OpenCloudOS-Kernel/net/bridge/br_if.c

506 lines
10 KiB
C
Raw Normal View History

/*
* Userspace interface
* 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/netdevice.h>
#include <linux/netpoll.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/rtnetlink.h>
#include <linux/if_ether.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 <net/sock.h>
#include "br_private.h"
/*
* Determine initial path cost based on speed.
* using recommendations from 802.1d standard
*
* Since driver might sleep need to not be holding any locks.
*/
static int port_cost(struct net_device *dev)
{
if (dev->ethtool_ops && dev->ethtool_ops->get_settings) {
struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, };
if (!dev->ethtool_ops->get_settings(dev, &ecmd)) {
switch(ecmd.speed) {
case SPEED_10000:
return 2;
case SPEED_1000:
return 4;
case SPEED_100:
return 19;
case SPEED_10:
return 100;
}
}
}
/* Old silly heuristics based on name */
if (!strncmp(dev->name, "lec", 3))
return 7;
if (!strncmp(dev->name, "plip", 4))
return 2500;
return 100; /* assume old 10Mbps */
}
/* Check for port carrier transistions. */
void br_port_carrier_check(struct net_bridge_port *p)
{
struct net_device *dev = p->dev;
struct net_bridge *br = p->br;
if (netif_running(dev) && netif_carrier_ok(dev))
p->path_cost = port_cost(dev);
if (!netif_running(br->dev))
return;
spin_lock_bh(&br->lock);
if (netif_running(dev) && netif_carrier_ok(dev)) {
if (p->state == BR_STATE_DISABLED)
br_stp_enable_port(p);
} else {
if (p->state != BR_STATE_DISABLED)
br_stp_disable_port(p);
}
spin_unlock_bh(&br->lock);
}
static void release_nbp(struct kobject *kobj)
{
struct net_bridge_port *p
= container_of(kobj, struct net_bridge_port, kobj);
kfree(p);
}
static struct kobj_type brport_ktype = {
#ifdef CONFIG_SYSFS
.sysfs_ops = &brport_sysfs_ops,
#endif
.release = release_nbp,
};
static void destroy_nbp(struct net_bridge_port *p)
{
struct net_device *dev = p->dev;
p->br = NULL;
p->dev = NULL;
dev_put(dev);
kobject_put(&p->kobj);
}
static void destroy_nbp_rcu(struct rcu_head *head)
{
struct net_bridge_port *p =
container_of(head, struct net_bridge_port, rcu);
destroy_nbp(p);
}
/* Delete port(interface) from bridge is done in two steps.
* via RCU. First step, marks device as down. That deletes
* all the timers and stops new packets from flowing through.
*
* Final cleanup doesn't occur until after all CPU's finished
* processing packets.
*
* Protected from multiple admin operations by RTNL mutex
*/
static void del_nbp(struct net_bridge_port *p)
{
struct net_bridge *br = p->br;
struct net_device *dev = p->dev;
sysfs_remove_link(br->ifobj, p->dev->name);
dev_set_promiscuity(dev, -1);
spin_lock_bh(&br->lock);
br_stp_disable_port(p);
spin_unlock_bh(&br->lock);
br_ifinfo_notify(RTM_DELLINK, p);
br_fdb_delete_by_port(br, p, 1);
list_del_rcu(&p->list);
dev->priv_flags &= ~IFF_BRIDGE_PORT;
netdev_rx_handler_unregister(dev);
br_multicast_del_port(p);
kobject_uevent(&p->kobj, KOBJ_REMOVE);
kobject_del(&p->kobj);
br_netpoll_disable(p);
call_rcu(&p->rcu, destroy_nbp_rcu);
}
/* called with RTNL */
static void del_br(struct net_bridge *br, struct list_head *head)
{
struct net_bridge_port *p, *n;
list_for_each_entry_safe(p, n, &br->port_list, list) {
del_nbp(p);
}
del_timer_sync(&br->gc_timer);
br_sysfs_delbr(br->dev);
unregister_netdevice_queue(br->dev, head);
}
static struct net_device *new_bridge_dev(struct net *net, const char *name)
{
struct net_bridge *br;
struct net_device *dev;
dev = alloc_netdev(sizeof(struct net_bridge), name,
br_dev_setup);
if (!dev)
return NULL;
dev_net_set(dev, net);
br = netdev_priv(dev);
br->dev = dev;
br->stats = alloc_percpu(struct br_cpu_netstats);
if (!br->stats) {
free_netdev(dev);
return NULL;
}
spin_lock_init(&br->lock);
INIT_LIST_HEAD(&br->port_list);
spin_lock_init(&br->hash_lock);
br->bridge_id.prio[0] = 0x80;
br->bridge_id.prio[1] = 0x00;
memcpy(br->group_addr, br_group_address, ETH_ALEN);
br->feature_mask = dev->features;
br->stp_enabled = BR_NO_STP;
br->designated_root = br->bridge_id;
br->root_path_cost = 0;
br->root_port = 0;
br->bridge_max_age = br->max_age = 20 * HZ;
br->bridge_hello_time = br->hello_time = 2 * HZ;
br->bridge_forward_delay = br->forward_delay = 15 * HZ;
br->topology_change = 0;
br->topology_change_detected = 0;
br->ageing_time = 300 * HZ;
br_netfilter_rtable_init(br);
br_stp_timer_init(br);
br_multicast_init(br);
return dev;
}
/* find an available port number */
static int find_portno(struct net_bridge *br)
{
int index;
struct net_bridge_port *p;
unsigned long *inuse;
inuse = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long),
GFP_KERNEL);
if (!inuse)
return -ENOMEM;
set_bit(0, inuse); /* zero is reserved */
list_for_each_entry(p, &br->port_list, list) {
set_bit(p->port_no, inuse);
}
index = find_first_zero_bit(inuse, BR_MAX_PORTS);
kfree(inuse);
return (index >= BR_MAX_PORTS) ? -EXFULL : index;
}
/* called with RTNL but without bridge lock */
static struct net_bridge_port *new_nbp(struct net_bridge *br,
struct net_device *dev)
{
int index;
struct net_bridge_port *p;
index = find_portno(br);
if (index < 0)
return ERR_PTR(index);
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (p == NULL)
return ERR_PTR(-ENOMEM);
p->br = br;
dev_hold(dev);
p->dev = dev;
p->path_cost = port_cost(dev);
p->priority = 0x8000 >> BR_PORT_BITS;
p->port_no = index;
p->flags = 0;
br_init_port(p);
p->state = BR_STATE_DISABLED;
br_stp_port_timer_init(p);
br_multicast_add_port(p);
return p;
}
static struct device_type br_type = {
.name = "bridge",
};
int br_add_bridge(struct net *net, const char *name)
{
struct net_device *dev;
int ret;
dev = new_bridge_dev(net, name);
if (!dev)
return -ENOMEM;
rtnl_lock();
if (strchr(dev->name, '%')) {
ret = dev_alloc_name(dev, dev->name);
if (ret < 0)
goto out_free;
}
SET_NETDEV_DEVTYPE(dev, &br_type);
ret = register_netdevice(dev);
if (ret)
goto out_free;
ret = br_sysfs_addbr(dev);
if (ret)
unregister_netdevice(dev);
out:
rtnl_unlock();
return ret;
out_free:
free_netdev(dev);
goto out;
}
int br_del_bridge(struct net *net, const char *name)
{
struct net_device *dev;
int ret = 0;
rtnl_lock();
dev = __dev_get_by_name(net, name);
if (dev == NULL)
ret = -ENXIO; /* Could not find device */
else if (!(dev->priv_flags & IFF_EBRIDGE)) {
/* Attempt to delete non bridge device! */
ret = -EPERM;
}
else if (dev->flags & IFF_UP) {
/* Not shutdown yet. */
ret = -EBUSY;
}
else
del_br(netdev_priv(dev), NULL);
rtnl_unlock();
return ret;
}
/* MTU of the bridge pseudo-device: ETH_DATA_LEN or the minimum of the ports */
int br_min_mtu(const struct net_bridge *br)
{
const struct net_bridge_port *p;
int mtu = 0;
ASSERT_RTNL();
if (list_empty(&br->port_list))
mtu = ETH_DATA_LEN;
else {
list_for_each_entry(p, &br->port_list, list) {
if (!mtu || p->dev->mtu < mtu)
mtu = p->dev->mtu;
}
}
return mtu;
}
/*
* Recomputes features using slave's features
*/
void br_features_recompute(struct net_bridge *br)
{
struct net_bridge_port *p;
unsigned long features, mask;
features = mask = br->feature_mask;
if (list_empty(&br->port_list))
goto done;
features &= ~NETIF_F_ONE_FOR_ALL;
list_for_each_entry(p, &br->port_list, list) {
features = netdev_increment_features(features,
p->dev->features, mask);
}
done:
br->dev->features = netdev_fix_features(features, NULL);
}
/* called with RTNL */
int br_add_if(struct net_bridge *br, struct net_device *dev)
{
struct net_bridge_port *p;
int err = 0;
/* Don't allow bridging non-ethernet like devices */
if ((dev->flags & IFF_LOOPBACK) ||
dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN)
return -EINVAL;
/* No bridging of bridges */
if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)
return -ELOOP;
/* Device is already being bridged */
if (br_port_exists(dev))
return -EBUSY;
/* No bridging devices that dislike that (e.g. wireless) */
if (dev->priv_flags & IFF_DONT_BRIDGE)
return -EOPNOTSUPP;
p = new_nbp(br, dev);
if (IS_ERR(p))
return PTR_ERR(p);
err = dev_set_promiscuity(dev, 1);
if (err)
goto put_back;
err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj),
SYSFS_BRIDGE_PORT_ATTR);
if (err)
goto err0;
err = br_fdb_insert(br, p, dev->dev_addr);
if (err)
goto err1;
err = br_sysfs_addif(p);
if (err)
goto err2;
if (br_netpoll_info(br) && ((err = br_netpoll_enable(p))))
goto err3;
err = netdev_rx_handler_register(dev, br_handle_frame, p);
if (err)
goto err3;
dev->priv_flags |= IFF_BRIDGE_PORT;
dev_disable_lro(dev);
list_add_rcu(&p->list, &br->port_list);
spin_lock_bh(&br->lock);
br_stp_recalculate_bridge_id(br);
br_features_recompute(br);
if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) &&
(br->dev->flags & IFF_UP))
br_stp_enable_port(p);
spin_unlock_bh(&br->lock);
br_ifinfo_notify(RTM_NEWLINK, p);
dev_set_mtu(br->dev, br_min_mtu(br));
kobject_uevent(&p->kobj, KOBJ_ADD);
return 0;
err3:
sysfs_remove_link(br->ifobj, p->dev->name);
err2:
br_fdb_delete_by_port(br, p, 1);
err1:
kobject_put(&p->kobj);
p = NULL; /* kobject_put frees */
err0:
dev_set_promiscuity(dev, -1);
put_back:
dev_put(dev);
kfree(p);
return err;
}
/* called with RTNL */
int br_del_if(struct net_bridge *br, struct net_device *dev)
{
struct net_bridge_port *p;
p = br_port_get_rtnl(dev);
if (!p || p->br != br)
return -EINVAL;
del_nbp(p);
spin_lock_bh(&br->lock);
br_stp_recalculate_bridge_id(br);
br_features_recompute(br);
spin_unlock_bh(&br->lock);
return 0;
}
void __net_exit br_net_exit(struct net *net)
{
struct net_device *dev;
LIST_HEAD(list);
rtnl_lock();
for_each_netdev(net, dev)
if (dev->priv_flags & IFF_EBRIDGE)
del_br(netdev_priv(dev), &list);
unregister_netdevice_many(&list);
rtnl_unlock();
}