X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Fmempolicy.c;h=a9963ceddd65c483f589efe4f5c5124bddd36e8c;hb=16c70f8c1b54b61c3b951b6fb220df250fe09b32;hp=d06eabbf74f0b0d2a1b2053fe784fed58e534368;hpb=9bf4aaab3e101692164d49b7ca357651eb691cb6;p=linux-2.6.git

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d06eabbf7..a9963cedd 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2,6 +2,7 @@
  * 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
@@ -17,13 +18,19 @@
  *                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.
@@ -66,6 +73,8 @@
 #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>
@@ -74,39 +83,39 @@
 #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 <linux/migrate.h>
+#include <linux/rmap.h>
+#include <linux/security.h>
+
+#include <asm/tlbflush.h>
 #include <asm/uaccess.h>
 
-static kmem_cache_t *policy_cache;
-static kmem_cache_t *sn_cache;
+/* 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;
 
 #define PDprintk(fmt...)
 
 /* Highest zone. An specific allocation for a zone below that is not
    policied. */
-static int policy_zone;
+int policy_zone = ZONE_DMA;
 
-static struct mempolicy default_policy = {
+struct mempolicy default_policy = {
 	.refcnt = ATOMIC_INIT(1), /* never free it */
 	.policy = MPOL_DEFAULT,
 };
 
-/* Check if all specified nodes are online */
-static int nodes_online(unsigned long *nodes)
-{
-	DECLARE_BITMAP(online2, MAX_NUMNODES);
-
-	bitmap_copy(online2, node_online_map, MAX_NUMNODES);
-	if (bitmap_empty(online2, MAX_NUMNODES))
-		set_bit(0, online2);
-	if (!bitmap_subset(nodes, online2, MAX_NUMNODES))
-		return -EINVAL;
-	return 0;
-}
-
 /* Do sanity checking on a policy */
-static int mpol_check_policy(int mode, unsigned long *nodes)
+static int mpol_check_policy(int mode, nodemask_t *nodes)
 {
-	int empty = bitmap_empty(nodes, MAX_NUMNODES);
+	int empty = nodes_empty(*nodes);
 
 	switch (mode) {
 	case MPOL_DEFAULT:
@@ -121,86 +130,41 @@ static int mpol_check_policy(int mode, unsigned long *nodes)
 			return -EINVAL;
 		break;
 	}
-	return nodes_online(nodes);
-}
-
-/* Copy a node mask from user space. */
-static int get_nodes(unsigned long *nodes, unsigned long __user *nmask,
-		     unsigned long maxnode, int mode)
-{
-	unsigned long k;
-	unsigned long nlongs;
-	unsigned long endmask;
-
-	--maxnode;
-	bitmap_zero(nodes, MAX_NUMNODES);
-	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)) {
-		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, nmask, nlongs*sizeof(unsigned long)))
-		return -EFAULT;
-	nodes[nlongs-1] &= endmask;
-	return mpol_check_policy(mode, nodes);
+	return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL;
 }
 
 /* Generate a custom zonelist for the BIND policy. */
-static struct zonelist *bind_zonelist(unsigned long *nodes)
+static struct zonelist *bind_zonelist(nodemask_t *nodes)
 {
 	struct zonelist *zl;
-	int num, max, nd;
+	int num, max, nd, k;
 
-	max = 1 + MAX_NR_ZONES * bitmap_weight(nodes, MAX_NUMNODES);
-	zl = kmalloc(sizeof(void *) * max, GFP_KERNEL);
+	max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
+	zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL);
 	if (!zl)
 		return NULL;
 	num = 0;
-	for (nd = find_first_bit(nodes, MAX_NUMNODES);
-	     nd < MAX_NUMNODES;
-	     nd = find_next_bit(nodes, MAX_NUMNODES, 1+nd)) {
-		int k;
-		for (k = MAX_NR_ZONES-1; k >= 0; k--) {
+	/* First put in the highest zones from all nodes, then all the next 
+	   lower zones etc. Avoid empty zones because the memory allocator
+	   doesn't like them. If you implement node hot removal you
+	   have to fix that. */
+	for (k = policy_zone; k >= 0; k--) { 
+		for_each_node_mask(nd, *nodes) { 
 			struct zone *z = &NODE_DATA(nd)->node_zones[k];
-			if (!z->present_pages)
-				continue;
-			zl->zones[num++] = z;
-			if (k > policy_zone)
-				policy_zone = k;
+			if (z->present_pages > 0) 
+				zl->zones[num++] = z;
 		}
 	}
-	BUG_ON(num >= max);
 	zl->zones[num] = NULL;
 	return zl;
 }
 
 /* Create a new policy */
-static struct mempolicy *mpol_new(int mode, unsigned long *nodes)
+static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
 {
 	struct mempolicy *policy;
 
-	PDprintk("setting mode %d nodes[0] %lx\n", mode, nodes[0]);
+	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);
@@ -209,10 +173,14 @@ static struct mempolicy *mpol_new(int mode, unsigned long *nodes)
 	atomic_set(&policy->refcnt, 1);
 	switch (mode) {
 	case MPOL_INTERLEAVE:
-		bitmap_copy(policy->v.nodes, nodes, MAX_NUMNODES);
+		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 = find_first_bit(nodes, MAX_NUMNODES);
+		policy->v.preferred_node = first_node(*nodes);
 		if (policy->v.preferred_node >= MAX_NUMNODES)
 			policy->v.preferred_node = -1;
 		break;
@@ -225,61 +193,173 @@ static struct mempolicy *mpol_new(int mode, unsigned long *nodes)
 		break;
 	}
 	policy->policy = mode;
+	policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
 	return policy;
 }
 
-/* Ensure all existing pages follow the policy. */
-static int
-verify_pages(unsigned long addr, unsigned long end, unsigned long *nodes)
+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)
 {
-	while (addr < end) {
-		struct page *p;
-		pte_t *pte;
-		pmd_t *pmd;
-		pgd_t *pgd = pgd_offset_k(addr);
-		if (pgd_none(*pgd)) {
-			addr = (addr + PGDIR_SIZE) & PGDIR_MASK;
+	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;
-		}
-		pmd = pmd_offset(pgd, addr);
-		if (pmd_none(*pmd)) {
-			addr = (addr + PMD_SIZE) & PMD_MASK;
+		page = vm_normal_page(vma, addr, *pte);
+		if (!page)
 			continue;
-		}
-		p = NULL;
-		pte = pte_offset_map(pmd, addr);
-		if (pte_present(*pte))
-			p = pte_page(*pte);
-		pte_unmap(pte);
-		if (p) {
-			unsigned nid = page_to_nid(p);
-			if (!test_bit(nid, nodes))
-				return -EIO;
-		}
-		addr += PAGE_SIZE;
-	}
+		/*
+		 * 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;
 }
 
-/* Step 1: check the range */
+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,
-	    unsigned long *nodes, unsigned long flags)
+		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 (!vma->vm_next && vma->vm_end < end)
-			return ERR_PTR(-EFAULT);
-		if (prev && prev->vm_end < vma->vm_start)
-			return ERR_PTR(-EFAULT);
-		if ((flags & MPOL_MF_STRICT) && !is_vm_hugetlb_page(vma)) {
-			err = verify_pages(vma->vm_start, vma->vm_end, nodes);
+		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;
@@ -333,98 +413,89 @@ static int mbind_range(struct vm_area_struct *vma, unsigned long start,
 	return err;
 }
 
-/* Change policy for a memory range */
-asmlinkage long sys_mbind(unsigned long start, unsigned long len,
-			  unsigned long mode,
-			  unsigned long __user *nmask, unsigned long maxnode,
-			  unsigned flags)
+static int contextualize_policy(int mode, nodemask_t *nodes)
 {
-	struct vm_area_struct *vma;
-	struct mm_struct *mm = current->mm;
-	struct mempolicy *new;
-	unsigned long end;
-	DECLARE_BITMAP(nodes, MAX_NUMNODES);
-	int err;
+	if (!nodes)
+		return 0;
 
-	if ((flags & ~(unsigned long)(MPOL_MF_STRICT)) || mode > MPOL_MAX)
-		return -EINVAL;
-	if (start & ~PAGE_MASK)
+	cpuset_update_task_memory_state();
+	if (!cpuset_nodes_subset_current_mems_allowed(*nodes))
 		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;
+	return mpol_check_policy(mode, nodes);
+}
 
-	err = get_nodes(nodes, nmask, maxnode, mode);
-	if (err)
-		return err;
 
-	new = mpol_new(mode, nodes);
-	if (IS_ERR(new))
-		return PTR_ERR(new);
+/*
+ * 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.
+ */
 
-	PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
-			mode,nodes[0]);
+void mpol_fix_fork_child_flag(struct task_struct *p)
+{
+	if (p->mempolicy)
+		p->flags |= PF_MEMPOLICY;
+	else
+		p->flags &= ~PF_MEMPOLICY;
+}
 
-	down_write(&mm->mmap_sem);
-	vma = check_range(mm, start, end, nodes, flags);
-	err = PTR_ERR(vma);
-	if (!IS_ERR(vma))
-		err = mbind_range(vma, start, end, new);
-	up_write(&mm->mmap_sem);
-	mpol_free(new);
-	return err;
+static void mpol_set_task_struct_flag(void)
+{
+	mpol_fix_fork_child_flag(current);
 }
 
 /* Set the process memory policy */
-asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
-				   unsigned long maxnode)
+long do_set_mempolicy(int mode, nodemask_t *nodes)
 {
-	int err;
 	struct mempolicy *new;
-	DECLARE_BITMAP(nodes, MAX_NUMNODES);
 
-	if (mode > MPOL_MAX)
+	if (contextualize_policy(mode, nodes))
 		return -EINVAL;
-	err = get_nodes(nodes, nmask, maxnode, mode);
-	if (err)
-		return err;
 	new = mpol_new(mode, nodes);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 	mpol_free(current->mempolicy);
 	current->mempolicy = new;
+	mpol_set_task_struct_flag();
 	if (new && new->policy == MPOL_INTERLEAVE)
-		current->il_next = find_first_bit(new->v.nodes, MAX_NUMNODES);
+		current->il_next = first_node(new->v.nodes);
 	return 0;
 }
 
 /* Fill a zone bitmap for a policy */
-static void get_zonemask(struct mempolicy *p, unsigned long *nodes)
+static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
 {
 	int i;
 
-	bitmap_zero(nodes, MAX_NUMNODES);
+	nodes_clear(*nodes);
 	switch (p->policy) {
 	case MPOL_BIND:
 		for (i = 0; p->v.zonelist->zones[i]; i++)
-			__set_bit(p->v.zonelist->zones[i]->zone_pgdat->node_id, nodes);
+			node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id,
+				*nodes);
 		break;
 	case MPOL_DEFAULT:
 		break;
 	case MPOL_INTERLEAVE:
-		bitmap_copy(nodes, p->v.nodes, MAX_NUMNODES);
+		*nodes = p->v.nodes;
 		break;
 	case MPOL_PREFERRED:
 		/* or use current node instead of online map? */
 		if (p->v.preferred_node < 0)
-			bitmap_copy(nodes, node_online_map, MAX_NUMNODES);
+			*nodes = node_online_map;
 		else
-			__set_bit(p->v.preferred_node, nodes);
+			node_set(p->v.preferred_node, *nodes);
 		break;
 	default:
 		BUG();
@@ -438,43 +509,24 @@ static int lookup_node(struct mm_struct *mm, unsigned long addr)
 
 	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
 	if (err >= 0) {
-		err = page_zone(p)->zone_pgdat->node_id;
+		err = page_to_nid(p);
 		put_page(p);
 	}
 	return err;
 }
 
-/* Copy a kernel node mask to user space */
-static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
-			      void *nodes, unsigned nbytes)
-{
-	unsigned long copy = ALIGN(maxnode-1, 64) / 8;
-
-	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, copy) ? -EFAULT : 0;
-}
-
 /* Retrieve NUMA policy */
-asmlinkage long sys_get_mempolicy(int __user *policy,
-				  unsigned long __user *nmask,
-				  unsigned long maxnode,
-				  unsigned long addr, unsigned long flags)
+long do_get_mempolicy(int *policy, nodemask_t *nmask,
+			unsigned long addr, unsigned long flags)
 {
-	int err, pval;
+	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 (nmask != NULL && maxnode < numnodes)
-		return -EINVAL;
 	if (flags & MPOL_F_ADDR) {
 		down_read(&mm->mmap_sem);
 		vma = find_vma_intersection(mm, addr, addr+1);
@@ -497,60 +549,530 @@ asmlinkage long sys_get_mempolicy(int __user *policy,
 			err = lookup_node(mm, addr);
 			if (err < 0)
 				goto out;
-			pval = err;
+			*policy = err;
 		} else if (pol == current->mempolicy &&
 				pol->policy == MPOL_INTERLEAVE) {
-			pval = current->il_next;
+			*policy = current->il_next;
 		} else {
 			err = -EINVAL;
 			goto out;
 		}
 	} else
-		pval = pol->policy;
+		*policy = pol->policy;
 
-	err = -EFAULT;
-	if (policy && put_user(pval, policy))
-		goto out;
+	if (vma) {
+		up_read(&current->mm->mmap_sem);
+		vma = NULL;
+	}
 
 	err = 0;
-	if (nmask) {
-		DECLARE_BITMAP(nodes, MAX_NUMNODES);
-		get_zonemask(pol, nodes);
-		err = copy_nodes_to_user(nmask, maxnode, nodes, sizeof(nodes));
+	if (nmask)
+		get_zonemask(pol, nmask);
+
+ out:
+	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, 0);
+}
+
+/*
+ * Migrate pages from one node to a target node.
+ * Returns error or the number of pages not migrated.
+ */
+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;
+
+}
+
+static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+{
+	struct vm_area_struct *vma = (struct vm_area_struct *)private;
+
+	return alloc_page_vma(GFP_HIGHUSER, vma, page_address_in_vma(page, vma));
+}
+#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)
+{
+	return NULL;
+}
+#endif
+
+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_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;
+
+	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 = migrate_pages(&pagelist, new_vma_page,
+						(unsigned long)vma);
+
+		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
+			err = -EIO;
 	}
 
- out:
-	if (vma)
-		up_read(&current->mm->mmap_sem);
+	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;
+	if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
+		return -EINVAL;
+
+	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 privileges 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_NICE)) {
+		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_NICE)) {
+		err = -EPERM;
+		goto out;
+	}
+
+	err = security_task_movememory(task);
+	if (err)
+		goto out;
+
+	err = do_migrate_pages(mm, &old, &new,
+		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : 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
-/* The other functions are compatible */
-asmlinkage long compat_get_mempolicy(int __user *policy,
-				  unsigned __user *nmask, unsigned  maxnode,
-				  unsigned addr, unsigned  flags)
+
+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(ALIGN(maxnode-1, 64) / 8);
-	err = sys_get_mempolicy(policy, nm, maxnode, addr, flags);
-	if (!err && copy_in_user(nmask, nm, ALIGN(maxnode-1, 32)/8))
-		err = -EFAULT;
+		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 vm_area_struct *vma, unsigned long addr)
+static struct mempolicy * get_vma_policy(struct task_struct *task,
+		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct mempolicy *pol = current->mempolicy;
+	struct mempolicy *pol = task->mempolicy;
 
 	if (vma) {
 		if (vma->vm_ops && vma->vm_ops->get_policy)
-		        pol = vma->vm_ops->get_policy(vma, addr);
+			pol = vma->vm_ops->get_policy(vma, addr);
 		else if (vma->vm_policy &&
 				vma->vm_policy->policy != MPOL_DEFAULT)
 			pol = vma->vm_policy;
@@ -561,7 +1083,7 @@ get_vma_policy(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /* Return a zonelist representing a mempolicy */
-static struct zonelist *zonelist_policy(unsigned gfp, struct mempolicy *policy)
+static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
 {
 	int nd;
 
@@ -573,8 +1095,10 @@ static struct zonelist *zonelist_policy(unsigned gfp, struct mempolicy *policy)
 		break;
 	case MPOL_BIND:
 		/* Lower zones don't get a policy applied */
-		if (gfp >= policy_zone)
-			return policy->v.zonelist;
+		/* 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:
@@ -584,7 +1108,7 @@ static struct zonelist *zonelist_policy(unsigned gfp, struct mempolicy *policy)
 		nd = 0;
 		BUG();
 	}
-	return NODE_DATA(nd)->node_zonelists + (gfp & GFP_ZONEMASK);
+	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
 }
 
 /* Do dynamic interleaving for a process */
@@ -594,47 +1118,107 @@ static unsigned interleave_nodes(struct mempolicy *policy)
 	struct task_struct *me = current;
 
 	nid = me->il_next;
-	BUG_ON(nid >= MAX_NUMNODES);
-	next = find_next_bit(policy->v.nodes, MAX_NUMNODES, 1+nid);
+	next = next_node(nid, policy->v.nodes);
 	if (next >= MAX_NUMNODES)
-		next = find_first_bit(policy->v.nodes, MAX_NUMNODES);
+		next = first_node(policy->v.nodes);
 	me->il_next = next;
 	return nid;
 }
 
+/*
+ * Depending on the memory policy provide a node from which to allocate the
+ * next slab entry.
+ */
+unsigned slab_node(struct mempolicy *policy)
+{
+	switch (policy->policy) {
+	case MPOL_INTERLEAVE:
+		return interleave_nodes(policy);
+
+	case MPOL_BIND:
+		/*
+		 * Follow bind policy behavior and start allocation at the
+		 * first node.
+		 */
+		return policy->v.zonelist->zones[0]->zone_pgdat->node_id;
+
+	case MPOL_PREFERRED:
+		if (policy->v.preferred_node >= 0)
+			return policy->v.preferred_node;
+		/* Fall through */
+
+	default:
+		return numa_node_id();
+	}
+}
+
 /* Do static interleaving for a VMA with known offset. */
 static unsigned offset_il_node(struct mempolicy *pol,
 		struct vm_area_struct *vma, unsigned long off)
 {
-	unsigned nnodes = bitmap_weight(pol->v.nodes, MAX_NUMNODES);
+	unsigned nnodes = nodes_weight(pol->v.nodes);
 	unsigned target = (unsigned)off % nnodes;
 	int c;
 	int nid = -1;
 
 	c = 0;
 	do {
-		nid = find_next_bit(pol->v.nodes, MAX_NUMNODES, nid+1);
+		nid = next_node(nid, pol->v.nodes);
 		c++;
 	} while (c <= target);
-	BUG_ON(nid >= MAX_NUMNODES);
-	BUG_ON(!test_bit(nid, pol->v.nodes));
 	return nid;
 }
 
+/* Determine a node number for interleave */
+static inline unsigned interleave_nid(struct mempolicy *pol,
+		 struct vm_area_struct *vma, unsigned long addr, int shift)
+{
+	if (vma) {
+		unsigned long off;
+
+		/*
+		 * for small pages, there is no difference between
+		 * shift and PAGE_SHIFT, so the bit-shift is safe.
+		 * for huge pages, since vm_pgoff is in units of small
+		 * pages, we need to shift off the always 0 bits to get
+		 * a useful offset.
+		 */
+		BUG_ON(shift < PAGE_SHIFT);
+		off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
+		off += (addr - vma->vm_start) >> shift;
+		return offset_il_node(pol, vma, off);
+	} else
+		return interleave_nodes(pol);
+}
+
+#ifdef CONFIG_HUGETLBFS
+/* Return a zonelist suitable for a huge page allocation. */
+struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr)
+{
+	struct mempolicy *pol = get_vma_policy(current, vma, addr);
+
+	if (pol->policy == MPOL_INTERLEAVE) {
+		unsigned nid;
+
+		nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
+		return NODE_DATA(nid)->node_zonelists + gfp_zone(GFP_HIGHUSER);
+	}
+	return zonelist_policy(GFP_HIGHUSER, pol);
+}
+#endif
+
 /* Allocate a page in interleaved policy.
    Own path because it needs to do special accounting. */
-static struct page *alloc_page_interleave(unsigned gfp, unsigned order, unsigned nid)
+static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
+					unsigned nid)
 {
 	struct zonelist *zl;
 	struct page *page;
 
-	BUG_ON(!test_bit(nid, node_online_map));
-	zl = NODE_DATA(nid)->node_zonelists + (gfp & GFP_ZONEMASK);
+	zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
 	page = __alloc_pages(gfp, order, zl);
-	if (page && page_zone(page) == zl->zones[0]) {
-		zl->zones[0]->pageset[get_cpu()].interleave_hit++;
-		put_cpu();
-	}
+	if (page && page_zone(page) == zl->zones[0])
+		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
 	return page;
 }
 
@@ -661,23 +1245,16 @@ static struct page *alloc_page_interleave(unsigned gfp, unsigned order, unsigned
  *	Should be called with the mm_sem of the vma hold.
  */
 struct page *
-alloc_page_vma(unsigned gfp, struct vm_area_struct *vma, unsigned long addr)
+alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 {
-	struct mempolicy *pol = get_vma_policy(vma, addr);
+	struct mempolicy *pol = get_vma_policy(current, vma, addr);
+
+	cpuset_update_task_memory_state();
 
 	if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
 		unsigned nid;
-		if (vma) {
-			unsigned long off;
-			BUG_ON(addr >= vma->vm_end);
-			BUG_ON(addr < vma->vm_start);
-			off = vma->vm_pgoff;
-			off += (addr - vma->vm_start) >> PAGE_SHIFT;
-			nid = offset_il_node(pol, vma, off);
-		} else {
-			/* fall back to process interleaving */
-			nid = interleave_nodes(pol);
-		}
+
+		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
 		return alloc_page_interleave(gfp, 0, nid);
 	}
 	return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol));
@@ -697,11 +1274,17 @@ alloc_page_vma(unsigned gfp, struct vm_area_struct *vma, unsigned long addr)
  *	Allocate a page from the kernel page pool.  When not in
  *	interrupt context and apply the current process NUMA policy.
  *	Returns NULL when no page can be allocated.
+ *
+ *	Don't call cpuset_update_task_memory_state() unless
+ *	1) it's ok to take cpuset_sem (can WAIT), and
+ *	2) allocating for current task (not interrupt).
  */
-struct page *alloc_pages_current(unsigned gfp, unsigned order)
+struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 
+	if ((gfp & __GFP_WAIT) && !in_interrupt())
+		cpuset_update_task_memory_state();
 	if (!pol || in_interrupt())
 		pol = &default_policy;
 	if (pol->policy == MPOL_INTERLEAVE)
@@ -710,6 +1293,15 @@ struct page *alloc_pages_current(unsigned gfp, unsigned order)
 }
 EXPORT_SYMBOL(alloc_pages_current);
 
+/*
+ * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
+ * rebinds the mempolicy its copying by calling mpol_rebind_policy()
+ * with the mems_allowed returned by cpuset_mems_allowed().  This
+ * keeps mempolicies cpuset relative after its cpuset moves.  See
+ * further kernel/cpuset.c update_nodemask().
+ */
+void *cpuset_being_rebound;
+
 /* Slow path of a mempolicy copy */
 struct mempolicy *__mpol_copy(struct mempolicy *old)
 {
@@ -717,6 +1309,10 @@ struct mempolicy *__mpol_copy(struct mempolicy *old)
 
 	if (!new)
 		return ERR_PTR(-ENOMEM);
+	if (current_cpuset_is_being_rebound()) {
+		nodemask_t mems = cpuset_mems_allowed(current);
+		mpol_rebind_policy(old, &mems);
+	}
 	*new = *old;
 	atomic_set(&new->refcnt, 1);
 	if (new->policy == MPOL_BIND) {
@@ -742,7 +1338,7 @@ int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 	case MPOL_DEFAULT:
 		return 1;
 	case MPOL_INTERLEAVE:
-		return bitmap_equal(a->v.nodes, b->v.nodes, MAX_NUMNODES);
+		return nodes_equal(a->v.nodes, b->v.nodes);
 	case MPOL_PREFERRED:
 		return a->v.preferred_node == b->v.preferred_node;
 	case MPOL_BIND: {
@@ -769,65 +1365,17 @@ void __mpol_free(struct mempolicy *p)
 	kmem_cache_free(policy_cache, p);
 }
 
-/*
- * Hugetlb policy. Same as above, just works with node numbers instead of
- * zonelists.
- */
-
-/* Find first node suitable for an allocation */
-int mpol_first_node(struct vm_area_struct *vma, unsigned long addr)
-{
-	struct mempolicy *pol = get_vma_policy(vma, addr);
-
-	switch (pol->policy) {
-	case MPOL_DEFAULT:
-		return numa_node_id();
-	case MPOL_BIND:
-		return pol->v.zonelist->zones[0]->zone_pgdat->node_id;
-	case MPOL_INTERLEAVE:
-		return interleave_nodes(pol);
-	case MPOL_PREFERRED:
-		return pol->v.preferred_node >= 0 ?
-				pol->v.preferred_node : numa_node_id();
-	}
-	BUG();
-	return 0;
-}
-
-/* Find secondary valid nodes for an allocation */
-int mpol_node_valid(int nid, struct vm_area_struct *vma, unsigned long addr)
-{
-	struct mempolicy *pol = get_vma_policy(vma, addr);
-
-	switch (pol->policy) {
-	case MPOL_PREFERRED:
-	case MPOL_DEFAULT:
-	case MPOL_INTERLEAVE:
-		return 1;
-	case MPOL_BIND: {
-		struct zone **z;
-		for (z = pol->v.zonelist->zones; *z; z++)
-			if ((*z)->zone_pgdat->node_id == nid)
-				return 1;
-		return 0;
-	}
-	default:
-		BUG();
-		return 0;
-	}
-}
-
 /*
  * Shared memory backing store policy support.
  *
  * Remember policies even when nobody has shared memory mapped.
  * The policies are kept in Red-Black tree linked from the inode.
- * They are protected by the sp->sem semaphore, which should be held
+ * They are protected by the sp->lock spinlock, which should be held
  * for any accesses to the tree.
  */
 
 /* lookup first element intersecting start-end */
-/* Caller holds sp->sem */
+/* Caller holds sp->lock */
 static struct sp_node *
 sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 {
@@ -835,13 +1383,13 @@ sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 
 	while (n) {
 		struct sp_node *p = rb_entry(n, struct sp_node, nd);
-		if (start >= p->end) {
+
+		if (start >= p->end)
 			n = n->rb_right;
-		} else if (end < p->start) {
+		else if (end <= p->start)
 			n = n->rb_left;
-		} else {
+		else
 			break;
-		}
 	}
 	if (!n)
 		return NULL;
@@ -859,7 +1407,7 @@ sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 }
 
 /* Insert a new shared policy into the list. */
-/* Caller holds sp->sem */
+/* Caller holds sp->lock */
 static void sp_insert(struct shared_policy *sp, struct sp_node *new)
 {
 	struct rb_node **p = &sp->root.rb_node;
@@ -889,13 +1437,15 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 	struct mempolicy *pol = NULL;
 	struct sp_node *sn;
 
-	down(&sp->sem);
+	if (!sp->root.rb_node)
+		return NULL;
+	spin_lock(&sp->lock);
 	sn = sp_lookup(sp, idx, idx+1);
 	if (sn) {
 		mpol_get(sn->policy);
 		pol = sn->policy;
 	}
-	up(&sp->sem);
+	spin_unlock(&sp->lock);
 	return pol;
 }
 
@@ -925,9 +1475,10 @@ sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol)
 static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 				 unsigned long end, struct sp_node *new)
 {
-	struct sp_node *n, *new2;
+	struct sp_node *n, *new2 = NULL;
 
-	down(&sp->sem);
+restart:
+	spin_lock(&sp->lock);
 	n = sp_lookup(sp, start, end);
 	/* Take care of old policies in the same range. */
 	while (n && n->start < end) {
@@ -940,16 +1491,18 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 		} else {
 			/* Old policy spanning whole new range. */
 			if (n->end > end) {
-				new2 = sp_alloc(end, n->end, n->policy);
 				if (!new2) {
-					up(&sp->sem);
-					return -ENOMEM;
+					spin_unlock(&sp->lock);
+					new2 = sp_alloc(end, n->end, n->policy);
+					if (!new2)
+						return -ENOMEM;
+					goto restart;
 				}
-				n->end = end;
+				n->end = start;
 				sp_insert(sp, new2);
-			}
-			/* Old crossing beginning, but not end (easy) */
-			if (n->start < start && n->end > start)
+				new2 = NULL;
+				break;
+			} else
 				n->end = start;
 		}
 		if (!next)
@@ -958,10 +1511,38 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 	}
 	if (new)
 		sp_insert(sp, new);
-	up(&sp->sem);
+	spin_unlock(&sp->lock);
+	if (new2) {
+		mpol_free(new2->policy);
+		kmem_cache_free(sn_cache, new2);
+	}
 	return 0;
 }
 
+void mpol_shared_policy_init(struct shared_policy *info, int policy,
+				nodemask_t *policy_nodes)
+{
+	info->root = RB_ROOT;
+	spin_lock_init(&info->lock);
+
+	if (policy != MPOL_DEFAULT) {
+		struct mempolicy *newpol;
+
+		/* Falls back to MPOL_DEFAULT on any error */
+		newpol = mpol_new(policy, policy_nodes);
+		if (!IS_ERR(newpol)) {
+			/* Create pseudo-vma that contains just the policy */
+			struct vm_area_struct pvma;
+
+			memset(&pvma, 0, sizeof(struct vm_area_struct));
+			/* Policy covers entire file */
+			pvma.vm_end = TASK_SIZE;
+			mpol_set_shared_policy(info, &pvma, newpol);
+			mpol_free(newpol);
+		}
+	}
+}
+
 int mpol_set_shared_policy(struct shared_policy *info,
 			struct vm_area_struct *vma, struct mempolicy *npol)
 {
@@ -972,7 +1553,7 @@ int mpol_set_shared_policy(struct shared_policy *info,
 	PDprintk("set_shared_policy %lx sz %lu %d %lx\n",
 		 vma->vm_pgoff,
 		 sz, npol? npol->policy : -1,
-		npol ? npol->v.nodes[0] : -1);
+		npol ? nodes_addr(npol->v.nodes)[0] : -1);
 
 	if (npol) {
 		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
@@ -991,7 +1572,9 @@ void mpol_free_shared_policy(struct shared_policy *p)
 	struct sp_node *n;
 	struct rb_node *next;
 
-	down(&p->sem);
+	if (!p->root.rb_node)
+		return;
+	spin_lock(&p->lock);
 	next = rb_first(&p->root);
 	while (next) {
 		n = rb_entry(next, struct sp_node, nd);
@@ -1000,7 +1583,7 @@ void mpol_free_shared_policy(struct shared_policy *p)
 		mpol_free(n->policy);
 		kmem_cache_free(sn_cache, n);
 	}
-	up(&p->sem);
+	spin_unlock(&p->lock);
 }
 
 /* assumes fs == KERNEL_DS */
@@ -1017,13 +1600,304 @@ void __init numa_policy_init(void)
 	/* Set interleaving policy for system init. This way not all
 	   the data structures allocated at system boot end up in node zero. */
 
-	if (sys_set_mempolicy(MPOL_INTERLEAVE, node_online_map, MAX_NUMNODES) < 0)
+	if (do_set_mempolicy(MPOL_INTERLEAVE, &node_online_map))
 		printk("numa_policy_init: interleaving failed\n");
 }
 
-/* Reset policy of current process to default.
- * Assumes fs == KERNEL_DS */
+/* Reset policy of current process to default */
 void numa_default_policy(void)
 {
-	sys_set_mempolicy(MPOL_DEFAULT, NULL, 0);
+	do_set_mempolicy(MPOL_DEFAULT, NULL);
+}
+
+/* Migrate a policy to a different set of nodes */
+void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
+{
+	nodemask_t *mpolmask;
+	nodemask_t tmp;
+
+	if (!pol)
+		return;
+	mpolmask = &pol->cpuset_mems_allowed;
+	if (nodes_equal(*mpolmask, *newmask))
+		return;
+
+	switch (pol->policy) {
+	case MPOL_DEFAULT:
+		break;
+	case MPOL_INTERLEAVE:
+		nodes_remap(tmp, pol->v.nodes, *mpolmask, *newmask);
+		pol->v.nodes = tmp;
+		*mpolmask = *newmask;
+		current->il_next = node_remap(current->il_next,
+						*mpolmask, *newmask);
+		break;
+	case MPOL_PREFERRED:
+		pol->v.preferred_node = node_remap(pol->v.preferred_node,
+						*mpolmask, *newmask);
+		*mpolmask = *newmask;
+		break;
+	case MPOL_BIND: {
+		nodemask_t nodes;
+		struct zone **z;
+		struct zonelist *zonelist;
+
+		nodes_clear(nodes);
+		for (z = pol->v.zonelist->zones; *z; z++)
+			node_set((*z)->zone_pgdat->node_id, nodes);
+		nodes_remap(tmp, nodes, *mpolmask, *newmask);
+		nodes = tmp;
+
+		zonelist = bind_zonelist(&nodes);
+
+		/* If no mem, then zonelist is NULL and we keep old zonelist.
+		 * If that old zonelist has no remaining mems_allowed nodes,
+		 * then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT.
+		 */
+
+		if (zonelist) {
+			/* Good - got mem - substitute new zonelist */
+			kfree(pol->v.zonelist);
+			pol->v.zonelist = zonelist;
+		}
+		*mpolmask = *newmask;
+		break;
+	}
+	default:
+		BUG();
+		break;
+	}
+}
+
+/*
+ * 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);
+}
+
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
+
+static const char *policy_types[] = { "default", "prefer", "bind",
+				      "interleave" };
+
+/*
+ * Convert a mempolicy into a string.
+ * Returns the number of characters in buffer (if positive)
+ * or an error (negative)
+ */
+static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+{
+	char *p = buffer;
+	int l;
+	nodemask_t nodes;
+	int mode = pol ? pol->policy : MPOL_DEFAULT;
+
+	switch (mode) {
+	case MPOL_DEFAULT:
+		nodes_clear(nodes);
+		break;
+
+	case MPOL_PREFERRED:
+		nodes_clear(nodes);
+		node_set(pol->v.preferred_node, nodes);
+		break;
+
+	case MPOL_BIND:
+		get_zonemask(pol, &nodes);
+		break;
+
+	case MPOL_INTERLEAVE:
+		nodes = pol->v.nodes;
+		break;
+
+	default:
+		BUG();
+		return -EFAULT;
+	}
+
+	l = strlen(policy_types[mode]);
+ 	if (buffer + maxlen < p + l + 1)
+ 		return -ENOSPC;
+
+	strcpy(p, policy_types[mode]);
+	p += l;
+
+	if (!nodes_empty(nodes)) {
+		if (buffer + maxlen < p + 2)
+			return -ENOSPC;
+		*p++ = '=';
+	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
+	}
+	return p - buffer;
+}
+
+struct numa_maps {
+	unsigned long pages;
+	unsigned long anon;
+	unsigned long active;
+	unsigned long writeback;
+	unsigned long mapcount_max;
+	unsigned long dirty;
+	unsigned long swapcache;
+	unsigned long node[MAX_NUMNODES];
+};
+
+static void gather_stats(struct page *page, void *private, int pte_dirty)
+{
+	struct numa_maps *md = private;
+	int count = page_mapcount(page);
+
+	md->pages++;
+	if (pte_dirty || PageDirty(page))
+		md->dirty++;
+
+	if (PageSwapCache(page))
+		md->swapcache++;
+
+	if (PageActive(page))
+		md->active++;
+
+	if (PageWriteback(page))
+		md->writeback++;
+
+	if (PageAnon(page))
+		md->anon++;
+
+	if (count > md->mapcount_max)
+		md->mapcount_max = count;
+
+	md->node[page_to_nid(page)]++;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static void check_huge_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct numa_maps *md)
+{
+	unsigned long addr;
+	struct page *page;
+
+	for (addr = start; addr < end; addr += HPAGE_SIZE) {
+		pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK);
+		pte_t pte;
+
+		if (!ptep)
+			continue;
+
+		pte = *ptep;
+		if (pte_none(pte))
+			continue;
+
+		page = pte_page(pte);
+		if (!page)
+			continue;
+
+		gather_stats(page, md, pte_dirty(*ptep));
+	}
+}
+#else
+static inline void check_huge_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct numa_maps *md)
+{
+}
+#endif
+
+int show_numa_map(struct seq_file *m, void *v)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma = v;
+	struct numa_maps *md;
+	struct file *file = vma->vm_file;
+	struct mm_struct *mm = vma->vm_mm;
+	int n;
+	char buffer[50];
+
+	if (!mm)
+		return 0;
+
+	md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
+	if (!md)
+		return 0;
+
+	mpol_to_str(buffer, sizeof(buffer),
+			    get_vma_policy(priv->task, vma, vma->vm_start));
+
+	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
+
+	if (file) {
+		seq_printf(m, " file=");
+		seq_path(m, file->f_vfsmnt, file->f_dentry, "\n\t= ");
+	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
+		seq_printf(m, " heap");
+	} else if (vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack) {
+		seq_printf(m, " stack");
+	}
+
+	if (is_vm_hugetlb_page(vma)) {
+		check_huge_range(vma, vma->vm_start, vma->vm_end, md);
+		seq_printf(m, " huge");
+	} else {
+		check_pgd_range(vma, vma->vm_start, vma->vm_end,
+				&node_online_map, MPOL_MF_STATS, md);
+	}
+
+	if (!md->pages)
+		goto out;
+
+	if (md->anon)
+		seq_printf(m," anon=%lu",md->anon);
+
+	if (md->dirty)
+		seq_printf(m," dirty=%lu",md->dirty);
+
+	if (md->pages != md->anon && md->pages != md->dirty)
+		seq_printf(m, " mapped=%lu", md->pages);
+
+	if (md->mapcount_max > 1)
+		seq_printf(m, " mapmax=%lu", md->mapcount_max);
+
+	if (md->swapcache)
+		seq_printf(m," swapcache=%lu", md->swapcache);
+
+	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
+		seq_printf(m," active=%lu", md->active);
+
+	if (md->writeback)
+		seq_printf(m," writeback=%lu", md->writeback);
+
+	for_each_online_node(n)
+		if (md->node[n])
+			seq_printf(m, " N%d=%lu", n, md->node[n]);
+out:
+	seq_putc(m, '\n');
+	kfree(md);
+
+	if (m->count < m->size)
+		m->version = (vma != priv->tail_vma) ? vma->vm_start : 0;
+	return 0;
 }
+