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.
   could replace all the switch()es with a mempolicy_ops structure.
*/

#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/mm.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/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/mempolicy.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.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 kmem_cache_t *policy_cache;
static kmem_cache_t *sn_cache;

#define PDprintk(fmt...)

/* Highest zone. An specific allocation for a zone below that is not
   policied. */
int policy_zone = ZONE_DMA;

struct mempolicy default_policy = {
	.refcnt = ATOMIC_INIT(1), /* never free it */
	.policy = MPOL_DEFAULT,
};

/* Do sanity checking on a policy */
static int mpol_check_policy(int mode, nodemask_t *nodes)
{
	int empty = nodes_empty(*nodes);

	switch (mode) {
	case MPOL_DEFAULT:
		if (!empty)
			return -EINVAL;
		break;
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		/* Preferred will only use the first bit, but allow
		   more for now. */
		if (empty)
			return -EINVAL;
		break;
	}
	return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL;
}
/* Generate a custom zonelist for the BIND policy. */
static struct zonelist *bind_zonelist(nodemask_t *nodes)
{
	struct zonelist *zl;
	int num, max, nd;

	max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
	zl = kmalloc(sizeof(void *) * max, GFP_KERNEL);
	if (!zl)
		return NULL;
	num = 0;
	for_each_node_mask(nd, *nodes)
		zl->zones[num++] = &NODE_DATA(nd)->node_zones[policy_zone];
	zl->zones[num] = NULL;
	return zl;
}

/* Create a new policy */
static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
{
	struct mempolicy *policy;

	PDprintk("setting mode %d nodes[0] %lx\n", mode, nodes_addr(*nodes)[0]);
	if (mode == MPOL_DEFAULT)
		return NULL;
	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!policy)
		return ERR_PTR(-ENOMEM);
	atomic_set(&policy->refcnt, 1);
	switch (mode) {
	case MPOL_INTERLEAVE:
		policy->v.nodes = *nodes;
		if (nodes_weight(*nodes) == 0) {
			kmem_cache_free(policy_cache, policy);
			return ERR_PTR(-EINVAL);
		}
		break;
	case MPOL_PREFERRED:
		policy->v.preferred_node = first_node(*nodes);
		if (policy->v.preferred_node >= MAX_NUMNODES)
			policy->v.preferred_node = -1;
		break;
	case MPOL_BIND:
		policy->v.zonelist = bind_zonelist(nodes);
		if (policy->v.zonelist == NULL) {
			kmem_cache_free(policy_cache, policy);
			return ERR_PTR(-ENOMEM);
		}
		break;
	}
	policy->policy = mode;
	policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
	return policy;
}

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,
		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;
		unsigned int nid;

		if (!pte_present(*pte))
			continue;
		page = vm_normal_page(vma, addr, *pte);
		if (!page)
			continue;
		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);
		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
			spin_unlock(ptl);
			migrate_page_add(vma, page, private, flags);
			spin_lock(ptl);
		}
		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 a vma is migratable */
static inline int vma_migratable(struct vm_area_struct *vma)
{
	if (vma->vm_flags & (
		VM_LOCKED|VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED))
		return 0;
	return 1;
}

/*
 * 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;

	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;

	PDprintk("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_free(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;
}

static int contextualize_policy(int mode, nodemask_t *nodes)
{
	if (!nodes)
		return 0;

	cpuset_update_task_memory_state();
	if (!cpuset_nodes_subset_current_mems_allowed(*nodes))
		return -EINVAL;
	return mpol_check_policy(mode, nodes);
}

/* Set the process memory policy */
long do_set_mempolicy(int mode, nodemask_t *nodes)
{
	struct mempolicy *new;

	if (contextualize_policy(mode, nodes))
		return -EINVAL;
	new = mpol_new(mode, nodes);
	if (IS_ERR(new))
		return PTR_ERR(new);
	mpol_free(current->mempolicy);
	current->mempolicy = new;
	if (new && new->policy == MPOL_INTERLEAVE)
		current->il_next = first_node(new->v.nodes);
	return 0;
}

/* Fill a zone bitmap for a policy */
static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
{
	int i;

	nodes_clear(*nodes);
	switch (p->policy) {
	case MPOL_BIND:
		for (i = 0; p->v.zonelist->zones[i]; i++)
			node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id,
				*nodes);
		break;
	case MPOL_DEFAULT:
		break;
	case MPOL_INTERLEAVE:
		*nodes = p->v.nodes;
		break;
	case MPOL_PREFERRED:
		/* or use current node instead of online map? */
		if (p->v.preferred_node < 0)
			*nodes = node_online_map;
		else
			node_set(p->v.preferred_node, *nodes);
		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 */
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))
		return -EINVAL;
	if (flags & MPOL_F_ADDR) {
		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;

	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->policy == MPOL_INTERLEAVE) {
			*policy = current->il_next;
		} else {
			err = -EINVAL;
			goto out;
		}
	} else
		*policy = pol->policy;

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

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

 out:
	if (vma)
		up_read(&current->mm->mmap_sem);
	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
 * want a function that moves pages between the two nodesets in such
 * a way 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 count = 0;
	nodemask_t nodes;

	nodes_andnot(nodes, *from_nodes, *to_nodes);

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

	if (!list_empty(&pagelist)) {
		count = swap_pages(&pagelist);
		putback_lru_pages(&pagelist);
	}

	up_read(&mm->mmap_sem);
	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.
 */

/* 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;

	--maxnode;
	nodes_clear(*nodes);
	if (maxnode == 0 || !nmask)
		return 0;

	nlongs = BITS_TO_LONGS(maxnode);
	if ((maxnode % BITS_PER_LONG) == 0)
		endmask = ~0UL;
	else
		endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;

	/* When the user specified more nodes than supported just check
	   if the non supported part is all zero. */
	if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
		if (nlongs > PAGE_SIZE/sizeof(long))
			return -EINVAL;
		for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
			unsigned long t;
			if (get_user(t, nmask + k))
				return -EFAULT;
			if (k == nlongs - 1) {
				if (t & endmask)
					return -EINVAL;
			} else if (t)
				return -EINVAL;
		}
		nlongs = BITS_TO_LONGS(MAX_NUMNODES);
		endmask = ~0UL;
	}

	if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
		return -EFAULT;
	nodes_addr(*nodes)[nlongs-1] &= endmask;
	return 0;
}

/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
			      nodemask_t *nodes)
{
	unsigned long copy = ALIGN(maxnode-1, 64) / 8;
	const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);

	if (copy > nbytes) {
		if (copy > PAGE_SIZE)
			return -EINVAL;
		if (clear_user((char __user *)mask + nbytes, copy - nbytes))
			return -EFAULT;
		copy = nbytes;
	}
	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}

asmlinkage long sys_mbind(unsigned long start, unsigned long len,
			unsigned long mode,
			unsigned long __user *nmask, unsigned long maxnode,
			unsigned flags)
{
	nodemask_t nodes;
	int err;

	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_mbind(start, len, mode, &nodes, flags);
}

/* Set the process memory policy */
asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
		unsigned long maxnode)
{
	int err;
	nodemask_t nodes;

	if (mode < 0 || mode > MPOL_MAX)
		return -EINVAL;
	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_set_mempolicy(mode, &nodes);
}

asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
		const unsigned long __user *old_nodes,
		const unsigned long __user *new_nodes)
{
	struct mm_struct *mm;
	struct task_struct *task;
	nodemask_t old;
	nodemask_t new;
	nodemask_t task_nodes;
	int err;

	err = get_nodes(&old, old_nodes, maxnode);
	if (err)
		return err;

	err = get_nodes(&new, new_nodes, maxnode);
	if (err)
		return err;

	/* Find the mm_struct */
	read_lock(&tasklist_lock);
	task = pid ? find_task_by_pid(pid) : current;
	if (!task) {
		read_unlock(&tasklist_lock);
		return -ESRCH;
	}
	mm = get_task_mm(task);
	read_unlock(&tasklist_lock);

	if (!mm)
		return -EINVAL;

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser priviledges or the same
	 * userid as the target process.
	 */
	if ((current->euid != task->suid) && (current->euid != task->uid) &&
	    (current->uid != task->suid) && (current->uid != task->uid) &&
	    !capable(CAP_SYS_ADMIN)) {
		err = -EPERM;
		goto out;
	}

	task_nodes = cpuset_mems_allowed(task);
	/* Is the user allowed to access the target nodes? */
	if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_ADMIN)) {
		err = -EPERM;
		goto out;
	}

	err = do_migrate_pages(mm, &old, &new, MPOL_MF_MOVE);
out:
	mmput(mm);
	return err;
}


/* Retrieve NUMA policy */
asmlinkage long sys_get_mempolicy(int __user *policy,
				unsigned long __user *nmask,
				unsigned long maxnode,
				unsigned long addr, unsigned long flags)
{
	int err, pval;
	nodemask_t nodes;

	if (nmask != NULL && maxnode < MAX_NUMNODES)
		return -EINVAL;

	err = do_get_mempolicy(&pval, &nodes, addr, flags);

	if (err)
		return err;

	if (policy && put_user(pval, policy))
		return -EFAULT;

	if (nmask)
		err = copy_nodes_to_user(nmask, maxnode, &nodes);

	return err;
}

#ifdef CONFIG_COMPAT

asmlinkage long compat_sys_get_mempolicy(int __user *policy,
				     compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode,
				     compat_ulong_t addr, compat_ulong_t flags)
{
	long err;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask)
		nm = compat_alloc_user_space(alloc_size);

	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);

	if (!err && nmask) {
		err = copy_from_user(bm, nm, alloc_size);
		/* ensure entire bitmap is zeroed */
		err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
		err |= compat_put_bitmap(nmask, bm, nr_bits);
	}

	return err;
}

asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(bm, nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, bm, alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_set_mempolicy(mode, nm, nr_bits+1);
}

asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
			     compat_ulong_t mode, compat_ulong_t __user *nmask,
			     compat_ulong_t maxnode, compat_ulong_t flags)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	nodemask_t bm;

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}

#endif

/* Return effective policy for a VMA */
static struct mempolicy * get_vma_policy(struct task_struct *task,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = task->mempolicy;

	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else if (vma->vm_policy &&
				vma->vm_policy->policy != MPOL_DEFAULT)
			pol = vma->vm_policy;
	}
	if (!pol)
		pol = &default_policy;
	return pol;
}

/* Return a zonelist representing a mempolicy */
static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
{
	int nd;

	switch (policy->policy) {
	case MPOL_PREFERRED:
		nd = policy->v.preferred_node;
		if (nd < 0)
			nd = numa_node_id();
		break;
	case MPOL_BIND:
		/* Lower zones don't get a policy applied */
		/* Careful: current->mems_allowed might have moved */
		if (gfp_zone(gfp) >= policy_zone)
			if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
				return policy->v.zonelist;
		/*FALL THROUGH*/
	case MPOL_INTERLEAVE: /* should not happen */
	case MPOL_DEFAULT:
		nd = numa_node_id();
		break;
	default:
		nd = 0;
		BUG();
	}
	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
}

/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
	unsigned nid, next;
	struct task_struct *me = current;

	nid = me->il_next;
	next = next_node(nid, policy->v.nodes);
	if (next >= MAX_NUMNODES)
		next = first_node(policy->v.nodes);
	me->il_next = next;
	return nid;