linux-stable/net/bridge/br_input.c

359 lines
9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Handle incoming frames
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*/
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/netfilter_bridge.h>
#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
#include <net/netfilter/nf_queue.h>
#endif
#include <linux/neighbour.h>
#include <net/arp.h>
#include <linux/export.h>
#include <linux/rculist.h>
#include "br_private.h"
#include "br_private_tunnel.h"
static int
br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
{
br_drop_fake_rtable(skb);
return netif_receive_skb(skb);
}
static int br_pass_frame_up(struct sk_buff *skb)
{
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
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>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
u64_stats_update_begin(&brstats->syncp);
brstats->rx_packets++;
brstats->rx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
vg = br_vlan_group_rcu(br);
/* Bridge is just like any other port. Make sure the
* packet is allowed except in promisc modue when someone
* may be running packet capture.
*/
if (!(brdev->flags & IFF_PROMISC) &&
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>
2015-09-25 17:00:11 +00:00
!br_allowed_egress(vg, skb)) {
kfree_skb(skb);
return NET_RX_DROP;
}
indev = skb->dev;
skb->dev = brdev;
skb = br_handle_vlan(br, NULL, vg, skb);
if (!skb)
return NET_RX_DROP;
/* update the multicast stats if the packet is IGMP/MLD */
br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
BR_MCAST_DIR_TX);
2015-09-16 01:04:16 +00:00
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
dev_net(indev), NULL, skb, indev, NULL,
br_netif_receive_skb);
}
/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
enum br_pkt_type pkt_type = BR_PKT_UNICAST;
struct net_bridge_fdb_entry *dst = NULL;
struct net_bridge_mdb_entry *mdst;
bool local_rcv, mcast_hit = false;
struct net_bridge *br;
u16 vid = 0;
u8 state;
if (!p || p->state == BR_STATE_DISABLED)
goto drop;
state = p->state;
if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid,
&state))
goto out;
bridge: switchdev: Add forward mark support for stacked devices switchdev_port_fwd_mark_set() is used to set the 'offload_fwd_mark' of port netdevs so that packets being flooded by the device won't be flooded twice. It works by assigning a unique identifier (the ifindex of the first bridge port) to bridge ports sharing the same parent ID. This prevents packets from being flooded twice by the same switch, but will flood packets through bridge ports belonging to a different switch. This method is problematic when stacked devices are taken into account, such as VLANs. In such cases, a physical port netdev can have upper devices being members in two different bridges, thus requiring two different 'offload_fwd_mark's to be configured on the port netdev, which is impossible. The main problem is that packet and netdev marking is performed at the physical netdev level, whereas flooding occurs between bridge ports, which are not necessarily port netdevs. Instead, packet and netdev marking should really be done in the bridge driver with the switch driver only telling it which packets it already forwarded. The bridge driver will mark such packets using the mark assigned to the ingress bridge port and will prevent the packet from being forwarded through any bridge port sharing the same mark (i.e. having the same parent ID). Remove the current switchdev 'offload_fwd_mark' implementation and instead implement the proposed method. In addition, make rocker - the sole user of the mark - use the proposed method. Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-25 16:42:37 +00:00
nbp_switchdev_frame_mark(p, skb);
/* insert into forwarding database after filtering to avoid spoofing */
br = p->br;
if (p->flags & BR_LEARNING)
br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0);
local_rcv = !!(br->dev->flags & IFF_PROMISC);
if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
/* by definition the broadcast is also a multicast address */
if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
pkt_type = BR_PKT_BROADCAST;
local_rcv = true;
} else {
pkt_type = BR_PKT_MULTICAST;
if (br_multicast_rcv(br, p, skb, vid))
goto drop;
}
}
if (state == BR_STATE_LEARNING)
goto drop;
BR_INPUT_SKB_CB(skb)->brdev = br->dev;
BR_INPUT_SKB_CB(skb)->src_port_isolated = !!(p->flags & BR_ISOLATED);
if (IS_ENABLED(CONFIG_INET) &&
(skb->protocol == htons(ETH_P_ARP) ||
skb->protocol == htons(ETH_P_RARP))) {
br_do_proxy_suppress_arp(skb, br, vid, p);
} else if (IS_ENABLED(CONFIG_IPV6) &&
skb->protocol == htons(ETH_P_IPV6) &&
br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
pskb_may_pull(skb, sizeof(struct ipv6hdr) +
sizeof(struct nd_msg)) &&
ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
struct nd_msg *msg, _msg;
msg = br_is_nd_neigh_msg(skb, &_msg);
if (msg)
br_do_suppress_nd(skb, br, vid, p, msg);
}
switch (pkt_type) {
case BR_PKT_MULTICAST:
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
br_multicast_querier_exists(br, eth_hdr(skb))) {
if ((mdst && mdst->host_joined) ||
br_multicast_is_router(br)) {
local_rcv = true;
br->dev->stats.multicast++;
}
mcast_hit = true;
} else {
local_rcv = true;
br->dev->stats.multicast++;
}
break;
case BR_PKT_UNICAST:
dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
default:
break;
}
if (dst) {
unsigned long now = jiffies;
if (test_bit(BR_FDB_LOCAL, &dst->flags))
return br_pass_frame_up(skb);
if (now != dst->used)
dst->used = now;
br_forward(dst->dst, skb, local_rcv, false);
} else {
if (!mcast_hit)
br_flood(br, skb, pkt_type, local_rcv, false);
else
br_multicast_flood(mdst, skb, local_rcv, false);
}
if (local_rcv)
return br_pass_frame_up(skb);
out:
return 0;
drop:
kfree_skb(skb);
goto out;
}
EXPORT_SYMBOL_GPL(br_handle_frame_finish);
static void __br_handle_local_finish(struct sk_buff *skb)
{
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
u16 vid = 0;
/* check if vlan is allowed, to avoid spoofing */
if ((p->flags & BR_LEARNING) &&
nbp_state_should_learn(p) &&
!br_opt_get(p->br, BROPT_NO_LL_LEARN) &&
br_should_learn(p, skb, &vid))
br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, 0);
}
/* note: already called with rcu_read_lock */
static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
__br_handle_local_finish(skb);
/* return 1 to signal the okfn() was called so it's ok to use the skb */
return 1;
}
static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
{
#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
struct nf_hook_entries *e = NULL;
struct nf_hook_state state;
unsigned int verdict, i;
struct net *net;
int ret;
net = dev_net(skb->dev);
#ifdef HAVE_JUMP_LABEL
if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING]))
goto frame_finish;
#endif
e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]);
if (!e)
goto frame_finish;
nf_hook_state_init(&state, NF_BR_PRE_ROUTING,
NFPROTO_BRIDGE, skb->dev, NULL, NULL,
net, br_handle_frame_finish);
for (i = 0; i < e->num_hook_entries; i++) {
verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state);
switch (verdict & NF_VERDICT_MASK) {
case NF_ACCEPT:
if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) {
*pskb = skb;
return RX_HANDLER_PASS;
}
break;
case NF_DROP:
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
case NF_QUEUE:
ret = nf_queue(skb, &state, i, verdict);
if (ret == 1)
continue;
return RX_HANDLER_CONSUMED;
default: /* STOLEN */
return RX_HANDLER_CONSUMED;
}
}
frame_finish:
net = dev_net(skb->dev);
br_handle_frame_finish(net, NULL, skb);
#else
br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
#endif
return RX_HANDLER_CONSUMED;
}
/*
* Return NULL if skb is handled
* note: already called with rcu_read_lock
*/
rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
{
struct net_bridge_port *p;
struct sk_buff *skb = *pskb;
const unsigned char *dest = eth_hdr(skb)->h_dest;
if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
return RX_HANDLER_PASS;
if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
goto drop;
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb)
return RX_HANDLER_CONSUMED;
memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
p = br_port_get_rcu(skb->dev);
if (p->flags & BR_VLAN_TUNNEL) {
if (br_handle_ingress_vlan_tunnel(skb, p,
nbp_vlan_group_rcu(p)))
goto drop;
}
if (unlikely(is_link_local_ether_addr(dest))) {
u16 fwd_mask = p->br->group_fwd_mask_required;
/*
* See IEEE 802.1D Table 7-10 Reserved addresses
*
* Assignment Value
* Bridge Group Address 01-80-C2-00-00-00
* (MAC Control) 802.3 01-80-C2-00-00-01
* (Link Aggregation) 802.3 01-80-C2-00-00-02
* 802.1X PAE address 01-80-C2-00-00-03
*
* 802.1AB LLDP 01-80-C2-00-00-0E
*
* Others reserved for future standardization
*/
fwd_mask |= p->group_fwd_mask;
switch (dest[5]) {
case 0x00: /* Bridge Group Address */
/* If STP is turned off,
then must forward to keep loop detection */
if (p->br->stp_enabled == BR_NO_STP ||
fwd_mask & (1u << dest[5]))
goto forward;
*pskb = skb;
__br_handle_local_finish(skb);
return RX_HANDLER_PASS;
case 0x01: /* IEEE MAC (Pause) */
goto drop;
case 0x0E: /* 802.1AB LLDP */
fwd_mask |= p->br->group_fwd_mask;
if (fwd_mask & (1u << dest[5]))
goto forward;
*pskb = skb;
__br_handle_local_finish(skb);
return RX_HANDLER_PASS;
default:
/* Allow selective forwarding for most other protocols */
fwd_mask |= p->br->group_fwd_mask;
if (fwd_mask & (1u << dest[5]))
goto forward;
}
/* The else clause should be hit when nf_hook():
* - returns < 0 (drop/error)
* - returns = 0 (stolen/nf_queue)
* Thus return 1 from the okfn() to signal the skb is ok to pass
*/
if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
dev_net(skb->dev), NULL, skb, skb->dev, NULL,
br_handle_local_finish) == 1) {
return RX_HANDLER_PASS;
} else {
return RX_HANDLER_CONSUMED;
}
}
forward:
switch (p->state) {
case BR_STATE_FORWARDING:
case BR_STATE_LEARNING:
if (ether_addr_equal(p->br->dev->dev_addr, dest))
skb->pkt_type = PACKET_HOST;
return nf_hook_bridge_pre(skb, pskb);
default:
drop:
kfree_skb(skb);
}
return RX_HANDLER_CONSUMED;
}