Re: [PATCH v8 03/12] ceph: handle idmapped mounts in create_request_message()

From: Aleksandr Mikhalitsyn
Date: Fri Aug 04 2023 - 02:26:01 EST


On Fri, Aug 4, 2023 at 4:26 AM Xiubo Li <xiubli@xxxxxxxxxx> wrote:
>
>
> On 8/3/23 21:59, Alexander Mikhalitsyn wrote:
> > From: Christian Brauner <brauner@xxxxxxxxxx>
> >
> > Inode operations that create a new filesystem object such as ->mknod,
> > ->create, ->mkdir() and others don't take a {g,u}id argument explicitly.
> > Instead the caller's fs{g,u}id is used for the {g,u}id of the new
> > filesystem object.
> >
> > In order to ensure that the correct {g,u}id is used map the caller's
> > fs{g,u}id for creation requests. This doesn't require complex changes.
> > It suffices to pass in the relevant idmapping recorded in the request
> > message. If this request message was triggered from an inode operation
> > that creates filesystem objects it will have passed down the relevant
> > idmaping. If this is a request message that was triggered from an inode
> > operation that doens't need to take idmappings into account the initial
> > idmapping is passed down which is an identity mapping.
> >
> > This change uses a new cephfs protocol extension CEPHFS_FEATURE_HAS_OWNER_UIDGID
> > which adds two new fields (owner_{u,g}id) to the request head structure.
> > So, we need to ensure that MDS supports it otherwise we need to fail
> > any IO that comes through an idmapped mount because we can't process it
> > in a proper way. MDS server without such an extension will use caller_{u,g}id
> > fields to set a new inode owner UID/GID which is incorrect because caller_{u,g}id
> > values are unmapped. At the same time we can't map these fields with an
> > idmapping as it can break UID/GID-based permission checks logic on the
> > MDS side. This problem was described with a lot of details at [1], [2].
> >
> > [1] https://lore.kernel.org/lkml/CAEivzxfw1fHO2TFA4dx3u23ZKK6Q+EThfzuibrhA3RKM=ZOYLg@xxxxxxxxxxxxxx/
> > [2] https://lore.kernel.org/all/20220104140414.155198-3-brauner@xxxxxxxxxx/
> >
> > https://github.com/ceph/ceph/pull/52575
> > https://tracker.ceph.com/issues/62217
> >
> > Cc: Xiubo Li <xiubli@xxxxxxxxxx>
> > Cc: Jeff Layton <jlayton@xxxxxxxxxx>
> > Cc: Ilya Dryomov <idryomov@xxxxxxxxx>
> > Cc: ceph-devel@xxxxxxxxxxxxxxx
> > Co-Developed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@xxxxxxxxxxxxx>
> > Signed-off-by: Christian Brauner <brauner@xxxxxxxxxx>
> > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@xxxxxxxxxxxxx>
> > ---
> > v7:
> > - reworked to use two new fields for owner UID/GID (https://github.com/ceph/ceph/pull/52575)
> > v8:
> > - properly handled case when old MDS used with new kernel client
> > ---
> > fs/ceph/mds_client.c | 46 +++++++++++++++++++++++++++++++++---
> > fs/ceph/mds_client.h | 5 +++-
> > include/linux/ceph/ceph_fs.h | 4 +++-
> > 3 files changed, 50 insertions(+), 5 deletions(-)
> >
> > diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
> > index 8829f55103da..7d3106d3b726 100644
> > --- a/fs/ceph/mds_client.c
> > +++ b/fs/ceph/mds_client.c
> > @@ -2902,6 +2902,17 @@ static void encode_mclientrequest_tail(void **p, const struct ceph_mds_request *
> > }
> > }
> >
> > +static inline u16 mds_supported_head_version(struct ceph_mds_session *session)
> > +{
> > + if (!test_bit(CEPHFS_FEATURE_32BITS_RETRY_FWD, &session->s_features))
> > + return 1;
> > +
> > + if (!test_bit(CEPHFS_FEATURE_HAS_OWNER_UIDGID, &session->s_features))
> > + return 2;
> > +
> > + return CEPH_MDS_REQUEST_HEAD_VERSION;
> > +}
> > +
> > static struct ceph_mds_request_head_legacy *
> > find_legacy_request_head(void *p, u64 features)
> > {
> > @@ -2923,6 +2934,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
> > {
> > int mds = session->s_mds;
> > struct ceph_mds_client *mdsc = session->s_mdsc;
> > + struct ceph_client *cl = mdsc->fsc->client;
> > struct ceph_msg *msg;
> > struct ceph_mds_request_head_legacy *lhead;
> > const char *path1 = NULL;
> > @@ -2936,7 +2948,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
> > void *p, *end;
> > int ret;
> > bool legacy = !(session->s_con.peer_features & CEPH_FEATURE_FS_BTIME);
> > - bool old_version = !test_bit(CEPHFS_FEATURE_32BITS_RETRY_FWD, &session->s_features);
> > + u16 request_head_version = mds_supported_head_version(session);
> >
> > ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry,
> > req->r_parent, req->r_path1, req->r_ino1.ino,
> > @@ -2977,8 +2989,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
> > */
> > if (legacy)
> > len = sizeof(struct ceph_mds_request_head_legacy);
> > - else if (old_version)
> > + else if (request_head_version == 1)
> > len = sizeof(struct ceph_mds_request_head_old);
> > + else if (request_head_version == 2)
> > + len = offsetofend(struct ceph_mds_request_head, ext_num_fwd);
> > else
> > len = sizeof(struct ceph_mds_request_head);
> >
>
> This is not what we suppose to. If we do this again and again when
> adding new members it will make the code very complicated to maintain.
>
> Once the CEPHFS_FEATURE_32BITS_RETRY_FWD has been supported the ceph
> should correctly decode it and if CEPHFS_FEATURE_HAS_OWNER_UIDGID is not
> supported the decoder should skip it directly.

I thought that too. But it doesn't work. Just try - take kernel client
testing branch, and then
add a new field to the struct ceph_mds_request_head. Compile and try to mount.
It will stop to work and on the MDS side you will see something like:

2023-08-03T13:15:40.871+0200 7fe64ef5e640 10 mds.c ms_handle_accept
v1:192.168.2.136:0/49354629 con 0x563962206880 session 0x563967054000
2023-08-03T13:15:40.871+0200 7fe650f62640 -1 failed to decode message
of type 24 v6: End of buffer [buffer:2]
2023-08-03T13:15:40.871+0200 7fe650f62640 1 dump:
00000000 03 00 01 00 00 00 00 00 00 00 10 00 00 00 00 00 |................|
00000010 00 00 00 00 00 00 01 01 00 00 00 00 00 00 00 00 |................|
00000020 00 00 00 00 00 00 00 00 00 00 01 00 00 00 00 00 |................|
00000030 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................|
*
00000070 00 00 01 01 00 00 00 00 00 00 00 00 00 00 00 01 |................|
00000080 00 00 00 00 00 00 00 00 00 00 00 00 5b 8c cb 64 |............[..d|
00000090 64 78 11 13 01 00 00 00 00 00 00 00 00 00 00 00 |dx..............|
000000a0 00 00 00 00 00 00 00 00 00 00 00 00 |............|
000000ac

As I understand, the MDS side is not ready to see struct
ceph_mds_request_head bigger in size
than supported.

>
> Is the MDS side buggy ? Why you last version didn't work ?
>
> Thanks
>
> - Xiubo
>
> > @@ -3028,6 +3042,16 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
> > lhead = find_legacy_request_head(msg->front.iov_base,
> > session->s_con.peer_features);
> >
> > + if ((req->r_mnt_idmap != &nop_mnt_idmap) &&
> > + !test_bit(CEPHFS_FEATURE_HAS_OWNER_UIDGID, &session->s_features)) {
> > + pr_err_ratelimited_client(cl,
> > + "idmapped mount is used and CEPHFS_FEATURE_HAS_OWNER_UIDGID"
> > + " is not supported by MDS. Fail request with -EIO.\n");
> > +
> > + ret = -EIO;
> > + goto out_err;
> > + }
> > +
> > /*
> > * The ceph_mds_request_head_legacy didn't contain a version field, and
> > * one was added when we moved the message version from 3->4.
> > @@ -3035,17 +3059,33 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
> > if (legacy) {
> > msg->hdr.version = cpu_to_le16(3);
> > p = msg->front.iov_base + sizeof(*lhead);
> > - } else if (old_version) {
> > + } else if (request_head_version == 1) {
> > struct ceph_mds_request_head_old *ohead = msg->front.iov_base;
> >
> > msg->hdr.version = cpu_to_le16(4);
> > ohead->version = cpu_to_le16(1);
> > p = msg->front.iov_base + sizeof(*ohead);
> > + } else if (request_head_version == 2) {
> > + struct ceph_mds_request_head *nhead = msg->front.iov_base;
> > +
> > + msg->hdr.version = cpu_to_le16(6);
> > + nhead->version = cpu_to_le16(2);
> > +
> > + p = msg->front.iov_base + offsetofend(struct ceph_mds_request_head, ext_num_fwd);
> > } else {
> > struct ceph_mds_request_head *nhead = msg->front.iov_base;
> > + kuid_t owner_fsuid;
> > + kgid_t owner_fsgid;
> >
> > msg->hdr.version = cpu_to_le16(6);
> > nhead->version = cpu_to_le16(CEPH_MDS_REQUEST_HEAD_VERSION);
> > +
> > + owner_fsuid = from_vfsuid(req->r_mnt_idmap, &init_user_ns,
> > + VFSUIDT_INIT(req->r_cred->fsuid));
> > + owner_fsgid = from_vfsgid(req->r_mnt_idmap, &init_user_ns,
> > + VFSGIDT_INIT(req->r_cred->fsgid));
> > + nhead->owner_uid = cpu_to_le32(from_kuid(&init_user_ns, owner_fsuid));
> > + nhead->owner_gid = cpu_to_le32(from_kgid(&init_user_ns, owner_fsgid));
> > p = msg->front.iov_base + sizeof(*nhead);
> > }
> >
> > diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
> > index e3bbf3ba8ee8..8f683e8203bd 100644
> > --- a/fs/ceph/mds_client.h
> > +++ b/fs/ceph/mds_client.h
> > @@ -33,8 +33,10 @@ enum ceph_feature_type {
> > CEPHFS_FEATURE_NOTIFY_SESSION_STATE,
> > CEPHFS_FEATURE_OP_GETVXATTR,
> > CEPHFS_FEATURE_32BITS_RETRY_FWD,
> > + CEPHFS_FEATURE_NEW_SNAPREALM_INFO,
> > + CEPHFS_FEATURE_HAS_OWNER_UIDGID,
> >
> > - CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_32BITS_RETRY_FWD,
> > + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_HAS_OWNER_UIDGID,
> > };
> >
> > #define CEPHFS_FEATURES_CLIENT_SUPPORTED { \
> > @@ -49,6 +51,7 @@ enum ceph_feature_type {
> > CEPHFS_FEATURE_NOTIFY_SESSION_STATE, \
> > CEPHFS_FEATURE_OP_GETVXATTR, \
> > CEPHFS_FEATURE_32BITS_RETRY_FWD, \
> > + CEPHFS_FEATURE_HAS_OWNER_UIDGID, \
> > }
> >
> > /*
> > diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
> > index 5f2301ee88bc..6eb83a51341c 100644
> > --- a/include/linux/ceph/ceph_fs.h
> > +++ b/include/linux/ceph/ceph_fs.h
> > @@ -499,7 +499,7 @@ struct ceph_mds_request_head_legacy {
> > union ceph_mds_request_args args;
> > } __attribute__ ((packed));
> >
> > -#define CEPH_MDS_REQUEST_HEAD_VERSION 2
> > +#define CEPH_MDS_REQUEST_HEAD_VERSION 3
> >
> > struct ceph_mds_request_head_old {
> > __le16 version; /* struct version */
> > @@ -530,6 +530,8 @@ struct ceph_mds_request_head {
> >
> > __le32 ext_num_retry; /* new count retry attempts */
> > __le32 ext_num_fwd; /* new count fwd attempts */
> > +
> > + __le32 owner_uid, owner_gid; /* used for OPs which create inodes */
> > } __attribute__ ((packed));
> >
> > /* cap/lease release record */
>