Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs fixes from Al Viro:
 "Overlayfs fixes from Miklos, assorted fixes from me.

  Stable fodder of varying severity, all sat in -next for a while"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ovl: ignore permissions on underlying lookup
  vfs: add lookup_hash() helper
  vfs: rename: check backing inode being equal
  vfs: add vfs_select_inode() helper
  get_rock_ridge_filename(): handle malformed NM entries
  ecryptfs: fix handling of directory opening
  atomic_open(): fix the handling of create_error
  fix the copy vs. map logics in blk_rq_map_user_iov()
  do_splice_to(): cap the size before passing to ->splice_read()

block/blk-map.c

@@ -9,24 +9,6 @@
 
 #include "blk.h"
 
-static bool iovec_gap_to_prv(struct request_queue *q,
-			     struct iovec *prv, struct iovec *cur)
-{
-	unsigned long prev_end;
-
-	if (!queue_virt_boundary(q))
-		return false;
-
-	if (prv->iov_base == NULL && prv->iov_len == 0)
-		/* prv is not set - don't check */
-		return false;
-
-	prev_end = (unsigned long)(prv->iov_base + prv->iov_len);
-
-	return (((unsigned long)cur->iov_base & queue_virt_boundary(q)) ||
-		prev_end & queue_virt_boundary(q));
-}
-
 int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		      struct bio *bio)
 {
@@ -125,31 +107,18 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			struct rq_map_data *map_data,
 			const struct iov_iter *iter, gfp_t gfp_mask)
 {
-	struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0};
-	bool copy = (q->dma_pad_mask & iter->count) || map_data;
+	bool copy = false;
+	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
 	struct bio *bio = NULL;
 	struct iov_iter i;
 	int ret;
 
-	if (!iter || !iter->count)
-		return -EINVAL;
-
-	iov_for_each(iov, i, *iter) {
-		unsigned long uaddr = (unsigned long) iov.iov_base;
-
-		if (!iov.iov_len)
-			return -EINVAL;
-
-		/*
-		 * Keep going so we check length of all segments
-		 */
-		if ((uaddr & queue_dma_alignment(q)) ||
-		    iovec_gap_to_prv(q, &prv, &iov))
+	if (map_data)
 		copy = true;
-
-		prv.iov_base = iov.iov_base;
-		prv.iov_len = iov.iov_len;
-	}
+	else if (iov_iter_alignment(iter) & align)
+		copy = true;
+	else if (queue_virt_boundary(q))
+		copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter);
 
 	i = *iter;
 	do {

fs/ecryptfs/file.c

@@ -112,7 +112,6 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
 		.sb = inode->i_sb,
 	};
 	lower_file = ecryptfs_file_to_lower(file);
-	lower_file->f_pos = ctx->pos;
 	rc = iterate_dir(lower_file, &buf.ctx);
 	ctx->pos = buf.ctx.pos;
 	if (rc < 0)
@@ -223,14 +222,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	}
 	ecryptfs_set_file_lower(
 		file, ecryptfs_inode_to_private(inode)->lower_file);
-	if (d_is_dir(ecryptfs_dentry)) {
-		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
-		mutex_lock(&crypt_stat->cs_mutex);
-		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
-		mutex_unlock(&crypt_stat->cs_mutex);
-		rc = 0;
-		goto out;
-	}
 	rc = read_or_initialize_metadata(ecryptfs_dentry);
 	if (rc)
 		goto out_put;
@@ -247,6 +238,45 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	return rc;
 }
 
+/**
+ * ecryptfs_dir_open
+ * @inode: inode speciying file to open
+ * @file: Structure to return filled in
+ *
+ * Opens the file specified by inode.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_dir_open(struct inode *inode, struct file *file)
+{
+	struct dentry *ecryptfs_dentry = file->f_path.dentry;
+	/* Private value of ecryptfs_dentry allocated in
+	 * ecryptfs_lookup() */
+	struct ecryptfs_file_info *file_info;
+	struct file *lower_file;
+
+	/* Released in ecryptfs_release or end of function if failure */
+	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
+	ecryptfs_set_file_private(file, file_info);
+	if (unlikely(!file_info)) {
+		ecryptfs_printk(KERN_ERR,
+				"Error attempting to allocate memory\n");
+		return -ENOMEM;
+	}
+	lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry),
+				 file->f_flags, current_cred());
+	if (IS_ERR(lower_file)) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the lower file for the dentry with name "
+			"[%pd]; rc = [%ld]\n", __func__,
+			ecryptfs_dentry, PTR_ERR(lower_file));
+		kmem_cache_free(ecryptfs_file_info_cache, file_info);
+		return PTR_ERR(lower_file);
+	}
+	ecryptfs_set_file_lower(file, lower_file);
+	return 0;
+}
+
 static int ecryptfs_flush(struct file *file, fl_owner_t td)
 {
 	struct file *lower_file = ecryptfs_file_to_lower(file);
@@ -267,6 +297,19 @@ static int ecryptfs_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int ecryptfs_dir_release(struct inode *inode, struct file *file)
+{
+	fput(ecryptfs_file_to_lower(file));
+	kmem_cache_free(ecryptfs_file_info_cache,
+			ecryptfs_file_to_private(file));
+	return 0;
+}
+
+static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence);
+}
+
 static int
 ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
@@ -346,20 +389,16 @@ const struct file_operations ecryptfs_dir_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.open = ecryptfs_open,
-	.flush = ecryptfs_flush,
-	.release = ecryptfs_release,
+	.open = ecryptfs_dir_open,
+	.release = ecryptfs_dir_release,
 	.fsync = ecryptfs_fsync,
-	.fasync = ecryptfs_fasync,
-	.splice_read = generic_file_splice_read,
-	.llseek = default_llseek,
+	.llseek = ecryptfs_dir_llseek,
 };
 
 const struct file_operations ecryptfs_main_fops = {
 	.llseek = generic_file_llseek,
 	.read_iter = ecryptfs_read_update_atime,
 	.write_iter = generic_file_write_iter,
-	.iterate = ecryptfs_readdir,
 	.unlocked_ioctl = ecryptfs_unlocked_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,

fs/isofs/rock.c

@@ -203,6 +203,8 @@ int get_rock_ridge_filename(struct iso_directory_record *de,
 	int retnamlen = 0;
 	int truncate = 0;
 	int ret = 0;
+	char *p;
+	int len;
 
 	if (!ISOFS_SB(inode->i_sb)->s_rock)
 		return 0;
@@ -267,12 +269,17 @@ int get_rock_ridge_filename(struct iso_directory_record *de,
 					rr->u.NM.flags);
 				break;
 			}
-			if ((strlen(retname) + rr->len - 5) >= 254) {
+			len = rr->len - 5;
+			if (retnamlen + len >= 254) {
 				truncate = 1;
 				break;
 			}
-			strncat(retname, rr->u.NM.name, rr->len - 5);
-			retnamlen += rr->len - 5;
+			p = memchr(rr->u.NM.name, '\0', len);
+			if (unlikely(p))
+				len = p - rr->u.NM.name;
+			memcpy(retname + retnamlen, rr->u.NM.name, len);
+			retnamlen += len;
+			retname[retnamlen] = '\0';
 			break;
 		case SIG('R', 'E'):
 			kfree(rs.buffer);

fs/namei.c

@@ -2266,6 +2266,33 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(vfs_path_lookup);
 
+/**
+ * lookup_hash - lookup single pathname component on already hashed name
+ * @name:	name and hash to lookup
+ * @base:	base directory to lookup from
+ *
+ * The name must have been verified and hashed (see lookup_one_len()).  Using
+ * this after just full_name_hash() is unsafe.
+ *
+ * This function also doesn't check for search permission on base directory.
+ *
+ * Use lookup_one_len_unlocked() instead, unless you really know what you are
+ * doing.
+ *
+ * Do not hold i_mutex; this helper takes i_mutex if necessary.
+ */
+struct dentry *lookup_hash(const struct qstr *name, struct dentry *base)
+{
+	struct dentry *ret;
+
+	ret = lookup_dcache(name, base, 0);
+	if (!ret)
+		ret = lookup_slow(name, base, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(lookup_hash);
+
 /**
  * lookup_one_len - filesystem helper to lookup single pathname component
  * @name:	pathname component to lookup
@@ -2337,7 +2364,6 @@ struct dentry *lookup_one_len_unlocked(const char *name,
 	struct qstr this;
 	unsigned int c;
 	int err;
-	struct dentry *ret;
 
 	this.name = name;
 	this.len = len;
@@ -2369,10 +2395,7 @@ struct dentry *lookup_one_len_unlocked(const char *name,
 	if (err)
 		return ERR_PTR(err);
 
-	ret = lookup_dcache(&this, base, 0);
-	if (!ret)
-		ret = lookup_slow(&this, base, 0);
-	return ret;
+	return lookup_hash(&this, base);
 }
 EXPORT_SYMBOL(lookup_one_len_unlocked);
 
@@ -2942,22 +2965,10 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 		dentry = lookup_real(dir, dentry, nd->flags);
 		if (IS_ERR(dentry))
 			return PTR_ERR(dentry);
-
-		if (create_error) {
-			int open_flag = op->open_flag;
-
+	}
+	if (create_error && !dentry->d_inode) {
 		error = create_error;
-			if ((open_flag & O_EXCL)) {
-				if (!dentry->d_inode)
 		goto out;
-			} else if (!dentry->d_inode) {
-				goto out;
-			} else if ((open_flag & O_TRUNC) &&
-				   d_is_reg(dentry)) {
-				goto out;
-			}
-			/* will fail later, go on to get the right error */
-		}
 	}
 looked_up:
 	path->dentry = dentry;
@@ -4213,7 +4224,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	bool new_is_dir = false;
 	unsigned max_links = new_dir->i_sb->s_max_links;
 
-	if (source == target)
+	/*
+	 * Check source == target.
+	 * On overlayfs need to look at underlying inodes.
+	 */
+	if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0))
 		return 0;
 
 	error = may_delete(old_dir, old_dentry, is_dir);

fs/open.c

@@ -840,16 +840,12 @@ EXPORT_SYMBOL(file_path);
 int vfs_open(const struct path *path, struct file *file,
 	     const struct cred *cred)
 {
-	struct dentry *dentry = path->dentry;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = vfs_select_inode(path->dentry, file->f_flags);
 
-	file->f_path = *path;
-	if (dentry->d_flags & DCACHE_OP_SELECT_INODE) {
-		inode = dentry->d_op->d_select_inode(dentry, file->f_flags);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
-	}
 
+	file->f_path = *path;
 	return do_dentry_open(file, inode, NULL, cred);
 }
 

fs/overlayfs/super.c

@@ -411,9 +411,7 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir,
 {
 	struct dentry *dentry;
 
-	inode_lock(dir->d_inode);
-	dentry = lookup_one_len(name->name, dir, name->len);
-	inode_unlock(dir->d_inode);
+	dentry = lookup_hash(name, dir);
 
 	if (IS_ERR(dentry)) {
 		if (PTR_ERR(dentry) == -ENOENT)

fs/splice.c

@@ -1143,6 +1143,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(ret < 0))
 		return ret;
 
+	if (unlikely(len > MAX_RW_COUNT))
+		len = MAX_RW_COUNT;
+
 	if (in->f_op->splice_read)
 		splice_read = in->f_op->splice_read;
 	else

include/linux/dcache.h

@@ -565,4 +565,16 @@ static inline struct dentry *d_real(struct dentry *dentry)
 		return dentry;
 }
 
+static inline struct inode *vfs_select_inode(struct dentry *dentry,
+					     unsigned open_flags)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (inode && unlikely(dentry->d_flags & DCACHE_OP_SELECT_INODE))
+		inode = dentry->d_op->d_select_inode(dentry, open_flags);
+
+	return inode;
+}
+
+
 #endif	/* __LINUX_DCACHE_H */

include/linux/namei.h

@@ -79,6 +79,8 @@ extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int);
 
 extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
 extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int);
+struct qstr;
+extern struct dentry *lookup_hash(const struct qstr *, struct dentry *);
 
 extern int follow_down_one(struct path *);
 extern int follow_down(struct path *);

include/linux/uio.h

@@ -87,6 +87,7 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
 size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
+unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
 void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec,

lib/iov_iter.c

@@ -569,6 +569,25 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 }
 EXPORT_SYMBOL(iov_iter_alignment);
 
+unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
+{
+        unsigned long res = 0;
+	size_t size = i->count;
+	if (!size)
+		return 0;
+
+	iterate_all_kinds(i, size, v,
+		(res |= (!res ? 0 : (unsigned long)v.iov_base) |
+			(size != v.iov_len ? size : 0), 0),
+		(res |= (!res ? 0 : (unsigned long)v.bv_offset) |
+			(size != v.bv_len ? size : 0)),
+		(res |= (!res ? 0 : (unsigned long)v.iov_base) |
+			(size != v.iov_len ? size : 0))
+		);
+		return res;
+}
+EXPORT_SYMBOL(iov_iter_gap_alignment);
+
 ssize_t iov_iter_get_pages(struct iov_iter *i,
 		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)