Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Subject: Re: [PATCH v3] ceph: fix statfs for subdir mounts
To:     =?UTF-8?Q?Lu=c3=ads_Henriques?= <lhenriques@suse.de>,
        Jeff Layton <jlayton@kernel.org>,
        Ilya Dryomov <idryomov@gmail.com>
Cc:     ceph-devel@vger.kernel.org, linux-kernel@vger.kernel.org,
        Ryan Taylor <rptaylor@uvic.ca>
References: <20220427155704.4758-1-lhenriques@suse.de>
From:   Xiubo Li <xiubli@redhat.com>
Message-ID: <8bbf90c4-e292-9918-f3c9-6823ae2e652c@redhat.com>
Date:   Thu, 28 Apr 2022 09:08:10 +0800
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101
 Thunderbird/78.10.1
MIME-Version: 1.0
In-Reply-To: <20220427155704.4758-1-lhenriques@suse.de>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Content-Language: en-US
Precedence: bulk


On 4/27/22 11:57 PM, 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>
> ---
> Changes since v2:
> Renamed function __ceph_has_any_quota() to __ceph_has_quota()
>
> Changes since v1:
> Moved some more logic into __ceph_has_any_quota() function.
>
>   fs/ceph/inode.c |  2 +-
>   fs/ceph/quota.c | 19 +++++++++++--------
>   fs/ceph/super.h | 28 ++++++++++++++++++++++++----
>   3 files changed, 36 insertions(+), 13 deletions(-)
>
> diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> index 5de7bb9048b7..1067209cf6f6 100644
> --- a/fs/ceph/inode.c
> +++ b/fs/ceph/inode.c
> @@ -691,7 +691,7 @@ void ceph_evict_inode(struct inode *inode)
>   
>   	__ceph_remove_caps(ci);
>   
> -	if (__ceph_has_any_quota(ci))
> +	if (__ceph_has_quota(ci, QUOTA_GET_ANY))
>   		ceph_adjust_quota_realms_count(inode, false);
>   
>   	/*
> diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
> index a338a3ec0dc4..64592adfe48f 100644
> --- a/fs/ceph/quota.c
> +++ b/fs/ceph/quota.c
> @@ -195,9 +195,9 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc)
>   
>   /*
>    * 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 +209,9 @@ 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 +250,7 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
>   		}
>   
>   		ci = ceph_inode(in);
> -		has_quota = __ceph_has_any_quota(ci);
> +		has_quota = __ceph_has_quota(ci, which_quota);
>   		iput(in);
>   
>   		next = realm->parent;
> @@ -279,8 +281,8 @@ 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 +485,8 @@ 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;
> diff --git a/fs/ceph/super.h b/fs/ceph/super.h
> index a2e1c83ab29a..0ecde1c12fee 100644
> --- a/fs/ceph/super.h
> +++ b/fs/ceph/super.h
> @@ -1317,9 +1317,29 @@ extern void ceph_fs_debugfs_init(struct ceph_fs_client *client);
>   extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);
>   
>   /* quota.c */
> -static inline bool __ceph_has_any_quota(struct ceph_inode_info *ci)
> +
> +enum quota_get_realm {
> +	QUOTA_GET_MAX_FILES,
> +	QUOTA_GET_MAX_BYTES,
> +	QUOTA_GET_ANY
> +};
> +
> +static inline bool __ceph_has_quota(struct ceph_inode_info *ci,
> +				    enum quota_get_realm which)
>   {
> -	return ci->i_max_files || ci->i_max_bytes;
> +	bool has_quota = false;
> +
> +	switch (which) {
> +	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:
> +		has_quota = !!(ci->i_max_files || ci->i_max_bytes);
> +	}
> +	return has_quota;
>   }
>   
>   extern void ceph_adjust_quota_realms_count(struct inode *inode, bool inc);
> @@ -1328,10 +1348,10 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci,
>   				       u64 max_bytes, u64 max_files)
>   {
>   	bool had_quota, has_quota;
> -	had_quota = __ceph_has_any_quota(ci);
> +	had_quota = __ceph_has_quota(ci, QUOTA_GET_ANY);
>   	ci->i_max_bytes = max_bytes;
>   	ci->i_max_files = max_files;
> -	has_quota = __ceph_has_any_quota(ci);
> +	has_quota = __ceph_has_quota(ci, QUOTA_GET_ANY);
>   
>   	if (had_quota != has_quota)
>   		ceph_adjust_quota_realms_count(&ci->vfs_inode, has_quota);
>
Looks good. Merged into the testing branch.

Thanks Luis.

-- Xiubo