Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/viro/vfs

Pull vfs updates from Al Viro:
 "Assorted cleanups and fixes.

  Probably the most interesting part long-term is ->d_init() - that will
  have a bunch of followups in (at least) ceph and lustre, but we'll
  need to sort the barrier-related rules before it can get used for
  really non-trivial stuff.

  Another fun thing is the merge of ->d_iput() callers (dentry_iput()
  and dentry_unlink_inode()) and a bunch of ->d_compare() ones (all
  except the one in __d_lookup_lru())"

* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (26 commits)
  fs/dcache.c: avoid soft-lockup in dput()
  vfs: new d_init method
  vfs: Update lookup_dcache() comment
  bdev: get rid of ->bd_inodes
  Remove last traces of ->sync_page
  new helper: d_same_name()
  dentry_cmp(): use lockless_dereference() instead of smp_read_barrier_depends()
  vfs: clean up documentation
  vfs: document ->d_real()
  vfs: merge .d_select_inode() into .d_real()
  unify dentry_iput() and dentry_unlink_inode()
  binfmt_misc: ->s_root is not going anywhere
  drop redundant ->owner initializations
  ufs: get rid of redundant checks
  orangefs: constify inode_operations
  missed comment updates from ->direct_IO() prototype change
  file_inode(f)->i_mapping is f->f_mapping
  trim fsnotify hooks a bit
  9p: new helper - v9fs_parent_fid()
  debugfs: ->d_parent is never NULL or negative
  ...

Documentation/block/biodoc.txt

@@ -1024,8 +1024,7 @@ could be on demand. For example wait_on_buffer sets the unplugging going
 through sync_buffer() running blk_run_address_space(mapping). Or the caller
 can do it explicity through blk_unplug(bdev). So in the read case,
 the queue gets explicitly unplugged as part of waiting for completion on that
-buffer. For page driven IO, the address space ->sync_page() takes care of
-doing the blk_run_address_space().
+buffer.
 
 Aside:
   This is kind of controversial territory, as it's not clear if plugging is

Documentation/filesystems/Locking

@@ -15,11 +15,14 @@ prototypes:
 	int (*d_compare)(const struct dentry *, const struct dentry *,
 			unsigned int, const char *, const struct qstr *);
 	int (*d_delete)(struct dentry *);
+	int (*d_init)(struct dentry *);
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
 	struct vfsmount *(*d_automount)(struct path *path);
 	int (*d_manage)(struct dentry *, bool);
+	struct dentry *(*d_real)(struct dentry *, const struct inode *,
+				 unsigned int);
 
 locking rules:
 		rename_lock	->d_lock	may block	rcu-walk
@@ -28,12 +31,14 @@ d_weak_revalidate:no		no		yes	 	no
 d_hash		no		no		no		maybe
 d_compare:	yes		no		no		maybe
 d_delete:	no		yes		no		no
+d_init:	no		no		yes		no
 d_release:	no		no		yes		no
 d_prune:        no              yes             no              no
 d_iput:		no		no		yes		no
 d_dname:	no		no		no		no
 d_automount:	no		no		yes		no
 d_manage:	no		no		yes (ref-walk)	maybe
+d_real		no		no		yes 		no
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
@@ -66,7 +71,6 @@ prototypes:
 				struct file *, unsigned open_flag,
 				umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 
 locking rules:
 	all may block
@@ -95,7 +99,6 @@ fiemap:		no
 update_time:	no
 atomic_open:	yes
 tmpfile:	no
-dentry_open:	no
 
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
@@ -179,7 +182,6 @@ unlocks and drops the reference.
 prototypes:
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*readpage)(struct file *, struct page *);
-	int (*sync_page)(struct page *);
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	int (*set_page_dirty)(struct page *page);
 	int (*readpages)(struct file *filp, struct address_space *mapping,
@@ -210,7 +212,6 @@ locking rules:
 			PageLocked(page)	i_mutex
 writepage:		yes, unlocks (see below)
 readpage:		yes, unlocks
-sync_page:		maybe
 writepages:
 set_page_dirty		no
 readpages:
@@ -230,8 +231,8 @@ error_remove_page:	yes
 swap_activate:		no
 swap_deactivate:	no
 
-	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
-may be called from the request handler (/dev/loop).
+	->write_begin(), ->write_end() and ->readpage() may be called from
+the request handler (/dev/loop).
 
 	->readpage() unlocks the page, either synchronously or via I/O
 completion.
@@ -287,11 +288,6 @@ will leave the page itself marked clean but it will be tagged as dirty in the
 radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
 in the filesystem like having dirty inodes at umount and losing written data.
 
-	->sync_page() locking rules are not well-defined - usually it is called
-with lock on page, but that is not guaranteed. Considering the currently
-existing instances of this method ->sync_page() itself doesn't look
-well-defined...
-
 	->writepages() is used for periodic writeback and for syscall-initiated
 sync operations.  The address_space should start I/O against at least
 *nr_to_write pages.  *nr_to_write must be decremented for each page which is

Documentation/filesystems/vfs.txt

@@ -364,7 +364,6 @@ struct inode_operations {
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
 			unsigned open_flag, umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -534,9 +533,7 @@ __sync_single_inode) to check if ->writepages has been successful in
 writing out the whole address_space.
 
 The Writeback tag is used by filemap*wait* and sync_page* functions,
-via filemap_fdatawait_range, to wait for all writeback to
-complete.  While waiting ->sync_page (if defined) will be called on
-each page that is found to require writeback.
+via filemap_fdatawait_range, to wait for all writeback to complete.
 
 An address_space handler may attach extra information to a page,
 typically using the 'private' field in the 'struct page'.  If such
@@ -554,8 +551,8 @@ address_space has finer control of write sizes.
 
 The read process essentially only requires 'readpage'.  The write
 process is more complicated and uses write_begin/write_end or
-set_page_dirty to write data into the address_space, and writepage,
-sync_page, and writepages to writeback data to storage.
+set_page_dirty to write data into the address_space, and writepage
+and writepages to writeback data to storage.
 
 Adding and removing pages to/from an address_space is protected by the
 inode's i_mutex.
@@ -701,13 +698,6 @@ struct address_space_operations {
   	but instead uses bmap to find out where the blocks in the file
   	are and uses those addresses directly.
 
-  dentry_open: *WARNING: probably going away soon, do not use!* This is an
-	alternative to f_op->open(), the difference is that this method may open
-	a file not necessarily originating from the same filesystem as the one
-	i_op->open() was called on.  It may be useful for stacking filesystems
-	which want to allow native I/O directly on underlying files.
-
-
   invalidatepage: If a page has PagePrivate set, then invalidatepage
         will be called when part or all of the page is to be removed
 	from the address space.  This generally corresponds to either a
@@ -944,11 +934,14 @@ struct dentry_operations {
 	int (*d_compare)(const struct dentry *, const struct dentry *,
 			unsigned int, const char *, const struct qstr *);
 	int (*d_delete)(const struct dentry *);
+	int (*d_init)(struct dentry *);
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(struct dentry *, bool);
+	struct dentry *(*d_real)(struct dentry *, const struct inode *,
+				 unsigned int);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -1014,6 +1007,8 @@ struct dentry_operations {
 	always cache a reachable dentry. d_delete must be constant and
 	idempotent.
 
+  d_init: called when a dentry is allocated
+
   d_release: called when a dentry is really deallocated
 
   d_iput: called when a dentry loses its inode (just prior to its
@@ -1033,6 +1028,14 @@ struct dentry_operations {
 	at the end of the buffer, and returns a pointer to the first char.
 	dynamic_dname() helper function is provided to take care of this.
 
+	Example :
+
+	static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
+	{
+		return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
+				dentry->d_inode->i_ino);
+	}
+
   d_automount: called when an automount dentry is to be traversed (optional).
 	This should create a new VFS mount record and return the record to the
 	caller.  The caller is supplied with a path parameter giving the
@@ -1071,13 +1074,23 @@ struct dentry_operations {
 	This function is only used if DCACHE_MANAGE_TRANSIT is set on the
 	dentry being transited from.
 
-Example :
+  d_real: overlay/union type filesystems implement this method to return one of
+	the underlying dentries hidden by the overlay.  It is used in three
+	different modes:
 
-static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
-{
-	return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
-				dentry->d_inode->i_ino);
-}
+	Called from open it may need to copy-up the file depending on the
+	supplied open flags.  This mode is selected with a non-zero flags
+	argument.  In this mode the d_real method can return an error.
+
+	Called from file_dentry() it returns the real dentry matching the inode
+	argument.  The real dentry may be from a lower layer already copied up,
+	but still referenced from the file.  This mode is selected with a
+	non-NULL inode argument.  This will always succeed.
+
+	With NULL inode and zero flags the topmost real underlying dentry is
+	returned.  This will always succeed.
+
+	This method is never called with both non-NULL inode and non-zero flags.
 
 Each dentry has a pointer to its parent dentry, as well as a hash list
 of child dentries. Child dentries are basically like files in a

drivers/block/drbd/drbd_debugfs.c

@@ -425,9 +425,6 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo
 	/* Are we still linked,
 	 * or has debugfs_remove() already been called? */
 	parent = file->f_path.dentry->d_parent;
-	/* not sure if this can happen: */
-	if (!parent || d_really_is_negative(parent))
-		goto out;
 	/* serialize with d_delete() */
 	inode_lock(d_inode(parent));
 	/* Make sure the object is still alive */
@@ -440,7 +437,6 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo
 		if (ret)
 			kref_put(kref, release);
 	}
-out:
 	return ret;
 }
 

drivers/gpu/drm/armada/armada_gem.c

@@ -231,7 +231,7 @@ struct armada_gem_object *armada_gem_alloc_object(struct drm_device *dev,
 
 	obj->dev_addr = DMA_ERROR_CODE;
 
-	mapping = file_inode(obj->obj.filp)->i_mapping;
+	mapping = obj->obj.filp->f_mapping;
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE);
 
 	DRM_DEBUG_DRIVER("alloc obj %p size %zu\n", obj, size);
@@ -441,7 +441,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 		if (sg_alloc_table(sgt, count, GFP_KERNEL))
 			goto free_sgt;
 
-		mapping = file_inode(dobj->obj.filp)->i_mapping;
+		mapping = dobj->obj.filp->f_mapping;
 
 		for_each_sg(sgt->sgl, sg, count, i) {
 			struct page *page;

drivers/gpu/drm/drm_gem.c

@@ -511,7 +511,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj)
 	int i, npages;
 
 	/* This is the shared memory object that backs the GEM resource */
-	mapping = file_inode(obj->filp)->i_mapping;
+	mapping = obj->filp->f_mapping;
 
 	/* We already BUG_ON() for non-page-aligned sizes in
 	 * drm_gem_object_init(), so we should never hit this unless

drivers/gpu/drm/etnaviv/etnaviv_gem.c

@@ -660,7 +660,7 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev,
 		 * why this is required _and_ expected if you're
 		 * going to pin these pages.
 		 */
-		mapping = file_inode(obj->filp)->i_mapping;
+		mapping = obj->filp->f_mapping;
 		mapping_set_gfp_mask(mapping, GFP_HIGHUSER);
 	}
 

drivers/gpu/drm/i915/i915_gem.c

@@ -151,7 +151,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 static int
 i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 {
-	struct address_space *mapping = file_inode(obj->base.filp)->i_mapping;
+	struct address_space *mapping = obj->base.filp->f_mapping;
 	char *vaddr = obj->phys_handle->vaddr;
 	struct sg_table *st;
 	struct scatterlist *sg;
@@ -218,7 +218,7 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj)
 		obj->dirty = 0;
 
 	if (obj->dirty) {
-		struct address_space *mapping = file_inode(obj->base.filp)->i_mapping;
+		struct address_space *mapping = obj->base.filp->f_mapping;
 		char *vaddr = obj->phys_handle->vaddr;
 		int i;
 
@@ -2155,7 +2155,7 @@ i915_gem_object_invalidate(struct drm_i915_gem_object *obj)
 	if (obj->base.filp == NULL)
 		return;
 
-	mapping = file_inode(obj->base.filp)->i_mapping,
+	mapping = obj->base.filp->f_mapping,
 	invalidate_mapping_pages(mapping, 0, (loff_t)-1);
 }
 
@@ -2271,7 +2271,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	 *
 	 * Fail silently without starting the shrinker
 	 */
-	mapping = file_inode(obj->base.filp)->i_mapping;
+	mapping = obj->base.filp->f_mapping;
 	gfp = mapping_gfp_constraint(mapping, ~(__GFP_IO | __GFP_RECLAIM));
 	gfp |= __GFP_NORETRY | __GFP_NOWARN;
 	sg = st->sgl;
@@ -4522,7 +4522,7 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 		mask |= __GFP_DMA32;
 	}
 
-	mapping = file_inode(obj->base.filp)->i_mapping;
+	mapping = obj->base.filp->f_mapping;
 	mapping_set_gfp_mask(mapping, mask);
 
 	i915_gem_object_init(obj, &i915_gem_object_ops);

drivers/gpu/drm/omapdrm/omap_gem.c

@@ -1407,7 +1407,7 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 		if (ret)
 			goto err_free;
 
-		mapping = file_inode(obj->filp)->i_mapping;
+		mapping = obj->filp->f_mapping;
 		mapping_set_gfp_mask(mapping, GFP_USER | __GFP_DMA32);
 	}
 

drivers/gpu/drm/ttm/ttm_tt.c

@@ -298,7 +298,7 @@ int ttm_tt_swapin(struct ttm_tt *ttm)
 	swap_storage = ttm->swap_storage;
 	BUG_ON(swap_storage == NULL);
 
-	swap_space = file_inode(swap_storage)->i_mapping;
+	swap_space = swap_storage->f_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
 		from_page = shmem_read_mapping_page(swap_space, i);
@@ -347,7 +347,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
 	} else
 		swap_storage = persistent_swap_storage;
 
-	swap_space = file_inode(swap_storage)->i_mapping;
+	swap_space = swap_storage->f_mapping;
 
 	for (i = 0; i < ttm->num_pages; ++i) {
 		from_page = ttm->pages[i];

fs/9p/fid.h

@@ -24,6 +24,10 @@
 #include <linux/list.h>
 
 struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
+static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry)
+{
+	return v9fs_fid_lookup(dentry->d_parent);
+}
 struct p9_fid *v9fs_fid_clone(struct dentry *dentry);
 void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
 struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);

fs/9p/vfs_addr.c

@@ -231,7 +231,6 @@ static int v9fs_launder_page(struct page *page)
 /**
  * v9fs_direct_IO - 9P address space operation for direct I/O
  * @iocb: target I/O control block
- * @pos: offset in file to begin the operation
  *
  * The presence of v9fs_direct_IO() in the address space ops vector
  * allowes open() O_DIRECT flags which would have failed otherwise.

fs/9p/vfs_inode.c

@@ -595,7 +595,7 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 
 	v9ses = v9fs_inode2v9ses(dir);
 	inode = d_inode(dentry);
-	dfid = v9fs_fid_lookup(dentry->d_parent);
+	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid)) {
 		retval = PTR_ERR(dfid);
 		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", retval);
@@ -653,7 +653,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	ofid = NULL;
 	fid = NULL;
 	name = (char *) dentry->d_name.name;
-	dfid = v9fs_fid_lookup(dentry->d_parent);
+	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid)) {
 		err = PTR_ERR(dfid);
 		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
@@ -798,7 +798,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 	v9ses = v9fs_inode2v9ses(dir);
 	/* We can walk d_parent because we hold the dir->i_mutex */
-	dfid = v9fs_fid_lookup(dentry->d_parent);
+	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid))
 		return ERR_CAST(dfid);
 
@@ -975,13 +975,13 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (IS_ERR(oldfid))
 		return PTR_ERR(oldfid);
 
-	olddirfid = v9fs_fid_clone(old_dentry->d_parent);
+	olddirfid = v9fs_parent_fid(old_dentry);
 	if (IS_ERR(olddirfid)) {
 		retval = PTR_ERR(olddirfid);
 		goto done;
 	}
 
-	newdirfid = v9fs_fid_clone(new_dentry->d_parent);
+	newdirfid = v9fs_parent_fid(new_dentry);
 	if (IS_ERR(newdirfid)) {
 		retval = PTR_ERR(newdirfid);
 		goto clunk_olddir;