X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fsuper.c;h=1527e6a0ee358d084a29f542816a91c4418f5ef6;hb=684bdc7ff95e0c1d4b0bcf236491840b55a54189;hp=ed080c41716757a3c0a71c714c5a7db8ec489287;hpb=2150edc6c5cf00f7adb54538b9ea2a3e9cedca3f;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/super.c b/fs/super.c index ed080c4..1527e6a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -28,7 +28,6 @@ #include #include #include -#include /* for fsync_super() */ #include #include #include @@ -38,7 +37,7 @@ #include #include #include -#include +#include #include #include "internal.h" @@ -56,7 +55,7 @@ DEFINE_SPINLOCK(sb_lock); static struct super_block *alloc_super(struct file_system_type *type) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); - static struct super_operations default_op; + static const struct super_operations default_op; if (s) { if (security_sb_alloc(s)) { @@ -64,15 +63,11 @@ static struct super_block *alloc_super(struct file_system_type *type) s = NULL; goto out; } - INIT_LIST_HEAD(&s->s_dirty); - INIT_LIST_HEAD(&s->s_io); - INIT_LIST_HEAD(&s->s_more_io); INIT_LIST_HEAD(&s->s_files); INIT_LIST_HEAD(&s->s_instances); INIT_HLIST_HEAD(&s->s_anon); INIT_LIST_HEAD(&s->s_inodes); INIT_LIST_HEAD(&s->s_dentry_lru); - INIT_LIST_HEAD(&s->s_async_list); init_rwsem(&s->s_umount); mutex_init(&s->s_lock); lockdep_set_class(&s->s_umount, &type->s_umount_key); @@ -82,7 +77,22 @@ static struct super_block *alloc_super(struct file_system_type *type) * lock ordering than usbfs: */ lockdep_set_class(&s->s_lock, &type->s_lock_key); - down_write(&s->s_umount); + /* + * sget() can have s_umount recursion. + * + * When it cannot find a suitable sb, it allocates a new + * one (this one), and tries again to find a suitable old + * one. + * + * In case that succeeds, it will acquire the s_umount + * lock of the old one. Since these are clearly distrinct + * locks, and this object isn't exposed yet, there's no + * risk of deadlocks. + * + * Annotate this by putting this lock in a different + * subclass. + */ + down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); s->s_count = S_BIAS; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); @@ -159,7 +169,7 @@ int __put_super_and_need_restart(struct super_block *sb) * Drops a temporary reference, frees superblock if there's no * references left. */ -static void put_super(struct super_block *sb) +void put_super(struct super_block *sb) { spin_lock(&sb_lock); __put_super(sb); @@ -182,7 +192,7 @@ void deactivate_super(struct super_block *s) if (atomic_dec_and_lock(&s->s_active, &sb_lock)) { s->s_count -= S_BIAS-1; spin_unlock(&sb_lock); - DQUOT_OFF(s, 0); + vfs_dq_off(s, 0); down_write(&s->s_umount); fs->kill_sb(s); put_filesystem(fs); @@ -193,6 +203,34 @@ void deactivate_super(struct super_block *s) EXPORT_SYMBOL(deactivate_super); /** + * deactivate_locked_super - drop an active reference to superblock + * @s: superblock to deactivate + * + * Equivalent of up_write(&s->s_umount); deactivate_super(s);, except that + * it does not unlock it until it's all over. As the result, it's safe to + * use to dispose of new superblock on ->get_sb() failure exits - nobody + * will see the sucker until it's all over. Equivalent using up_write + + * deactivate_super is safe for that purpose only if superblock is either + * safe to use or has NULL ->s_root when we unlock. + */ +void deactivate_locked_super(struct super_block *s) +{ + struct file_system_type *fs = s->s_type; + if (atomic_dec_and_lock(&s->s_active, &sb_lock)) { + s->s_count -= S_BIAS-1; + spin_unlock(&sb_lock); + vfs_dq_off(s, 0); + fs->kill_sb(s); + put_filesystem(fs); + put_super(s); + } else { + up_write(&s->s_umount); + } +} + +EXPORT_SYMBOL(deactivate_locked_super); + +/** * grab_super - acquire an active reference * @s: reference we are trying to make active * @@ -242,37 +280,6 @@ void unlock_super(struct super_block * sb) 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 @@ -294,21 +301,13 @@ void generic_shutdown_super(struct super_block *sb) if (sb->s_root) { shrink_dcache_for_umount(sb); - fsync_super(sb); - lock_super(sb); + sync_filesystem(sb); + get_fs_excl(); sb->s_flags &= ~MS_ACTIVE; - /* - * wait for asynchronous fs operations to finish before going further - */ - async_synchronize_full_special(&sb->s_async_list); - /* bad name - it should be evict_inodes() */ invalidate_inodes(sb); - lock_kernel(); - if (sop->write_super && sb->s_dirt) - sop->write_super(sb); if (sop->put_super) sop->put_super(sb); @@ -318,9 +317,7 @@ void generic_shutdown_super(struct super_block *sb) "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); } - - unlock_kernel(); - unlock_super(sb); + put_fs_excl(); } spin_lock(&sb_lock); /* should be initialized for __put_super_and_need_restart() */ @@ -356,8 +353,10 @@ retry: continue; if (!grab_super(old)) goto retry; - if (s) + if (s) { + up_write(&s->s_umount); destroy_super(s); + } return old; } } @@ -372,6 +371,7 @@ retry: err = set(s, data); if (err) { spin_unlock(&sb_lock); + up_write(&s->s_umount); destroy_super(s); return ERR_PTR(err); } @@ -394,16 +394,14 @@ void drop_super(struct super_block *sb) EXPORT_SYMBOL(drop_super); -static inline void write_super(struct super_block *sb) -{ - lock_super(sb); - if (sb->s_root && sb->s_dirt) - if (sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); -} - -/* +/** + * sync_supers - helper for periodic superblock writeback + * + * Call the write_super method if present on all dirty superblocks in + * the system. This is for the periodic writeback used by most older + * filesystems. For data integrity superblock writeback use + * sync_filesystems() instead. + * * Note: check the dirty flag before waiting, so we don't * hold up the sync while mounting a device. (The newly * mounted device won't need syncing.) @@ -415,12 +413,15 @@ void sync_supers(void) spin_lock(&sb_lock); restart: list_for_each_entry(sb, &super_blocks, s_list) { - if (sb->s_dirt) { + if (sb->s_op->write_super && sb->s_dirt) { sb->s_count++; spin_unlock(&sb_lock); + down_read(&sb->s_umount); - write_super(sb); + if (sb->s_root && sb->s_dirt) + sb->s_op->write_super(sb); up_read(&sb->s_umount); + spin_lock(&sb_lock); if (__put_super_and_need_restart(sb)) goto restart; @@ -429,60 +430,6 @@ restart: spin_unlock(&sb_lock); } -/* - * Call the ->sync_fs super_op against all filesystems which are r/w and - * which implement it. - * - * This operation is careful to avoid the livelock which could easily happen - * if two or more filesystems are being continuously dirtied. s_need_sync_fs - * is used only here. We set it against all filesystems and then clear it as - * we sync them. So redirtied filesystems are skipped. - * - * But if process A is currently running sync_filesystems and then process B - * calls sync_filesystems as well, process B will set all the s_need_sync_fs - * flags again, which will cause process A to resync everything. Fix that with - * a local mutex. - * - * (Fabian) Avoid sync_fs with clean fs & wait mode 0 - */ -void sync_filesystems(int wait) -{ - struct super_block *sb; - static DEFINE_MUTEX(mutex); - - 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) - continue; - if (sb->s_flags & MS_RDONLY) - continue; - sb->s_need_sync_fs = 1; - } - -restart: - list_for_each_entry(sb, &super_blocks, s_list) { - if (!sb->s_need_sync_fs) - continue; - sb->s_need_sync_fs = 0; - if (sb->s_flags & MS_RDONLY) - continue; /* hm. Was remounted r/o meanwhile */ - sb->s_count++; - spin_unlock(&sb_lock); - down_read(&sb->s_umount); - async_synchronize_full_special(&sb->s_async_list); - if (sb->s_root && (wait || sb->s_dirt)) - sb->s_op->sync_fs(sb, wait); - up_read(&sb->s_umount); - /* restart only when sb is no longer on the list */ - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; - } - spin_unlock(&sb_lock); - mutex_unlock(&mutex); -} - /** * get_super - get the superblock of a device * @bdev: device to get the superblock for @@ -519,6 +466,48 @@ rescan: } EXPORT_SYMBOL(get_super); + +/** + * get_active_super - get an active reference to the superblock of a device + * @bdev: device to get the superblock for + * + * Scans the superblock list and finds the superblock of the file system + * mounted on the device given. Returns the superblock with an active + * reference and s_umount held exclusively or %NULL if none was found. + */ +struct super_block *get_active_super(struct block_device *bdev) +{ + struct super_block *sb; + + if (!bdev) + return NULL; + + spin_lock(&sb_lock); + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_bdev != bdev) + continue; + + sb->s_count++; + spin_unlock(&sb_lock); + down_write(&sb->s_umount); + if (sb->s_root) { + spin_lock(&sb_lock); + if (sb->s_count > S_BIAS) { + atomic_inc(&sb->s_active); + sb->s_count--; + spin_unlock(&sb_lock); + return sb; + } + spin_unlock(&sb_lock); + } + up_write(&sb->s_umount); + put_super(sb); + yield(); + spin_lock(&sb_lock); + } + spin_unlock(&sb_lock); + return NULL; +} struct super_block * user_get_super(dev_t dev) { @@ -544,7 +533,7 @@ rescan: return NULL; } -asmlinkage long sys_ustat(unsigned dev, struct ustat __user * ubuf) +SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) { struct super_block *s; struct ustat tmp; @@ -569,45 +558,6 @@ out: } /** - * mark_files_ro - mark all files read-only - * @sb: superblock in question - * - * All files are marked read-only. We don't care about pending - * delete files so this should be used in 'force' mode only. - */ - -static void mark_files_ro(struct super_block *sb) -{ - struct file *f; - -retry: - file_list_lock(); - list_for_each_entry(f, &sb->s_files, f_u.fu_list) { - struct vfsmount *mnt; - if (!S_ISREG(f->f_path.dentry->d_inode->i_mode)) - continue; - if (!file_count(f)) - continue; - if (!(f->f_mode & FMODE_WRITE)) - continue; - f->f_mode &= ~FMODE_WRITE; - if (file_check_writeable(f) != 0) - continue; - file_release_write(f); - mnt = mntget(f->f_path.mnt); - file_list_unlock(); - /* - * This can sleep, so we can't hold - * the file_list_lock() spinlock. - */ - mnt_drop_write(mnt); - mntput(mnt); - goto retry; - } - file_list_unlock(); -} - -/** * do_remount_sb - asks filesystem to change mount options. * @sb: superblock in question * @flags: numeric part of options @@ -619,44 +569,58 @@ retry: int do_remount_sb(struct super_block *sb, int flags, void *data, int force) { int retval; - int remount_rw; - + int remount_rw, remount_ro; + + if (sb->s_frozen != SB_UNFROZEN) + return -EBUSY; + #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); - fsync_super(sb); + sync_filesystem(sb); + + remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY); + remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY); /* If we are remounting RDONLY and current sb is read/write, make sure there are no rw files opened */ - if ((flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY)) { + if (remount_ro) { if (force) mark_files_ro(sb); else if (!fs_may_remount_ro(sb)) return -EBUSY; - retval = DQUOT_OFF(sb, 1); + retval = vfs_dq_off(sb, 1); if (retval < 0 && retval != -ENOSYS) return -EBUSY; } - remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY); if (sb->s_op->remount_fs) { - lock_super(sb); retval = sb->s_op->remount_fs(sb, &flags, data); - unlock_super(sb); if (retval) return retval; } sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK); if (remount_rw) - DQUOT_ON_REMOUNT(sb); + vfs_dq_quota_on_remount(sb); + /* + * Some filesystems modify their metadata via some other path than the + * bdev buffer cache (eg. use a private mapping, or directories in + * pagecache, etc). Also file data modifications go via their own + * mappings. So If we try to mount readonly then copy the filesystem + * from bdev, we could get stale data, so invalidate it to give a best + * effort at coherency. + */ + if (remount_ro && sb->s_bdev) + invalidate_bdev(sb->s_bdev); return 0; } -static void do_emergency_remount(unsigned long foo) +static void do_emergency_remount(struct work_struct *work) { struct super_block *sb; @@ -664,27 +628,33 @@ static void do_emergency_remount(unsigned long foo) list_for_each_entry(sb, &super_blocks, s_list) { sb->s_count++; spin_unlock(&sb_lock); - down_read(&sb->s_umount); + down_write(&sb->s_umount); if (sb->s_root && sb->s_bdev && !(sb->s_flags & MS_RDONLY)) { /* * ->remount_fs needs lock_kernel(). * * What lock protects sb->s_flags?? */ - lock_kernel(); do_remount_sb(sb, MS_RDONLY, NULL, 1); - unlock_kernel(); } - drop_super(sb); + up_write(&sb->s_umount); + put_super(sb); spin_lock(&sb_lock); } spin_unlock(&sb_lock); + kfree(work); printk("Emergency Remount complete\n"); } void emergency_remount(void) { - pdflush_operation(do_emergency_remount, 0); + struct work_struct *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + INIT_WORK(work, do_emergency_remount); + schedule_work(work); + } } /* @@ -694,6 +664,7 @@ void emergency_remount(void) static DEFINE_IDA(unnamed_dev_ida); static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */ +static int unnamed_dev_start = 0; /* don't bother trying below it */ int set_anon_super(struct super_block *s, void *data) { @@ -704,7 +675,9 @@ int set_anon_super(struct super_block *s, void *data) if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0) return -ENOMEM; spin_lock(&unnamed_dev_lock); - error = ida_get_new(&unnamed_dev_ida, &dev); + error = ida_get_new_above(&unnamed_dev_ida, unnamed_dev_start, &dev); + if (!error) + unnamed_dev_start = dev + 1; spin_unlock(&unnamed_dev_lock); if (error == -EAGAIN) /* We raced and lost with another CPU. */ @@ -715,10 +688,13 @@ int set_anon_super(struct super_block *s, void *data) if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) { spin_lock(&unnamed_dev_lock); ida_remove(&unnamed_dev_ida, dev); + if (unnamed_dev_start > dev) + unnamed_dev_start = dev; spin_unlock(&unnamed_dev_lock); return -EMFILE; } s->s_dev = MKDEV(0, dev & MINORMASK); + s->s_bdi = &noop_backing_dev_info; return 0; } @@ -731,6 +707,8 @@ void kill_anon_super(struct super_block *sb) generic_shutdown_super(sb); spin_lock(&unnamed_dev_lock); ida_remove(&unnamed_dev_ida, slot); + if (slot < unnamed_dev_start) + unnamed_dev_start = slot; spin_unlock(&unnamed_dev_lock); } @@ -745,11 +723,56 @@ void kill_litter_super(struct super_block *sb) EXPORT_SYMBOL(kill_litter_super); +static int ns_test_super(struct super_block *sb, void *data) +{ + return sb->s_fs_info == data; +} + +static int ns_set_super(struct super_block *sb, void *data) +{ + sb->s_fs_info = data; + return set_anon_super(sb, NULL); +} + +int get_sb_ns(struct file_system_type *fs_type, int flags, void *data, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) +{ + struct super_block *sb; + + sb = sget(fs_type, ns_test_super, ns_set_super, data); + if (IS_ERR(sb)) + return PTR_ERR(sb); + + if (!sb->s_root) { + int err; + sb->s_flags = flags; + err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); + if (err) { + deactivate_locked_super(sb); + return err; + } + + sb->s_flags |= MS_ACTIVE; + } + + simple_set_mnt(mnt, sb); + return 0; +} + +EXPORT_SYMBOL(get_sb_ns); + #ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; + + /* + * We set the bdi here to the queue backing, file systems can + * overwrite this in ->fill_super() + */ + s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } @@ -780,16 +803,20 @@ int get_sb_bdev(struct file_system_type *fs_type, * will protect the lockfs code from trying to start a snapshot * while we are mounting */ - down(&bdev->bd_mount_sem); + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (bdev->bd_fsfreeze_count > 0) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + error = -EBUSY; + goto error_bdev; + } s = sget(fs_type, test_bdev_super, set_bdev_super, bdev); - up(&bdev->bd_mount_sem); + mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) goto error_s; if (s->s_root) { if ((flags ^ s->s_flags) & MS_RDONLY) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = -EBUSY; goto error_bdev; } @@ -804,8 +831,7 @@ int get_sb_bdev(struct file_system_type *fs_type, sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto error; } @@ -813,7 +839,8 @@ int get_sb_bdev(struct file_system_type *fs_type, bdev->bd_super = s; } - return simple_set_mnt(mnt, s); + simple_set_mnt(mnt, s); + return 0; error_s: error = PTR_ERR(s); @@ -830,7 +857,7 @@ void kill_block_super(struct super_block *sb) struct block_device *bdev = sb->s_bdev; fmode_t mode = sb->s_mode; - bdev->bd_super = 0; + bdev->bd_super = NULL; generic_shutdown_super(sb); sync_blockdev(bdev); close_bdev_exclusive(bdev, mode); @@ -854,12 +881,12 @@ int get_sb_nodev(struct file_system_type *fs_type, error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); return error; } s->s_flags |= MS_ACTIVE; - return simple_set_mnt(mnt, s); + simple_set_mnt(mnt, s); + return 0; } EXPORT_SYMBOL(get_sb_nodev); @@ -884,14 +911,15 @@ int get_sb_single(struct file_system_type *fs_type, s->s_flags = flags; error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); return error; } s->s_flags |= MS_ACTIVE; + } else { + do_remount_sb(s, flags, data, 0); } - do_remount_sb(s, flags, data, 0); - return simple_set_mnt(mnt, s); + simple_set_mnt(mnt, s); + return 0; } EXPORT_SYMBOL(get_sb_single); @@ -911,6 +939,9 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (!mnt) goto out; + if (flags & MS_KERNMOUNT) + mnt->mnt_flags = MNT_INTERNAL; + if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) { secdata = alloc_secdata(); if (!secdata) @@ -925,10 +956,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (error < 0) goto out_free_secdata; BUG_ON(!mnt->mnt_sb); + WARN_ON(!mnt->mnt_sb->s_bdi); - error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata); - if (error) - goto out_sb; + error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata); + if (error) + goto out_sb; + + /* + * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE + * but s_maxbytes was an unsigned long long for many releases. Throw + * this warning for a little while to try and catch filesystems that + * violate this rule. This warning should be either removed or + * converted to a BUG() in 2.6.34. + */ + WARN((mnt->mnt_sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " + "negative value (%lld)\n", type->name, mnt->mnt_sb->s_maxbytes); mnt->mnt_mountpoint = mnt->mnt_root; mnt->mnt_parent = mnt; @@ -937,8 +979,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void return mnt; out_sb: dput(mnt->mnt_root); - up_write(&mnt->mnt_sb->s_umount); - deactivate_super(mnt->mnt_sb); + deactivate_locked_super(mnt->mnt_sb); out_free_secdata: free_secdata(secdata); out_mnt: