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

Pull vfs pile two from Al Viro:

 - orangefs fix

 - series of fs/namei.c cleanups from me

 - VFS stuff coming from overlayfs tree

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  orangefs: Use RCU for destroy_inode
  vfs: use helper for calling f_op->fsync()
  mm: use helper for calling f_op->mmap()
  vfs: use helpers for calling f_op->{read,write}_iter()
  vfs: pass type instead of fn to do_{loop,iter}_readv_writev()
  vfs: extract common parts of {compat_,}do_readv_writev()
  vfs: wrap write f_ops with file_{start,end}_write()
  vfs: deny copy_file_range() for non regular files
  vfs: deny fallocate() on directory
  vfs: create vfs helper vfs_tmpfile()
  namei.c: split unlazy_walk()
  namei.c: fold the check for DCACHE_OP_REVALIDATE into d_revalidate()
  lookup_fast(): clean up the logics around the fallback to non-rcu mode
  namei: fold unlazy_link() into its sole caller

drivers/block/loop.c

@@ -501,9 +501,9 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	cmd->iocb.ki_flags = IOCB_DIRECT;
 
 	if (rw == WRITE)
-		ret = file->f_op->write_iter(&cmd->iocb, &iter);
+		ret = call_write_iter(file, &cmd->iocb, &iter);
 	else
-		ret = file->f_op->read_iter(&cmd->iocb, &iter);
+		ret = call_read_iter(file, &cmd->iocb, &iter);
 
 	if (ret != -EIOCBQUEUED)
 		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);

drivers/gpu/drm/i915/i915_gem_dmabuf.c

@@ -141,7 +141,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 	if (!obj->base.filp)
 		return -ENODEV;
 
-	ret = obj->base.filp->f_op->mmap(obj->base.filp, vma);
+	ret = call_mmap(obj->base.filp, vma);
 	if (ret)
 		return ret;
 

drivers/gpu/drm/vgem/vgem_drv.c

@@ -288,7 +288,7 @@ static int vgem_prime_mmap(struct drm_gem_object *obj,
 	if (!obj->filp)
 		return -ENODEV;
 
-	ret = obj->filp->f_op->mmap(obj->filp, vma);
+	ret = call_mmap(obj->filp, vma);
 	if (ret)
 		return ret;
 

fs/aio.c

@@ -1495,7 +1495,7 @@ static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 		return ret;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
-		ret = aio_ret(req, file->f_op->read_iter(req, &iter));
+		ret = aio_ret(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
 	return ret;
 }
@@ -1520,7 +1520,7 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 	if (!ret) {
 		req->ki_flags |= IOCB_WRITE;
 		file_start_write(file);
-		ret = aio_ret(req, file->f_op->write_iter(req, &iter));
+		ret = aio_ret(req, call_write_iter(file, req, &iter));
 		/*
 		 * We release freeze protection in aio_complete().  Fool lockdep
 		 * by telling it the lock got released so that it doesn't

fs/coda/file.c

@@ -96,7 +96,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	cfi->cfi_mapcount++;
 	spin_unlock(&cii->c_lock);
 
-	return host_file->f_op->mmap(host_file, vma);
+	return call_mmap(host_file, vma);
 }
 
 int coda_open(struct inode *coda_inode, struct file *coda_file)

fs/namei.c

@@ -672,52 +672,83 @@ static bool legitimize_links(struct nameidata *nd)
 /**
  * unlazy_walk - try to switch to ref-walk mode.
  * @nd: nameidata pathwalk data
- * @dentry: child of nd->path.dentry or NULL
- * @seq: seq number to check dentry against
  * Returns: 0 on success, -ECHILD on failure
  *
- * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
- * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
- * @nd or NULL.  Must be called from rcu-walk context.
+ * unlazy_walk attempts to legitimize the current nd->path and nd->root
+ * for ref-walk mode.
+ * Must be called from rcu-walk context.
  * Nothing should touch nameidata between unlazy_walk() failure and
  * terminate_walk().
  */
-static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+static int unlazy_walk(struct nameidata *nd)
 {
 	struct dentry *parent = nd->path.dentry;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
+	nd->flags &= ~LOOKUP_RCU;
+	if (unlikely(!legitimize_links(nd)))
+		goto out2;
+	if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
+		goto out1;
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
+			goto out;
+	}
+	rcu_read_unlock();
+	BUG_ON(nd->inode != parent->d_inode);
+	return 0;
+
+out2:
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
+out1:
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
+out:
+	rcu_read_unlock();
+	return -ECHILD;
+}
+
+/**
+ * unlazy_child - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * @dentry: child of nd->path.dentry
+ * @seq: seq number to check dentry against
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry
+ * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
+ * @nd.  Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_child() failure and
+ * terminate_walk().
+ */
+static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+{
+	BUG_ON(!(nd->flags & LOOKUP_RCU));
+
 	nd->flags &= ~LOOKUP_RCU;
 	if (unlikely(!legitimize_links(nd)))
 		goto out2;
 	if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
 		goto out2;
-	if (unlikely(!lockref_get_not_dead(&parent->d_lockref)))
+	if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
 		goto out1;
 
 	/*
-	 * For a negative lookup, the lookup sequence point is the parents
-	 * sequence point, and it only needs to revalidate the parent dentry.
-	 *
-	 * For a positive lookup, we need to move both the parent and the
-	 * dentry from the RCU domain to be properly refcounted. And the
-	 * sequence number in the dentry validates *both* dentry counters,
-	 * since we checked the sequence number of the parent after we got
-	 * the child sequence number. So we know the parent must still
-	 * be valid if the child sequence number is still valid.
+	 * We need to move both the parent and the dentry from the RCU domain
+	 * to be properly refcounted. And the sequence number in the dentry
+	 * validates *both* dentry counters, since we checked the sequence
+	 * number of the parent after we got the child sequence number. So we
+	 * know the parent must still be valid if the child sequence number is
 	 */
-	if (!dentry) {
-		if (read_seqcount_retry(&parent->d_seq, nd->seq))
-			goto out;
-		BUG_ON(nd->inode != parent->d_inode);
-	} else {
-		if (!lockref_get_not_dead(&dentry->d_lockref))
-			goto out;
-		if (read_seqcount_retry(&dentry->d_seq, seq))
-			goto drop_dentry;
+	if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
+		goto out;
+	if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) {
+		rcu_read_unlock();
+		dput(dentry);
+		goto drop_root_mnt;
 	}
-
 	/*
 	 * Sequence counts matched. Now make sure that the root is
 	 * still valid and get it if required.
@@ -733,10 +764,6 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
 	rcu_read_unlock();
 	return 0;
 
-drop_dentry:
-	rcu_read_unlock();
-	dput(dentry);
-	goto drop_root_mnt;
 out2:
 	nd->path.mnt = NULL;
 out1:
@@ -749,27 +776,12 @@ drop_root_mnt:
 	return -ECHILD;
 }
 
-static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq)
-{
-	if (unlikely(!legitimize_path(nd, link, seq))) {
-		drop_links(nd);
-		nd->depth = 0;
-		nd->flags &= ~LOOKUP_RCU;
-		nd->path.mnt = NULL;
-		nd->path.dentry = NULL;
-		if (!(nd->flags & LOOKUP_ROOT))
-			nd->root.mnt = NULL;
-		rcu_read_unlock();
-	} else if (likely(unlazy_walk(nd, NULL, 0)) == 0) {
-		return 0;
-	}
-	path_put(link);
-	return -ECHILD;
-}
-
 static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	return dentry->d_op->d_revalidate(dentry, flags);
+	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+		return dentry->d_op->d_revalidate(dentry, flags);
+	else
+		return 1;
 }
 
 /**
@@ -790,7 +802,7 @@ static int complete_walk(struct nameidata *nd)
 	if (nd->flags & LOOKUP_RCU) {
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
-		if (unlikely(unlazy_walk(nd, NULL, 0)))
+		if (unlikely(unlazy_walk(nd)))
 			return -ECHILD;
 	}
 
@@ -1016,7 +1028,7 @@ const char *get_link(struct nameidata *nd)
 		touch_atime(&last->link);
 		cond_resched();
 	} else if (atime_needs_update_rcu(&last->link, inode)) {
-		if (unlikely(unlazy_walk(nd, NULL, 0)))
+		if (unlikely(unlazy_walk(nd)))
 			return ERR_PTR(-ECHILD);
 		touch_atime(&last->link);
 	}
@@ -1035,7 +1047,7 @@ const char *get_link(struct nameidata *nd)
 		if (nd->flags & LOOKUP_RCU) {
 			res = get(NULL, inode, &last->done);
 			if (res == ERR_PTR(-ECHILD)) {
-				if (unlikely(unlazy_walk(nd, NULL, 0)))
+				if (unlikely(unlazy_walk(nd)))
 					return ERR_PTR(-ECHILD);
 				res = get(dentry, inode, &last->done);
 			}
@@ -1469,19 +1481,14 @@ static struct dentry *lookup_dcache(const struct qstr *name,
 				    struct dentry *dir,
 				    unsigned int flags)
 {
-	struct dentry *dentry;
-	int error;
-
-	dentry = d_lookup(dir, name);
+	struct dentry *dentry = d_lookup(dir, name);
 	if (dentry) {
-		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
-			error = d_revalidate(dentry, flags);
-			if (unlikely(error <= 0)) {
-				if (!error)
-					d_invalidate(dentry);
-				dput(dentry);
-				return ERR_PTR(error);
-			}
+		int error = d_revalidate(dentry, flags);
+		if (unlikely(error <= 0)) {
+			if (!error)
+				d_invalidate(dentry);
+			dput(dentry);
+			return ERR_PTR(error);
 		}
 	}
 	return dentry;
@@ -1546,7 +1553,7 @@ static int lookup_fast(struct nameidata *nd,
 		bool negative;
 		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
 		if (unlikely(!dentry)) {
-			if (unlazy_walk(nd, NULL, 0))
+			if (unlazy_walk(nd))
 				return -ECHILD;
 			return 0;
 		}
@@ -1571,14 +1578,8 @@ static int lookup_fast(struct nameidata *nd,
 			return -ECHILD;
 
 		*seqp = seq;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			status = d_revalidate(dentry, nd->flags);
-		if (unlikely(status <= 0)) {
-			if (unlazy_walk(nd, dentry, seq))
-				return -ECHILD;
-			if (status == -ECHILD)
-				status = d_revalidate(dentry, nd->flags);
-		} else {
+		status = d_revalidate(dentry, nd->flags);
+		if (likely(status > 0)) {
 			/*
 			 * Note: do negative dentry check after revalidation in
 			 * case that drops it.
@@ -1589,15 +1590,17 @@ static int lookup_fast(struct nameidata *nd,
 			path->dentry = dentry;
 			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
 				return 1;
-			if (unlazy_walk(nd, dentry, seq))
-				return -ECHILD;
 		}
+		if (unlazy_child(nd, dentry, seq))
+			return -ECHILD;
+		if (unlikely(status == -ECHILD))
+			/* we'd been told to redo it in non-rcu mode */
+			status = d_revalidate(dentry, nd->flags);
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
 		if (unlikely(!dentry))
 			return 0;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			status = d_revalidate(dentry, nd->flags);
+		status = d_revalidate(dentry, nd->flags);
 	}
 	if (unlikely(status <= 0)) {
 		if (!status)
@@ -1636,8 +1639,7 @@ again:
 	if (IS_ERR(dentry))
 		goto out;
 	if (unlikely(!d_in_lookup(dentry))) {
-		if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
-		    !(flags & LOOKUP_NO_REVAL)) {
+		if (!(flags & LOOKUP_NO_REVAL)) {
 			int error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
 				if (!error) {
@@ -1668,7 +1670,7 @@ static inline int may_lookup(struct nameidata *nd)
 		int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
 		if (err != -ECHILD)
 			return err;
-		if (unlazy_walk(nd, NULL, 0))
+		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
 	return inode_permission(nd->inode, MAY_EXEC);
@@ -1703,9 +1705,17 @@ static int pick_link(struct nameidata *nd, struct path *link,
 	error = nd_alloc_stack(nd);
 	if (unlikely(error)) {
 		if (error == -ECHILD) {
-			if (unlikely(unlazy_link(nd, link, seq)))
-				return -ECHILD;
-			error = nd_alloc_stack(nd);
+			if (unlikely(!legitimize_path(nd, link, seq))) {
+				drop_links(nd);
+				nd->depth = 0;
+				nd->flags &= ~LOOKUP_RCU;
+				nd->path.mnt = NULL;
+				nd->path.dentry = NULL;
+				if (!(nd->flags & LOOKUP_ROOT))
+					nd->root.mnt = NULL;
+				rcu_read_unlock();
+			} else if (likely(unlazy_walk(nd)) == 0)
+				error = nd_alloc_stack(nd);
 		}
 		if (error) {
 			path_put(link);
@@ -2122,7 +2132,7 @@ OK:
 		}
 		if (unlikely(!d_can_lookup(nd->path.dentry))) {
 			if (nd->flags & LOOKUP_RCU) {
-				if (unlazy_walk(nd, NULL, 0))
+				if (unlazy_walk(nd))
 					return -ECHILD;
 			}
 			return -ENOTDIR;
@@ -2579,7 +2589,7 @@ mountpoint_last(struct nameidata *nd)
 
 	/* If we're in rcuwalk, drop out of it to handle last component */
 	if (nd->flags & LOOKUP_RCU) {
-		if (unlazy_walk(nd, NULL, 0))
+		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
 
@@ -3072,9 +3082,6 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 		if (d_in_lookup(dentry))
 			break;
 
-		if (!(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			break;
-
 		error = d_revalidate(dentry, nd->flags);
 		if (likely(error > 0))
 			break;
@@ -3356,13 +3363,50 @@ out:
 	return error;
 }
 
+struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+{
+	static const struct qstr name = QSTR_INIT("/", 1);
+	struct dentry *child = NULL;
+	struct inode *dir = dentry->d_inode;
+	struct inode *inode;
+	int error;
+
+	/* we want directory to be writable */
+	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	if (error)
+		goto out_err;
+	error = -EOPNOTSUPP;
+	if (!dir->i_op->tmpfile)
+		goto out_err;
+	error = -ENOMEM;
+	child = d_alloc(dentry, &name);
+	if (unlikely(!child))
+		goto out_err;
+	error = dir->i_op->tmpfile(dir, child, mode);
+	if (error)
+		goto out_err;
+	error = -ENOENT;
+	inode = child->d_inode;
+	if (unlikely(!inode))
+		goto out_err;
+	if (!(open_flag & O_EXCL)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_LINKABLE;
+		spin_unlock(&inode->i_lock);
+	}
+	return child;
+
+out_err:
+	dput(child);
+	return ERR_PTR(error);
+}
+EXPORT_SYMBOL(vfs_tmpfile);
+
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
 		struct file *file, int *opened)
 {
-	static const struct qstr name = QSTR_INIT("/", 1);
 	struct dentry *child;
-	struct inode *dir;
 	struct path path;
 	int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
 	if (unlikely(error))
@@ -3370,25 +3414,12 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	error = mnt_want_write(path.mnt);
 	if (unlikely(error))
 		goto out;
-	dir = path.dentry->d_inode;
-	/* we want directory to be writable */
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
-	if (error)
+	child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+	error = PTR_ERR(child);
+	if (unlikely(IS_ERR(child)))
 		goto out2;
-	if (!dir->i_op->tmpfile) {
-		error = -EOPNOTSUPP;
-		goto out2;
-	}
-	child = d_alloc(path.dentry, &name);
-	if (unlikely(!child)) {
-		error = -ENOMEM;
-		goto out2;
-	}
 	dput(path.dentry);
 	path.dentry = child;
-	error = dir->i_op->tmpfile(dir, child, op->mode);
-	if (error)
-		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
 	error = may_open(&path, 0, op->open_flag);
@@ -3399,14 +3430,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	error = open_check_o_direct(file);
-	if (error) {
+	if (error)
 		fput(file);
-	} else if (!(op->open_flag & O_EXCL)) {
-		struct inode *inode = file_inode(file);
-		spin_lock(&inode->i_lock);
-		inode->i_state |= I_LINKABLE;
-		spin_unlock(&inode->i_lock);
-	}
 out2:
 	mnt_drop_write(path.mnt);
 out:

fs/open.c

@@ -301,12 +301,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (S_ISFIFO(inode->i_mode))
 		return -ESPIPE;
 
-	/*
-	 * Let individual file system decide if it supports preallocation
-	 * for directories or not.
-	 */
-	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) &&
-	    !S_ISBLK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
 		return -ENODEV;
 
 	/* Check for wrap through zero too */
@@ -316,7 +314,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	sb_start_write(inode->i_sb);
+	file_start_write(file);
 	ret = file->f_op->fallocate(file, mode, offset, len);
 
 	/*
@@ -329,7 +327,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret == 0)
 		fsnotify_modify(file);
 
-	sb_end_write(inode->i_sb);
+	file_end_write(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vfs_fallocate);

fs/orangefs/super.c

@@ -115,6 +115,13 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb)
 	return &orangefs_inode->vfs_inode;
 }
 
+static void orangefs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+}
+
 static void orangefs_destroy_inode(struct inode *inode)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
@@ -123,7 +130,7 @@ static void orangefs_destroy_inode(struct inode *inode)
 			"%s: deallocated %p destroying inode %pU\n",
 			__func__, orangefs_inode, get_khandle_from_ino(inode));
 
-	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+	call_rcu(&inode->i_rcu, orangefs_i_callback);
 }
 
 /*

fs/read_write.c

@@ -23,9 +23,6 @@
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
-typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
-typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *);
-
 const struct file_operations generic_ro_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
@@ -370,7 +367,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
 	kiocb.ki_pos = *ppos;
 
 	iter->type |= READ;
-	ret = file->f_op->read_iter(&kiocb, iter);
+	ret = call_read_iter(file, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -390,7 +387,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
 	kiocb.ki_pos = *ppos;
 
 	iter->type |= WRITE;
-	ret = file->f_op->write_iter(&kiocb, iter);
+	ret = call_write_iter(file, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -439,7 +436,7 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	kiocb.ki_pos = *ppos;
 	iov_iter_init(&iter, READ, &iov, 1, len);
 
-	ret = filp->f_op->read_iter(&kiocb, &iter);
+	ret = call_read_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
@@ -496,7 +493,7 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	kiocb.ki_pos = *ppos;
 	iov_iter_init(&iter, WRITE, &iov, 1, len);
 
-	ret = filp->f_op->write_iter(&kiocb, &iter);
+	ret = call_write_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -675,7 +672,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 EXPORT_SYMBOL(iov_shorten);
 
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, iter_fn_t fn, int flags)
+		loff_t *ppos, int type, int flags)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
@@ -692,7 +689,10 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 		kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
 	kiocb.ki_pos = *ppos;
 
-	ret = fn(&kiocb, iter);
+	if (type == READ)
+		ret = call_read_iter(filp, &kiocb, iter);
+	else
+		ret = call_write_iter(filp, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
@@ -700,7 +700,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 
 /* Do it by hand, with file-ops */
 static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, io_fn_t fn, int flags)
+		loff_t *ppos, int type, int flags)
 {
 	ssize_t ret = 0;
 
@@ -711,7 +711,13 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
 
-		nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
+		if (type == READ) {
+			nr = filp->f_op->read(filp, iovec.iov_base,
+					      iovec.iov_len, ppos);
+		} else {
+			nr = filp->f_op->write(filp, iovec.iov_base,
+					       iovec.iov_len, ppos);
+		}
 
 		if (nr < 0) {
 			if (!ret)
@@ -834,50 +840,32 @@ out:
 	return ret;
 }
 
-static ssize_t do_readv_writev(int type, struct file *file,
-			       const struct iovec __user * uvector,
-			       unsigned long nr_segs, loff_t *pos,
-			       int flags)
+static ssize_t __do_readv_writev(int type, struct file *file,
+				 struct iov_iter *iter, loff_t *pos, int flags)
 {
 	size_t tot_len;
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-	io_fn_t fn;
-	iter_fn_t iter_fn;
-
-	ret = import_iovec(type, uvector, nr_segs,
-			   ARRAY_SIZE(iovstack), &iov, &iter);
-	if (ret < 0)
-		return ret;
+	ssize_t ret = 0;
 
-	tot_len = iov_iter_count(&iter);
+	tot_len = iov_iter_count(iter);
 	if (!tot_len)
 		goto out;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
 
-	if (type == READ) {
-		fn = file->f_op->read;
-		iter_fn = file->f_op->read_iter;
-	} else {
-		fn = (io_fn_t)file->f_op->write;
-		iter_fn = file->f_op->write_iter;
+	if (type != READ)
 		file_start_write(file);
-	}
 
-	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
+	if ((type == READ && file->f_op->read_iter) ||
+	    (type == WRITE && file->f_op->write_iter))
+		ret = do_iter_readv_writev(file, iter, pos, type, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
+		ret = do_loop_readv_writev(file, iter, pos, type, flags);
 
 	if (type != READ)
 		file_end_write(file);
 
 out:
-	kfree(iov);
 	if ((ret + (type == READ)) > 0) {
 		if (type == READ)
 			fsnotify_access(file);
@@ -887,6 +875,27 @@ out:
 	return ret;
 }
 
+static ssize_t do_readv_writev(int type, struct file *file,
+			       const struct iovec __user *uvector,
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = import_iovec(type, uvector, nr_segs,
+			   ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		return ret;
+
+	ret = __do_readv_writev(type, file, &iter, pos, flags);
+	kfree(iov);
+
+	return ret;
+}
+
 ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, int flags)
 {
@@ -1064,51 +1073,19 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 			       unsigned long nr_segs, loff_t *pos,
 			       int flags)
 {
-	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
 	ssize_t ret;
-	io_fn_t fn;
-	iter_fn_t iter_fn;
 
 	ret = compat_import_iovec(type, uvector, nr_segs,
 				  UIO_FASTIOV, &iov, &iter);
 	if (ret < 0)
 		return ret;
 
-	tot_len = iov_iter_count(&iter);
-	if (!tot_len)
-		goto out;
-	ret = rw_verify_area(type, file, pos, tot_len);
-	if (ret < 0)
-		goto out;
-
-	if (type == READ) {
-		fn = file->f_op->read;
-		iter_fn = file->f_op->read_iter;
-	} else {
-		fn = (io_fn_t)file->f_op->write;
-		iter_fn = file->f_op->write_iter;
-		file_start_write(file);
-	}
-
-	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
-	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
-
-	if (type != READ)
-		file_end_write(file);
-
-out:
+	ret = __do_readv_writev(type, file, &iter, pos, flags);
 	kfree(iov);
-	if ((ret + (type == READ)) > 0) {
-		if (type == READ)
-			fsnotify_access(file);
-		else
-			fsnotify_modify(file);
-	}
+
 	return ret;
 }
 
@@ -1518,6 +1495,11 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (flags != 0)
 		return -EINVAL;
 
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
 	ret = rw_verify_area(READ, file_in, &pos_in, len);
 	if (unlikely(ret))
 		return ret;
@@ -1538,7 +1520,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (len == 0)
 		return 0;
 
-	sb_start_write(inode_out->i_sb);
+	file_start_write(file_out);
 
 	/*
 	 * Try cloning first, this is supported by more file systems, and
@@ -1574,7 +1556,7 @@ done:
 	inc_syscr(current);
 	inc_syscw(current);
 
-	sb_end_write(inode_out->i_sb);
+	file_end_write(file_out);
 
 	return ret;
 }

fs/splice.c

@@ -307,7 +307,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 	idx = to.idx;
 	init_sync_kiocb(&kiocb, in);
 	kiocb.ki_pos = *ppos;
-	ret = in->f_op->read_iter(&kiocb, &to);
+	ret = call_read_iter(in, &kiocb, &to);
 	if (ret > 0) {
 		*ppos = kiocb.ki_pos;
 		file_accessed(in);

fs/sync.c

@@ -192,7 +192,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync)
 		spin_unlock(&inode->i_lock);
 		mark_inode_dirty_sync(inode);
 	}
-	return file->f_op->fsync(file, start, end, datasync);
+	return call_fsync(file, start, end, datasync);
 }
 EXPORT_SYMBOL(vfs_fsync_range);
 

include/linux/fs.h

@@ -1567,6 +1567,9 @@ extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 extern int vfs_whiteout(struct inode *, struct dentry *);
 
+extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
+				  int open_flag);
+
 /*
  * VFS file helper functions.
  */
@@ -1718,6 +1721,29 @@ struct inode_operations {
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 } ____cacheline_aligned;
 
+static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
+				     struct iov_iter *iter)
+{
+	return file->f_op->read_iter(kio, iter);
+}
+
+static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
+				      struct iov_iter *iter)
+{
+	return file->f_op->write_iter(kio, iter);
+}
+
+static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	return file->f_op->mmap(file, vma);
+}
+
+static inline int call_fsync(struct file *file, loff_t start, loff_t end,
+			     int datasync)
+{
+	return file->f_op->fsync(file, start, end, datasync);
+}
+
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
@@ -1744,19 +1770,6 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
 
-static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
-				      struct file *file_out, loff_t pos_out,
-				      u64 len)
-{
-	int ret;
-
-	sb_start_write(file_inode(file_out)->i_sb);
-	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
-	sb_end_write(file_inode(file_out)->i_sb);
-
-	return ret;
-}
-
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
@@ -2568,6 +2581,19 @@ static inline void file_end_write(struct file *file)
 	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 }
 
+static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
+				      struct file *file_out, loff_t pos_out,
+				      u64 len)
+{
+	int ret;
+
+	file_start_write(file_out);
+	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+	file_end_write(file_out);
+
+	return ret;
+}
+
 /*
  * get_write_access() gets write permission for a file.
  * put_write_access() releases this write permission.

ipc/shm.c

@@ -423,7 +423,7 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	if (ret)
 		return ret;
 
-	ret = sfd->file->f_op->mmap(sfd->file, vma);
+	ret = call_mmap(sfd->file, vma);
 	if (ret) {
 		shm_close(vma);
 		return ret;
@@ -452,7 +452,7 @@ static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	if (!sfd->file->f_op->fsync)
 		return -EINVAL;
-	return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
+	return call_fsync(sfd->file, start, end, datasync);
 }
 
 static long shm_fallocate(struct file *file, int mode, loff_t offset,

mm/mmap.c

@@ -1672,7 +1672,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		 * new file must not have been exposed to user-space, yet.
 		 */
 		vma->vm_file = get_file(file);
-		error = file->f_op->mmap(file, vma);
+		error = call_mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
 

mm/nommu.c

@@ -1084,7 +1084,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma)
 {
 	int ret;
 
-	ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+	ret = call_mmap(vma->vm_file, vma);
 	if (ret == 0) {
 		vma->vm_region->vm_top = vma->vm_region->vm_end;
 		return 0;
@@ -1115,7 +1115,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 	 * - VM_MAYSHARE will be set if it may attempt to share
 	 */
 	if (capabilities & NOMMU_MAP_DIRECT) {
-		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+		ret = call_mmap(vma->vm_file, vma);
 		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
 			BUG_ON(!(vma->vm_flags & VM_MAYSHARE));