1 files changed, 31 insertions, 108 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fe76f8fd5a73..cbf32d2824fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -648,6 +648,8 @@ retry:
 			}
 
 			del += t - f;
+			hugetlb_cgroup_uncharge_file_region(
+				resv, rg, t - f);
 
 			/* New entry for end of split region */
 			nrg->from = t;
@@ -660,9 +662,6 @@ retry:
 			/* Original entry is trimmed */
 			rg->to = f;
 
-			hugetlb_cgroup_uncharge_file_region(
-				resv, rg, nrg->to - nrg->from);
-
 			list_add(&nrg->link, &rg->link);
 			nrg = NULL;
 			break;
@@ -678,17 +677,17 @@ retry:
 		}
 
 		if (f <= rg->from) {	/* Trim beginning of region */
-			del += t - rg->from;
-			rg->from = t;
-
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
 							    t - rg->from);
-		} else {		/* Trim end of region */
-			del += rg->to - f;
-			rg->to = f;
 
+			del += t - rg->from;
+			rg->from = t;
+		} else {		/* Trim end of region */
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
 							    rg->to - f);
+
+			del += rg->to - f;
+			rg->to = f;
 		}
 	}
 
@@ -1217,6 +1216,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	}
 
 	set_compound_order(page, 0);
+	page[1].compound_nr = 0;
 	__ClearPageHead(page);
 }
 
@@ -1569,103 +1569,23 @@ int PageHeadHuge(struct page *page_head)
 }
 
 /*
- * Find address_space associated with hugetlbfs page.
- * Upon entry page is locked and page 'was' mapped although mapped state
- * could change.  If necessary, use anon_vma to find vma and associated
- * address space.  The returned mapping may be stale, but it can not be
- * invalid as page lock (which is held) is required to destroy mapping.
- */
-static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
-{
-	struct anon_vma *anon_vma;
-	pgoff_t pgoff_start, pgoff_end;
-	struct anon_vma_chain *avc;
-	struct address_space *mapping = page_mapping(hpage);
-
-	/* Simple file based mapping */
-	if (mapping)
-		return mapping;
-
-	/*
-	 * Even anonymous hugetlbfs mappings are associated with an
-	 * underlying hugetlbfs file (see hugetlb_file_setup in mmap
-	 * code).  Find a vma associated with the anonymous vma, and
-	 * use the file pointer to get address_space.
-	 */
-	anon_vma = page_lock_anon_vma_read(hpage);
-	if (!anon_vma)
-		return mapping;  /* NULL */
-
-	/* Use first found vma */
-	pgoff_start = page_to_pgoff(hpage);
-	pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
-					pgoff_start, pgoff_end) {
-		struct vm_area_struct *vma = avc->vma;
-
-		mapping = vma->vm_file->f_mapping;
-		break;
-	}
-
-	anon_vma_unlock_read(anon_vma);
-	return mapping;
-}
-
-/*
  * Find and lock address space (mapping) in write mode.
  *
- * Upon entry, the page is locked which allows us to find the mapping
- * even in the case of an anon page.  However, locking order dictates
- * the i_mmap_rwsem be acquired BEFORE the page lock.  This is hugetlbfs
- * specific.  So, we first try to lock the sema while still holding the
- * page lock.  If this works, great!  If not, then we need to drop the
- * page lock and then acquire i_mmap_rwsem and reacquire page lock.  Of
- * course, need to revalidate state along the way.
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable.  Due to locking order, we can only trylock_write.  If we can
+ * not get the lock, simply return NULL to caller.
  */
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
 {
-	struct address_space *mapping, *mapping2;
+	struct address_space *mapping = page_mapping(hpage);
 
-	mapping = _get_hugetlb_page_mapping(hpage);
-retry:
 	if (!mapping)
 		return mapping;
 
-	/*
-	 * If no contention, take lock and return
-	 */
 	if (i_mmap_trylock_write(mapping))
 		return mapping;
 
-	/*
-	 * Must drop page lock and wait on mapping sema.
-	 * Note:  Once page lock is dropped, mapping could become invalid.
-	 * As a hack, increase map count until we lock page again.
-	 */
-	atomic_inc(&hpage->_mapcount);
-	unlock_page(hpage);
-	i_mmap_lock_write(mapping);
-	lock_page(hpage);
-	atomic_add_negative(-1, &hpage->_mapcount);
-
-	/* verify page is still mapped */
-	if (!page_mapped(hpage)) {
-		i_mmap_unlock_write(mapping);
-		return NULL;
-	}
-
-	/*
-	 * Get address space again and verify it is the same one
-	 * we locked.  If not, drop lock and retry.
-	 */
-	mapping2 = _get_hugetlb_page_mapping(hpage);
-	if (mapping2 != mapping) {
-		i_mmap_unlock_write(mapping);
-		mapping = mapping2;
-		goto retry;
-	}
-
-	return mapping;
+	return NULL;
 }
 
 pgoff_t __basepage_index(struct page *page)
@@ -2024,13 +1944,14 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
  * Increase the hugetlb pool such that it can accommodate a reservation
  * of size 'delta'.
  */
-static int gather_surplus_pages(struct hstate *h, int delta)
+static int gather_surplus_pages(struct hstate *h, long delta)
 	__must_hold(&hugetlb_lock)
 {
 	struct list_head surplus_list;
 	struct page *page, *tmp;
-	int ret, i;
-	int needed, allocated;
+	int ret;
+	long i;
+	long needed, allocated;
 	bool alloc_ok = true;
 
 	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
@@ -2094,8 +2015,7 @@ retry:
 		 * This page is now managed by the hugetlb allocator and has
 		 * no users -- drop the buddy allocator's reference.
 		 */
-		put_page_testzero(page);
-		VM_BUG_ON_PAGE(page_count(page), page);
+		VM_BUG_ON_PAGE(!put_page_testzero(page), page);
 		enqueue_huge_page(h, page);
 	}
 free:
@@ -2443,6 +2363,9 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 
 		rsv_adjust = hugepage_subpool_put_pages(spool, 1);
 		hugetlb_acct_memory(h, -rsv_adjust);
+		if (deferred_reserve)
+			hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+					pages_per_huge_page(h), page);
 	}
 	return page;
 
@@ -2837,7 +2760,7 @@ static ssize_t nr_hugepages_show_common(struct kobject *kobj,
 	else
 		nr_huge_pages = h->nr_huge_pages_node[nid];
 
-	return sprintf(buf, "%lu\n", nr_huge_pages);
+	return sysfs_emit(buf, "%lu\n", nr_huge_pages);
 }
 
 static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
@@ -2910,7 +2833,8 @@ HSTATE_ATTR(nr_hugepages);
  * huge page alloc/free.
  */
 static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
-				       struct kobj_attribute *attr, char *buf)
+					   struct kobj_attribute *attr,
+					   char *buf)
 {
 	return nr_hugepages_show_common(kobj, attr, buf);
 }
@@ -2928,7 +2852,7 @@ static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
 					struct kobj_attribute *attr, char *buf)
 {
 	struct hstate *h = kobj_to_hstate(kobj, NULL);
-	return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
+	return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages);
 }
 
 static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
@@ -2966,7 +2890,7 @@ static ssize_t free_hugepages_show(struct kobject *kobj,
 	else
 		free_huge_pages = h->free_huge_pages_node[nid];
 
-	return sprintf(buf, "%lu\n", free_huge_pages);
+	return sysfs_emit(buf, "%lu\n", free_huge_pages);
 }
 HSTATE_ATTR_RO(free_hugepages);
 
@@ -2974,7 +2898,7 @@ static ssize_t resv_hugepages_show(struct kobject *kobj,
 					struct kobj_attribute *attr, char *buf)
 {
 	struct hstate *h = kobj_to_hstate(kobj, NULL);
-	return sprintf(buf, "%lu\n", h->resv_huge_pages);
+	return sysfs_emit(buf, "%lu\n", h->resv_huge_pages);
 }
 HSTATE_ATTR_RO(resv_hugepages);
 
@@ -2991,7 +2915,7 @@ static ssize_t surplus_hugepages_show(struct kobject *kobj,
 	else
 		surplus_huge_pages = h->surplus_huge_pages_node[nid];
 
-	return sprintf(buf, "%lu\n", surplus_huge_pages);
+	return sysfs_emit(buf, "%lu\n", surplus_huge_pages);
 }
 HSTATE_ATTR_RO(surplus_hugepages);
 
@@ -3275,8 +3199,6 @@ void __init hugetlb_add_hstate(unsigned int order)
 	h = &hstates[hugetlb_max_hstate++];
 	h->order = order;
 	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
-	h->nr_huge_pages = 0;
-	h->free_huge_pages = 0;
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
 	INIT_LIST_HEAD(&h->hugepage_activelist);
@@ -3750,7 +3672,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
-	.split = hugetlb_vm_op_split,
+	.may_split = hugetlb_vm_op_split,
 	.pagesize = hugetlb_vm_op_pagesize,
 };
 
@@ -5192,6 +5114,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 
 		if (unlikely(add < 0)) {
 			hugetlb_acct_memory(h, -gbl_reserve);
+			ret = add;
 			goto out_put_pages;
 		} else if (unlikely(chg > add)) {
 			/*