diff options
Diffstat (limited to 'fs/super.c')
| -rw-r--r-- | fs/super.c | 1583 |
1 files changed, 1043 insertions, 540 deletions
diff --git a/fs/super.c b/fs/super.c index 12c08cb20405..3d85265d1400 100644 --- a/fs/super.c +++ b/fs/super.c @@ -39,7 +39,8 @@ #include <uapi/linux/mount.h> #include "internal.h" -static int thaw_super_locked(struct super_block *sb); +static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner); static LIST_HEAD(super_blocks); static DEFINE_SPINLOCK(sb_lock); @@ -50,11 +51,128 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = { "sb_internal", }; +static inline void __super_lock(struct super_block *sb, bool excl) +{ + if (excl) + down_write(&sb->s_umount); + else + down_read(&sb->s_umount); +} + +static inline void super_unlock(struct super_block *sb, bool excl) +{ + if (excl) + up_write(&sb->s_umount); + else + up_read(&sb->s_umount); +} + +static inline void __super_lock_excl(struct super_block *sb) +{ + __super_lock(sb, true); +} + +static inline void super_unlock_excl(struct super_block *sb) +{ + super_unlock(sb, true); +} + +static inline void super_unlock_shared(struct super_block *sb) +{ + super_unlock(sb, false); +} + +static bool super_flags(const struct super_block *sb, unsigned int flags) +{ + /* + * Pairs with smp_store_release() in super_wake() and ensures + * that we see @flags after we're woken. + */ + return smp_load_acquire(&sb->s_flags) & flags; +} + +/** + * super_lock - wait for superblock to become ready and lock it + * @sb: superblock to wait for + * @excl: whether exclusive access is required + * + * If the superblock has neither passed through vfs_get_tree() or + * generic_shutdown_super() yet wait for it to happen. Either superblock + * creation will succeed and SB_BORN is set by vfs_get_tree() or we're + * woken and we'll see SB_DYING. + * + * The caller must have acquired a temporary reference on @sb->s_count. + * + * Return: The function returns true if SB_BORN was set and with + * s_umount held. The function returns false if SB_DYING was + * set and without s_umount held. + */ +static __must_check bool super_lock(struct super_block *sb, bool excl) +{ + lockdep_assert_not_held(&sb->s_umount); + + /* wait until the superblock is ready or dying */ + wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING)); + + /* Don't pointlessly acquire s_umount. */ + if (super_flags(sb, SB_DYING)) + return false; + + __super_lock(sb, excl); + + /* + * Has gone through generic_shutdown_super() in the meantime. + * @sb->s_root is NULL and @sb->s_active is 0. No one needs to + * grab a reference to this. Tell them so. + */ + if (sb->s_flags & SB_DYING) { + super_unlock(sb, excl); + return false; + } + + WARN_ON_ONCE(!(sb->s_flags & SB_BORN)); + return true; +} + +/* wait and try to acquire read-side of @sb->s_umount */ +static inline bool super_lock_shared(struct super_block *sb) +{ + return super_lock(sb, false); +} + +/* wait and try to acquire write-side of @sb->s_umount */ +static inline bool super_lock_excl(struct super_block *sb) +{ + return super_lock(sb, true); +} + +/* wake waiters */ +#define SUPER_WAKE_FLAGS (SB_BORN | SB_DYING | SB_DEAD) +static void super_wake(struct super_block *sb, unsigned int flag) +{ + WARN_ON_ONCE((flag & ~SUPER_WAKE_FLAGS)); + WARN_ON_ONCE(hweight32(flag & SUPER_WAKE_FLAGS) > 1); + + /* + * Pairs with smp_load_acquire() in super_lock() to make sure + * all initializations in the superblock are seen by the user + * seeing SB_BORN sent. + */ + smp_store_release(&sb->s_flags, sb->s_flags | flag); + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees SB_BORN set or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ + smp_mb(); + wake_up_var(&sb->s_flags); +} + /* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the - * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we + * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, @@ -67,7 +185,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, long dentries; long inodes; - sb = container_of(shrink, struct super_block, s_shrink); + sb = shrink->private_data; /* * Deadlock avoidance. We may hold various FS locks, and we don't want @@ -76,7 +194,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, if (!(sc->gfp_mask & __GFP_FS)) return SHRINK_STOP; - if (!trylock_super(sb)) + if (!super_trylock_shared(sb)) return SHRINK_STOP; if (sb->s_op->nr_cached_objects) @@ -84,7 +202,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, inodes = list_lru_shrink_count(&sb->s_inode_lru, sc); dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc); - total_objects = dentries + inodes + fs_objects + 1; + total_objects = dentries + inodes + fs_objects; if (!total_objects) total_objects = 1; @@ -110,7 +228,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, freed += sb->s_op->free_cached_objects(sb, sc); } - up_read(&sb->s_umount); + super_unlock_shared(sb); return freed; } @@ -120,20 +238,20 @@ static unsigned long super_cache_count(struct shrinker *shrink, struct super_block *sb; long total_objects = 0; - sb = container_of(shrink, struct super_block, s_shrink); + sb = shrink->private_data; /* - * We don't call trylock_super() here as it is a scalability bottleneck, - * so we're exposed to partial setup state. The shrinker rwsem does not - * protect filesystem operations backing list_lru_shrink_count() or - * s_op->nr_cached_objects(). Counts can change between - * super_cache_count and super_cache_scan, so we really don't need locks - * here. + * We don't call super_trylock_shared() here as it is a scalability + * bottleneck, so we're exposed to partial setup state. The shrinker + * rwsem does not protect filesystem operations backing + * list_lru_shrink_count() or s_op->nr_cached_objects(). Counts can + * change between super_cache_count and super_cache_scan, so we really + * don't need locks here. * * However, if we are currently mounting the superblock, the underlying * filesystem might be in a state of partial construction and hence it - * is dangerous to access it. trylock_super() uses a SB_BORN check to - * avoid this situation, so do the same here. The memory barrier is + * is dangerous to access it. super_trylock_shared() uses a SB_BORN check + * to avoid this situation, so do the same here. The memory barrier is * matched with the one in mount_fs() as we don't hold locks here. */ if (!(sb->s_flags & SB_BORN)) @@ -157,9 +275,11 @@ static void destroy_super_work(struct work_struct *work) { struct super_block *s = container_of(work, struct super_block, destroy_work); - int i; - - for (i = 0; i < SB_FREEZE_LEVELS; i++) + fsnotify_sb_free(s); + security_sb_free(s); + put_user_ns(s->s_user_ns); + kfree(s->s_subtype); + for (int i = 0; i < SB_FREEZE_LEVELS; i++) percpu_free_rwsem(&s->s_writers.rw_sem[i]); kfree(s); } @@ -176,13 +296,10 @@ static void destroy_unused_super(struct super_block *s) { if (!s) return; - up_write(&s->s_umount); + super_unlock_excl(s); list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); - security_sb_free(s); - put_user_ns(s->s_user_ns); - kfree(s->s_subtype); - free_prealloced_shrinker(&s->s_shrink); + shrinker_free(s->s_shrink); /* no delays needed */ destroy_super_work(&s->destroy_work); } @@ -199,14 +316,13 @@ static void destroy_unused_super(struct super_block *s) static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { - struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); + struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL); static const struct super_operations default_op; int i; if (!s) return NULL; - INIT_LIST_HEAD(&s->s_mounts); s->s_user_ns = get_user_ns(user_ns); init_rwsem(&s->s_umount); lockdep_set_class(&s->s_umount, &type->s_umount_key); @@ -236,7 +352,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, &type->s_writers_key[i])) goto fail; } - init_waitqueue_head(&s->s_writers.wait_unfrozen); s->s_bdi = &noop_backing_dev_info; s->s_flags = flags; if (s->s_user_ns != &init_user_ns) @@ -260,17 +375,21 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; - s->s_shrink.seeks = DEFAULT_SEEKS; - s->s_shrink.scan_objects = super_cache_scan; - s->s_shrink.count_objects = super_cache_count; - s->s_shrink.batch = 1024; - s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE; - if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name)) + s->s_shrink = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, + "sb-%s", type->name); + if (!s->s_shrink) goto fail; - if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) + + s->s_shrink->scan_objects = super_cache_scan; + s->s_shrink->count_objects = super_cache_count; + s->s_shrink->batch = 1024; + s->s_shrink->private_data = s; + + if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink)) goto fail; - if (list_lru_init_memcg(&s->s_inode_lru, &s->s_shrink)) + if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink)) goto fail; + s->s_min_writeback_pages = MIN_WRITEBACK_PAGES; return s; fail: @@ -289,11 +408,7 @@ static void __put_super(struct super_block *s) list_del_init(&s->s_list); WARN_ON(s->s_dentry_lru.node); WARN_ON(s->s_inode_lru.node); - WARN_ON(!list_empty(&s->s_mounts)); - security_sb_free(s); - fscrypt_destroy_keyring(s); - put_user_ns(s->s_user_ns); - kfree(s->s_subtype); + WARN_ON(s->s_mounts); call_rcu(&s->rcu, destroy_super_rcu); } } @@ -312,6 +427,33 @@ void put_super(struct super_block *sb) spin_unlock(&sb_lock); } +static void kill_super_notify(struct super_block *sb) +{ + lockdep_assert_not_held(&sb->s_umount); + + /* already notified earlier */ + if (sb->s_flags & SB_DEAD) + return; + + /* + * Remove it from @fs_supers so it isn't found by new + * sget{_fc}() walkers anymore. Any concurrent mounter still + * managing to grab a temporary reference is guaranteed to + * already see SB_DYING and will wait until we notify them about + * SB_DEAD. + */ + spin_lock(&sb_lock); + hlist_del_init(&sb->s_instances); + spin_unlock(&sb_lock); + + /* + * Let concurrent mounts know that this thing is really dead. + * We don't need @sb->s_umount here as every concurrent caller + * will see SB_DYING and either discard the superblock or wait + * for SB_DEAD. + */ + super_wake(sb, SB_DEAD); +} /** * deactivate_locked_super - drop an active reference to superblock @@ -328,9 +470,11 @@ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { - unregister_shrinker(&s->s_shrink); + shrinker_free(s->s_shrink); fs->kill_sb(s); + kill_super_notify(s); + /* * Since list_lru_destroy() may sleep, we cannot call it from * put_super(), where we hold the sb_lock. Therefore we destroy @@ -342,7 +486,7 @@ void deactivate_locked_super(struct super_block *s) put_filesystem(fs); put_super(s); } else { - up_write(&s->s_umount); + super_unlock_excl(s); } } @@ -359,7 +503,7 @@ EXPORT_SYMBOL(deactivate_locked_super); void deactivate_super(struct super_block *s) { if (!atomic_add_unless(&s->s_active, -1, 1)) { - down_write(&s->s_umount); + __super_lock_excl(s); deactivate_locked_super(s); } } @@ -367,34 +511,38 @@ void deactivate_super(struct super_block *s) EXPORT_SYMBOL(deactivate_super); /** - * grab_super - acquire an active reference - * @s: reference we are trying to make active + * grab_super - acquire an active reference to a superblock + * @sb: superblock to acquire * - * Tries to acquire an active reference. grab_super() is used when we - * had just found a superblock in super_blocks or fs_type->fs_supers - * and want to turn it into a full-blown active reference. grab_super() - * is called with sb_lock held and drops it. Returns 1 in case of - * success, 0 if we had failed (superblock contents was already dead or - * dying when grab_super() had been called). Note that this is only - * called for superblocks not in rundown mode (== ones still on ->fs_supers - * of their type), so increment of ->s_count is OK here. + * Acquire a temporary reference on a superblock and try to trade it for + * an active reference. This is used in sget{_fc}() to wait for a + * superblock to either become SB_BORN or for it to pass through + * sb->kill() and be marked as SB_DEAD. + * + * Return: This returns true if an active reference could be acquired, + * false if not. */ -static int grab_super(struct super_block *s) __releases(sb_lock) +static bool grab_super(struct super_block *sb) { - s->s_count++; + bool locked; + + sb->s_count++; spin_unlock(&sb_lock); - down_write(&s->s_umount); - if ((s->s_flags & SB_BORN) && atomic_inc_not_zero(&s->s_active)) { - put_super(s); - return 1; + locked = super_lock_excl(sb); + if (locked) { + if (atomic_inc_not_zero(&sb->s_active)) { + put_super(sb); + return true; + } + super_unlock_excl(sb); } - up_write(&s->s_umount); - put_super(s); - return 0; + wait_var_event(&sb->s_flags, super_flags(sb, SB_DEAD)); + put_super(sb); + return false; } /* - * trylock_super - try to grab ->s_umount shared + * super_trylock_shared - try to grab ->s_umount shared * @sb: reference we are trying to grab * * Try to prevent fs shutdown. This is used in places where we @@ -410,13 +558,13 @@ static int grab_super(struct super_block *s) __releases(sb_lock) * of down_read(). There's a couple of places that are OK with that, but * it's very much not a general-purpose interface. */ -bool trylock_super(struct super_block *sb) +bool super_trylock_shared(struct super_block *sb) { if (down_read_trylock(&sb->s_umount)) { - if (!hlist_unhashed(&sb->s_instances) && - sb->s_root && (sb->s_flags & SB_BORN)) + if (!(sb->s_flags & SB_DYING) && sb->s_root && + (sb->s_flags & SB_BORN)) return true; - up_read(&sb->s_umount); + super_unlock_shared(sb); } return false; @@ -441,13 +589,13 @@ bool trylock_super(struct super_block *sb) void retire_super(struct super_block *sb) { WARN_ON(!sb->s_bdev); - down_write(&sb->s_umount); + __super_lock_excl(sb); if (sb->s_iflags & SB_I_PERSB_BDI) { bdi_unregister(sb->s_bdi); sb->s_iflags &= ~SB_I_PERSB_BDI; } sb->s_iflags |= SB_I_RETIRED; - up_write(&sb->s_umount); + super_unlock_excl(sb); } EXPORT_SYMBOL(retire_super); @@ -474,13 +622,16 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - cgroup_writeback_umount(); + cgroup_writeback_umount(sb); - /* evict all inodes with zero refcount */ + /* Evict all inodes with zero refcount. */ evict_inodes(sb); - /* only nonzero refcount inodes can have marks */ + + /* + * Clean up and evict any inodes that still have references due + * to fsnotify or the security policy. + */ fsnotify_sb_delete(sb); - fscrypt_destroy_keyring(sb); security_sb_delete(sb); if (sb->s_dio_done_wq) { @@ -491,17 +642,42 @@ void generic_shutdown_super(struct super_block *sb) if (sop->put_super) sop->put_super(sb); - if (!list_empty(&sb->s_inodes)) { - printk("VFS: Busy inodes after unmount of %s. " - "Self-destruct in 5 seconds. Have a nice day...\n", - sb->s_id); + /* + * Now that all potentially-encrypted inodes have been evicted, + * the fscrypt keyring can be destroyed. + */ + fscrypt_destroy_keyring(sb); + + if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), NULL, + "VFS: Busy inodes after unmount of %s (%s)", + sb->s_id, sb->s_type->name)) { + /* + * Adding a proper bailout path here would be hard, but + * we can at least make it more likely that a later + * iput_final() or such crashes cleanly. + */ + struct inode *inode; + + spin_lock(&sb->s_inode_list_lock); + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + inode->i_op = VFS_PTR_POISON; + inode->i_sb = VFS_PTR_POISON; + inode->i_mapping = VFS_PTR_POISON; + } + spin_unlock(&sb->s_inode_list_lock); } } - spin_lock(&sb_lock); - /* should be initialized for __put_super_and_need_restart() */ - hlist_del_init(&sb->s_instances); - spin_unlock(&sb_lock); - up_write(&sb->s_umount); + /* + * Broadcast to everyone that grabbed a temporary reference to this + * superblock before we removed it from @fs_supers that the superblock + * is dying. Every walker of @fs_supers outside of sget{_fc}() will now + * discard this superblock and treat it as dead. + * + * We leave the superblock on @fs_supers so it can be found by + * sget{_fc}() until we passed sb->kill_sb(). + */ + super_wake(sb, SB_DYING); + super_unlock_excl(sb); if (sb->s_bdi != &noop_backing_dev_info) { if (sb->s_iflags & SB_I_PERSB_BDI) bdi_unregister(sb->s_bdi); @@ -526,17 +702,31 @@ bool mount_capable(struct fs_context *fc) * @test: Comparison callback * @set: Setup callback * - * Find or create a superblock using the parameters stored in the filesystem - * context and the two callback functions. + * Create a new superblock or find an existing one. + * + * The @test callback is used to find a matching existing superblock. + * Whether or not the requested parameters in @fc are taken into account + * is specific to the @test callback that is used. They may even be + * completely ignored. + * + * If an extant superblock is matched, it will be returned unless: + * + * (1) the namespace the filesystem context @fc and the extant + * superblock's namespace differ + * + * (2) the filesystem context @fc has requested that reusing an extant + * superblock is not allowed * - * If an extant superblock is matched, then that will be returned with an - * elevated reference count that the caller must transfer or discard. + * In both cases EBUSY will be returned. * * If no match is made, a new superblock will be allocated and basic - * initialisation will be performed (s_type, s_fs_info and s_id will be set and - * the set() callback will be invoked), the superblock will be published and it - * will be returned in a partially constructed state with SB_BORN and SB_ACTIVE - * as yet unset. + * initialisation will be performed (s_type, s_fs_info and s_id will be + * set and the @set callback will be invoked), the superblock will be + * published and it will be returned in a partially constructed state + * with SB_BORN and SB_ACTIVE as yet unset. + * + * Return: On success, an extant or newly created superblock is + * returned. On failure an error pointer is returned. */ struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), @@ -547,6 +737,17 @@ struct super_block *sget_fc(struct fs_context *fc, struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns; int err; + /* + * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is + * not set, as the filesystem is likely unprepared to handle it. + * This can happen when fsconfig() is called from init_user_ns with + * an fs_fd opened in another user namespace. + */ + if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) { + errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed"); + return ERR_PTR(-EPERM); + } + retry: spin_lock(&sb_lock); if (test) { @@ -574,18 +775,27 @@ retry: fc->s_fs_info = NULL; s->s_type = fc->fs_type; s->s_iflags |= fc->s_iflags; - strlcpy(s->s_id, s->s_type->name, sizeof(s->s_id)); + strscpy(s->s_id, s->s_type->name, sizeof(s->s_id)); + /* + * Make the superblock visible on @super_blocks and @fs_supers. + * It's in a nascent state and users should wait on SB_BORN or + * SB_DYING to be set. + */ list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &s->s_type->fs_supers); spin_unlock(&sb_lock); get_filesystem(s->s_type); - register_shrinker_prepared(&s->s_shrink); + shrinker_register(s->s_shrink); return s; share_extant_sb: - if (user_ns != old->s_user_ns) { + if (user_ns != old->s_user_ns || fc->exclusive) { spin_unlock(&sb_lock); destroy_unused_super(s); + if (fc->exclusive) + warnfc(fc, "reusing existing filesystem not allowed"); + else + warnfc(fc, "reusing existing filesystem in another namespace not allowed"); return ERR_PTR(-EBUSY); } if (!grab_super(old)) @@ -614,13 +824,6 @@ struct super_block *sget(struct file_system_type *type, struct super_block *old; int err; - /* We don't yet pass the user namespace of the parent - * mount through to here so always use &init_user_ns - * until that changes. - */ - if (flags & SB_SUBMOUNT) - user_ns = &init_user_ns; - retry: spin_lock(&sb_lock); if (test) { @@ -640,7 +843,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns); + s = alloc_super(type, flags, user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -653,19 +856,19 @@ retry: return ERR_PTR(err); } s->s_type = type; - strlcpy(s->s_id, type->name, sizeof(s->s_id)); + strscpy(s->s_id, type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); - register_shrinker_prepared(&s->s_shrink); + shrinker_register(s->s_shrink); return s; } EXPORT_SYMBOL(sget); void drop_super(struct super_block *sb) { - up_read(&sb->s_umount); + super_unlock_shared(sb); put_super(sb); } @@ -673,56 +876,54 @@ EXPORT_SYMBOL(drop_super); void drop_super_exclusive(struct super_block *sb) { - up_write(&sb->s_umount); + super_unlock_excl(sb); put_super(sb); } EXPORT_SYMBOL(drop_super_exclusive); -static void __iterate_supers(void (*f)(struct super_block *)) -{ - struct super_block *sb, *p = NULL; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - sb->s_count++; - spin_unlock(&sb_lock); +enum super_iter_flags_t { + SUPER_ITER_EXCL = (1U << 0), + SUPER_ITER_UNLOCKED = (1U << 1), + SUPER_ITER_REVERSE = (1U << 2), +}; - f(sb); +static inline struct super_block *first_super(enum super_iter_flags_t flags) +{ + if (flags & SUPER_ITER_REVERSE) + return list_last_entry(&super_blocks, struct super_block, s_list); + return list_first_entry(&super_blocks, struct super_block, s_list); +} - spin_lock(&sb_lock); - if (p) - __put_super(p); - p = sb; - } - if (p) - __put_super(p); - spin_unlock(&sb_lock); +static inline struct super_block *next_super(struct super_block *sb, + enum super_iter_flags_t flags) +{ + if (flags & SUPER_ITER_REVERSE) + return list_prev_entry(sb, s_list); + return list_next_entry(sb, s_list); } -/** - * iterate_supers - call function for all active superblocks - * @f: function to call - * @arg: argument to pass to it - * - * Scans the superblock list and calls given function, passing it - * locked superblock and given argument. - */ -void iterate_supers(void (*f)(struct super_block *, void *), void *arg) + +static void __iterate_supers(void (*f)(struct super_block *, void *), void *arg, + enum super_iter_flags_t flags) { struct super_block *sb, *p = NULL; + bool excl = flags & SUPER_ITER_EXCL; - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) + guard(spinlock)(&sb_lock); + + for (sb = first_super(flags); + !list_entry_is_head(sb, &super_blocks, s_list); + sb = next_super(sb, flags)) { + if (super_flags(sb, SB_DYING)) continue; sb->s_count++; spin_unlock(&sb_lock); - down_read(&sb->s_umount); - if (sb->s_root && (sb->s_flags & SB_BORN)) + if (flags & SUPER_ITER_UNLOCKED) { f(sb, arg); - up_read(&sb->s_umount); + } else if (super_lock(sb, excl)) { + f(sb, arg); + super_unlock(sb, excl); + } spin_lock(&sb_lock); if (p) @@ -731,7 +932,11 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) } if (p) __put_super(p); - spin_unlock(&sb_lock); +} + +void iterate_supers(void (*f)(struct super_block *, void *), void *arg) +{ + __iterate_supers(f, arg, 0); } /** @@ -750,13 +955,19 @@ void iterate_supers_type(struct file_system_type *type, spin_lock(&sb_lock); hlist_for_each_entry(sb, &type->fs_supers, s_instances) { + bool locked; + + if (super_flags(sb, SB_DYING)) + continue; + sb->s_count++; spin_unlock(&sb_lock); - down_read(&sb->s_umount); - if (sb->s_root && (sb->s_flags & SB_BORN)) + locked = super_lock_shared(sb); + if (locked) { f(sb, arg); - up_read(&sb->s_umount); + super_unlock_shared(sb); + } spin_lock(&sb_lock); if (p) @@ -770,102 +981,27 @@ void iterate_supers_type(struct file_system_type *type, EXPORT_SYMBOL(iterate_supers_type); -/** - * get_super - get 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. %NULL is returned if no match is found. - */ -struct super_block *get_super(struct block_device *bdev) +struct super_block *user_get_super(dev_t dev, bool excl) { struct super_block *sb; - if (!bdev) - return NULL; - spin_lock(&sb_lock); -rescan: list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - if (sb->s_bdev == bdev) { - sb->s_count++; - spin_unlock(&sb_lock); - down_read(&sb->s_umount); - /* still alive? */ - if (sb->s_root && (sb->s_flags & SB_BORN)) - return sb; - up_read(&sb->s_umount); - /* nope, got unmounted */ - spin_lock(&sb_lock); - __put_super(sb); - goto rescan; - } - } - spin_unlock(&sb_lock); - return NULL; -} + bool locked; -/** - * 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 or %NULL if none was found. - */ -struct super_block *get_active_super(struct block_device *bdev) -{ - struct super_block *sb; + if (sb->s_dev != dev) + continue; - if (!bdev) - return NULL; + sb->s_count++; + spin_unlock(&sb_lock); -restart: - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - if (sb->s_bdev == bdev) { - if (!grab_super(sb)) - goto restart; - up_write(&sb->s_umount); + locked = super_lock(sb, excl); + if (locked) return sb; - } - } - spin_unlock(&sb_lock); - return NULL; -} - -struct super_block *user_get_super(dev_t dev, bool excl) -{ - struct super_block *sb; - spin_lock(&sb_lock); -rescan: - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - if (sb->s_dev == dev) { - sb->s_count++; - spin_unlock(&sb_lock); - if (excl) - down_write(&sb->s_umount); - else - down_read(&sb->s_umount); - /* still alive? */ - if (sb->s_root && (sb->s_flags & SB_BORN)) - return sb; - if (excl) - up_write(&sb->s_umount); - else - up_read(&sb->s_umount); - /* nope, got unmounted */ - spin_lock(&sb_lock); - __put_super(sb); - goto rescan; - } + spin_lock(&sb_lock); + __put_super(sb); + break; } spin_unlock(&sb_lock); return NULL; @@ -882,6 +1018,7 @@ int reconfigure_super(struct fs_context *fc) struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; + bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) @@ -899,15 +1036,15 @@ int reconfigure_super(struct fs_context *fc) bdev_read_only(sb->s_bdev)) return -EACCES; #endif - + remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } if (remount_ro) { if (!hlist_empty(&sb->s_pins)) { - up_write(&sb->s_umount); + super_unlock_excl(sb); group_pin_kill(&sb->s_pins); - down_write(&sb->s_umount); + __super_lock_excl(sb); if (!sb->s_root) return 0; if (sb->s_writers.frozen != SB_UNFROZEN) @@ -922,13 +1059,18 @@ int reconfigure_super(struct fs_context *fc) */ if (remount_ro) { if (force) { - sb->s_readonly_remount = 1; - smp_wmb(); + sb_start_ro_state_change(sb); } else { retval = sb_prepare_remount_readonly(sb); if (retval) return retval; } + } else if (remount_rw) { + /* + * Protect filesystem's reconfigure code from writes from + * userspace until reconfigure finishes. + */ + sb_start_ro_state_change(sb); } if (fc->ops->reconfigure) { @@ -944,9 +1086,7 @@ int reconfigure_super(struct fs_context *fc) WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | (fc->sb_flags & fc->sb_flags_mask))); - /* Needs to be ordered wrt mnt_is_readonly() */ - smp_wmb(); - sb->s_readonly_remount = 0; + sb_end_ro_state_change(sb); /* * Some filesystems modify their metadata via some other path than the @@ -961,15 +1101,13 @@ int reconfigure_super(struct fs_context *fc) return 0; cancel_readonly: - sb->s_readonly_remount = 0; + sb_end_ro_state_change(sb); return retval; } -static void do_emergency_remount_callback(struct super_block *sb) +static void do_emergency_remount_callback(struct super_block *sb, void *unused) { - down_write(&sb->s_umount); - if (sb->s_root && sb->s_bdev && (sb->s_flags & SB_BORN) && - !sb_rdonly(sb)) { + if (sb->s_bdev && !sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, @@ -980,12 +1118,12 @@ static void do_emergency_remount_callback(struct super_block *sb) put_fs_context(fc); } } - up_write(&sb->s_umount); } static void do_emergency_remount(struct work_struct *work) { - __iterate_supers(do_emergency_remount_callback); + __iterate_supers(do_emergency_remount_callback, NULL, + SUPER_ITER_EXCL | SUPER_ITER_REVERSE); kfree(work); printk("Emergency Remount complete\n"); } @@ -1001,20 +1139,18 @@ void emergency_remount(void) } } -static void do_thaw_all_callback(struct super_block *sb) +static void do_thaw_all_callback(struct super_block *sb, void *unused) { - down_write(&sb->s_umount); - if (sb->s_root && sb->s_flags & SB_BORN) { - emergency_thaw_bdev(sb); - thaw_super_locked(sb); - } else { - up_write(&sb->s_umount); - } + if (IS_ENABLED(CONFIG_BLOCK)) + while (sb->s_bdev && !bdev_thaw(sb->s_bdev)) + pr_warn("Emergency Thaw on %pg\n", sb->s_bdev); + thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE, NULL); + return; } static void do_thaw_all(struct work_struct *work) { - __iterate_supers(do_thaw_all_callback); + __iterate_supers(do_thaw_all_callback, NULL, SUPER_ITER_EXCL); kfree(work); printk(KERN_WARNING "Emergency Thaw complete\n"); } @@ -1035,6 +1171,73 @@ void emergency_thaw_all(void) } } +static inline bool get_active_super(struct super_block *sb) +{ + bool active = false; + + if (super_lock_excl(sb)) { + active = atomic_inc_not_zero(&sb->s_active); + super_unlock_excl(sb); + } + return active; +} + +static const char *filesystems_freeze_ptr = "filesystems_freeze"; + +static void filesystems_freeze_callback(struct super_block *sb, void *freeze_all_ptr) +{ + if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) + return; + + if (!freeze_all_ptr && !(sb->s_type->fs_flags & FS_POWER_FREEZE)) + return; + + if (!get_active_super(sb)) + return; + + if (sb->s_op->freeze_super) + sb->s_op->freeze_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + else + freeze_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + + deactivate_super(sb); +} + +void filesystems_freeze(bool freeze_all) +{ + void *freeze_all_ptr = NULL; + + if (freeze_all) + freeze_all_ptr = &freeze_all; + __iterate_supers(filesystems_freeze_callback, freeze_all_ptr, + SUPER_ITER_UNLOCKED | SUPER_ITER_REVERSE); +} + +static void filesystems_thaw_callback(struct super_block *sb, void *unused) +{ + if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) + return; + + if (!get_active_super(sb)) + return; + + if (sb->s_op->thaw_super) + sb->s_op->thaw_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + else + thaw_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + + deactivate_super(sb); +} + +void filesystems_thaw(void) +{ + __iterate_supers(filesystems_thaw_callback, NULL, SUPER_ITER_UNLOCKED); +} + static DEFINE_IDA(unnamed_dev_ida); /** @@ -1084,18 +1287,11 @@ void kill_anon_super(struct super_block *sb) { dev_t dev = sb->s_dev; generic_shutdown_super(sb); + kill_super_notify(sb); free_anon_bdev(dev); } EXPORT_SYMBOL(kill_anon_super); -void kill_litter_super(struct super_block *sb) -{ - if (sb->s_root) - d_genocide(sb->s_root); - kill_anon_super(sb); -} -EXPORT_SYMBOL(kill_litter_super); - int set_anon_super_fc(struct super_block *sb, struct fs_context *fc) { return set_anon_super(sb, NULL); @@ -1112,7 +1308,7 @@ static int test_single_super(struct super_block *s, struct fs_context *fc) return 1; } -static int vfs_get_super(struct fs_context *fc, bool reconf, +static int vfs_get_super(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*fill_super)(struct super_block *sb, struct fs_context *fc)) @@ -1130,19 +1326,9 @@ static int vfs_get_super(struct fs_context *fc, bool reconf, goto error; sb->s_flags |= SB_ACTIVE; - fc->root = dget(sb->s_root); - } else { - fc->root = dget(sb->s_root); - if (reconf) { - err = reconfigure_super(fc); - if (err < 0) { - dput(fc->root); - fc->root = NULL; - goto error; - } - } } + fc->root = dget(sb->s_root); return 0; error: @@ -1154,7 +1340,7 @@ int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { - return vfs_get_super(fc, false, NULL, fill_super); + return vfs_get_super(fc, NULL, fill_super); } EXPORT_SYMBOL(get_tree_nodev); @@ -1162,310 +1348,386 @@ int get_tree_single(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { - return vfs_get_super(fc, false, test_single_super, fill_super); + return vfs_get_super(fc, test_single_super, fill_super); } EXPORT_SYMBOL(get_tree_single); -int get_tree_single_reconf(struct fs_context *fc, - int (*fill_super)(struct super_block *sb, - struct fs_context *fc)) -{ - return vfs_get_super(fc, true, test_single_super, fill_super); -} -EXPORT_SYMBOL(get_tree_single_reconf); - int get_tree_keyed(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), void *key) { fc->s_fs_info = key; - return vfs_get_super(fc, false, test_keyed_super, fill_super); + return vfs_get_super(fc, test_keyed_super, fill_super); } EXPORT_SYMBOL(get_tree_keyed); -#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; - s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi); - - if (bdev_stable_writes(s->s_bdev)) - s->s_iflags |= SB_I_STABLE_WRITES; + s->s_dev = *(dev_t *)data; return 0; } -static int set_bdev_super_fc(struct super_block *s, struct fs_context *fc) +static int super_s_dev_set(struct super_block *s, struct fs_context *fc) { return set_bdev_super(s, fc->sget_key); } -static int test_bdev_super_fc(struct super_block *s, struct fs_context *fc) +static int super_s_dev_test(struct super_block *s, struct fs_context *fc) { - return !(s->s_iflags & SB_I_RETIRED) && s->s_bdev == fc->sget_key; + return !(s->s_iflags & SB_I_RETIRED) && + s->s_dev == *(dev_t *)fc->sget_key; } /** - * get_tree_bdev - Get a superblock based on a single block device - * @fc: The filesystem context holding the parameters - * @fill_super: Helper to initialise a new superblock + * sget_dev - Find or create a superblock by device number + * @fc: Filesystem context. + * @dev: device number + * + * Find or create a superblock using the provided device number that + * will be stored in fc->sget_key. + * + * If an extant superblock is matched, then that will be returned with + * an elevated reference count that the caller must transfer or discard. + * + * If no match is made, a new superblock will be allocated and basic + * initialisation will be performed (s_type, s_fs_info, s_id, s_dev will + * be set). The superblock will be published and it will be returned in + * a partially constructed state with SB_BORN and SB_ACTIVE as yet + * unset. + * + * Return: an existing or newly created superblock on success, an error + * pointer on failure. */ -int get_tree_bdev(struct fs_context *fc, - int (*fill_super)(struct super_block *, - struct fs_context *)) +struct super_block *sget_dev(struct fs_context *fc, dev_t dev) { - struct block_device *bdev; - struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; - int error = 0; + fc->sget_key = &dev; + return sget_fc(fc, super_s_dev_test, super_s_dev_set); +} +EXPORT_SYMBOL(sget_dev); - if (!(fc->sb_flags & SB_RDONLY)) - mode |= FMODE_WRITE; +#ifdef CONFIG_BLOCK +/* + * Lock the superblock that is holder of the bdev. Returns the superblock + * pointer if we successfully locked the superblock and it is alive. Otherwise + * we return NULL and just unlock bdev->bd_holder_lock. + * + * The function must be called with bdev->bd_holder_lock and releases it. + */ +static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl) + __releases(&bdev->bd_holder_lock) +{ + struct super_block *sb = bdev->bd_holder; + bool locked; - if (!fc->source) - return invalf(fc, "No source specified"); + lockdep_assert_held(&bdev->bd_holder_lock); + lockdep_assert_not_held(&sb->s_umount); + lockdep_assert_not_held(&bdev->bd_disk->open_mutex); - bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type); - if (IS_ERR(bdev)) { - errorf(fc, "%s: Can't open blockdev", fc->source); - return PTR_ERR(bdev); - } + /* Make sure sb doesn't go away from under us */ + spin_lock(&sb_lock); + sb->s_count++; + spin_unlock(&sb_lock); - /* Once the superblock is inserted into the list by sget_fc(), s_umount - * will protect the lockfs code from trying to start a snapshot while - * we are mounting - */ - mutex_lock(&bdev->bd_fsfreeze_mutex); - if (bdev->bd_fsfreeze_count > 0) { - mutex_unlock(&bdev->bd_fsfreeze_mutex); - warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - blkdev_put(bdev, mode); - return -EBUSY; - } + mutex_unlock(&bdev->bd_holder_lock); - fc->sb_flags |= SB_NOSEC; - fc->sget_key = bdev; - s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc); - mutex_unlock(&bdev->bd_fsfreeze_mutex); - if (IS_ERR(s)) { - blkdev_put(bdev, mode); - return PTR_ERR(s); - } + locked = super_lock(sb, excl); - if (s->s_root) { - /* Don't summarily change the RO/RW state. */ - if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { - warnf(fc, "%pg: Can't mount, would change RO state", bdev); - deactivate_locked_super(s); - blkdev_put(bdev, mode); - return -EBUSY; - } + /* + * If the superblock wasn't already SB_DYING then we hold + * s_umount and can safely drop our temporary reference. + */ + put_super(sb); - /* - * s_umount nests inside open_mutex during - * __invalidate_device(). blkdev_put() acquires - * open_mutex and can't be called under s_umount. Drop - * s_umount temporarily. This is safe as we're - * holding an active reference. - */ - up_write(&s->s_umount); - blkdev_put(bdev, mode); - down_write(&s->s_umount); - } else { - s->s_mode = mode; - snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); - shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", - fc->fs_type->name, s->s_id); - sb_set_blocksize(s, block_size(bdev)); - error = fill_super(s, fc); - if (error) { - deactivate_locked_super(s); - return error; - } + if (!locked) + return NULL; - s->s_flags |= SB_ACTIVE; - bdev->bd_super = s; + if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) { + super_unlock(sb, excl); + return NULL; } - BUG_ON(fc->root); - fc->root = dget(s->s_root); - return 0; + return sb; } -EXPORT_SYMBOL(get_tree_bdev); -static int test_bdev_super(struct super_block *s, void *data) +static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { - return !(s->s_iflags & SB_I_RETIRED) && (void *)s->s_bdev == data; -} - -struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)) -{ - struct block_device *bdev; - struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; - int error = 0; + struct super_block *sb; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; + sb = bdev_super_lock(bdev, false); + if (!sb) + return; - bdev = blkdev_get_by_path(dev_name, mode, fs_type); - if (IS_ERR(bdev)) - return ERR_CAST(bdev); + if (sb->s_op->remove_bdev) { + int ret; - /* - * once the super is inserted into the list by sget, s_umount - * will protect the lockfs code from trying to start a snapshot - * while we are mounting - */ - mutex_lock(&bdev->bd_fsfreeze_mutex); - if (bdev->bd_fsfreeze_count > 0) { - mutex_unlock(&bdev->bd_fsfreeze_mutex); - error = -EBUSY; - goto error_bdev; + ret = sb->s_op->remove_bdev(sb, bdev); + if (!ret) { + super_unlock_shared(sb); + return; + } + /* Fallback to shutdown. */ } - s = sget(fs_type, test_bdev_super, set_bdev_super, flags | SB_NOSEC, - bdev); - mutex_unlock(&bdev->bd_fsfreeze_mutex); - if (IS_ERR(s)) - goto error_s; - if (s->s_root) { - if ((flags ^ s->s_flags) & SB_RDONLY) { - deactivate_locked_super(s); - error = -EBUSY; - goto error_bdev; - } + if (!surprise) + sync_filesystem(sb); + shrink_dcache_sb(sb); + evict_inodes(sb); + if (sb->s_op->shutdown) + sb->s_op->shutdown(sb); - /* - * s_umount nests inside open_mutex during - * __invalidate_device(). blkdev_put() acquires - * open_mutex and can't be called under s_umount. Drop - * s_umount temporarily. This is safe as we're - * holding an active reference. - */ - up_write(&s->s_umount); - blkdev_put(bdev, mode); - down_write(&s->s_umount); - } else { - s->s_mode = mode; - snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); - shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", - fs_type->name, s->s_id); - sb_set_blocksize(s, block_size(bdev)); - error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); - if (error) { - deactivate_locked_super(s); - goto error; - } + super_unlock_shared(sb); +} - s->s_flags |= SB_ACTIVE; - bdev->bd_super = s; - } +static void fs_bdev_sync(struct block_device *bdev) +{ + struct super_block *sb; - return dget(s->s_root); + sb = bdev_super_lock(bdev, false); + if (!sb) + return; -error_s: - error = PTR_ERR(s); -error_bdev: - blkdev_put(bdev, mode); -error: - return ERR_PTR(error); + sync_filesystem(sb); + super_unlock_shared(sb); } -EXPORT_SYMBOL(mount_bdev); -void kill_block_super(struct super_block *sb) +static struct super_block *get_bdev_super(struct block_device *bdev) { - struct block_device *bdev = sb->s_bdev; - fmode_t mode = sb->s_mode; + bool active = false; + struct super_block *sb; - bdev->bd_super = NULL; - generic_shutdown_super(sb); - sync_blockdev(bdev); - WARN_ON_ONCE(!(mode & FMODE_EXCL)); - blkdev_put(bdev, mode | FMODE_EXCL); + sb = bdev_super_lock(bdev, true); + if (sb) { + active = atomic_inc_not_zero(&sb->s_active); + super_unlock_excl(sb); + } + if (!active) + return NULL; + return sb; } -EXPORT_SYMBOL(kill_block_super); -#endif - -struct dentry *mount_nodev(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)) +/** + * fs_bdev_freeze - freeze owning filesystem of block device + * @bdev: block device + * + * Freeze the filesystem that owns this block device if it is still + * active. + * + * A filesystem that owns multiple block devices may be frozen from each + * block device and won't be unfrozen until all block devices are + * unfrozen. Each block device can only freeze the filesystem once as we + * nest freezes for block devices in the block layer. + * + * Return: If the freeze was successful zero is returned. If the freeze + * failed a negative error code is returned. + */ +static int fs_bdev_freeze(struct block_device *bdev) { - int error; - struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); + struct super_block *sb; + int error = 0; - if (IS_ERR(s)) - return ERR_CAST(s); + lockdep_assert_held(&bdev->bd_fsfreeze_mutex); - error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); - if (error) { - deactivate_locked_super(s); - return ERR_PTR(error); - } - s->s_flags |= SB_ACTIVE; - return dget(s->s_root); + sb = get_bdev_super(bdev); + if (!sb) + return -EINVAL; + + if (sb->s_op->freeze_super) + error = sb->s_op->freeze_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); + else + error = freeze_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); + if (!error) + error = sync_blockdev(bdev); + deactivate_super(sb); + return error; } -EXPORT_SYMBOL(mount_nodev); -int reconfigure_single(struct super_block *s, - int flags, void *data) +/** + * fs_bdev_thaw - thaw owning filesystem of block device + * @bdev: block device + * + * Thaw the filesystem that owns this block device. + * + * A filesystem that owns multiple block devices may be frozen from each + * block device and won't be unfrozen until all block devices are + * unfrozen. Each block device can only freeze the filesystem once as we + * nest freezes for block devices in the block layer. + * + * Return: If the thaw was successful zero is returned. If the thaw + * failed a negative error code is returned. If this function + * returns zero it doesn't mean that the filesystem is unfrozen + * as it may have been frozen multiple times (kernel may hold a + * freeze or might be frozen from other block devices). + */ +static int fs_bdev_thaw(struct block_device *bdev) { - struct fs_context *fc; - int ret; + struct super_block *sb; + int error; - /* The caller really need to be passing fc down into mount_single(), - * then a chunk of this can be removed. [Bollocks -- AV] - * Better yet, reconfiguration shouldn't happen, but rather the second - * mount should be rejected if the parameters are not compatible. - */ - fc = fs_context_for_reconfigure(s->s_root, flags, MS_RMT_MASK); - if (IS_ERR(fc)) - return PTR_ERR(fc); + lockdep_assert_held(&bdev->bd_fsfreeze_mutex); - ret = parse_monolithic_mount_data(fc, data); - if (ret < 0) - goto out; + /* + * The block device may have been frozen before it was claimed by a + * filesystem. Concurrently another process might try to mount that + * frozen block device and has temporarily claimed the block device for + * that purpose causing a concurrent fs_bdev_thaw() to end up here. The + * mounter is already about to abort mounting because they still saw an + * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return + * NULL in that case. + */ + sb = get_bdev_super(bdev); + if (!sb) + return -EINVAL; - ret = reconfigure_super(fc); -out: - put_fs_context(fc); - return ret; + if (sb->s_op->thaw_super) + error = sb->s_op->thaw_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); + else + error = thaw_super(sb, + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); + deactivate_super(sb); + return error; } -static int compare_single(struct super_block *s, void *p) +const struct blk_holder_ops fs_holder_ops = { + .mark_dead = fs_bdev_mark_dead, + .sync = fs_bdev_sync, + .freeze = fs_bdev_freeze, + .thaw = fs_bdev_thaw, +}; +EXPORT_SYMBOL_GPL(fs_holder_ops); + +int setup_bdev_super(struct super_block *sb, int sb_flags, + struct fs_context *fc) { - return 1; + blk_mode_t mode = sb_open_mode(sb_flags); + struct file *bdev_file; + struct block_device *bdev; + + bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); + if (IS_ERR(bdev_file)) { + if (fc) + errorf(fc, "%s: Can't open blockdev", fc->source); + return PTR_ERR(bdev_file); + } + bdev = file_bdev(bdev_file); + + /* + * This really should be in blkdev_get_by_dev, but right now can't due + * to legacy issues that require us to allow opening a block device node + * writable from userspace even for a read-only block device. + */ + if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { + bdev_fput(bdev_file); + return -EACCES; + } + + /* + * It is enough to check bdev was not frozen before we set + * s_bdev as freezing will wait until SB_BORN is set. + */ + if (atomic_read(&bdev->bd_fsfreeze_count) > 0) { + if (fc) + warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); + bdev_fput(bdev_file); + return -EBUSY; + } + spin_lock(&sb_lock); + sb->s_bdev_file = bdev_file; + sb->s_bdev = bdev; + sb->s_bdi = bdi_get(bdev->bd_disk->bdi); + if (bdev_stable_writes(bdev)) + sb->s_iflags |= SB_I_STABLE_WRITES; + spin_unlock(&sb_lock); + + snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); + shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name, + sb->s_id); + sb_set_blocksize(sb, block_size(bdev)); + return 0; } +EXPORT_SYMBOL_GPL(setup_bdev_super); -struct dentry *mount_single(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)) +/** + * get_tree_bdev_flags - Get a superblock based on a single block device + * @fc: The filesystem context holding the parameters + * @fill_super: Helper to initialise a new superblock + * @flags: GET_TREE_BDEV_* flags + */ +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags) { struct super_block *s; - int error; + int error = 0; + dev_t dev; - s = sget(fs_type, compare_single, set_anon_super, flags, NULL); + if (!fc->source) + return invalf(fc, "No source specified"); + + error = lookup_bdev(fc->source, &dev); + if (error) { + if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP)) + errorf(fc, "%s: Can't lookup blockdev", fc->source); + return error; + } + fc->sb_flags |= SB_NOSEC; + s = sget_dev(fc, dev); if (IS_ERR(s)) - return ERR_CAST(s); - if (!s->s_root) { - error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); - if (!error) - s->s_flags |= SB_ACTIVE; + return PTR_ERR(s); + + if (s->s_root) { + /* Don't summarily change the RO/RW state. */ + if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { + warnf(fc, "%pg: Can't mount, would change RO state", s->s_bdev); + deactivate_locked_super(s); + return -EBUSY; + } } else { - error = reconfigure_single(s, flags, data); + error = setup_bdev_super(s, fc->sb_flags, fc); + if (!error) + error = fill_super(s, fc); + if (error) { + deactivate_locked_super(s); + return error; + } + s->s_flags |= SB_ACTIVE; } - if (unlikely(error)) { - deactivate_locked_super(s); - return ERR_PTR(error); + + BUG_ON(fc->root); + fc->root = dget(s->s_root); + return 0; +} +EXPORT_SYMBOL_GPL(get_tree_bdev_flags); + +/** + * get_tree_bdev - Get a superblock based on a single block device + * @fc: The filesystem context holding the parameters + * @fill_super: Helper to initialise a new superblock + */ +int get_tree_bdev(struct fs_context *fc, + int (*fill_super)(struct super_block *, + struct fs_context *)) +{ + return get_tree_bdev_flags(fc, fill_super, 0); +} +EXPORT_SYMBOL(get_tree_bdev); + +void kill_block_super(struct super_block *sb) +{ + struct block_device *bdev = sb->s_bdev; + + generic_shutdown_super(sb); + if (bdev) { + sync_blockdev(bdev); + bdev_fput(sb->s_bdev_file); } - return dget(s->s_root); } -EXPORT_SYMBOL(mount_single); + +EXPORT_SYMBOL(kill_block_super); +#endif /** * vfs_get_tree - Get the mountable root @@ -1491,8 +1753,8 @@ int vfs_get_tree(struct fs_context *fc) return error; if (!fc->root) { - pr_err("Filesystem %s get_tree() didn't set fc->root\n", - fc->fs_type->name); + pr_err("Filesystem %s get_tree() didn't set fc->root, returned %i\n", + fc->fs_type->name, error); /* We don't know what the locking state of the superblock is - * if there is a superblock. */ @@ -1503,13 +1765,13 @@ int vfs_get_tree(struct fs_context *fc) WARN_ON(!sb->s_bdi); /* - * Write barrier is for super_cache_count(). We place it before setting - * SB_BORN as the data dependency between the two functions is the - * superblock structure contents that we just set up, not the SB_BORN - * flag. + * super_wake() contains a memory barrier which also care of + * ordering for super_cache_count(). We place it before setting + * SB_BORN as the data dependency between the two functions is + * the superblock structure contents that we just set up, not + * the SB_BORN flag. */ - smp_wmb(); - sb->s_flags |= SB_BORN; + super_wake(sb, SB_BORN); error = security_sb_set_mnt_opts(sb, fc->security, 0, NULL); if (unlikely(error)) { @@ -1594,7 +1856,7 @@ static void lockdep_sb_freeze_release(struct super_block *sb) int level; for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) - percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_); + percpu_rwsem_release(sb->s_writers.rw_sem + level, _THIS_IP_); } /* @@ -1614,14 +1876,166 @@ static void sb_freeze_unlock(struct super_block *sb, int level) percpu_up_write(sb->s_writers.rw_sem + level); } +static int wait_for_partially_frozen(struct super_block *sb) +{ + int ret = 0; + + do { + unsigned short old = sb->s_writers.frozen; + + up_write(&sb->s_umount); + ret = wait_var_event_killable(&sb->s_writers.frozen, + sb->s_writers.frozen != old); + down_write(&sb->s_umount); + } while (ret == 0 && + sb->s_writers.frozen != SB_UNFROZEN && + sb->s_writers.frozen != SB_FREEZE_COMPLETE); + + return ret; +} + +#define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE) +#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST | FREEZE_EXCL) + +static inline int freeze_inc(struct super_block *sb, enum freeze_holder who) +{ + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if (who & FREEZE_HOLDER_KERNEL) + ++sb->s_writers.freeze_kcount; + if (who & FREEZE_HOLDER_USERSPACE) + ++sb->s_writers.freeze_ucount; + return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; +} + +static inline int freeze_dec(struct super_block *sb, enum freeze_holder who) +{ + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount) + --sb->s_writers.freeze_kcount; + if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount) + --sb->s_writers.freeze_ucount; + return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; +} + +static inline bool may_freeze(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) +{ + lockdep_assert_held(&sb->s_umount); + + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if (who & FREEZE_EXCL) { + if (WARN_ON_ONCE(!(who & FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(who & ~(FREEZE_EXCL | FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(!freeze_owner)) + return false; + /* This freeze already has a specific owner. */ + if (sb->s_writers.freeze_owner) + return false; + /* + * This is already frozen multiple times so we're just + * going to take a reference count and mark the freeze as + * being owned by the caller. + */ + if (sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount) + sb->s_writers.freeze_owner = freeze_owner; + return true; + } + + if (who & FREEZE_HOLDER_KERNEL) + return (who & FREEZE_MAY_NEST) || + sb->s_writers.freeze_kcount == 0; + if (who & FREEZE_HOLDER_USERSPACE) + return (who & FREEZE_MAY_NEST) || + sb->s_writers.freeze_ucount == 0; + return false; +} + +static inline bool may_unfreeze(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) +{ + lockdep_assert_held(&sb->s_umount); + + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if (who & FREEZE_EXCL) { + if (WARN_ON_ONCE(!(who & FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(who & ~(FREEZE_EXCL | FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(!freeze_owner)) + return false; + if (WARN_ON_ONCE(sb->s_writers.freeze_kcount == 0)) + return false; + /* This isn't exclusively frozen. */ + if (!sb->s_writers.freeze_owner) + return false; + /* This isn't exclusively frozen by us. */ + if (sb->s_writers.freeze_owner != freeze_owner) + return false; + /* + * This is still frozen multiple times so we're just + * going to drop our reference count and undo our + * exclusive freeze. + */ + if ((sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount) > 1) + sb->s_writers.freeze_owner = NULL; + return true; + } + + if (who & FREEZE_HOLDER_KERNEL) { + /* + * Someone's trying to steal the reference belonging to + * @sb->s_writers.freeze_owner. + */ + if (sb->s_writers.freeze_kcount == 1 && + sb->s_writers.freeze_owner) + return false; + return sb->s_writers.freeze_kcount > 0; + } + + if (who & FREEZE_HOLDER_USERSPACE) + return sb->s_writers.freeze_ucount > 0; + + return false; +} + /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock + * @who: context that wants to freeze + * @freeze_owner: owner of the freeze * * Syncs the super to make sure the filesystem is consistent and calls the fs's - * freeze_fs. Subsequent calls to this without first thawing the fs will return + * freeze_fs. Subsequent calls to this without first thawing the fs may return * -EBUSY. * + * @who should be: + * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs; + * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs. + * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed. + * + * The @who argument distinguishes between the kernel and userspace trying to + * freeze the filesystem. Although there cannot be multiple kernel freezes or + * multiple userspace freezes in effect at any given time, the kernel and + * userspace can both hold a filesystem frozen. The filesystem remains frozen + * until there are no kernel or userspace freezes in effect. + * + * A filesystem may hold multiple devices and thus a filesystems may be + * frozen through the block layer via multiple block devices. In this + * case the request is marked as being allowed to nest by passing + * FREEZE_MAY_NEST. The filesystem remains frozen until all block + * devices are unfrozen. If multiple freezes are attempted without + * FREEZE_MAY_NEST -EBUSY will be returned. + * * During this function, sb->s_writers.frozen goes through these values: * * SB_UNFROZEN: File system is normal, all writes progress as usual. @@ -1646,35 +2060,56 @@ static void sb_freeze_unlock(struct super_block *sb, int level) * mostly auxiliary for filesystems to verify they do not modify frozen fs. * * sb->s_writers.frozen is protected by sb->s_umount. + * + * Return: If the freeze was successful zero is returned. If the freeze + * failed a negative error code is returned. */ -int freeze_super(struct super_block *sb) +int freeze_super(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { int ret; + if (!super_lock_excl(sb)) { + WARN_ON_ONCE("Dying superblock while freezing!"); + return -EINVAL; + } atomic_inc(&sb->s_active); - down_write(&sb->s_umount); - if (sb->s_writers.frozen != SB_UNFROZEN) { + +retry: + if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) { + if (may_freeze(sb, who, freeze_owner)) + ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1); + else + ret = -EBUSY; + /* All freezers share a single active reference. */ deactivate_locked_super(sb); - return -EBUSY; + return ret; } - if (!(sb->s_flags & SB_BORN)) { - up_write(&sb->s_umount); - return 0; /* sic - it's "nothing to do" */ + if (sb->s_writers.frozen != SB_UNFROZEN) { + ret = wait_for_partially_frozen(sb); + if (ret) { + deactivate_locked_super(sb); + return ret; + } + + goto retry; } if (sb_rdonly(sb)) { /* Nothing to do really... */ + WARN_ON_ONCE(freeze_inc(sb, who) > 1); + sb->s_writers.freeze_owner = freeze_owner; sb->s_writers.frozen = SB_FREEZE_COMPLETE; - up_write(&sb->s_umount); + wake_up_var(&sb->s_writers.frozen); + super_unlock_excl(sb); return 0; } sb->s_writers.frozen = SB_FREEZE_WRITE; /* Release s_umount to preserve sb_start_write -> s_umount ordering */ - up_write(&sb->s_umount); + super_unlock_excl(sb); sb_wait_write(sb, SB_FREEZE_WRITE); - down_write(&sb->s_umount); + __super_lock_excl(sb); /* Now we go and block page faults... */ sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; @@ -1685,7 +2120,7 @@ int freeze_super(struct super_block *sb) if (ret) { sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); - wake_up(&sb->s_writers.wait_unfrozen); + wake_up_var(&sb->s_writers.frozen); deactivate_locked_super(sb); return ret; } @@ -1701,7 +2136,7 @@ int freeze_super(struct super_block *sb) "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_FS); - wake_up(&sb->s_writers.wait_unfrozen); + wake_up_var(&sb->s_writers.frozen); deactivate_locked_super(sb); return ret; } @@ -1710,25 +2145,45 @@ int freeze_super(struct super_block *sb) * For debugging purposes so that fs can warn if it sees write activity * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ + WARN_ON_ONCE(freeze_inc(sb, who) > 1); + sb->s_writers.freeze_owner = freeze_owner; sb->s_writers.frozen = SB_FREEZE_COMPLETE; + wake_up_var(&sb->s_writers.frozen); lockdep_sb_freeze_release(sb); - up_write(&sb->s_umount); + super_unlock_excl(sb); return 0; } EXPORT_SYMBOL(freeze_super); -static int thaw_super_locked(struct super_block *sb) +/* + * Undoes the effect of a freeze_super_locked call. If the filesystem is + * frozen both by userspace and the kernel, a thaw call from either source + * removes that state without releasing the other state or unlocking the + * filesystem. + */ +static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { - int error; + int error = -EINVAL; - if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) { - up_write(&sb->s_umount); - return -EINVAL; - } + if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) + goto out_unlock; + + if (!may_unfreeze(sb, who, freeze_owner)) + goto out_unlock; + + /* + * All freezers share a single active reference. + * So just unlock in case there are any left. + */ + if (freeze_dec(sb, who)) + goto out_unlock; if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; - goto out; + sb->s_writers.freeze_owner = NULL; + wake_up_var(&sb->s_writers.frozen); + goto out_deactivate; } lockdep_sb_freeze_acquire(sb); @@ -1736,31 +2191,79 @@ static int thaw_super_locked(struct super_block *sb) if (sb->s_op->unfreeze_fs) { error = sb->s_op->unfreeze_fs(sb); if (error) { - printk(KERN_ERR - "VFS:Filesystem thaw failed\n"); + pr_err("VFS: Filesystem thaw failed\n"); + freeze_inc(sb, who); lockdep_sb_freeze_release(sb); - up_write(&sb->s_umount); - return error; + goto out_unlock; } } sb->s_writers.frozen = SB_UNFROZEN; + sb->s_writers.freeze_owner = NULL; + wake_up_var(&sb->s_writers.frozen); sb_freeze_unlock(sb, SB_FREEZE_FS); -out: - wake_up(&sb->s_writers.wait_unfrozen); +out_deactivate: deactivate_locked_super(sb); return 0; + +out_unlock: + super_unlock_excl(sb); + return error; } /** * thaw_super -- unlock filesystem * @sb: the super to thaw + * @who: context that wants to freeze + * @freeze_owner: owner of the freeze + * + * Unlocks the filesystem and marks it writeable again after freeze_super() + * if there are no remaining freezes on the filesystem. + * + * @who should be: + * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs; + * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs. + * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed * - * Unlocks the filesystem and marks it writeable again after freeze_super(). + * A filesystem may hold multiple devices and thus a filesystems may + * have been frozen through the block layer via multiple block devices. + * The filesystem remains frozen until all block devices are unfrozen. */ -int thaw_super(struct super_block *sb) +int thaw_super(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { - down_write(&sb->s_umount); - return thaw_super_locked(sb); + if (!super_lock_excl(sb)) { + WARN_ON_ONCE("Dying superblock while thawing!"); + return -EINVAL; + } + return thaw_super_locked(sb, who, freeze_owner); } EXPORT_SYMBOL(thaw_super); + +/* + * Create workqueue for deferred direct IO completions. We allocate the + * workqueue when it's first needed. This avoids creating workqueue for + * filesystems that don't need it and also allows us to create the workqueue + * late enough so the we can include s_id in the name of the workqueue. + */ +int sb_init_dio_done_wq(struct super_block *sb) +{ + struct workqueue_struct *old; + struct workqueue_struct *wq = alloc_workqueue("dio/%s", + WQ_MEM_RECLAIM | WQ_PERCPU, + 0, + sb->s_id); + if (!wq) + return -ENOMEM; + + old = NULL; + /* + * This has to be atomic as more DIOs can race to create the workqueue + */ + if (!try_cmpxchg(&sb->s_dio_done_wq, &old, wq)) { + /* Someone created workqueue before us? Free ours... */ + destroy_workqueue(wq); + } + return 0; +} +EXPORT_SYMBOL_GPL(sb_init_dio_done_wq); |