capability: handle idmapped mounts

In order to determine whether a caller holds privilege over a given
inode the capability framework exposes the two helpers
privileged_wrt_inode_uidgid() and capable_wrt_inode_uidgid(). The former
verifies that the inode has a mapping in the caller's user namespace and
the latter additionally verifies that the caller has the requested
capability in their current user namespace.
If the inode is accessed through an idmapped mount map it into the
mount's user namespace. Afterwards the checks are identical to
non-idmapped inodes. If the initial user namespace is passed all
operations are a nop so non-idmapped mounts will not see a change in
behavior.

Link: https://lore.kernel.org/r/20210121131959.646623-5-christian.brauner@ubuntu.com
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

7 files changed, 19 insertions, 14 deletions

diff --git a/fs/attr.c b/fs/attr.c
index b4bbdbd4c8ca..d270f640a192 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -23,7 +23,7 @@ static bool chown_ok(const struct inode *inode, kuid_t uid)
 	if (uid_eq(current_fsuid(), inode->i_uid) &&
 	    uid_eq(uid, inode->i_uid))
 		return true;
-	if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+	if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_CHOWN))
 		return true;
 	if (uid_eq(inode->i_uid, INVALID_UID) &&
 	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
@@ -36,7 +36,7 @@ static bool chgrp_ok(const struct inode *inode, kgid_t gid)
 	if (uid_eq(current_fsuid(), inode->i_uid) &&
 	    (in_group_p(gid) || gid_eq(gid, inode->i_gid)))
 		return true;
-	if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+	if (capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_CHOWN))
 		return true;
 	if (gid_eq(inode->i_gid, INVALID_GID) &&
 	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
@@ -92,7 +92,7 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr)
 		/* Also check the setgid bit! */
 		if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
 				inode->i_gid) &&
-		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
 			attr->ia_mode &= ~S_ISGID;
 	}
 
@@ -193,7 +193,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 		umode_t mode = attr->ia_mode;
 
 		if (!in_group_p(inode->i_gid) &&
-		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
 			mode &= ~S_ISGID;
 		inode->i_mode = mode;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index 5d4d52039105..89d4780ff48f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1411,7 +1411,8 @@ void would_dump(struct linux_binprm *bprm, struct file *file)
 		/* Ensure mm->user_ns contains the executable */
 		user_ns = old = bprm->mm->user_ns;
 		while ((user_ns != &init_user_ns) &&
-		       !privileged_wrt_inode_uidgid(user_ns, inode))
+		       !privileged_wrt_inode_uidgid(user_ns, &init_user_ns,
+						    inode))
 			user_ns = user_ns->parent;
 
 		if (old != user_ns) {
diff --git a/fs/inode.c b/fs/inode.c
index 6442d97d9a4a..cd40cbf87ce4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2146,7 +2146,8 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
 			mode |= S_ISGID;
 		else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
 			 !in_group_p(inode->i_gid) &&
-			 !capable_wrt_inode_uidgid(dir, CAP_FSETID))
+			 !capable_wrt_inode_uidgid(&init_user_ns, dir,
+						   CAP_FSETID))
 			mode &= ~S_ISGID;
 	} else
 		inode->i_gid = current_fsgid();
diff --git a/fs/namei.c b/fs/namei.c
index 78443a85480a..fd4724bce4f5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -357,10 +357,11 @@ int generic_permission(struct inode *inode, int mask)
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
 		if (!(mask & MAY_WRITE))
-			if (capable_wrt_inode_uidgid(inode,
+			if (capable_wrt_inode_uidgid(&init_user_ns, inode,
 						     CAP_DAC_READ_SEARCH))
 				return 0;
-		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+					     CAP_DAC_OVERRIDE))
 			return 0;
 		return -EACCES;
 	}
@@ -370,7 +371,8 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
+		if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+					     CAP_DAC_READ_SEARCH))
 			return 0;
 	/*
 	 * Read/write DACs are always overridable.
@@ -378,7 +380,8 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+					     CAP_DAC_OVERRIDE))
 			return 0;
 
 	return -EACCES;
@@ -2659,7 +2662,7 @@ int __check_sticky(struct inode *dir, struct inode *inode)
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
-	return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
+	return !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FOWNER);
 }
 EXPORT_SYMBOL(__check_sticky);
 
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 2bd570cbe8a4..88d877787770 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1017,7 +1017,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 	if (unlikely(inode->i_mode & S_ISGID) &&
 	    handler->flags == ACL_TYPE_ACCESS &&
 	    !in_group_p(inode->i_gid) &&
-	    !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+	    !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) {
 		struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
 
 		err = ovl_setattr(dentry, &iattr);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 95882b3f5f62..4ca6d53c6f0a 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -656,7 +656,7 @@ int posix_acl_update_mode(struct inode *inode, umode_t *mode_p,
 	if (error == 0)
 		*acl = NULL;
 	if (!in_group_p(inode->i_gid) &&
-	    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+	    !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
 		mode &= ~S_ISGID;
 	*mode_p = mode;
 	return 0;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 3fbd98f61ea5..97bd29fc8c43 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1502,7 +1502,7 @@ xfs_ioctl_setattr(
 	 */
 
 	if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
-	    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
+	    !capable_wrt_inode_uidgid(&init_user_ns, VFS_I(ip), CAP_FSETID))
 		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
 
 	/* Change the ownerships and register project quota modifications */