Message-ID: <20110829215732.GJ5672@quack.suse.cz>
Date:	Mon, 29 Aug 2011 23:57:32 +0200
From:	Jan Kara <jack@...e.cz>
To:	Aditya Kali <adityakali@...gle.com>
Cc:	adilger@...ger.ca, tytso@....edu, jack@...e.cz,
	linux-ext4@...r.kernel.org
Subject: Re: [PATCH v2] ext4: make quota as first class supported feature

On Fri 19-08-11 12:06:09, Aditya Kali wrote:
> This patch is an attempt towards supporting quotas as first class
> feature in ext4. It is based on the proposal at:
> https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4
> This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when
> turned on, enables quota accounting at mount time iteself. Also, the
> quota inodes are stored in two additional superblock fields.
> Some changes introduced by this patch that should be pointed out are:
> 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum
>    for storing the quota inodes in use.
> 2) If the QUOTA feature and corresponding quota inodes are set in superblock,
>    Quotas are turned on at mount time irrespective of the quota mount options.
>    Thus the mount options 'quota', 'usrquota' and 'grpquota' are completely
>    ignored with the new QUOTA feature flag.
  Hmm, cannot we automatically enable 'usrquota' and 'grpquota' options
when we see QUOTA feature enabled? Quota tools still need these options to
identify a filesystem they can work with (although another option would be
to change quota tools to use GETFMT with ext4 filesystem to identify
whether quotas are enabled or not).

> 3) Default quota inodes are: inode#3 for tracking userquota and inode#4 for
>    tracking group quota. The superblock fields can be set to use other inodes
>    as well.
> 4) mke2fs or tune2fs will initialize these inodes when quota feature is
>    being set. The default reserved inodes will not be visible to user as
>    regular files.
> 5) Once quotas are turned on, they cannot be turned off while the FS is
>    mounted. This is because we do not want to let the quota get inconsistent.
  Both xfs and ocfs2 allow for mode in which usage is tracked (i.e. quota
information is kept uptodate) but limits are not enforced. I imagine this
might be useful in some cases and also from consistency point of view it
would be nice.

In ocfs2 I implemented it so that on mount, updating of quota information
is enabled (when appropriate fs feature is enabled) but limits are not
enforced. Quotaon/quotaoff commands then toggle enforcement of quota
limits. XFS has mount options which decide whether quota information should
be kept uptodate and whether it should be enforced or not.

> 6) With the QUOTA feature set, since the quota inodes are hidden, some of the
>    utilities from quota-tools will no longer work correctly. Instead, e2fsprogs
>    will include support for fixing the quota files.
  I think it might be useful in some cases to enable only user quotas but
leave group quotas disabled (it slightly reduces quota overhead - mainly
because we have less quota structures to update on disk). So it would be
useful to have USRQUOTA and GRPQUOTA features separate...

								Honza
> 7) Support is only for the new V2 quota file format.
> 
> Signed-off-by: Aditya Kali <adityakali@...gle.com>
> ---
>  fs/ext4/ext4.h      |   10 ++++-
>  fs/ext4/ext4_jbd2.h |   18 +++++++---
>  fs/ext4/super.c     |   89 +++++++++++++++++++++++++++++++++++++++++++++++++--
>  3 files changed, 106 insertions(+), 11 deletions(-)
> 
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index e717dfd..5b57bc2 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -1065,7 +1065,9 @@ struct ext4_super_block {
>  	__u8	s_last_error_func[32];	/* function where the error happened */
>  #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
>  	__u8	s_mount_opts[64];
> -	__le32	s_reserved[112];        /* Padding to the end of the block */
> +	__le32	s_usr_quota_inum;	/* inode for tracking user quota */
> +	__le32	s_grp_quota_inum;	/* inode for tracking group quota */
> +	__le32	s_reserved[110];        /* Padding to the end of the block */
>  };
>  
>  #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
> @@ -1142,6 +1144,7 @@ struct ext4_sb_info {
>  #ifdef CONFIG_QUOTA
>  	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
>  	int s_jquota_fmt;			/* Format of quota to use */
> +	unsigned long s_qf_inums[MAXQUOTAS];	/* Quota file inodes */
>  #endif
>  	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
>  	struct rb_root system_blks;
> @@ -1241,6 +1244,8 @@ static inline struct timespec ext4_current_time(struct inode *inode)
>  static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
>  {
>  	return ino == EXT4_ROOT_INO ||
> +		ino == EXT4_USR_QUOTA_INO ||
> +		ino == EXT4_GRP_QUOTA_INO ||
>  		ino == EXT4_JOURNAL_INO ||
>  		ino == EXT4_RESIZE_INO ||
>  		(ino >= EXT4_FIRST_INO(sb) &&
> @@ -1401,7 +1406,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
>  					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
>  					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
>  					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
> -					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
> +					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE| \
> +					 EXT4_FEATURE_RO_COMPAT_QUOTA)
>  
>  /*
>   * Default values for user and/or group using reserved blocks
> diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
> index bb85757..0f097ed 100644
> --- a/fs/ext4/ext4_jbd2.h
> +++ b/fs/ext4/ext4_jbd2.h
> @@ -87,14 +87,20 @@
>  #ifdef CONFIG_QUOTA
>  /* Amount of blocks needed for quota update - we know that the structure was
>   * allocated so we need to update only data block */
> -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0)
> +#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
> +		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
> +		1 : 0)
>  /* Amount of blocks needed for quota insert/delete - we do some block writes
>   * but inode, sb and group updates are done only once */
> -#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
> -		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
> -
> -#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
> -		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
> +#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
> +		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
> +		(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
> +		 +3+DQUOT_INIT_REWRITE) : 0)
> +
> +#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
> +		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
> +		(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
> +		 +3+DQUOT_DEL_REWRITE) : 0)
>  #else
>  #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
>  #define EXT4_QUOTA_INIT_BLOCKS(sb) 0
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 4687fea..3f3d87e 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -1225,6 +1225,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot);
>  static int ext4_write_info(struct super_block *sb, int type);
>  static int ext4_quota_on(struct super_block *sb, int type, int format_id,
>  			 struct path *path);
> +static int ext4_quota_on_meta(struct super_block *sb, int type, int format_id);
>  static int ext4_quota_off(struct super_block *sb, int type);
>  static int ext4_quota_on_mount(struct super_block *sb, int type);
>  static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
> @@ -1252,6 +1253,16 @@ static const struct quotactl_ops ext4_qctl_operations = {
>  	.get_dqblk	= dquot_get_dqblk,
>  	.set_dqblk	= dquot_set_dqblk
>  };
> +
> +static const struct quotactl_ops ext4_new_qctl_operations = {
> +	.quota_on_meta	= ext4_quota_on_meta,
> +	.quota_off	= ext4_quota_off,
> +	.quota_sync	= dquot_quota_sync,
> +	.get_info	= dquot_get_dqinfo,
> +	.set_info	= dquot_set_dqinfo,
> +	.get_dqblk	= dquot_get_dqblk,
> +	.set_dqblk	= dquot_set_dqblk
> +};
>  #endif
>  
>  static const struct super_operations ext4_sops = {
> @@ -3518,6 +3529,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
>  #ifdef CONFIG_QUOTA
>  	sb->s_qcop = &ext4_qctl_operations;
>  	sb->dq_op = &ext4_quota_operations;
> +
> +	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
> +		/* Use new qctl operations with quota on function that does not
> +		 * require user specified quota file path. */
> +		sb->s_qcop = &ext4_new_qctl_operations;
> +
> +		sbi->s_qf_inums[USRQUOTA] = es->s_usr_quota_inum;
> +		sbi->s_qf_inums[GRPQUOTA] = es->s_grp_quota_inum;
> +	}
>  #endif
>  	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
>  
> @@ -3745,8 +3765,19 @@ no_journal:
>  	} else
>  		descr = "out journal";
>  
> -	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
> -		 "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
> +#ifdef CONFIG_QUOTA
> +	/* Enable quotas during mount. */
> +	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
> +	    !(sb->s_flags & MS_RDONLY)) {
> +		ext4_quota_on_meta(sb, USRQUOTA, QFMT_VFS_V1);
> +		ext4_quota_on_meta(sb, GRPQUOTA, QFMT_VFS_V1);
> +	}
> +#endif  /* CONFIG_QUOTA */
> +
> +	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. quota=%s. "
> +		 "Opts: %s%s%s", descr,
> +		 sb_any_quota_loaded(sb) ? "on" : "off",
> +		 sbi->s_es->s_mount_opts,
>  		 *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
>  
>  	if (es->s_error_count)
> @@ -4106,6 +4137,12 @@ static int ext4_commit_super(struct super_block *sb, int sync)
>  	es->s_free_inodes_count =
>  		cpu_to_le32(percpu_counter_sum_positive(
>  				&EXT4_SB(sb)->s_freeinodes_counter));
> +#ifdef CONFIG_QUOTA
> +	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
> +		es->s_usr_quota_inum = EXT4_SB(sb)->s_qf_inums[USRQUOTA];
> +		es->s_grp_quota_inum = EXT4_SB(sb)->s_qf_inums[GRPQUOTA];
> +	}
> +#endif
>  	sb->s_dirt = 0;
>  	BUFFER_TRACE(sbh, "marking dirty");
>  	mark_buffer_dirty(sbh);
> @@ -4687,7 +4724,7 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
>   * Standard function to be called on quota_on
>   */
>  static int ext4_quota_on(struct super_block *sb, int type, int format_id,
> -			 struct path *path)
> +			struct path *path)
>  {
>  	int err;
>  
> @@ -4726,11 +4763,57 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
>  	return dquot_quota_on(sb, type, format_id, path);
>  }
>  
> +/*
> + * New quota_on function that is used when QUOTA feature is set.
> + */
> +static int ext4_quota_on_meta(struct super_block *sb, int type, int format_id)
> +{
> +	int err;
> +	struct inode *qf_inode;
> +
> +	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) ||
> +	    !EXT4_SB(sb)->s_qf_inums[type])
> +		return -EINVAL;
> +
> +	qf_inode = ext4_iget(sb, EXT4_SB(sb)->s_qf_inums[type]);
> +	if (IS_ERR(qf_inode)) {
> +		EXT4_SB(sb)->s_qf_inums[type] = 0;
> +		return PTR_ERR(qf_inode);
> +	}
> +
> +	/*
> +	 * When we journal data on quota file, we have to flush journal to see
> +	 * all updates to the file when we bypass pagecache...
> +	 */
> +	if (EXT4_SB(sb)->s_journal &&
> +	    ext4_should_journal_data(qf_inode)) {
> +		/*
> +		 * We don't need to lock updates but journal_flush() could
> +		 * otherwise be livelocked...
> +		 */
> +		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
> +		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
> +		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
> +		if (err)
> +			return err;
> +	}
> +
> +	err = dquot_enable(qf_inode, type, format_id,
> +			   DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
> +	iput(qf_inode);
> +
> +	return err;
> +}
> +
>  static int ext4_quota_off(struct super_block *sb, int type)
>  {
>  	struct inode *inode = sb_dqopt(sb)->files[type];
>  	handle_t *handle;
>  
> +	/* Do not allow turning quotas off if QUOTA feature is set. */
> +	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
> +		return -EINVAL;
> +
>  	/* Force all delayed allocation blocks to be allocated.
>  	 * Caller already holds s_umount sem */
>  	if (test_opt(sb, DELALLOC))
> -- 
> 1.7.3.1
> 
-- 
Jan Kara <jack@...e.cz>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists