Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (107 commits)
  vfs: use ERR_CAST for err-ptr tossing in lookup_instantiate_filp
  isofs: Remove global fs lock
  jffs2: fix IN_DELETE_SELF on overwriting rename() killing a directory
  fix IN_DELETE_SELF on overwriting rename() on ramfs et.al.
  mm/truncate.c: fix build for CONFIG_BLOCK not enabled
  fs:update the NOTE of the file_operations structure
  Remove dead code in dget_parent()
  AFS: Fix silly characters in a comment
  switch d_add_ci() to d_splice_alias() in "found negative" case as well
  simplify gfs2_lookup()
  jfs_lookup(): don't bother with . or ..
  get rid of useless dget_parent() in btrfs rename() and link()
  get rid of useless dget_parent() in fs/btrfs/ioctl.c
  fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers
  drivers: fix up various ->llseek() implementations
  fs: handle SEEK_HOLE/SEEK_DATA properly in all fs's that define their own llseek
  Ext4: handle SEEK_HOLE/SEEK_DATA generically
  Btrfs: implement our own ->llseek
  fs: add SEEK_HOLE and SEEK_DATA flags
  reiserfs: make reiserfs default to barrier=flush
  ...

Fix up trivial conflicts in fs/xfs/linux-2.6/xfs_super.c due to the new
shrinker callout for the inode cache, that clashed with the xfs code to
start the periodic workers later.

1 files changed, 73 insertions, 27 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index b5b97924786..b224dc468a2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -32,7 +32,9 @@
 #define SEEK_SET	0	/* seek relative to beginning of file */
 #define SEEK_CUR	1	/* seek relative to current file position */
 #define SEEK_END	2	/* seek relative to end of file */
-#define SEEK_MAX	SEEK_END
+#define SEEK_DATA	3	/* seek to the next data */
+#define SEEK_HOLE	4	/* seek to the next hole */
+#define SEEK_MAX	SEEK_HOLE
 
 struct fstrim_range {
 	__u64 start;
@@ -63,6 +65,7 @@ struct inodes_stat_t {
 #define MAY_ACCESS 16
 #define MAY_OPEN 32
 #define MAY_CHDIR 64
+#define MAY_NOT_BLOCK 128	/* called from RCU mode, don't block */
 
 /*
  * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
@@ -392,8 +395,9 @@ struct inodes_stat_t {
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
 #include <linux/rculist_bl.h>
+#include <linux/shrinker.h>
+#include <linux/atomic.h>
 
-#include <asm/atomic.h>
 #include <asm/byteorder.h>
 
 struct export_operations;
@@ -777,7 +781,7 @@ struct inode {
 	struct timespec		i_ctime;
 	blkcnt_t		i_blocks;
 	unsigned short          i_bytes;
-	struct rw_semaphore	i_alloc_sem;
+	atomic_t		i_dio_count;
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct file_lock	*i_flock;
 	struct address_space	*i_mapping;
@@ -1396,6 +1400,11 @@ struct super_block {
 	struct list_head	s_dentry_lru;	/* unused dentry lru */
 	int			s_nr_dentry_unused;	/* # of dentry on lru */
 
+	/* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
+	spinlock_t		s_inode_lru_lock ____cacheline_aligned_in_smp;
+	struct list_head	s_inode_lru;		/* unused inode lru */
+	int			s_nr_inodes_unused;	/* # of inodes on lru */
+
 	struct block_device	*s_bdev;
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
@@ -1438,8 +1447,14 @@ struct super_block {
 	 * Saved pool identifier for cleancache (-1 means none)
 	 */
 	int cleancache_poolid;
+
+	struct shrinker s_shrink;	/* per-sb shrinker handle */
 };
 
+/* superblock cache pruning functions */
+extern void prune_icache_sb(struct super_block *sb, int nr_to_scan);
+extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan);
+
 extern struct timespec current_fs_time(struct super_block *sb);
 
 /*
@@ -1490,7 +1505,6 @@ extern void dentry_unhash(struct dentry *dentry);
 /*
  * VFS file helper functions.
  */
-extern int file_permission(struct file *, int);
 extern void inode_init_owner(struct inode *inode, const struct inode *dir,
 			mode_t mode);
 /*
@@ -1538,11 +1552,6 @@ struct block_device_operations;
 #define HAVE_COMPAT_IOCTL 1
 #define HAVE_UNLOCKED_IOCTL 1
 
-/*
- * NOTE:
- * all file operations except setlease can be called without
- * the big kernel lock held in all filesystems.
- */
 struct file_operations {
 	struct module *owner;
 	loff_t (*llseek) (struct file *, loff_t, int);
@@ -1558,7 +1567,7 @@ struct file_operations {
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
-	int (*fsync) (struct file *, int datasync);
+	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
 	int (*aio_fsync) (struct kiocb *, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
@@ -1573,13 +1582,11 @@ struct file_operations {
 			  loff_t len);
 };
 
-#define IPERM_FLAG_RCU	0x0001
-
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
-	int (*permission) (struct inode *, int, unsigned int);
-	int (*check_acl)(struct inode *, int, unsigned int);
+	int (*permission) (struct inode *, int);
+	int (*check_acl)(struct inode *, int);
 
 	int (*readlink) (struct dentry *, char __user *,int);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -1645,6 +1652,8 @@ struct super_operations {
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
+	int (*nr_cached_objects)(struct super_block *);
+	void (*free_cached_objects)(struct super_block *, int);
 };
 
 /*
@@ -1693,6 +1702,10 @@ struct super_operations {
  *			set during data writeback, and cleared with a wakeup
  *			on the bit address once it is done.
  *
+ * I_REFERENCED		Marks the inode as recently references on the LRU list.
+ *
+ * I_DIO_WAKEUP		Never set.  Only used as a key for wait_on_bit().
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -1706,6 +1719,8 @@ struct super_operations {
 #define __I_SYNC		7
 #define I_SYNC			(1 << __I_SYNC)
 #define I_REFERENCED		(1 << 8)
+#define __I_DIO_WAKEUP		9
+#define I_DIO_WAKEUP		(1 << I_DIO_WAKEUP)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 
@@ -1816,7 +1831,6 @@ struct file_system_type {
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
 	struct lock_class_key i_mutex_dir_key;
-	struct lock_class_key i_alloc_sem_key;
 };
 
 extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
@@ -1837,6 +1851,8 @@ void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
 void deactivate_locked_super(struct super_block *sb);
 int set_anon_super(struct super_block *s, void *data);
+int get_anon_bdev(dev_t *);
+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 *),
@@ -2188,16 +2204,38 @@ extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int inode_permission(struct inode *, int);
-extern int generic_permission(struct inode *, int, unsigned int,
-		int (*check_acl)(struct inode *, int, unsigned int));
+extern int generic_permission(struct inode *, int);
 
 static inline bool execute_ok(struct inode *inode)
 {
 	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
 }
 
-extern int get_write_access(struct inode *);
-extern int deny_write_access(struct file *);
+/*
+ * get_write_access() gets write permission for a file.
+ * put_write_access() releases this write permission.
+ * This is used for regular files.
+ * We cannot support write (and maybe mmap read-write shared) accesses and
+ * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
+ * can have the following values:
+ * 0: no writers, no VM_DENYWRITE mappings
+ * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
+ * > 0: (i_writecount) users are writing to the file.
+ *
+ * Normally we operate on that counter with atomic_{inc,dec} and it's safe
+ * except for the cases where we don't hold i_writecount yet. Then we need to
+ * use {get,deny}_write_access() - these functions check the sign and refuse
+ * to do the change if sign is wrong.
+ */
+static inline int get_write_access(struct inode *inode)
+{
+	return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
+}
+static inline int deny_write_access(struct file *file)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
+}
 static inline void put_write_access(struct inode * inode)
 {
 	atomic_dec(&inode->i_writecount);
@@ -2317,7 +2355,8 @@ extern int generic_segment_checks(const struct iovec *iov,
 /* fs/block_dev.c */
 extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos);
-extern int blkdev_fsync(struct file *filp, int datasync);
+extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
+			int datasync);
 
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
@@ -2368,6 +2407,8 @@ enum {
 };
 
 void dio_end_io(struct bio *bio, int error);
+void inode_dio_wait(struct inode *inode);
+void inode_dio_done(struct inode *inode);
 
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	struct block_device *bdev, const struct iovec *iov, loff_t offset,
@@ -2375,14 +2416,17 @@ ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	dio_submit_t submit_io,	int flags);
 
 static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
-	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
-	loff_t offset, unsigned long nr_segs, get_block_t get_block,
-	dio_iodone_t end_io)
+		struct inode *inode, const struct iovec *iov, loff_t offset,
+		unsigned long nr_segs, get_block_t get_block)
 {
-	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
-				    nr_segs, get_block, end_io, NULL,
+	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+				    offset, nr_segs, get_block, NULL, NULL,
 				    DIO_LOCKING | DIO_SKIP_HOLES);
 }
+#else
+static inline void inode_dio_wait(struct inode *inode)
+{
+}
 #endif
 
 extern const struct file_operations generic_ro_fops;
@@ -2432,6 +2476,8 @@ extern struct super_block *get_active_super(struct block_device *bdev);
 extern struct super_block *user_get_super(dev_t);
 extern void drop_super(struct super_block *sb);
 extern void iterate_supers(void (*)(struct super_block *, void *), void *);
+extern void iterate_supers_type(struct file_system_type *,
+			        void (*)(struct super_block *, void *), void *);
 
 extern int dcache_dir_open(struct inode *, struct file *);
 extern int dcache_dir_close(struct inode *, struct file *);
@@ -2444,7 +2490,7 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
 extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
-extern int noop_fsync(struct file *, int);
+extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern int simple_empty(struct dentry *);
 extern int simple_readpage(struct file *file, struct page *page);
 extern int simple_write_begin(struct file *file, struct address_space *mapping,
@@ -2469,7 +2515,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
 extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 		const void __user *from, size_t count);
 
-extern int generic_file_fsync(struct file *, int);
+extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);