linux-sg2042/net/bridge/br_device.c

392 lines
9.0 KiB
C
Raw Normal View History

/*
* Device handling code
* 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/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/list.h>
#include <linux/netfilter_bridge.h>
#include <asm/uaccess.h>
#include "br_private.h"
#define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
NETIF_F_GSO_MASK | NETIF_F_HW_CSUM)
/* net device transmit always called with BH disabled */
netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
const unsigned char *dest = skb->data;
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
u16 vid = 0;
rcu_read_lock();
#ifdef CONFIG_BRIDGE_NETFILTER
if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
br_nf_pre_routing_finish_bridge_slow(skb);
rcu_read_unlock();
return NETDEV_TX_OK;
}
#endif
u64_stats_update_begin(&brstats->syncp);
brstats->tx_packets++;
brstats->tx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
goto out;
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
if (is_broadcast_ether_addr(dest))
br_flood_deliver(br, skb, false);
else if (is_multicast_ether_addr(dest)) {
if (unlikely(netpoll_tx_running(dev))) {
br_flood_deliver(br, skb, false);
goto out;
}
if (br_multicast_rcv(br, NULL, skb, vid)) {
kfree_skb(skb);
goto out;
}
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb)))
br_multicast_deliver(mdst, skb);
else
br_flood_deliver(br, skb, false);
} else if ((dst = __br_fdb_get(br, dest, vid)) != NULL)
br_deliver(dst->dst, skb);
else
br_flood_deliver(br, skb, true);
out:
rcu_read_unlock();
return NETDEV_TX_OK;
}
static int br_dev_init(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
net: Explicitly initialize u64_stats_sync structures for lockdep In order to enable lockdep on seqcount/seqlock structures, we must explicitly initialize any locks. The u64_stats_sync structure, uses a seqcount, and thus we need to introduce a u64_stats_init() function and use it to initialize the structure. This unfortunately adds a lot of fairly trivial initialization code to a number of drivers. But the benefit of ensuring correctness makes this worth while. Because these changes are required for lockdep to be enabled, and the changes are quite trivial, I've not yet split this patch out into 30-some separate patches, as I figured it would be better to get the various maintainers thoughts on how to best merge this change along with the seqcount lockdep enablement. Feedback would be appreciated! Signed-off-by: John Stultz <john.stultz@linaro.org> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: "David S. Miller" <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: James Morris <jmorris@namei.org> Cc: Jesse Gross <jesse@nicira.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mirko Lindner <mlindner@marvell.com> Cc: Patrick McHardy <kaber@trash.net> Cc: Roger Luethi <rl@hellgate.ch> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Simon Horman <horms@verge.net.au> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Cc: Wensong Zhang <wensong@linux-vs.org> Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/1381186321-4906-2-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-08 06:51:58 +08:00
int i;
br->stats = alloc_percpu(struct pcpu_sw_netstats);
if (!br->stats)
return -ENOMEM;
net: Explicitly initialize u64_stats_sync structures for lockdep In order to enable lockdep on seqcount/seqlock structures, we must explicitly initialize any locks. The u64_stats_sync structure, uses a seqcount, and thus we need to introduce a u64_stats_init() function and use it to initialize the structure. This unfortunately adds a lot of fairly trivial initialization code to a number of drivers. But the benefit of ensuring correctness makes this worth while. Because these changes are required for lockdep to be enabled, and the changes are quite trivial, I've not yet split this patch out into 30-some separate patches, as I figured it would be better to get the various maintainers thoughts on how to best merge this change along with the seqcount lockdep enablement. Feedback would be appreciated! Signed-off-by: John Stultz <john.stultz@linaro.org> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: "David S. Miller" <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: James Morris <jmorris@namei.org> Cc: Jesse Gross <jesse@nicira.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mirko Lindner <mlindner@marvell.com> Cc: Patrick McHardy <kaber@trash.net> Cc: Roger Luethi <rl@hellgate.ch> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Simon Horman <horms@verge.net.au> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Cc: Wensong Zhang <wensong@linux-vs.org> Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/1381186321-4906-2-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-08 06:51:58 +08:00
for_each_possible_cpu(i) {
struct pcpu_sw_netstats *br_dev_stats;
net: Explicitly initialize u64_stats_sync structures for lockdep In order to enable lockdep on seqcount/seqlock structures, we must explicitly initialize any locks. The u64_stats_sync structure, uses a seqcount, and thus we need to introduce a u64_stats_init() function and use it to initialize the structure. This unfortunately adds a lot of fairly trivial initialization code to a number of drivers. But the benefit of ensuring correctness makes this worth while. Because these changes are required for lockdep to be enabled, and the changes are quite trivial, I've not yet split this patch out into 30-some separate patches, as I figured it would be better to get the various maintainers thoughts on how to best merge this change along with the seqcount lockdep enablement. Feedback would be appreciated! Signed-off-by: John Stultz <john.stultz@linaro.org> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: "David S. Miller" <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: James Morris <jmorris@namei.org> Cc: Jesse Gross <jesse@nicira.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mirko Lindner <mlindner@marvell.com> Cc: Patrick McHardy <kaber@trash.net> Cc: Roger Luethi <rl@hellgate.ch> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Simon Horman <horms@verge.net.au> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Cc: Wensong Zhang <wensong@linux-vs.org> Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/1381186321-4906-2-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-08 06:51:58 +08:00
br_dev_stats = per_cpu_ptr(br->stats, i);
u64_stats_init(&br_dev_stats->syncp);
}
return 0;
}
static int br_dev_open(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
netdev_update_features(dev);
netif_start_queue(dev);
br_stp_enable_bridge(br);
br_multicast_open(br);
return 0;
}
static void br_dev_set_multicast_list(struct net_device *dev)
{
}
static int br_dev_stop(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
br_stp_disable_bridge(br);
br_multicast_stop(br);
netif_stop_queue(dev);
return 0;
}
static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct net_bridge *br = netdev_priv(dev);
struct pcpu_sw_netstats tmp, sum = { 0 };
unsigned int cpu;
for_each_possible_cpu(cpu) {
unsigned int start;
const struct pcpu_sw_netstats *bstats
= per_cpu_ptr(br->stats, cpu);
do {
start = u64_stats_fetch_begin_bh(&bstats->syncp);
memcpy(&tmp, bstats, sizeof(tmp));
} while (u64_stats_fetch_retry_bh(&bstats->syncp, start));
sum.tx_bytes += tmp.tx_bytes;
sum.tx_packets += tmp.tx_packets;
sum.rx_bytes += tmp.rx_bytes;
sum.rx_packets += tmp.rx_packets;
}
stats->tx_bytes = sum.tx_bytes;
stats->tx_packets = sum.tx_packets;
stats->rx_bytes = sum.rx_bytes;
stats->rx_packets = sum.rx_packets;
return stats;
}
static int br_change_mtu(struct net_device *dev, int new_mtu)
{
struct net_bridge *br = netdev_priv(dev);
if (new_mtu < 68 || new_mtu > br_min_mtu(br))
return -EINVAL;
dev->mtu = new_mtu;
#ifdef CONFIG_BRIDGE_NETFILTER
/* remember the MTU in the rtable for PMTU */
dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
#endif
return 0;
}
/* Allow setting mac address to any valid ethernet address. */
static int br_set_mac_address(struct net_device *dev, void *p)
{
struct net_bridge *br = netdev_priv(dev);
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
spin_lock_bh(&br->lock);
if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
/* Mac address will be changed in br_stp_change_bridge_id(). */
br_stp_change_bridge_id(br, addr->sa_data);
}
spin_unlock_bh(&br->lock);
return 0;
}
static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
strlcpy(info->driver, "bridge", sizeof(info->driver));
strlcpy(info->version, BR_VERSION, sizeof(info->version));
strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
strlcpy(info->bus_info, "N/A", sizeof(info->bus_info));
}
static netdev_features_t br_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct net_bridge *br = netdev_priv(dev);
return br_features_recompute(br, features);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void br_poll_controller(struct net_device *br_dev)
{
}
static void br_netpoll_cleanup(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p;
list_for_each_entry(p, &br->port_list, list)
br_netpoll_disable(p);
}
static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
struct netpoll *np;
int err;
np = kzalloc(sizeof(*p->np), gfp);
if (!np)
return -ENOMEM;
err = __netpoll_setup(np, p->dev, gfp);
if (err) {
kfree(np);
return err;
}
p->np = np;
return err;
}
int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
if (!p->br->dev->npinfo)
return 0;
return __br_netpoll_enable(p, gfp);
}
static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
gfp_t gfp)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p;
int err = 0;
list_for_each_entry(p, &br->port_list, list) {
if (!p->dev)
continue;
err = __br_netpoll_enable(p, gfp);
if (err)
goto fail;
}
out:
return err;
fail:
br_netpoll_cleanup(dev);
goto out;
}
void br_netpoll_disable(struct net_bridge_port *p)
{
struct netpoll *np = p->np;
if (!np)
return;
p->np = NULL;
__netpoll_free_async(np);
}
#endif
static int br_add_slave(struct net_device *dev, struct net_device *slave_dev)
{
struct net_bridge *br = netdev_priv(dev);
return br_add_if(br, slave_dev);
}
static int br_del_slave(struct net_device *dev, struct net_device *slave_dev)
{
struct net_bridge *br = netdev_priv(dev);
return br_del_if(br, slave_dev);
}
static const struct ethtool_ops br_ethtool_ops = {
.get_drvinfo = br_getinfo,
.get_link = ethtool_op_get_link,
};
static const struct net_device_ops br_netdev_ops = {
.ndo_open = br_dev_open,
.ndo_stop = br_dev_stop,
.ndo_init = br_dev_init,
.ndo_start_xmit = br_dev_xmit,
.ndo_get_stats64 = br_get_stats64,
.ndo_set_mac_address = br_set_mac_address,
.ndo_set_rx_mode = br_dev_set_multicast_list,
.ndo_change_mtu = br_change_mtu,
.ndo_do_ioctl = br_dev_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_netpoll_setup = br_netpoll_setup,
.ndo_netpoll_cleanup = br_netpoll_cleanup,
.ndo_poll_controller = br_poll_controller,
#endif
.ndo_add_slave = br_add_slave,
.ndo_del_slave = br_del_slave,
.ndo_fix_features = br_fix_features,
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 14:43:56 +08:00
.ndo_fdb_add = br_fdb_add,
.ndo_fdb_del = br_fdb_delete,
.ndo_fdb_dump = br_fdb_dump,
.ndo_bridge_getlink = br_getlink,
.ndo_bridge_setlink = br_setlink,
.ndo_bridge_dellink = br_dellink,
};
static void br_dev_free(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
free_percpu(br->stats);
free_netdev(dev);
}
static struct device_type br_type = {
.name = "bridge",
};
void br_dev_setup(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
eth_hw_addr_random(dev);
ether_setup(dev);
dev->netdev_ops = &br_netdev_ops;
dev->destructor = br_dev_free;
SET_ETHTOOL_OPS(dev, &br_ethtool_ops);
SET_NETDEV_DEVTYPE(dev, &br_type);
dev->tx_queue_len = 0;
dev->priv_flags = IFF_EBRIDGE;
dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
NETIF_F_HW_VLAN_CTAG_TX;
dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX;
dev->vlan_features = COMMON_FEATURES;
br->dev = dev;
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, eth_reserved_addr_base, ETH_ALEN);
br->stp_enabled = BR_NO_STP;
br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
br->designated_root = br->bridge_id;
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->ageing_time = 300 * HZ;
br_netfilter_rtable_init(br);
br_stp_timer_init(br);
br_multicast_init(br);
}