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, 48 insertions, 71 deletions

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 8ce57691e7b6..f8e54f5b9080 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -413,7 +413,7 @@ static void mqueue_evict_inode(struct inode *inode)
 }
 
 static int mqueue_create(struct inode *dir, struct dentry *dentry,
-				umode_t mode, struct nameidata *nd)
+				umode_t mode, bool excl)
 {
 	struct inode *inode;
 	struct mq_attr *attr = dentry->d_fsdata;
@@ -721,8 +721,8 @@ static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
 /*
  * Invoked when creating a new queue via sys_mq_open
  */
-static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir,
-			struct dentry *dentry, int oflag, umode_t mode,
+static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir,
+			struct path *path, int oflag, umode_t mode,
 			struct mq_attr *attr)
 {
 	const struct cred *cred = current_cred();
@@ -732,9 +732,9 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir,
 	if (attr) {
 		ret = mq_attr_ok(ipc_ns, attr);
 		if (ret)
-			goto out;
+			return ERR_PTR(ret);
 		/* store for use during create */
-		dentry->d_fsdata = attr;
+		path->dentry->d_fsdata = attr;
 	} else {
 		struct mq_attr def_attr;
 
@@ -744,71 +744,51 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir,
 					  ipc_ns->mq_msgsize_default);
 		ret = mq_attr_ok(ipc_ns, &def_attr);
 		if (ret)
-			goto out;
+			return ERR_PTR(ret);
 	}
 
 	mode &= ~current_umask();
-	ret = mnt_want_write(ipc_ns->mq_mnt);
+	ret = mnt_want_write(path->mnt);
 	if (ret)
-		goto out;
-	ret = vfs_create(dir->d_inode, dentry, mode, NULL);
-	dentry->d_fsdata = NULL;
-	if (ret)
-		goto out_drop_write;
-
-	result = dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred);
+		return ERR_PTR(ret);
+	ret = vfs_create(dir, path->dentry, mode, true);
+	path->dentry->d_fsdata = NULL;
+	if (!ret)
+		result = dentry_open(path, oflag, cred);
+	else
+		result = ERR_PTR(ret);
 	/*
 	 * dentry_open() took a persistent mnt_want_write(),
 	 * so we can now drop this one.
 	 */
-	mnt_drop_write(ipc_ns->mq_mnt);
+	mnt_drop_write(path->mnt);
 	return result;
-
-out_drop_write:
-	mnt_drop_write(ipc_ns->mq_mnt);
-out:
-	dput(dentry);
-	mntput(ipc_ns->mq_mnt);
-	return ERR_PTR(ret);
 }
 
 /* Opens existing queue */
-static struct file *do_open(struct ipc_namespace *ipc_ns,
-				struct dentry *dentry, int oflag)
+static struct file *do_open(struct path *path, int oflag)
 {
-	int ret;
-	const struct cred *cred = current_cred();
-
 	static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
 						  MAY_READ | MAY_WRITE };
-
-	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) {
-		ret = -EINVAL;
-		goto err;
-	}
-
-	if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) {
-		ret = -EACCES;
-		goto err;
-	}
-
-	return dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred);
-
-err:
-	dput(dentry);
-	mntput(ipc_ns->mq_mnt);
-	return ERR_PTR(ret);
+	int acc;
+	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
+		return ERR_PTR(-EINVAL);
+	acc = oflag2acc[oflag & O_ACCMODE];
+	if (inode_permission(path->dentry->d_inode, acc))
+		return ERR_PTR(-EACCES);
+	return dentry_open(path, oflag, current_cred());
 }
 
 SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
 		struct mq_attr __user *, u_attr)
 {
-	struct dentry *dentry;
+	struct path path;
 	struct file *filp;
 	char *name;
 	struct mq_attr attr;
 	int fd, error;
 	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
+	struct dentry *root = ipc_ns->mq_mnt->mnt_root;
 
 	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
 		return -EFAULT;
@@ -822,52 +802,49 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
 	if (fd < 0)
 		goto out_putname;
 
-	mutex_lock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
-	dentry = lookup_one_len(name, ipc_ns->mq_mnt->mnt_root, strlen(name));
-	if (IS_ERR(dentry)) {
-		error = PTR_ERR(dentry);
+	error = 0;
+	mutex_lock(&root->d_inode->i_mutex);
+	path.dentry = lookup_one_len(name, root, strlen(name));
+	if (IS_ERR(path.dentry)) {
+		error = PTR_ERR(path.dentry);
 		goto out_putfd;
 	}
-	mntget(ipc_ns->mq_mnt);
+	path.mnt = mntget(ipc_ns->mq_mnt);
 
 	if (oflag & O_CREAT) {
-		if (dentry->d_inode) {	/* entry already exists */
-			audit_inode(name, dentry);
+		if (path.dentry->d_inode) {	/* entry already exists */
+			audit_inode(name, path.dentry);
 			if (oflag & O_EXCL) {
 				error = -EEXIST;
 				goto out;
 			}
-			filp = do_open(ipc_ns, dentry, oflag);
+			filp = do_open(&path, oflag);
 		} else {
-			filp = do_create(ipc_ns, ipc_ns->mq_mnt->mnt_root,
-						dentry, oflag, mode,
+			filp = do_create(ipc_ns, root->d_inode,
+						&path, oflag, mode,
 						u_attr ? &attr : NULL);
 		}
 	} else {
-		if (!dentry->d_inode) {
+		if (!path.dentry->d_inode) {
 			error = -ENOENT;
 			goto out;
 		}
-		audit_inode(name, dentry);
-		filp = do_open(ipc_ns, dentry, oflag);
+		audit_inode(name, path.dentry);
+		filp = do_open(&path, oflag);
 	}
 
-	if (IS_ERR(filp)) {
+	if (!IS_ERR(filp))
+		fd_install(fd, filp);
+	else
 		error = PTR_ERR(filp);
-		goto out_putfd;
-	}
-
-	fd_install(fd, filp);
-	goto out_upsem;
-
 out:
-	dput(dentry);
-	mntput(ipc_ns->mq_mnt);
+	path_put(&path);
 out_putfd:
-	put_unused_fd(fd);
-	fd = error;
-out_upsem:
-	mutex_unlock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
+	if (error) {
+		put_unused_fd(fd);
+		fd = error;
+	}
+	mutex_unlock(&root->d_inode->i_mutex);
 out_putname:
 	putname(name);
 	return fd;