summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
authorChristian Brauner <brauner@kernel.org>2023-08-07 16:26:17 +0300
committerIlya Dryomov <idryomov@gmail.com>2023-11-04 01:28:33 +0300
commit5ccd8530dd7ba97531a50ffa11eabe258d65a7af (patch)
tree4de510c16a0229c8a9f169fb82e4d6ab99e3c098 /fs/ceph
parent9c2df2271c6901ba67d3437494b3d889dc43645b (diff)
downloadlinux-5ccd8530dd7ba97531a50ffa11eabe258d65a7af.tar.xz
ceph: handle idmapped mounts in create_request_message()
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@mail.gmail.com/ [2] https://lore.kernel.org/all/20220104140414.155198-3-brauner@kernel.org/ Link: https://github.com/ceph/ceph/pull/52575 Link: https://tracker.ceph.com/issues/62217 Co-Developed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Reviewed-by: Xiubo Li <xiubli@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/mds_client.c56
-rw-r--r--fs/ceph/mds_client.h5
2 files changed, 56 insertions, 5 deletions
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index ff5a05346f52..b97a16df7580 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2881,6 +2881,17 @@ static void encode_mclientrequest_tail(void **p,
}
}
+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)
{
@@ -2902,6 +2913,7 @@ 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;
@@ -2915,8 +2927,7 @@ 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,
@@ -2957,8 +2968,10 @@ 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);
@@ -3008,6 +3021,18 @@ 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)) {
+ WARN_ON_ONCE(!IS_CEPH_MDS_OP_NEWINODE(req->r_op));
+
+ 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.
@@ -3015,17 +3040,40 @@ 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);
+ nhead->struct_len = cpu_to_le32(sizeof(struct ceph_mds_request_head));
+
+ if (IS_CEPH_MDS_OP_NEWINODE(req->r_op)) {
+ 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));
+ } else {
+ nhead->owner_uid = cpu_to_le32(-1);
+ nhead->owner_gid = cpu_to_le32(-1);
+ }
+
p = msg->front.iov_base + sizeof(*nhead);
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index eb5e76446046..7c942294e96b 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, \
}
/*