Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull quota, fsnotify and ext2 updates from Jan Kara:
 "Changes to locking of some quota operations from dedicated quota mutex
  to s_umount semaphore, a fsnotify fix and a simple ext2 fix"

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  quota: Fix bogus warning in dquot_disable()
  fsnotify: Fix possible use-after-free in inode iteration on umount
  ext2: reject inodes with negative size
  quota: Remove dqonoff_mutex
  ocfs2: Use s_umount for quota recovery protection
  quota: Remove dqonoff_mutex from dquot_scan_active()
  ocfs2: Protect periodic quota syncing with s_umount semaphore
  quota: Use s_umount protection for quota operations
  quota: Hold s_umount in exclusive mode when enabling / disabling quotas
  fs: Provide function to get superblock with exclusive s_umount

fs/ext2/inode.c

@@ -1478,6 +1478,10 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 		inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
 	else
 		ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl);
+	if (i_size_read(inode) < 0) {
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_dtime = 0;
 	inode->i_generation = le32_to_cpu(raw_inode->i_generation);
 	ei->i_state = 0;

fs/notify/inode_mark.c

@@ -150,12 +150,10 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
  */
 void fsnotify_unmount_inodes(struct super_block *sb)
 {
-	struct inode *inode, *next_i, *need_iput = NULL;
+	struct inode *inode, *iput_inode = NULL;
 
 	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry_safe(inode, next_i, &sb->s_inodes, i_sb_list) {
-		struct inode *need_iput_tmp;
-
+	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		/*
 		 * We cannot __iget() an inode in state I_FREEING,
 		 * I_WILL_FREE, or I_NEW which is fine because by that point
@@ -178,49 +176,24 @@ void fsnotify_unmount_inodes(struct super_block *sb)
 			continue;
 		}
 
-		need_iput_tmp = need_iput;
-		need_iput = NULL;
-
-		/* In case fsnotify_inode_delete() drops a reference. */
-		if (inode != need_iput_tmp)
-			__iget(inode);
-		else
-			need_iput_tmp = NULL;
+		__iget(inode);
 		spin_unlock(&inode->i_lock);
-
-		/* In case the dropping of a reference would nuke next_i. */
-		while (&next_i->i_sb_list != &sb->s_inodes) {
-			spin_lock(&next_i->i_lock);
-			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
-						atomic_read(&next_i->i_count)) {
-				__iget(next_i);
-				need_iput = next_i;
-				spin_unlock(&next_i->i_lock);
-				break;
-			}
-			spin_unlock(&next_i->i_lock);
-			next_i = list_next_entry(next_i, i_sb_list);
-		}
-
-		/*
-		 * We can safely drop s_inode_list_lock here because either
-		 * we actually hold references on both inode and next_i or
-		 * end of list.  Also no new inodes will be added since the
-		 * umount has begun.
-		 */
 		spin_unlock(&sb->s_inode_list_lock);
 
-		if (need_iput_tmp)
-			iput(need_iput_tmp);
+		if (iput_inode)
+			iput(iput_inode);
 
 		/* for each watch, send FS_UNMOUNT and then remove it */
 		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 
 		fsnotify_inode_delete(inode);
 
-		iput(inode);
+		iput_inode = inode;
 
 		spin_lock(&sb->s_inode_list_lock);
 	}
 	spin_unlock(&sb->s_inode_list_lock);
+
+	if (iput_inode)
+		iput(iput_inode);
 }

fs/ocfs2/quota_global.c

@@ -634,7 +634,15 @@ static void qsync_work_fn(struct work_struct *work)
 						      dqi_sync_work.work);
 	struct super_block *sb = oinfo->dqi_gqinode->i_sb;
 
-	dquot_scan_active(sb, ocfs2_sync_dquot_helper, oinfo->dqi_type);
+	/*
+	 * We have to be careful here not to deadlock on s_umount as umount
+	 * disabling quotas may be in progress and it waits for this work to
+	 * complete. If trylock fails, we'll do the sync next time...
+	 */
+	if (down_read_trylock(&sb->s_umount)) {
+		dquot_scan_active(sb, ocfs2_sync_dquot_helper, oinfo->dqi_type);
+		up_read(&sb->s_umount);
+	}
 	schedule_delayed_work(&oinfo->dqi_sync_work,
 			      msecs_to_jiffies(oinfo->dqi_syncms));
 }

fs/ocfs2/quota_local.c

@@ -454,7 +454,7 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
 /* Sync changes in local quota file into global quota file and
  * reinitialize local quota file.
  * The function expects local quota file to be already locked and
- * dqonoff_mutex locked. */
+ * s_umount locked in shared mode. */
 static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 					  int type,
 					  struct ocfs2_quota_recovery *rec)
@@ -597,7 +597,7 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
 	       "slot %u\n", osb->dev_str, slot_num);
 
-	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
+	down_read(&sb->s_umount);
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
 			continue;
@@ -674,7 +674,7 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 			break;
 	}
 out:
-	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
+	up_read(&sb->s_umount);
 	kfree(rec);
 	return status;
 }
@@ -840,7 +840,10 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
 	}
 	ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
 
-	/* dqonoff_mutex protects us against racing with recovery thread... */
+	/*
+	 * s_umount held in exclusive mode protects us against racing with
+	 * recovery thread...
+	 */
 	if (oinfo->dqi_rec) {
 		ocfs2_free_quota_recovery(oinfo->dqi_rec);
 		mark_clean = 0;

fs/ocfs2/super.c

@@ -985,7 +985,6 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!sb_has_quota_loaded(sb, type))
 			continue;
-		/* Cancel periodic syncing before we grab dqonoff_mutex */
 		oinfo = sb_dqinfo(sb, type)->dqi_priv;
 		cancel_delayed_work_sync(&oinfo->dqi_sync_work);
 		inode = igrab(sb->s_dquot.files[type]);

fs/quota/quota.c

@@ -104,13 +104,9 @@ static int quota_getfmt(struct super_block *sb, int type, void __user *addr)
 {
 	__u32 fmt;
 
-	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
-	if (!sb_has_quota_active(sb, type)) {
-		mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
+	if (!sb_has_quota_active(sb, type))
 		return -ESRCH;
-	}
 	fmt = sb_dqopt(sb)->info[type].dqi_format->qf_fmt_id;
-	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
 	if (copy_to_user(addr, &fmt, sizeof(fmt)))
 		return -EFAULT;
 	return 0;
@@ -789,9 +785,14 @@ static int quotactl_cmd_write(int cmd)
 	}
 	return 1;
 }
-
 #endif /* CONFIG_BLOCK */
 
+/* Return true if quotactl command is manipulating quota on/off state */
+static bool quotactl_cmd_onoff(int cmd)
+{
+	return (cmd == Q_QUOTAON) || (cmd == Q_QUOTAOFF);
+}
+
 /*
  * look up a superblock on which quota ops will be performed
  * - use the name of a block device to find the superblock thereon
@@ -809,7 +810,9 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
 	putname(tmp);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
-	if (quotactl_cmd_write(cmd))
+	if (quotactl_cmd_onoff(cmd))
+		sb = get_super_exclusive_thawed(bdev);
+	else if (quotactl_cmd_write(cmd))
 		sb = get_super_thawed(bdev);
 	else
 		sb = get_super(bdev);
@@ -872,7 +875,10 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
 
 	ret = do_quotactl(sb, type, cmds, id, addr, pathp);
 
-	drop_super(sb);
+	if (!quotactl_cmd_onoff(cmds))
+		drop_super(sb);
+	else
+		drop_super_exclusive(sb);
 out:
 	if (pathp && !IS_ERR(pathp))
 		path_put(pathp);

fs/super.c

@@ -244,7 +244,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	mutex_init(&s->s_vfs_rename_mutex);
 	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
 	mutex_init(&s->s_dquot.dqio_mutex);
-	mutex_init(&s->s_dquot.dqonoff_mutex);
 	s->s_maxbytes = MAX_NON_LFS;
 	s->s_op = &default_op;
 	s->s_time_gran = 1000000000;
@@ -558,6 +557,13 @@ void drop_super(struct super_block *sb)
 
 EXPORT_SYMBOL(drop_super);
 
+void drop_super_exclusive(struct super_block *sb)
+{
+	up_write(&sb->s_umount);
+	put_super(sb);
+}
+EXPORT_SYMBOL(drop_super_exclusive);
+
 /**
  *	iterate_supers - call function for all active superblocks
  *	@f: function to call
@@ -628,15 +634,7 @@ 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)
+static struct super_block *__get_super(struct block_device *bdev, bool excl)
 {
 	struct super_block *sb;
 
@@ -651,11 +649,17 @@ struct super_block *get_super(struct block_device *bdev)
 		if (sb->s_bdev == bdev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			down_read(&sb->s_umount);
+			if (!excl)
+				down_read(&sb->s_umount);
+			else
+				down_write(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & MS_BORN))
 				return sb;
-			up_read(&sb->s_umount);
+			if (!excl)
+				up_read(&sb->s_umount);
+			else
+				up_write(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
@@ -666,31 +670,66 @@ struct super_block *get_super(struct block_device *bdev)
 	return NULL;
 }
 
-EXPORT_SYMBOL(get_super);
-
 /**
- *	get_super_thawed - get thawed superblock of a device
+ *	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. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen). %NULL is returned if no match
- *	is found.
+ *	mounted on the device given. %NULL is returned if no match is found.
  */
-struct super_block *get_super_thawed(struct block_device *bdev)
+struct super_block *get_super(struct block_device *bdev)
+{
+	return __get_super(bdev, false);
+}
+EXPORT_SYMBOL(get_super);
+
+static struct super_block *__get_super_thawed(struct block_device *bdev,
+					      bool excl)
 {
 	while (1) {
-		struct super_block *s = get_super(bdev);
+		struct super_block *s = __get_super(bdev, excl);
 		if (!s || s->s_writers.frozen == SB_UNFROZEN)
 			return s;
-		up_read(&s->s_umount);
+		if (!excl)
+			up_read(&s->s_umount);
+		else
+			up_write(&s->s_umount);
 		wait_event(s->s_writers.wait_unfrozen,
 			   s->s_writers.frozen == SB_UNFROZEN);
 		put_super(s);
 	}
 }
+
+/**
+ *	get_super_thawed - get thawed 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. The superblock is returned once it is thawed
+ *	(or immediately if it was not frozen). %NULL is returned if no match
+ *	is found.
+ */
+struct super_block *get_super_thawed(struct block_device *bdev)
+{
+	return __get_super_thawed(bdev, false);
+}
 EXPORT_SYMBOL(get_super_thawed);
 
+/**
+ *	get_super_exclusive_thawed - get thawed 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. The superblock is returned once it is thawed
+ *	(or immediately if it was not frozen) and s_umount semaphore is held
+ *	in exclusive mode. %NULL is returned if no match is found.
+ */
+struct super_block *get_super_exclusive_thawed(struct block_device *bdev)
+{
+	return __get_super_thawed(bdev, true);
+}
+EXPORT_SYMBOL(get_super_exclusive_thawed);
+
 /**
  * get_active_super - get an active reference to the superblock of a device
  * @bdev: device to get the superblock for

include/linux/fs.h

@@ -2903,8 +2903,10 @@ extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
 extern struct super_block *get_super(struct block_device *);
 extern struct super_block *get_super_thawed(struct block_device *);
+extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev);
 extern struct super_block *get_active_super(struct block_device *bdev);
 extern void drop_super(struct super_block *sb);
+extern void drop_super_exclusive(struct super_block *sb);
 extern void iterate_supers(void (*)(struct super_block *, void *), void *);
 extern void iterate_supers_type(struct file_system_type *,
 			        void (*)(struct super_block *, void *), void *);

include/linux/quota.h

@@ -520,7 +520,6 @@ static inline void quota_send_warning(struct kqid qid, dev_t dev,
 struct quota_info {
 	unsigned int flags;			/* Flags for diskquotas on this device */
 	struct mutex dqio_mutex;		/* lock device while I/O in progress */
-	struct mutex dqonoff_mutex;		/* Serialize quotaon & quotaoff */
 	struct inode *files[MAXQUOTAS];		/* inodes of quotafiles */
 	struct mem_dqinfo info[MAXQUOTAS];	/* Information for each quota type */
 	const struct quota_format_ops *ops[MAXQUOTAS];	/* Operations for each type */