mempolicy.c

/*
 * Simple NUMA memory policy for the Linux kernel.
 *
 * Copyright 2003,2004 Andi Kleen, SuSE Labs.
 * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
 * Subject to the GNU Public License, version 2.
 *
 * NUMA policy allows the user to give hints in which node(s) memory should
 * be allocated.
 *
 * Support four policies per VMA and per process:
 *
 * The VMA policy has priority over the process policy for a page fault.
 *
 * interleave     Allocate memory interleaved over a set of nodes,
 *                with normal fallback if it fails.
 *                For VMA based allocations this interleaves based on the
 *                offset into the backing object or offset into the mapping
 *                for anonymous memory. For process policy an process counter
 *                is used.
 *
 * bind           Only allocate memory on a specific set of nodes,
 *                no fallback.
 *                FIXME: memory is allocated starting with the first node
 *                to the last. It would be better if bind would truly restrict
 *                the allocation to memory nodes instead
 *
 * preferred       Try a specific node first before normal fallback.
 *                As a special case node -1 here means do the allocation
 *                on the local CPU. This is normally identical to default,
 *                but useful to set in a VMA when you have a non default
 *                process policy.
 *
 * default        Allocate on the local node first, or when on a VMA
 *                use the process policy. This is what Linux always did
 *		  in a NUMA aware kernel and still does by, ahem, default.
 *
 * The process policy is applied for most non interrupt memory allocations
 * in that process' context. Interrupts ignore the policies and always
 * try to allocate on the local CPU. The VMA policy is only applied for memory
 * allocations for a VMA in the VM.
 *
 * Currently there are a few corner cases in swapping where the policy
 * is not applied, but the majority should be handled. When process policy
 * is used it is not remembered over swap outs/swap ins.
 *
 * Only the highest zone in the zone hierarchy gets policied. Allocations
 * requesting a lower zone just use default policy. This implies that
 * on systems with highmem kernel lowmem allocation don't get policied.
 * Same with GFP_DMA allocations.
 *
 * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
 * all users and remembered even when nobody has memory mapped.
 */

/* Notebook:
   fix mmap readahead to honour policy and enable policy for any page cache
   object
   statistics for bigpages
   global policy for page cache? currently it uses process policy. Requires
   first item above.
   handle mremap for shared memory (currently ignored for the policy)
   grows down?
   make bind policy root only? It can trigger oom much faster and the
   kernel is not always grateful with that.
*/

#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/migrate.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/syscalls.h>

#include <asm/tlbflush.h>
#include <asm/uaccess.h>

/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)	/* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2)		/* Gather statistics */

static struct kmem_cache *policy_cache;
static struct kmem_cache *sn_cache;

/* Highest zone. An specific allocation for a zone below that is not
   policied. */
enum zone_type policy_zone = 0;

/*
 * run-time system-wide default policy => local allocation
 */
struct mempolicy default_policy = {
	.refcnt = ATOMIC_INIT(1), /* never free it */
	.mode = MPOL_PREFERRED,
	.v =  { .preferred_node =  -1 },
};

static const struct mempolicy_operations {
	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
	void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
} mpol_ops[MPOL_MAX];

/* Check that the nodemask contains at least one populated zone */
static int is_valid_nodemask(const nodemask_t *nodemask)
{
	int nd, k;

	/* Check that there is something useful in this mask */
	k = policy_zone;

	for_each_node_mask(nd, *nodemask) {
		struct zone *z;

		for (k = 0; k <= policy_zone; k++) {
			z = &NODE_DATA(nd)->node_zones[k];
			if (z->present_pages > 0)
				return 1;
		}
	}

	return 0;
}

static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
{
	return pol->flags & (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES);
}

static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
				   const nodemask_t *rel)
{
	nodemask_t tmp;
	nodes_fold(tmp, *orig, nodes_weight(*rel));
	nodes_onto(*ret, tmp, *rel);
}

static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (nodes_empty(*nodes))
		return -EINVAL;
	pol->v.nodes = *nodes;
	return 0;
}

static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (!nodes)
		pol->v.preferred_node = -1;	/* local allocation */
	else if (nodes_empty(*nodes))
		return -EINVAL;			/*  no allowed nodes */
	else
		pol->v.preferred_node = first_node(*nodes);
	return 0;
}

static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (!is_valid_nodemask(nodes))
		return -EINVAL;
	pol->v.nodes = *nodes;
	return 0;
}

/* Create a new policy */
static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
				  nodemask_t *nodes)
{
	struct mempolicy *policy;
	nodemask_t cpuset_context_nmask;
	int ret;

	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);

	if (mode == MPOL_DEFAULT) {
		if (nodes && !nodes_empty(*nodes))
			return ERR_PTR(-EINVAL);
		return NULL;	/* simply delete any existing policy */
	}
	VM_BUG_ON(!nodes);

	/*
	 * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
	 * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
	 * All other modes require a valid pointer to a non-empty nodemask.
	 */
	if (mode == MPOL_PREFERRED) {
		if (nodes_empty(*nodes)) {
			if (((flags & MPOL_F_STATIC_NODES) ||
			     (flags & MPOL_F_RELATIVE_NODES)))
				return ERR_PTR(-EINVAL);
			nodes = NULL;	/* flag local alloc */
		}
	} else if (nodes_empty(*nodes))
		return ERR_PTR(-EINVAL);
	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!policy)
		return ERR_PTR(-ENOMEM);
	atomic_set(&policy->refcnt, 1);
	policy->mode = mode;
	policy->flags = flags;

	if (nodes) {
		/*
		 * cpuset related setup doesn't apply to local allocation
		 */
		cpuset_update_task_memory_state();
		if (flags & MPOL_F_RELATIVE_NODES)
			mpol_relative_nodemask(&cpuset_context_nmask, nodes,
					       &cpuset_current_mems_allowed);
		else
			nodes_and(cpuset_context_nmask, *nodes,
				  cpuset_current_mems_allowed);
		if (mpol_store_user_nodemask(policy))
			policy->w.user_nodemask = *nodes;
		else
			policy->w.cpuset_mems_allowed =
						cpuset_mems_allowed(current);
	}

	ret = mpol_ops[mode].create(policy,
				nodes ? &cpuset_context_nmask : NULL);
	if (ret < 0) {
		kmem_cache_free(policy_cache, policy);
		return ERR_PTR(ret);
	}
	return policy;
}

/* Slow path of a mpol destructor. */
void __mpol_put(struct mempolicy *p)
{
	if (!atomic_dec_and_test(&p->refcnt))
		return;
	kmem_cache_free(policy_cache, p);
}

static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
{
}

static void mpol_rebind_nodemask(struct mempolicy *pol,
				 const nodemask_t *nodes)
{
	nodemask_t tmp;

	if (pol->flags & MPOL_F_STATIC_NODES)
		nodes_and(tmp, pol->w.user_nodemask, *nodes);
	else if (pol->flags & MPOL_F_RELATIVE_NODES)
		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
	else {
		nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed,
			    *nodes);
		pol->w.cpuset_mems_allowed = *nodes;
	}

	pol->v.nodes = tmp;
	if (!node_isset(current->il_next, tmp)) {
		current->il_next = next_node(current->il_next, tmp);
		if (current->il_next >= MAX_NUMNODES)
			current->il_next = first_node(tmp);
		if (current->il_next >= MAX_NUMNODES)
			current->il_next = numa_node_id();
	}
}

static void mpol_rebind_preferred(struct mempolicy *pol,
				  const nodemask_t *nodes)
{
	nodemask_t tmp;

	if (pol->flags & MPOL_F_STATIC_NODES) {
		int node = first_node(pol->w.user_nodemask);

		if (node_isset(node, *nodes))
			pol->v.preferred_node = node;
		else
			pol->v.preferred_node = -1;
	} else if (pol->flags & MPOL_F_RELATIVE_NODES) {
		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
		pol->v.preferred_node = first_node(tmp);
	} else if (pol->v.preferred_node != -1) {
		pol->v.preferred_node = node_remap(pol->v.preferred_node,
						   pol->w.cpuset_mems_allowed,
						   *nodes);
		pol->w.cpuset_mems_allowed = *nodes;
	}
}

/* Migrate a policy to a different set of nodes */
static void mpol_rebind_policy(struct mempolicy *pol,
			       const nodemask_t *newmask)
{
	if (!pol)
		return;
	if (!mpol_store_user_nodemask(pol) &&
	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
		return;
	mpol_ops[pol->mode].rebind(pol, newmask);
}

/*
 * Wrapper for mpol_rebind_policy() that just requires task
 * pointer, and updates task mempolicy.
 */

void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
{
	mpol_rebind_policy(tsk->mempolicy, new);
}

/*
 * Rebind each vma in mm to new nodemask.
 *
 * Call holding a reference to mm.  Takes mm->mmap_sem during call.
 */

void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
	struct vm_area_struct *vma;

	down_write(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next)
		mpol_rebind_policy(vma->vm_policy, new);
	up_write(&mm->mmap_sem);
}

static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
	[MPOL_DEFAULT] = {
		.rebind = mpol_rebind_default,
	},
	[MPOL_INTERLEAVE] = {
		.create = mpol_new_interleave,
		.rebind = mpol_rebind_nodemask,
	},
	[MPOL_PREFERRED] = {
		.create = mpol_new_preferred,
		.rebind = mpol_rebind_preferred,
	},
	[MPOL_BIND] = {
		.create = mpol_new_bind,
		.rebind = mpol_rebind_nodemask,
	},
};

static void gather_stats(struct page *, void *, int pte_dirty);
static void migrate_page_add(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,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pte_t *orig_pte;
	pte_t *pte;
	spinlock_t *ptl;

	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	do {
		struct page *page;
		int nid;

		if (!pte_present(*pte))
			continue;
		page = vm_normal_page(vma, addr, *pte);
		if (!page)
			continue;
		/*
		 * The check for PageReserved here is important to avoid
		 * handling zero pages and other pages that may have been
		 * marked special by the system.
		 *
		 * If the PageReserved would not be checked here then f.e.
		 * the location of the zero page could have an influence
		 * on MPOL_MF_STRICT, zero pages would be counted for
		 * the per node stats, and there would be useless attempts
		 * to put zero pages on the migration list.
		 */
		if (PageReserved(page))
			continue;
		nid = page_to_nid(page);
		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
			continue;

		if (flags & MPOL_MF_STATS)
			gather_stats(page, private, pte_dirty(*pte));
		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
			migrate_page_add(page, private, flags);
		else
			break;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap_unlock(orig_pte, ptl);
	return addr != end;
}

static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		if (check_pte_range(vma, pmd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		if (check_pmd_range(vma, pud, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static inline int check_pgd_range(struct vm_area_struct *vma,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pgd_t *pgd;
	unsigned long next;

	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		if (check_pud_range(vma, pgd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pgd++, addr = next, addr != end);
	return 0;
}

/*
 * Check if all pages in a range are on a set of nodes.
 * If pagelist != NULL then isolate pages from the LRU and
 * put them on the pagelist.
 */
static struct vm_area_struct *
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
		const nodemask_t *nodes, unsigned long flags, void *private)
{
	int err;
	struct vm_area_struct *first, *vma, *prev;

	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {

		err = migrate_prep();
		if (err)
			return ERR_PTR(err);
	}

	first = find_vma(mm, start);
	if (!first)
		return ERR_PTR(-EFAULT);
	prev = NULL;
	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
			if (!vma->vm_next && vma->vm_end < end)
				return ERR_PTR(-EFAULT);
			if (prev && prev->vm_end < vma->vm_start)
				return ERR_PTR(-EFAULT);
		}
		if (!is_vm_hugetlb_page(vma) &&
		    ((flags & MPOL_MF_STRICT) ||
		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
				vma_migratable(vma)))) {
			unsigned long endvma = vma->vm_end;

			if (endvma > end)
				endvma = end;
			if (vma->vm_start > start)
				start = vma->vm_start;
			err = check_pgd_range(vma, start, endvma, nodes,
						flags, private);
			if (err) {
				first = ERR_PTR(err);
				break;
			}
		}
		prev = vma;
	}
	return first;
}

/* Apply policy to a single VMA */
static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
{
	int err = 0;
	struct mempolicy *old = vma->vm_policy;

	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
		 vma->vm_ops, vma->vm_file,
		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);

	if (vma->vm_ops && vma->vm_ops->set_policy)
		err = vma->vm_ops->set_policy(vma, new);
	if (!err) {
		mpol_get(new);
		vma->vm_policy = new;
		mpol_put(old);
	}
	return err;
}

/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct vm_area_struct *vma, unsigned long start,
		       unsigned long end, struct mempolicy *new)
{
	struct vm_area_struct *next;
	int err;

	err = 0;
	for (; vma && vma->vm_start < end; vma = next) {
		next = vma->vm_next;
		if (vma->vm_start < start)
			err = split_vma(vma->vm_mm, vma, start, 1);
		if (!err && vma->vm_end > end)
			err = split_vma(vma->vm_mm, vma, end, 0);
		if (!err)
			err = policy_vma(vma, new);
		if (err)
			break;
	}
	return err;
}

/*
 * Update task->flags PF_MEMPOLICY bit: set iff non-default
 * mempolicy.  Allows more rapid checking of this (combined perhaps
 * with other PF_* flag bits) on memory allocation hot code paths.
 *
 * If called from outside this file, the task 'p' should -only- be
 * a newly forked child not yet visible on the task list, because
 * manipulating the task flags of a visible task is not safe.
 *
 * The above limitation is why this routine has the funny name
 * mpol_fix_fork_child_flag().
 *
 * It is also safe to call this with a task pointer of current,
 * which the static wrapper mpol_set_task_struct_flag() does,
 * for use within this file.
 */

void mpol_fix_fork_child_flag(struct task_struct *p)
{
	if (p->mempolicy)
		p->flags |= PF_MEMPOLICY;
	else
		p->flags &= ~PF_MEMPOLICY;
}

static void mpol_set_task_struct_flag(void)
{
	mpol_fix_fork_child_flag(current);
}

/* Set the process memory policy */
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
			     nodemask_t *nodes)
{
	struct mempolicy *new;
	struct mm_struct *mm = current->mm;

	new = mpol_new(mode, flags, nodes);
	if (IS_ERR(new))
		return PTR_ERR(new);

	/*
	 * prevent changing our mempolicy while show_numa_maps()
	 * is using it.
	 * Note:  do_set_mempolicy() can be called at init time
	 * with no 'mm'.
	 */
	if (mm)
		down_write(&mm->mmap_sem);
	mpol_put(current->mempolicy);
	current->mempolicy = new;
	mpol_set_task_struct_flag();
	if (new && new->mode == MPOL_INTERLEAVE &&
	    nodes_weight(new->v.nodes))
		current->il_next = first_node(new->v.nodes);
	if (mm)
		up_write(&mm->mmap_sem);

	return 0;
}

/*
 * Return nodemask for policy for get_mempolicy() query
 */
static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
{
	nodes_clear(*nodes);
	if (p == &default_policy)
		return;

	switch (p->mode) {
	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		*nodes = p->v.nodes;
		break;
	case MPOL_PREFERRED:
		if (p->v.preferred_node >= 0)
			node_set(p->v.preferred_node, *nodes);
		/* else return empty node mask for local allocation */
		break;
	default:
		BUG();
	}
}

static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
	struct page *p;
	int err;

	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
	if (err >= 0) {
		err = page_to_nid(p);
		put_page(p);
	}
	return err;
}

/* Retrieve NUMA policy */
static long do_get_mempolicy(int *policy, nodemask_t *nmask,
			     unsigned long addr, unsigned long flags)
{
	int err;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	struct mempolicy *pol = current->mempolicy;

	cpuset_update_task_memory_state();
	if (flags &
		~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
		return -EINVAL;

	if (flags & MPOL_F_MEMS_ALLOWED) {
		if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
			return -EINVAL;
		*policy = 0;	/* just so it's initialized */
		*nmask  = cpuset_current_mems_allowed;
		return 0;
	}

	if (flags & MPOL_F_ADDR) {
		/*
		 * Do NOT fall back to task policy if the
		 * vma/shared policy at addr is NULL.  We
		 * want to return MPOL_DEFAULT in this case.
		 */
		down_read(&mm->mmap_sem);
		vma = find_vma_intersection(mm, addr, addr+1);
		if (!vma) {
			up_read(&mm->mmap_sem);
			return -EFAULT;
		}
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else
			pol = vma->vm_policy;
	} else if (addr)
		return -EINVAL;

	if (!pol)
		pol = &default_policy;	/* indicates default behavior */

	if (flags & MPOL_F_NODE) {
		if (flags & MPOL_F_ADDR) {
			err = lookup_node(mm, addr);
			if (err < 0)
				goto out;
			*policy = err;
		} else if (pol == current->mempolicy &&
				pol->mode == MPOL_INTERLEAVE) {
			*policy = current->il_next;
		} else {
			err = -EINVAL;
			goto out;
		}
	} else {
		*policy = pol == &default_policy ? MPOL_DEFAULT :
						pol->mode;
		*policy |= pol->flags;
	}

	if (vma) {
		up_read(&current->mm->mmap_sem);
		vma = NULL;
	}

	err = 0;
	if (nmask)
		get_policy_nodemask(pol, nmask);

 out:
	mpol_cond_put(pol);
	if (vma)
		up_read(&current->mm->mmap_sem);
	return err;
}

#ifdef CONFIG_MIGRATION
/*
 * page migration
 */
static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags)
{
	/*
	 * Avoid migrating a page that is shared with others.
	 */
	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1)
		isolate_lru_page(page, pagelist);
}

static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
	return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
}

/*
 * Migrate pages from one node to a target node.
 * Returns error or the number of pages not migrated.
 */
static int migrate_to_node(struct mm_struct *mm, int source, int dest,
			   int flags)
{
	nodemask_t nmask;
	LIST_HEAD(pagelist);
	int err = 0;

	nodes_clear(nmask);
	node_set(source, nmask);

	check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask,
			flags | MPOL_MF_DISCONTIG_OK, &pagelist);

	if (!list_empty(&pagelist))
		err = migrate_pages(&pagelist, new_node_page, dest);

	return err;
}

/*
 * Move pages between the two nodesets so as to preserve the physical
 * layout as much as possible.
 *
 * Returns the number of page that could not be moved.
 */
int do_migrate_pages(struct mm_struct *mm,
	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
	LIST_HEAD(pagelist);
	int busy = 0;
	int err = 0;
	nodemask_t tmp;

	down_read(&mm->mmap_sem);

	err = migrate_vmas(mm, from_nodes, to_nodes, flags);
	if (err)
		goto out;

/*
 * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
 * bit in 'to' is not also set in 'tmp'.  Clear the found 'source'
 * bit in 'tmp', and return that <source, dest> pair for migration.
 * The pair of nodemasks 'to' and 'from' define the map.
 *
 * If no pair of bits is found that way, fallback to picking some
 * pair of 'source' and 'dest' bits that are not the same.  If the
 * 'source' and 'dest' bits are the same, this represents a node
 * that will be migrating to itself, so no pages need move.
 *
 * If no bits are left in 'tmp', or if all remaining bits left
 * in 'tmp' correspond to the same bit in 'to', return false
 * (nothing left to migrate).
 *
 * This lets us pick a pair of nodes to migrate between, such that
 * if possible the dest node is not already occupied by some other
 * source node, minimizing the risk of overloading the memory on a
 * node that would happen if we migrated incoming memory to a node
 * before migrating outgoing memory source that same node.
 *
 * A single scan of tmp is sufficient.  As we go, we remember the
 * most recent <s, d> pair that moved (s != d).  If we find a pair
 * that not only moved, but what's better, moved to an empty slot
 * (d is not set in tmp), then we break out then, with that pair.
 * Otherwise when we finish scannng from_tmp, we at least have the
 * most recent <s, d> pair that moved.  If we get all the way through
 * the scan of tmp without finding any node that moved, much less
 * moved to an empty node, then there is nothing left worth migrating.
 */

	tmp = *from_nodes;
	while (!nodes_empty(tmp)) {
		int s,d;
		int source = -1;
		int dest = 0;

		for_each_node_mask(s, tmp) {
			d = node_remap(s, *from_nodes, *to_nodes);
			if (s == d)
				continue;

			source = s;	/* Node moved. Memorize */
			dest = d;

			/* dest not in remaining from nodes? */
			if (!node_isset(dest, tmp))
				break;
		}
		if (source == -1)
			break;

		node_clear(source, tmp);
		err = migrate_to_node(mm, source, dest, flags);
		if (err > 0)
			busy += err;
		if (err < 0)
			break;
	}
out:
	up_read(&mm->mmap_sem);
	if (err < 0)
		return err;
	return busy;

}

/*
 * Allocate a new page for page migration based on vma policy.
 * Start assuming that page is mapped by vma pointed to by @private.
 * Search forward from there, if not.  N.B., this assumes that the
 * list of pages handed to migrate_pages()--which is how we get here--
 * is in virtual address order.
 */
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
	struct vm_area_struct *vma = (struct vm_area_struct *)private;
	unsigned long uninitialized_var(address);

	while (vma) {
		address = page_address_in_vma(page, vma);
		if (address != -EFAULT)
			break;
		vma = vma->vm_next;
	}

	/*
	 * if !vma, alloc_page_vma() will use task or system default policy
	 */
	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
}
#else

static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags)
{
}

int do_migrate_pages(struct mm_struct *mm,
	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
	return -ENOSYS;
}

static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
	return NULL;
}
#endif

static long do_mbind(unsigned long start, unsigned long len,
		     unsigned short mode, unsigned short mode_flags,
		     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))
		return -EINVAL;
	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
		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;

	new = mpol_new(mode, mode_flags, 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;

	pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
		 start, start + len, mode, mode_flags,
		 nmask ? nodes_addr(*nmask)[0] : -1);

	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 = migrate_pages(&pagelist, new_vma_page,
						(unsigned long)vma);

		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
			err = -EIO;
	}

	up_write(&mm->mmap_sem);
	mpol_put(new);
	return err;
}

/*
 * User space interface with variable sized bitmaps for nodelists.
 */

/* Copy a node mask from user space. */
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
		     unsigned long maxnode)
{
	unsigned long k;
	unsigned long nlongs;
	unsigned long endmask;