Revision 25fb6ca4ed9cad72f14f61629b68dc03c0d9713f authored by Balakumaran Kannan on 02 April 2013, 10:45:05 UTC, committed by David S. Miller on 02 April 2013, 18:37:19 UTC
IPv6 Routing table becomes broken once we do ifdown, ifup of the loopback(lo)
interface. After down-up, routes of other interface's IPv6 addresses through
'lo' are lost.

IPv6 addresses assigned to all interfaces are routed through 'lo' for internal
communication. Once 'lo' is down, those routing entries are removed from routing
table. But those removed entries are not being re-created properly when 'lo' is
brought up. So IPv6 addresses of other interfaces becomes unreachable from the
same machine. Also this breaks communication with other machines because of
NDISC packet processing failure.

This patch fixes this issue by reading all interface's IPv6 addresses and adding
them to IPv6 routing table while bringing up 'lo'.

==Testing==
Before applying the patch:
$ route -A inet6
Kernel IPv6 routing table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
2000::20/128                   ::                         Un   0   1     0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128  ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$ sudo ifdown lo
$ sudo ifup lo
$ route -A inet6
Kernel IPv6 routing table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$

After applying the patch:
$ route -A inet6
Kernel IPv6 routing
table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
2000::20/128                   ::                         Un   0   1     0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128  ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$ sudo ifdown lo
$ sudo ifup lo
$ route -A inet6
Kernel IPv6 routing table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
2000::20/128                   ::                         Un   0   1     0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128  ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$

Signed-off-by: Balakumaran Kannan <Balakumaran.Kannan@ap.sony.com>
Signed-off-by: Maruthi Thotad <Maruthi.Thotad@ap.sony.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent f0f6ee1
Raw File
kcmp.c
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/fdtable.h>
#include <linux/string.h>
#include <linux/random.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/cache.h>
#include <linux/bug.h>
#include <linux/err.h>
#include <linux/kcmp.h>

#include <asm/unistd.h>

/*
 * We don't expose the real in-memory order of objects for security reasons.
 * But still the comparison results should be suitable for sorting. So we
 * obfuscate kernel pointers values and compare the production instead.
 *
 * The obfuscation is done in two steps. First we xor the kernel pointer with
 * a random value, which puts pointer into a new position in a reordered space.
 * Secondly we multiply the xor production with a large odd random number to
 * permute its bits even more (the odd multiplier guarantees that the product
 * is unique ever after the high bits are truncated, since any odd number is
 * relative prime to 2^n).
 *
 * Note also that the obfuscation itself is invisible to userspace and if needed
 * it can be changed to an alternate scheme.
 */
static unsigned long cookies[KCMP_TYPES][2] __read_mostly;

static long kptr_obfuscate(long v, int type)
{
	return (v ^ cookies[type][0]) * cookies[type][1];
}

/*
 * 0 - equal, i.e. v1 = v2
 * 1 - less than, i.e. v1 < v2
 * 2 - greater than, i.e. v1 > v2
 * 3 - not equal but ordering unavailable (reserved for future)
 */
static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
{
	long ret;

	ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);

	return (ret < 0) | ((ret > 0) << 1);
}

/* The caller must have pinned the task */
static struct file *
get_file_raw_ptr(struct task_struct *task, unsigned int idx)
{
	struct file *file = NULL;

	task_lock(task);
	rcu_read_lock();

	if (task->files)
		file = fcheck_files(task->files, idx);

	rcu_read_unlock();
	task_unlock(task);

	return file;
}

static void kcmp_unlock(struct mutex *m1, struct mutex *m2)
{
	if (likely(m2 != m1))
		mutex_unlock(m2);
	mutex_unlock(m1);
}

static int kcmp_lock(struct mutex *m1, struct mutex *m2)
{
	int err;

	if (m2 > m1)
		swap(m1, m2);

	err = mutex_lock_killable(m1);
	if (!err && likely(m1 != m2)) {
		err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING);
		if (err)
			mutex_unlock(m1);
	}

	return err;
}

SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
		unsigned long, idx1, unsigned long, idx2)
{
	struct task_struct *task1, *task2;
	int ret;

	rcu_read_lock();

	/*
	 * Tasks are looked up in caller's PID namespace only.
	 */
	task1 = find_task_by_vpid(pid1);
	task2 = find_task_by_vpid(pid2);
	if (!task1 || !task2)
		goto err_no_task;

	get_task_struct(task1);
	get_task_struct(task2);

	rcu_read_unlock();

	/*
	 * One should have enough rights to inspect task details.
	 */
	ret = kcmp_lock(&task1->signal->cred_guard_mutex,
			&task2->signal->cred_guard_mutex);
	if (ret)
		goto err;
	if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
	    !ptrace_may_access(task2, PTRACE_MODE_READ)) {
		ret = -EPERM;
		goto err_unlock;
	}

	switch (type) {
	case KCMP_FILE: {
		struct file *filp1, *filp2;

		filp1 = get_file_raw_ptr(task1, idx1);
		filp2 = get_file_raw_ptr(task2, idx2);

		if (filp1 && filp2)
			ret = kcmp_ptr(filp1, filp2, KCMP_FILE);
		else
			ret = -EBADF;
		break;
	}
	case KCMP_VM:
		ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM);
		break;
	case KCMP_FILES:
		ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
		break;
	case KCMP_FS:
		ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
		break;
	case KCMP_SIGHAND:
		ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
		break;
	case KCMP_IO:
		ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO);
		break;
	case KCMP_SYSVSEM:
#ifdef CONFIG_SYSVIPC
		ret = kcmp_ptr(task1->sysvsem.undo_list,
			       task2->sysvsem.undo_list,
			       KCMP_SYSVSEM);
#else
		ret = -EOPNOTSUPP;
#endif
		break;
	default:
		ret = -EINVAL;
		break;
	}

err_unlock:
	kcmp_unlock(&task1->signal->cred_guard_mutex,
		    &task2->signal->cred_guard_mutex);
err:
	put_task_struct(task1);
	put_task_struct(task2);

	return ret;

err_no_task:
	rcu_read_unlock();
	return -ESRCH;
}

static __init int kcmp_cookies_init(void)
{
	int i;

	get_random_bytes(cookies, sizeof(cookies));

	for (i = 0; i < KCMP_TYPES; i++)
		cookies[i][1] |= (~(~0UL >>  1) | 1);

	return 0;
}
arch_initcall(kcmp_cookies_init);
back to top