The patch titled
userns: security: Make capabilities relative to the user namespace.
has been added to the -mm tree. Its filename is
userns-security-make-capabilities-relative-to-the-user-namespace.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: userns: security: Make capabilities relative to the user namespace.
From: "Serge E. Hallyn" <serge@xxxxxxxxxx>
- Introduce ns_capable to test for a capability in a non-default
user namespace.
- Teach cap_capable to handle capabilities in a non-default
user namespace.
The motivation is to get to the unprivileged creation of new namespaces.
It looks like this gets us 90% of the way there, with only potential uid
confusion issues left.
I still need to handle getting all caps after creation but otherwise I
think I have a good starter patch that achieves all of your goals.
Changelog:
11/05/2010: [serge] add apparmor
12/14/2010: [serge] fix capabilities to created user namespaces
Without this, if user serge creates a user_ns, he won't have
capabilities to the user_ns he created. THis is because we
were first checking whether his effective caps had the caps
he needed and returning -EPERM if not, and THEN checking whether
he was the creator. Reverse those checks.
12/16/2010: [serge] security_real_capable needs ns argument in !security case
01/11/2011: [serge] add task_ns_capable helper
01/11/2011: [serge] add nsown_capable() helper per Bastian Blank suggestion
02/16/2011: [serge] fix a logic bug: the root user is always creator of
init_user_ns, but should not always have capabilities to
it! Fix the check in cap_capable().
Signed-off-by: Eric W. Biederman <ebiederm@xxxxxxxxxxxx>
Signed-off-by: Serge E. Hallyn <serge.hallyn@xxxxxxxxxxxxx>
Cc: James Morris <jmorris@xxxxxxxxx>
Cc: Kees Cook <kees.cook@xxxxxxxxxxxxx>
Cc: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/capability.h | 10 +++++++-
include/linux/security.h | 25 ++++++++++++---------
kernel/capability.c | 32 ++++++++++++++++++++++++++--
security/apparmor/lsm.c | 5 ++--
security/commoncap.c | 40 ++++++++++++++++++++++++++++-------
security/security.c | 16 ++++++++------
security/selinux/hooks.c | 14 +++++++-----
7 files changed, 107 insertions(+), 35 deletions(-)
diff -puN include/linux/capability.h~userns-security-make-capabilities-relative-to-the-user-namespace include/linux/capability.h
--- a/include/linux/capability.h~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/include/linux/capability.h
@@ -544,7 +544,7 @@ extern const kernel_cap_t __cap_init_eff
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
-#define has_capability(t, cap) (security_real_capable((t), (cap)) == 0)
+#define has_capability(t, cap) (security_real_capable((t), &init_user_ns, (cap)) == 0)
/**
* has_capability_noaudit - Determine if a task has a superior capability available (unaudited)
@@ -558,9 +558,15 @@ extern const kernel_cap_t __cap_init_eff
* Note that this does not set PF_SUPERPRIV on the task.
*/
#define has_capability_noaudit(t, cap) \
- (security_real_capable_noaudit((t), (cap)) == 0)
+ (security_real_capable_noaudit((t), &init_user_ns, (cap)) == 0)
+struct user_namespace;
+extern struct user_namespace init_user_ns;
extern int capable(int cap);
+extern int ns_capable(struct user_namespace *ns, int cap);
+extern int task_ns_capable(struct task_struct *t, int cap);
+
+#define nsown_capable(cap) (ns_capable(current_user_ns(), (cap)))
/* audit system wants to get cap info from files as well */
struct dentry;
diff -puN include/linux/security.h~userns-security-make-capabilities-relative-to-the-user-namespace include/linux/security.h
--- a/include/linux/security.h~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/include/linux/security.h
@@ -47,13 +47,14 @@
struct ctl_table;
struct audit_krule;
+struct user_namespace;
/*
* These functions are in security/capability.c and are used
* as the default capabilities functions
*/
extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
- int cap, int audit);
+ struct user_namespace *ns, int cap, int audit);
extern int cap_settime(const struct timespec *ts, const struct timezone *tz);
extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode);
extern int cap_ptrace_traceme(struct task_struct *parent);
@@ -1256,6 +1257,7 @@ static inline void security_free_mnt_opt
* credentials.
* @tsk contains the task_struct for the process.
* @cred contains the credentials to use.
+ * @ns contains the user namespace we want the capability in
* @cap contains the capability <include/linux/capability.h>.
* @audit: Whether to write an audit message or not
* Return 0 if the capability is granted for @tsk.
@@ -1378,7 +1380,7 @@ struct security_operations {
const kernel_cap_t *inheritable,
const kernel_cap_t *permitted);
int (*capable) (struct task_struct *tsk, const struct cred *cred,
- int cap, int audit);
+ struct user_namespace *ns, int cap, int audit);
int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
int (*quota_on) (struct dentry *dentry);
int (*syslog) (int type);
@@ -1658,9 +1660,9 @@ int security_capset(struct cred *new, co
const kernel_cap_t *effective,
const kernel_cap_t *inheritable,
const kernel_cap_t *permitted);
-int security_capable(const struct cred *cred, int cap);
-int security_real_capable(struct task_struct *tsk, int cap);
-int security_real_capable_noaudit(struct task_struct *tsk, int cap);
+int security_capable(struct user_namespace *ns, const struct cred *cred, int cap);
+int security_real_capable(struct task_struct *tsk, struct user_namespace *ns, int cap);
+int security_real_capable_noaudit(struct task_struct *tsk, struct user_namespace *ns, int cap);
int security_quotactl(int cmds, int type, int id, struct super_block *sb);
int security_quota_on(struct dentry *dentry);
int security_syslog(int type);
@@ -1852,28 +1854,29 @@ static inline int security_capset(struct
return cap_capset(new, old, effective, inheritable, permitted);
}
-static inline int security_capable(const struct cred *cred, int cap)
+static inline int security_capable(struct user_namespace *ns,
+ const struct cred *cred, int cap)
{
- return cap_capable(current, cred, cap, SECURITY_CAP_AUDIT);
+ return cap_capable(current, cred, ns, cap, SECURITY_CAP_AUDIT);
}
-static inline int security_real_capable(struct task_struct *tsk, int cap)
+static inline int security_real_capable(struct task_struct *tsk, struct user_namespace *ns, int cap)
{
int ret;
rcu_read_lock();
- ret = cap_capable(tsk, __task_cred(tsk), cap, SECURITY_CAP_AUDIT);
+ ret = cap_capable(tsk, __task_cred(tsk), ns, cap, SECURITY_CAP_AUDIT);
rcu_read_unlock();
return ret;
}
static inline
-int security_real_capable_noaudit(struct task_struct *tsk, int cap)
+int security_real_capable_noaudit(struct task_struct *tsk, struct user_namespace *ns, int cap)
{
int ret;
rcu_read_lock();
- ret = cap_capable(tsk, __task_cred(tsk), cap,
+ ret = cap_capable(tsk, __task_cred(tsk), ns, cap,
SECURITY_CAP_NOAUDIT);
rcu_read_unlock();
return ret;
diff -puN kernel/capability.c~userns-security-make-capabilities-relative-to-the-user-namespace kernel/capability.c
--- a/kernel/capability.c~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/kernel/capability.c
@@ -14,6 +14,7 @@
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
#include <asm/uaccess.h>
/*
@@ -301,15 +302,42 @@ error:
*/
int capable(int cap)
{
+ return ns_capable(&init_user_ns, cap);
+}
+EXPORT_SYMBOL(capable);
+
+/**
+ * ns_capable - Determine if the current task has a superior capability in effect
+ * @ns: The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+int ns_capable(struct user_namespace *ns, int cap)
+{
if (unlikely(!cap_valid(cap))) {
printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
BUG();
}
- if (security_capable(current_cred(), cap) == 0) {
+ if (security_capable(ns, current_cred(), cap) == 0) {
current->flags |= PF_SUPERPRIV;
return 1;
}
return 0;
}
-EXPORT_SYMBOL(capable);
+EXPORT_SYMBOL(ns_capable);
+
+/*
+ * does current have capability 'cap' to the user namespace of task
+ * 't'. Return true if it does, false otherwise.
+ */
+int task_ns_capable(struct task_struct *t, int cap)
+{
+ return ns_capable(task_cred_xxx(t, user)->user_ns, cap);
+}
+EXPORT_SYMBOL(task_ns_capable);
diff -puN security/apparmor/lsm.c~userns-security-make-capabilities-relative-to-the-user-namespace security/apparmor/lsm.c
--- a/security/apparmor/lsm.c~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/security/apparmor/lsm.c
@@ -22,6 +22,7 @@
#include <linux/ctype.h>
#include <linux/sysctl.h>
#include <linux/audit.h>
+#include <linux/user_namespace.h>
#include <net/sock.h>
#include "include/apparmor.h"
@@ -136,11 +137,11 @@ static int apparmor_capget(struct task_s
}
static int apparmor_capable(struct task_struct *task, const struct cred *cred,
- int cap, int audit)
+ struct user_namespace *ns, int cap, int audit)
{
struct aa_profile *profile;
/* cap_capable returns 0 on success, else -EPERM */
- int error = cap_capable(task, cred, cap, audit);
+ int error = cap_capable(task, cred, ns, cap, audit);
if (!error) {
profile = aa_cred_profile(cred);
if (!unconfined(profile))
diff -puN security/commoncap.c~userns-security-make-capabilities-relative-to-the-user-namespace security/commoncap.c
--- a/security/commoncap.c~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/security/commoncap.c
@@ -27,6 +27,7 @@
#include <linux/sched.h>
#include <linux/prctl.h>
#include <linux/securebits.h>
+#include <linux/user_namespace.h>
/*
* If a non-root user executes a setuid-root binary in
@@ -68,6 +69,7 @@ EXPORT_SYMBOL(cap_netlink_recv);
* cap_capable - Determine whether a task has a particular effective capability
* @tsk: The task to query
* @cred: The credentials to use
+ * @ns: The user namespace in which we need the capability
* @cap: The capability to check for
* @audit: Whether to write an audit message or not
*
@@ -79,10 +81,32 @@ EXPORT_SYMBOL(cap_netlink_recv);
* cap_has_capability() returns 0 when a task has a capability, but the
* kernel's capable() and has_capability() returns 1 for this case.
*/
-int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
- int audit)
+int cap_capable(struct task_struct *tsk, const struct cred *cred,
+ struct user_namespace *targ_ns, int cap, int audit)
{
- return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+ for (;;) {
+ /* The creator of the user namespace has all caps. */
+ if (targ_ns != &init_user_ns && targ_ns->creator == cred->user)
+ return 0;
+
+ /* Do we have the necessary capabilities? */
+ if (targ_ns == cred->user->user_ns)
+ return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+
+ /* Have we tried all of the parent namespaces? */
+ if (targ_ns == &init_user_ns)
+ return -EPERM;
+
+ /* If you have the capability in a parent user ns you have it
+ * in the over all children user namespaces as well, so see
+ * if this process has the capability in the parent user
+ * namespace.
+ */
+ targ_ns = targ_ns->creator->user_ns;
+ }
+
+ /* We never get here */
+ return -EPERM;
}
/**
@@ -177,7 +201,8 @@ static inline int cap_inh_is_capped(void
/* they are so limited unless the current task has the CAP_SETPCAP
* capability
*/
- if (cap_capable(current, current_cred(), CAP_SETPCAP,
+ if (cap_capable(current, current_cred(),
+ current_cred()->user->user_ns, CAP_SETPCAP,
SECURITY_CAP_AUDIT) == 0)
return 0;
return 1;
@@ -829,7 +854,8 @@ int cap_task_prctl(int option, unsigned
& (new->securebits ^ arg2)) /*[1]*/
|| ((new->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/
|| (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/
- || (cap_capable(current, current_cred(), CAP_SETPCAP,
+ || (cap_capable(current, current_cred(),
+ current_cred()->user->user_ns, CAP_SETPCAP,
SECURITY_CAP_AUDIT) != 0) /*[4]*/
/*
* [1] no changing of bits that are locked
@@ -894,7 +920,7 @@ int cap_vm_enough_memory(struct mm_struc
{
int cap_sys_admin = 0;
- if (cap_capable(current, current_cred(), CAP_SYS_ADMIN,
+ if (cap_capable(current, current_cred(), &init_user_ns, CAP_SYS_ADMIN,
SECURITY_CAP_NOAUDIT) == 0)
cap_sys_admin = 1;
return __vm_enough_memory(mm, pages, cap_sys_admin);
@@ -921,7 +947,7 @@ int cap_file_mmap(struct file *file, uns
int ret = 0;
if (addr < dac_mmap_min_addr) {
- ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO,
+ ret = cap_capable(current, current_cred(), &init_user_ns, CAP_SYS_RAWIO,
SECURITY_CAP_AUDIT);
/* set PF_SUPERPRIV if it turns out we allow the low mmap */
if (ret == 0)
diff -puN security/security.c~userns-security-make-capabilities-relative-to-the-user-namespace security/security.c
--- a/security/security.c~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/security/security.c
@@ -154,29 +154,33 @@ int security_capset(struct cred *new, co
effective, inheritable, permitted);
}
-int security_capable(const struct cred *cred, int cap)
+int security_capable(struct user_namespace *ns, const struct cred *cred,
+ int cap)
{
- return security_ops->capable(current, cred, cap, SECURITY_CAP_AUDIT);
+ return security_ops->capable(current, cred, ns, cap,
+ SECURITY_CAP_AUDIT);
}
-int security_real_capable(struct task_struct *tsk, int cap)
+int security_real_capable(struct task_struct *tsk, struct user_namespace *ns,
+ int cap)
{
const struct cred *cred;
int ret;
cred = get_task_cred(tsk);
- ret = security_ops->capable(tsk, cred, cap, SECURITY_CAP_AUDIT);
+ ret = security_ops->capable(tsk, cred, ns, cap, SECURITY_CAP_AUDIT);
put_cred(cred);
return ret;
}
-int security_real_capable_noaudit(struct task_struct *tsk, int cap)
+int security_real_capable_noaudit(struct task_struct *tsk,
+ struct user_namespace *ns, int cap)
{
const struct cred *cred;
int ret;
cred = get_task_cred(tsk);
- ret = security_ops->capable(tsk, cred, cap, SECURITY_CAP_NOAUDIT);
+ ret = security_ops->capable(tsk, cred, ns, cap, SECURITY_CAP_NOAUDIT);
put_cred(cred);
return ret;
}
diff -puN security/selinux/hooks.c~userns-security-make-capabilities-relative-to-the-user-namespace security/selinux/hooks.c
--- a/security/selinux/hooks.c~userns-security-make-capabilities-relative-to-the-user-namespace
+++ a/security/selinux/hooks.c
@@ -76,6 +76,7 @@
#include <linux/mutex.h>
#include <linux/posix-timers.h>
#include <linux/syslog.h>
+#include <linux/user_namespace.h>
#include "avc.h"
#include "objsec.h"
@@ -1415,6 +1416,7 @@ static int current_has_perm(const struct
/* Check whether a task is allowed to use a capability. */
static int task_has_capability(struct task_struct *tsk,
const struct cred *cred,
+ struct user_namespace *ns,
int cap, int audit)
{
struct common_audit_data ad;
@@ -1843,15 +1845,15 @@ static int selinux_capset(struct cred *n
*/
static int selinux_capable(struct task_struct *tsk, const struct cred *cred,
- int cap, int audit)
+ struct user_namespace *ns, int cap, int audit)
{
int rc;
- rc = cap_capable(tsk, cred, cap, audit);
+ rc = cap_capable(tsk, cred, ns, cap, audit);
if (rc)
return rc;
- return task_has_capability(tsk, cred, cap, audit);
+ return task_has_capability(tsk, cred, ns, cap, audit);
}
static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb)
@@ -1928,7 +1930,8 @@ static int selinux_vm_enough_memory(stru
{
int rc, cap_sys_admin = 0;
- rc = selinux_capable(current, current_cred(), CAP_SYS_ADMIN,
+ rc = selinux_capable(current, current_cred(),
+ &init_user_ns, CAP_SYS_ADMIN,
SECURITY_CAP_NOAUDIT);
if (rc == 0)
cap_sys_admin = 1;
@@ -2746,7 +2749,8 @@ static int selinux_inode_getsecurity(con
* and lack of permission just means that we fall back to the
* in-core context value, not a denial.
*/
- error = selinux_capable(current, current_cred(), CAP_MAC_ADMIN,
+ error = selinux_capable(current, current_cred(),
+ &init_user_ns, CAP_MAC_ADMIN,
SECURITY_CAP_NOAUDIT);
if (!error)
error = security_sid_to_context_force(isec->sid, &context,
_
Patches currently in -mm which might be from serge@xxxxxxxxxx are
lib-hexdumpc-make-hex2bin-return-the-updated-src-address.patch
fs-binfmt_miscc-use-kernels-hex_to_bin-method.patch
fs-binfmt_miscc-use-kernels-hex_to_bin-method-fix.patch
fs-binfmt_miscc-use-kernels-hex_to_bin-method-fix-fix.patch
pid-remove-the-child_reaper-special-case-in-init-mainc.patch
pidns-call-pid_ns_prepare_proc-from-create_pid_namespace.patch
procfs-kill-the-global-proc_mnt-variable.patch
userns-add-a-user_namespace-as-creator-owner-of-uts_namespace.patch
userns-security-make-capabilities-relative-to-the-user-namespace.patch
userns-allow-sethostname-in-a-container.patch
userns-allow-killing-tasks-in-your-own-or-child-userns.patch
userns-allow-ptrace-from-non-init-user-namespaces.patch
userns-user-namespaces-convert-all-capable-checks-in-kernel-sysc.patch
userns-add-a-user-namespace-owner-of-ipc-ns.patch
userns-user-namespaces-convert-several-capable-calls.patch
userns-userns-check-user-namespace-for-task-file-uid-equivalence-checks.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
