From: Christian Brauner christian.brauner@ubuntu.com

commit a793d79ea3e041081cd7cbd8ee43d0b5e4914a2b upstream.

The low-level mapping helpers were so far crammed into fs.h. They are out of place there. The fs.h header should just contain the higher-level mapping helpers that interact directly with vfs objects such as struct super_block or struct inode and not the bare mapping helpers. Similarly, only vfs and specific fs code shall interact with low-level mapping helpers. And so they won't be made accessible automatically through regular {g,u}id helpers.

Link: https://lore.kernel.org/r/20211123114227.3124056-3-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-3-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-3-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein amir73il@gmail.com Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org --- fs/ksmbd/smbacl.c | 1 + fs/ksmbd/smbacl.h | 1 + fs/open.c | 1 + fs/posix_acl.c | 1 + fs/xfs/xfs_linux.h | 1 + include/linux/fs.h | 91 +----------------------------- include/linux/mnt_idmapping.h | 101 ++++++++++++++++++++++++++++++++++ security/commoncap.c | 1 + 8 files changed, 108 insertions(+), 90 deletions(-) create mode 100644 include/linux/mnt_idmapping.h

diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index 7e57ffdb4ce3..7a6675fe57f7 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -9,6 +9,7 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/mnt_idmapping.h>

#include "smbacl.h" #include "smb_common.h" diff --git a/fs/ksmbd/smbacl.h b/fs/ksmbd/smbacl.h index 73e08cad412b..eba1ebb9e92e 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/namei.h> #include <linux/posix_acl.h> +#include <linux/mnt_idmapping.h>

#include "mgmt/tree_connect.h"

diff --git a/fs/open.c b/fs/open.c index e0df1536eb69..3d2a95ca6404 100644 --- a/fs/open.c +++ b/fs/open.c @@ -32,6 +32,7 @@ #include <linux/ima.h> #include <linux/dnotify.h> #include <linux/compat.h> +#include <linux/mnt_idmapping.h>

#include "internal.h"

diff --git a/fs/posix_acl.c b/fs/posix_acl.c index f5c25f580dd9..f7cacce3c3e2 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -23,6 +23,7 @@ #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> +#include <linux/mnt_idmapping.h>

static struct posix_acl **acl_by_type(struct inode *inode, int type) { diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index c174262a074e..09a8fba84ff9 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -61,6 +61,7 @@ typedef __u32 xfs_nlink_t; #include <linux/ratelimit.h> #include <linux/rhashtable.h> #include <linux/xattr.h> +#include <linux/mnt_idmapping.h>

#include <asm/page.h> #include <asm/div64.h> diff --git a/include/linux/fs.h b/include/linux/fs.h index 5720473b94b1..b1d446d71c3f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -41,6 +41,7 @@ #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> +#include <linux/mnt_idmapping.h>

#include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -1626,34 +1627,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); }

-/** - * kuid_into_mnt - map a kuid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return make_kuid(mnt_userns, __kuid_val(kuid)); -} - -/** - * kgid_into_mnt - map a kgid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return make_kgid(mnt_userns, __kgid_val(kgid)); -} - /** * i_uid_into_mnt - map an inode's i_uid down into a mnt_userns * @mnt_userns: user namespace of the mount the inode was found from @@ -1682,68 +1655,6 @@ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, return kgid_into_mnt(mnt_userns, inode->i_gid); }

-/** - * kuid_from_mnt - map a kuid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped up according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return KUIDT_INIT(from_kuid(mnt_userns, kuid)); -} - -/** - * kgid_from_mnt - map a kgid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped up according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return KGIDT_INIT(from_kgid(mnt_userns, kgid)); -} - -/** - * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsuid. A common example is initializing the i_uid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsuid mapped up according to @mnt_userns. - */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) -{ - return kuid_from_mnt(mnt_userns, current_fsuid()); -} - -/** - * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsgid. A common example is initializing the i_gid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsgid mapped up according to @mnt_userns. - */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) -{ - return kgid_from_mnt(mnt_userns, current_fsgid()); -} - /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h new file mode 100644 index 000000000000..47c7811fadfe --- /dev/null +++ b/include/linux/mnt_idmapping.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MNT_IDMAPPING_H +#define _LINUX_MNT_IDMAPPING_H + +#include <linux/types.h> +#include <linux/uidgid.h> + +struct user_namespace; +extern struct user_namespace init_user_ns; + +/** + * kuid_into_mnt - map a kuid down into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kuid: kuid to be mapped + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping INVALID_UID is returned. + */ +static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return make_kuid(mnt_userns, __kuid_val(kuid)); +} + +/** + * kgid_into_mnt - map a kgid down into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kgid: kgid to be mapped + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping INVALID_GID is returned. + */ +static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return make_kgid(mnt_userns, __kgid_val(kgid)); +} + +/** + * kuid_from_mnt - map a kuid up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kuid: kuid to be mapped + * + * Return: @kuid mapped up according to @mnt_userns. + * If @kuid has no mapping INVALID_UID is returned. + */ +static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return KUIDT_INIT(from_kuid(mnt_userns, kuid)); +} + +/** + * kgid_from_mnt - map a kgid up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kgid: kgid to be mapped + * + * Return: @kgid mapped up according to @mnt_userns. + * If @kgid has no mapping INVALID_GID is returned. + */ +static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return KGIDT_INIT(from_kgid(mnt_userns, kgid)); +} + +/** + * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsuid. A common example is initializing the i_uid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsuid mapped up according to @mnt_userns. + */ +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) +{ + return kuid_from_mnt(mnt_userns, current_fsuid()); +} + +/** + * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsgid. A common example is initializing the i_gid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsgid mapped up according to @mnt_userns. + */ +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) +{ + return kgid_from_mnt(mnt_userns, current_fsgid()); +} + +#endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/security/commoncap.c b/security/commoncap.c index 3f810d37b71b..09479f71ee2e 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -24,6 +24,7 @@ #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> +#include <linux/mnt_idmapping.h>

/* * If a non-root user executes a setuid-root binary in

From: Christian Brauner christian.brauner@ubuntu.com

commit 1ac2a4104968e0a60b4b3572216a92aab5c1b025 upstream.

Currently we only support idmapped mounts for filesystems mounted without an idmapping. This was a conscious decision mentioned in multiple places (cf. e.g. [1]).

As explained at length in [3] it is perfectly fine to extend support for idmapped mounts to filesystem's mounted with an idmapping should the need arise. The need has been there for some time now. Various container projects in userspace need this to run unprivileged and nested unprivileged containers (cf. [2]).

Before we can port any filesystem that is mountable with an idmapping to support idmapped mounts we need to first extend the mapping helpers to account for the filesystem's idmapping. This again, is explained at length in our documentation at [3] but I'll give an overview here again.

Currently, the low-level mapping helpers implement the remapping algorithms described in [3] in a simplified manner. Because we could rely on the fact that all filesystems supporting idmapped mounts are mounted without an idmapping the translation step from or into the filesystem idmapping could be skipped.

In order to support idmapped mounts of filesystem's mountable with an idmapping the translation step we were able to skip before cannot be skipped anymore. A filesystem mounted with an idmapping is very likely to not use an identity mapping and will instead use a non-identity mapping. So the translation step from or into the filesystem's idmapping in the remapping algorithm cannot be skipped for such filesystems. More details with examples can be found in [3].

This patch adds a few new and prepares some already existing low-level mapping helpers to perform the full translation algorithm explained in [3]. The low-level helpers can be written in a way that they only perform the additional translation step when the filesystem is indeed mounted with an idmapping.

If the low-level helpers detect that they are not dealing with an idmapped mount they can simply return the relevant k{g,u}id unchanged; no remapping needs to be performed at all. The no_idmapping() helper detects whether the shortcut can be used.

If the low-level helpers detected that they are dealing with an idmapped mount but the underlying filesystem is mounted without an idmapping we can rely on the previous shorcut and can continue to skip the translation step from or into the filesystem's idmapping.

These checks guarantee that only the minimal amount of work is performed. As before, if idmapped mounts aren't used the low-level helpers are idempotent and no work is performed at all.

This patch adds the helpers mapped_k{g,u}id_fs() and mapped_k{g,u}id_user(). Following patches will port all places to replace the old k{g,u}id_into_mnt() and k{g,u}id_from_mnt() with these two new helpers. After the conversion is done k{g,u}id_into_mnt() and k{g,u}id_from_mnt() will be removed. This also concludes the renaming of the mapping helpers we started in [4]. Now, all mapping helpers will started with the "mapped_" prefix making everything nice and consistent.

The mapped_k{g,u}id_fs() helpers replace the k{g,u}id_into_mnt() helpers. They are to be used when k{g,u}ids are to be mapped from the vfs, e.g. from from struct inode's i_{g,u}id. Conversely, the mapped_k{g,u}id_user() helpers replace the k{g,u}id_from_mnt() helpers. They are to be used when k{g,u}ids are to be written to disk, e.g. when entering from a system call to change ownership of a file.

This patch only introduces the helpers. It doesn't yet convert the relevant places to account for filesystem mounted with an idmapping.

[1]: commit 2ca4dcc4909d ("fs/mount_setattr: tighten permission checks") [2]: https://github.com/containers/podman/issues/10374 [3]: Documentations/filesystems/idmappings.rst [4]: commit a65e58e791a1 ("fs: document and rename fsid helpers")

Link: https://lore.kernel.org/r/20211123114227.3124056-5-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-5-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-5-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Amir Goldstein amir73il@gmail.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org --- include/linux/fs.h | 4 +- include/linux/mnt_idmapping.h | 193 +++++++++++++++++++++++++++++++++- 2 files changed, 191 insertions(+), 6 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h index ffc06557618c..889f2e9be028 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1638,7 +1638,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kuid_into_mnt(mnt_userns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, &init_user_ns, inode->i_uid); }

/** @@ -1652,7 +1652,7 @@ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kgid_into_mnt(mnt_userns, inode->i_gid); + return mapped_kgid_fs(mnt_userns, &init_user_ns, inode->i_gid); }

/** diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 47c7811fadfe..60341cd33ccc 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -6,6 +6,11 @@ #include <linux/uidgid.h>

struct user_namespace; +/* + * Carries the initial idmapping of 0:0:4294967295 which is an identity + * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is + * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. + */ extern struct user_namespace init_user_ns;

/** @@ -64,9 +69,189 @@ static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, return KGIDT_INIT(from_kgid(mnt_userns, kgid)); }

+/** + * initial_idmapping - check whether this is the initial mapping + * @ns: idmapping to check + * + * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, + * [...], 1000 to 1000 [...]. + * + * Return: true if this is the initial mapping, false if not. + */ +static inline bool initial_idmapping(const struct user_namespace *ns) +{ + return ns == &init_user_ns; +} + +/** + * no_idmapping - check whether we can skip remapping a kuid/gid + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * This function can be used to check whether a remapping between two + * idmappings is required. + * An idmapped mount is a mount that has an idmapping attached to it that + * is different from the filsystem's idmapping and the initial idmapping. + * If the initial mapping is used or the idmapping of the mount and the + * filesystem are identical no remapping is required. + * + * Return: true if remapping can be skipped, false if not. + */ +static inline bool no_idmapping(const struct user_namespace *mnt_userns, + const struct user_namespace *fs_userns) +{ + return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; +} + +/** + * mapped_kuid_fs - map a filesystem kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kuid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * from_kuid() so we can simply retrieve the value via __kuid_val() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + if (initial_idmapping(fs_userns)) + uid = __kuid_val(kuid); + else + uid = from_kuid(fs_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + return make_kuid(mnt_userns, uid); +} + +/** + * mapped_kgid_fs - map a filesystem kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kgid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * from_kgid() so we can simply retrieve the value via __kgid_val() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + if (initial_idmapping(fs_userns)) + gid = __kgid_val(kgid); + else + gid = from_kgid(fs_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + return make_kgid(mnt_userns, gid); +} + +/** + * mapped_kuid_user - map a user kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kuid into @fs_userns. Use this + * function when preparing a @kuid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * make_kuid() so we can simply retrieve the value via KUIDT_INIT() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + uid = from_kuid(mnt_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + if (initial_idmapping(fs_userns)) + return KUIDT_INIT(uid); + return make_kuid(fs_userns, uid); +} + +/** + * mapped_kgid_user - map a user kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kgid into @fs_userns. Use this + * function when preparing a @kgid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * make_kgid() so we can simply retrieve the value via KGIDT_INIT() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + gid = from_kgid(mnt_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + if (initial_idmapping(fs_userns)) + return KGIDT_INIT(gid); + return make_kgid(fs_userns, gid); +} + /** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount + * @mnt_userns: the mount's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of @@ -78,12 +263,12 @@ static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, */ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) { - return kuid_from_mnt(mnt_userns, current_fsuid()); + return mapped_kuid_user(mnt_userns, &init_user_ns, current_fsuid()); }

/** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount + * @mnt_userns: the mount's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of @@ -95,7 +280,7 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) */ static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) { - return kgid_from_mnt(mnt_userns, current_fsgid()); + return mapped_kgid_user(mnt_userns, &init_user_ns, current_fsgid()); }

#endif /* _LINUX_MNT_IDMAPPING_H */

From: Christian Brauner christian.brauner@ubuntu.com

commit 4472071331549e911a5abad41aea6e3be855a1a4 upstream.

In a few places the vfs needs to interact with bare k{g,u}ids directly instead of struct inode. These are just a few. In previous patches we introduced low-level mapping helpers that are able to support filesystems mounted an idmapping. This patch simply converts the places to use these new helpers.

Link: https://lore.kernel.org/r/20211123114227.3124056-7-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-7-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-7-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Amir Goldstein amir73il@gmail.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org --- fs/ksmbd/smbacl.c | 18 ++---------------- fs/ksmbd/smbacl.h | 4 ++-- fs/open.c | 4 ++-- fs/posix_acl.c | 16 ++++++++++------ security/commoncap.c | 13 ++++++++----- 5 files changed, 24 insertions(+), 31 deletions(-)

diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index 7a6675fe57f7..38f23bf981ac 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -275,14 +275,7 @@ static int sid_to_id(struct user_namespace *user_ns, uid_t id;

id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); - /* - * Translate raw sid into kuid in the server's user - * namespace. - */ - uid = make_kuid(&init_user_ns, id); - - /* If this is an idmapped mount, apply the idmapping. */ - uid = kuid_from_mnt(user_ns, uid); + uid = mapped_kuid_user(user_ns, &init_user_ns, KUIDT_INIT(id)); if (uid_valid(uid)) { fattr->cf_uid = uid; rc = 0; @@ -292,14 +285,7 @@ static int sid_to_id(struct user_namespace *user_ns, gid_t id;

id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); - /* - * Translate raw sid into kgid in the server's user - * namespace. - */ - gid = make_kgid(&init_user_ns, id); - - /* If this is an idmapped mount, apply the idmapping. */ - gid = kgid_from_mnt(user_ns, gid); + gid = mapped_kgid_user(user_ns, &init_user_ns, KGIDT_INIT(id)); if (gid_valid(gid)) { fattr->cf_gid = gid; rc = 0; diff --git a/fs/ksmbd/smbacl.h b/fs/ksmbd/smbacl.h index eba1ebb9e92e..811af3309429 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -217,7 +217,7 @@ static inline uid_t posix_acl_uid_translate(struct user_namespace *mnt_userns, kuid_t kuid;

/* If this is an idmapped mount, apply the idmapping. */ - kuid = kuid_into_mnt(mnt_userns, pace->e_uid); + kuid = mapped_kuid_fs(mnt_userns, &init_user_ns, pace->e_uid);

/* Translate the kuid into a userspace id ksmbd would see. */ return from_kuid(&init_user_ns, kuid); @@ -229,7 +229,7 @@ static inline gid_t posix_acl_gid_translate(struct user_namespace *mnt_userns, kgid_t kgid;

/* If this is an idmapped mount, apply the idmapping. */ - kgid = kgid_into_mnt(mnt_userns, pace->e_gid); + kgid = mapped_kgid_fs(mnt_userns, &init_user_ns, pace->e_gid);

/* Translate the kgid into a userspace id ksmbd would see. */ return from_kgid(&init_user_ns, kgid); diff --git a/fs/open.c b/fs/open.c index 3d2a95ca6404..31c47abbddf6 100644 --- a/fs/open.c +++ b/fs/open.c @@ -653,8 +653,8 @@ int chown_common(const struct path *path, uid_t user, gid_t group) gid = make_kgid(current_user_ns(), group);

mnt_userns = mnt_user_ns(path->mnt); - uid = kuid_from_mnt(mnt_userns, uid); - gid = kgid_from_mnt(mnt_userns, gid); + uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); + gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid);

retry_deleg: newattrs.ia_valid = ATTR_CTIME; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index f7cacce3c3e2..3d7ee193424a 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -376,7 +376,9 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, goto check_perm; break; case ACL_USER: - uid = kuid_into_mnt(mnt_userns, pa->e_uid); + uid = mapped_kuid_fs(mnt_userns, + &init_user_ns, + pa->e_uid); if (uid_eq(uid, current_fsuid())) goto mask; break; @@ -389,7 +391,9 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, } break; case ACL_GROUP: - gid = kgid_into_mnt(mnt_userns, pa->e_gid); + gid = mapped_kgid_fs(mnt_userns, + &init_user_ns, + pa->e_gid); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) @@ -736,17 +740,17 @@ static void posix_acl_fix_xattr_userns( case ACL_USER: uid = make_kuid(from, le32_to_cpu(entry->e_id)); if (from_user) - uid = kuid_from_mnt(mnt_userns, uid); + uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); else - uid = kuid_into_mnt(mnt_userns, uid); + uid = mapped_kuid_fs(mnt_userns, &init_user_ns, uid); entry->e_id = cpu_to_le32(from_kuid(to, uid)); break; case ACL_GROUP: gid = make_kgid(from, le32_to_cpu(entry->e_id)); if (from_user) - gid = kgid_from_mnt(mnt_userns, gid); + gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid); else - gid = kgid_into_mnt(mnt_userns, gid); + gid = mapped_kgid_fs(mnt_userns, &init_user_ns, gid); entry->e_id = cpu_to_le32(from_kgid(to, gid)); break; default: diff --git a/security/commoncap.c b/security/commoncap.c index 09479f71ee2e..d288a62e2999 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -419,7 +419,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, kroot = make_kuid(fs_ns, root);

/* If this is an idmapped mount shift the kuid. */ - kroot = kuid_into_mnt(mnt_userns, kroot); + kroot = mapped_kuid_fs(mnt_userns, &init_user_ns, kroot);

/* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ @@ -489,6 +489,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, * @size: size of @ivalue * @task_ns: user namespace of the caller * @mnt_userns: user namespace of the mount the inode was found from + * @fs_userns: user namespace of the filesystem * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then @@ -498,7 +499,8 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, */ static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns, - struct user_namespace *mnt_userns) + struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { const struct vfs_ns_cap_data *nscap = value; kuid_t rootkid; @@ -508,7 +510,7 @@ static kuid_t rootid_from_xattr(const void *value, size_t size, rootid = le32_to_cpu(nscap->rootid);

rootkid = make_kuid(task_ns, rootid); - return kuid_from_mnt(mnt_userns, rootkid); + return mapped_kuid_user(mnt_userns, fs_userns, rootkid); }

static bool validheader(size_t size, const struct vfs_cap_data *cap) @@ -559,7 +561,8 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, /* user is privileged, just write the v2 */ return size;

- rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns); + rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, + &init_user_ns); if (!uid_valid(rootid)) return -EINVAL;

@@ -700,7 +703,7 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ - rootkuid = kuid_into_mnt(mnt_userns, rootkuid); + rootkuid = mapped_kuid_fs(mnt_userns, &init_user_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA;

From: Christian Brauner christian.brauner@ubuntu.com

commit 209188ce75d0d357c292f6bb81d712acdd4e7db7 upstream.

Enable the mapped_fs{g,u}id() helpers to support filesystems mounted with an idmapping. Apart from core mapping helpers that use mapped_fs{g,u}id() to initialize struct inode's i_{g,u}id fields xfs is the only place that uses these low-level helpers directly.

The patch only extends the helpers to be able to take the filesystem idmapping into account. Since we don't actually yet pass the filesystem's idmapping in no functional changes happen. This will happen in a final patch.

Link: https://lore.kernel.org/r/20211123114227.3124056-9-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-9-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-9-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein amir73il@gmail.com Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org --- fs/xfs/xfs_inode.c | 8 ++++---- fs/xfs/xfs_symlink.c | 4 ++-- include/linux/fs.h | 8 ++++---- include/linux/mnt_idmapping.h | 12 ++++++++---- 4 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index a4f6f034fb81..2477e301fa82 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -994,8 +994,8 @@ xfs_create( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1148,8 +1148,8 @@ xfs_create_tmpfile( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index fc2c6a404647..a31d2e5d0321 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -184,8 +184,8 @@ xfs_symlink( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/include/linux/fs.h b/include/linux/fs.h index 889f2e9be028..f62c1b9cd7cd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1666,7 +1666,7 @@ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns); + inode->i_uid = mapped_fsuid(mnt_userns, &init_user_ns); }

/** @@ -1680,7 +1680,7 @@ static inline void inode_fsuid_set(struct inode *inode, static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns); + inode->i_gid = mapped_fsgid(mnt_userns, &init_user_ns); }

/** @@ -1701,10 +1701,10 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, kuid_t kuid; kgid_t kgid;

- kuid = mapped_fsuid(mnt_userns); + kuid = mapped_fsuid(mnt_userns, &init_user_ns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns); + kgid = mapped_fsgid(mnt_userns, &init_user_ns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 0c6ab3f4c952..ee5a217de2a8 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -196,6 +196,7 @@ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, /** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of @@ -205,14 +206,16 @@ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, * * Return: the caller's current fsuid mapped up according to @mnt_userns. */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { - return mapped_kuid_user(mnt_userns, &init_user_ns, current_fsuid()); + return mapped_kuid_user(mnt_userns, fs_userns, current_fsuid()); }

/** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of @@ -222,9 +225,10 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) * * Return: the caller's current fsgid mapped up according to @mnt_userns. */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { - return mapped_kgid_user(mnt_userns, &init_user_ns, current_fsgid()); + return mapped_kgid_user(mnt_userns, fs_userns, current_fsgid()); }

#endif /* _LINUX_MNT_IDMAPPING_H */

From: Christian Brauner christian.brauner@ubuntu.com

commit bd303368b776eead1c29e6cdda82bde7128b82a7 upstream.

In previous patches we added new and modified existing helpers to handle idmapped mounts of filesystems mounted with an idmapping. In this final patch we convert all relevant places in the vfs to actually pass the filesystem's idmapping into these helpers.

With this the vfs is in shape to handle idmapped mounts of filesystems mounted with an idmapping. Note that this is just the generic infrastructure. Actually adding support for idmapped mounts to a filesystem mountable with an idmapping is follow-up work.

In this patch we extend the definition of an idmapped mount from a mount that that has the initial idmapping attached to it to a mount that has an idmapping attached to it which is not the same as the idmapping the filesystem was mounted with.

As before we do not allow the initial idmapping to be attached to a mount. In addition this patch prevents that the idmapping the filesystem was mounted with can be attached to a mount created based on this filesystem.

This has multiple reasons and advantages. First, attaching the initial idmapping or the filesystem's idmapping doesn't make much sense as in both cases the values of the i_{g,u}id and other places where k{g,u}ids are used do not change. Second, a user that really wants to do this for whatever reason can just create a separate dedicated identical idmapping to attach to the mount. Third, we can continue to use the initial idmapping as an indicator that a mount is not idmapped allowing us to continue to keep passing the initial idmapping into the mapping helpers to tell them that something isn't an idmapped mount even if the filesystem is mounted with an idmapping.

Link: https://lore.kernel.org/r/20211123114227.3124056-11-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-11-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-11-brauner@kernel.org Cc: Seth Forshee sforshee@digitalocean.com Cc: Amir Goldstein amir73il@gmail.com Cc: Christoph Hellwig hch@lst.de Cc: Al Viro viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org --- fs/namespace.c | 51 +++++++++++++++++++++++++++++++++----------- fs/open.c | 7 +++--- fs/posix_acl.c | 8 +++---- include/linux/fs.h | 17 ++++++++------- security/commoncap.c | 9 ++++---- 5 files changed, 59 insertions(+), 33 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c index 5b5aa107b9f3..dc31ad6b370f 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -31,6 +31,7 @@ #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> +#include <linux/mnt_idmapping.h>

#include "pnode.h" #include "internal.h" @@ -561,7 +562,7 @@ static void free_vfsmnt(struct mount *mnt) struct user_namespace *mnt_userns;

mnt_userns = mnt_user_ns(&mnt->mnt); - if (mnt_userns != &init_user_ns) + if (!initial_idmapping(mnt_userns)) put_user_ns(mnt_userns); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP @@ -965,6 +966,7 @@ static struct mount *skip_mnt_tree(struct mount *p) struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; + struct user_namespace *fs_userns;

if (!fc->root) return ERR_PTR(-EINVAL); @@ -982,6 +984,10 @@ struct vfsmount *vfs_create_mount(struct fs_context *fc) mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt;

+ fs_userns = mnt->mnt.mnt_sb->s_user_ns; + if (!initial_idmapping(fs_userns)) + mnt->mnt.mnt_userns = get_user_ns(fs_userns); + lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); @@ -1072,7 +1078,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,

atomic_inc(&sb->s_active); mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt); - if (mnt->mnt.mnt_userns != &init_user_ns) + if (!initial_idmapping(mnt->mnt.mnt_userns)) mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); @@ -3927,10 +3933,18 @@ static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; + struct user_namespace *fs_userns = m->mnt_sb->s_user_ns;

if (!kattr->mnt_userns) return 0;

+ /* + * Creating an idmapped mount with the filesystem wide idmapping + * doesn't make sense so block that. We don't allow mushy semantics. + */ + if (kattr->mnt_userns == fs_userns) + return -EINVAL; + /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create @@ -3943,12 +3957,8 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL;

- /* Don't yet support filesystem mountable in user namespaces. */ - if (m->mnt_sb->s_user_ns != &init_user_ns) - return -EINVAL; - /* We're not controlling the superblock. */ - if (!capable(CAP_SYS_ADMIN)) + if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM;

/* Mount has already been visible in the filesystem hierarchy. */ @@ -4002,14 +4012,27 @@ static struct mount *mount_setattr_prepare(struct mount_kattr *kattr,

static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { - struct user_namespace *mnt_userns; + struct user_namespace *mnt_userns, *old_mnt_userns;

if (!kattr->mnt_userns) return;

+ /* + * We're the only ones able to change the mount's idmapping. So + * mnt->mnt.mnt_userns is stable and we can retrieve it directly. + */ + old_mnt_userns = mnt->mnt.mnt_userns; + mnt_userns = get_user_ns(kattr->mnt_userns); /* Pairs with smp_load_acquire() in mnt_user_ns(). */ smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); + + /* + * If this is an idmapped filesystem drop the reference we've taken + * in vfs_create_mount() before. + */ + if (!initial_idmapping(old_mnt_userns)) + put_user_ns(old_mnt_userns); }

static void mount_setattr_commit(struct mount_kattr *kattr, @@ -4133,13 +4156,15 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, }

/* - * The init_user_ns is used to indicate that a vfsmount is not idmapped. - * This is simpler than just having to treat NULL as unmapped. Users - * wanting to idmap a mount to init_user_ns can just use a namespace - * with an identity mapping. + * The initial idmapping cannot be used to create an idmapped + * mount. We use the initial idmapping as an indicator of a mount + * that is not idmapped. It can simply be passed into helpers that + * are aware of idmapped mounts as a convenient shortcut. A user + * can just create a dedicated identity mapping to achieve the same + * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); - if (mnt_userns == &init_user_ns) { + if (initial_idmapping(mnt_userns)) { err = -EPERM; goto out_fput; } diff --git a/fs/open.c b/fs/open.c index 31c47abbddf6..1ba1d2ab2ef0 100644 --- a/fs/open.c +++ b/fs/open.c @@ -641,7 +641,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)

int chown_common(const struct path *path, uid_t user, gid_t group) { - struct user_namespace *mnt_userns; + struct user_namespace *mnt_userns, *fs_userns; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; @@ -653,8 +653,9 @@ int chown_common(const struct path *path, uid_t user, gid_t group) gid = make_kgid(current_user_ns(), group);

mnt_userns = mnt_user_ns(path->mnt); - uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); - gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid); + fs_userns = i_user_ns(inode); + uid = mapped_kuid_user(mnt_userns, fs_userns, uid); + gid = mapped_kgid_user(mnt_userns, fs_userns, gid);

retry_deleg: newattrs.ia_valid = ATTR_CTIME; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 3d7ee193424a..d6c7b620fb8f 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -377,8 +377,8 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, break; case ACL_USER: uid = mapped_kuid_fs(mnt_userns, - &init_user_ns, - pa->e_uid); + i_user_ns(inode), + pa->e_uid); if (uid_eq(uid, current_fsuid())) goto mask; break; @@ -392,8 +392,8 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, break; case ACL_GROUP: gid = mapped_kgid_fs(mnt_userns, - &init_user_ns, - pa->e_gid); + i_user_ns(inode), + pa->e_gid); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) diff --git a/include/linux/fs.h b/include/linux/fs.h index d418dffb1681..76162f046670 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1643,7 +1643,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kuid_fs(mnt_userns, &init_user_ns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid); }

/** @@ -1657,7 +1657,7 @@ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kgid_fs(mnt_userns, &init_user_ns, inode->i_gid); + return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid); }

/** @@ -1671,7 +1671,7 @@ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns, &init_user_ns); + inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); }

/** @@ -1685,7 +1685,7 @@ static inline void inode_fsuid_set(struct inode *inode, static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns, &init_user_ns); + inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); }

/** @@ -1706,10 +1706,10 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, kuid_t kuid; kgid_t kgid;

- kuid = mapped_fsuid(mnt_userns, &init_user_ns); + kuid = mapped_fsuid(mnt_userns, fs_userns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns, &init_user_ns); + kgid = mapped_fsgid(mnt_userns, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && @@ -2655,13 +2655,14 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * - * If @mnt has an idmapping attached to it @mnt is mapped. + * If @mnt has an idmapping attached different from the + * filesystem's idmapping then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { - return mnt_user_ns(mnt) != &init_user_ns; + return mnt_user_ns(mnt) != mnt->mnt_sb->s_user_ns; }

extern long vfs_truncate(const struct path *, loff_t); diff --git a/security/commoncap.c b/security/commoncap.c index d288a62e2999..5fc8986c3c77 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -419,7 +419,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, kroot = make_kuid(fs_ns, root);

/* If this is an idmapped mount shift the kuid. */ - kroot = mapped_kuid_fs(mnt_userns, &init_user_ns, kroot); + kroot = mapped_kuid_fs(mnt_userns, fs_ns, kroot);

/* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ @@ -556,13 +556,12 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; - if (size == XATTR_CAPS_SZ_2 && (mnt_userns == &init_user_ns)) + if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size;

- rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, - &init_user_ns); + rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, fs_ns); if (!uid_valid(rootid)) return -EINVAL;

@@ -703,7 +702,7 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ - rootkuid = mapped_kuid_fs(mnt_userns, &init_user_ns, rootkuid); + rootkuid = mapped_kuid_fs(mnt_userns, fs_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA;

commit 168f912893407a5acb798a4a58613b5f1f98c717 upstream.

When calling setattr_prepare() to determine the validity of the attributes the ia_{g,u}id fields contain the value that will be written to inode->i_{g,u}id. This is exactly the same for idmapped and non-idmapped mounts and allows callers to pass in the values they want to see written to inode->i_{g,u}id.

When group ownership is changed a caller whose fsuid owns the inode can change the group of the inode to any group they are a member of. When searching through the caller's groups we need to use the gid mapped according to the idmapped mount otherwise we will fail to change ownership for unprivileged users.

Consider a caller running with fsuid and fsgid 1000 using an idmapped mount that maps id 65534 to 1000 and 65535 to 1001. Consequently, a file owned by 65534:65535 in the filesystem will be owned by 1000:1001 in the idmapped mount.

The caller now requests the gid of the file to be changed to 1000 going through the idmapped mount. In the vfs we will immediately map the requested gid to the value that will need to be written to inode->i_gid and place it in attr->ia_gid. Since this idmapped mount maps 65534 to 1000 we place 65534 in attr->ia_gid.

When we check whether the caller is allowed to change group ownership we first validate that their fsuid matches the inode's uid. The inode->i_uid is 65534 which is mapped to uid 1000 in the idmapped mount. Since the caller's fsuid is 1000 we pass the check.

We now check whether the caller is allowed to change inode->i_gid to the requested gid by calling in_group_p(). This will compare the passed in gid to the caller's fsgid and search the caller's additional groups.

Since we're dealing with an idmapped mount we need to pass in the gid mapped according to the idmapped mount. This is akin to checking whether a caller is privileged over the future group the inode is owned by. And that needs to take the idmapped mount into account. Note, all helpers are nops without idmapped mounts.

New regression test sent to xfstests.

Link: https://github.com/lxc/lxd/issues/10537 Link: https://lore.kernel.org/r/20220613111517.2186646-1-brauner@kernel.org Fixes: 2f221d6f7b88 ("attr: handle idmapped mounts") Cc: Seth Forshee sforshee@digitalocean.com Cc: Christoph Hellwig hch@lst.de Cc: Aleksa Sarai cyphar@cyphar.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: stable@vger.kernel.org # 5.15+ CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee sforshee@digitalocean.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org --- fs/attr.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/fs/attr.c b/fs/attr.c index 66899b6e9bd8..dbe996b0dedf 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -61,9 +61,15 @@ static bool chgrp_ok(struct user_namespace *mnt_userns, const struct inode *inode, kgid_t gid) { kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); - if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) && - (in_group_p(gid) || gid_eq(gid, inode->i_gid))) - return true; + if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) { + kgid_t mapped_gid; + + if (gid_eq(gid, inode->i_gid)) + return true; + mapped_gid = mapped_kgid_fs(mnt_userns, i_user_ns(inode), gid); + if (in_group_p(mapped_gid)) + return true; + } if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; if (gid_eq(kgid, INVALID_GID) && @@ -123,12 +129,20 @@ int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,

/* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { + kgid_t mapped_gid; + if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; + + if (ia_valid & ATTR_GID) + mapped_gid = mapped_kgid_fs(mnt_userns, + i_user_ns(inode), attr->ia_gid); + else + mapped_gid = i_gid_into_mnt(mnt_userns, inode); + /* Also check the setgid bit! */ - if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : - i_gid_into_mnt(mnt_userns, inode)) && - !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) + if (!in_group_p(mapped_gid) && + !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; }