Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull the big VFS changes from Al Viro:
 "This one is *big* and changes quite a few things around VFS.  What's in there:

   - the first of two really major architecture changes - death to open
     intents.

     The former is finally there; it was very long in making, but with
     Miklos getting through really hard and messy final push in
     fs/namei.c, we finally have it.  Unlike his variant, this one
     doesn't introduce struct opendata; what we have instead is
     ->atomic_open() taking preallocated struct file * and passing
     everything via its fields.

     Instead of returning struct file *, it returns -E...  on error, 0
     on success and 1 in "deal with it yourself" case (e.g.  symlink
     found on server, etc.).

     See comments before fs/namei.c:atomic_open().  That made a lot of
     goodies finally possible and quite a few are in that pile:
     ->lookup(), ->d_revalidate() and ->create() do not get struct
     nameidata * anymore; ->lookup() and ->d_revalidate() get lookup
     flags instead, ->create() gets "do we want it exclusive" flag.

     With the introduction of new helper (kern_path_locked()) we are rid
     of all struct nameidata instances outside of fs/namei.c; it's still
     visible in namei.h, but not for long.  Come the next cycle,
     declaration will move either to fs/internal.h or to fs/namei.c
     itself.  [me, miklos, hch]

   - The second major change: behaviour of final fput().  Now we have
     __fput() done without any locks held by caller *and* not from deep
     in call stack.

     That obviously lifts a lot of constraints on the locking in there.
     Moreover, it's legal now to call fput() from atomic contexts (which
     has immediately simplified life for aio.c).  We also don't need
     anti-recursion logics in __scm_destroy() anymore.

     There is a price, though - the damn thing has become partially
     asynchronous.  For fput() from normal process we are guaranteed
     that pending __fput() will be done before the caller returns to
     userland, exits or gets stopped for ptrace.

     For kernel threads and atomic contexts it's done via
     schedule_work(), so theoretically we might need a way to make sure
     it's finished; so far only one such place had been found, but there
     might be more.

     There's flush_delayed_fput() (do all pending __fput()) and there's
     __fput_sync() (fput() analog doing __fput() immediately).  I hope
     we won't need them often; see warnings in fs/file_table.c for
     details.  [me, based on task_work series from Oleg merged last
     cycle]

   - sync series from Jan

   - large part of "death to sync_supers()" work from Artem; the only
     bits missing here are exofs and ext4 ones.  As far as I understand,
     those are going via the exofs and ext4 trees resp.; once they are
     in, we can put ->write_super() to the rest, along with the thread
     calling it.

   - preparatory bits from unionmount series (from dhowells).

   - assorted cleanups and fixes all over the place, as usual.

  This is not the last pile for this cycle; there's at least jlayton's
  ESTALE work and fsfreeze series (the latter - in dire need of fixes,
  so I'm not sure it'll make the cut this cycle).  I'll probably throw
  symlink/hardlink restrictions stuff from Kees into the next pile, too.
  Plus there's a lot of misc patches I hadn't thrown into that one -
  it's large enough as it is..."

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (127 commits)
  ext4: switch EXT4_IOC_RESIZE_FS to mnt_want_write_file()
  btrfs: switch btrfs_ioctl_balance() to mnt_want_write_file()
  switch dentry_open() to struct path, make it grab references itself
  spufs: shift dget/mntget towards dentry_open()
  zoran: don't bother with struct file * in zoran_map
  ecryptfs: don't reinvent the wheels, please - use struct completion
  don't expose I_NEW inodes via dentry->d_inode
  tidy up namei.c a bit
  unobfuscate follow_up() a bit
  ext3: pass custom EOF to generic_file_llseek_size()
  ext4: use core vfs llseek code for dir seeks
  vfs: allow custom EOF in generic_file_llseek code
  vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes
  vfs: Remove unnecessary flushing of block devices
  vfs: Make sys_sync writeout also block device inodes
  vfs: Create function for iterating over block devices
  vfs: Reorder operations during sys_sync
  quota: Move quota syncing to ->sync_fs method
  quota: Split dquot_quota_sync() to writeback and cache flushing part
  vfs: Move noop_backing_dev_info check from sync into writeback
  ...

1 files changed, 65 insertions, 146 deletions

diff --git a/fs/open.c b/fs/open.c
index 1540632d8387..1e914b397e12 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -537,25 +537,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	return error;
 }
 
-SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
-{
-	struct path path;
-	int error;
-
-	error = user_path(filename, &path);
-	if (error)
-		goto out;
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_release;
-	error = chown_common(&path, user, group);
-	mnt_drop_write(path.mnt);
-out_release:
-	path_put(&path);
-out:
-	return error;
-}
-
 SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
 		gid_t, group, int, flag)
 {
@@ -583,23 +564,15 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
+SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
 {
-	struct path path;
-	int error;
+	return sys_fchownat(AT_FDCWD, filename, user, group, 0);
+}
 
-	error = user_lpath(filename, &path);
-	if (error)
-		goto out;
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_release;
-	error = chown_common(&path, user, group);
-	mnt_drop_write(path.mnt);
-out_release:
-	path_put(&path);
-out:
-	return error;
+SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
+{
+	return sys_fchownat(AT_FDCWD, filename, user, group,
+			    AT_SYMLINK_NOFOLLOW);
 }
 
 SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
@@ -667,10 +640,9 @@ int open_check_o_direct(struct file *f)
 	return 0;
 }
 
-static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
-				   struct file *f,
-				   int (*open)(struct inode *, struct file *),
-				   const struct cred *cred)
+static int do_dentry_open(struct file *f,
+			  int (*open)(struct inode *, struct file *),
+			  const struct cred *cred)
 {
 	static const struct file_operations empty_fops = {};
 	struct inode *inode;
@@ -682,9 +654,9 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	if (unlikely(f->f_flags & O_PATH))
 		f->f_mode = FMODE_PATH;
 
-	inode = dentry->d_inode;
+	inode = f->f_path.dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
-		error = __get_file_write_access(inode, mnt);
+		error = __get_file_write_access(inode, f->f_path.mnt);
 		if (error)
 			goto cleanup_file;
 		if (!special_file(inode->i_mode))
@@ -692,14 +664,12 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	}
 
 	f->f_mapping = inode->i_mapping;
-	f->f_path.dentry = dentry;
-	f->f_path.mnt = mnt;
 	f->f_pos = 0;
 	file_sb_list_add(f, inode->i_sb);
 
 	if (unlikely(f->f_mode & FMODE_PATH)) {
 		f->f_op = &empty_fops;
-		return f;
+		return 0;
 	}
 
 	f->f_op = fops_get(inode->i_fop);
@@ -726,10 +696,11 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
-	return f;
+	return 0;
 
 cleanup_all:
 	fops_put(f->f_op);
+	file_sb_list_del(f);
 	if (f->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
 		if (!special_file(inode->i_mode)) {
@@ -740,124 +711,62 @@ cleanup_all:
 			 * here, so just reset the state.
 			 */
 			file_reset_write(f);
-			mnt_drop_write(mnt);
+			mnt_drop_write(f->f_path.mnt);
 		}
 	}
-	file_sb_list_del(f);
-	f->f_path.dentry = NULL;
-	f->f_path.mnt = NULL;
 cleanup_file:
-	dput(dentry);
-	mntput(mnt);
-	return ERR_PTR(error);
-}
-
-static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
-				struct file *f,
-				int (*open)(struct inode *, struct file *),
-				const struct cred *cred)
-{
-	struct file *res = do_dentry_open(dentry, mnt, f, open, cred);
-	if (!IS_ERR(res)) {
-		int error = open_check_o_direct(f);
-		if (error) {
-			fput(res);
-			res = ERR_PTR(error);
-		}
-	} else {
-		put_filp(f);
-	}
-	return res;
+	path_put(&f->f_path);
+	f->f_path.mnt = NULL;
+	f->f_path.dentry = NULL;
+	return error;
 }
 
 /**
- * lookup_instantiate_filp - instantiates the open intent filp
- * @nd: pointer to nameidata
+ * finish_open - finish opening a file
+ * @od: opaque open data
  * @dentry: pointer to dentry
  * @open: open callback
  *
- * Helper for filesystems that want to use lookup open intents and pass back
- * a fully instantiated struct file to the caller.
- * This function is meant to be called from within a filesystem's
- * lookup method.
- * Beware of calling it for non-regular files! Those ->open methods might block
- * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo,
- * leading to a deadlock, as nobody can open that fifo anymore, because
- * another process to open fifo will block on locked parent when doing lookup).
- * Note that in case of error, nd->intent.open.file is destroyed, but the
- * path information remains valid.
+ * This can be used to finish opening a file passed to i_op->atomic_open().
+ *
  * If the open callback is set to NULL, then the standard f_op->open()
  * filesystem callback is substituted.
  */
-struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
-		int (*open)(struct inode *, struct file *))
+int finish_open(struct file *file, struct dentry *dentry,
+		int (*open)(struct inode *, struct file *),
+		int *opened)
 {
-	const struct cred *cred = current_cred();
+	int error;
+	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
-	if (IS_ERR(nd->intent.open.file))
-		goto out;
-	if (IS_ERR(dentry))
-		goto out_err;
-	nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
-					     nd->intent.open.file,
-					     open, cred);
-out:
-	return nd->intent.open.file;
-out_err:
-	release_open_intent(nd);
-	nd->intent.open.file = ERR_CAST(dentry);
-	goto out;
+	mntget(file->f_path.mnt);
+	file->f_path.dentry = dget(dentry);
+
+	error = do_dentry_open(file, open, current_cred());
+	if (!error)
+		*opened |= FILE_OPENED;
+
+	return error;
 }
-EXPORT_SYMBOL_GPL(lookup_instantiate_filp);
+EXPORT_SYMBOL(finish_open);
 
 /**
- * nameidata_to_filp - convert a nameidata to an open filp.
- * @nd: pointer to nameidata
- * @flags: open flags
+ * finish_no_open - finish ->atomic_open() without opening the file
+ *
+ * @od: opaque open data
+ * @dentry: dentry or NULL (as returned from ->lookup())
  *
- * Note that this function destroys the original nameidata
+ * This can be used to set the result of a successful lookup in ->atomic_open().
+ * The filesystem's atomic_open() method shall return NULL after calling this.
  */
-struct file *nameidata_to_filp(struct nameidata *nd)
+int finish_no_open(struct file *file, struct dentry *dentry)
 {
-	const struct cred *cred = current_cred();
-	struct file *filp;
-
-	/* Pick up the filp from the open intent */
-	filp = nd->intent.open.file;
-
-	/* Has the filesystem initialised the file for us? */
-	if (filp->f_path.dentry != NULL) {
-		nd->intent.open.file = NULL;
-	} else {
-		struct file *res;
-
-		path_get(&nd->path);
-		res = do_dentry_open(nd->path.dentry, nd->path.mnt,
-				     filp, NULL, cred);
-		if (!IS_ERR(res)) {
-			int error;
-
-			nd->intent.open.file = NULL;
-			BUG_ON(res != filp);
-
-			error = open_check_o_direct(filp);
-			if (error) {
-				fput(filp);
-				filp = ERR_PTR(error);
-			}
-		} else {
-			/* Allow nd->intent.open.file to be recycled */
-			filp = res;
-		}
-	}
-	return filp;
+	file->f_path.dentry = dentry;
+	return 1;
 }
+EXPORT_SYMBOL(finish_no_open);
 
-/*
- * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
- * error.
- */
-struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
+struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *cred)
 {
 	int error;
@@ -866,18 +775,28 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
 	validate_creds(cred);
 
 	/* We must always pass in a valid mount pointer. */
-	BUG_ON(!mnt);
+	BUG_ON(!path->mnt);
 
 	error = -ENFILE;
 	f = get_empty_filp();
-	if (f == NULL) {
-		dput(dentry);
-		mntput(mnt);
+	if (f == NULL)
 		return ERR_PTR(error);
-	}
 
 	f->f_flags = flags;
-	return __dentry_open(dentry, mnt, f, NULL, cred);
+	f->f_path = *path;
+	path_get(&f->f_path);
+	error = do_dentry_open(f, NULL, cred);
+	if (!error) {
+		error = open_check_o_direct(f);
+		if (error) {
+			fput(f);
+			f = ERR_PTR(error);
+		}
+	} else { 
+		put_filp(f);
+		f = ERR_PTR(error);
+	}
+	return f;
 }
 EXPORT_SYMBOL(dentry_open);