linux/net/bridge/br_forward.c

335 lines
7.5 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Forwarding decision
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*/
#include <linux/err.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/kernel.h>
#include <linux/netdevice.h>
#include <linux/netpoll.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/netfilter_bridge.h>
#include "br_private.h"
/* Don't forward packets to originating port or forwarding disabled */
static inline int should_deliver(const struct net_bridge_port *p,
const struct sk_buff *skb)
{
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan_group *vg;
vg = nbp_vlan_group_rcu(p);
return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) &&
nbp_switchdev_allowed_egress(p, skb) &&
!br_skb_isolated(p, skb);
}
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb_push(skb, ETH_HLEN);
if (!is_skb_forwardable(skb->dev, skb))
goto drop;
br_drop_fake_rtable(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL &&
eth_type_vlan(skb->protocol)) {
int depth;
if (!__vlan_get_protocol(skb, skb->protocol, &depth))
goto drop;
skb_set_network_header(skb, depth);
}
dev_queue_xmit(skb);
return 0;
drop:
kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb->tstamp = 0;
2015-09-16 09:04:16 +08:00
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING,
net, sk, skb, NULL, skb->dev,
br_dev_queue_push_xmit);
}
EXPORT_SYMBOL_GPL(br_forward_finish);
static void __br_forward(const struct net_bridge_port *to,
struct sk_buff *skb, bool local_orig)
{
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan_group *vg;
struct net_device *indev;
struct net *net;
int br_hook;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-26 01:00:11 +08:00
vg = nbp_vlan_group_rcu(to);
skb = br_handle_vlan(to->br, to, vg, skb);
if (!skb)
return;
indev = skb->dev;
skb->dev = to->dev;
if (!local_orig) {
if (skb_warn_if_lro(skb)) {
kfree_skb(skb);
return;
}
br_hook = NF_BR_FORWARD;
skb_forward_csum(skb);
net = dev_net(indev);
} else {
if (unlikely(netpoll_tx_running(to->br->dev))) {
skb_push(skb, ETH_HLEN);
if (!is_skb_forwardable(skb->dev, skb))
kfree_skb(skb);
else
br_netpoll_send_skb(to, skb);
return;
}
br_hook = NF_BR_LOCAL_OUT;
net = dev_net(skb->dev);
indev = NULL;
}
NF_HOOK(NFPROTO_BRIDGE, br_hook,
net, NULL, skb, indev, skb->dev,
br_forward_finish);
}
static int deliver_clone(const struct net_bridge_port *prev,
struct sk_buff *skb, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb) {
dev->stats.tx_dropped++;
return -ENOMEM;
}
__br_forward(prev, skb, local_orig);
return 0;
}
/**
* br_forward - forward a packet to a specific port
* @to: destination port
* @skb: packet being forwarded
* @local_rcv: packet will be received locally after forwarding
* @local_orig: packet is locally originated
*
* Should be called with rcu_read_lock.
*/
void br_forward(const struct net_bridge_port *to,
struct sk_buff *skb, bool local_rcv, bool local_orig)
{
net: bridge: add support for backup port This patch adds a new port attribute - IFLA_BRPORT_BACKUP_PORT, which allows to set a backup port to be used for known unicast traffic if the port has gone carrier down. The backup pointer is rcu protected and set only under RTNL, a counter is maintained so when deleting a port we know how many other ports reference it as a backup and we remove it from all. Also the pointer is in the first cache line which is hot at the time of the check and thus in the common case we only add one more test. The backup port will be used only for the non-flooding case since it's a part of the bridge and the flooded packets will be forwarded to it anyway. To remove the forwarding just send a 0/non-existing backup port. This is used to avoid numerous scalability problems when using MLAG most notably if we have thousands of fdbs one would need to change all of them on port carrier going down which takes too long and causes a storm of fdb notifications (and again when the port comes back up). In a Multi-chassis Link Aggregation setup usually hosts are connected to two different switches which act as a single logical switch. Those switches usually have a control and backup link between them called peerlink which might be used for communication in case a host loses connectivity to one of them. We need a fast way to failover in case a host port goes down and currently none of the solutions (like bond) cannot fulfill the requirements because the participating ports are actually the "master" devices and must have the same peerlink as their backup interface and at the same time all of them must participate in the bridge device. As Roopa noted it's normal practice in routing called fast re-route where a precalculated backup path is used when the main one is down. Another use case of this is with EVPN, having a single vxlan device which is backup of every port. Due to the nature of master devices it's not currently possible to use one device as a backup for many and still have all of them participate in the bridge (which is master itself). More detailed information about MLAG is available at the link below. https://docs.cumulusnetworks.com/display/DOCS/Multi-Chassis+Link+Aggregation+-+MLAG Further explanation and a diagram by Roopa: Two switches acting in a MLAG pair are connected by the peerlink interface which is a bridge port. the config on one of the switches looks like the below. The other switch also has a similar config. eth0 is connected to one port on the server. And the server is connected to both switches. br0 -- team0---eth0 | -- switch-peerlink Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-23 16:16:59 +08:00
if (unlikely(!to))
goto out;
/* redirect to backup link if the destination port is down */
if (rcu_access_pointer(to->backup_port) && !netif_carrier_ok(to->dev)) {
struct net_bridge_port *backup_port;
backup_port = rcu_dereference(to->backup_port);
if (unlikely(!backup_port))
goto out;
to = backup_port;
}
if (should_deliver(to, skb)) {
if (local_rcv)
deliver_clone(to, skb, local_orig);
else
__br_forward(to, skb, local_orig);
return;
}
net: bridge: add support for backup port This patch adds a new port attribute - IFLA_BRPORT_BACKUP_PORT, which allows to set a backup port to be used for known unicast traffic if the port has gone carrier down. The backup pointer is rcu protected and set only under RTNL, a counter is maintained so when deleting a port we know how many other ports reference it as a backup and we remove it from all. Also the pointer is in the first cache line which is hot at the time of the check and thus in the common case we only add one more test. The backup port will be used only for the non-flooding case since it's a part of the bridge and the flooded packets will be forwarded to it anyway. To remove the forwarding just send a 0/non-existing backup port. This is used to avoid numerous scalability problems when using MLAG most notably if we have thousands of fdbs one would need to change all of them on port carrier going down which takes too long and causes a storm of fdb notifications (and again when the port comes back up). In a Multi-chassis Link Aggregation setup usually hosts are connected to two different switches which act as a single logical switch. Those switches usually have a control and backup link between them called peerlink which might be used for communication in case a host loses connectivity to one of them. We need a fast way to failover in case a host port goes down and currently none of the solutions (like bond) cannot fulfill the requirements because the participating ports are actually the "master" devices and must have the same peerlink as their backup interface and at the same time all of them must participate in the bridge device. As Roopa noted it's normal practice in routing called fast re-route where a precalculated backup path is used when the main one is down. Another use case of this is with EVPN, having a single vxlan device which is backup of every port. Due to the nature of master devices it's not currently possible to use one device as a backup for many and still have all of them participate in the bridge (which is master itself). More detailed information about MLAG is available at the link below. https://docs.cumulusnetworks.com/display/DOCS/Multi-Chassis+Link+Aggregation+-+MLAG Further explanation and a diagram by Roopa: Two switches acting in a MLAG pair are connected by the peerlink interface which is a bridge port. the config on one of the switches looks like the below. The other switch also has a similar config. eth0 is connected to one port on the server. And the server is connected to both switches. br0 -- team0---eth0 | -- switch-peerlink Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-23 16:16:59 +08:00
out:
if (!local_rcv)
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(br_forward);
static struct net_bridge_port *maybe_deliver(
struct net_bridge_port *prev, struct net_bridge_port *p,
struct sk_buff *skb, bool local_orig)
{
u8 igmp_type = br_multicast_igmp_type(skb);
int err;
if (!should_deliver(p, skb))
return prev;
if (!prev)
goto out;
err = deliver_clone(prev, skb, local_orig);
if (err)
return ERR_PTR(err);
out:
br_multicast_count(p->br, p, skb, igmp_type, BR_MCAST_DIR_TX);
return p;
}
/* called under rcu_read_lock */
void br_flood(struct net_bridge *br, struct sk_buff *skb,
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig)
{
struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
list_for_each_entry_rcu(p, &br->port_list, list) {
/* Do not flood unicast traffic to ports that turn it off, nor
* other traffic if flood off, except for traffic we originate
*/
switch (pkt_type) {
case BR_PKT_UNICAST:
if (!(p->flags & BR_FLOOD))
continue;
break;
case BR_PKT_MULTICAST:
if (!(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
continue;
break;
case BR_PKT_BROADCAST:
if (!(p->flags & BR_BCAST_FLOOD) && skb->dev != br->dev)
continue;
break;
}
/* Do not flood to ports that enable proxy ARP */
if (p->flags & BR_PROXYARP)
continue;
if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) &&
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
continue;
prev = maybe_deliver(prev, p, skb, local_orig);
if (IS_ERR(prev))
goto out;
}
if (!prev)
goto out;
if (local_rcv)
deliver_clone(prev, skb, local_orig);
else
__br_forward(prev, skb, local_orig);
return;
out:
if (!local_rcv)
kfree_skb(skb);
}
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb,
const unsigned char *addr, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
const unsigned char *src = eth_hdr(skb)->h_source;
if (!should_deliver(p, skb))
return;
/* Even with hairpin, no soliloquies - prevent breaking IPv6 DAD */
if (skb->dev == p->dev && ether_addr_equal(src, addr))
return;
skb = skb_copy(skb, GFP_ATOMIC);
if (!skb) {
dev->stats.tx_dropped++;
return;
}
if (!is_broadcast_ether_addr(addr))
memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN);
__br_forward(p, skb, local_orig);
}
/* called with rcu_read_lock */
void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb,
struct net_bridge_mcast *brmctx,
bool local_rcv, bool local_orig)
{
struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
bool allow_mode_include = true;
struct hlist_node *rp;
rp = br_multicast_get_first_rport_node(brmctx, skb);
if (mdst) {
p = rcu_dereference(mdst->ports);
if (br_multicast_should_handle_mode(brmctx, mdst->addr.proto) &&
br_multicast_is_star_g(&mdst->addr))
allow_mode_include = false;
} else {
p = NULL;
}
while (p || rp) {
struct net_bridge_port *port, *lport, *rport;
lport = p ? p->key.port : NULL;
rport = br_multicast_rport_from_node_skb(rp, skb);
if ((unsigned long)lport > (unsigned long)rport) {
port = lport;
if (port->flags & BR_MULTICAST_TO_UNICAST) {
maybe_deliver_addr(lport, skb, p->eth_addr,
local_orig);
goto delivered;
}
if ((!allow_mode_include &&
p->filter_mode == MCAST_INCLUDE) ||
(p->flags & MDB_PG_FLAGS_BLOCKED))
goto delivered;
} else {
port = rport;
}
prev = maybe_deliver(prev, port, skb, local_orig);
if (IS_ERR(prev))
goto out;
delivered:
if ((unsigned long)lport >= (unsigned long)port)
p = rcu_dereference(p->next);
if ((unsigned long)rport >= (unsigned long)port)
rp = rcu_dereference(hlist_next_rcu(rp));
}
if (!prev)
goto out;
if (local_rcv)
deliver_clone(prev, skb, local_orig);
else
__br_forward(prev, skb, local_orig);
return;
out:
if (!local_rcv)
kfree_skb(skb);
}
#endif