linux/net/bridge/br_fdb.c

415 lines
9.7 KiB
C
Raw Normal View History

/*
* Forwarding database
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/spinlock.h>
#include <linux/times.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/jhash.h>
#include <linux/random.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 08:04:11 +00:00
#include <linux/slab.h>
#include <asm/atomic.h>
#include <asm/unaligned.h>
#include "br_private.h"
static struct kmem_cache *br_fdb_cache __read_mostly;
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr);
static u32 fdb_salt __read_mostly;
int __init br_fdb_init(void)
{
br_fdb_cache = kmem_cache_create("bridge_fdb_cache",
sizeof(struct net_bridge_fdb_entry),
0,
SLAB_HWCACHE_ALIGN, NULL);
if (!br_fdb_cache)
return -ENOMEM;
get_random_bytes(&fdb_salt, sizeof(fdb_salt));
return 0;
}
void br_fdb_fini(void)
{
kmem_cache_destroy(br_fdb_cache);
}
/* if topology_changing then use forward_delay (default 15 sec)
* otherwise keep longer (default 5 minutes)
*/
static inline unsigned long hold_time(const struct net_bridge *br)
{
return br->topology_change ? br->forward_delay : br->ageing_time;
}
static inline int has_expired(const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb)
{
return !fdb->is_static &&
time_before_eq(fdb->ageing_timer + hold_time(br), jiffies);
}
static inline int br_mac_hash(const unsigned char *mac)
{
/* use 1 byte of OUI cnd 3 bytes of NIC */
u32 key = get_unaligned((u32 *)(mac + 2));
return jhash_1word(key, fdb_salt) & (BR_HASH_SIZE - 1);
}
static void fdb_rcu_free(struct rcu_head *head)
{
struct net_bridge_fdb_entry *ent
= container_of(head, struct net_bridge_fdb_entry, rcu);
kmem_cache_free(br_fdb_cache, ent);
}
static inline void fdb_delete(struct net_bridge_fdb_entry *f)
{
hlist_del_rcu(&f->hlist);
call_rcu(&f->rcu, fdb_rcu_free);
}
void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
{
struct net_bridge *br = p->br;
int i;
spin_lock_bh(&br->hash_lock);
/* Search all chains since old address/hash is unknown */
for (i = 0; i < BR_HASH_SIZE; i++) {
struct hlist_node *h;
hlist_for_each(h, &br->hash[i]) {
struct net_bridge_fdb_entry *f;
f = hlist_entry(h, struct net_bridge_fdb_entry, hlist);
if (f->dst == p && f->is_local) {
/* maybe another port has same hw addr? */
struct net_bridge_port *op;
list_for_each_entry(op, &br->port_list, list) {
if (op != p &&
!compare_ether_addr(op->dev->dev_addr,
f->addr.addr)) {
f->dst = op;
goto insert;
}
}
/* delete old one */
fdb_delete(f);
goto insert;
}
}
}
insert:
/* insert new address, may fail if invalid address or dup. */
fdb_insert(br, p, newaddr);
spin_unlock_bh(&br->hash_lock);
}
void br_fdb_cleanup(unsigned long _data)
{
struct net_bridge *br = (struct net_bridge *)_data;
unsigned long delay = hold_time(br);
unsigned long next_timer = jiffies + br->ageing_time;
int i;
spin_lock_bh(&br->hash_lock);
for (i = 0; i < BR_HASH_SIZE; i++) {
struct net_bridge_fdb_entry *f;
struct hlist_node *h, *n;
hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) {
unsigned long this_timer;
if (f->is_static)
continue;
this_timer = f->ageing_timer + delay;
if (time_before_eq(this_timer, jiffies))
fdb_delete(f);
else if (time_before(this_timer, next_timer))
next_timer = this_timer;
}
}
spin_unlock_bh(&br->hash_lock);
mod_timer(&br->gc_timer, round_jiffies_up(next_timer));
}
/* Completely flush all dynamic entries in forwarding database.*/
void br_fdb_flush(struct net_bridge *br)
{
int i;
spin_lock_bh(&br->hash_lock);
for (i = 0; i < BR_HASH_SIZE; i++) {
struct net_bridge_fdb_entry *f;
struct hlist_node *h, *n;
hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) {
if (!f->is_static)
fdb_delete(f);
}
}
spin_unlock_bh(&br->hash_lock);
}
/* Flush all entries refering to a specific port.
* if do_all is set also flush static entries
*/
void br_fdb_delete_by_port(struct net_bridge *br,
const struct net_bridge_port *p,
int do_all)
{
int i;
spin_lock_bh(&br->hash_lock);
for (i = 0; i < BR_HASH_SIZE; i++) {
struct hlist_node *h, *g;
hlist_for_each_safe(h, g, &br->hash[i]) {
struct net_bridge_fdb_entry *f
= hlist_entry(h, struct net_bridge_fdb_entry, hlist);
if (f->dst != p)
continue;
if (f->is_static && !do_all)
continue;
/*
* if multiple ports all have the same device address
* then when one port is deleted, assign
* the local entry to other port
*/
if (f->is_local) {
struct net_bridge_port *op;
list_for_each_entry(op, &br->port_list, list) {
if (op != p &&
!compare_ether_addr(op->dev->dev_addr,
f->addr.addr)) {
f->dst = op;
goto skip_delete;
}
}
}
fdb_delete(f);
skip_delete: ;
}
}
spin_unlock_bh(&br->hash_lock);
}
/* No locking or refcounting, assumes caller has rcu_read_lock */
struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br,
const unsigned char *addr)
{
struct hlist_node *h;
struct net_bridge_fdb_entry *fdb;
hlist_for_each_entry_rcu(fdb, h, &br->hash[br_mac_hash(addr)], hlist) {
if (!compare_ether_addr(fdb->addr.addr, addr)) {
if (unlikely(has_expired(br, fdb)))
break;
return fdb;
}
}
return NULL;
}
#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
/* Interface used by ATM LANE hook to test
* if an addr is on some other bridge port */
int br_fdb_test_addr(struct net_device *dev, unsigned char *addr)
{
struct net_bridge_fdb_entry *fdb;
int ret;
if (!br_port_exists(dev))
return 0;
rcu_read_lock();
fdb = __br_fdb_get(br_port_get_rcu(dev)->br, addr);
ret = fdb && fdb->dst->dev != dev &&
fdb->dst->state == BR_STATE_FORWARDING;
rcu_read_unlock();
return ret;
}
#endif /* CONFIG_ATM_LANE */
/*
* Fill buffer with forwarding table records in
* the API format.
*/
int br_fdb_fillbuf(struct net_bridge *br, void *buf,
unsigned long maxnum, unsigned long skip)
{
struct __fdb_entry *fe = buf;
int i, num = 0;
struct hlist_node *h;
struct net_bridge_fdb_entry *f;
memset(buf, 0, maxnum*sizeof(struct __fdb_entry));
rcu_read_lock();
for (i = 0; i < BR_HASH_SIZE; i++) {
hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) {
if (num >= maxnum)
goto out;
if (has_expired(br, f))
continue;
if (skip) {
--skip;
continue;
}
/* convert from internal format to API */
memcpy(fe->mac_addr, f->addr.addr, ETH_ALEN);
/* due to ABI compat need to split into hi/lo */
fe->port_no = f->dst->port_no;
fe->port_hi = f->dst->port_no >> 8;
fe->is_local = f->is_local;
if (!f->is_static)
fe->ageing_timer_value = jiffies_to_clock_t(jiffies - f->ageing_timer);
++fe;
++num;
}
}
out:
rcu_read_unlock();
return num;
}
static inline struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head,
const unsigned char *addr)
{
struct hlist_node *h;
struct net_bridge_fdb_entry *fdb;
hlist_for_each_entry_rcu(fdb, h, head, hlist) {
if (!compare_ether_addr(fdb->addr.addr, addr))
return fdb;
}
return NULL;
}
static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
struct net_bridge_port *source,
const unsigned char *addr,
int is_local)
{
struct net_bridge_fdb_entry *fdb;
fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC);
if (fdb) {
memcpy(fdb->addr.addr, addr, ETH_ALEN);
hlist_add_head_rcu(&fdb->hlist, head);
fdb->dst = source;
fdb->is_local = is_local;
fdb->is_static = is_local;
fdb->ageing_timer = jiffies;
}
return fdb;
}
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr)];
struct net_bridge_fdb_entry *fdb;
if (!is_valid_ether_addr(addr))
return -EINVAL;
fdb = fdb_find(head, addr);
if (fdb) {
/* it is okay to have multiple ports with same
* address, just use the first one.
*/
if (fdb->is_local)
return 0;
br_warn(br, "adding interface %s with same address "
"as a received packet\n",
source->dev->name);
fdb_delete(fdb);
}
if (!fdb_create(head, source, addr, 1))
return -ENOMEM;
return 0;
}
int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr)
{
int ret;
spin_lock_bh(&br->hash_lock);
ret = fdb_insert(br, source, addr);
spin_unlock_bh(&br->hash_lock);
return ret;
}
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr)];
struct net_bridge_fdb_entry *fdb;
/* some users want to always flood. */
if (hold_time(br) == 0)
return;
/* ignore packets unless we are using this port */
if (!(source->state == BR_STATE_LEARNING ||
source->state == BR_STATE_FORWARDING))
return;
fdb = fdb_find(head, addr);
if (likely(fdb)) {
/* attempt to update an entry for a local interface */
if (unlikely(fdb->is_local)) {
if (net_ratelimit())
br_warn(br, "received packet on %s with "
"own address as source address\n",
source->dev->name);
} else {
/* fastpath: update of existing entry */
fdb->dst = source;
fdb->ageing_timer = jiffies;
}
} else {
spin_lock(&br->hash_lock);
if (!fdb_find(head, addr))
fdb_create(head, source, addr, 0);
/* else we lose race and someone else inserts
* it first, don't bother updating
*/
spin_unlock(&br->hash_lock);
}
}