mempolicy.c

		return offset_il_node(pol, off);
	} else
		return interleave_nodes(pol);
}

#ifdef CONFIG_HUGETLBFS
/*
 * huge_node(@vma, @addr, @gfp_flags, @mpol)
 * @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 mempolicy
 * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask
 *
 * Returns a nid suitable for a huge page allocation and a pointer
 * to the struct mempolicy for conditional unref after allocation.
 * If the effective policy is 'BIND, returns a pointer to the mempolicy's
 * @nodemask for filtering the zonelist.
 *
 * Must be protected by read_mems_allowed_begin()
 */
int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags,
				struct mempolicy **mpol, nodemask_t **nodemask)
{
	int nid;

	*mpol = get_vma_policy(vma, addr);
	*nodemask = NULL;	/* assume !MPOL_BIND */

	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
		nid = interleave_nid(*mpol, vma, addr,
					huge_page_shift(hstate_vma(vma)));
	} else {
		nid = policy_node(gfp_flags, *mpol, numa_node_id());
		if ((*mpol)->mode == MPOL_BIND)
			*nodemask = &(*mpol)->v.nodes;
	}
	return nid;
}

/*
 * init_nodemask_of_mempolicy
 *
 * If the current task's mempolicy is "default" [NULL], return 'false'
 * to indicate default policy.  Otherwise, extract the policy nodemask
 * for 'bind' or 'interleave' policy into the argument nodemask, or
 * initialize the argument nodemask to contain the single node for
 * 'preferred' or 'local' policy and return 'true' to indicate presence
 * of non-default mempolicy.
 *
 * We don't bother with reference counting the mempolicy [mpol_get/put]
 * because the current task is examining it's own mempolicy and a task's
 * mempolicy is only ever changed by the task itself.
 *
 * N.B., it is the caller's responsibility to free a returned nodemask.
 */
bool init_nodemask_of_mempolicy(nodemask_t *mask)
{
	struct mempolicy *mempolicy;
	int nid;

	if (!(mask && current->mempolicy))
		return false;

	task_lock(current);
	mempolicy = current->mempolicy;
	switch (mempolicy->mode) {
	case MPOL_PREFERRED:
		if (mempolicy->flags & MPOL_F_LOCAL)
			nid = numa_node_id();
		else
			nid = mempolicy->v.preferred_node;
		init_nodemask_of_node(mask, nid);
		break;

	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		*mask =  mempolicy->v.nodes;
		break;

	default:
		BUG();
	}
	task_unlock(current);

	return true;
}
#endif

/*
 * mempolicy_nodemask_intersects
 *
 * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default
 * policy.  Otherwise, check for intersection between mask and the policy
 * nodemask for 'bind' or 'interleave' policy.  For 'perferred' or 'local'
 * policy, always return true since it may allocate elsewhere on fallback.
 *
 * Takes task_lock(tsk) to prevent freeing of its mempolicy.
 */
bool mempolicy_nodemask_intersects(struct task_struct *tsk,
					const nodemask_t *mask)
{
	struct mempolicy *mempolicy;
	bool ret = true;

	if (!mask)
		return ret;
	task_lock(tsk);
	mempolicy = tsk->mempolicy;
	if (!mempolicy)
		goto out;

	switch (mempolicy->mode) {
	case MPOL_PREFERRED:
		/*
		 * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to
		 * allocate from, they may fallback to other nodes when oom.
		 * Thus, it's possible for tsk to have allocated memory from
		 * nodes in mask.
		 */
		break;
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		ret = nodes_intersects(mempolicy->v.nodes, *mask);
		break;
	default:
		BUG();
	}
out:
	task_unlock(tsk);
	return ret;
}

/* Allocate a page in interleaved policy.
   Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
					unsigned nid)
{
	struct page *page;

	page = __alloc_pages(gfp, order, nid);
	/* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */
	if (!static_branch_likely(&vm_numa_stat_key))
		return page;
	if (page && page_to_nid(page) == nid) {
		preempt_disable();
		__inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT);
		preempt_enable();
	}
	return page;
}

/**
 * 	alloc_pages_vma	- Allocate a page for a VMA.
 *
 * 	@gfp:
 *      %GFP_USER    user allocation.
 *      %GFP_KERNEL  kernel allocations,
 *      %GFP_HIGHMEM highmem/user allocations,
 *      %GFP_FS      allocation should not call back into a file system.
 *      %GFP_ATOMIC  don't sleep.
 *
 *	@order:Order of the GFP allocation.
 * 	@vma:  Pointer to VMA or NULL if not available.
 *	@addr: Virtual Address of the allocation. Must be inside the VMA.
 *	@node: Which node to prefer for allocation (modulo policy).
 *	@hugepage: for hugepages try only the preferred node if possible
 *
 * 	This function allocates a page from the kernel page pool and applies
 *	a NUMA policy associated with the VMA or the current process.
 *	When VMA is not NULL caller must read-lock the mmap_lock of the
 *	mm_struct of the VMA to prevent it from going away. Should be used for
 *	all allocations for pages that will be mapped into user space. Returns
 *	NULL when no page can be allocated.
 */
struct page *
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
		unsigned long addr, int node, bool hugepage)
{
	struct mempolicy *pol;
	struct page *page;
	int preferred_nid;
	nodemask_t *nmask;

	pol = get_vma_policy(vma, addr);

	if (pol->mode == MPOL_INTERLEAVE) {
		unsigned nid;

		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
		mpol_cond_put(pol);
		page = alloc_page_interleave(gfp, order, nid);
		goto out;
	}

	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
		int hpage_node = node;

		/*
		 * For hugepage allocation and non-interleave policy which
		 * allows the current node (or other explicitly preferred
		 * node) we only try to allocate from the current/preferred
		 * node and don't fall back to other nodes, as the cost of
		 * remote accesses would likely offset THP benefits.
		 *
		 * If the policy is interleave, or does not allow the current
		 * node in its nodemask, we allocate the standard way.
		 */
		if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
			hpage_node = pol->v.preferred_node;

		nmask = policy_nodemask(gfp, pol);
		if (!nmask || node_isset(hpage_node, *nmask)) {
			mpol_cond_put(pol);
			/*
			 * First, try to allocate THP only on local node, but
			 * don't reclaim unnecessarily, just compact.
			 */
			page = __alloc_pages_node(hpage_node,
				gfp | __GFP_THISNODE | __GFP_NORETRY, order);

			/*
			 * If hugepage allocations are configured to always
			 * synchronous compact or the vma has been madvised
			 * to prefer hugepage backing, retry allowing remote
			 * memory with both reclaim and compact as well.
			 */
			if (!page && (gfp & __GFP_DIRECT_RECLAIM))
				page = __alloc_pages_node(hpage_node,
								gfp, order);

			goto out;
		}
	}

	nmask = policy_nodemask(gfp, pol);
	preferred_nid = policy_node(gfp, pol, node);
	page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
	mpol_cond_put(pol);
out:
	return page;
}
EXPORT_SYMBOL(alloc_pages_vma);

/**
 * 	alloc_pages_current - Allocate pages.
 *
 *	@gfp:
 *		%GFP_USER   user allocation,
 *      	%GFP_KERNEL kernel allocation,
 *      	%GFP_HIGHMEM highmem allocation,
 *      	%GFP_FS     don't call back into a file system.
 *      	%GFP_ATOMIC don't sleep.
 *	@order: Power of two of allocation size in pages. 0 is a single page.
 *
 *	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.
 */
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
	struct mempolicy *pol = &default_policy;
	struct page *page;

	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
		pol = get_task_policy(current);

	/*
	 * No reference counting needed for current->mempolicy
	 * nor system default_policy
	 */
	if (pol->mode == MPOL_INTERLEAVE)
		page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
	else
		page = __alloc_pages_nodemask(gfp, order,
				policy_node(gfp, pol, numa_node_id()),
				policy_nodemask(gfp, pol));

	return page;
}
EXPORT_SYMBOL(alloc_pages_current);

int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
	struct mempolicy *pol = mpol_dup(vma_policy(src));

	if (IS_ERR(pol))
		return PTR_ERR(pol);
	dst->vm_policy = pol;
	return 0;
}

/*
 * 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().
 *
 * current's mempolicy may be rebinded by the other task(the task that changes
 * cpuset's mems), so we needn't do rebind work for current task.
 */

/* Slow path of a mempolicy duplicate */
struct mempolicy *__mpol_dup(struct mempolicy *old)
{
	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);

	if (!new)
		return ERR_PTR(-ENOMEM);

	/* task's mempolicy is protected by alloc_lock */
	if (old == current->mempolicy) {
		task_lock(current);
		*new = *old;
		task_unlock(current);
	} else
		*new = *old;

	if (current_cpuset_is_being_rebound()) {
		nodemask_t mems = cpuset_mems_allowed(current);
		mpol_rebind_policy(new, &mems);
	}
	atomic_set(&new->refcnt, 1);
	return new;
}

/* Slow path of a mempolicy comparison */
bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (!a || !b)
		return false;
	if (a->mode != b->mode)
		return false;
	if (a->flags != b->flags)
		return false;
	if (mpol_store_user_nodemask(a))
		if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask))
			return false;

	switch (a->mode) {
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		return !!nodes_equal(a->v.nodes, b->v.nodes);
	case MPOL_PREFERRED:
		/* a's ->flags is the same as b's */
		if (a->flags & MPOL_F_LOCAL)
			return true;
		return a->v.preferred_node == b->v.preferred_node;
	default:
		BUG();
		return false;
	}
}

/*
 * 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->lock rwlock, which should be held
 * for any accesses to the tree.
 */

/*
 * lookup first element intersecting start-end.  Caller holds sp->lock for
 * reading or for writing
 */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
	struct rb_node *n = sp->root.rb_node;

	while (n) {
		struct sp_node *p = rb_entry(n, struct sp_node, nd);

		if (start >= p->end)
			n = n->rb_right;
		else if (end <= p->start)
			n = n->rb_left;
		else
			break;
	}
	if (!n)
		return NULL;
	for (;;) {
		struct sp_node *w = NULL;
		struct rb_node *prev = rb_prev(n);
		if (!prev)
			break;
		w = rb_entry(prev, struct sp_node, nd);
		if (w->end <= start)
			break;
		n = prev;
	}
	return rb_entry(n, struct sp_node, nd);
}

/*
 * Insert a new shared policy into the list.  Caller holds sp->lock for
 * writing.
 */
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
	struct rb_node **p = &sp->root.rb_node;
	struct rb_node *parent = NULL;
	struct sp_node *nd;

	while (*p) {
		parent = *p;
		nd = rb_entry(parent, struct sp_node, nd);
		if (new->start < nd->start)
			p = &(*p)->rb_left;
		else if (new->end > nd->end)
			p = &(*p)->rb_right;
		else
			BUG();
	}
	rb_link_node(&new->nd, parent, p);
	rb_insert_color(&new->nd, &sp->root);
	pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
		 new->policy ? new->policy->mode : 0);
}

/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
	struct mempolicy *pol = NULL;
	struct sp_node *sn;

	if (!sp->root.rb_node)
		return NULL;
	read_lock(&sp->lock);
	sn = sp_lookup(sp, idx, idx+1);
	if (sn) {
		mpol_get(sn->policy);
		pol = sn->policy;
	}
	read_unlock(&sp->lock);
	return pol;
}

static void sp_free(struct sp_node *n)
{
	mpol_put(n->policy);
	kmem_cache_free(sn_cache, n);
}

/**
 * mpol_misplaced - check whether current page node is valid in policy
 *
 * @page: page to be checked
 * @vma: vm area where page mapped
 * @addr: virtual address where page mapped
 *
 * Lookup current policy node id for vma,addr and "compare to" page's
 * node id.
 *
 * Returns:
 *	-1	- not misplaced, page is in the right node
 *	node	- node id where the page should be
 *
 * Policy determination "mimics" alloc_page_vma().
 * Called from fault path where we know the vma and faulting address.
 */
int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol;
	struct zoneref *z;
	int curnid = page_to_nid(page);
	unsigned long pgoff;
	int thiscpu = raw_smp_processor_id();
	int thisnid = cpu_to_node(thiscpu);
	int polnid = NUMA_NO_NODE;
	int ret = -1;

	pol = get_vma_policy(vma, addr);
	if (!(pol->flags & MPOL_F_MOF))
		goto out;

	switch (pol->mode) {
	case MPOL_INTERLEAVE:
		pgoff = vma->vm_pgoff;
		pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
		polnid = offset_il_node(pol, pgoff);
		break;

	case MPOL_PREFERRED:
		if (pol->flags & MPOL_F_LOCAL)
			polnid = numa_node_id();
		else
			polnid = pol->v.preferred_node;
		break;

	case MPOL_BIND:

		/*
		 * allows binding to multiple nodes.
		 * use current page if in policy nodemask,
		 * else select nearest allowed node, if any.
		 * If no allowed nodes, use current [!misplaced].
		 */
		if (node_isset(curnid, pol->v.nodes))
			goto out;
		z = first_zones_zonelist(
				node_zonelist(numa_node_id(), GFP_HIGHUSER),
				gfp_zone(GFP_HIGHUSER),
				&pol->v.nodes);
		polnid = zone_to_nid(z->zone);
		break;

	default:
		BUG();
	}

	/* Migrate the page towards the node whose CPU is referencing it */
	if (pol->flags & MPOL_F_MORON) {
		polnid = thisnid;

		if (!should_numa_migrate_memory(current, page, curnid, thiscpu))
			goto out;
	}

	if (curnid != polnid)
		ret = polnid;
out:
	mpol_cond_put(pol);

	return ret;
}

/*
 * Drop the (possibly final) reference to task->mempolicy.  It needs to be
 * dropped after task->mempolicy is set to NULL so that any allocation done as
 * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed
 * policy.
 */
void mpol_put_task_policy(struct task_struct *task)
{
	struct mempolicy *pol;

	task_lock(task);
	pol = task->mempolicy;
	task->mempolicy = NULL;
	task_unlock(task);
	mpol_put(pol);
}

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);
	sp_free(n);
}

static void sp_node_init(struct sp_node *node, unsigned long start,
			unsigned long end, struct mempolicy *pol)
{
	node->start = start;
	node->end = end;
	node->policy = pol;
}

static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
				struct mempolicy *pol)
{
	struct sp_node *n;
	struct mempolicy *newpol;

	n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
	if (!n)
		return NULL;

	newpol = mpol_dup(pol);
	if (IS_ERR(newpol)) {
		kmem_cache_free(sn_cache, n);
		return NULL;
	}
	newpol->flags |= MPOL_F_SHARED;
	sp_node_init(n, start, end, newpol);

	return n;
}

/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
				 unsigned long end, struct sp_node *new)
{
	struct sp_node *n;
	struct sp_node *n_new = NULL;
	struct mempolicy *mpol_new = NULL;
	int ret = 0;

restart:
	write_lock(&sp->lock);
	n = sp_lookup(sp, start, end);
	/* Take care of old policies in the same range. */
	while (n && n->start < end) {
		struct rb_node *next = rb_next(&n->nd);
		if (n->start >= start) {
			if (n->end <= end)
				sp_delete(sp, n);
			else
				n->start = end;
		} else {
			/* Old policy spanning whole new range. */
			if (n->end > end) {
				if (!n_new)
					goto alloc_new;

				*mpol_new = *n->policy;
				atomic_set(&mpol_new->refcnt, 1);
				sp_node_init(n_new, end, n->end, mpol_new);
				n->end = start;
				sp_insert(sp, n_new);
				n_new = NULL;
				mpol_new = NULL;
				break;
			} else
				n->end = start;
		}
		if (!next)
			break;
		n = rb_entry(next, struct sp_node, nd);
	}
	if (new)
		sp_insert(sp, new);
	write_unlock(&sp->lock);
	ret = 0;

err_out:
	if (mpol_new)
		mpol_put(mpol_new);
	if (n_new)
		kmem_cache_free(sn_cache, n_new);

	return ret;

alloc_new:
	write_unlock(&sp->lock);
	ret = -ENOMEM;
	n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL);
	if (!n_new)
		goto err_out;
	mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!mpol_new)
		goto err_out;
	goto restart;
}

/**
 * mpol_shared_policy_init - initialize shared policy for inode
 * @sp: pointer to inode shared policy
 * @mpol:  struct mempolicy to install
 *
 * Install non-NULL @mpol in inode's shared policy rb-tree.
 * On entry, the current task has a reference on a non-NULL @mpol.
 * This must be released on exit.
 * This is called at get_inode() calls and we can use GFP_KERNEL.
 */
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
{
	int ret;

	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
	rwlock_init(&sp->lock);

	if (mpol) {
		struct vm_area_struct pvma;
		struct mempolicy *new;
		NODEMASK_SCRATCH(scratch);

		if (!scratch)
			goto put_mpol;
		/* contextualize the tmpfs mount point mempolicy */
		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
		if (IS_ERR(new))
			goto free_scratch; /* no valid nodemask intersection */

		task_lock(current);
		ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
		task_unlock(current);
		if (ret)
			goto put_new;

		/* Create pseudo-vma that contains just the policy */
		vma_init(&pvma, NULL);
		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */

put_new:
		mpol_put(new);			/* drop initial ref */
free_scratch:
		NODEMASK_SCRATCH_FREE(scratch);
put_mpol:
		mpol_put(mpol);	/* drop our incoming ref on sb mpol */
	}
}

int mpol_set_shared_policy(struct shared_policy *info,
			struct vm_area_struct *vma, struct mempolicy *npol)
{
	int err;
	struct sp_node *new = NULL;
	unsigned long sz = vma_pages(vma);

	pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
		 vma->vm_pgoff,
		 sz, npol ? npol->mode : -1,
		 npol ? npol->flags : -1,
		 npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE);

	if (npol) {
		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
		if (!new)
			return -ENOMEM;
	}
	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
	if (err && new)
		sp_free(new);
	return err;
}

/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *p)
{
	struct sp_node *n;
	struct rb_node *next;

	if (!p->root.rb_node)
		return;
	write_lock(&p->lock);
	next = rb_first(&p->root);
	while (next) {
		n = rb_entry(next, struct sp_node, nd);
		next = rb_next(&n->nd);
		sp_delete(p, n);
	}
	write_unlock(&p->lock);
}

#ifdef CONFIG_NUMA_BALANCING
static int __initdata numabalancing_override;

static void __init check_numabalancing_enable(void)
{
	bool numabalancing_default = false;

	if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
		numabalancing_default = true;

	/* Parsed by setup_numabalancing. override == 1 enables, -1 disables */
	if (numabalancing_override)
		set_numabalancing_state(numabalancing_override == 1);

	if (num_online_nodes() > 1 && !numabalancing_override) {
		pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n",
			numabalancing_default ? "Enabling" : "Disabling");
		set_numabalancing_state(numabalancing_default);
	}
}

static int __init setup_numabalancing(char *str)
{
	int ret = 0;
	if (!str)
		goto out;

	if (!strcmp(str, "enable")) {
		numabalancing_override = 1;
		ret = 1;
	} else if (!strcmp(str, "disable")) {
		numabalancing_override = -1;
		ret = 1;
	}
out:
	if (!ret)
		pr_warn("Unable to parse numa_balancing=\n");

	return ret;
}
__setup("numa_balancing=", setup_numabalancing);
#else
static inline void __init check_numabalancing_enable(void)
{
}
#endif /* CONFIG_NUMA_BALANCING */

/* assumes fs == KERNEL_DS */
void __init numa_policy_init(void)
{
	nodemask_t interleave_nodes;
	unsigned long largest = 0;
	int nid, prefer = 0;

	policy_cache = kmem_cache_create("numa_policy",
					 sizeof(struct mempolicy),
					 0, SLAB_PANIC, NULL);

	sn_cache = kmem_cache_create("shared_policy_node",
				     sizeof(struct sp_node),
				     0, SLAB_PANIC, NULL);

	for_each_node(nid) {
		preferred_node_policy[nid] = (struct mempolicy) {
			.refcnt = ATOMIC_INIT(1),
			.mode = MPOL_PREFERRED,
			.flags = MPOL_F_MOF | MPOL_F_MORON,
			.v = { .preferred_node = nid, },
		};
	}

	/*
	 * Set interleaving policy for system init. Interleaving is only
	 * enabled across suitably sized nodes (default is >= 16MB), or
	 * fall back to the largest node if they're all smaller.
	 */
	nodes_clear(interleave_nodes);
	for_each_node_state(nid, N_MEMORY) {
		unsigned long total_pages = node_present_pages(nid);

		/* Preserve the largest node */
		if (largest < total_pages) {
			largest = total_pages;
			prefer = nid;
		}

		/* Interleave this node? */
		if ((total_pages << PAGE_SHIFT) >= (16 << 20))
			node_set(nid, interleave_nodes);
	}

	/* All too small, use the largest */
	if (unlikely(nodes_empty(interleave_nodes)))
		node_set(prefer, interleave_nodes);

	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
		pr_err("%s: interleaving failed\n", __func__);

	check_numabalancing_enable();
}

/* Reset policy of current process to default */
void numa_default_policy(void)
{
	do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
}

/*
 * Parse and format mempolicy from/to strings
 */

/*
 * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
 */
static const char * const policy_modes[] =
{
	[MPOL_DEFAULT]    = "default",
	[MPOL_PREFERRED]  = "prefer",
	[MPOL_BIND]       = "bind",
	[MPOL_INTERLEAVE] = "interleave",
	[MPOL_LOCAL]      = "local",
};


#ifdef CONFIG_TMPFS
/**
 * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
 * @str:  string containing mempolicy to parse
 * @mpol:  pointer to struct mempolicy pointer, returned on success.
 *
 * Format of input:
 *	<mode>[=<flags>][:<nodelist>]
 *
 * On success, returns 0, else 1
 */
int mpol_parse_str(char *str, struct mempolicy **mpol)
{
	struct mempolicy *new = NULL;
	unsigned short mode_flags;
	nodemask_t nodes;
	char *nodelist = strchr(str, ':');
	char *flags = strchr(str, '=');
	int err = 1, mode;

	if (flags)
		*flags++ = '\0';	/* terminate mode string */

	if (nodelist) {
		/* NUL-terminate mode or flags string */
		*nodelist++ = '\0';
		if (nodelist_parse(nodelist, nodes))
			goto out;
		if (!nodes_subset(nodes, node_states[N_MEMORY]))
			goto out;
	} else
		nodes_clear(nodes);

	mode = match_string(policy_modes, MPOL_MAX, str);
	if (mode < 0)
		goto out;

	switch (mode) {
	case MPOL_PREFERRED:
		/*
		 * Insist on a nodelist of one node only, although later
		 * we use first_node(nodes) to grab a single node, so here
		 * nodelist (or nodes) cannot be empty.
		 */
		if (nodelist) {
			char *rest = nodelist;
			while (isdigit(*rest))
				rest++;
			if (*rest)
				goto out;
			if (nodes_empty(nodes))
				goto out;
		}
		break;
	case MPOL_INTERLEAVE:
		/*
		 * Default to online nodes with memory if no nodelist
		 */
		if (!nodelist)
			nodes = node_states[N_MEMORY];
		break;
	case MPOL_LOCAL:
		/*
		 * Don't allow a nodelist;  mpol_new() checks flags
		 */
		if (nodelist)
			goto out;
		mode = MPOL_PREFERRED;
		break;
	case MPOL_DEFAULT:
		/*
		 * Insist on a empty nodelist
		 */
		if (!nodelist)
			err = 0;
		goto out;
	case MPOL_BIND:
		/*
		 * Insist on a nodelist
		 */
		if (!nodelist)
			goto out;
	}

	mode_flags = 0;
	if (flags) {
		/*
		 * Currently, we only support two mutually exclusive
		 * mode flags.
		 */
		if (!strcmp(flags, "static"))
			mode_flags |= MPOL_F_STATIC_NODES;
		else if (!strcmp(flags, "relative"))
			mode_flags |= MPOL_F_RELATIVE_NODES;
		else
			goto out;
	}

	new = mpol_new(mode, mode_flags, &nodes);
	if (IS_ERR(new))
		goto out;

	/*
	 * Save nodes for mpol_to_str() to show the tmpfs mount options
	 * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
	 */
	if (mode != MPOL_PREFERRED)
		new->v.nodes = nodes;
	else if (nodelist)
		new->v.preferred_node = first_node(nodes);
	else
		new->flags |= MPOL_F_LOCAL;

	/*
	 * Save nodes for contextualization: this will be used to "clone"
	 * the mempolicy in a specific context [cpuset] at a later time.
	 */
	new->w.user_nodemask = nodes;

	err = 0;

out:
	/* Restore string for error message */
	if (nodelist)
		*--nodelist = ':';
	if (flags)
		*--flags = '=';
	if (!err)
		*mpol = new;
	return err;
}
#endif /* CONFIG_TMPFS */

/**