capabilites: allow the application of capability limits to usermode helpers

There is no way to limit the capabilities of usermodehelpers. This problem
reared its head recently when someone complained that any user with
cap_net_admin was able to load arbitrary kernel modules, even though the user
didn't have cap_sys_module.  The reason is because the actual load is done by
a usermode helper and those always have the full cap set.  This patch addes new
sysctls which allow us to bound the permissions of usermode helpers.

/proc/sys/kernel/usermodehelper/bset
/proc/sys/kernel/usermodehelper/inheritable

You must have CAP_SYS_MODULE  and CAP_SETPCAP to change these (changes are
&= ONLY).  When the kernel launches a usermodehelper it will do so with these
as the bset and pI.

-v2:	make globals static
	create spinlock to protect globals

-v3:	require both CAP_SETPCAP and CAP_SYS_MODULE
-v4:	fix the typo s/CAP_SET_PCAP/CAP_SETPCAP/ because I didn't commit
Signed-off-by: Eric Paris <eparis@redhat.com>
No-objection-from: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: David Howells <dhowells@redhat.com>
Acked-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: Andrew G. Morgan <morgan@kernel.org>
Signed-off-by: James Morris <jmorris@namei.org>

include/linux/kmod.h

@@ -24,6 +24,7 @@
 #include <linux/errno.h>
 #include <linux/compiler.h>
 #include <linux/workqueue.h>
+#include <linux/sysctl.h>
 
 #define KMOD_PATH_LEN 256
 
@@ -109,6 +110,8 @@ call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait)
 				       NULL, NULL, NULL);
 }
 
+extern struct ctl_table usermodehelper_table[];
+
 extern void usermodehelper_init(void);
 
 extern int usermodehelper_disable(void);

kernel/kmod.c

@@ -25,6 +25,7 @@
 #include <linux/kmod.h>
 #include <linux/slab.h>
 #include <linux/completion.h>
+#include <linux/cred.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/workqueue.h>
@@ -43,6 +44,13 @@ extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
 
+#define CAP_BSET	(void *)1
+#define CAP_PI		(void *)2
+
+static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
+static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
+static DEFINE_SPINLOCK(umh_sysctl_lock);
+
 #ifdef CONFIG_MODULES
 
 /*
@@ -132,6 +140,7 @@ EXPORT_SYMBOL(__request_module);
 static int ____call_usermodehelper(void *data)
 {
 	struct subprocess_info *sub_info = data;
+	struct cred *new;
 	int retval;
 
 	spin_lock_irq(&current->sighand->siglock);
@@ -153,6 +162,19 @@ static int ____call_usermodehelper(void *data)
 			goto fail;
 	}
 
+	retval = -ENOMEM;
+	new = prepare_kernel_cred(current);
+	if (!new)
+		goto fail;
+
+	spin_lock(&umh_sysctl_lock);
+	new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
+	new->cap_inheritable = cap_intersect(usermodehelper_inheritable,
+					     new->cap_inheritable);
+	spin_unlock(&umh_sysctl_lock);
+
+	commit_creds(new);
+
 	retval = kernel_execve(sub_info->path,
 			       (const char *const *)sub_info->argv,
 			       (const char *const *)sub_info->envp);
@@ -418,6 +440,84 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info,
 }
 EXPORT_SYMBOL(call_usermodehelper_exec);
 
+static int proc_cap_handler(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
+	kernel_cap_t new_cap;
+	int err, i;
+
+	if (write && (!capable(CAP_SETPCAP) ||
+		      !capable(CAP_SYS_MODULE)))
+		return -EPERM;
+
+	/*
+	 * convert from the global kernel_cap_t to the ulong array to print to
+	 * userspace if this is a read.
+	 */
+	spin_lock(&umh_sysctl_lock);
+	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)  {
+		if (table->data == CAP_BSET)
+			cap_array[i] = usermodehelper_bset.cap[i];
+		else if (table->data == CAP_PI)
+			cap_array[i] = usermodehelper_inheritable.cap[i];
+		else
+			BUG();
+	}
+	spin_unlock(&umh_sysctl_lock);
+
+	t = *table;
+	t.data = &cap_array;
+
+	/*
+	 * actually read or write and array of ulongs from userspace.  Remember
+	 * these are least significant 32 bits first
+	 */
+	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+
+	/*
+	 * convert from the sysctl array of ulongs to the kernel_cap_t
+	 * internal representation
+	 */
+	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)
+		new_cap.cap[i] = cap_array[i];
+
+	/*
+	 * Drop everything not in the new_cap (but don't add things)
+	 */
+	spin_lock(&umh_sysctl_lock);
+	if (write) {
+		if (table->data == CAP_BSET)
+			usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
+		if (table->data == CAP_PI)
+			usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
+	}
+	spin_unlock(&umh_sysctl_lock);
+
+	return 0;
+}
+
+struct ctl_table usermodehelper_table[] = {
+	{
+		.procname	= "bset",
+		.data		= CAP_BSET,
+		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
+		.mode		= 0600,
+		.proc_handler	= proc_cap_handler,
+	},
+	{
+		.procname	= "inheritable",
+		.data		= CAP_PI,
+		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
+		.mode		= 0600,
+		.proc_handler	= proc_cap_handler,
+	},
+	{ }
+};
+
 void __init usermodehelper_init(void)
 {
 	khelper_wq = create_singlethread_workqueue("khelper");

kernel/sysctl.c

@@ -56,6 +56,7 @@
 #include <linux/kprobes.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
+#include <linux/kmod.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -615,6 +616,11 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0555,
 		.child		= random_table,
 	},
+	{
+		.procname	= "usermodehelper",
+		.mode		= 0555,
+		.child		= usermodehelper_table,
+	},
 	{
 		.procname	= "overflowuid",
 		.data		= &overflowuid,