Introduce v3 namespaced file capabilities
Root in a user ns cannot be trusted to write a traditional
security.capability xattr. If it were allowed to do so, then any
unprivileged user on the host could map his own uid to root in a
namespace, write the xattr, and execute the file with privilege on the
host.
However, supporting file capabilities in a user namespace is very
desirable. Not doing so means that any programs designed to run
with limited privilege must continue to support other methods of
gaining and dropping privilege. For instance a program installer
must detect whether file capabilities can be assigned, and assign
them if so but set setuid-root otherwise.
This patch introduces v3 of the security.capability xattr. It builds a
vfs_ns_cap_data struct by appending a uid_t rootid to struct
vfs_cap_data. This is the absolute uid_t (i.e. the uid_t in
init_user_ns) of the root id (uid 0 in a namespace) in whose namespaces
the file capabilities may take effect.
When a task in a user ns (which is privileged with CAP_SETFCAP toward
that user_ns) asks to write v2 security.capability, the kernel will
transparently rewrite the xattr as a v3 with the appropriate rootid.
Subsequently, any task executing the file which has the noted kuid as
its root uid, or which is in a descendent user_ns of such a user_ns,
will run the file with capabilities.
Similarly when asking to read a v2 capability, a v3 capability will
be presented as v2 if it applies to the caller'snamespace.
If a task writes a v3 security.capability, then it can provide a
uid (valid within its own user namespace, over which it has CAP_SETFCAP)
for the xattr. The kernel will translate that to the absolute uid, and
write that to disk. After this, a task in the writer's namespace will
not be able to use those capabilities, but a task in a namespace where
the given uid is root will.
Only a single security.capability xattr may be written. A task may
overwrite the existing one so long as it was written by a user mapped
into his own user_ns over which he has CAP_SETFCAP.
This allows a simple setxattr to work, allows tar/untar to work, and
allows us to tar in one namespace and untar in another while preserving
the capability, without risking leaking privilege into a parent
namespace.
Changelog:
Nov 02 2016: fix invalid check at refuse_fcap_overwrite()
Nov 07 2016: convert rootid from and to fs user_ns
(From ebiederm: mar 28 2017)
commoncap.c: fix typos - s/v4/v3
get_vfs_caps_from_disk: clarify the fs_ns root access check
nsfscaps: change the code split for cap_inode_setxattr()
Apr 09 2017:
don't return v3 cap for caps owned by current root.
return a v2 cap for a true v2 cap in non-init ns
diff --git a/fs/xattr.c b/fs/xattr.c
index 7e3317c..179918c 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -171,11 +171,33 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
{
struct inode *inode = dentry->d_inode;
int error = -EAGAIN;
+ void *wvalue = NULL;
+ size_t wsize = 0;
int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
- if (issec)
+ if (issec) {
inode->i_flags &= ~S_NOSEC;
+
+ if (!strcmp(name, "security.capability")) {
+ /* Normal semantics for caller in init_user_ns */
+ if (current_user_ns() == &init_user_ns) {
+ if (!capable(CAP_SETFCAP))
+ return -EPERM;
+ } else {
+ /* Root in a non-init user_ns asks to set
+ * security.capability, so we write the virtualized
+ * xattr in its place */
+ cap_setxattr_make_nscap(dentry, value, size,
+ &wvalue, &wsize);
+ if (!wvalue)
+ return -EPERM;
+ value = wvalue;
+ size = wsize;
+ }
+ }
+ }
+
if (inode->i_opflags & IOP_XATTR) {
error = __vfs_setxattr(dentry, inode, name, value, size, flags);
if (!error) {
@@ -184,8 +206,10 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
size, flags);
}
} else {
- if (unlikely(is_bad_inode(inode)))
- return -EIO;
+ if (unlikely(is_bad_inode(inode))) {
+ error = -EIO;
+ goto out;
+ }
}
if (error == -EAGAIN) {
error = -EOPNOTSUPP;
@@ -200,10 +224,11 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
}
}
+out:
+ kfree(wvalue);
return error;
}
-
int
vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags)
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 6ffb67e..5fdc513 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -13,7 +13,7 @@
#define _LINUX_CAPABILITY_H
#include <uapi/linux/capability.h>
-
+#include <linux/uidgid.h>
#define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3
#define _KERNEL_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3
@@ -248,4 +248,7 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
/* audit system wants to get cap info from files as well */
extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
+extern void cap_setxattr_make_nscap(struct dentry *dentry, const void *value,
+ size_t size, void **wvalue, size_t *wsize);
+
#endif /* !_LINUX_CAPABILITY_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index 96899fa..bd49cc1 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -86,6 +86,8 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
extern int cap_inode_need_killpriv(struct dentry *dentry);
extern int cap_inode_killpriv(struct dentry *dentry);
+extern int cap_inode_getsecurity(struct inode *inode, const char *name,
+ void **buffer, bool alloc);
extern int cap_mmap_addr(unsigned long addr);
extern int cap_mmap_file(struct file *file, unsigned long reqprot,
unsigned long prot, unsigned long flags);
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 49bc062..fd4f87d 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -60,9 +60,13 @@ typedef struct __user_cap_data_struct {
#define VFS_CAP_U32_2 2
#define XATTR_CAPS_SZ_2 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2))
-#define XATTR_CAPS_SZ XATTR_CAPS_SZ_2
-#define VFS_CAP_U32 VFS_CAP_U32_2
-#define VFS_CAP_REVISION VFS_CAP_REVISION_2
+#define VFS_CAP_REVISION_3 0x03000000
+#define VFS_CAP_U32_3 2
+#define XATTR_CAPS_SZ_3 (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3))
+
+#define XATTR_CAPS_SZ XATTR_CAPS_SZ_3
+#define VFS_CAP_U32 VFS_CAP_U32_3
+#define VFS_CAP_REVISION VFS_CAP_REVISION_3
struct vfs_cap_data {
__le32 magic_etc; /* Little endian */
@@ -72,6 +76,18 @@ struct vfs_cap_data {
} data[VFS_CAP_U32];
};
+/*
+ * same as vfs_cap_data but with a rootid at the end
+ */
+struct vfs_ns_cap_data {
+ __le32 magic_etc;
+ struct {
+ __le32 permitted; /* Little endian */
+ __le32 inheritable; /* Little endian */
+ } data[VFS_CAP_U32];
+ __le32 rootid;
+};
+
#ifndef __KERNEL__
/*
diff --git a/security/commoncap.c b/security/commoncap.c
index 78b3783..df91a0d 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -332,6 +332,235 @@ int cap_inode_killpriv(struct dentry *dentry)
return error;
}
+static bool rootid_owns_currentns(kuid_t kroot)
+{
+ struct user_namespace *ns;
+
+ if (!uid_valid(kroot))
+ return false;
+
+ for (ns = current_user_ns(); ; ns = ns->parent) {
+ if (from_kuid(ns, kroot) == 0) {
+ return true;
+ }
+ if (ns == &init_user_ns)
+ break;
+ }
+
+ return false;
+}
+
+/*
+ * getsecurity: We are called for security.* before any attempt to read the
+ * xattr from the inode itself.
+ *
+ * This gives us a chance to read the on-disk value and convert it. If we
+ * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler.
+ *
+ * Note we are not called by vfs_getxattr_alloc(), but that is only called
+ * by the integrity subsystem, which really wants the unconverted values -
+ * so that's good.
+ */
+int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
+ bool alloc)
+{
+ int size, ret;
+ kuid_t kroot;
+ uid_t root, mappedroot;
+ char *tmpbuf = NULL;
+ struct vfs_ns_cap_data *nscap;
+ struct dentry *dentry;
+ struct user_namespace *fs_ns;
+
+ if (strcmp(name, "capability") != 0)
+ return -EOPNOTSUPP;
+
+ dentry = d_find_alias(inode);
+ if (!dentry)
+ return -EINVAL;
+
+ size = sizeof(struct vfs_ns_cap_data);
+ ret = vfs_getxattr_alloc(dentry, "security.capability",
+ &tmpbuf, size, GFP_NOFS);
+
+ if (ret < 0)
+ return ret;
+
+ fs_ns = inode->i_sb->s_user_ns;
+ if (ret == sizeof(struct vfs_cap_data) && fs_ns == &init_user_ns) {
+ /* If this is sizeof(vfs_cap_data) then we're ok with the
+ * on-disk value, so return that. */
+ if (alloc)
+ *buffer = tmpbuf;
+ else
+ kfree(tmpbuf);
+ return ret;
+ } else if (ret != sizeof(struct vfs_ns_cap_data)) {
+ kfree(tmpbuf);
+ return -EINVAL;
+ }
+
+ nscap = (struct vfs_ns_cap_data *) tmpbuf;
+ root = le32_to_cpu(nscap->rootid);
+ kroot = make_kuid(fs_ns, root);
+
+ /* If the root kuid maps to a valid uid in current ns, then return
+ * this as a nscap. */
+ mappedroot = from_kuid(current_user_ns(), kroot);
+ if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) {
+ if (alloc) {
+ *buffer = tmpbuf;
+ nscap->rootid = cpu_to_le32(mappedroot);
+ } else
+ kfree(tmpbuf);
+ return size;
+ }
+
+ if (!rootid_owns_currentns(kroot)) {
+ kfree(tmpbuf);
+ return -EOPNOTSUPP;
+ }
+
+ /* This comes from a parent namespace. Return as a v2 capability */
+ size = sizeof(struct vfs_cap_data);
+ if (alloc) {
+ *buffer = kmalloc(size, GFP_ATOMIC);
+ if (*buffer) {
+ struct vfs_cap_data *cap = *buffer;
+ __le32 nsmagic, magic;
+ magic = VFS_CAP_REVISION_2;
+ nsmagic = le32_to_cpu(nscap->magic_etc);
+ if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE)
+ magic |= VFS_CAP_FLAGS_EFFECTIVE;
+ memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+ cap->magic_etc = cpu_to_le32(magic);
+ }
+ }
+ kfree(tmpbuf);
+ return size;
+}
+
+/*
+ * Root can only overwite an existing security.capability xattr
+ * if it is privileged over the root listed in the xattr
+ * Note we've already checked for ns_capable(CAP_SETFCAP) in the
+ * !capable_wrt_inode_uidgid() call by the caller, so we do not
+ * check for that here.
+ */
+static bool refuse_fcap_overwrite(struct inode *inode)
+{
+ void *tmpbuf;
+ int ret;
+ uid_t root;
+ kuid_t kroot;
+ struct vfs_ns_cap_data *nscap;
+ __u32 magic_etc;
+ bool should_refuse;
+ struct user_namespace *fs_ns = inode->i_sb->s_user_ns;
+
+ ret = cap_inode_getsecurity(inode, "capability", &tmpbuf, true);
+ if (ret < 0)
+ return false;
+ if (ret == sizeof(struct vfs_cap_data) && fs_ns == &init_user_ns) {
+ /*
+ * host-root-installed capability, user-namespace-root may
+ * not overwrite this.
+ * TODO - if inode->i_sb->s_user_ns != &init_user_ns we do
+ * in fact want to allow it.
+ */
+ kfree(tmpbuf);
+ return true;
+ }
+ if (ret < sizeof(struct vfs_ns_cap_data)) {
+ /* Corrupt fscap. Caller is privileged wrt inode, permit fixup */
+ kfree(tmpbuf);
+ return false;
+ }
+
+ nscap = (struct vfs_ns_cap_data *)tmpbuf;
+
+ magic_etc = le32_to_cpu(nscap->magic_etc);
+ if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_3) {
+ /*
+ * This version is newer than we know about - i.e. from a newer
+ * kernel. Don't overwrite.
+ */
+ kfree(tmpbuf);
+ return true;
+ }
+ if (ret != sizeof(struct vfs_ns_cap_data)) {
+ /* Corrupt v3 fscap. Permit fixup */
+ kfree(tmpbuf);
+ return false;
+ }
+ root = le32_to_cpu(nscap->rootid);
+ kroot = make_kuid(&init_user_ns, root);
+ should_refuse = !kuid_has_mapping(current_user_ns(), kroot);
+ kfree(tmpbuf);
+ return should_refuse;
+}
+
+static kuid_t rootid_from_xattr(const void *value, size_t size,
+ struct user_namespace *task_ns)
+{
+ const struct vfs_ns_cap_data *nscap = value;
+ uid_t rootid = 0;
+
+ if (size == XATTR_CAPS_SZ_3)
+ rootid = le32_to_cpu(nscap->rootid);
+
+ return make_kuid(task_ns, rootid);
+}
+
+/*
+ * Use requested a write of security.capability but is in a non-init
+ * userns. So we construct and write a v3.
+ *
+ * If all is ok, wvalue has an allocated new value. Otherwise, wvalue
+ * is NULL.
+ */
+void cap_setxattr_make_nscap(struct dentry *dentry, const void *value, size_t size,
+ void **wvalue, size_t *wsize)
+{
+ struct vfs_ns_cap_data *nscap;
+ const struct vfs_cap_data *cap = value;
+ __u32 magic, nsmagic;
+ struct inode *inode = d_backing_inode(dentry);
+ struct user_namespace *task_ns = current_user_ns(),
+ *fs_ns = inode->i_sb->s_user_ns;
+ kuid_t rootid;
+
+ if (!value)
+ return;
+ if (size != XATTR_CAPS_SZ_2 && size != XATTR_CAPS_SZ_3)
+ return;
+ if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP))
+ return;
+
+ /* refuse if security.capability exists */
+ if (refuse_fcap_overwrite(inode))
+ return;
+
+ rootid = rootid_from_xattr(value, size, task_ns);
+ if (!uid_valid(rootid))
+ return;
+
+ *wsize = sizeof(struct vfs_ns_cap_data);
+ nscap = kmalloc(*wsize, GFP_ATOMIC);
+ if (!nscap)
+ return;
+ nscap->rootid = cpu_to_le32(from_kuid(fs_ns, rootid));
+ nsmagic = VFS_CAP_REVISION_3;
+ magic = le32_to_cpu(cap->magic_etc);
+ if (magic & VFS_CAP_FLAGS_EFFECTIVE)
+ nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
+ nscap->magic_etc = cpu_to_le32(nsmagic);
+ memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+
+ *wvalue = nscap;
+ return;
+}
+
/*
* Calculate the new process capability sets from the capability sets attached
* to a file.
@@ -385,7 +614,10 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
__u32 magic_etc;
unsigned tocopy, i;
int size;
- struct vfs_cap_data caps;
+ struct vfs_ns_cap_data data, *nscaps = &data;
+ struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
+ kuid_t rootkuid;
+ struct user_namespace *fs_ns = inode->i_sb->s_user_ns;
memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
@@ -393,18 +625,20 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
return -ENODATA;
size = __vfs_getxattr((struct dentry *)dentry, inode,
- XATTR_NAME_CAPS, &caps, XATTR_CAPS_SZ);
+ XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ);
if (size == -ENODATA || size == -EOPNOTSUPP)
/* no data, that's ok */
return -ENODATA;
+
if (size < 0)
return size;
if (size < sizeof(magic_etc))
return -EINVAL;
- cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc);
+ cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc);
+ rootkuid = make_kuid(fs_ns, 0);
switch (magic_etc & VFS_CAP_REVISION_MASK) {
case VFS_CAP_REVISION_1:
if (size != XATTR_CAPS_SZ_1)
@@ -416,15 +650,27 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
return -EINVAL;
tocopy = VFS_CAP_U32_2;
break;
+ case VFS_CAP_REVISION_3:
+ if (size != XATTR_CAPS_SZ_3)
+ return -EINVAL;
+ tocopy = VFS_CAP_U32_3;
+ rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid));
+ break;
+
default:
return -EINVAL;
}
+ /* Limit the caps to the mounter of the filesystem
+ * or the more limited uid specified in the xattr.
+ */
+ if (!rootid_owns_currentns(rootkuid))
+ return -ENODATA;
CAP_FOR_EACH_U32(i) {
if (i >= tocopy)
break;
- cpu_caps->permitted.cap[i] = le32_to_cpu(caps.data[i].permitted);
- cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
+ cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted);
+ cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable);
}
cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
@@ -462,8 +708,8 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_c
rc = get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps);
if (rc < 0) {
if (rc == -EINVAL)
- printk(KERN_NOTICE "%s: get_vfs_caps_from_disk returned %d for %s\n",
- __func__, rc, bprm->filename);
+ printk(KERN_NOTICE "Invalid argument reading file caps for %s\n",
+ bprm->filename);
else if (rc == -ENODATA)
rc = 0;
goto out;
@@ -660,15 +906,16 @@ int cap_bprm_secureexec(struct linux_binprm *bprm)
int cap_inode_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
- if (!strcmp(name, XATTR_NAME_CAPS)) {
- if (!capable(CAP_SETFCAP))
- return -EPERM;
+ /* Ignore non-security xattrs */
+ if (strncmp(name, XATTR_SECURITY_PREFIX,
+ sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
return 0;
- }
- if (!strncmp(name, XATTR_SECURITY_PREFIX,
- sizeof(XATTR_SECURITY_PREFIX) - 1) &&
- !capable(CAP_SYS_ADMIN))
+ // For XATTR_NAME_CAPS the check will be done in __vfs_setxattr_noperm()
+ if (strcmp(name, XATTR_NAME_CAPS) == 0)
+ return 0;
+
+ if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
@@ -686,15 +933,22 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
*/
int cap_inode_removexattr(struct dentry *dentry, const char *name)
{
- if (!strcmp(name, XATTR_NAME_CAPS)) {
- if (!capable(CAP_SETFCAP))
+ /* Ignore non-security xattrs */
+ if (strncmp(name, XATTR_SECURITY_PREFIX,
+ sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
+ return 0;
+
+ if (strcmp(name, XATTR_NAME_CAPS) == 0) {
+ /* security.capability gets namespaced */
+ struct inode *inode = d_backing_inode(dentry);
+ if (!inode)
+ return -EINVAL;
+ if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP))
return -EPERM;
return 0;
}
- if (!strncmp(name, XATTR_SECURITY_PREFIX,
- sizeof(XATTR_SECURITY_PREFIX) - 1) &&
- !capable(CAP_SYS_ADMIN))
+ if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
@@ -1082,6 +1336,7 @@ struct security_hook_list capability_hooks[] = {
LSM_HOOK_INIT(bprm_secureexec, cap_bprm_secureexec),
LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv),
LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv),
+ LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity),
LSM_HOOK_INIT(mmap_addr, cap_mmap_addr),
LSM_HOOK_INIT(mmap_file, cap_mmap_file),
LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid),
