1 files changed, 137 insertions, 185 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 04729647f35..8f5330d74f4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -65,6 +65,8 @@
    kernel is not always grateful with that.
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/mempolicy.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
@@ -91,6 +93,7 @@
 #include <linux/ctype.h>
 #include <linux/mm_inline.h>
 #include <linux/mmu_notifier.h>
+#include <linux/printk.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -525,9 +528,14 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 #ifdef CONFIG_HUGETLB_PAGE
 	int nid;
 	struct page *page;
+	spinlock_t *ptl;
+	pte_t entry;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
-	page = pte_page(huge_ptep_get((pte_t *)pmd));
+	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
+	entry = huge_ptep_get((pte_t *)pmd);
+	if (!pte_present(entry))
+		goto unlock;
+	page = pte_page(entry);
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
 		goto unlock;
@@ -536,7 +544,7 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
 		isolate_huge_page(page, private);
 unlock:
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(ptl);
 #else
 	BUG();
 #endif
@@ -612,7 +620,7 @@ static inline int queue_pages_pgd_range(struct vm_area_struct *vma,
 	return 0;
 }
 
-#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+#ifdef CONFIG_NUMA_BALANCING
 /*
  * This is used to mark a range of virtual addresses to be inaccessible.
  * These are later cleared by a NUMA hinting fault. Depending on these
@@ -626,7 +634,6 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long addr, unsigned long end)
 {
 	int nr_updated;
-	BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE);
 
 	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
 	if (nr_updated)
@@ -640,7 +647,7 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
 {
 	return 0;
 }
-#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * Walk through page tables and collect pages to be migrated.
@@ -649,19 +656,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  * @nodes and @flags,) it's isolated and queued to the pagelist which is
  * passed via @private.)
  */
-static struct vm_area_struct *
+static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		const nodemask_t *nodes, unsigned long flags, void *private)
 {
-	int err;
-	struct vm_area_struct *first, *vma, *prev;
-
+	int err = 0;
+	struct vm_area_struct *vma, *prev;
 
-	first = find_vma(mm, start);
-	if (!first)
-		return ERR_PTR(-EFAULT);
+	vma = find_vma(mm, start);
+	if (!vma)
+		return -EFAULT;
 	prev = NULL;
-	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+	for (; vma && vma->vm_start < end; vma = vma->vm_next) {
 		unsigned long endvma = vma->vm_end;
 
 		if (endvma > end)
@@ -671,9 +677,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 			if (prev && prev->vm_end < vma->vm_start)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 		}
 
 		if (flags & MPOL_MF_LAZY) {
@@ -687,15 +693,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 			err = queue_pages_pgd_range(vma, start, endvma, nodes,
 						flags, private);
-			if (err) {
-				first = ERR_PTR(err);
+			if (err)
 				break;
-			}
 		}
 next:
 		prev = vma;
 	}
-	return first;
+	return err;
 }
 
 /*
@@ -795,36 +799,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
-/*
- * Update task->flags PF_MEMPOLICY bit: set iff non-default
- * mempolicy.  Allows more rapid checking of this (combined perhaps
- * with other PF_* flag bits) on memory allocation hot code paths.
- *
- * If called from outside this file, the task 'p' should -only- be
- * a newly forked child not yet visible on the task list, because
- * manipulating the task flags of a visible task is not safe.
- *
- * The above limitation is why this routine has the funny name
- * mpol_fix_fork_child_flag().
- *
- * It is also safe to call this with a task pointer of current,
- * which the static wrapper mpol_set_task_struct_flag() does,
- * for use within this file.
- */
-
-void mpol_fix_fork_child_flag(struct task_struct *p)
-{
-	if (p->mempolicy)
-		p->flags |= PF_MEMPOLICY;
-	else
-		p->flags &= ~PF_MEMPOLICY;
-}
-
-static void mpol_set_task_struct_flag(void)
-{
-	mpol_fix_fork_child_flag(current);
-}
-
 /* Set the process memory policy */
 static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 			     nodemask_t *nodes)
@@ -861,7 +835,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	}
 	old = current->mempolicy;
 	current->mempolicy = new;
-	mpol_set_task_struct_flag();
 	if (new && new->mode == MPOL_INTERLEAVE &&
 	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
@@ -1059,7 +1032,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_node_page, dest,
+		err = migrate_pages(&pagelist, new_node_page, NULL, dest,
 					MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
@@ -1125,7 +1098,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	tmp = *from;
 	while (!nodes_empty(tmp)) {
 		int s,d;
-		int source = -1;
+		int source = NUMA_NO_NODE;
 		int dest = 0;
 
 		for_each_node_mask(s, tmp) {
@@ -1160,7 +1133,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 			if (!node_isset(dest, tmp))
 				break;
 		}
-		if (source == -1)
+		if (source == NUMA_NO_NODE)
 			break;
 
 		node_clear(source, tmp);
@@ -1180,30 +1153,31 @@ out:
 
 /*
  * Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
  * 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)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
-	struct vm_area_struct *vma = (struct vm_area_struct *)private;
+	struct vm_area_struct *vma;
 	unsigned long uninitialized_var(address);
 
+	vma = find_vma(current->mm, start);
 	while (vma) {
 		address = page_address_in_vma(page, vma);
 		if (address != -EFAULT)
 			break;
 		vma = vma->vm_next;
 	}
-	/*
-	 * queue_pages_range() confirms that @page belongs to some vma,
-	 * so vma shouldn't be NULL.
-	 */
-	BUG_ON(!vma);
 
-	if (PageHuge(page))
+	if (PageHuge(page)) {
+		BUG_ON(!vma);
 		return alloc_huge_page_noerr(vma, address, 1);
+	}
+	/*
+	 * if !vma, alloc_page_vma() will use task or system default policy
+	 */
 	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 }
 #else
@@ -1219,7 +1193,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	return -ENOSYS;
 }
 
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
 	return NULL;
 }
@@ -1229,7 +1203,6 @@ static long do_mbind(unsigned long start, unsigned long len,
 		     unsigned short mode, unsigned short mode_flags,
 		     nodemask_t *nmask, unsigned long flags)
 {
-	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	struct mempolicy *new;
 	unsigned long end;
@@ -1295,11 +1268,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (err)
 		goto mpol_out;
 
-	vma = queue_pages_range(mm, start, end, nmask,
+	err = queue_pages_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
-
-	err = PTR_ERR(vma);	/* maybe ... */
-	if (!IS_ERR(vma))
+	if (!err)
 		err = mbind_range(mm, start, end, new);
 
 	if (!err) {
@@ -1307,9 +1278,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
-			nr_failed = migrate_pages(&pagelist, new_vma_page,
-					(unsigned long)vma,
-					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+			nr_failed = migrate_pages(&pagelist, new_page, NULL,
+				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_movable_pages(&pagelist);
 		}
@@ -1317,7 +1287,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	} else
-		putback_lru_pages(&pagelist);
+		putback_movable_pages(&pagelist);
 
 	up_write(&mm->mmap_sem);
  mpol_out:
@@ -1393,7 +1363,7 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
 }
 
 SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
-		unsigned long, mode, unsigned long __user *, nmask,
+		unsigned long, mode, const unsigned long __user *, nmask,
 		unsigned long, maxnode, unsigned, flags)
 {
 	nodemask_t nodes;
@@ -1414,7 +1384,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 }
 
 /* Set the process memory policy */
-SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask,
+SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
 		unsigned long, maxnode)
 {
 	int err;
@@ -1556,10 +1526,10 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 
 #ifdef CONFIG_COMPAT
 
-asmlinkage long compat_sys_get_mempolicy(int __user *policy,
-				     compat_ulong_t __user *nmask,
-				     compat_ulong_t maxnode,
-				     compat_ulong_t addr, compat_ulong_t flags)
+COMPAT_SYSCALL_DEFINE5(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;
@@ -1586,8 +1556,8 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy,
 	return err;
 }
 
-asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
-				     compat_ulong_t maxnode)
+COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
+		       compat_ulong_t, maxnode)
 {
 	long err = 0;
 	unsigned long __user *nm = NULL;
@@ -1609,9 +1579,9 @@ asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
 	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)
+COMPAT_SYSCALL_DEFINE6(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;
@@ -1637,9 +1607,9 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
 
 /*
  * get_vma_policy(@task, @vma, @addr)
- * @task - task for fallback if vma policy == default
- * @vma   - virtual memory area whose policy is sought
- * @addr  - address in @vma for shared policy lookup
+ * @task: task for fallback if vma policy == default
+ * @vma: virtual memory area whose policy is sought
+ * @addr: address in @vma for shared policy lookup
  *
  * Returns effective policy for a VMA at specified address.
  * Falls back to @task or system default policy, as necessary.
@@ -1679,6 +1649,30 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 	return pol;
 }
 
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
+{
+	struct mempolicy *pol = get_task_policy(task);
+	if (vma) {
+		if (vma->vm_ops && vma->vm_ops->get_policy) {
+			bool ret = false;
+
+			pol = vma->vm_ops->get_policy(vma, vma->vm_start);
+			if (pol && (pol->flags & MPOL_F_MOF))
+				ret = true;
+			mpol_cond_put(pol);
+
+			return ret;
+		} else if (vma->vm_policy) {
+			pol = vma->vm_policy;
+		}
+	}
+
+	if (!pol)
+		return default_policy.flags & MPOL_F_MOF;
+
+	return pol->flags & MPOL_F_MOF;
+}
+
 static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
 {
 	enum zone_type dynamic_policy_zone = policy_zone;
@@ -1758,21 +1752,18 @@ static unsigned interleave_nodes(struct mempolicy *policy)
 /*
  * Depending on the memory policy provide a node from which to allocate the
  * next slab entry.
- * @policy must be protected by freeing by the caller.  If @policy is
- * the current task's mempolicy, this protection is implicit, as only the
- * task can change it's policy.  The system default policy requires no
- * such protection.
  */
-unsigned slab_node(void)
+unsigned int mempolicy_slab_node(void)
 {
 	struct mempolicy *policy;
+	int node = numa_mem_id();
 
 	if (in_interrupt())
-		return numa_node_id();
+		return node;
 
 	policy = current->mempolicy;
 	if (!policy || policy->flags & MPOL_F_LOCAL)
-		return numa_node_id();
+		return node;
 
 	switch (policy->mode) {
 	case MPOL_PREFERRED:
@@ -1792,11 +1783,11 @@ unsigned slab_node(void)
 		struct zonelist *zonelist;
 		struct zone *zone;
 		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
-		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
+		zonelist = &NODE_DATA(node)->node_zonelists[0];
 		(void)first_zones_zonelist(zonelist, highest_zoneidx,
 							&policy->v.nodes,
 							&zone);
-		return zone ? zone->node : numa_node_id();
+		return zone ? zone->node : node;
 	}
 
 	default:
@@ -1811,7 +1802,7 @@ static unsigned offset_il_node(struct mempolicy *pol,
 	unsigned nnodes = nodes_weight(pol->v.nodes);
 	unsigned target;
 	int c;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	if (!nnodes)
 		return numa_node_id();
@@ -1848,11 +1839,11 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 
 /*
  * Return the bit number of a random bit set in the nodemask.
- * (returns -1 if nodemask is empty)
+ * (returns NUMA_NO_NODE if nodemask is empty)
  */
 int node_random(const nodemask_t *maskp)
 {
-	int w, bit = -1;
+	int w, bit = NUMA_NO_NODE;
 
 	w = nodes_weight(*maskp);
 	if (w)
@@ -1864,18 +1855,18 @@ int node_random(const nodemask_t *maskp)
 #ifdef CONFIG_HUGETLBFS
 /*
  * huge_zonelist(@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
+ * @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 zonelist 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 get_mems_allowed()
+ * Must be protected by read_mems_allowed_begin()
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 				gfp_t gfp_flags, struct mempolicy **mpol,
@@ -2039,7 +2030,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 retry_cpuset:
 	pol = get_vma_policy(current, vma, addr);
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
@@ -2047,7 +2038,7 @@ retry_cpuset:
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 			goto retry_cpuset;
 
 		return page;
@@ -2057,7 +2048,7 @@ retry_cpuset:
 				      policy_nodemask(gfp, pol));
 	if (unlikely(mpol_needs_cond_ref(pol)))
 		__mpol_put(pol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 }
@@ -2091,7 +2082,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		pol = &default_policy;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/*
 	 * No reference counting needed for current->mempolicy
@@ -2104,7 +2095,7 @@ retry_cpuset:
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	return page;
@@ -2148,7 +2139,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	} else
 		*new = *old;
 
-	rcu_read_lock();
 	if (current_cpuset_is_being_rebound()) {
 		nodemask_t mems = cpuset_mems_allowed(current);
 		if (new->flags & MPOL_F_REBINDING)
@@ -2156,7 +2146,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 		else
 			mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
 	}
-	rcu_read_unlock();
 	atomic_set(&new->refcnt, 1);
 	return new;
 }
@@ -2280,9 +2269,9 @@ static void sp_free(struct sp_node *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
+ * @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.
@@ -2300,6 +2289,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 	struct zone *zone;
 	int curnid = page_to_nid(page);
 	unsigned long pgoff;
+	int thiscpu = raw_smp_processor_id();
+	int thisnid = cpu_to_node(thiscpu);
 	int polnid = -1;
 	int ret = -1;
 
@@ -2348,33 +2339,9 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	/* Migrate the page towards the node whose CPU is referencing it */
 	if (pol->flags & MPOL_F_MORON) {
-		int last_nid;
-
-		polnid = numa_node_id();
+		polnid = thisnid;
 
-		/*
-		 * Multi-stage node selection is used in conjunction
-		 * with a periodic migration fault to build a temporal
-		 * task<->page relation. By using a two-stage filter we
-		 * remove short/unlikely relations.
-		 *
-		 * Using P(p) ~ n_p / n_t as per frequentist
-		 * probability, we can equate a task's usage of a
-		 * particular page (n_p) per total usage of this
-		 * page (n_t) (in a given time-span) to a probability.
-		 *
-		 * Our periodic faults will sample this probability and
-		 * getting the same result twice in a row, given these
-		 * samples are fully independent, is then given by
-		 * P(n)^2, provided our sample period is sufficiently
-		 * short compared to the usage pattern.
-		 *
-		 * This quadric squishes small probabilities, making
-		 * it less likely we act on an unlikely task<->page
-		 * relation.
-		 */
-		last_nid = page_nid_xchg_last(page, polnid);
-		if (last_nid != polnid)
+		if (!should_numa_migrate_memory(current, page, curnid, thiscpu))
 			goto out;
 	}
 
@@ -2580,7 +2547,7 @@ void mpol_free_shared_policy(struct shared_policy *p)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-static bool __initdata numabalancing_override;
+static int __initdata numabalancing_override;
 
 static void __init check_numabalancing_enable(void)
 {
@@ -2589,9 +2556,15 @@ static void __init check_numabalancing_enable(void)
 	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 (nr_node_ids > 1 && !numabalancing_override) {
-		printk(KERN_INFO "Enabling automatic NUMA balancing. "
-			"Configure with numa_balancing= or sysctl");
+		pr_info("%s automatic NUMA balancing. "
+			"Configure with numa_balancing= or the "
+			"kernel.numa_balancing sysctl",
+			numabalancing_default ? "Enabling" : "Disabling");
 		set_numabalancing_state(numabalancing_default);
 	}
 }
@@ -2601,18 +2574,17 @@ static int __init setup_numabalancing(char *str)
 	int ret = 0;
 	if (!str)
 		goto out;
-	numabalancing_override = true;
 
 	if (!strcmp(str, "enable")) {
-		set_numabalancing_state(true);
+		numabalancing_override = 1;
 		ret = 1;
 	} else if (!strcmp(str, "disable")) {
-		set_numabalancing_state(false);
+		numabalancing_override = -1;
 		ret = 1;
 	}
 out:
 	if (!ret)
-		printk(KERN_WARNING "Unable to parse numa_balancing=\n");
+		pr_warn("Unable to parse numa_balancing=\n");
 
 	return ret;
 }
@@ -2672,7 +2644,7 @@ void __init numa_policy_init(void)
 		node_set(prefer, interleave_nodes);
 
 	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
-		printk("numa_policy_init: interleaving failed\n");
+		pr_err("%s: interleaving failed\n", __func__);
 
 	check_numabalancing_enable();
 }
@@ -2840,62 +2812,45 @@ out:
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
  *
- * Convert a mempolicy into a string.
- * Returns the number of characters in buffer (if positive)
- * or an error (negative)
+ * Convert @pol into a string.  If @buffer is too short, truncate the string.
+ * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
+ * longest flag, "relative", and to display at least a few node ids.
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	char *p = buffer;
-	int l;
-	nodemask_t nodes;
-	unsigned short mode;
-	unsigned short flags = pol ? pol->flags : 0;
+	nodemask_t nodes = NODE_MASK_NONE;
+	unsigned short mode = MPOL_DEFAULT;
+	unsigned short flags = 0;
 
-	/*
-	 * Sanity check:  room for longest mode, flag and some nodes
-	 */
-	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
-
-	if (!pol || pol == &default_policy)
-		mode = MPOL_DEFAULT;
-	else
+	if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) {
 		mode = pol->mode;
+		flags = pol->flags;
+	}
 
 	switch (mode) {
 	case MPOL_DEFAULT:
-		nodes_clear(nodes);
 		break;
-
 	case MPOL_PREFERRED:
-		nodes_clear(nodes);
 		if (flags & MPOL_F_LOCAL)
 			mode = MPOL_LOCAL;
 		else
 			node_set(pol->v.preferred_node, nodes);
 		break;
-
 	case MPOL_BIND:
-		/* Fall through */
 	case MPOL_INTERLEAVE:
 		nodes = pol->v.nodes;
 		break;
-
 	default:
-		return -EINVAL;
+		WARN_ON_ONCE(1);
+		snprintf(p, maxlen, "unknown");
+		return;
 	}
 
-	l = strlen(policy_modes[mode]);
-	if (buffer + maxlen < p + l + 1)
-		return -ENOSPC;
-
-	strcpy(p, policy_modes[mode]);
-	p += l;
+	p += snprintf(p, maxlen, "%s", policy_modes[mode]);
 
 	if (flags & MPOL_MODE_FLAGS) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = '=';
+		p += snprintf(p, buffer + maxlen - p, "=");
 
 		/*
 		 * Currently, the only defined flags are mutually exclusive
@@ -2907,10 +2862,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	}
 
 	if (!nodes_empty(nodes)) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = ':';
+		p += snprintf(p, buffer + maxlen - p, ":");
 	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
 	}
-	return p - buffer;
 }