Merge branch 'x86/urgent' into x86/mm, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 104 insertions, 45 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 618ab125228b..a2af6d58a68f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -97,6 +97,7 @@
 #include <linux/mm_inline.h>
 #include <linux/mmu_notifier.h>
 #include <linux/printk.h>
+#include <linux/swapops.h>
 
 #include <asm/tlbflush.h>
 #include <linux/uaccess.h>
@@ -412,6 +413,64 @@ struct queue_pages {
 };
 
 /*
+ * Check if the page's nid is in qp->nmask.
+ *
+ * If MPOL_MF_INVERT is set in qp->flags, check if the nid is
+ * in the invert of qp->nmask.
+ */
+static inline bool queue_pages_required(struct page *page,
+					struct queue_pages *qp)
+{
+	int nid = page_to_nid(page);
+	unsigned long flags = qp->flags;
+
+	return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
+}
+
+static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+{
+	int ret = 0;
+	struct page *page;
+	struct queue_pages *qp = walk->private;
+	unsigned long flags;
+
+	if (unlikely(is_pmd_migration_entry(*pmd))) {
+		ret = 1;
+		goto unlock;
+	}
+	page = pmd_page(*pmd);
+	if (is_huge_zero_page(page)) {
+		spin_unlock(ptl);
+		__split_huge_pmd(walk->vma, pmd, addr, false, NULL);
+		goto out;
+	}
+	if (!thp_migration_supported()) {
+		get_page(page);
+		spin_unlock(ptl);
+		lock_page(page);
+		ret = split_huge_page(page);
+		unlock_page(page);
+		put_page(page);
+		goto out;
+	}
+	if (!queue_pages_required(page, qp)) {
+		ret = 1;
+		goto unlock;
+	}
+
+	ret = 1;
+	flags = qp->flags;
+	/* go to thp migration */
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+		migrate_page_add(page, qp->pagelist, flags);
+unlock:
+	spin_unlock(ptl);
+out:
+	return ret;
+}
+
+/*
  * Scan through pages checking if pages follow certain conditions,
  * and move them to the pagelist if they do.
  */
@@ -422,30 +481,15 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 	struct queue_pages *qp = walk->private;
 	unsigned long flags = qp->flags;
-	int nid, ret;
+	int ret;
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge(*pmd)) {
-		ptl = pmd_lock(walk->mm, pmd);
-		if (pmd_trans_huge(*pmd)) {
-			page = pmd_page(*pmd);
-			if (is_huge_zero_page(page)) {
-				spin_unlock(ptl);
-				__split_huge_pmd(vma, pmd, addr, false, NULL);
-			} else {
-				get_page(page);
-				spin_unlock(ptl);
-				lock_page(page);
-				ret = split_huge_page(page);
-				unlock_page(page);
-				put_page(page);
-				if (ret)
-					return 0;
-			}
-		} else {
-			spin_unlock(ptl);
-		}
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
+		ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
+		if (ret)
+			return 0;
 	}
 
 	if (pmd_trans_unstable(pmd))
@@ -464,10 +508,9 @@ retry:
 		 */
 		if (PageReserved(page))
 			continue;
-		nid = page_to_nid(page);
-		if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
+		if (!queue_pages_required(page, qp))
 			continue;
-		if (PageTransCompound(page)) {
+		if (PageTransCompound(page) && !thp_migration_supported()) {
 			get_page(page);
 			pte_unmap_unlock(pte, ptl);
 			lock_page(page);
@@ -497,7 +540,6 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
 #ifdef CONFIG_HUGETLB_PAGE
 	struct queue_pages *qp = walk->private;
 	unsigned long flags = qp->flags;
-	int nid;
 	struct page *page;
 	spinlock_t *ptl;
 	pte_t entry;
@@ -507,8 +549,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
 	if (!pte_present(entry))
 		goto unlock;
 	page = pte_page(entry);
-	nid = page_to_nid(page);
-	if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
+	if (!queue_pages_required(page, qp))
 		goto unlock;
 	/* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
 	if (flags & (MPOL_MF_MOVE_ALL) ||
@@ -881,19 +922,21 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 
 #ifdef CONFIG_MIGRATION
 /*
- * page migration
+ * page migration, thp tail pages can be passed.
  */
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags)
 {
+	struct page *head = compound_head(page);
 	/*
 	 * Avoid migrating a page that is shared with others.
 	 */
-	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
-		if (!isolate_lru_page(page)) {
-			list_add_tail(&page->lru, pagelist);
-			inc_node_page_state(page, NR_ISOLATED_ANON +
-					    page_is_file_cache(page));
+	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) {
+		if (!isolate_lru_page(head)) {
+			list_add_tail(&head->lru, pagelist);
+			mod_node_page_state(page_pgdat(head),
+				NR_ISOLATED_ANON + page_is_file_cache(head),
+				hpage_nr_pages(head));
 		}
 	}
 }
@@ -903,7 +946,17 @@ static struct page *new_node_page(struct page *page, unsigned long node, int **x
 	if (PageHuge(page))
 		return alloc_huge_page_node(page_hstate(compound_head(page)),
 					node);
-	else
+	else if (thp_migration_supported() && PageTransHuge(page)) {
+		struct page *thp;
+
+		thp = alloc_pages_node(node,
+			(GFP_TRANSHUGE | __GFP_THISNODE),
+			HPAGE_PMD_ORDER);
+		if (!thp)
+			return NULL;
+		prep_transhuge_page(thp);
+		return thp;
+	} else
 		return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE |
 						    __GFP_THISNODE, 0);
 }
@@ -1069,6 +1122,15 @@ static struct page *new_page(struct page *page, unsigned long start, int **x)
 	if (PageHuge(page)) {
 		BUG_ON(!vma);
 		return alloc_huge_page_noerr(vma, address, 1);
+	} else if (thp_migration_supported() && PageTransHuge(page)) {
+		struct page *thp;
+
+		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
+					 HPAGE_PMD_ORDER);
+		if (!thp)
+			return NULL;
+		prep_transhuge_page(thp);
+		return thp;
 	}
 	/*
 	 * if !vma, alloc_page_vma() will use task or system default policy
@@ -1683,8 +1745,7 @@ unsigned int mempolicy_slab_node(void)
  * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the
  * number of present nodes.
  */
-static unsigned offset_il_node(struct mempolicy *pol,
-			       struct vm_area_struct *vma, unsigned long n)
+static unsigned offset_il_node(struct mempolicy *pol, unsigned long n)
 {
 	unsigned nnodes = nodes_weight(pol->v.nodes);
 	unsigned target;
@@ -1717,7 +1778,7 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 		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);
+		return offset_il_node(pol, off);
 	} else
 		return interleave_nodes(pol);
 }
@@ -1859,8 +1920,11 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 	struct page *page;
 
 	page = __alloc_pages(gfp, order, nid);
-	if (page && page_to_nid(page) == nid)
-		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
+	if (page && page_to_nid(page) == nid) {
+		preempt_disable();
+		__inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT);
+		preempt_enable();
+	}
 	return page;
 }
 
@@ -2172,20 +2236,15 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 	int polnid = -1;
 	int ret = -1;
 
-	BUG_ON(!vma);
-
 	pol = get_vma_policy(vma, addr);
 	if (!(pol->flags & MPOL_F_MOF))
 		goto out;
 
 	switch (pol->mode) {
 	case MPOL_INTERLEAVE:
-		BUG_ON(addr >= vma->vm_end);
-		BUG_ON(addr < vma->vm_start);
-
 		pgoff = vma->vm_pgoff;
 		pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
-		polnid = offset_il_node(pol, vma, pgoff);
+		polnid = offset_il_node(pol, pgoff);
 		break;
 
 	case MPOL_PREFERRED: