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, 67 insertions, 32 deletions

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 334e0b18a014..8964cf3999b2 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -154,7 +154,7 @@ u64 fuse_get_attr_version(struct fuse_conn *fc)
  * the lookup once more.  If the lookup results in the same inode,
  * then refresh the attributes, timeouts and mark the dentry valid.
  */
-static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
+static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 {
 	struct inode *inode;
 
@@ -174,7 +174,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 		if (!inode)
 			return 0;
 
-		if (nd && (nd->flags & LOOKUP_RCU))
+		if (flags & LOOKUP_RCU)
 			return -ECHILD;
 
 		fc = get_fuse_conn(inode);
@@ -249,7 +249,7 @@ static struct dentry *fuse_d_add_directory(struct dentry *entry,
 		/* This tries to shrink the subtree below alias */
 		fuse_invalidate_entry(alias);
 		dput(alias);
-		if (!list_empty(&inode->i_dentry))
+		if (!hlist_empty(&inode->i_dentry))
 			return ERR_PTR(-EBUSY);
 	} else {
 		dput(alias);
@@ -316,7 +316,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 }
 
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
-				  struct nameidata *nd)
+				  unsigned int flags)
 {
 	int err;
 	struct fuse_entry_out outarg;
@@ -370,7 +370,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  * 'mknod' + 'open' requests.
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
-			    umode_t mode, struct nameidata *nd)
+			    struct file *file, unsigned flags,
+			    umode_t mode, int *opened)
 {
 	int err;
 	struct inode *inode;
@@ -381,15 +382,11 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	struct fuse_open_out outopen;
 	struct fuse_entry_out outentry;
 	struct fuse_file *ff;
-	struct file *file;
-	int flags = nd->intent.open.flags;
-
-	if (fc->no_create)
-		return -ENOSYS;
 
 	forget = fuse_alloc_forget();
+	err = -ENOMEM;
 	if (!forget)
-		return -ENOMEM;
+		goto out_err;
 
 	req = fuse_get_req(fc);
 	err = PTR_ERR(req);
@@ -428,11 +425,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	req->out.args[1].value = &outopen;
 	fuse_request_send(fc, req);
 	err = req->out.h.error;
-	if (err) {
-		if (err == -ENOSYS)
-			fc->no_create = 1;
+	if (err)
 		goto out_free_ff;
-	}
 
 	err = -EIO;
 	if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
@@ -448,28 +442,74 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		fuse_sync_release(ff, flags);
 		fuse_queue_forget(fc, forget, outentry.nodeid, 1);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out_err;
 	}
 	kfree(forget);
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	file = lookup_instantiate_filp(nd, entry, generic_file_open);
-	if (IS_ERR(file)) {
+	err = finish_open(file, entry, generic_file_open, opened);
+	if (err) {
 		fuse_sync_release(ff, flags);
-		return PTR_ERR(file);
+	} else {
+		file->private_data = fuse_file_get(ff);
+		fuse_finish_open(inode, file);
 	}
-	file->private_data = fuse_file_get(ff);
-	fuse_finish_open(inode, file);
-	return 0;
+	return err;
 
- out_free_ff:
+out_free_ff:
 	fuse_file_free(ff);
- out_put_request:
+out_put_request:
 	fuse_put_request(fc, req);
- out_put_forget_req:
+out_put_forget_req:
 	kfree(forget);
+out_err:
+	return err;
+}
+
+static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
+			    struct file *file, unsigned flags,
+			    umode_t mode, int *opened)
+{
+	int err;
+	struct fuse_conn *fc = get_fuse_conn(dir);
+	struct dentry *res = NULL;
+
+	if (d_unhashed(entry)) {
+		res = fuse_lookup(dir, entry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			entry = res;
+	}
+
+	if (!(flags & O_CREAT) || entry->d_inode)
+		goto no_open;
+
+	/* Only creates */
+	*opened |= FILE_CREATED;
+
+	if (fc->no_create)
+		goto mknod;
+
+	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	if (err == -ENOSYS) {
+		fc->no_create = 1;
+		goto mknod;
+	}
+out_dput:
+	dput(res);
 	return err;
+
+mknod:
+	err = fuse_mknod(dir, entry, mode, 0);
+	if (err)
+		goto out_dput;
+no_open:
+	return finish_no_open(file, res);
 }
 
 /*
@@ -571,14 +611,8 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode,
 }
 
 static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode,
-		       struct nameidata *nd)
+		       bool excl)
 {
-	if (nd) {
-		int err = fuse_create_open(dir, entry, mode, nd);
-		if (err != -ENOSYS)
-			return err;
-		/* Fall back on mknod */
-	}
 	return fuse_mknod(dir, entry, mode, 0);
 }
 
@@ -1646,6 +1680,7 @@ static const struct inode_operations fuse_dir_inode_operations = {
 	.link		= fuse_link,
 	.setattr	= fuse_setattr,
 	.create		= fuse_create,
+	.atomic_open	= fuse_atomic_open,
 	.mknod		= fuse_mknod,
 	.permission	= fuse_permission,
 	.getattr	= fuse_getattr,