Merge tag 'fs.idmapped.v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull fs idmapping updates from Christian Brauner:
 "This contains the work to enable the idmapping infrastructure to
  support idmapped mounts of filesystems mounted with an idmapping.

  In addition this contains various cleanups that avoid repeated
  open-coding of the same functionality and simplify the code in quite a
  few places.

  We also finish the renaming of the mapping helpers we started a few
  kernel releases back and move them to a dedicated header to not
  continue polluting the fs header needlessly with low-level idmapping
  helpers. With this series the fs header only contains idmapping
  helpers that interact with fs objects.

  Currently we only support idmapped mounts for filesystems mounted
  without an idmapping themselves. This was a conscious decision
  mentioned in multiple places (cf. [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 (cf. [2]).

  Before we can port any filesystem that is mountable with an idmapping
  to support idmapped mounts in the coming cycles, 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] and
  also in the individual commit messages so here's an overview.

  Currently, the low-level mapping helpers implement the remapping
  algorithms described in [3] in a simplified manner as we could rely on
  the fact that all filesystems supporting idmapped mounts are mounted
  without an idmapping.

  In contrast, filesystems mounted with an idmapping are 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.

  Non-idmapped filesystems and filesystems not supporting idmapped
  mounts are unaffected by this change as the remapping algorithms can
  take the same shortcut as before. If the low-level helpers detect that
  they are dealing with an idmapped mount but the underlying filesystem
  is mounted without an idmapping we can rely on the previous shortcut
  and can continue to skip the translation step from or into the
  filesystem's idmapping. And of course, if the low-level helpers detect
  that they are not dealing with an idmapped mount they can simply
  return the relevant id unchanged; no remapping needs to be performed
  at all.

  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"

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

* tag 'fs.idmapped.v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  fs: support mapped mounts of mapped filesystems
  fs: add i_user_ns() helper
  fs: port higher-level mapping helpers
  fs: remove unused low-level mapping helpers
  fs: use low-level mapping helpers
  docs: update mapping documentation
  fs: account for filesystem mappings
  fs: tweak fsuidgid_has_mapping()
  fs: move mapping helpers
  fs: add is_idmapped_mnt() helper

2 files changed, 274 insertions, 101 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbf812ce89a8..493b87e3616b 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>
@@ -1599,6 +1600,11 @@ struct super_block {
 	struct list_head	s_inodes_wb;	/* writeback inodes */
 } __randomize_layout;
 
+static inline struct user_namespace *i_user_ns(const struct inode *inode)
+{
+	return inode->i_sb->s_user_ns;
+}
+
 /* Helper functions so that in most cases filesystems will
  * not need to deal directly with kuid_t and kgid_t and can
  * instead deal with the raw numeric values that are stored
@@ -1606,50 +1612,22 @@ struct super_block {
  */
 static inline uid_t i_uid_read(const struct inode *inode)
 {
-	return from_kuid(inode->i_sb->s_user_ns, inode->i_uid);
+	return from_kuid(i_user_ns(inode), inode->i_uid);
 }
 
 static inline gid_t i_gid_read(const struct inode *inode)
 {
-	return from_kgid(inode->i_sb->s_user_ns, inode->i_gid);
+	return from_kgid(i_user_ns(inode), inode->i_gid);
 }
 
 static inline void i_uid_write(struct inode *inode, uid_t uid)
 {
-	inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid);
+	inode->i_uid = make_kuid(i_user_ns(inode), uid);
 }
 
 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));
+	inode->i_gid = make_kgid(i_user_ns(inode), gid);
 }
 
 /**
@@ -1663,7 +1641,7 @@ static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns,
 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, i_user_ns(inode), inode->i_uid);
 }
 
 /**
@@ -1677,69 +1655,7 @@ 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);
-}
-
-/**
- * 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());
+	return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid);
 }
 
 /**
@@ -1753,7 +1669,7 @@ static inline kgid_t mapped_fsgid(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, i_user_ns(inode));
 }
 
 /**
@@ -1767,7 +1683,7 @@ 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, i_user_ns(inode));
 }
 
 /**
@@ -1784,10 +1700,18 @@ static inline void inode_fsgid_set(struct inode *inode,
 static inline bool fsuidgid_has_mapping(struct super_block *sb,
 					struct user_namespace *mnt_userns)
 {
-	struct user_namespace *s_user_ns = sb->s_user_ns;
+	struct user_namespace *fs_userns = sb->s_user_ns;
+	kuid_t kuid;
+	kgid_t kgid;
 
-	return kuid_has_mapping(s_user_ns, mapped_fsuid(mnt_userns)) &&
-	       kgid_has_mapping(s_user_ns, mapped_fsgid(mnt_userns));
+	kuid = mapped_fsuid(mnt_userns, fs_userns);
+	if (!uid_valid(kuid))
+		return false;
+	kgid = mapped_fsgid(mnt_userns, fs_userns);
+	if (!gid_valid(kgid))
+		return false;
+	return kuid_has_mapping(fs_userns, kuid) &&
+	       kgid_has_mapping(fs_userns, kgid);
 }
 
 extern struct timespec64 current_time(struct inode *inode);
@@ -2724,6 +2648,21 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file)
 {
 	return mnt_user_ns(file->f_path.mnt);
 }
+
+/**
+ * is_idmapped_mnt - check whether a mount is mapped
+ * @mnt: the mount to check
+ *
+ * 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) != mnt->mnt_sb->s_user_ns;
+}
+
 extern long vfs_truncate(const struct path *, loff_t);
 int do_truncate(struct user_namespace *, struct dentry *, loff_t start,
 		unsigned int time_attrs, struct file *filp);
diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h
new file mode 100644
index 000000000000..ee5a217de2a8
--- /dev/null
+++ b/include/linux/mnt_idmapping.h
@@ -0,0 +1,234 @@
+/* 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;
+/*
+ * 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;
+
+/**
+ * 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: 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
+ * 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,
+				  struct user_namespace *fs_userns)
+{
+	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
+ * 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,
+				  struct user_namespace *fs_userns)
+{
+	return mapped_kgid_user(mnt_userns, fs_userns, current_fsgid());
+}
+
+#endif /* _LINUX_MNT_IDMAPPING_H */