linux/net/bridge/br_forward.c

286 lines
6.5 KiB
C
Raw Normal View History

/*
* Forwarding decision
* 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/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 08:04:11 +00:00
#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"
static int deliver_clone(const struct net_bridge_port *prev,
struct sk_buff *skb,
void (*__packet_hook)(const struct net_bridge_port *p,
struct sk_buff *skb));
/* Don't forward packets to originating port or forwarding diasabled */
static inline int should_deliver(const struct net_bridge_port *p,
const struct sk_buff *skb)
{
return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
p->state == BR_STATE_FORWARDING);
}
static inline unsigned packet_length(const struct sk_buff *skb)
{
return skb->len - (skb->protocol == htons(ETH_P_8021Q) ? VLAN_HLEN : 0);
}
int br_dev_queue_push_xmit(struct sk_buff *skb)
{
/* drop mtu oversized packets except gso */
if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))
kfree_skb(skb);
else {
/* ip_fragment doesn't copy the MAC header */
if (nf_bridge_maybe_copy_header(skb))
kfree_skb(skb);
else {
skb_push(skb, ETH_HLEN);
#ifdef CONFIG_NET_POLL_CONTROLLER
if (unlikely(skb->dev->priv_flags & IFF_IN_NETPOLL)) {
netpoll_send_skb(skb->dev->npinfo->netpoll, skb);
skb->dev->priv_flags &= ~IFF_IN_NETPOLL;
} else
#endif
dev_queue_xmit(skb);
}
}
return 0;
}
int br_forward_finish(struct sk_buff *skb)
{
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev,
br_dev_queue_push_xmit);
}
static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
{
#ifdef CONFIG_NET_POLL_CONTROLLER
struct net_bridge *br = to->br;
if (unlikely(br->dev->priv_flags & IFF_IN_NETPOLL)) {
struct netpoll *np;
to->dev->npinfo = skb->dev->npinfo;
np = skb->dev->npinfo->netpoll;
np->real_dev = np->dev = to->dev;
to->dev->priv_flags |= IFF_IN_NETPOLL;
}
#endif
skb->dev = to->dev;
NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
br_forward_finish);
#ifdef CONFIG_NET_POLL_CONTROLLER
if (skb->dev->npinfo)
skb->dev->npinfo->netpoll->dev = br->dev;
#endif
}
static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
{
struct net_device *indev;
bridge: Fix LRO crash with tun > Kernel BUG at drivers/net/tun.c:444 > invalid opcode: 0000 [1] SMP > last sysfs file: /class/net/lo/ifindex > CPU 0 > Modules linked in: tun ipt_MASQUERADE iptable_nat ip_nat xt_state ip_conntrack > nfnetlink ipt_REJECT xt_tcpudp iptable_filter d > Pid: 6912, comm: qemu-kvm Tainted: G 2.6.18-128.el5 #1 > RIP: 0010:[<ffffffff886f57b0>] [<ffffffff886f57b0>] > :tun:tun_chr_readv+0x2b1/0x3a6 > RSP: 0018:ffff8102202c5e48 EFLAGS: 00010246 > RAX: 0000000000000000 RBX: ffff8102202c5e98 RCX: 0000000004010000 > RDX: ffff810227063680 RSI: ffff8102202c5e9e RDI: ffff8102202c5e92 > RBP: 0000000000010ff6 R08: 0000000000000000 R09: 0000000000000001 > R10: ffff8102202c5e94 R11: 0000000000000202 R12: ffff8102275357c0 > R13: ffff81022755e500 R14: 0000000000000000 R15: ffff8102202c5ef8 > FS: 00002ae4398db980(0000) GS:ffffffff803ac000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 00002ae4ab514000 CR3: 0000000221344000 CR4: 00000000000026e0 > Process qemu-kvm (pid: 6912, threadinfo ffff8102202c4000, task > ffff81022e58d820) > Stack: 00000000498735cb ffff810229d1a3c0 0000000000000000 ffff81022e58d820 > ffffffff8008a461 ffff81022755e528 ffff81022755e528 ffffffff8009f925 > 000005ea05ea0000 ffff8102209d0000 00001051143e1600 ffffffff8003c00e > Call Trace: > [<ffffffff8008a461>] default_wake_function+0x0/0xe > [<ffffffff8009f925>] enqueue_hrtimer+0x55/0x70 > [<ffffffff8003c00e>] hrtimer_start+0xbc/0xce > [<ffffffff886f58bf>] :tun:tun_chr_read+0x1a/0x1f > [<ffffffff8000b3f3>] vfs_read+0xcb/0x171 > [<ffffffff800117d4>] sys_read+0x45/0x6e > [<ffffffff8005d116>] system_call+0x7e/0x83 > > > Code: 0f 0b 68 40 62 6f 88 c2 bc 01 f6 42 0a 08 74 0c 80 4c 24 41 > RIP [<ffffffff886f57b0>] :tun:tun_chr_readv+0x2b1/0x3a6 > RSP <ffff8102202c5e48> > <0>Kernel panic - not syncing: Fatal exception This crashed when an LRO packet generated by bnx2x reached a tun device through the bridge. We're supposed to drop it at the bridge. However, because the check was placed in br_forward instead of __br_forward, it's only effective if we are sending the packet through a single port. This patch fixes it by moving the check into __br_forward. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-09 23:07:18 +00:00
if (skb_warn_if_lro(skb)) {
kfree_skb(skb);
return;
}
indev = skb->dev;
skb->dev = to->dev;
skb_forward_csum(skb);
NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
br_forward_finish);
}
/* called with rcu_read_lock */
void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
{
if (should_deliver(to, skb)) {
__br_deliver(to, skb);
return;
}
kfree_skb(skb);
}
/* called with rcu_read_lock */
void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0)
{
bridge: Fix LRO crash with tun > Kernel BUG at drivers/net/tun.c:444 > invalid opcode: 0000 [1] SMP > last sysfs file: /class/net/lo/ifindex > CPU 0 > Modules linked in: tun ipt_MASQUERADE iptable_nat ip_nat xt_state ip_conntrack > nfnetlink ipt_REJECT xt_tcpudp iptable_filter d > Pid: 6912, comm: qemu-kvm Tainted: G 2.6.18-128.el5 #1 > RIP: 0010:[<ffffffff886f57b0>] [<ffffffff886f57b0>] > :tun:tun_chr_readv+0x2b1/0x3a6 > RSP: 0018:ffff8102202c5e48 EFLAGS: 00010246 > RAX: 0000000000000000 RBX: ffff8102202c5e98 RCX: 0000000004010000 > RDX: ffff810227063680 RSI: ffff8102202c5e9e RDI: ffff8102202c5e92 > RBP: 0000000000010ff6 R08: 0000000000000000 R09: 0000000000000001 > R10: ffff8102202c5e94 R11: 0000000000000202 R12: ffff8102275357c0 > R13: ffff81022755e500 R14: 0000000000000000 R15: ffff8102202c5ef8 > FS: 00002ae4398db980(0000) GS:ffffffff803ac000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 00002ae4ab514000 CR3: 0000000221344000 CR4: 00000000000026e0 > Process qemu-kvm (pid: 6912, threadinfo ffff8102202c4000, task > ffff81022e58d820) > Stack: 00000000498735cb ffff810229d1a3c0 0000000000000000 ffff81022e58d820 > ffffffff8008a461 ffff81022755e528 ffff81022755e528 ffffffff8009f925 > 000005ea05ea0000 ffff8102209d0000 00001051143e1600 ffffffff8003c00e > Call Trace: > [<ffffffff8008a461>] default_wake_function+0x0/0xe > [<ffffffff8009f925>] enqueue_hrtimer+0x55/0x70 > [<ffffffff8003c00e>] hrtimer_start+0xbc/0xce > [<ffffffff886f58bf>] :tun:tun_chr_read+0x1a/0x1f > [<ffffffff8000b3f3>] vfs_read+0xcb/0x171 > [<ffffffff800117d4>] sys_read+0x45/0x6e > [<ffffffff8005d116>] system_call+0x7e/0x83 > > > Code: 0f 0b 68 40 62 6f 88 c2 bc 01 f6 42 0a 08 74 0c 80 4c 24 41 > RIP [<ffffffff886f57b0>] :tun:tun_chr_readv+0x2b1/0x3a6 > RSP <ffff8102202c5e48> > <0>Kernel panic - not syncing: Fatal exception This crashed when an LRO packet generated by bnx2x reached a tun device through the bridge. We're supposed to drop it at the bridge. However, because the check was placed in br_forward instead of __br_forward, it's only effective if we are sending the packet through a single port. This patch fixes it by moving the check into __br_forward. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-09 23:07:18 +00:00
if (should_deliver(to, skb)) {
if (skb0)
deliver_clone(to, skb, __br_forward);
else
__br_forward(to, skb);
return;
}
if (!skb0)
kfree_skb(skb);
}
static int deliver_clone(const struct net_bridge_port *prev,
struct sk_buff *skb,
void (*__packet_hook)(const struct net_bridge_port *p,
struct sk_buff *skb))
{
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb) {
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
dev->stats.tx_dropped++;
return -ENOMEM;
}
__packet_hook(prev, skb);
return 0;
}
static struct net_bridge_port *maybe_deliver(
struct net_bridge_port *prev, struct net_bridge_port *p,
struct sk_buff *skb,
void (*__packet_hook)(const struct net_bridge_port *p,
struct sk_buff *skb))
{
int err;
if (!should_deliver(p, skb))
return prev;
if (!prev)
goto out;
err = deliver_clone(prev, skb, __packet_hook);
if (err)
return ERR_PTR(err);
out:
return p;
}
/* called under bridge lock */
static void br_flood(struct net_bridge *br, struct sk_buff *skb,
struct sk_buff *skb0,
void (*__packet_hook)(const struct net_bridge_port *p,
struct sk_buff *skb))
{
struct net_bridge_port *p;
struct net_bridge_port *prev;
prev = NULL;
list_for_each_entry_rcu(p, &br->port_list, list) {
prev = maybe_deliver(prev, p, skb, __packet_hook);
if (IS_ERR(prev))
goto out;
}
if (!prev)
goto out;
if (skb0)
deliver_clone(prev, skb, __packet_hook);
else
__packet_hook(prev, skb);
return;
out:
if (!skb0)
kfree_skb(skb);
}
/* called with rcu_read_lock */
void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb)
{
br_flood(br, skb, NULL, __br_deliver);
}
/* called under bridge lock */
void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
struct sk_buff *skb2)
{
br_flood(br, skb, skb2, __br_forward);
}
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
/* called with rcu_read_lock */
static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb, struct sk_buff *skb0,
void (*__packet_hook)(
const struct net_bridge_port *p,
struct sk_buff *skb))
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
struct hlist_node *rp;
rp = rcu_dereference(br->router_list.first);
p = mdst ? rcu_dereference(mdst->ports) : NULL;
while (p || rp) {
struct net_bridge_port *port, *lport, *rport;
lport = p ? p->port : NULL;
rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) :
NULL;
port = (unsigned long)lport > (unsigned long)rport ?
lport : rport;
prev = maybe_deliver(prev, port, skb, __packet_hook);
if (IS_ERR(prev))
goto out;
if ((unsigned long)lport >= (unsigned long)port)
p = rcu_dereference(p->next);
if ((unsigned long)rport >= (unsigned long)port)
rp = rcu_dereference(rp->next);
}
if (!prev)
goto out;
if (skb0)
deliver_clone(prev, skb, __packet_hook);
else
__packet_hook(prev, skb);
return;
out:
if (!skb0)
kfree_skb(skb);
}
/* called with rcu_read_lock */
void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb)
{
br_multicast_flood(mdst, skb, NULL, __br_deliver);
}
/* called with rcu_read_lock */
void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb, struct sk_buff *skb2)
{
br_multicast_flood(mdst, skb, skb2, __br_forward);
}
#endif