1 files changed, 240 insertions, 173 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a5fe68189ee..1e2872b2534 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1,11 +1,13 @@
 /*
  * hugetlbpage-backed filesystem.  Based on ramfs.
  *
- * William Irwin, 2002
+ * Nadia Yvette Chambers, 2002
  *
  * Copyright (C) 2002 Linus Torvalds.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/thread_info.h>
 #include <asm/current.h>
@@ -41,6 +43,25 @@ const struct file_operations hugetlbfs_file_operations;
 static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
+struct hugetlbfs_config {
+	kuid_t   uid;
+	kgid_t   gid;
+	umode_t mode;
+	long	nr_blocks;
+	long	nr_inodes;
+	struct hstate *hstate;
+};
+
+struct hugetlbfs_inode_info {
+	struct shared_policy policy;
+	struct inode vfs_inode;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
 static struct backing_dev_info hugetlbfs_backing_dev_info = {
 	.name		= "hugetlbfs",
 	.ra_pages	= 0,	/* No readahead */
@@ -78,7 +99,7 @@ static void huge_pagevec_release(struct pagevec *pvec)
 
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
@@ -91,10 +112,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * way when do_mmap_pgoff unwinds (may be important on powerpc
 	 * and ia64).
 	 */
-	vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
+	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
 	vma->vm_ops = &hugetlb_vm_ops;
 
-	if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT))
+	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
@@ -132,8 +153,8 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
 	struct hstate *h = hstate_file(file);
+	struct vm_unmapped_area_info info;
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
@@ -154,32 +175,13 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 			return addr;
 	}
 
-	start_addr = mm->free_area_cache;
-
-	if (len <= mm->cached_hole_size)
-		start_addr = TASK_UNMAPPED_BASE;
-
-full_search:
-	addr = ALIGN(start_addr, huge_page_size(h));
-
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
-		/* At this point:  (!vma || addr < vma->vm_end). */
-		if (TASK_SIZE - len < addr) {
-			/*
-			 * Start a new search - just in case we missed
-			 * some holes.
-			 */
-			if (start_addr != TASK_UNMAPPED_BASE) {
-				start_addr = TASK_UNMAPPED_BASE;
-				goto full_search;
-			}
-			return -ENOMEM;
-		}
-
-		if (!vma || addr + len <= vma->vm_start)
-			return addr;
-		addr = ALIGN(vma->vm_end, huge_page_size(h));
-	}
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = TASK_UNMAPPED_BASE;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	return vm_unmapped_area(&info);
 }
 #endif
 
@@ -238,17 +240,10 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 	loff_t isize;
 	ssize_t retval = 0;
 
-	mutex_lock(&inode->i_mutex);
-
 	/* validate length */
 	if (len == 0)
 		goto out;
 
-	isize = i_size_read(inode);
-	if (!isize)
-		goto out;
-
-	end_index = (isize - 1) >> huge_page_shift(h);
 	for (;;) {
 		struct page *page;
 		unsigned long nr, ret;
@@ -256,18 +251,21 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = huge_page_size(h);
+		isize = i_size_read(inode);
+		if (!isize)
+			goto out;
+		end_index = (isize - 1) >> huge_page_shift(h);
 		if (index >= end_index) {
 			if (index > end_index)
 				goto out;
 			nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
-			if (nr <= offset) {
+			if (nr <= offset)
 				goto out;
-			}
 		}
 		nr = nr - offset;
 
 		/* Find the page */
-		page = find_get_page(mapping, index);
+		page = find_lock_page(mapping, index);
 		if (unlikely(page == NULL)) {
 			/*
 			 * We have a HOLE, zero out the user-buffer for the
@@ -279,17 +277,18 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 			else
 				ra = 0;
 		} else {
+			unlock_page(page);
+
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
 			ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
 			ret = ra;
+			page_cache_release(page);
 		}
 		if (ra < 0) {
 			if (retval == 0)
 				retval = ra;
-			if (page)
-				page_cache_release(page);
 			goto out;
 		}
 
@@ -299,16 +298,12 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 		index += offset >> huge_page_shift(h);
 		offset &= ~huge_page_mask(h);
 
-		if (page)
-			page_cache_release(page);
-
 		/* short read or no more work */
 		if ((ret != nr) || (len == 0))
 			break;
 	}
 out:
 	*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
-	mutex_unlock(&inode->i_mutex);
 	return retval;
 }
 
@@ -332,8 +327,7 @@ static void truncate_huge_page(struct page *page)
 {
 	cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
 	ClearPageUptodate(page);
-	remove_from_page_cache(page);
-	put_page(page);
+	delete_from_page_cache(page);
 }
 
 static void truncate_hugepages(struct inode *inode, loff_t lstart)
@@ -374,22 +368,27 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
+	struct resv_map *resv_map;
+
 	truncate_hugepages(inode, 0);
-	end_writeback(inode);
+	resv_map = (struct resv_map *)inode->i_mapping->private_data;
+	/* root inode doesn't have the resv_map, so we should check it */
+	if (resv_map)
+		resv_map_release(&resv_map->refs);
+	clear_inode(inode);
 }
 
 static inline void
-hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
+hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
 {
 	struct vm_area_struct *vma;
-	struct prio_tree_iter iter;
 
-	vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) {
+	vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) {
 		unsigned long v_offset;
 
 		/*
 		 * Can the expression below overflow on 32-bit arches?
-		 * No, because the prio_tree returns us only those vmas
+		 * No, because the interval tree returns us only those vmas
 		 * which overlap the truncated area starting at pgoff,
 		 * and no vma on a 32-bit arch can span beyond the 4GB.
 		 */
@@ -398,8 +397,8 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
 		else
 			v_offset = 0;
 
-		__unmap_hugepage_range(vma,
-				vma->vm_start + v_offset, vma->vm_end, NULL);
+		unmap_hugepage_range(vma, vma->vm_start + v_offset,
+				     vma->vm_end, NULL);
 	}
 }
 
@@ -413,10 +412,10 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	pgoff = offset >> PAGE_SHIFT;
 
 	i_size_write(inode, offset);
-	spin_lock(&mapping->i_mmap_lock);
-	if (!prio_tree_empty(&mapping->i_mmap))
+	mutex_lock(&mapping->i_mmap_mutex);
+	if (!RB_EMPTY_ROOT(&mapping->i_mmap))
 		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 	truncate_hugepages(inode, offset);
 	return 0;
 }
@@ -448,8 +447,8 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 	return 0;
 }
 
-static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, 
-					gid_t gid, int mode, dev_t dev)
+static struct inode *hugetlbfs_get_root(struct super_block *sb,
+					struct hugetlbfs_config *config)
 {
 	struct inode *inode;
 
@@ -457,13 +456,51 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 	if (inode) {
 		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
-		inode->i_mode = mode;
-		inode->i_uid = uid;
-		inode->i_gid = gid;
+		inode->i_mode = S_IFDIR | config->mode;
+		inode->i_uid = config->uid;
+		inode->i_gid = config->gid;
+		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		info = HUGETLBFS_I(inode);
+		mpol_shared_policy_init(&info->policy, NULL);
+		inode->i_op = &hugetlbfs_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		/* directory inodes start off with i_nlink == 2 (for "." entry) */
+		inc_nlink(inode);
+		lockdep_annotate_inode_mutex_key(inode);
+	}
+	return inode;
+}
+
+/*
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * be taken from reclaim -- unlike regular filesystems. This needs an
+ * annotation because huge_pmd_share() does an allocation under
+ * i_mmap_mutex.
+ */
+static struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+
+static struct inode *hugetlbfs_get_inode(struct super_block *sb,
+					struct inode *dir,
+					umode_t mode, dev_t dev)
+{
+	struct inode *inode;
+	struct resv_map *resv_map;
+
+	resv_map = resv_map_alloc();
+	if (!resv_map)
+		return NULL;
+
+	inode = new_inode(sb);
+	if (inode) {
+		struct hugetlbfs_inode_info *info;
+		inode->i_ino = get_next_ino();
+		inode_init_owner(inode, dir, mode);
+		lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
+				&hugetlbfs_i_mmap_mutex_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		INIT_LIST_HEAD(&inode->i_mapping->private_list);
+		inode->i_mapping->private_data = resv_map;
 		info = HUGETLBFS_I(inode);
 		/*
 		 * The policy is initialized here even if we are creating a
@@ -492,7 +529,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 			inode->i_op = &page_symlink_inode_operations;
 			break;
 		}
-	}
+		lockdep_annotate_inode_mutex_key(inode);
+	} else
+		kref_put(&resv_map->refs, resv_map_release);
+
 	return inode;
 }
 
@@ -500,20 +540,12 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
  * File creation. Allocate an inode, and we're done..
  */
 static int hugetlbfs_mknod(struct inode *dir,
-			struct dentry *dentry, int mode, dev_t dev)
+			struct dentry *dentry, umode_t mode, dev_t dev)
 {
 	struct inode *inode;
 	int error = -ENOSPC;
-	gid_t gid;
-
-	if (dir->i_mode & S_ISGID) {
-		gid = dir->i_gid;
-		if (S_ISDIR(mode))
-			mode |= S_ISGID;
-	} else {
-		gid = current_fsgid();
-	}
-	inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, mode, dev);
+
+	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
 	if (inode) {
 		dir->i_ctime = dir->i_mtime = CURRENT_TIME;
 		d_instantiate(dentry, inode);
@@ -523,7 +555,7 @@ static int hugetlbfs_mknod(struct inode *dir,
 	return error;
 }
 
-static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
 	if (!retval)
@@ -531,7 +563,7 @@ static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	return retval;
 }
 
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
+static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
 {
 	return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
 }
@@ -541,15 +573,8 @@ static int hugetlbfs_symlink(struct inode *dir,
 {
 	struct inode *inode;
 	int error = -ENOSPC;
-	gid_t gid;
-
-	if (dir->i_mode & S_ISGID)
-		gid = dir->i_gid;
-	else
-		gid = current_fsgid();
 
-	inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(),
-					gid, S_IFLNK|S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
 		error = page_symlink(inode, symname, l);
@@ -576,16 +601,17 @@ static int hugetlbfs_set_page_dirty(struct page *page)
 }
 
 static int hugetlbfs_migrate_page(struct address_space *mapping,
-				struct page *newpage, struct page *page)
+				struct page *newpage, struct page *page,
+				enum migrate_mode mode)
 {
 	int rc;
 
 	rc = migrate_huge_page_move_mapping(mapping, newpage, page);
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 	migrate_page_copy(newpage, page);
 
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 
 static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -599,9 +625,15 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		spin_lock(&sbinfo->stat_lock);
 		/* If no limits set, just report 0 for max/free/used
 		 * blocks, like simple_statfs() */
-		if (sbinfo->max_blocks >= 0) {
-			buf->f_blocks = sbinfo->max_blocks;
-			buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+		if (sbinfo->spool) {
+			long free_pages;
+
+			spin_lock(&sbinfo->spool->lock);
+			buf->f_blocks = sbinfo->spool->max_hpages;
+			free_pages = sbinfo->spool->max_hpages
+				- sbinfo->spool->used_hpages;
+			buf->f_bavail = buf->f_bfree = free_pages;
+			spin_unlock(&sbinfo->spool->lock);
 			buf->f_files = sbinfo->max_inodes;
 			buf->f_ffree = sbinfo->free_inodes;
 		}
@@ -617,6 +649,10 @@ static void hugetlbfs_put_super(struct super_block *sb)
 
 	if (sbi) {
 		sb->s_fs_info = NULL;
+
+		if (sbi->spool)
+			hugepage_put_subpool(sbi->spool);
+
 		kfree(sbi);
 	}
 }
@@ -663,11 +699,17 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 	return &p->vfs_inode;
 }
 
+static void hugetlbfs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
+}
+
 static void hugetlbfs_destroy_inode(struct inode *inode)
 {
 	hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
 	mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
-	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
+	call_rcu(&inode->i_rcu, hugetlbfs_i_callback);
 }
 
 static const struct address_space_operations hugetlbfs_aops = {
@@ -741,13 +783,17 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 		case Opt_uid:
 			if (match_int(&args[0], &option))
  				goto bad_val;
-			pconfig->uid = option;
+			pconfig->uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(pconfig->uid))
+				goto bad_val;
 			break;
 
 		case Opt_gid:
 			if (match_int(&args[0], &option))
  				goto bad_val;
-			pconfig->gid = option;
+			pconfig->gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(pconfig->gid))
+				goto bad_val;
 			break;
 
 		case Opt_mode:
@@ -779,8 +825,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 			ps = memparse(args[0].from, &rest);
 			pconfig->hstate = size_to_hstate(ps);
 			if (!pconfig->hstate) {
-				printk(KERN_ERR
-				"hugetlbfs: Unsupported page size %lu MB\n",
+				pr_err("Unsupported page size %lu MB\n",
 					ps >> 20);
 				return -EINVAL;
 			}
@@ -788,8 +833,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 		}
 
 		default:
-			printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
-				 p);
+			pr_err("Bad mount option: \"%s\"\n", p);
 			return -EINVAL;
 			break;
 		}
@@ -809,16 +853,13 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 	return 0;
 
 bad_val:
- 	printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
-	       args[0].from, p);
+	pr_err("Bad value '%s' for mount option '%s'\n", args[0].from, p);
  	return -EINVAL;
 }
 
 static int
 hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct inode * inode;
-	struct dentry * root;
 	int ret;
 	struct hugetlbfs_config config;
 	struct hugetlbfs_sb_info *sbinfo;
@@ -841,61 +882,30 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_fs_info = sbinfo;
 	sbinfo->hstate = config.hstate;
 	spin_lock_init(&sbinfo->stat_lock);
-	sbinfo->max_blocks = config.nr_blocks;
-	sbinfo->free_blocks = config.nr_blocks;
 	sbinfo->max_inodes = config.nr_inodes;
 	sbinfo->free_inodes = config.nr_inodes;
+	sbinfo->spool = NULL;
+	if (config.nr_blocks != -1) {
+		sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
+		if (!sbinfo->spool)
+			goto out_free;
+	}
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize = huge_page_size(config.hstate);
 	sb->s_blocksize_bits = huge_page_shift(config.hstate);
 	sb->s_magic = HUGETLBFS_MAGIC;
 	sb->s_op = &hugetlbfs_ops;
 	sb->s_time_gran = 1;
-	inode = hugetlbfs_get_inode(sb, config.uid, config.gid,
-					S_IFDIR | config.mode, 0);
-	if (!inode)
-		goto out_free;
-
-	root = d_alloc_root(inode);
-	if (!root) {
-		iput(inode);
+	sb->s_root = d_make_root(hugetlbfs_get_root(sb, &config));
+	if (!sb->s_root)
 		goto out_free;
-	}
-	sb->s_root = root;
 	return 0;
 out_free:
+	kfree(sbinfo->spool);
 	kfree(sbinfo);
 	return -ENOMEM;
 }
 
-int hugetlb_get_quota(struct address_space *mapping, long delta)
-{
-	int ret = 0;
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
-	if (sbinfo->free_blocks > -1) {
-		spin_lock(&sbinfo->stat_lock);
-		if (sbinfo->free_blocks - delta >= 0)
-			sbinfo->free_blocks -= delta;
-		else
-			ret = -ENOMEM;
-		spin_unlock(&sbinfo->stat_lock);
-	}
-
-	return ret;
-}
-
-void hugetlb_put_quota(struct address_space *mapping, long delta)
-{
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
-	if (sbinfo->free_blocks > -1) {
-		spin_lock(&sbinfo->stat_lock);
-		sbinfo->free_blocks += delta;
-		spin_unlock(&sbinfo->stat_lock);
-	}
-}
-
 static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
@@ -907,54 +917,82 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.mount		= hugetlbfs_mount,
 	.kill_sb	= kill_litter_super,
 };
+MODULE_ALIAS_FS("hugetlbfs");
 
-static struct vfsmount *hugetlbfs_vfsmount;
+static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
 
 static int can_do_hugetlb_shm(void)
 {
-	return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
+	kgid_t shm_group;
+	shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group);
+	return capable(CAP_IPC_LOCK) || in_group_p(shm_group);
 }
 
-struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
-				struct user_struct **user, int creat_flags)
+static int get_hstate_idx(int page_size_log)
 {
-	int error = -ENOMEM;
-	struct file *file;
+	struct hstate *h = hstate_sizelog(page_size_log);
+
+	if (!h)
+		return -1;
+	return h - hstates;
+}
+
+static const struct dentry_operations anon_ops = {
+	.d_dname = simple_dname
+};
+
+/*
+ * Note that size should be aligned to proper hugepage size in caller side,
+ * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
+ */
+struct file *hugetlb_file_setup(const char *name, size_t size,
+				vm_flags_t acctflag, struct user_struct **user,
+				int creat_flags, int page_size_log)
+{
+	struct file *file = ERR_PTR(-ENOMEM);
 	struct inode *inode;
 	struct path path;
-	struct dentry *root;
+	struct super_block *sb;
 	struct qstr quick_string;
+	int hstate_idx;
+
+	hstate_idx = get_hstate_idx(page_size_log);
+	if (hstate_idx < 0)
+		return ERR_PTR(-ENODEV);
 
 	*user = NULL;
-	if (!hugetlbfs_vfsmount)
+	if (!hugetlbfs_vfsmount[hstate_idx])
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
 		*user = current_user();
 		if (user_shm_lock(size, *user)) {
-			printk_once(KERN_WARNING "Using mlock ulimits for SHM_HUGETLB is deprecated\n");
+			task_lock(current);
+			pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+				current->comm, current->pid);
+			task_unlock(current);
 		} else {
 			*user = NULL;
 			return ERR_PTR(-EPERM);
 		}
 	}
 
-	root = hugetlbfs_vfsmount->mnt_root;
+	sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
 	quick_string.name = name;
 	quick_string.len = strlen(quick_string.name);
 	quick_string.hash = 0;
-	path.dentry = d_alloc(root, &quick_string);
+	path.dentry = d_alloc_pseudo(sb, &quick_string);
 	if (!path.dentry)
 		goto out_shm_unlock;
 
-	path.mnt = mntget(hugetlbfs_vfsmount);
-	error = -ENOSPC;
-	inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(),
-				current_fsgid(), S_IFREG | S_IRWXUGO, 0);
+	d_set_d_op(path.dentry, &anon_ops);
+	path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
+	file = ERR_PTR(-ENOSPC);
+	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
 
-	error = -ENOMEM;
+	file = ERR_PTR(-ENOMEM);
 	if (hugetlb_reserve_pages(inode, 0,
 			size >> huge_page_shift(hstate_inode(inode)), NULL,
 			acctflag))
@@ -962,12 +1000,11 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
 
 	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
-	inode->i_nlink = 0;
+	clear_nlink(inode);
 
-	error = -ENFILE;
 	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
 			&hugetlbfs_file_operations);
-	if (!file)
+	if (IS_ERR(file))
 		goto out_dentry; /* inode is already attached */
 
 	return file;
@@ -981,18 +1018,25 @@ out_shm_unlock:
 		user_shm_unlock(size, *user);
 		*user = NULL;
 	}
-	return ERR_PTR(error);
+	return file;
 }
 
 static int __init init_hugetlbfs_fs(void)
 {
+	struct hstate *h;
 	int error;
-	struct vfsmount *vfsmount;
+	int i;
+
+	if (!hugepages_supported()) {
+		pr_info("disabling because there are no supported hugepage sizes\n");
+		return -ENOTSUPP;
+	}
 
 	error = bdi_init(&hugetlbfs_backing_dev_info);
 	if (error)
 		return error;
 
+	error = -ENOMEM;
 	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
 					sizeof(struct hugetlbfs_inode_info),
 					0, 0, init_once);
@@ -1003,18 +1047,29 @@ static int __init init_hugetlbfs_fs(void)
 	if (error)
 		goto out;
 
-	vfsmount = kern_mount(&hugetlbfs_fs_type);
+	i = 0;
+	for_each_hstate(h) {
+		char buf[50];
+		unsigned ps_kb = 1U << (h->order + PAGE_SHIFT - 10);
 
-	if (!IS_ERR(vfsmount)) {
-		hugetlbfs_vfsmount = vfsmount;
-		return 0;
-	}
+		snprintf(buf, sizeof(buf), "pagesize=%uK", ps_kb);
+		hugetlbfs_vfsmount[i] = kern_mount_data(&hugetlbfs_fs_type,
+							buf);
 
-	error = PTR_ERR(vfsmount);
+		if (IS_ERR(hugetlbfs_vfsmount[i])) {
+			pr_err("Cannot mount internal hugetlbfs for "
+				"page size %uK", ps_kb);
+			error = PTR_ERR(hugetlbfs_vfsmount[i]);
+			hugetlbfs_vfsmount[i] = NULL;
+		}
+		i++;
+	}
+	/* Non default hstates are optional */
+	if (!IS_ERR_OR_NULL(hugetlbfs_vfsmount[default_hstate_idx]))
+		return 0;
 
  out:
-	if (error)
-		kmem_cache_destroy(hugetlbfs_inode_cachep);
+	kmem_cache_destroy(hugetlbfs_inode_cachep);
  out2:
 	bdi_destroy(&hugetlbfs_backing_dev_info);
 	return error;
@@ -1022,7 +1077,19 @@ static int __init init_hugetlbfs_fs(void)
 
 static void __exit exit_hugetlbfs_fs(void)
 {
+	struct hstate *h;
+	int i;
+
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
+	i = 0;
+	for_each_hstate(h)
+		kern_unmount(hugetlbfs_vfsmount[i++]);
 	unregister_filesystem(&hugetlbfs_fs_type);
 	bdi_destroy(&hugetlbfs_backing_dev_info);
 }