kernel_optimize_test/net/bridge/br_if.c

578 lines
12 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/etherdevice.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 <linux/if_vlan.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)
{
struct ethtool_cmd ecmd;
if (!__ethtool_get_settings(dev, &ecmd)) {
switch (ethtool_cmd_speed(&ecmd)) {
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 transitions. */
void br_port_carrier_check(struct net_bridge_port *p)
{
struct net_device *dev = p->dev;
struct net_bridge *br = p->br;
if (!(p->flags & BR_ADMIN_COST) &&
netif_running(dev) && netif_oper_up(dev))
p->path_cost = port_cost(dev);
if (!netif_running(br->dev))
return;
spin_lock_bh(&br->lock);
if (netif_running(dev) && netif_oper_up(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);
}
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
static void br_port_set_promisc(struct net_bridge_port *p)
{
int err = 0;
if (br_promisc_port(p))
return;
err = dev_set_promiscuity(p->dev, 1);
if (err)
return;
br_fdb_unsync_static(p->br, p);
p->flags |= BR_PROMISC;
}
static void br_port_clear_promisc(struct net_bridge_port *p)
{
int err;
/* Check if the port is already non-promisc or if it doesn't
* support UNICAST filtering. Without unicast filtering support
* we'll end up re-enabling promisc mode anyway, so just check for
* it here.
*/
if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT))
return;
/* Since we'll be clearing the promisc mode, program the port
* first so that we don't have interruption in traffic.
*/
err = br_fdb_sync_static(p->br, p);
if (err)
return;
dev_set_promiscuity(p->dev, -1);
p->flags &= ~BR_PROMISC;
}
/* When a port is added or removed or when certain port flags
* change, this function is called to automatically manage
* promiscuity setting of all the bridge ports. We are always called
* under RTNL so can skip using rcu primitives.
*/
void br_manage_promisc(struct net_bridge *br)
{
struct net_bridge_port *p;
bool set_all = false;
/* If vlan filtering is disabled or bridge interface is placed
* into promiscuous mode, place all ports in promiscuous mode.
*/
if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br))
set_all = true;
list_for_each_entry(p, &br->port_list, list) {
if (set_all) {
br_port_set_promisc(p);
} else {
/* If the number of auto-ports is <= 1, then all other
* ports will have their output configuration
* statically specified through fdbs. Since ingress
* on the auto-port becomes forwarding/egress to other
* ports and egress configuration is statically known,
* we can say that ingress configuration of the
* auto-port is also statically known.
* This lets us disable promiscuous mode and write
* this config to hw.
*/
if (br->auto_cnt == 0 ||
(br->auto_cnt == 1 && br_auto_port(p)))
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
br_port_clear_promisc(p);
else
br_port_set_promisc(p);
}
}
}
static void nbp_update_port_count(struct net_bridge *br)
{
struct net_bridge_port *p;
u32 cnt = 0;
list_for_each_entry(p, &br->port_list, list) {
if (br_auto_port(p))
cnt++;
}
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
if (br->auto_cnt != cnt) {
br->auto_cnt = cnt;
br_manage_promisc(br);
}
}
static void nbp_delete_promisc(struct net_bridge_port *p)
{
/* If port is currently promiscuous, unset promiscuity.
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
* Otherwise, it is a static port so remove all addresses
* from it.
*/
dev_set_allmulti(p->dev, -1);
if (br_promisc_port(p))
dev_set_promiscuity(p->dev, -1);
else
br_fdb_unsync_static(p->br, p);
}
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);
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
nbp_delete_promisc(p);
spin_lock_bh(&br->lock);
br_stp_disable_port(p);
spin_unlock_bh(&br->lock);
br_ifinfo_notify(RTM_DELLINK, p);
list_del_rcu(&p->list);
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
nbp_vlan_flush(p);
br_fdb_delete_by_port(br, p, 1);
nbp_update_port_count(br);
netdev_upper_dev_unlink(dev, br->dev);
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);
}
/* Delete bridge device */
void br_dev_delete(struct net_device *dev, struct list_head *head)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p, *n;
list_for_each_entry_safe(p, n, &br->port_list, list) {
del_nbp(p);
}
bridge: flush br's address entry in fdb when remove the bridge dev When the following commands are executed: brctl addbr br0 ifconfig br0 hw ether <addr> rmmod bridge The calltrace will occur: [ 563.312114] device eth1 left promiscuous mode [ 563.312188] br0: port 1(eth1) entered disabled state [ 563.468190] kmem_cache_destroy bridge_fdb_cache: Slab cache still has objects [ 563.468197] CPU: 6 PID: 6982 Comm: rmmod Tainted: G O 3.12.0-0.7-default+ #9 [ 563.468199] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007 [ 563.468200] 0000000000000880 ffff88010f111e98 ffffffff814d1c92 ffff88010f111eb8 [ 563.468204] ffffffff81148efd ffff88010f111eb8 0000000000000000 ffff88010f111ec8 [ 563.468206] ffffffffa062a270 ffff88010f111ed8 ffffffffa063ac76 ffff88010f111f78 [ 563.468209] Call Trace: [ 563.468218] [<ffffffff814d1c92>] dump_stack+0x6a/0x78 [ 563.468234] [<ffffffff81148efd>] kmem_cache_destroy+0xfd/0x100 [ 563.468242] [<ffffffffa062a270>] br_fdb_fini+0x10/0x20 [bridge] [ 563.468247] [<ffffffffa063ac76>] br_deinit+0x4e/0x50 [bridge] [ 563.468254] [<ffffffff810c7dc9>] SyS_delete_module+0x199/0x2b0 [ 563.468259] [<ffffffff814e0922>] system_call_fastpath+0x16/0x1b [ 570.377958] Bridge firewalling registered --------------------------- cut here ------------------------------- The reason is that when the bridge dev's address is changed, the br_fdb_change_mac_address() will add new address in fdb, but when the bridge was removed, the address entry in the fdb did not free, the bridge_fdb_cache still has objects when destroy the cache, Fix this by flushing the bridge address entry when removing the bridge. v2: according to the Toshiaki Makita and Vlad's suggestion, I only delete the vlan0 entry, it still have a leak here if the vlan id is other number, so I need to call fdb_delete_by_port(br, NULL, 1) to flush all entries whose dst is NULL for the bridge. Suggested-by: Toshiaki Makita <toshiaki.makita1@gmail.com> Suggested-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-07 22:12:05 +08:00
br_fdb_delete_by_port(br, NULL, 1);
bridge: Fix memory leak when deleting bridge with vlan filtering enabled We currently don't call br_vlan_flush() when deleting a bridge, which leads to memory leak if br->vlan_info is allocated. Steps to reproduce: while : do brctl addbr br0 bridge vlan add dev br0 vid 10 self brctl delbr br0 done We can observe the cache size of corresponding slab entry (as kmalloc-2048 in SLUB) is increased. kmemleak output: unreferenced object 0xffff8800b68a7000 (size 2048): comm "bridge", pid 2086, jiffies 4295774704 (age 47.656s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 48 9b 36 00 88 ff ff .........H.6.... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff815eb6ae>] kmemleak_alloc+0x4e/0xb0 [<ffffffff8116a1ca>] kmem_cache_alloc_trace+0xca/0x220 [<ffffffffa03eddd6>] br_vlan_add+0x66/0xe0 [bridge] [<ffffffffa03e543c>] br_setlink+0x2dc/0x340 [bridge] [<ffffffff8150e481>] rtnl_bridge_setlink+0x101/0x200 [<ffffffff8150d9d9>] rtnetlink_rcv_msg+0x99/0x260 [<ffffffff81528679>] netlink_rcv_skb+0xa9/0xc0 [<ffffffff8150d938>] rtnetlink_rcv+0x28/0x30 [<ffffffff81527ccd>] netlink_unicast+0xdd/0x190 [<ffffffff8152807f>] netlink_sendmsg+0x2ff/0x740 [<ffffffff814e8368>] sock_sendmsg+0x88/0xc0 [<ffffffff814e8ac8>] ___sys_sendmsg.part.14+0x298/0x2b0 [<ffffffff814e91de>] __sys_sendmsg+0x4e/0x90 [<ffffffff814e922e>] SyS_sendmsg+0xe/0x10 [<ffffffff81601669>] system_call_fastpath+0x16/0x1b [<ffffffffffffffff>] 0xffffffffffffffff Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-13 16:26:14 +08:00
br_vlan_flush(br);
del_timer_sync(&br->gc_timer);
br_sysfs_delbr(br->dev);
unregister_netdevice_queue(br->dev, head);
}
/* 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;
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
p->flags = BR_LEARNING | BR_FLOOD;
br_init_port(p);
br_set_state(p, BR_STATE_DISABLED);
br_stp_port_timer_init(p);
br_multicast_add_port(p);
return p;
}
int br_add_bridge(struct net *net, const char *name)
{
struct net_device *dev;
int res;
dev = alloc_netdev(sizeof(struct net_bridge), name, NET_NAME_UNKNOWN,
br_dev_setup);
if (!dev)
return -ENOMEM;
dev_net_set(dev, net);
dev->rtnl_link_ops = &br_link_ops;
res = register_netdev(dev);
if (res)
free_netdev(dev);
return res;
}
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
br_dev_delete(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
*/
netdev_features_t br_features_recompute(struct net_bridge *br,
netdev_features_t features)
{
struct net_bridge_port *p;
netdev_features_t mask;
if (list_empty(&br->port_list))
return features;
mask = features;
features &= ~NETIF_F_ONE_FOR_ALL;
list_for_each_entry(p, &br->port_list, list) {
features = netdev_increment_features(features,
p->dev->features, mask);
}
return features;
}
/* called with RTNL */
int br_add_if(struct net_bridge *br, struct net_device *dev)
{
struct net_bridge_port *p;
int err = 0;
bool changed_addr;
/* Don't allow bridging non-ethernet like devices */
if ((dev->flags & IFF_LOOPBACK) ||
dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN ||
!is_valid_ether_addr(dev->dev_addr))
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);
call_netdevice_notifiers(NETDEV_JOIN, dev);
bridge: Automatically manage port promiscuous mode. There exist configurations where the administrator or another management entity has the foreknowledge of all the mac addresses of end systems that are being bridged together. In these environments, the administrator can statically configure known addresses in the bridge FDB and disable flooding and learning on ports. This makes it possible to turn off promiscuous mode on the interfaces connected to the bridge. Here is why disabling flooding and learning allows us to control promiscuity: Consider port X. All traffic coming into this port from outside the bridge (ingress) will be either forwarded through other ports of the bridge (egress) or dropped. Forwarding (egress) is defined by FDB entries and by flooding in the event that no FDB entry exists. In the event that flooding is disabled, only FDB entries define the egress. Once learning is disabled, only static FDB entries provided by a management entity define the egress. If we provide information from these static FDBs to the ingress port X, then we'll be able to accept all traffic that can be successfully forwarded and drop all the other traffic sooner without spending CPU cycles to process it. Another way to define the above is as following equations: ingress = egress + drop expanding egress ingress = static FDB + learned FDB + flooding + drop disabling flooding and learning we a left with ingress = static FDB + drop By adding addresses from the static FDB entries to the MAC address filter of an ingress port X, we fully define what the bridge can process without dropping and can thus turn off promiscuous mode, thus dropping packets sooner. There have been suggestions that we may want to allow learning and update the filters with learned addresses as well. This would require mac-level authentication similar to 802.1x to prevent attacks against the hw filters as they are limited resource. Additionally, if the user places the bridge device in promiscuous mode, all ports are placed in promiscuous mode regardless of the changes to flooding and learning. Since the above functionality depends on full static configuration, we have also require that vlan filtering be enabled to take advantage of this. The reason is that the bridge has to be able to receive and process VLAN-tagged frames and the there are only 2 ways to accomplish this right now: promiscuous mode or vlan filtering. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-16 21:59:20 +08:00
err = dev_set_allmulti(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 err1;
err = br_sysfs_addif(p);
if (err)
goto err2;
netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang <amwang@redhat.com> Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong <dingtianhong@huawei.com> Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Cc: Jay Vosburgh <fubar@us.ibm.com> Cc: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: David S. Miller <davem@davemloft.net> Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28 06:36:38 +08:00
err = br_netpoll_enable(p);
if (err)
goto err3;
err = netdev_rx_handler_register(dev, br_handle_frame, p);
if (err)
goto err4;
dev->priv_flags |= IFF_BRIDGE_PORT;
err = netdev_master_upper_dev_link(dev, br->dev);
if (err)
goto err5;
dev_disable_lro(dev);
list_add_rcu(&p->list, &br->port_list);
nbp_update_port_count(br);
netdev_update_features(br->dev);
if (br->dev->needed_headroom < dev->needed_headroom)
br->dev->needed_headroom = dev->needed_headroom;
bridge: Change local fdb entries whenever mac address of bridge device changes Vlan code may need fdb change when changing mac address of bridge device even if it is caused by the mac address changing of a bridge port. Example configuration: ip link set eth0 address 12:34:56:78:90:ab ip link set eth1 address aa:bb:cc:dd:ee:ff brctl addif br0 eth0 brctl addif br0 eth1 # br0 will have mac address 12:34:56:78:90:ab bridge vlan add dev br0 vid 10 self bridge vlan add dev eth0 vid 10 We will have fdb entry such that f->dst == NULL, f->vlan_id == 10 and f->addr == 12:34:56:78:90:ab at this time. Next, change the mac address of eth0 to greater value. ip link set eth0 address ee:ff:12:34:56:78 Then, mac address of br0 will be recalculated and set to aa:bb:cc:dd:ee:ff. However, an entry aa:bb:cc:dd:ee:ff will not be created and we will be not able to communicate using br0 on vlan 10. Address this issue by deleting and adding local entries whenever changing the mac address of the bridge device. If there already exists an entry that has the same address, for example, in case that br_fdb_changeaddr() has already inserted it, br_fdb_change_mac_address() will simply fail to insert it and no duplicated entry will be made, as it was. This approach also needs br_add_if() to call br_fdb_insert() before br_stp_recalculate_bridge_id() so that we don't create an entry whose dst == NULL in this function to preserve previous behavior. Note that this is a slight change in behavior where the bridge device can receive the traffic to the new address before calling br_stp_recalculate_bridge_id() in br_add_if(). However, it is not a problem because we have already the address on the new port and such a way to insert new one before recalculating bridge id is taken in br_device_event() as well. Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-07 15:48:21 +08:00
if (br_fdb_insert(br, p, dev->dev_addr, 0))
netdev_err(dev, "failed insert local address bridge forwarding table\n");
if (nbp_vlan_init(p))
netdev_err(dev, "failed to initialize vlan filtering on this port\n");
spin_lock_bh(&br->lock);
changed_addr = br_stp_recalculate_bridge_id(br);
if (netif_running(dev) && netif_oper_up(dev) &&
(br->dev->flags & IFF_UP))
br_stp_enable_port(p);
spin_unlock_bh(&br->lock);
br_ifinfo_notify(RTM_NEWLINK, p);
if (changed_addr)
call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
dev_set_mtu(br->dev, br_min_mtu(br));
kobject_uevent(&p->kobj, KOBJ_ADD);
return 0;
err5:
dev->priv_flags &= ~IFF_BRIDGE_PORT;
netdev_rx_handler_unregister(dev);
err4:
br_netpoll_disable(p);
err3:
sysfs_remove_link(br->ifobj, p->dev->name);
err2:
kobject_put(&p->kobj);
p = NULL; /* kobject_put frees */
err1:
dev_set_allmulti(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;
bool changed_addr;
p = br_port_get_rtnl(dev);
if (!p || p->br != br)
return -EINVAL;
/* Since more than one interface can be attached to a bridge,
* there still maybe an alternate path for netconsole to use;
* therefore there is no reason for a NETDEV_RELEASE event.
*/
del_nbp(p);
spin_lock_bh(&br->lock);
changed_addr = br_stp_recalculate_bridge_id(br);
spin_unlock_bh(&br->lock);
if (changed_addr)
call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
netdev_update_features(br->dev);
return 0;
}
void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
{
struct net_bridge *br = p->br;
if (mask & BR_AUTO_MASK)
nbp_update_port_count(br);
}