Re: [PATCH] ceph: fix statfs for subdir mounts

[Xiubo Li <xiubli@redhat.com>]

On 4/27/22 12:12 AM, Luís Henriques wrote:
> When doing a mount using as base a directory that has 'max_bytes' quotas
> statfs uses that value as the total; if a subdirectory is used instead,
> the same 'max_bytes' too in statfs, unless there is another quota set.
>
> Unfortunately, if this subdirectory only has the 'max_files' quota set,
> then statfs uses the filesystem total.  Fix this by making sure we only
> lookup realms that contain the 'max_bytes' quota.
>
> Link: https://tracker.ceph.com/issues/55090
> Cc: Ryan Taylor <rptaylor@uvic.ca>
> Signed-off-by: Luís Henriques <lhenriques@suse.de>
> ---
> Hi!
>
> Unfortunately, I don't think this is the real fix for the bug reported in
> the tracker (or by Ryan on the mailing-list).  I haven't seen any
> reference to 'max_files' so I suspect Ryan and Dan are hitting another
> bug.  This can be easily checked by 'getfattr -n ceph.quota <subdir>'.
>
> Also, Dan (in the tracker) states the bug is on the kernel client only but
> I can also see if in the fuse client.
>
> Anyway, this patch fixes a real bug.
>
>   fs/ceph/quota.c | 35 +++++++++++++++++++++++++++--------
>   1 file changed, 27 insertions(+), 8 deletions(-)
>
> diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
> index a338a3ec0dc4..235a8d06a8ee 100644
> --- a/fs/ceph/quota.c
> +++ b/fs/ceph/quota.c
> @@ -193,11 +193,17 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
>   	mutex_unlock(&mdsc->quotarealms_inodes_mutex);
>   }
>   
> +enum quota_get_realm {
> +	QUOTA_GET_MAX_FILES,
> +	QUOTA_GET_MAX_BYTES,
> +	QUOTA_GET_ANY
> +};
> +
>   /*
>    * This function walks through the snaprealm for an inode and returns the
> - * ceph_snap_realm for the first snaprealm that has quotas set (either max_files
> - * or max_bytes).  If the root is reached, return the root ceph_snap_realm
> - * instead.
> + * ceph_snap_realm for the first snaprealm that has quotas set (max_files,
> + * max_bytes, or any, depending on the 'which_quota' argument).  If the root is
> + * reached, return the root ceph_snap_realm instead.
>    *
>    * Note that the caller is responsible for calling ceph_put_snap_realm() on the
>    * returned realm.
> @@ -209,7 +215,9 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
>    * will be restarted.
>    */
>   static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
> -					       struct inode *inode, bool retry)
> +					       struct inode *inode,
> +					       enum quota_get_realm which_quota,
> +					       bool retry)
>   {
>   	struct ceph_inode_info *ci = NULL;
>   	struct ceph_snap_realm *realm, *next;
> @@ -248,7 +256,17 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
>   		}
>   
>   		ci = ceph_inode(in);
> -		has_quota = __ceph_has_any_quota(ci);
> +		switch (which_quota) {
> +		case QUOTA_GET_MAX_BYTES:
> +			has_quota = ci->i_max_bytes;
> +			break;
> +		case QUOTA_GET_MAX_FILES:
> +			has_quota = ci->i_max_files;
> +			break;
> +		default: /* QUOTA_GET_ANY */
> +			has_quota = __ceph_has_any_quota(ci);

How about moving this logic to __ceph_has_any_quota() by renaming it to 
__ceph_has_quota(ci, enum quota_get_realm which) ?

+ static inline bool __ceph_has_quota(ci, enum quota_get_realm which) {
+		switch (which) {
+		case QUOTA_GET_MAX_BYTES:
+			return !!ci->i_max_bytes;
+			break;
+		case QUOTA_GET_MAX_FILES:
+			return !!ci->i_max_files;
+			break;
+		default: /* QUOTA_GET_ANY */
+			return !!(ci->i_max_files || ci->i_max_bytes);
+ }

The other LGTM.

-- Xiubo


> +			break;
> +		}
>   		iput(in);
>   
>   		next = realm->parent;
> @@ -279,8 +297,8 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
>   	 * dropped and we can then restart the whole operation.
>   	 */
>   	down_read(&mdsc->snap_rwsem);
> -	old_realm = get_quota_realm(mdsc, old, true);
> -	new_realm = get_quota_realm(mdsc, new, false);
> +	old_realm = get_quota_realm(mdsc, old, QUOTA_GET_ANY, true);
> +	new_realm = get_quota_realm(mdsc, new, QUOTA_GET_ANY, false);
>   	if (PTR_ERR(new_realm) == -EAGAIN) {
>   		up_read(&mdsc->snap_rwsem);
>   		if (old_realm)
> @@ -483,7 +501,8 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
>   	bool is_updated = false;
>   
>   	down_read(&mdsc->snap_rwsem);
> -	realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root), true);
> +	realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root),
> +				QUOTA_GET_MAX_BYTES, true);
>   	up_read(&mdsc->snap_rwsem);
>   	if (!realm)
>   		return false;
>