X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmempolicy.c;h=8924aaf4665ce9f4178ddf9cb751abc50aeae980;hb=ae4d8c16aa22775f5731677abb8a82f03cec877e;hp=568152ae6cafe9c6f6052cf704c0e6dae0d198f7;hpb=dbcb0f19c877df9026b8c1227758d38bd561e9c4;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 568152a..8924aaf 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -63,7 +63,6 @@
    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>
@@ -78,6 +77,7 @@
 #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>
@@ -109,110 +109,246 @@ struct mempolicy default_policy = {
 	.policy = MPOL_DEFAULT,
 };
 
-static void mpol_rebind_policy(struct mempolicy *pol,
-                               const nodemask_t *newmask);
+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];
 
-/* Do sanity checking on a policy */
-static int mpol_check_policy(int mode, nodemask_t *nodes)
+/* Check that the nodemask contains at least one populated zone */
+static int is_valid_nodemask(const nodemask_t *nodemask)
 {
-	int empty = nodes_empty(*nodes);
+	int nd, k;
 
-	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;
+	/* 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 nodes_subset(*nodes, node_states[N_HIGH_MEMORY]) ? 0 : -EINVAL;
+
+	return 0;
 }
 
-/* Generate a custom zonelist for the BIND policy. */
-static struct zonelist *bind_zonelist(nodemask_t *nodes)
+static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
 {
-	struct zonelist *zl;
-	int num, max, nd;
-	enum zone_type k;
+	return pol->flags & (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES);
+}
 
-	max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
-	max++;			/* space for zlcache_ptr (see mmzone.h) */
-	zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL);
-	if (!zl)
-		return ERR_PTR(-ENOMEM);
-	zl->zlcache_ptr = NULL;
-	num = 0;
-	/* 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. */
-	k = MAX_NR_ZONES - 1;
-	while (1) {
-		for_each_node_mask(nd, *nodes) { 
-			struct zone *z = &NODE_DATA(nd)->node_zones[k];
-			if (z->present_pages > 0) 
-				zl->zones[num++] = z;
-		}
-		if (k == 0)
-			break;
-		k--;
-	}
-	if (num == 0) {
-		kfree(zl);
-		return ERR_PTR(-EINVAL);
-	}
-	zl->zones[num] = NULL;
-	return zl;
+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(int mode, nodemask_t *nodes)
+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 nodes[0] %lx\n",
-		 mode, nodes ? nodes_addr(*nodes)[0] : -1);
+	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
+		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
 
-	if (mode == MPOL_DEFAULT)
+	if (mode == MPOL_DEFAULT) {
+		if (nodes && !nodes_empty(*nodes))
+			return ERR_PTR(-EINVAL);
 		return NULL;
+	}
+	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);
-	switch (mode) {
-	case MPOL_INTERLEAVE:
-		policy->v.nodes = *nodes;
-		nodes_and(policy->v.nodes, policy->v.nodes,
-					node_states[N_HIGH_MEMORY]);
-		if (nodes_weight(policy->v.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 (IS_ERR(policy->v.zonelist)) {
-			void *error_code = policy->v.zonelist;
-			kmem_cache_free(policy_cache, policy);
-			return error_code;
-		}
-		break;
-	}
 	policy->policy = mode;
-	policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
+	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;
 }
 
+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->policy].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);
@@ -393,7 +529,7 @@ static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
 	if (!err) {
 		mpol_get(new);
 		vma->vm_policy = new;
-		mpol_free(old);
+		mpol_put(old);
 	}
 	return err;
 }
@@ -420,18 +556,6 @@ static int mbind_range(struct vm_area_struct *vma, unsigned long start,
 	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);
-}
-
-
 /*
  * Update task->flags PF_MEMPOLICY bit: set iff non-default
  * mempolicy.  Allows more rapid checking of this (combined perhaps
@@ -463,37 +587,45 @@ static void mpol_set_task_struct_flag(void)
 }
 
 /* Set the process memory policy */
-static long do_set_mempolicy(int mode, nodemask_t *nodes)
+static long do_set_mempolicy(unsigned short mode, unsigned short flags,
+			     nodemask_t *nodes)
 {
 	struct mempolicy *new;
+	struct mm_struct *mm = current->mm;
 
-	if (contextualize_policy(mode, nodes))
-		return -EINVAL;
-	new = mpol_new(mode, nodes);
+	new = mpol_new(mode, flags, nodes);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
-	mpol_free(current->mempolicy);
+
+	/*
+	 * 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->policy == MPOL_INTERLEAVE)
+	if (new && new->policy == MPOL_INTERLEAVE &&
+	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
+	if (mm)
+		up_write(&mm->mmap_sem);
+
 	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(zone_to_nid(p->v.zonelist->zones[i]),
-				*nodes);
-		break;
 	case MPOL_DEFAULT:
 		break;
+	case MPOL_BIND:
+		/* Fall through */
 	case MPOL_INTERLEAVE:
 		*nodes = p->v.nodes;
 		break;
@@ -575,7 +707,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 			goto out;
 		}
 	} else
-		*policy = pol->policy;
+		*policy = pol->policy | pol->flags;
 
 	if (vma) {
 		up_read(&current->mm->mmap_sem);
@@ -721,12 +853,29 @@ out:
 
 }
 
+/*
+ * 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;
+	}
 
-	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
-					page_address_in_vma(page, vma));
+	/*
+	 * if !vma, alloc_page_vma() will use task or system default policy
+	 */
+	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 }
 #else
 
@@ -748,8 +897,8 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
 #endif
 
 static long do_mbind(unsigned long start, unsigned long len,
-		     unsigned long mode, nodemask_t *nmask,
-		     unsigned long flags)
+		     unsigned short mode, unsigned short mode_flags,
+		     nodemask_t *nmask, unsigned long flags)
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
@@ -758,9 +907,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 	int err;
 	LIST_HEAD(pagelist);
 
-	if ((flags & ~(unsigned long)(MPOL_MF_STRICT |
-				      MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-	    || mode > MPOL_MAX)
+	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;
@@ -779,10 +927,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (end == start)
 		return 0;
 
-	if (mpol_check_policy(mode, nmask))
-		return -EINVAL;
-
-	new = mpol_new(mode, nmask);
+	new = mpol_new(mode, mode_flags, nmask);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
@@ -793,8 +938,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (!new)
 		flags |= MPOL_MF_DISCONTIG_OK;
 
-	pr_debug("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
-		 mode, nmask ? nodes_addr(*nmask)[0] : -1);
+	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,
@@ -815,7 +961,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	}
 
 	up_write(&mm->mmap_sem);
-	mpol_free(new);
+	mpol_put(new);
 	return err;
 }
 
@@ -893,15 +1039,19 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len,
 {
 	nodemask_t nodes;
 	int err;
+	unsigned short mode_flags;
 
+	mode_flags = mode & MPOL_MODE_FLAGS;
+	mode &= ~MPOL_MODE_FLAGS;
+	if (mode >= MPOL_MAX)
+		return -EINVAL;
+	if ((mode_flags & MPOL_F_STATIC_NODES) &&
+	    (mode_flags & MPOL_F_RELATIVE_NODES))
+		return -EINVAL;
 	err = get_nodes(&nodes, nmask, maxnode);
 	if (err)
 		return err;
-#ifdef CONFIG_CPUSETS
-	/* Restrict the nodes to the allowed nodes in the cpuset */
-	nodes_and(nodes, nodes, current->mems_allowed);
-#endif
-	return do_mbind(start, len, mode, &nodes, flags);
+	return do_mbind(start, len, mode, mode_flags, &nodes, flags);
 }
 
 /* Set the process memory policy */
@@ -910,13 +1060,18 @@ asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
 {
 	int err;
 	nodemask_t nodes;
+	unsigned short flags;
 
-	if (mode < 0 || mode > MPOL_MAX)
+	flags = mode & MPOL_MODE_FLAGS;
+	mode &= ~MPOL_MODE_FLAGS;
+	if ((unsigned int)mode >= MPOL_MAX)
+		return -EINVAL;
+	if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES))
 		return -EINVAL;
 	err = get_nodes(&nodes, nmask, maxnode);
 	if (err)
 		return err;
-	return do_set_mempolicy(mode, &nodes);
+	return do_set_mempolicy(mode, flags, &nodes);
 }
 
 asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
@@ -940,7 +1095,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 
 	/* Find the mm_struct */
 	read_lock(&tasklist_lock);
-	task = pid ? find_task_by_pid(pid) : current;
+	task = pid ? find_task_by_vpid(pid) : current;
 	if (!task) {
 		read_unlock(&tasklist_lock);
 		return -ESRCH;
@@ -1107,7 +1262,7 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
  * @task != current].  It is the caller's responsibility to
  * free the reference in these cases.
  */
-static struct mempolicy * get_vma_policy(struct task_struct *task,
+static struct mempolicy *get_vma_policy(struct task_struct *task,
 		struct vm_area_struct *vma, unsigned long addr)
 {
 	struct mempolicy *pol = task->mempolicy;
@@ -1115,7 +1270,10 @@ static struct mempolicy * get_vma_policy(struct task_struct *task,
 
 	if (vma) {
 		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			pol = vma->vm_ops->get_policy(vma, addr);
+			struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
+									addr);
+			if (vpol)
+				pol = vpol;
 			shared_pol = 1;	/* if pol non-NULL, add ref below */
 		} else if (vma->vm_policy &&
 				vma->vm_policy->policy != MPOL_DEFAULT)
@@ -1128,6 +1286,18 @@ static struct mempolicy * get_vma_policy(struct task_struct *task,
 	return pol;
 }
 
+/* Return a nodemask representing a mempolicy */
+static nodemask_t *nodemask_policy(gfp_t gfp, struct mempolicy *policy)
+{
+	/* Lower zones don't get a nodemask applied for MPOL_BIND */
+	if (unlikely(policy->policy == MPOL_BIND) &&
+			gfp_zone(gfp) >= policy_zone &&
+			cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
+		return &policy->v.nodes;
+
+	return NULL;
+}
+
 /* Return a zonelist representing a mempolicy */
 static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
 {
@@ -1140,12 +1310,17 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
 			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*/
+		/*
+		 * Normally, MPOL_BIND allocations node-local are node-local
+		 * within the allowed nodemask. However, if __GFP_THISNODE is
+		 * set and the current node is part of the mask, we use the
+		 * the zonelist for the first node in the mask instead.
+		 */
+		nd = numa_node_id();
+		if (unlikely(gfp & __GFP_THISNODE) &&
+				unlikely(!node_isset(nd, policy->v.nodes)))
+			nd = first_node(policy->v.nodes);
+		break;
 	case MPOL_INTERLEAVE: /* should not happen */
 	case MPOL_DEFAULT:
 		nd = numa_node_id();
@@ -1154,7 +1329,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
 		nd = 0;
 		BUG();
 	}
-	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
+	return node_zonelist(nd, gfp);
 }
 
 /* Do dynamic interleaving for a process */
@@ -1167,7 +1342,8 @@ static unsigned interleave_nodes(struct mempolicy *policy)
 	next = next_node(nid, policy->v.nodes);
 	if (next >= MAX_NUMNODES)
 		next = first_node(policy->v.nodes);
-	me->il_next = next;
+	if (next < MAX_NUMNODES)
+		me->il_next = next;
 	return nid;
 }
 
@@ -1177,18 +1353,26 @@ static unsigned interleave_nodes(struct mempolicy *policy)
  */
 unsigned slab_node(struct mempolicy *policy)
 {
-	int pol = policy ? policy->policy : MPOL_DEFAULT;
+	unsigned short pol = policy ? policy->policy : MPOL_DEFAULT;
 
 	switch (pol) {
 	case MPOL_INTERLEAVE:
 		return interleave_nodes(policy);
 
-	case MPOL_BIND:
+	case MPOL_BIND: {
 		/*
 		 * Follow bind policy behavior and start allocation at the
 		 * first node.
 		 */
-		return zone_to_nid(policy->v.zonelist->zones[0]);
+		struct zonelist *zonelist;
+		struct zone *zone;
+		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
+		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
+		(void)first_zones_zonelist(zonelist, highest_zoneidx,
+							&policy->v.nodes,
+							&zone);
+		return zone->node;
+	}
 
 	case MPOL_PREFERRED:
 		if (policy->v.preferred_node >= 0)
@@ -1205,10 +1389,13 @@ static unsigned offset_il_node(struct mempolicy *pol,
 		struct vm_area_struct *vma, unsigned long off)
 {
 	unsigned nnodes = nodes_weight(pol->v.nodes);
-	unsigned target = (unsigned)off % nnodes;
+	unsigned target;
 	int c;
 	int nid = -1;
 
+	if (!nnodes)
+		return numa_node_id();
+	target = (unsigned int)off % nnodes;
 	c = 0;
 	do {
 		nid = next_node(nid, pol->v.nodes);
@@ -1245,36 +1432,44 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
  * @vma = virtual memory area whose policy is sought
  * @addr = address in @vma for shared policy lookup and interleave policy
  * @gfp_flags = for requested zone
- * @mpol = pointer to mempolicy pointer for reference counted 'BIND policy
+ * @mpol = pointer to mempolicy pointer for reference counted mempolicy
+ * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
  *
  * Returns a zonelist suitable for a huge page allocation.
- * If the effective policy is 'BIND, returns pointer to policy's zonelist.
+ * If the effective policy is 'BIND, returns pointer to local node's zonelist,
+ * and a pointer to the mempolicy's @nodemask for filtering the zonelist.
  * If it is also a policy for which get_vma_policy() returns an extra
- * reference, we must hold that reference until after allocation.
+ * reference, we must hold that reference until after the allocation.
  * In that case, return policy via @mpol so hugetlb allocation can drop
- * the reference.  For non-'BIND referenced policies, we can/do drop the
+ * the reference. For non-'BIND referenced policies, we can/do drop the
  * reference here, so the caller doesn't need to know about the special case
  * for default and current task policy.
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
-				gfp_t gfp_flags, struct mempolicy **mpol)
+				gfp_t gfp_flags, struct mempolicy **mpol,
+				nodemask_t **nodemask)
 {
 	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 	struct zonelist *zl;
 
 	*mpol = NULL;		/* probably no unref needed */
-	if (pol->policy == MPOL_INTERLEAVE) {
+	*nodemask = NULL;	/* assume !MPOL_BIND */
+	if (pol->policy == MPOL_BIND) {
+			*nodemask = &pol->v.nodes;
+	} else if (pol->policy == MPOL_INTERLEAVE) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
-		__mpol_free(pol);		/* finished with pol */
-		return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
+		if (unlikely(pol != &default_policy &&
+				pol != current->mempolicy))
+			__mpol_put(pol);	/* finished with pol */
+		return node_zonelist(nid, gfp_flags);
 	}
 
 	zl = zonelist_policy(GFP_HIGHUSER, pol);
 	if (unlikely(pol != &default_policy && pol != current->mempolicy)) {
 		if (pol->policy != MPOL_BIND)
-			__mpol_free(pol);	/* finished with pol */
+			__mpol_put(pol);	/* finished with pol */
 		else
 			*mpol = pol;	/* unref needed after allocation */
 	}
@@ -1290,9 +1485,9 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 	struct zonelist *zl;
 	struct page *page;
 
-	zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
+	zl = node_zonelist(nid, gfp);
 	page = __alloc_pages(gfp, order, zl);
-	if (page && page_zone(page) == zl->zones[0])
+	if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
 		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
 	return page;
 }
@@ -1331,6 +1526,9 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
+		if (unlikely(pol != &default_policy &&
+				pol != current->mempolicy))
+			__mpol_put(pol);	/* finished with pol */
 		return alloc_page_interleave(gfp, 0, nid);
 	}
 	zl = zonelist_policy(gfp, pol);
@@ -1338,14 +1536,15 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 		/*
 		 * slow path: ref counted policy -- shared or vma
 		 */
-		struct page *page =  __alloc_pages(gfp, 0, zl);
-		__mpol_free(pol);
+		struct page *page =  __alloc_pages_nodemask(gfp, 0,
+						zl, nodemask_policy(gfp, pol));
+		__mpol_put(pol);
 		return page;
 	}
 	/*
 	 * fast path:  default or task policy
 	 */
-	return __alloc_pages(gfp, 0, zl);
+	return __alloc_pages_nodemask(gfp, 0, zl, nodemask_policy(gfp, pol));
 }
 
 /**
@@ -1377,21 +1576,21 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		pol = &default_policy;
 	if (pol->policy == MPOL_INTERLEAVE)
 		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
-	return __alloc_pages(gfp, order, zonelist_policy(gfp, pol));
+	return __alloc_pages_nodemask(gfp, order,
+			zonelist_policy(gfp, pol), nodemask_policy(gfp, pol));
 }
 EXPORT_SYMBOL(alloc_pages_current);
 
 /*
- * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
+ * If mpol_dup() 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)
+/* Slow path of a mempolicy duplicate */
+struct mempolicy *__mpol_dup(struct mempolicy *old)
 {
 	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
 
@@ -1403,17 +1602,19 @@ struct mempolicy *__mpol_copy(struct mempolicy *old)
 	}
 	*new = *old;
 	atomic_set(&new->refcnt, 1);
-	if (new->policy == MPOL_BIND) {
-		int sz = ksize(old->v.zonelist);
-		new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL);
-		if (!new->v.zonelist) {
-			kmem_cache_free(policy_cache, new);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
 	return new;
 }
 
+static int mpol_match_intent(const struct mempolicy *a,
+			     const struct mempolicy *b)
+{
+	if (a->flags != b->flags)
+		return 0;
+	if (!mpol_store_user_nodemask(a))
+		return 1;
+	return nodes_equal(a->w.user_nodemask, b->w.user_nodemask);
+}
+
 /* Slow path of a mempolicy comparison */
 int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
@@ -1421,20 +1622,17 @@ int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 		return 0;
 	if (a->policy != b->policy)
 		return 0;
+	if (a->policy != MPOL_DEFAULT && !mpol_match_intent(a, b))
+		return 0;
 	switch (a->policy) {
 	case MPOL_DEFAULT:
 		return 1;
+	case MPOL_BIND:
+		/* Fall through */
 	case MPOL_INTERLEAVE:
 		return nodes_equal(a->v.nodes, b->v.nodes);
 	case MPOL_PREFERRED:
 		return a->v.preferred_node == b->v.preferred_node;
-	case MPOL_BIND: {
-		int i;
-		for (i = 0; a->v.zonelist->zones[i]; i++)
-			if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i])
-				return 0;
-		return b->v.zonelist->zones[i] == NULL;
-	}
 	default:
 		BUG();
 		return 0;
@@ -1442,12 +1640,10 @@ int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 }
 
 /* Slow path of a mpol destructor. */
-void __mpol_free(struct mempolicy *p)
+void __mpol_put(struct mempolicy *p)
 {
 	if (!atomic_dec_and_test(&p->refcnt))
 		return;
-	if (p->policy == MPOL_BIND)
-		kfree(p->v.zonelist);
 	p->policy = MPOL_DEFAULT;
 	kmem_cache_free(policy_cache, p);
 }
@@ -1540,7 +1736,7 @@ static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
 	rb_erase(&n->nd, &sp->root);
-	mpol_free(n->policy);
+	mpol_put(n->policy);
 	kmem_cache_free(sn_cache, n);
 }
 
@@ -1600,14 +1796,14 @@ restart:
 		sp_insert(sp, new);
 	spin_unlock(&sp->lock);
 	if (new2) {
-		mpol_free(new2->policy);
+		mpol_put(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)
+void mpol_shared_policy_init(struct shared_policy *info, unsigned short policy,
+			unsigned short flags, nodemask_t *policy_nodes)
 {
 	info->root = RB_ROOT;
 	spin_lock_init(&info->lock);
@@ -1616,7 +1812,7 @@ void mpol_shared_policy_init(struct shared_policy *info, int policy,
 		struct mempolicy *newpol;
 
 		/* Falls back to MPOL_DEFAULT on any error */
-		newpol = mpol_new(policy, policy_nodes);
+		newpol = mpol_new(policy, flags, policy_nodes);
 		if (!IS_ERR(newpol)) {
 			/* Create pseudo-vma that contains just the policy */
 			struct vm_area_struct pvma;
@@ -1625,7 +1821,7 @@ void mpol_shared_policy_init(struct shared_policy *info, int policy,
 			/* Policy covers entire file */
 			pvma.vm_end = TASK_SIZE;
 			mpol_set_shared_policy(info, &pvma, newpol);
-			mpol_free(newpol);
+			mpol_put(newpol);
 		}
 	}
 }
@@ -1637,9 +1833,10 @@ int mpol_set_shared_policy(struct shared_policy *info,
 	struct sp_node *new = NULL;
 	unsigned long sz = vma_pages(vma);
 
-	pr_debug("set_shared_policy %lx sz %lu %d %lx\n",
+	pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
 		 vma->vm_pgoff,
-		 sz, npol? npol->policy : -1,
+		 sz, npol ? npol->policy : -1,
+		 npol ? npol->flags : -1,
 		 npol ? nodes_addr(npol->v.nodes)[0] : -1);
 
 	if (npol) {
@@ -1667,7 +1864,7 @@ void mpol_free_shared_policy(struct shared_policy *p)
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
 		rb_erase(&n->nd, &p->root);
-		mpol_free(n->policy);
+		mpol_put(n->policy);
 		kmem_cache_free(sn_cache, n);
 	}
 	spin_unlock(&p->lock);
@@ -1712,106 +1909,19 @@ void __init numa_policy_init(void)
 	if (unlikely(nodes_empty(interleave_nodes)))
 		node_set(prefer, interleave_nodes);
 
-	if (do_set_mempolicy(MPOL_INTERLEAVE, &interleave_nodes))
+	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
 		printk("numa_policy_init: interleaving failed\n");
 }
 
 /* Reset policy of current process to default */
 void numa_default_policy(void)
 {
-	do_set_mempolicy(MPOL_DEFAULT, NULL);
-}
-
-/* Migrate a policy to a different set of nodes */
-static 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(zone_to_nid(*z), 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 (!IS_ERR(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);
+	do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
 }
 
 /*
  * Display pages allocated per node and memory policy via /proc.
  */
-
 static const char * const policy_types[] =
 	{ "default", "prefer", "bind", "interleave" };
 
@@ -1825,7 +1935,8 @@ 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;
+	unsigned short mode = pol ? pol->policy : MPOL_DEFAULT;
+	unsigned short flags = pol ? pol->flags : 0;
 
 	switch (mode) {
 	case MPOL_DEFAULT:
@@ -1838,9 +1949,7 @@ static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 		break;
 
 	case MPOL_BIND:
-		get_zonemask(pol, &nodes);
-		break;
-
+		/* Fall through */
 	case MPOL_INTERLEAVE:
 		nodes = pol->v.nodes;
 		break;
@@ -1857,6 +1966,19 @@ static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	strcpy(p, policy_types[mode]);
 	p += l;
 
+	if (flags) {
+		int need_bar = 0;
+
+		if (buffer + maxlen < p + 2)
+			return -ENOSPC;
+		*p++ = '=';
+
+		if (flags & MPOL_F_STATIC_NODES)
+			p += sprintf(p, "%sstatic", need_bar++ ? "|" : "");
+		if (flags & MPOL_F_RELATIVE_NODES)
+			p += sprintf(p, "%srelative", need_bar++ ? "|" : "");
+	}
+
 	if (!nodes_empty(nodes)) {
 		if (buffer + maxlen < p + 2)
 			return -ENOSPC;
@@ -1962,13 +2084,13 @@ int show_numa_map(struct seq_file *m, void *v)
 	 * unref shared or other task's mempolicy
 	 */
 	if (pol != &default_policy && pol != current->mempolicy)
-		__mpol_free(pol);
+		__mpol_put(pol);
 
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
 	if (file) {
 		seq_printf(m, " file=");
-		seq_path(m, file->f_path.mnt, file->f_path.dentry, "\n\t= ");
+		seq_path(m, &file->f_path, "\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 &&
@@ -2019,4 +2141,3 @@ out:
 		m->version = (vma != priv->tail_vma) ? vma->vm_start : 0;
 	return 0;
 }
-