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
  ...

11 files changed, 53 insertions, 49 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 094789ff3e9..caa34e50537 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -128,7 +128,7 @@ struct dentry {
 	 	struct rcu_head d_rcu;
 	} d_u;
 	struct list_head d_subdirs;	/* our children */
-	struct list_head d_alias;	/* inode alias list */
+	struct hlist_node d_alias;	/* inode alias list */
 };
 
 /*
@@ -144,7 +144,7 @@ enum dentry_d_lock_class
 };
 
 struct dentry_operations {
-	int (*d_revalidate)(struct dentry *, struct nameidata *);
+	int (*d_revalidate)(struct dentry *, unsigned int);
 	int (*d_hash)(const struct dentry *, const struct inode *,
 			struct qstr *);
 	int (*d_compare)(const struct dentry *, const struct inode *,
diff --git a/include/linux/file.h b/include/linux/file.h
index 58bf158c53d..a22408bac0d 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -39,4 +39,7 @@ extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
+extern void flush_delayed_fput(void);
+extern void __fput_sync(struct file *);
+
 #endif /* __LINUX_FILE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 17fd887c798..8fabb037a48 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -826,7 +826,7 @@ struct inode {
 	struct list_head	i_lru;		/* inode LRU list */
 	struct list_head	i_sb_list;
 	union {
-		struct list_head	i_dentry;
+		struct hlist_head	i_dentry;
 		struct rcu_head		i_rcu;
 	};
 	u64			i_version;
@@ -1571,7 +1571,7 @@ extern void unlock_super(struct super_block *);
 /*
  * VFS helper functions..
  */
-extern int vfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
+extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
 extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
 extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
@@ -1666,7 +1666,7 @@ struct file_operations {
 };
 
 struct inode_operations {
-	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	int (*permission) (struct inode *, int);
 	struct posix_acl * (*get_acl)(struct inode *, int);
@@ -1674,7 +1674,7 @@ struct inode_operations {
 	int (*readlink) (struct dentry *, char __user *,int);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
 
-	int (*create) (struct inode *,struct dentry *,umode_t,struct nameidata *);
+	int (*create) (struct inode *,struct dentry *, umode_t, bool);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -1693,6 +1693,9 @@ struct inode_operations {
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
 	int (*update_time)(struct inode *, struct timespec *, int);
+	int (*atomic_open)(struct inode *, struct dentry *,
+			   struct file *, unsigned open_flag,
+			   umode_t create_mode, int *opened);
 } ____cacheline_aligned;
 
 struct seq_file;
@@ -1911,7 +1914,7 @@ void free_anon_bdev(dev_t);
 struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
-			void *data);
+			int flags, void *data);
 extern struct dentry *mount_pseudo(struct file_system_type *, char *,
 	const struct super_operations *ops,
 	const struct dentry_operations *dops,
@@ -2057,10 +2060,17 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags,
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
-extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
-				 const struct cred *);
+extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 extern char * getname(const char __user *);
+enum {
+	FILE_CREATED = 1,
+	FILE_OPENED = 2
+};
+extern int finish_open(struct file *file, struct dentry *dentry,
+			int (*open)(struct inode *, struct file *),
+			int *opened);
+extern int finish_no_open(struct file *file, struct dentry *dentry);
 
 /* fs/ioctl.c */
 
@@ -2091,6 +2101,7 @@ extern sector_t blkdev_max_block(struct block_device *bdev);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
 extern void invalidate_bdev(struct block_device *);
+extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 extern int sync_blockdev(struct block_device *bdev);
 extern void kill_bdev(struct block_device *);
 extern struct super_block *freeze_bdev(struct block_device *);
@@ -2112,6 +2123,10 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 {
 	return 0;
 }
+
+static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
+{
+}
 #endif
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
@@ -2438,7 +2453,7 @@ extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
-		int origin, loff_t maxsize);
+		int origin, loff_t maxsize, loff_t eof);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
@@ -2560,7 +2575,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata);
 
-extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
 extern const struct file_operations simple_dir_operations;
 extern const struct inode_operations simple_dir_inode_operations;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index ffc02135c48..d2ef8b34b96 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -7,12 +7,6 @@
 
 struct vfsmount;
 
-struct open_intent {
-	int	flags;
-	int	create_mode;
-	struct file *file;
-};
-
 enum { MAX_NESTED_LINKS = 8 };
 
 struct nameidata {
@@ -25,11 +19,6 @@ struct nameidata {
 	int		last_type;
 	unsigned	depth;
 	char *saved_names[MAX_NESTED_LINKS + 1];
-
-	/* Intent data */
-	union {
-		struct open_intent open;
-	} intent;
 };
 
 /*
@@ -78,13 +67,10 @@ extern int kern_path(const char *, unsigned, struct path *);
 
 extern struct dentry *kern_path_create(int, const char *, struct path *, int);
 extern struct dentry *user_path_create(int, const char __user *, struct path *, int);
-extern int kern_path_parent(const char *, struct nameidata *);
+extern struct dentry *kern_path_locked(const char *, struct path *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
 
-extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
-		int (*open)(struct inode *, struct file *));
-
 extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
 
 extern int follow_down_one(struct path *);
@@ -94,6 +80,8 @@ extern int follow_up(struct path *);
 extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
 
+extern void nd_jump_link(struct nameidata *nd, struct path *path);
+
 static inline void nd_set_link(struct nameidata *nd, char *path)
 {
 	nd->saved_names[nd->depth] = path;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 8aadd90b808..d3b7c18b18f 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1374,7 +1374,7 @@ struct nfs_rpc_ops {
 	int	(*readlink)(struct inode *, struct page *, unsigned int,
 			    unsigned int);
 	int	(*create)  (struct inode *, struct dentry *,
-			    struct iattr *, int, struct nfs_open_context *);
+			    struct iattr *, int);
 	int	(*remove)  (struct inode *, struct qstr *);
 	void	(*unlink_setup)  (struct rpc_message *, struct inode *dir);
 	void	(*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *);
diff --git a/include/linux/quota.h b/include/linux/quota.h
index c09fa042b5e..524ede8a160 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -333,7 +333,7 @@ struct quotactl_ops {
 	int (*quota_on)(struct super_block *, int, int, struct path *);
 	int (*quota_on_meta)(struct super_block *, int, int);
 	int (*quota_off)(struct super_block *, int);
-	int (*quota_sync)(struct super_block *, int, int);
+	int (*quota_sync)(struct super_block *, int);
 	int (*get_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*set_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*get_dqblk)(struct super_block *, int, qid_t, struct fs_disk_quota *);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 17b977304a0..ec6b65feaab 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -83,7 +83,8 @@ int dquot_quota_on(struct super_block *sb, int type, int format_id,
 int dquot_quota_on_mount(struct super_block *sb, char *qf_name,
  	int format_id, int type);
 int dquot_quota_off(struct super_block *sb, int type);
-int dquot_quota_sync(struct super_block *sb, int type, int wait);
+int dquot_writeback_dquots(struct super_block *sb, int type);
+int dquot_quota_sync(struct super_block *sb, int type);
 int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_get_dqblk(struct super_block *sb, int type, qid_t id,
@@ -255,6 +256,11 @@ static inline int dquot_resume(struct super_block *sb, int type)
 
 #define dquot_file_open		generic_file_open
 
+static inline int dquot_writeback_dquots(struct super_block *sb, int type)
+{
+	return 0;
+}
+
 #endif /* CONFIG_QUOTA */
 
 static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 64d9df5c3a4..1a2ebd39b80 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1405,7 +1405,7 @@ struct task_struct {
 	int (*notifier)(void *priv);
 	void *notifier_data;
 	sigset_t *notifier_mask;
-	struct hlist_head task_works;
+	struct callback_head *task_works;
 
 	struct audit_context *audit_context;
 #ifdef CONFIG_AUDITSYSCALL
@@ -1546,7 +1546,6 @@ struct task_struct {
 	unsigned long timer_slack_ns;
 	unsigned long default_timer_slack_ns;
 
-	struct list_head	*scm_work_list;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored address in ret_stack */
 	int curr_ret_stack;
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 294d5d5e90b..fb46b03b185 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -4,29 +4,21 @@
 #include <linux/list.h>
 #include <linux/sched.h>
 
-struct task_work;
-typedef void (*task_work_func_t)(struct task_work *);
-
-struct task_work {
-	struct hlist_node hlist;
-	task_work_func_t func;
-	void *data;
-};
+typedef void (*task_work_func_t)(struct callback_head *);
 
 static inline void
-init_task_work(struct task_work *twork, task_work_func_t func, void *data)
+init_task_work(struct callback_head *twork, task_work_func_t func)
 {
 	twork->func = func;
-	twork->data = data;
 }
 
-int task_work_add(struct task_struct *task, struct task_work *twork, bool);
-struct task_work *task_work_cancel(struct task_struct *, task_work_func_t);
+int task_work_add(struct task_struct *task, struct callback_head *twork, bool);
+struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);
 
 static inline void exit_task_work(struct task_struct *task)
 {
-	if (unlikely(!hlist_empty(&task->task_works)))
+	if (unlikely(task->task_works))
 		task_work_run();
 }
 
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 6a4d82bedb0..1e98b553042 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -192,7 +192,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	 * hlist_add_head(task->task_works);
 	 */
 	smp_mb__after_clear_bit();
-	if (unlikely(!hlist_empty(&current->task_works)))
+	if (unlikely(current->task_works))
 		task_work_run();
 }
 
diff --git a/include/linux/types.h b/include/linux/types.h
index 9c1bd539ea7..bf0dd7524b2 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -246,14 +246,15 @@ struct ustat {
 };
 
 /**
- * struct rcu_head - callback structure for use with RCU
+ * struct callback_head - callback structure for use with RCU and task_work
  * @next: next update requests in a list
  * @func: actual update function to call after the grace period.
  */
-struct rcu_head {
-	struct rcu_head *next;
-	void (*func)(struct rcu_head *head);
+struct callback_head {
+	struct callback_head *next;
+	void (*func)(struct callback_head *head);
 };
+#define rcu_head callback_head
 
 #endif	/* __KERNEL__ */
 #endif /*  __ASSEMBLY__ */