int i;
for (i = 0; i < SB_FREEZE_LEVELS; i++)
- percpu_counter_destroy(&s->s_writers.counter[i]);
+ percpu_free_rwsem(&s->s_writers.rw_sem[i]);
kfree(s);
}
goto fail;
for (i = 0; i < SB_FREEZE_LEVELS; i++) {
- if (percpu_counter_init(&s->s_writers.counter[i], 0,
- GFP_KERNEL) < 0)
+ if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
+ sb_writers_name[i],
+ &type->s_writers_key[i]))
goto fail;
- 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);
s->s_bdi = &noop_backing_dev_info;
s->s_flags = flags;
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
+ mutex_init(&s->s_sync_lock);
INIT_LIST_HEAD(&s->s_inodes);
+ spin_lock_init(&s->s_inode_list_lock);
if (list_lru_init_memcg(&s->s_dentry_lru))
goto fail;
sync_filesystem(sb);
sb->s_flags &= ~MS_ACTIVE;
- fsnotify_unmount_inodes(&sb->s_inodes);
+ fsnotify_unmount_inodes(sb);
evict_inodes(sb);
*/
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_);
+ percpu_up_read(sb->s_writers.rw_sem + level-1);
}
EXPORT_SYMBOL(__sb_end_write);
-static int do_sb_start_write(struct super_block *sb, int level, bool wait,
- unsigned long ip)
-{
- if (wait)
- rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, 0, ip);
-retry:
- if (unlikely(sb->s_writers.frozen >= level)) {
- if (!wait)
- return 0;
- wait_event(sb->s_writers.wait_unfrozen,
- sb->s_writers.frozen < level);
- }
-
- 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;
- }
-
- if (!wait)
- rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, 1, ip);
- return 1;
-}
-
/*
* 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)
{
bool force_trylock = false;
- int ret;
+ int ret = 1;
#ifdef CONFIG_LOCKDEP
/*
int i;
for (i = 0; i < level - 1; i++)
- if (lock_is_held(&sb->s_writers.lock_map[i])) {
+ if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
force_trylock = true;
break;
}
}
#endif
- ret = do_sb_start_write(sb, level, wait && !force_trylock, _RET_IP_);
+ if (wait && !force_trylock)
+ percpu_down_read(sb->s_writers.rw_sem + level-1);
+ else
+ ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
+
WARN_ON(force_trylock & !ret);
return ret;
}
* @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.
+ * system.
*/
static void sb_wait_write(struct super_block *sb, int level)
{
- s64 writers;
-
- rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_);
+ percpu_down_write(sb->s_writers.rw_sem + level-1);
/*
* We are going to return to userspace and forget about this lock, the
* ownership goes to the caller of thaw_super() which does unlock.
* this leads to lockdep false-positives, so currently we do the early
* release right after acquire.
*/
- rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_);
-
- do {
- DEFINE_WAIT(wait);
+ percpu_rwsem_release(sb->s_writers.rw_sem + level-1, 0, _THIS_IP_);
+}
- /*
- * 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);
+static void sb_freeze_unlock(struct super_block *sb)
+{
+ int level;
- writers = percpu_counter_sum(&sb->s_writers.counter[level-1]);
- if (writers)
- schedule();
+ for (level = 0; level < SB_FREEZE_LEVELS; ++level)
+ percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
- finish_wait(&sb->s_writers.wait, &wait);
- } while (writers);
+ for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
+ percpu_up_write(sb->s_writers.rw_sem + level);
}
/**
return 0;
}
- /* 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);
+ down_write(&sb->s_umount);
/* 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 */
/* Now wait for internal filesystem counter */
sb->s_writers.frozen = SB_FREEZE_FS;
- smp_wmb();
sb_wait_write(sb, SB_FREEZE_FS);
if (sb->s_op->freeze_fs) {
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
sb->s_writers.frozen = SB_UNFROZEN;
- smp_wmb();
+ sb_freeze_unlock(sb);
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return ret;
return -EINVAL;
}
- if (sb->s_flags & MS_RDONLY)
+ if (sb->s_flags & MS_RDONLY) {
+ sb->s_writers.frozen = SB_UNFROZEN;
goto out;
+ }
if (sb->s_op->unfreeze_fs) {
error = sb->s_op->unfreeze_fs(sb);
}
}
-out:
sb->s_writers.frozen = SB_UNFROZEN;
- smp_wmb();
+ sb_freeze_unlock(sb);
+out:
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
-
return 0;
}
EXPORT_SYMBOL(thaw_super);
projects / cascardo / linux.git / blobdiff