In order to support per-mount idmappings vfsmounts will be marked with user namespaces. The idmapping associated with that user namespace will be used to map the ids of vfs objects when they are accessed through that mount. By default all vfsmounts will be marked with the initial user namespace. The initial user namespace is used to indicate that a mount is not idmapped. All operations behave as before and no performance impact is seen. Based on prior discussions we want to attach the whole user namespace and not just a dedicated idmapping struct. This allows us to reuse all the helpers that already exist for dealing with idmappings instead of introducing a whole new range of helpers. In addition, if we decide in the future that we are confident enough to enable unprivileged user to setup idmapped mounts we can allow already idmapped mounts to be marked with another user namespace. For now, we will enforce in later patches that once a mount has been idmapped it can't be remapped. This keeps permission checking and life-cycle management simple especially since users can always create a new mount with a different idmapping anyway. The idea to attach user namespaces to vfsmounts has been floated around in various forms at Linux Plumbers in ~2018 with the original idea being tracing back to a discussion during a conference in St. Petersburg between Christoph, Tycho, and myself. Cc: Christoph Hellwig <hch@xxxxxx> Cc: David Howells <dhowells@xxxxxxxxxx> Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx> Cc: linux-fsdevel@xxxxxxxxxxxxxxx Signed-off-by: Christian Brauner <christian.brauner@xxxxxxxxxx> --- /* v2 */ patch introduced - Christoph Hellwig: - Split internal implementation into separate patch and move syscall implementation later. --- fs/namespace.c | 6 ++++++ include/linux/fs.h | 1 + include/linux/mount.h | 12 ++++++++++++ 3 files changed, 19 insertions(+) diff --git a/fs/namespace.c b/fs/namespace.c index 9fc8b22dba26..15fb0ae3f01f 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -220,6 +220,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + mnt->mnt.mnt_user_ns = &init_user_ns; } return mnt; @@ -559,6 +560,8 @@ int sb_prepare_remount_readonly(struct super_block *sb) static void free_vfsmnt(struct mount *mnt) { + if (mnt_idmapped(&mnt->mnt) && mnt_user_ns(&mnt->mnt) != &init_user_ns) + put_user_ns(mnt_user_ns(&mnt->mnt)); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); @@ -1067,6 +1070,9 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); + mnt->mnt.mnt_user_ns = old->mnt.mnt_user_ns; + if (mnt_user_ns(&old->mnt) != &init_user_ns) + mnt->mnt.mnt_user_ns = get_user_ns(mnt->mnt.mnt_user_ns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; diff --git a/include/linux/fs.h b/include/linux/fs.h index 9e487cbf0f5c..9e05fb4f997c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2260,6 +2260,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ +#define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); diff --git a/include/linux/mount.h b/include/linux/mount.h index aaf343b38671..3c7ba1bd4a21 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -31,6 +31,7 @@ struct fs_context; #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ #define MNT_NOSYMFOLLOW 0x80 +#define MNT_IDMAPPED 0x400 #define MNT_SHRINKABLE 0x100 #define MNT_WRITE_HOLD 0x200 @@ -72,8 +73,19 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; + struct user_namespace *mnt_user_ns; } __randomize_layout; +static inline bool mnt_idmapped(const struct vfsmount *mnt) +{ + return READ_ONCE(mnt->mnt_flags) & MNT_IDMAPPED; +} + +static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) +{ + return mnt->mnt_user_ns; +} + struct file; /* forward dec */ struct path; -- 2.29.2