1 files changed, 47 insertions, 102 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index eca4a31..0472964 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,9 +525,8 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 #ifdef CONFIG_HUGETLB_PAGE
 	int nid;
 	struct page *page;
-	spinlock_t *ptl;
 
-	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
+	spin_lock(&vma->vm_mm->page_table_lock);
 	page = pte_page(huge_ptep_get((pte_t *)pmd));
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -537,7 +536,7 @@ 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(ptl);
+	spin_unlock(&vma->vm_mm->page_table_lock);
 #else
 	BUG();
 #endif
@@ -1126,7 +1125,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	tmp = *from;
 	while (!nodes_empty(tmp)) {
 		int s,d;
-		int source = NUMA_NO_NODE;
+		int source = -1;
 		int dest = 0;
 
 		for_each_node_mask(s, tmp) {
@@ -1161,7 +1160,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 			if (!node_isset(dest, tmp))
 				break;
 		}
-		if (source == NUMA_NO_NODE)
+		if (source == -1)
 			break;
 
 		node_clear(source, tmp);
@@ -1680,30 +1679,6 @@ 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;
@@ -1836,7 +1811,7 @@ static unsigned offset_il_node(struct mempolicy *pol,
 	unsigned nnodes = nodes_weight(pol->v.nodes);
 	unsigned target;
 	int c;
-	int nid = NUMA_NO_NODE;
+	int nid = -1;
 
 	if (!nnodes)
 		return numa_node_id();
@@ -1873,11 +1848,11 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 
 /*
  * Return the bit number of a random bit set in the nodemask.
- * (returns NUMA_NO_NODE if nodemask is empty)
+ * (returns -1 if nodemask is empty)
  */
 int node_random(const nodemask_t *maskp)
 {
-	int w, bit = NUMA_NO_NODE;
+	int w, bit = -1;
 
 	w = nodes_weight(*maskp);
 	if (w)
@@ -2302,35 +2277,6 @@ static void sp_free(struct sp_node *n)
 	kmem_cache_free(sn_cache, n);
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-	/* Never defer a private fault */
-	if (cpupid_match_pid(p, last_cpupid))
-		return false;
-
-	if (p->numa_migrate_deferred) {
-		p->numa_migrate_deferred--;
-		return true;
-	}
-	return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-	p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
-}
-#else
-static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-	return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2354,8 +2300,6 @@ 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;
 
@@ -2404,11 +2348,9 @@ 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_cpupid;
-		int this_cpupid;
+		int last_nid;
 
-		polnid = thisnid;
-		this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);
+		polnid = numa_node_id();
 
 		/*
 		 * Multi-stage node selection is used in conjunction
@@ -2431,25 +2373,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * it less likely we act on an unlikely task<->page
 		 * relation.
 		 */
-		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
-		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
-
-			/* See sysctl_numa_balancing_migrate_deferred comment */
-			if (!cpupid_match_pid(current, last_cpupid))
-				defer_numa_migrate(current);
-
-			goto out;
-		}
-
-		/*
-		 * The quadratic filter above reduces extraneous migration
-		 * of shared pages somewhat. This code reduces it even more,
-		 * reducing the overhead of page migrations of shared pages.
-		 * This makes workloads with shared pages rely more on
-		 * "move task near its memory", and less on "move memory
-		 * towards its task", which is exactly what we want.
-		 */
-		if (numa_migrate_deferred(current, last_cpupid))
+		last_nid = page_nid_xchg_last(page, polnid);
+		if (last_nid != polnid)
 			goto out;
 	}
 
@@ -2915,45 +2840,62 @@ out:
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
  *
- * 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.
+ * Convert a mempolicy into a string.
+ * Returns the number of characters in buffer (if positive)
+ * or an error (negative)
  */
-void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	char *p = buffer;
-	nodemask_t nodes = NODE_MASK_NONE;
-	unsigned short mode = MPOL_DEFAULT;
-	unsigned short flags = 0;
+	int l;
+	nodemask_t nodes;
+	unsigned short mode;
+	unsigned short flags = pol ? pol->flags : 0;
 
-	if (pol && pol != &default_policy) {
+	/*
+	 * 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
 		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:
-		WARN_ON_ONCE(1);
-		snprintf(p, maxlen, "unknown");
-		return;
+		return -EINVAL;
 	}
 
-	p += snprintf(p, maxlen, "%s", policy_modes[mode]);
+	l = strlen(policy_modes[mode]);
+	if (buffer + maxlen < p + l + 1)
+		return -ENOSPC;
+
+	strcpy(p, policy_modes[mode]);
+	p += l;
 
 	if (flags & MPOL_MODE_FLAGS) {
-		p += snprintf(p, buffer + maxlen - p, "=");
+		if (buffer + maxlen < p + 2)
+			return -ENOSPC;
+		*p++ = '=';
 
 		/*
 		 * Currently, the only defined flags are mutually exclusive
@@ -2965,7 +2907,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	}
 
 	if (!nodes_empty(nodes)) {
-		p += snprintf(p, buffer + maxlen - p, ":");
+		if (buffer + maxlen < p + 2)
+			return -ENOSPC;
+		*p++ = ':';
 	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
 	}
+	return p - buffer;
 }