fs: Improve filesystem freezing handling

#include <linux/rculist_bl.h>

#include <linux/cleancache.h>

#include <linux/fsnotify.h>

#include <linux/lockdep.h>

#include "internal.h"

LIST_HEAD(super_blocks);

DEFINE_SPINLOCK(sb_lock);

static char *sb_writers_name[SB_FREEZE_LEVELS] = {

	"sb_writers",

	"sb_pagefaults",

	"sb_internal",

};

/*

 * 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.

	return total_objects;

}

static int init_sb_writers(struct super_block *s, struct file_system_type *type)

{

	int err;

	int i;

	for (i = 0; i < SB_FREEZE_LEVELS; i++) {

		err = percpu_counter_init(&s->s_writers.counter[i], 0);

		if (err < 0)

			goto err_out;

		lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],

				 &type->s_writers_key[i], 0);

	}

	init_waitqueue_head(&s->s_writers.wait);

	init_waitqueue_head(&s->s_writers.wait_unfrozen);

	return 0;

err_out:

	while (--i >= 0)

		percpu_counter_destroy(&s->s_writers.counter[i]);

	return err;

}

static void destroy_sb_writers(struct super_block *s)

{

	int i;

	for (i = 0; i < SB_FREEZE_LEVELS; i++)

		percpu_counter_destroy(&s->s_writers.counter[i]);

}

/**

 *	alloc_super	-	create new superblock

 *	@type:	filesystem type superblock should belong to

	if (s) {

		if (security_sb_alloc(s)) {

			/*

			 * We cannot call security_sb_free() without

			 * security_sb_alloc() succeeding. So bail out manually

			 */

			kfree(s);

			s = NULL;

			goto out;

		}

#ifdef CONFIG_SMP

		s->s_files = alloc_percpu(struct list_head);

		if (!s->s_files) {

			security_sb_free(s);

			kfree(s);

			s = NULL;

			goto out;

		} else {

		if (!s->s_files)

			goto err_out;

		else {

			int i;

			for_each_possible_cpu(i)

#else

		INIT_LIST_HEAD(&s->s_files);

#endif

		if (init_sb_writers(s, type))

			goto err_out;

		s->s_flags = flags;

		s->s_bdi = &default_backing_dev_info;

		INIT_HLIST_NODE(&s->s_instances);

	}

out:

	return s;

err_out:

	security_sb_free(s);

#ifdef CONFIG_SMP

	if (s->s_files)

		free_percpu(s->s_files);

#endif

	destroy_sb_writers(s);

	kfree(s);

	s = NULL;

	goto out;

}

/**

#ifdef CONFIG_SMP

	free_percpu(s->s_files);

#endif

	destroy_sb_writers(s);

	security_sb_free(s);

	WARN_ON(!list_empty(&s->s_mounts));

	kfree(s->s_subtype);

{

	while (1) {

		struct super_block *s = get_super(bdev);

		if (!s || s->s_frozen == SB_UNFROZEN)

		if (!s || s->s_writers.frozen == SB_UNFROZEN)

			return s;

		up_read(&s->s_umount);

		vfs_check_frozen(s, SB_FREEZE_WRITE);

		wait_event(s->s_writers.wait_unfrozen,

			   s->s_writers.frozen == SB_UNFROZEN);

		put_super(s);

	}

}

	int retval;

	int remount_ro;

	if (sb->s_frozen != SB_UNFROZEN)

	if (sb->s_writers.frozen != SB_UNFROZEN)

		return -EBUSY;

#ifdef CONFIG_BLOCK

	return ERR_PTR(error);

}

/*

 * This is an internal function, please use sb_end_{write,pagefault,intwrite}

 * instead.

 */

void __sb_end_write(struct super_block *sb, int level)

{

	percpu_counter_dec(&sb->s_writers.counter[level-1]);

	/*

	 * Make sure s_writers are updated before we wake up waiters in

	 * freeze_super().

	 */

	smp_mb();

	if (waitqueue_active(&sb->s_writers.wait))

		wake_up(&sb->s_writers.wait);

	rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_);

}

EXPORT_SYMBOL(__sb_end_write);

#ifdef CONFIG_LOCKDEP

/*

 * We want lockdep to tell us about possible deadlocks with freezing but

 * it's it bit tricky to properly instrument it. Getting a freeze protection

 * works as getting a read lock but there are subtle problems. XFS for example

 * gets freeze protection on internal level twice in some cases, which is OK

 * only because we already hold a freeze protection also on higher level. Due

 * to these cases we have to tell lockdep we are doing trylock when we

 * already hold a freeze protection for a higher freeze level.

 */

static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock,

				unsigned long ip)

{

	int i;

	if (!trylock) {

		for (i = 0; i < level - 1; i++)

			if (lock_is_held(&sb->s_writers.lock_map[i])) {

				trylock = true;

				break;

			}

	}

	rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip);

}

#endif

/*

 * This is an internal function, please use sb_start_{write,pagefault,intwrite}

 * instead.

 */

int __sb_start_write(struct super_block *sb, int level, bool wait)

{

retry:

	if (unlikely(sb->s_writers.frozen >= level)) {

		if (!wait)

			return 0;

		wait_event(sb->s_writers.wait_unfrozen,

			   sb->s_writers.frozen < level);

	}

#ifdef CONFIG_LOCKDEP

	acquire_freeze_lock(sb, level, !wait, _RET_IP_);

#endif

	percpu_counter_inc(&sb->s_writers.counter[level-1]);

	/*

	 * Make sure counter is updated before we check for frozen.

	 * freeze_super() first sets frozen and then checks the counter.

	 */

	smp_mb();

	if (unlikely(sb->s_writers.frozen >= level)) {

		__sb_end_write(sb, level);

		goto retry;

	}

	return 1;

}

EXPORT_SYMBOL(__sb_start_write);

/**

 * sb_wait_write - wait until all writers to given file system finish

 * @sb: the super for which we wait

 * @level: type of writers we wait for (normal vs page fault)

 *

 * This function waits until there are no writers of given type to given file

 * system. Caller of this function should make sure there can be no new writers

 * of type @level before calling this function. Otherwise this function can

 * livelock.

 */

static void sb_wait_write(struct super_block *sb, int level)

{

	s64 writers;

	/*

	 * We just cycle-through lockdep here so that it does not complain

	 * about returning with lock to userspace

	 */

	rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_);

	rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_);

	do {

		DEFINE_WAIT(wait);

		/*

		 * We use a barrier in prepare_to_wait() to separate setting

		 * of frozen and checking of the counter

		 */

		prepare_to_wait(&sb->s_writers.wait, &wait,

				TASK_UNINTERRUPTIBLE);

		writers = percpu_counter_sum(&sb->s_writers.counter[level-1]);

		if (writers)

			schedule();

		finish_wait(&sb->s_writers.wait, &wait);

	} while (writers);

}

/**

 * freeze_super - lock the filesystem and force it into a consistent state

 * @sb: the super to lock

 * 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

 * -EBUSY.

 *

 * During this function, sb->s_writers.frozen goes through these values:

 *

 * SB_UNFROZEN: File system is normal, all writes progress as usual.

 *

 * SB_FREEZE_WRITE: The file system is in the process of being frozen.  New

 * writes should be blocked, though page faults are still allowed. We wait for

 * all writes to complete and then proceed to the next stage.

 *

 * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked

 * but internal fs threads can still modify the filesystem (although they

 * should not dirty new pages or inodes), writeback can run etc. After waiting

 * for all running page faults we sync the filesystem which will clean all

 * dirty pages and inodes (no new dirty pages or inodes can be created when

 * sync is running).

 *

 * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs

 * modification are blocked (e.g. XFS preallocation truncation on inode

 * reclaim). This is usually implemented by blocking new transactions for

 * filesystems that have them and need this additional guard. After all

 * internal writers are finished we call ->freeze_fs() to finish filesystem

 * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is

 * mostly auxiliary for filesystems to verify they do not modify frozen fs.

 *

 * sb->s_writers.frozen is protected by sb->s_umount.

 */

int freeze_super(struct super_block *sb)

{

	atomic_inc(&sb->s_active);

	down_write(&sb->s_umount);

	if (sb->s_frozen) {

	if (sb->s_writers.frozen != SB_UNFROZEN) {

		deactivate_locked_super(sb);

		return -EBUSY;

	}

	}

	if (sb->s_flags & MS_RDONLY) {

		sb->s_frozen = SB_FREEZE_TRANS;

		smp_wmb();

		/* Nothing to do really... */

		sb->s_writers.frozen = SB_FREEZE_COMPLETE;

		up_write(&sb->s_umount);

		return 0;

	}

	sb->s_frozen = SB_FREEZE_WRITE;

	/* From now on, no new normal writers can start */

	sb->s_writers.frozen = SB_FREEZE_WRITE;

	smp_wmb();

	/* Release s_umount to preserve sb_start_write -> s_umount ordering */

	up_write(&sb->s_umount);

	sb_wait_write(sb, SB_FREEZE_WRITE);

	/* Now we go and block page faults... */

	down_write(&sb->s_umount);

	sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;

	smp_wmb();

	sb_wait_write(sb, SB_FREEZE_PAGEFAULT);

	/* All writers are done so after syncing there won't be dirty data */

	sync_filesystem(sb);

	sb->s_frozen = SB_FREEZE_TRANS;

	/* Now wait for internal filesystem counter */

	sb->s_writers.frozen = SB_FREEZE_FS;

	smp_wmb();

	sb_wait_write(sb, SB_FREEZE_FS);

	sync_blockdev(sb->s_bdev);

	if (sb->s_op->freeze_fs) {

		ret = sb->s_op->freeze_fs(sb);

		if (ret) {

			printk(KERN_ERR

				"VFS:Filesystem freeze failed\n");

			sb->s_frozen = SB_UNFROZEN;

			sb->s_writers.frozen = SB_UNFROZEN;

			smp_wmb();

			wake_up(&sb->s_wait_unfrozen);

			wake_up(&sb->s_writers.wait_unfrozen);

			deactivate_locked_super(sb);

			return ret;

		}

	}

	/*

	 * This is just for debugging purposes so that fs can warn if it

	 * sees write activity when frozen is set to SB_FREEZE_COMPLETE.

	 */

	sb->s_writers.frozen = SB_FREEZE_COMPLETE;

	up_write(&sb->s_umount);

	return 0;

}

	int error;

	down_write(&sb->s_umount);

	if (sb->s_frozen == SB_UNFROZEN) {

	if (sb->s_writers.frozen == SB_UNFROZEN) {

		up_write(&sb->s_umount);

		return -EINVAL;

	}

		if (error) {

			printk(KERN_ERR

				"VFS:Filesystem thaw failed\n");

			sb->s_frozen = SB_FREEZE_TRANS;

			up_write(&sb->s_umount);

			return error;

		}

	}

out:

	sb->s_frozen = SB_UNFROZEN;

	sb->s_writers.frozen = SB_UNFROZEN;

	smp_wmb();

	wake_up(&sb->s_wait_unfrozen);

	wake_up(&sb->s_writers.wait_unfrozen);

	deactivate_locked_super(sb);

	return 0;

#include <linux/shrinker.h>

#include <linux/migrate_mode.h>

#include <linux/uidgid.h>

#include <linux/lockdep.h>

#include <asm/byteorder.h>

extern pid_t f_getown(struct file *filp);

extern int send_sigurg(struct fown_struct *fown);

struct mm_struct;

/*

 *	Umount options

 */

extern struct list_head super_blocks;

extern spinlock_t sb_lock;

/* Possible states of 'frozen' field */

enum {

	SB_UNFROZEN = 0,		/* FS is unfrozen */

	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */

	SB_FREEZE_TRANS = 2,

	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */

	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop

					 * internal threads if needed) */

	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */

};

#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)

struct sb_writers {

	/* Counters for counting writers at each level */

	struct percpu_counter	counter[SB_FREEZE_LEVELS];

	wait_queue_head_t	wait;		/* queue for waiting for

						   writers / faults to finish */

	int			frozen;		/* Is sb frozen? */

	wait_queue_head_t	wait_unfrozen;	/* queue for waiting for

						   sb to be thawed */

#ifdef CONFIG_DEBUG_LOCK_ALLOC

	struct lockdep_map	lock_map[SB_FREEZE_LEVELS];

#endif

};

struct super_block {

	struct list_head	s_list;		/* Keep this first */

	dev_t			s_dev;		/* search index; _not_ kdev_t */

	int			s_frozen;

	wait_queue_head_t	s_wait_unfrozen;

	struct sb_writers	s_writers;

	char s_id[32];				/* Informational name */

	u8 s_uuid[16];				/* UUID */

/*

 * Snapshotting support.

 */

enum {

	SB_UNFROZEN = 0,

	SB_FREEZE_WRITE	= 1,

	SB_FREEZE_TRANS = 2,

};

/* Will go away when all users are converted */

#define vfs_check_frozen(sb, level) do { } while (0)

void __sb_end_write(struct super_block *sb, int level);

int __sb_start_write(struct super_block *sb, int level, bool wait);

/**

 * sb_end_write - drop write access to a superblock

 * @sb: the super we wrote to

 *

 * Decrement number of writers to the filesystem. Wake up possible waiters

 * wanting to freeze the filesystem.

 */

static inline void sb_end_write(struct super_block *sb)

{

	__sb_end_write(sb, SB_FREEZE_WRITE);

}

/**

 * sb_end_pagefault - drop write access to a superblock from a page fault

 * @sb: the super we wrote to

 *

 * Decrement number of processes handling write page fault to the filesystem.

 * Wake up possible waiters wanting to freeze the filesystem.

 */

static inline void sb_end_pagefault(struct super_block *sb)

{

	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);

}

/**

 * sb_end_intwrite - drop write access to a superblock for internal fs purposes

 * @sb: the super we wrote to

 *

 * Decrement fs-internal number of writers to the filesystem.  Wake up possible

 * waiters wanting to freeze the filesystem.

 */

static inline void sb_end_intwrite(struct super_block *sb)

{

	__sb_end_write(sb, SB_FREEZE_FS);

}

/**

 * sb_start_write - get write access to a superblock

 * @sb: the super we write to

 *

 * When a process wants to write data or metadata to a file system (i.e. dirty

 * a page or an inode), it should embed the operation in a sb_start_write() -

 * sb_end_write() pair to get exclusion against file system freezing. This

 * function increments number of writers preventing freezing. If the file

 * system is already frozen, the function waits until the file system is

 * thawed.

 *

 * Since freeze protection behaves as a lock, users have to preserve

 * ordering of freeze protection and other filesystem locks. Generally,

 * freeze protection should be the outermost lock. In particular, we have:

 *

 * sb_start_write

 *   -> i_mutex			(write path, truncate, directory ops, ...)

 *   -> s_umount		(freeze_super, thaw_super)

 */

static inline void sb_start_write(struct super_block *sb)

{

	__sb_start_write(sb, SB_FREEZE_WRITE, true);

}

static inline int sb_start_write_trylock(struct super_block *sb)

{

	return __sb_start_write(sb, SB_FREEZE_WRITE, false);

}

/**

 * sb_start_pagefault - get write access to a superblock from a page fault

 * @sb: the super we write to

 *

 * When a process starts handling write page fault, it should embed the

 * operation into sb_start_pagefault() - sb_end_pagefault() pair to get

 * exclusion against file system freezing. This is needed since the page fault

 * is going to dirty a page. This function increments number of running page

 * faults preventing freezing. If the file system is already frozen, the

 * function waits until the file system is thawed.

 *

 * Since page fault freeze protection behaves as a lock, users have to preserve

 * ordering of freeze protection and other filesystem locks. It is advised to

 * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault

 * handling code implies lock dependency:

 *

 * mmap_sem

 *   -> sb_start_pagefault

 */

static inline void sb_start_pagefault(struct super_block *sb)

{

	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);

}

/*

 * sb_start_intwrite - get write access to a superblock for internal fs purposes

 * @sb: the super we write to

 *

 * This is the third level of protection against filesystem freezing. It is

 * free for use by a filesystem. The only requirement is that it must rank

 * below sb_start_pagefault.

 *

 * For example filesystem can call sb_start_intwrite() when starting a

 * transaction which somewhat eases handling of freezing for internal sources

 * of filesystem changes (internal fs threads, discarding preallocation on file

 * close, etc.).

 */

static inline void sb_start_intwrite(struct super_block *sb)

{

	__sb_start_write(sb, SB_FREEZE_FS, true);

}

#define vfs_check_frozen(sb, level) \

	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))

extern bool inode_owner_or_capable(const struct inode *inode);

	struct lock_class_key s_lock_key;

	struct lock_class_key s_umount_key;

	struct lock_class_key s_vfs_rename_key;

	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];

	struct lock_class_key i_lock_key;

	struct lock_class_key i_mutex_key;