linux/security/selinux/netnode.c

318 lines
7.9 KiB
C
Raw Normal View History

/*
* Network node table
*
* SELinux must keep a mapping of network nodes to labels/SIDs. This
* mapping is maintained as part of the normal policy but a fast cache is
* needed to reduce the lookup overhead since most of these queries happen on
* a per-packet basis.
*
* Author: Paul Moore <paul@paul-moore.com>
*
* This code is heavily based on the "netif" concept originally developed by
* James Morris <jmorris@redhat.com>
* (see security/selinux/netif.c for more information)
*
*/
/*
* (c) Copyright Hewlett-Packard Development Company, L.P., 2007
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include "netnode.h"
#include "objsec.h"
#define SEL_NETNODE_HASH_SIZE 256
#define SEL_NETNODE_HASH_BKT_LIMIT 16
struct sel_netnode_bkt {
unsigned int size;
struct list_head list;
};
struct sel_netnode {
struct netnode_security_struct nsec;
struct list_head list;
struct rcu_head rcu;
};
/* NOTE: we are using a combined hash table for both IPv4 and IPv6, the reason
* for this is that I suspect most users will not make heavy use of both
* address families at the same time so one table will usually end up wasted,
* if this becomes a problem we can always add a hash table for each address
* family later */
static LIST_HEAD(sel_netnode_list);
static DEFINE_SPINLOCK(sel_netnode_lock);
static struct sel_netnode_bkt sel_netnode_hash[SEL_NETNODE_HASH_SIZE];
/**
* sel_netnode_hashfn_ipv4 - IPv4 hashing function for the node table
* @addr: IPv4 address
*
* Description:
* This is the IPv4 hashing function for the node interface table, it returns
* the bucket number for the given IP address.
*
*/
static unsigned int sel_netnode_hashfn_ipv4(__be32 addr)
{
/* at some point we should determine if the mismatch in byte order
* affects the hash function dramatically */
return (addr & (SEL_NETNODE_HASH_SIZE - 1));
}
/**
* sel_netnode_hashfn_ipv6 - IPv6 hashing function for the node table
* @addr: IPv6 address
*
* Description:
* This is the IPv6 hashing function for the node interface table, it returns
* the bucket number for the given IP address.
*
*/
static unsigned int sel_netnode_hashfn_ipv6(const struct in6_addr *addr)
{
/* just hash the least significant 32 bits to keep things fast (they
* are the most likely to be different anyway), we can revisit this
* later if needed */
return (addr->s6_addr32[3] & (SEL_NETNODE_HASH_SIZE - 1));
}
/**
* sel_netnode_find - Search for a node record
* @addr: IP address
* @family: address family
*
* Description:
* Search the network node table and return the record matching @addr. If an
* entry can not be found in the table return NULL.
*
*/
static struct sel_netnode *sel_netnode_find(const void *addr, u16 family)
{
unsigned int idx;
struct sel_netnode *node;
switch (family) {
case PF_INET:
idx = sel_netnode_hashfn_ipv4(*(__be32 *)addr);
break;
case PF_INET6:
idx = sel_netnode_hashfn_ipv6(addr);
break;
default:
BUG();
return NULL;
}
list_for_each_entry_rcu(node, &sel_netnode_hash[idx].list, list)
if (node->nsec.family == family)
switch (family) {
case PF_INET:
if (node->nsec.addr.ipv4 == *(__be32 *)addr)
return node;
break;
case PF_INET6:
if (ipv6_addr_equal(&node->nsec.addr.ipv6,
addr))
return node;
break;
}
return NULL;
}
/**
* sel_netnode_insert - Insert a new node into the table
* @node: the new node record
*
* Description:
* Add a new node record to the network address hash table.
*
*/
static void sel_netnode_insert(struct sel_netnode *node)
{
unsigned int idx;
switch (node->nsec.family) {
case PF_INET:
idx = sel_netnode_hashfn_ipv4(node->nsec.addr.ipv4);
break;
case PF_INET6:
idx = sel_netnode_hashfn_ipv6(&node->nsec.addr.ipv6);
break;
default:
BUG();
return;
}
/* we need to impose a limit on the growth of the hash table so check
* this bucket to make sure it is within the specified bounds */
list_add_rcu(&node->list, &sel_netnode_hash[idx].list);
if (sel_netnode_hash[idx].size == SEL_NETNODE_HASH_BKT_LIMIT) {
struct sel_netnode *tail;
tail = list_entry(
selinux: fix sel_netnode_insert() suspicious rcu dereference =============================== [ INFO: suspicious RCU usage. ] 3.5.0-rc1+ #63 Not tainted ------------------------------- security/selinux/netnode.c:178 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 1 lock held by trinity-child1/8750: #0: (sel_netnode_lock){+.....}, at: [<ffffffff812d8f8a>] sel_netnode_sid+0x16a/0x3e0 stack backtrace: Pid: 8750, comm: trinity-child1 Not tainted 3.5.0-rc1+ #63 Call Trace: [<ffffffff810cec2d>] lockdep_rcu_suspicious+0xfd/0x130 [<ffffffff812d91d1>] sel_netnode_sid+0x3b1/0x3e0 [<ffffffff812d8e20>] ? sel_netnode_find+0x1a0/0x1a0 [<ffffffff812d24a6>] selinux_socket_bind+0xf6/0x2c0 [<ffffffff810cd1dd>] ? trace_hardirqs_off+0xd/0x10 [<ffffffff810cdb55>] ? lock_release_holdtime.part.9+0x15/0x1a0 [<ffffffff81093841>] ? lock_hrtimer_base+0x31/0x60 [<ffffffff812c9536>] security_socket_bind+0x16/0x20 [<ffffffff815550ca>] sys_bind+0x7a/0x100 [<ffffffff816c03d5>] ? sysret_check+0x22/0x5d [<ffffffff810d392d>] ? trace_hardirqs_on_caller+0x10d/0x1a0 [<ffffffff8133b09e>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff816c03a9>] system_call_fastpath+0x16/0x1b This patch below does what Paul McKenney suggested in the previous thread. Signed-off-by: Dave Jones <davej@redhat.com> Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Paul Moore <paul@paul-moore.com> Cc: Eric Paris <eparis@parisplace.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: James Morris <james.l.morris@oracle.com>
2012-11-09 08:09:27 +08:00
rcu_dereference_protected(sel_netnode_hash[idx].list.prev,
lockdep_is_held(&sel_netnode_lock)),
struct sel_netnode, list);
list_del_rcu(&tail->list);
kfree_rcu(tail, rcu);
} else
sel_netnode_hash[idx].size++;
}
/**
* sel_netnode_sid_slow - Lookup the SID of a network address using the policy
* @addr: the IP address
* @family: the address family
* @sid: node SID
*
* Description:
* This function determines the SID of a network address by quering the
* security policy. The result is added to the network address table to
* speedup future queries. Returns zero on success, negative values on
* failure.
*
*/
static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
{
int ret = -ENOMEM;
struct sel_netnode *node;
struct sel_netnode *new = NULL;
spin_lock_bh(&sel_netnode_lock);
node = sel_netnode_find(addr, family);
if (node != NULL) {
*sid = node->nsec.sid;
spin_unlock_bh(&sel_netnode_lock);
return 0;
}
new = kzalloc(sizeof(*new), GFP_ATOMIC);
if (new == NULL)
goto out;
switch (family) {
case PF_INET:
ret = security_node_sid(&selinux_state, PF_INET,
addr, sizeof(struct in_addr), sid);
new->nsec.addr.ipv4 = *(__be32 *)addr;
break;
case PF_INET6:
ret = security_node_sid(&selinux_state, PF_INET6,
addr, sizeof(struct in6_addr), sid);
new->nsec.addr.ipv6 = *(struct in6_addr *)addr;
break;
default:
BUG();
ret = -EINVAL;
}
if (ret != 0)
goto out;
new->nsec.family = family;
new->nsec.sid = *sid;
sel_netnode_insert(new);
out:
spin_unlock_bh(&sel_netnode_lock);
if (unlikely(ret)) {
pr_warn("SELinux: failure in %s(), unable to determine network node label\n",
__func__);
kfree(new);
}
return ret;
}
/**
* sel_netnode_sid - Lookup the SID of a network address
* @addr: the IP address
* @family: the address family
* @sid: node SID
*
* Description:
* This function determines the SID of a network address using the fastest
* method possible. First the address table is queried, but if an entry
* can't be found then the policy is queried and the result is added to the
* table to speedup future queries. Returns zero on success, negative values
* on failure.
*
*/
int sel_netnode_sid(void *addr, u16 family, u32 *sid)
{
struct sel_netnode *node;
rcu_read_lock();
node = sel_netnode_find(addr, family);
if (node != NULL) {
*sid = node->nsec.sid;
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
return sel_netnode_sid_slow(addr, family, sid);
}
/**
* sel_netnode_flush - Flush the entire network address table
*
* Description:
* Remove all entries from the network address table.
*
*/
void sel_netnode_flush(void)
{
unsigned int idx;
struct sel_netnode *node, *node_tmp;
spin_lock_bh(&sel_netnode_lock);
for (idx = 0; idx < SEL_NETNODE_HASH_SIZE; idx++) {
list_for_each_entry_safe(node, node_tmp,
&sel_netnode_hash[idx].list, list) {
list_del_rcu(&node->list);
kfree_rcu(node, rcu);
}
sel_netnode_hash[idx].size = 0;
}
spin_unlock_bh(&sel_netnode_lock);
}
static __init int sel_netnode_init(void)
{
int iter;
if (!selinux_enabled)
return 0;
for (iter = 0; iter < SEL_NETNODE_HASH_SIZE; iter++) {
INIT_LIST_HEAD(&sel_netnode_hash[iter].list);
sel_netnode_hash[iter].size = 0;
}
return 0;
}
__initcall(sel_netnode_init);