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: [RFC PATCH v4] ceph: prevent a client from exceeding the MDS
 maximum xattr size
To:     =?UTF-8?Q?Lu=c3=ads_Henriques?= <lhenriques@suse.de>,
        Jeff Layton <jlayton@kernel.org>,
        Ilya Dryomov <idryomov@gmail.com>,
        Gregory Farnum <gfarnum@redhat.com>
Cc:     ceph-devel@vger.kernel.org, linux-kernel@vger.kernel.org
References: <20220602143652.28244-1-lhenriques@suse.de>
From:   Xiubo Li <xiubli@redhat.com>
Message-ID: <b89ca6a2-4332-b4db-2a40-ae3b00ebdf35@redhat.com>
Date:   Fri, 3 Jun 2022 19:29:55 +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: <20220602143652.28244-1-lhenriques@suse.de>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Content-Language: en-US
Precedence: bulk


On 6/2/22 10:36 PM, Luís Henriques wrote:
> The MDS tries to enforce a limit on the total key/values in extended
> attributes.  However, this limit is enforced only if doing a synchronous
> operation (MDS_OP_SETXATTR) -- if we're buffering the xattrs, the MDS
> doesn't have a chance to enforce these limits.
>
> This patch adds support for decoding the xattrs maximum size setting that is
> distributed in the mdsmap.  Then, when setting an xattr, the kernel client
> will revert to do a synchronous operation if that maximum size is exceeded.
>
> While there, fix a dout() that would trigger a printk warning:
>
> [   98.718078] ------------[ cut here ]------------
> [   98.719012] precision 65536 too large
> [   98.719039] WARNING: CPU: 1 PID: 3755 at lib/vsprintf.c:2703 vsnprintf+0x5e3/0x600
> ...
>
> URL: https://tracker.ceph.com/issues/55725
> Signed-off-by: Luís Henriques <lhenriques@suse.de>
> ---
>   fs/ceph/mdsmap.c            | 28 ++++++++++++++++++++++++----
>   fs/ceph/xattr.c             | 12 ++++++++----
>   include/linux/ceph/mdsmap.h |  1 +
>   3 files changed, 33 insertions(+), 8 deletions(-)
>
> * Changes since v3
>
> As per Xiubo review:
>    - Always force a (sync) SETXATTR Op when connecting to an old cluster
>    - use '>' instead of '>='
> Also fixed the warning detected by 0day.
>
> * Changes since v2
>
> Well, a lot has changed since v2!  Now the xattr max value setting is
> obtained through the mdsmap, which needs to be decoded, and the feature
> that was used in the previous revision was dropped.  The drawback is that
> the MDS isn't unable to know in advance if a client is aware of this xattr
> max value.
>
> * Changes since v1
>
> Added support for new feature bit to get the MDS max_xattr_pairs_size
> setting.
>
> Also note that this patch relies on a patch that hasn't been merged yet
> ("ceph: use correct index when encoding client supported features"),
> otherwise the new feature bit won't be correctly encoded.
>
> diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
> index 30387733765d..c6ce83a48175 100644
> --- a/fs/ceph/mdsmap.c
> +++ b/fs/ceph/mdsmap.c
> @@ -13,6 +13,12 @@
>   
>   #include "super.h"
>   
> +/*
> + * Maximum size of xattrs the MDS can handle per inode by default.  This
> + * includes the attribute name and 4+4 bytes for the key/value sizes.
> + */
> +#define MDS_MAX_XATTR_SIZE (1<<16) /* 64K */

This macro makes no sense anymore, right ?

I will merge this patch by removing this then.

-- Xiubo


> +
>   #define CEPH_MDS_IS_READY(i, ignore_laggy) \
>   	(m->m_info[i].state > 0 && ignore_laggy ? true : !m->m_info[i].laggy)
>   
> @@ -352,12 +358,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
>   		__decode_and_drop_type(p, end, u8, bad_ext);
>   	}
>   	if (mdsmap_ev >= 8) {
> -		u32 name_len;
>   		/* enabled */
>   		ceph_decode_8_safe(p, end, m->m_enabled, bad_ext);
> -		ceph_decode_32_safe(p, end, name_len, bad_ext);
> -		ceph_decode_need(p, end, name_len, bad_ext);
> -		*p += name_len;
> +		/* fs_name */
> +		ceph_decode_skip_string(p, end, bad_ext);
>   	}
>   	/* damaged */
>   	if (mdsmap_ev >= 9) {
> @@ -370,6 +374,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
>   	} else {
>   		m->m_damaged = false;
>   	}
> +	if (mdsmap_ev >= 17) {
> +		/* balancer */
> +		ceph_decode_skip_string(p, end, bad_ext);
> +		/* standby_count_wanted */
> +		ceph_decode_skip_32(p, end, bad_ext);
> +		/* old_max_mds */
> +		ceph_decode_skip_32(p, end, bad_ext);
> +		/* min_compat_client */
> +		ceph_decode_skip_8(p, end, bad_ext);
> +		/* required_client_features */
> +		ceph_decode_skip_set(p, end, 64, bad_ext);
> +		ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext);
> +	} else {
> +		/* This forces the usage of the (sync) SETXATTR Op */
> +		m->m_max_xattr_size = 0;
> +	}
>   bad_ext:
>   	dout("mdsmap_decode m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
>   	     !!m->m_enabled, !!m->m_damaged, m->m_num_laggy);
> diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
> index 8c2dc2c762a4..1be415e9220b 100644
> --- a/fs/ceph/xattr.c
> +++ b/fs/ceph/xattr.c
> @@ -1086,7 +1086,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
>   			flags |= CEPH_XATTR_REMOVE;
>   	}
>   
> -	dout("setxattr value=%.*s\n", (int)size, value);
> +	dout("setxattr value size: %lu\n", size);
>   
>   	/* do request */
>   	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
> @@ -1184,8 +1184,14 @@ int __ceph_setxattr(struct inode *inode, const char *name,
>   	spin_lock(&ci->i_ceph_lock);
>   retry:
>   	issued = __ceph_caps_issued(ci, NULL);
> -	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
> +	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
> +	if ((ci->i_xattrs.version == 0) || !(issued & CEPH_CAP_XATTR_EXCL) ||
> +	    (required_blob_size > mdsc->mdsmap->m_max_xattr_size)) {
> +		dout("%s do sync setxattr: version: %llu size: %d max: %llu\n",
> +		     __func__, ci->i_xattrs.version, required_blob_size,
> +		     mdsc->mdsmap->m_max_xattr_size);
>   		goto do_sync;
> +	}
>   
>   	if (!lock_snap_rwsem && !ci->i_head_snapc) {
>   		lock_snap_rwsem = true;
> @@ -1201,8 +1207,6 @@ int __ceph_setxattr(struct inode *inode, const char *name,
>   	     ceph_cap_string(issued));
>   	__build_xattrs(inode);
>   
> -	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
> -
>   	if (!ci->i_xattrs.prealloc_blob ||
>   	    required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
>   		struct ceph_buffer *blob;
> diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
> index 523fd0452856..4c3e0648dc27 100644
> --- a/include/linux/ceph/mdsmap.h
> +++ b/include/linux/ceph/mdsmap.h
> @@ -25,6 +25,7 @@ struct ceph_mdsmap {
>   	u32 m_session_timeout;          /* seconds */
>   	u32 m_session_autoclose;        /* seconds */
>   	u64 m_max_file_size;
> +	u64 m_max_xattr_size;		/* maximum size for xattrs blob */
>   	u32 m_max_mds;			/* expected up:active mds number */
>   	u32 m_num_active_mds;		/* actual up:active mds number */
>   	u32 possible_max_rank;		/* possible max rank index */
>