linux_dsm_epyc7002/net/bridge/br_input.c

316 lines
7.6 KiB
C
Raw Normal View History

/*
* Handle incoming frames
* 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 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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/netfilter_bridge.h>
#include <linux/neighbour.h>
#include <net/arp.h>
#include <linux/export.h>
#include <linux/rculist.h>
#include "br_private.h"
/* Hook for brouter */
br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
EXPORT_SYMBOL(br_should_route_hook);
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);
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
struct net_port_vlans *pv;
u64_stats_update_begin(&brstats->syncp);
brstats->rx_packets++;
brstats->rx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
/* Bridge is just like any other port. Make sure the
* packet is allowed except in promisc modue when someone
* may be running packet capture.
*/
pv = br_get_vlan_info(br);
if (!(brdev->flags & IFF_PROMISC) &&
!br_allowed_egress(br, pv, skb)) {
kfree_skb(skb);
return NET_RX_DROP;
}
indev = skb->dev;
skb->dev = brdev;
skb = br_handle_vlan(br, pv, skb);
if (!skb)
return NET_RX_DROP;
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb,
indev, NULL,
netif_receive_skb_sk);
}
static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
u16 vid, struct net_bridge_port *p)
{
struct net_device *dev = br->dev;
struct neighbour *n;
struct arphdr *parp;
u8 *arpptr, *sha;
__be32 sip, tip;
BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
if (dev->flags & IFF_NOARP)
return;
if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
dev->stats.tx_dropped++;
return;
}
parp = arp_hdr(skb);
if (parp->ar_pro != htons(ETH_P_IP) ||
parp->ar_op != htons(ARPOP_REQUEST) ||
parp->ar_hln != dev->addr_len ||
parp->ar_pln != 4)
return;
arpptr = (u8 *)parp + sizeof(struct arphdr);
sha = arpptr;
arpptr += dev->addr_len; /* sha */
memcpy(&sip, arpptr, sizeof(sip));
arpptr += sizeof(sip);
arpptr += dev->addr_len; /* tha */
memcpy(&tip, arpptr, sizeof(tip));
if (ipv4_is_loopback(tip) ||
ipv4_is_multicast(tip))
return;
n = neigh_lookup(&arp_tbl, &tip, dev);
if (n) {
struct net_bridge_fdb_entry *f;
if (!(n->nud_state & NUD_VALID)) {
neigh_release(n);
return;
}
f = __br_fdb_get(br, n->ha, vid);
if (f && ((p->flags & BR_PROXYARP) ||
(f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) {
arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
sha, n->ha, sha);
BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
}
neigh_release(n);
}
}
/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb)
{
const unsigned char *dest = eth_hdr(skb)->h_dest;
struct net_bridge_port *p = br_port_get_rcu(skb->dev);
struct net_bridge *br;
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
struct sk_buff *skb2;
bool unicast = true;
u16 vid = 0;
if (!p || p->state == BR_STATE_DISABLED)
goto drop;
if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
goto out;
/* 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, false);
if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
br_multicast_rcv(br, p, skb, vid))
goto drop;
if (p->state == BR_STATE_LEARNING)
goto drop;
BR_INPUT_SKB_CB(skb)->brdev = br->dev;
/* The packet skb2 goes to the local host (NULL to skip). */
skb2 = NULL;
if (br->dev->flags & IFF_PROMISC)
skb2 = skb;
dst = NULL;
if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
br_do_proxy_arp(skb, br, vid, p);
if (is_broadcast_ether_addr(dest)) {
skb2 = skb;
unicast = false;
} else if (is_multicast_ether_addr(dest)) {
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->mglist) ||
br_multicast_is_router(br))
skb2 = skb;
br_multicast_forward(mdst, skb, skb2);
skb = NULL;
if (!skb2)
goto out;
} else
skb2 = skb;
unicast = false;
br->dev->stats.multicast++;
} else if ((dst = __br_fdb_get(br, dest, vid)) &&
dst->is_local) {
skb2 = skb;
/* Do not forward the packet since it's local. */
skb = NULL;
}
if (skb) {
if (dst) {
dst->used = jiffies;
br_forward(dst->dst, skb, skb2);
} else
br_flood_forward(br, skb, skb2, unicast);
}
if (skb2)
return br_pass_frame_up(skb2);
out:
return 0;
drop:
kfree_skb(skb);
goto out;
}
EXPORT_SYMBOL_GPL(br_handle_frame_finish);
/* note: already called with rcu_read_lock */
static int br_handle_local_finish(struct sock *sk, 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 && br_should_learn(p, skb, &vid))
br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
return 0; /* process further */
}
/*
* 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;
br_should_route_hook_t *rhook;
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;
p = br_port_get_rcu(skb->dev);
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
*/
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;
break;
case 0x01: /* IEEE MAC (Pause) */
goto drop;
default:
/* Allow selective forwarding for most other protocols */
fwd_mask |= p->br->group_fwd_mask;
if (fwd_mask & (1u << dest[5]))
goto forward;
}
/* Deliver packet to local host only */
if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb,
skb->dev, NULL, br_handle_local_finish)) {
return RX_HANDLER_CONSUMED; /* consumed by filter */
} else {
*pskb = skb;
return RX_HANDLER_PASS; /* continue processing */
}
}
forward:
switch (p->state) {
case BR_STATE_FORWARDING:
rhook = rcu_dereference(br_should_route_hook);
if (rhook) {
if ((*rhook)(skb)) {
*pskb = skb;
return RX_HANDLER_PASS;
}
dest = eth_hdr(skb)->h_dest;
}
/* fall through */
case BR_STATE_LEARNING:
if (ether_addr_equal(p->br->dev->dev_addr, dest))
skb->pkt_type = PACKET_HOST;
NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, NULL, skb,
skb->dev, NULL,
br_handle_frame_finish);
break;
default:
drop:
kfree_skb(skb);
}
return RX_HANDLER_CONSUMED;
}