X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=fs%2Fsuper.c;h=4c602902a3ba41e261a8329c1ab515aff29b046d;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=87845e4234fe02b467794d6b095b26b1a16a58e2;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/fs/super.c b/fs/super.c index 87845e423..4c602902a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -20,7 +20,6 @@ * Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000 */ -#include #include #include #include @@ -37,8 +36,10 @@ #include /* for the emergency remount stuff */ #include #include +#include #include #include +#include #include @@ -51,17 +52,17 @@ DEFINE_SPINLOCK(sb_lock); /** * alloc_super - create new superblock + * @type: filesystem type superblock should belong to * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ -static struct super_block *alloc_super(void) +static struct super_block *alloc_super(struct file_system_type *type) { - struct super_block *s = kmalloc(sizeof(struct super_block), GFP_USER); + struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); static struct super_operations default_op; if (s) { - memset(s, 0, sizeof(struct super_block)); if (security_sb_alloc(s)) { kfree(s); s = NULL; @@ -75,12 +76,19 @@ static struct super_block *alloc_super(void) INIT_LIST_HEAD(&s->s_inodes); init_rwsem(&s->s_umount); mutex_init(&s->s_lock); + lockdep_set_class(&s->s_umount, &type->s_umount_key); + /* + * The locking rules for s_lock are up to the + * filesystem. For example ext3fs has different + * lock ordering than usbfs: + */ + lockdep_set_class(&s->s_lock, &type->s_lock_key); down_write(&s->s_umount); s->s_count = S_BIAS; atomic_set(&s->s_active, 1); - sema_init(&s->s_vfs_rename_sem,1); - sema_init(&s->s_dquot.dqio_sem, 1); - sema_init(&s->s_dquot.dqonoff_sem, 1); + mutex_init(&s->s_vfs_rename_mutex); + mutex_init(&s->s_dquot.dqio_mutex); + mutex_init(&s->s_dquot.dqonoff_mutex); init_rwsem(&s->s_dquot.dqptr_sem); init_waitqueue_head(&s->s_wait_unfrozen); s->s_maxbytes = MAX_NON_LFS; @@ -194,7 +202,7 @@ EXPORT_SYMBOL(deactivate_super); * success, 0 if we had failed (superblock contents was already dead or * dying when grab_super() had been called). */ -static int grab_super(struct super_block *s) +static int grab_super(struct super_block *s) __releases(sb_lock) { s->s_count++; spin_unlock(&sb_lock); @@ -215,6 +223,55 @@ static int grab_super(struct super_block *s) return 0; } +/* + * Superblock locking. We really ought to get rid of these two. + */ +void lock_super(struct super_block * sb) +{ + get_fs_excl(); + mutex_lock(&sb->s_lock); +} + +void unlock_super(struct super_block * sb) +{ + put_fs_excl(); + mutex_unlock(&sb->s_lock); +} + +EXPORT_SYMBOL(lock_super); +EXPORT_SYMBOL(unlock_super); + +/* + * Write out and wait upon all dirty data associated with this + * superblock. Filesystem data as well as the underlying block + * device. Takes the superblock lock. Requires a second blkdev + * flush by the caller to complete the operation. + */ +void __fsync_super(struct super_block *sb) +{ + sync_inodes_sb(sb, 0); + DQUOT_SYNC(sb); + lock_super(sb); + if (sb->s_dirt && sb->s_op->write_super) + sb->s_op->write_super(sb); + unlock_super(sb); + if (sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, 1); + sync_blockdev(sb->s_bdev); + sync_inodes_sb(sb, 1); +} + +/* + * Write out and wait upon all dirty data associated with this + * superblock. Filesystem data as well as the underlying block + * device. Takes the superblock lock. + */ +int fsync_super(struct super_block *sb) +{ + __fsync_super(sb); + return sync_blockdev(sb->s_bdev); +} + /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill @@ -224,17 +281,17 @@ static int grab_super(struct super_block *s) * that need destruction out of superblock, call generic_shutdown_super() * and release aforementioned objects. Note: dentries and inodes _are_ * taken care of and do not need specific handling. + * + * Upon calling this function, the filesystem may no longer alter or + * rearrange the set of dentries belonging to this super_block, nor may it + * change the attachments of dentries to inodes. */ void generic_shutdown_super(struct super_block *sb) { - struct dentry *root = sb->s_root; struct super_operations *sop = sb->s_op; - if (root) { - sb->s_root = NULL; - shrink_dcache_parent(root); - shrink_dcache_anon(&sb->s_anon); - dput(root); + if (sb->s_root) { + shrink_dcache_for_umount(sb); fsync_super(sb); lock_super(sb); sb->s_flags &= ~MS_ACTIVE; @@ -298,7 +355,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(); + s = alloc_super(type); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -383,9 +440,9 @@ restart: void sync_filesystems(int wait) { struct super_block *sb; - static DECLARE_MUTEX(mutex); + static DEFINE_MUTEX(mutex); - down(&mutex); /* Could be down_interruptible */ + mutex_lock(&mutex); /* Could be down_interruptible */ spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (!sb->s_op->sync_fs) @@ -414,7 +471,7 @@ restart: goto restart; } spin_unlock(&sb_lock); - up(&mutex); + mutex_unlock(&mutex); } /** @@ -488,7 +545,7 @@ asmlinkage long sys_ustat(unsigned dev, struct ustat __user * ubuf) s = user_get_super(new_decode_dev(dev)); if (s == NULL) goto out; - err = vfs_statfs(s, &sbuf); + err = vfs_statfs(s->s_root, &sbuf); drop_super(s); if (err) goto out; @@ -516,7 +573,7 @@ static void mark_files_ro(struct super_block *sb) file_list_lock(); list_for_each_entry(f, &sb->s_files, f_u.fu_list) { - if (S_ISREG(f->f_dentry->d_inode->i_mode) && file_count(f)) + if (S_ISREG(f->f_path.dentry->d_inode->i_mode) && file_count(f)) f->f_mode &= ~FMODE_WRITE; } file_list_unlock(); @@ -535,8 +592,10 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) { int retval; +#ifdef CONFIG_BLOCK if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev)) return -EACCES; +#endif if (flags & MS_RDONLY) acct_auto_close(sb); shrink_dcache_sb(sb); @@ -656,6 +715,7 @@ void kill_litter_super(struct super_block *sb) EXPORT_SYMBOL(kill_litter_super); +#ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; @@ -678,9 +738,10 @@ static void bdev_uevent(struct block_device *bdev, enum kobject_action action) } } -struct super_block *get_sb_bdev(struct file_system_type *fs_type, +int get_sb_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)) + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) { struct block_device *bdev; struct super_block *s; @@ -688,7 +749,7 @@ struct super_block *get_sb_bdev(struct file_system_type *fs_type, bdev = open_bdev_excl(dev_name, flags, fs_type); if (IS_ERR(bdev)) - return (struct super_block *)bdev; + return PTR_ERR(bdev); /* * once the super is inserted into the list by sget, s_umount @@ -699,37 +760,42 @@ struct super_block *get_sb_bdev(struct file_system_type *fs_type, s = sget(fs_type, test_bdev_super, set_bdev_super, bdev); up(&bdev->bd_mount_sem); if (IS_ERR(s)) - goto out; + goto error_s; if (s->s_root) { if ((flags ^ s->s_flags) & MS_RDONLY) { up_write(&s->s_umount); deactivate_super(s); - s = ERR_PTR(-EBUSY); + error = -EBUSY; + goto error_bdev; } - goto out; + + close_bdev_excl(bdev); } else { char b[BDEVNAME_SIZE]; s->s_flags = flags; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); - error = fill_super(s, data, flags & MS_VERBOSE ? 1 : 0); + error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { up_write(&s->s_umount); deactivate_super(s); - s = ERR_PTR(error); - } else { - s->s_flags |= MS_ACTIVE; - bdev_uevent(bdev, KOBJ_MOUNT); + goto error; } + + s->s_flags |= MS_ACTIVE; + bdev_uevent(bdev, KOBJ_MOUNT); } - return s; + return simple_set_mnt(mnt, s); -out: +error_s: + error = PTR_ERR(s); +error_bdev: close_bdev_excl(bdev); - return s; +error: + return error; } EXPORT_SYMBOL(get_sb_bdev); @@ -745,27 +811,29 @@ void kill_block_super(struct super_block *sb) } EXPORT_SYMBOL(kill_block_super); +#endif -struct super_block *get_sb_nodev(struct file_system_type *fs_type, +int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)) + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) { int error; struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); if (IS_ERR(s)) - return s; + return PTR_ERR(s); s->s_flags = flags; - error = fill_super(s, data, flags & MS_VERBOSE ? 1 : 0); + error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { up_write(&s->s_umount); deactivate_super(s); - return ERR_PTR(error); + return error; } s->s_flags |= MS_ACTIVE; - return s; + return simple_set_mnt(mnt, s); } EXPORT_SYMBOL(get_sb_nodev); @@ -775,107 +843,116 @@ static int compare_single(struct super_block *s, void *p) return 1; } -struct super_block *get_sb_single(struct file_system_type *fs_type, +int get_sb_single(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)) + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) { struct super_block *s; int error; s = sget(fs_type, compare_single, set_anon_super, NULL); if (IS_ERR(s)) - return s; + return PTR_ERR(s); if (!s->s_root) { s->s_flags = flags; - error = fill_super(s, data, flags & MS_VERBOSE ? 1 : 0); + error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { up_write(&s->s_umount); deactivate_super(s); - return ERR_PTR(error); + return error; } s->s_flags |= MS_ACTIVE; } do_remount_sb(s, flags, data, 0); - return s; + return simple_set_mnt(mnt, s); } EXPORT_SYMBOL(get_sb_single); struct vfsmount * -do_kern_mount(const char *fstype, int flags, const char *name, void *data) +vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { - struct file_system_type *type = get_fs_type(fstype); - struct super_block *sb; struct vfsmount *mnt; - int error; + struct super_block *sb; char *secdata = NULL; + int error; if (!type) return ERR_PTR(-ENODEV); - sb = ERR_PTR(-EPERM); - if ((type->fs_flags & FS_BINARY_MOUNTDATA) && - !vx_capable(CAP_SYS_ADMIN, VXC_BINARY_MOUNT)) - goto out; - - sb = ERR_PTR(-ENOMEM); + error = -ENOMEM; mnt = alloc_vfsmnt(name); if (!mnt) goto out; if (data) { secdata = alloc_secdata(); - if (!secdata) { - sb = ERR_PTR(-ENOMEM); + if (!secdata) goto out_mnt; - } error = security_sb_copy_data(type, data, secdata); - if (error) { - sb = ERR_PTR(error); + if (error) goto out_free_secdata; - } } - sb = type->get_sb(type, flags, name, data); - if (IS_ERR(sb)) + error = type->get_sb(type, flags, name, data, mnt); + if (error < 0) goto out_free_secdata; + sb = mnt->mnt_sb; error = -EPERM; - if (!capable(CAP_SYS_ADMIN) && !sb->s_bdev && + if (!vx_capable(CAP_SYS_ADMIN, VXC_BINARY_MOUNT) && !sb->s_bdev && (sb->s_magic != PROC_SUPER_MAGIC) && (sb->s_magic != DEVPTS_SUPER_MAGIC)) goto out_sb; - error = security_sb_kern_mount(sb, secdata); + error = security_sb_kern_mount(sb, secdata); if (error) goto out_sb; - mnt->mnt_sb = sb; - mnt->mnt_root = dget(sb->s_root); - mnt->mnt_mountpoint = sb->s_root; + + mnt->mnt_mountpoint = mnt->mnt_root; mnt->mnt_parent = mnt; - up_write(&sb->s_umount); + up_write(&mnt->mnt_sb->s_umount); free_secdata(secdata); - put_filesystem(type); return mnt; out_sb: - up_write(&sb->s_umount); - deactivate_super(sb); - sb = ERR_PTR(error); + dput(mnt->mnt_root); + up_write(&mnt->mnt_sb->s_umount); + deactivate_super(mnt->mnt_sb); out_free_secdata: free_secdata(secdata); out_mnt: free_vfsmnt(mnt); out: - put_filesystem(type); - return (struct vfsmount *)sb; + return ERR_PTR(error); } -EXPORT_SYMBOL_GPL(do_kern_mount); +EXPORT_SYMBOL_GPL(vfs_kern_mount); + +struct vfsmount * +do_kern_mount(const char *fstype, int flags, const char *name, void *data) +{ + struct file_system_type *type = get_fs_type(fstype); + struct vfsmount *mnt; + + if (!type) + return ERR_PTR(-ENODEV); + + mnt = ERR_PTR(-EPERM); + if ((type->fs_flags & FS_BINARY_MOUNTDATA) && + !vx_capable(CAP_SYS_ADMIN, VXC_BINARY_MOUNT)) + goto out_put; + + mnt = vfs_kern_mount(type, flags, name, data); +out_put: + put_filesystem(type); + return mnt; +} struct vfsmount *kern_mount(struct file_system_type *type) { - return do_kern_mount(type->name, 0, type->name, NULL); + return vfs_kern_mount(type, 0, type->name, NULL); } EXPORT_SYMBOL(kern_mount);