To properly support vfs idmappings we need to provide
a fuse daemon with the correct owner uid/gid for
inode creation requests like mkdir, mknod, atomic_open,
symlink.
Right now, fuse daemons use req->in.h.uid/req->in.h.gid
to set inode owner. These fields contain fsuid/fsgid of the
syscall's caller. And that's perfectly fine, because inode
owner have to be set to these values. But, for idmapped mounts
it's not the case and caller fsuid/fsgid != inode owner, because
idmapped mounts do nothing with the caller fsuid/fsgid, but
affect inode owner uid/gid. It means that we can't apply vfsid
mapping to caller fsuid/fsgid, but instead we have to introduce
a new fields to store inode owner uid/gid which will be appropriately
transformed.
Christian and I have done the same to support idmapped mounts in
the cephfs recently [1].
[1] 5ccd8530 ("ceph: handle idmapped mounts in create_request_message()")
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Seth Forshee <sforshee@kernel.org>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Bernd Schubert <bschubert@ddn.com>
Cc: <linux-fsdevel@vger.kernel.org>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
---
fs/fuse/dir.c | 34 +++++++++++++++++++++++++++++++---
fs/fuse/fuse_i.h | 3 +++
fs/fuse/inode.c | 4 +++-
include/uapi/linux/fuse.h | 19 +++++++++++++++++++
4 files changed, 56 insertions(+), 4 deletions(-)
@@ -568,7 +568,33 @@ static int get_create_supp_group(struct inode *dir, struct fuse_in_arg *ext)
return 0;
}
-static int get_create_ext(struct fuse_args *args,
+static int get_owner_uid_gid(struct mnt_idmap *idmap, struct fuse_conn *fc, struct fuse_in_arg *ext)
+{
+ struct fuse_ext_header *xh;
+ struct fuse_owner_uid_gid *owner_creds;
+ u32 owner_creds_len = fuse_ext_size(sizeof(*owner_creds));
+ kuid_t owner_fsuid;
+ kgid_t owner_fsgid;
+
+ xh = extend_arg(ext, owner_creds_len);
+ if (!xh)
+ return -ENOMEM;
+
+ xh->size = owner_creds_len;
+ xh->type = FUSE_EXT_OWNER_UID_GID;
+
+ owner_creds = (struct fuse_owner_uid_gid *) &xh[1];
+
+ owner_fsuid = mapped_fsuid(idmap, fc->user_ns);
+ owner_fsgid = mapped_fsgid(idmap, fc->user_ns);
+ owner_creds->uid = from_kuid(fc->user_ns, owner_fsuid);
+ owner_creds->gid = from_kgid(fc->user_ns, owner_fsgid);
+
+ return 0;
+}
+
+static int get_create_ext(struct mnt_idmap *idmap,
+ struct fuse_args *args,
struct inode *dir, struct dentry *dentry,
umode_t mode)
{
@@ -580,6 +606,8 @@ static int get_create_ext(struct fuse_args *args,
err = get_security_context(dentry, mode, &ext);
if (!err && fc->create_supp_group)
err = get_create_supp_group(dir, &ext);
+ if (!err && fc->owner_uid_gid_ext)
+ err = get_owner_uid_gid(idmap, fc, &ext);
if (!err && ext.size) {
WARN_ON(args->in_numargs >= ARRAY_SIZE(args->in_args));
@@ -662,7 +690,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
args.out_args[1].size = sizeof(outopen);
args.out_args[1].value = &outopen;
- err = get_create_ext(&args, dir, entry, mode);
+ err = get_create_ext(&nop_mnt_idmap, &args, dir, entry, mode);
if (err)
goto out_put_forget_req;
@@ -790,7 +818,7 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args,
args->out_args[0].value = &outarg;
if (args->opcode != FUSE_LINK) {
- err = get_create_ext(args, dir, entry, mode);
+ err = get_create_ext(&nop_mnt_idmap, args, dir, entry, mode);
if (err)
goto out_put_forget_req;
}
@@ -806,6 +806,9 @@ struct fuse_conn {
/* Add supplementary group info when creating a new inode */
unsigned int create_supp_group:1;
+ /* Add owner_{u,g}id info when creating a new inode */
+ unsigned int owner_uid_gid_ext:1;
+
/* Does the filesystem support per inode DAX? */
unsigned int inode_dax:1;
@@ -1284,6 +1284,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
fc->create_supp_group = 1;
if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
fc->direct_io_allow_mmap = 1;
+ if (flags & FUSE_OWNER_UID_GID_EXT)
+ fc->owner_uid_gid_ext = 1;
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
@@ -1330,7 +1332,7 @@ void fuse_send_init(struct fuse_mount *fm)
FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
- FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
+ FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP | FUSE_OWNER_UID_GID_EXT;
#ifdef CONFIG_FUSE_DAX
if (fm->fc->dax)
flags |= FUSE_MAP_ALIGNMENT;
@@ -211,6 +211,10 @@
* 7.39
* - add FUSE_DIRECT_IO_ALLOW_MMAP
* - add FUSE_STATX and related structures
+ *
+ * 7.40
+ * - add FUSE_EXT_OWNER_UID_GID
+ * - add FUSE_OWNER_UID_GID_EXT
*/
#ifndef _LINUX_FUSE_H
@@ -410,6 +414,8 @@ struct fuse_file_lock {
* symlink and mknod (single group that matches parent)
* FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
* FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
+ * FUSE_OWNER_UID_GID_EXT: add inode owner UID/GID info to create, mkdir,
+ * symlink and mknod
*/
#define FUSE_ASYNC_READ (1 << 0)
#define FUSE_POSIX_LOCKS (1 << 1)
@@ -452,6 +458,7 @@ struct fuse_file_lock {
/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP
+#define FUSE_OWNER_UID_GID_EXT (1ULL << 37)
/**
* CUSE INIT request/reply flags
@@ -561,11 +568,13 @@ struct fuse_file_lock {
* extension type
* FUSE_MAX_NR_SECCTX: maximum value of &fuse_secctx_header.nr_secctx
* FUSE_EXT_GROUPS: &fuse_supp_groups extension
+ * FUSE_EXT_OWNER_UID_GID: &fuse_owner_uid_gid extension
*/
enum fuse_ext_type {
/* Types 0..31 are reserved for fuse_secctx_header */
FUSE_MAX_NR_SECCTX = 31,
FUSE_EXT_GROUPS = 32,
+ FUSE_EXT_OWNER_UID_GID = 33,
};
enum fuse_opcode {
@@ -1153,4 +1162,14 @@ struct fuse_supp_groups {
uint32_t groups[];
};
+/**
+ * struct fuse_owner_uid_gid - Inode owner UID/GID extension
+ * @uid: inode owner UID
+ * @gid: inode owner GID
+ */
+struct fuse_owner_uid_gid {
+ uint32_t uid;
+ uint32_t gid;
+};
+
#endif /* _LINUX_FUSE_H */