{

	struct vm_area_struct *vma;

	struct prio_tree_iter iter;

	int rc = 1;



	spin_lock(&mapping->i_mmap_lock);

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)

		if (mm != vma->vm_mm) {

			rc = 0;

			goto out;

		}

	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)

		if (mm != vma->vm_mm) {

			rc = 0;

			goto out;

		}

out:

	spin_unlock(&mapping->i_mmap_lock);

	return rc;

}



/*

 * Add a page to be migrated to the pagelist

 */

static void migrate_page_add(struct vm_area_struct *vma,

	struct page *page, struct list_head *pagelist, unsigned long flags)

{

	/*

	 * Avoid migrating a page that is shared by others and not writable.

	 */

	if ((flags & MPOL_MF_MOVE_ALL) || !page->mapping || PageAnon(page) ||

	    mapping_writably_mapped(page->mapping) ||

	    single_mm_mapping(vma->vm_mm, page->mapping)) {

		int rc = isolate_lru_page(page);



		if (rc == 1)

			list_add(&page->lru, pagelist);

		/*

		 * If the isolate attempt was not successful then we just

		 * encountered an unswappable page. Something must be wrong.

	 	 */

		WARN_ON(rc == 0);

	}

}



static int swap_pages(struct list_head *pagelist)

{

	LIST_HEAD(moved);

	LIST_HEAD(failed);

	int n;



	n = migrate_pages(pagelist, NULL, &moved, &failed);

	putback_lru_pages(&failed);

	putback_lru_pages(&moved);



	return n;

}



/*

 * For now migrate_pages simply swaps out the pages from nodes that are in

 * the source set but not in the target set. In the future, we would
@@ -673,6 +608,77 @@ int do_migrate_pages(struct mm_struct *mm, 
	return count;

}



long do_mbind(unsigned long start, unsigned long len,

		unsigned long mode, nodemask_t *nmask, unsigned long flags)

{

	struct vm_area_struct *vma;

	struct mm_struct *mm = current->mm;

	struct mempolicy *new;

	unsigned long end;

	int err;

	LIST_HEAD(pagelist);



	if ((flags & ~(unsigned long)(MPOL_MF_STRICT |

				      MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))

	    || mode > MPOL_MAX)

		return -EINVAL;

	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_RESOURCE))

		return -EPERM;



	if (start & ~PAGE_MASK)

		return -EINVAL;



	if (mode == MPOL_DEFAULT)

		flags &= ~MPOL_MF_STRICT;



	len = (len + PAGE_SIZE - 1) & PAGE_MASK;

	end = start + len;



	if (end < start)

		return -EINVAL;

	if (end == start)

		return 0;



	if (mpol_check_policy(mode, nmask))

		return -EINVAL;



	new = mpol_new(mode, nmask);

	if (IS_ERR(new))

		return PTR_ERR(new);



	/*

	 * If we are using the default policy then operation

	 * on discontinuous address spaces is okay after all

	 */

	if (!new)

		flags |= MPOL_MF_DISCONTIG_OK;



	PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,

			mode,nodes_addr(nodes)[0]);



	down_write(&mm->mmap_sem);

	vma = check_range(mm, start, end, nmask,

			  flags | MPOL_MF_INVERT, &pagelist);



	err = PTR_ERR(vma);

	if (!IS_ERR(vma)) {

		int nr_failed = 0;



		err = mbind_range(vma, start, end, new);

		if (!list_empty(&pagelist))

			nr_failed = swap_pages(&pagelist);



		if (!err && nr_failed && (flags & MPOL_MF_STRICT))

			err = -EIO;

	}

	if (!list_empty(&pagelist))

		putback_lru_pages(&pagelist);



	up_write(&mm->mmap_sem);

	mpol_free(new);

	return err;

}



/*

 * User space interface with variable sized bitmaps for nodelists.

 */