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: (96 commits)
  no need for list_for_each_entry_safe()/resetting with superblock list
  Fix sget() race with failing mount
  vfs: don't hold s_umount over close_bdev_exclusive() call
  sysv: do not mark superblock dirty on remount
  sysv: do not mark superblock dirty on mount
  btrfs: remove junk sb_dirt change
  BFS: clean up the superblock usage
  AFFS: wait for sb synchronization when needed
  AFFS: clean up dirty flag usage
  cifs: truncate fallout
  mbcache: fix shrinker function return value
  mbcache: Remove unused features
  add f_flags to struct statfs(64)
  pass a struct path to vfs_statfs
  update VFS documentation for method changes.
  All filesystems that need invalidate_inode_buffers() are doing that explicitly
  convert remaining ->clear_inode() to ->evict_inode()
  Make ->drop_inode() just return whether inode needs to be dropped
  fs/inode.c:clear_inode() is gone
  fs/inode.c:evict() doesn't care about delete vs. non-delete paths now
  ...

Fix up trivial conflicts in fs/nilfs2/super.c

Documentation/filesystems/Locking

@@ -92,46 +92,48 @@ prototypes:
 	void (*destroy_inode)(struct inode *);
 	void (*dirty_inode) (struct inode *);
 	int (*write_inode) (struct inode *, int);
-	void (*drop_inode) (struct inode *);
-	void (*delete_inode) (struct inode *);
+	int (*drop_inode) (struct inode *);
+	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	void (*write_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
 	int (*freeze_fs) (struct super_block *);
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
-	void (*clear_inode) (struct inode *);
 	void (*umount_begin) (struct super_block *);
 	int (*show_options)(struct seq_file *, struct vfsmount *);
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 
 locking rules:
-	All may block.
+	All may block [not true, see below]
 	None have BKL
 			s_umount
 alloc_inode:
 destroy_inode:
 dirty_inode:				(must not sleep)
 write_inode:
 drop_inode:				!!!inode_lock!!!
-delete_inode:
+evict_inode:
 put_super:		write
 write_super:		read
 sync_fs:		read
 freeze_fs:		read
 unfreeze_fs:		read
-statfs:			no
-remount_fs:		maybe		(see below)
-clear_inode:
+statfs:			maybe(read)	(see below)
+remount_fs:		write
 umount_begin:		no
 show_options:		no		(namespace_sem)
 quota_read:		no		(see below)
 quota_write:		no		(see below)
 
-->remount_fs() will have the s_umount exclusive lock if it's already mounted.
-When called from get_sb_single, it does NOT have the s_umount lock.
+->statfs() has s_umount (shared) when called by ustat(2) (native or
+compat), but that's an accident of bad API; s_umount is used to pin
+the superblock down when we only have dev_t given us by userland to
+identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
+doesn't hold it when calling ->statfs() - superblock is pinned down
+by resolving the pathname passed to syscall.
 ->quota_read() and ->quota_write() functions are both guaranteed to
 be the only ones operating on the quota file by the quota code (via
 dqio_sem) (unless an admin really wants to screw up something and

Documentation/filesystems/porting

@@ -273,3 +273,48 @@ it's safe to remove it.  If you don't need it, remove it.
 deliberate; as soon as struct block_device * is propagated in a reasonable
 way by that code fixing will become trivial; until then nothing can be
 done.
+
+[mandatory]
+
+	block truncatation on error exit from ->write_begin, and ->direct_IO
+moved from generic methods (block_write_begin, cont_write_begin,
+nobh_write_begin, blockdev_direct_IO*) to callers.  Take a look at
+ext2_write_failed and callers for an example.
+
+[mandatory]
+
+	->truncate is going away.  The whole truncate sequence needs to be
+implemented in ->setattr, which is now mandatory for filesystems
+implementing on-disk size changes.  Start with a copy of the old inode_setattr
+and vmtruncate, and the reorder the vmtruncate + foofs_vmtruncate sequence to
+be in order of zeroing blocks using block_truncate_page or similar helpers,
+size update and on finally on-disk truncation which should not fail.
+inode_change_ok now includes the size checks for ATTR_SIZE and must be called
+in the beginning of ->setattr unconditionally.
+
+[mandatory]
+
+	->clear_inode() and ->delete_inode() are gone; ->evict_inode() should
+be used instead.  It gets called whenever the inode is evicted, whether it has
+remaining links or not.  Caller does *not* evict the pagecache or inode-associated
+metadata buffers; getting rid of those is responsibility of method, as it had
+been for ->delete_inode().
+	->drop_inode() returns int now; it's called on final iput() with inode_lock
+held and it returns true if filesystems wants the inode to be dropped.  As before,
+generic_drop_inode() is still the default and it's been updated appropriately.
+generic_delete_inode() is also alive and it consists simply of return 1.  Note that
+all actual eviction work is done by caller after ->drop_inode() returns.
+	clear_inode() is gone; use end_writeback() instead.  As before, it must
+be called exactly once on each call of ->evict_inode() (as it used to be for
+each call of ->delete_inode()).  Unlike before, if you are using inode-associated
+metadata buffers (i.e. mark_buffer_dirty_inode()), it's your responsibility to
+call invalidate_inode_buffers() before end_writeback().
+	No async writeback (and thus no calls of ->write_inode()) will happen
+after end_writeback() returns, so actions that should not overlap with ->write_inode()
+(e.g. freeing on-disk inode if i_nlink is 0) ought to be done after that call.
+
+	NOTE: checking i_nlink in the beginning of ->write_inode() and bailing out
+if it's zero is not *and* *never* *had* *been* enough.  Final unlink() and iput()
+may happen while the inode is in the middle of ->write_inode(); e.g. if you blindly
+free the on-disk inode, you may end up doing that while ->write_inode() is writing
+to it.

arch/alpha/kernel/osf_sys.c

@@ -234,11 +234,11 @@ linux_to_osf_statfs(struct kstatfs *linux_stat, struct osf_statfs __user *osf_st
 }
 
 static int
-do_osf_statfs(struct dentry * dentry, struct osf_statfs __user *buffer,
+do_osf_statfs(struct path *path, struct osf_statfs __user *buffer,
 	      unsigned long bufsiz)
 {
 	struct kstatfs linux_stat;
-	int error = vfs_statfs(dentry, &linux_stat);
+	int error = vfs_statfs(path, &linux_stat);
 	if (!error)
 		error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
 	return error;	
@@ -252,7 +252,7 @@ SYSCALL_DEFINE3(osf_statfs, char __user *, pathname,
 
 	retval = user_path(pathname, &path);
 	if (!retval) {
-		retval = do_osf_statfs(path.dentry, buffer, bufsiz);
+		retval = do_osf_statfs(&path buffer, bufsiz);
 		path_put(&path);
 	}
 	return retval;
@@ -267,7 +267,7 @@ SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd,
 	retval = -EBADF;
 	file = fget(fd);
 	if (file) {
-		retval = do_osf_statfs(file->f_path.dentry, buffer, bufsiz);
+		retval = do_osf_statfs(&file->f_path, buffer, bufsiz);
 		fput(file);
 	}
 	return retval;

arch/mips/include/asm/statfs.h

@@ -33,7 +33,8 @@ struct statfs {
 	/* Linux specials */
 	__kernel_fsid_t	f_fsid;
 	long		f_namelen;
-	long		f_spare[6];
+	long		f_flags;
+	long		f_spare[5];
 };
 
 #if (_MIPS_SIM == _MIPS_SIM_ABI32) || (_MIPS_SIM == _MIPS_SIM_NABI32)
@@ -53,7 +54,8 @@ struct statfs64 {
 	__u64	f_bavail;
 	__kernel_fsid_t f_fsid;
 	__u32	f_namelen;
-	__u32	f_spare[6];
+	__u32	f_flags;
+	__u32	f_spare[5];
 };
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
@@ -73,7 +75,8 @@ struct statfs64 {			/* Same as struct statfs */
 	/* Linux specials */
 	__kernel_fsid_t	f_fsid;
 	long		f_namelen;
-	long		f_spare[6];
+	long		f_flags;
+	long		f_spare[5];
 };
 
 struct compat_statfs64 {
@@ -88,7 +91,8 @@ struct compat_statfs64 {
 	__u64	f_bavail;
 	__kernel_fsid_t f_fsid;
 	__u32	f_namelen;
-	__u32	f_spare[6];
+	__u32	f_flags;
+	__u32	f_spare[5];
 };
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */

arch/parisc/hpux/sys_hpux.c

@@ -145,7 +145,7 @@ static int hpux_ustat(dev_t dev, struct hpux_ustat __user *ubuf)
 	s = user_get_super(dev);
 	if (s == NULL)
 		goto out;
-	err = vfs_statfs(s->s_root, &sbuf);
+	err = statfs_by_dentry(s->s_root, &sbuf);
 	drop_super(s);
 	if (err)
 		goto out;
@@ -186,12 +186,12 @@ struct hpux_statfs {
      int16_t f_pad;
 };
 
-static int vfs_statfs_hpux(struct dentry *dentry, struct hpux_statfs *buf)
+static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf)
 {
 	struct kstatfs st;
 	int retval;
 
-	retval = vfs_statfs(dentry, &st);
+	retval = vfs_statfs(path, &st);
 	if (retval)
 		return retval;
 
@@ -219,7 +219,7 @@ asmlinkage long hpux_statfs(const char __user *pathname,
 	error = user_path(pathname, &path);
 	if (!error) {
 		struct hpux_statfs tmp;
-		error = vfs_statfs_hpux(path.dentry, &tmp);
+		error = do_statfs_hpux(&path, &tmp);
 		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
 			error = -EFAULT;
 		path_put(&path);
@@ -237,7 +237,7 @@ asmlinkage long hpux_fstatfs(unsigned int fd, struct hpux_statfs __user * buf)
 	file = fget(fd);
 	if (!file)
 		goto out;
-	error = vfs_statfs_hpux(file->f_path.dentry, &tmp);
+	error = do_statfs_hpux(&file->f_path, &tmp);
 	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
 		error = -EFAULT;
 	fput(file);

arch/powerpc/platforms/cell/spufs/inode.c

@@ -110,7 +110,9 @@ spufs_setattr(struct dentry *dentry, struct iattr *attr)
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    (attr->ia_size != inode->i_size))
 		return -EINVAL;
-	return inode_setattr(inode, attr);
+	setattr_copy(inode, attr);
+	mark_inode_dirty(inode);
+	return 0;
 }
 
 
@@ -141,15 +143,14 @@ spufs_new_file(struct super_block *sb, struct dentry *dentry,
 }
 
 static void
-spufs_delete_inode(struct inode *inode)
+spufs_evict_inode(struct inode *inode)
 {
 	struct spufs_inode_info *ei = SPUFS_I(inode);
-
+	end_writeback(inode);
 	if (ei->i_ctx)
 		put_spu_context(ei->i_ctx);
 	if (ei->i_gang)
 		put_spu_gang(ei->i_gang);
-	clear_inode(inode);
 }
 
 static void spufs_prune_dir(struct dentry *dir)
@@ -777,8 +778,7 @@ spufs_fill_super(struct super_block *sb, void *data, int silent)
 		.alloc_inode = spufs_alloc_inode,
 		.destroy_inode = spufs_destroy_inode,
 		.statfs = simple_statfs,
-		.delete_inode = spufs_delete_inode,
-		.drop_inode = generic_delete_inode,
+		.evict_inode = spufs_evict_inode,
 		.show_options = generic_show_options,
 	};
 

arch/s390/hypfs/inode.c

@@ -117,10 +117,10 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode)
 	return ret;
 }
 
-static void hypfs_drop_inode(struct inode *inode)
+static void hypfs_evict_inode(struct inode *inode)
 {
+	end_writeback(inode);
 	kfree(inode->i_private);
-	generic_delete_inode(inode);
 }
 
 static int hypfs_open(struct inode *inode, struct file *filp)
@@ -460,7 +460,7 @@ static struct file_system_type hypfs_type = {
 
 static const struct super_operations hypfs_s_ops = {
 	.statfs		= simple_statfs,
-	.drop_inode	= hypfs_drop_inode,
+	.evict_inode	= hypfs_evict_inode,
 	.show_options	= hypfs_show_options,
 };
 

arch/s390/include/asm/statfs.h

@@ -33,7 +33,8 @@ struct statfs {
 	__kernel_fsid_t f_fsid;
 	int  f_namelen;
 	int  f_frsize;
-	int  f_spare[5];
+	int  f_flags;
+	int  f_spare[4];
 };
 
 struct statfs64 {
@@ -47,7 +48,8 @@ struct statfs64 {
 	__kernel_fsid_t f_fsid;
 	int  f_namelen;
 	int  f_frsize;
-	int  f_spare[5];
+	int  f_flags;
+	int  f_spare[4];
 };
 
 struct compat_statfs64 {
@@ -61,7 +63,8 @@ struct compat_statfs64 {
 	__kernel_fsid_t f_fsid;
 	__u32 f_namelen;
 	__u32 f_frsize;
-	__u32 f_spare[5];
+	__u32 f_flags;
+	__u32 f_spare[4];
 };
 
 #endif /* __s390x__ */

arch/um/include/shared/os.h

@@ -161,6 +161,9 @@ extern int os_stat_filesystem(char *path, long *bsize_out,
 			      long *spare_out);
 extern int os_change_dir(char *dir);
 extern int os_fchange_dir(int fd);
+extern unsigned os_major(unsigned long long dev);
+extern unsigned os_minor(unsigned long long dev);
+extern unsigned long long os_makedev(unsigned major, unsigned minor);
 
 /* start_up.c */
 extern void os_early_checks(void);

arch/um/kernel/ksyms.c

@@ -58,6 +58,9 @@ EXPORT_SYMBOL(os_accept_connection);
 EXPORT_SYMBOL(os_rcv_fd);
 EXPORT_SYMBOL(run_helper);
 EXPORT_SYMBOL(start_thread);
+EXPORT_SYMBOL(os_major);
+EXPORT_SYMBOL(os_minor);
+EXPORT_SYMBOL(os_makedev);
 
 EXPORT_SYMBOL(add_sigio_fd);
 EXPORT_SYMBOL(ignore_sigio_fd);

arch/um/os-Linux/file.c

@@ -561,3 +561,18 @@ int os_lock_file(int fd, int excl)
  out:
 	return err;
 }
+
+unsigned os_major(unsigned long long dev)
+{
+	return major(dev);
+}
+
+unsigned os_minor(unsigned long long dev)
+{
+	return minor(dev);
+}
+
+unsigned long long os_makedev(unsigned major, unsigned minor)
+{
+	return makedev(major, minor);
+}

arch/um/os-Linux/user_syms.c

@@ -103,6 +103,10 @@ EXPORT_SYMBOL_PROTO(getuid);
 EXPORT_SYMBOL_PROTO(fsync);
 EXPORT_SYMBOL_PROTO(fdatasync);
 
+EXPORT_SYMBOL_PROTO(lstat64);
+EXPORT_SYMBOL_PROTO(fstat64);
+EXPORT_SYMBOL_PROTO(mknod);
+
 /* Export symbols used by GCC for the stack protector. */
 extern void __stack_smash_handler(void *) __attribute__((weak));
 EXPORT_SYMBOL(__stack_smash_handler);