linux-stable/net/ipv4/arp.c

1452 lines
36 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* linux/net/ipv4/arp.c
*
* Copyright (C) 1994 by Florian La Roche
*
* This module implements the Address Resolution Protocol ARP (RFC 826),
* which is used to convert IP addresses (or in the future maybe other
* high-level addresses) into a low-level hardware address (like an Ethernet
* address).
*
* Fixes:
* Alan Cox : Removed the Ethernet assumptions in
* Florian's code
* Alan Cox : Fixed some small errors in the ARP
* logic
* Alan Cox : Allow >4K in /proc
* Alan Cox : Make ARP add its own protocol entry
* Ross Martin : Rewrote arp_rcv() and arp_get_info()
* Stephen Henson : Add AX25 support to arp_get_info()
* Alan Cox : Drop data when a device is downed.
* Alan Cox : Use init_timer().
* Alan Cox : Double lock fixes.
* Martin Seine : Move the arphdr structure
* to if_arp.h for compatibility.
* with BSD based programs.
* Andrew Tridgell : Added ARP netmask code and
* re-arranged proxy handling.
* Alan Cox : Changed to use notifiers.
* Niibe Yutaka : Reply for this device or proxies only.
* Alan Cox : Don't proxy across hardware types!
* Jonathan Naylor : Added support for NET/ROM.
* Mike Shaver : RFC1122 checks.
* Jonathan Naylor : Only lookup the hardware address for
* the correct hardware type.
* Germano Caronni : Assorted subtle races.
* Craig Schlenter : Don't modify permanent entry
* during arp_rcv.
* Russ Nelson : Tidied up a few bits.
* Alexey Kuznetsov: Major changes to caching and behaviour,
* eg intelligent arp probing and
* generation
* of host down events.
* Alan Cox : Missing unlock in device events.
* Eckes : ARP ioctl control errors.
* Alexey Kuznetsov: Arp free fix.
* Manuel Rodriguez: Gratuitous ARP.
* Jonathan Layes : Added arpd support through kerneld
* message queue (960314)
* Mike Shaver : /proc/sys/net/ipv4/arp_* support
* Mike McLagan : Routing by source
* Stuart Cheshire : Metricom and grat arp fixes
* *** FOR 2.1 clean this up ***
* Lawrence V. Stefani: (08/12/96) Added FDDI support.
* Alan Cox : Took the AP1000 nasty FDDI hack and
* folded into the mainstream FDDI code.
* Ack spit, Linus how did you allow that
* one in...
* Jes Sorensen : Make FDDI work again in 2.1.x and
* clean up the APFDDI & gen. FDDI bits.
* Alexey Kuznetsov: new arp state machine;
* now it is in net/core/neighbour.c.
* Krzysztof Halasa: Added Frame Relay ARP support.
* Arnaldo C. Melo : convert /proc/net/arp to seq_file
* Shmulik Hen: Split arp_send to arp_create and
* arp_xmit so intermediate drivers like
* bonding can change the skb before
* sending (e.g. insert 8021q tag).
* Harald Welte : convert to make use of jenkins hash
* Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/capability.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/fddidevice.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/net.h>
#include <linux/rcupdate.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>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ax25.h>
#include <net/netrom.h>
#include <net/dst_metadata.h>
#include <net/ip_tunnels.h>
#include <linux/uaccess.h>
#include <linux/netfilter_arp.h>
/*
* Interface to generic neighbour cache.
*/
static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd);
static bool arp_key_eq(const struct neighbour *n, const void *pkey);
static int arp_constructor(struct neighbour *neigh);
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
static void parp_redo(struct sk_buff *skb);
static int arp_is_multicast(const void *pkey);
static const struct neigh_ops arp_generic_ops = {
.family = AF_INET,
.solicit = arp_solicit,
.error_report = arp_error_report,
.output = neigh_resolve_output,
.connected_output = neigh_connected_output,
};
static const struct neigh_ops arp_hh_ops = {
.family = AF_INET,
.solicit = arp_solicit,
.error_report = arp_error_report,
.output = neigh_resolve_output,
.connected_output = neigh_resolve_output,
};
static const struct neigh_ops arp_direct_ops = {
.family = AF_INET,
.output = neigh_direct_output,
.connected_output = neigh_direct_output,
};
struct neigh_table arp_tbl = {
.family = AF_INET,
.key_len = 4,
.protocol = cpu_to_be16(ETH_P_IP),
.hash = arp_hash,
.key_eq = arp_key_eq,
.constructor = arp_constructor,
.proxy_redo = parp_redo,
.is_multicast = arp_is_multicast,
.id = "arp_cache",
.parms = {
.tbl = &arp_tbl,
.reachable_time = 30 * HZ,
.data = {
[NEIGH_VAR_MCAST_PROBES] = 3,
[NEIGH_VAR_UCAST_PROBES] = 3,
[NEIGH_VAR_RETRANS_TIME] = 1 * HZ,
[NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ,
[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
[NEIGH_VAR_PROXY_QLEN] = 64,
[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
[NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10,
[NEIGH_VAR_LOCKTIME] = 1 * HZ,
},
},
.gc_interval = 30 * HZ,
.gc_thresh1 = 128,
.gc_thresh2 = 512,
.gc_thresh3 = 1024,
};
EXPORT_SYMBOL(arp_tbl);
int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir)
{
switch (dev->type) {
case ARPHRD_ETHER:
case ARPHRD_FDDI:
case ARPHRD_IEEE802:
ip_eth_mc_map(addr, haddr);
return 0;
case ARPHRD_INFINIBAND:
ip_ib_mc_map(addr, dev->broadcast, haddr);
return 0;
case ARPHRD_IPGRE:
ip_ipgre_mc_map(addr, dev->broadcast, haddr);
return 0;
default:
if (dir) {
memcpy(haddr, dev->broadcast, dev->addr_len);
return 0;
}
}
return -EINVAL;
}
static u32 arp_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd)
{
return arp_hashfn(pkey, dev, hash_rnd);
}
static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)
{
return neigh_key_eq32(neigh, pkey);
}
static int arp_constructor(struct neighbour *neigh)
{
__be32 addr;
struct net_device *dev = neigh->dev;
struct in_device *in_dev;
struct neigh_parms *parms;
u32 inaddr_any = INADDR_ANY;
if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len);
addr = *(__be32 *)neigh->primary_key;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (!in_dev) {
rcu_read_unlock();
return -EINVAL;
}
neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr);
parms = in_dev->arp_parms;
__neigh_parms_put(neigh->parms);
neigh->parms = neigh_parms_clone(parms);
rcu_read_unlock();
if (!dev->header_ops) {
neigh->nud_state = NUD_NOARP;
neigh->ops = &arp_direct_ops;
neigh->output = neigh_direct_output;
} else {
/* Good devices (checked by reading texts, but only Ethernet is
tested)
ARPHRD_ETHER: (ethernet, apfddi)
ARPHRD_FDDI: (fddi)
ARPHRD_IEEE802: (tr)
ARPHRD_METRICOM: (strip)
ARPHRD_ARCNET:
etc. etc. etc.
ARPHRD_IPDDP will also work, if author repairs it.
I did not it, because this driver does not work even
in old paradigm.
*/
if (neigh->type == RTN_MULTICAST) {
neigh->nud_state = NUD_NOARP;
arp_mc_map(addr, neigh->ha, dev, 1);
} else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
} else if (neigh->type == RTN_BROADCAST ||
(dev->flags & IFF_POINTOPOINT)) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->broadcast, dev->addr_len);
}
if (dev->header_ops->cache)
neigh->ops = &arp_hh_ops;
else
neigh->ops = &arp_generic_ops;
if (neigh->nud_state & NUD_VALID)
neigh->output = neigh->ops->connected_output;
else
neigh->output = neigh->ops->output;
}
return 0;
}
static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb)
{
dst_link_failure(skb);
kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_FAILED);
}
/* Create and send an arp packet. */
static void arp_send_dst(int type, int ptype, __be32 dest_ip,
struct net_device *dev, __be32 src_ip,
const unsigned char *dest_hw,
const unsigned char *src_hw,
const unsigned char *target_hw,
struct dst_entry *dst)
{
struct sk_buff *skb;
/* arp on this interface. */
if (dev->flags & IFF_NOARP)
return;
skb = arp_create(type, ptype, dest_ip, dev, src_ip,
dest_hw, src_hw, target_hw);
if (!skb)
return;
skb_dst_set(skb, dst_clone(dst));
arp_xmit(skb);
}
void arp_send(int type, int ptype, __be32 dest_ip,
struct net_device *dev, __be32 src_ip,
const unsigned char *dest_hw, const unsigned char *src_hw,
const unsigned char *target_hw)
{
arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw,
target_hw, NULL);
}
EXPORT_SYMBOL(arp_send);
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
{
__be32 saddr = 0;
u8 dst_ha[MAX_ADDR_LEN], *dst_hw = NULL;
struct net_device *dev = neigh->dev;
__be32 target = *(__be32 *)neigh->primary_key;
int probes = atomic_read(&neigh->probes);
struct in_device *in_dev;
struct dst_entry *dst = NULL;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (!in_dev) {
rcu_read_unlock();
return;
}
switch (IN_DEV_ARP_ANNOUNCE(in_dev)) {
default:
case 0: /* By default announce any local IP */
if (skb && inet_addr_type_dev_table(dev_net(dev), dev,
ip_hdr(skb)->saddr) == RTN_LOCAL)
saddr = ip_hdr(skb)->saddr;
break;
case 1: /* Restrict announcements of saddr in same subnet */
if (!skb)
break;
saddr = ip_hdr(skb)->saddr;
if (inet_addr_type_dev_table(dev_net(dev), dev,
saddr) == RTN_LOCAL) {
/* saddr should be known to target */
if (inet_addr_onlink(in_dev, target, saddr))
break;
}
saddr = 0;
break;
case 2: /* Avoid secondary IPs, get a primary/preferred one */
break;
}
rcu_read_unlock();
if (!saddr)
saddr = inet_select_addr(dev, target, RT_SCOPE_LINK);
probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
if (probes < 0) {
if (!(neigh->nud_state & NUD_VALID))
pr_debug("trying to ucast probe in NUD_INVALID\n");
ipv4: arp: fix a lockdep splat in arp_solicit() Yan Burman reported following lockdep warning : ============================================= [ INFO: possible recursive locking detected ] 3.7.0+ #24 Not tainted --------------------------------------------- swapper/1/0 is trying to acquire lock: (&n->lock){++--..}, at: [<ffffffff8139f56e>] __neigh_event_send +0x2e/0x2f0 but task is already holding lock: (&n->lock){++--..}, at: [<ffffffff813f63f4>] arp_solicit+0x1d4/0x280 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&n->lock); lock(&n->lock); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by swapper/1/0: #0: (((&n->timer))){+.-...}, at: [<ffffffff8104b350>] call_timer_fn+0x0/0x1c0 #1: (&n->lock){++--..}, at: [<ffffffff813f63f4>] arp_solicit +0x1d4/0x280 #2: (rcu_read_lock_bh){.+....}, at: [<ffffffff81395400>] dev_queue_xmit+0x0/0x5d0 #3: (rcu_read_lock_bh){.+....}, at: [<ffffffff813cb41e>] ip_finish_output+0x13e/0x640 stack backtrace: Pid: 0, comm: swapper/1 Not tainted 3.7.0+ #24 Call Trace: <IRQ> [<ffffffff8108c7ac>] validate_chain+0xdcc/0x11f0 [<ffffffff8108d570>] ? __lock_acquire+0x440/0xc30 [<ffffffff81120565>] ? kmem_cache_free+0xe5/0x1c0 [<ffffffff8108d570>] __lock_acquire+0x440/0xc30 [<ffffffff813c3570>] ? inet_getpeer+0x40/0x600 [<ffffffff8108d570>] ? __lock_acquire+0x440/0xc30 [<ffffffff8139f56e>] ? __neigh_event_send+0x2e/0x2f0 [<ffffffff8108ddf5>] lock_acquire+0x95/0x140 [<ffffffff8139f56e>] ? __neigh_event_send+0x2e/0x2f0 [<ffffffff8108d570>] ? __lock_acquire+0x440/0xc30 [<ffffffff81448d4b>] _raw_write_lock_bh+0x3b/0x50 [<ffffffff8139f56e>] ? __neigh_event_send+0x2e/0x2f0 [<ffffffff8139f56e>] __neigh_event_send+0x2e/0x2f0 [<ffffffff8139f99b>] neigh_resolve_output+0x16b/0x270 [<ffffffff813cb62d>] ip_finish_output+0x34d/0x640 [<ffffffff813cb41e>] ? ip_finish_output+0x13e/0x640 [<ffffffffa046f146>] ? vxlan_xmit+0x556/0xbec [vxlan] [<ffffffff813cb9a0>] ip_output+0x80/0xf0 [<ffffffff813ca368>] ip_local_out+0x28/0x80 [<ffffffffa046f25a>] vxlan_xmit+0x66a/0xbec [vxlan] [<ffffffffa046f146>] ? vxlan_xmit+0x556/0xbec [vxlan] [<ffffffff81394a50>] ? skb_gso_segment+0x2b0/0x2b0 [<ffffffff81449355>] ? _raw_spin_unlock_irqrestore+0x65/0x80 [<ffffffff81394c57>] ? dev_queue_xmit_nit+0x207/0x270 [<ffffffff813950c8>] dev_hard_start_xmit+0x298/0x5d0 [<ffffffff813956f3>] dev_queue_xmit+0x2f3/0x5d0 [<ffffffff81395400>] ? dev_hard_start_xmit+0x5d0/0x5d0 [<ffffffff813f5788>] arp_xmit+0x58/0x60 [<ffffffff813f59db>] arp_send+0x3b/0x40 [<ffffffff813f6424>] arp_solicit+0x204/0x280 [<ffffffff813a1a70>] ? neigh_add+0x310/0x310 [<ffffffff8139f515>] neigh_probe+0x45/0x70 [<ffffffff813a1c10>] neigh_timer_handler+0x1a0/0x2a0 [<ffffffff8104b3cf>] call_timer_fn+0x7f/0x1c0 [<ffffffff8104b350>] ? detach_if_pending+0x120/0x120 [<ffffffff8104b748>] run_timer_softirq+0x238/0x2b0 [<ffffffff813a1a70>] ? neigh_add+0x310/0x310 [<ffffffff81043e51>] __do_softirq+0x101/0x280 [<ffffffff814518cc>] call_softirq+0x1c/0x30 [<ffffffff81003b65>] do_softirq+0x85/0xc0 [<ffffffff81043a7e>] irq_exit+0x9e/0xc0 [<ffffffff810264f8>] smp_apic_timer_interrupt+0x68/0xa0 [<ffffffff8145122f>] apic_timer_interrupt+0x6f/0x80 <EOI> [<ffffffff8100a054>] ? mwait_idle+0xa4/0x1c0 [<ffffffff8100a04b>] ? mwait_idle+0x9b/0x1c0 [<ffffffff8100a6a9>] cpu_idle+0x89/0xe0 [<ffffffff81441127>] start_secondary+0x1b2/0x1b6 Bug is from arp_solicit(), releasing the neigh lock after arp_send() In case of vxlan, we eventually need to write lock a neigh lock later. Its a false positive, but we can get rid of it without lockdep annotations. We can instead use neigh_ha_snapshot() helper. Reported-by: Yan Burman <yanb@mellanox.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-21 07:32:10 +00:00
neigh_ha_snapshot(dst_ha, neigh, dev);
dst_hw = dst_ha;
} else {
probes -= NEIGH_VAR(neigh->parms, APP_PROBES);
if (probes < 0) {
neigh_app_ns(neigh);
return;
}
}
if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE))
dst = skb_dst(skb);
arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
dst_hw, dev->dev_addr, NULL, dst);
}
static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
{
struct net *net = dev_net(in_dev->dev);
int scope;
switch (IN_DEV_ARP_IGNORE(in_dev)) {
case 0: /* Reply, the tip is already validated */
return 0;
case 1: /* Reply only if tip is configured on the incoming interface */
sip = 0;
scope = RT_SCOPE_HOST;
break;
case 2: /*
* Reply only if tip is configured on the incoming interface
* and is in same subnet as sip
*/
scope = RT_SCOPE_HOST;
break;
case 3: /* Do not reply for scope host addresses */
sip = 0;
scope = RT_SCOPE_LINK;
in_dev = NULL;
break;
case 4: /* Reserved */
case 5:
case 6:
case 7:
return 0;
case 8: /* Do not reply */
return 1;
default:
return 0;
}
return !inet_confirm_addr(net, in_dev, sip, tip, scope);
}
static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
{
struct rtable *rt;
int flag = 0;
/*unsigned long now; */
struct net *net = dev_net(dev);
rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev));
if (IS_ERR(rt))
return 1;
if (rt->dst.dev != dev) {
__NET_INC_STATS(net, LINUX_MIB_ARPFILTER);
flag = 1;
}
ip_rt_put(rt);
return flag;
}
/*
* Check if we can use proxy ARP for this path
*/
static inline int arp_fwd_proxy(struct in_device *in_dev,
struct net_device *dev, struct rtable *rt)
{
struct in_device *out_dev;
int imi, omi = -1;
if (rt->dst.dev == dev)
return 0;
if (!IN_DEV_PROXY_ARP(in_dev))
return 0;
imi = IN_DEV_MEDIUM_ID(in_dev);
if (imi == 0)
return 1;
if (imi == -1)
return 0;
/* place to check for proxy_arp for routes */
out_dev = __in_dev_get_rcu(rt->dst.dev);
if (out_dev)
omi = IN_DEV_MEDIUM_ID(out_dev);
return omi != imi && omi != -1;
}
/*
* Check for RFC3069 proxy arp private VLAN (allow to send back to same dev)
*
* RFC3069 supports proxy arp replies back to the same interface. This
* is done to support (ethernet) switch features, like RFC 3069, where
* the individual ports are not allowed to communicate with each
* other, BUT they are allowed to talk to the upstream router. As
* described in RFC 3069, it is possible to allow these hosts to
* communicate through the upstream router, by proxy_arp'ing.
*
* RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation"
*
* This technology is known by different names:
* In RFC 3069 it is called VLAN Aggregation.
* Cisco and Allied Telesyn call it Private VLAN.
* Hewlett-Packard call it Source-Port filtering or port-isolation.
* Ericsson call it MAC-Forced Forwarding (RFC Draft).
*
*/
static inline int arp_fwd_pvlan(struct in_device *in_dev,
struct net_device *dev, struct rtable *rt,
__be32 sip, __be32 tip)
{
/* Private VLAN is only concerned about the same ethernet segment */
if (rt->dst.dev != dev)
return 0;
/* Don't reply on self probes (often done by windowz boxes)*/
if (sip == tip)
return 0;
if (IN_DEV_PROXY_ARP_PVLAN(in_dev))
return 1;
else
return 0;
}
/*
* Interface to link layer: send routine and receive handler.
*/
/*
* Create an arp packet. If dest_hw is not set, we create a broadcast
* message.
*/
struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
struct net_device *dev, __be32 src_ip,
const unsigned char *dest_hw,
const unsigned char *src_hw,
const unsigned char *target_hw)
{
struct sk_buff *skb;
struct arphdr *arp;
unsigned char *arp_ptr;
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
/*
* Allocate a buffer
*/
skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC);
if (!skb)
return NULL;
skb_reserve(skb, hlen);
skb_reset_network_header(skb);
arp = skb_put(skb, arp_hdr_len(dev));
skb->dev = dev;
skb->protocol = htons(ETH_P_ARP);
if (!src_hw)
src_hw = dev->dev_addr;
if (!dest_hw)
dest_hw = dev->broadcast;
/*
* Fill the device header for the ARP frame
*/
if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0)
goto out;
/*
* Fill out the arp protocol part.
*
* The arp hardware type should match the device type, except for FDDI,
* which (according to RFC 1390) should always equal 1 (Ethernet).
*/
/*
* Exceptions everywhere. AX.25 uses the AX.25 PID value not the
* DIX code for the protocol. Make these device structure fields.
*/
switch (dev->type) {
default:
arp->ar_hrd = htons(dev->type);
arp->ar_pro = htons(ETH_P_IP);
break;
#if IS_ENABLED(CONFIG_AX25)
case ARPHRD_AX25:
arp->ar_hrd = htons(ARPHRD_AX25);
arp->ar_pro = htons(AX25_P_IP);
break;
#if IS_ENABLED(CONFIG_NETROM)
case ARPHRD_NETROM:
arp->ar_hrd = htons(ARPHRD_NETROM);
arp->ar_pro = htons(AX25_P_IP);
break;
#endif
#endif
#if IS_ENABLED(CONFIG_FDDI)
case ARPHRD_FDDI:
arp->ar_hrd = htons(ARPHRD_ETHER);
arp->ar_pro = htons(ETH_P_IP);
break;
#endif
}
arp->ar_hln = dev->addr_len;
arp->ar_pln = 4;
arp->ar_op = htons(type);
arp_ptr = (unsigned char *)(arp + 1);
memcpy(arp_ptr, src_hw, dev->addr_len);
arp_ptr += dev->addr_len;
memcpy(arp_ptr, &src_ip, 4);
arp_ptr += 4;
firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection. Inspection of upper layer protocol is considered harmful, especially if it is about ARP or other stateful upper layer protocol; driver cannot (and should not) have full state of them. IPv4 over Firewire module used to inspect ARP (both in sending path and in receiving path), and record peer's GUID, max packet size, max speed and fifo address. This patch removes such inspection by extending our "hardware address" definition to include other information as well: max packet size, max speed and fifo. By doing this, The neighbour module in networking subsystem can cache them. Note: As we have started ignoring sspd and max_rec in ARP/NDP, those information will not be used in the driver when sending. When a packet is being sent, the IP layer fills our pseudo header with the extended "hardware address", including GUID and fifo. The driver can look-up node-id (the real but rather volatile low-level address) by GUID, and then the module can send the packet to the wire using parameters provided in the extendedn hardware address. This approach is realistic because IP over IEEE1394 (RFC2734) and IPv6 over IEEE1394 (RFC3146) share same "hardware address" format in their address resolution protocols. Here, extended "hardware address" is defined as follows: union fwnet_hwaddr { u8 u[16]; struct { __be64 uniq_id; /* EUI-64 */ u8 max_rec; /* max packet size */ u8 sspd; /* max speed */ __be16 fifo_hi; /* hi 16bits of FIFO addr */ __be32 fifo_lo; /* lo 32bits of FIFO addr */ } __packed uc; }; Note that Hardware address is declared as union, so that we can map full IP address into this, when implementing MCAP (Multicast Cannel Allocation Protocol) for IPv6, but IP and ARP subsystem do not need to know this format in detail. One difference between original ARP (RFC826) and 1394 ARP (RFC2734) is that 1394 ARP Request/Reply do not contain the target hardware address field (aka ar$tha). This difference is handled in the ARP subsystem. CC: Stephan Gatzka <stephan.gatzka@gmail.com> Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-25 08:26:16 +00:00
switch (dev->type) {
#if IS_ENABLED(CONFIG_FIREWIRE_NET)
case ARPHRD_IEEE1394:
break;
#endif
default:
if (target_hw)
firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection. Inspection of upper layer protocol is considered harmful, especially if it is about ARP or other stateful upper layer protocol; driver cannot (and should not) have full state of them. IPv4 over Firewire module used to inspect ARP (both in sending path and in receiving path), and record peer's GUID, max packet size, max speed and fifo address. This patch removes such inspection by extending our "hardware address" definition to include other information as well: max packet size, max speed and fifo. By doing this, The neighbour module in networking subsystem can cache them. Note: As we have started ignoring sspd and max_rec in ARP/NDP, those information will not be used in the driver when sending. When a packet is being sent, the IP layer fills our pseudo header with the extended "hardware address", including GUID and fifo. The driver can look-up node-id (the real but rather volatile low-level address) by GUID, and then the module can send the packet to the wire using parameters provided in the extendedn hardware address. This approach is realistic because IP over IEEE1394 (RFC2734) and IPv6 over IEEE1394 (RFC3146) share same "hardware address" format in their address resolution protocols. Here, extended "hardware address" is defined as follows: union fwnet_hwaddr { u8 u[16]; struct { __be64 uniq_id; /* EUI-64 */ u8 max_rec; /* max packet size */ u8 sspd; /* max speed */ __be16 fifo_hi; /* hi 16bits of FIFO addr */ __be32 fifo_lo; /* lo 32bits of FIFO addr */ } __packed uc; }; Note that Hardware address is declared as union, so that we can map full IP address into this, when implementing MCAP (Multicast Cannel Allocation Protocol) for IPv6, but IP and ARP subsystem do not need to know this format in detail. One difference between original ARP (RFC826) and 1394 ARP (RFC2734) is that 1394 ARP Request/Reply do not contain the target hardware address field (aka ar$tha). This difference is handled in the ARP subsystem. CC: Stephan Gatzka <stephan.gatzka@gmail.com> Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-25 08:26:16 +00:00
memcpy(arp_ptr, target_hw, dev->addr_len);
else
memset(arp_ptr, 0, dev->addr_len);
arp_ptr += dev->addr_len;
}
memcpy(arp_ptr, &dest_ip, 4);
return skb;
out:
kfree_skb(skb);
return NULL;
}
EXPORT_SYMBOL(arp_create);
static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
return dev_queue_xmit(skb);
}
/*
* Send an arp packet.
*/
void arp_xmit(struct sk_buff *skb)
{
/* Send it off, maybe filter it using firewalling first. */
2015-09-16 01:04:16 +00:00
NF_HOOK(NFPROTO_ARP, NF_ARP_OUT,
dev_net(skb->dev), NULL, skb, NULL, skb->dev,
arp_xmit_finish);
}
EXPORT_SYMBOL(arp_xmit);
static bool arp_is_garp(struct net *net, struct net_device *dev,
int *addr_type, __be16 ar_op,
__be32 sip, __be32 tip,
unsigned char *sha, unsigned char *tha)
{
bool is_garp = tip == sip;
/* Gratuitous ARP _replies_ also require target hwaddr to be
* the same as source.
*/
if (is_garp && ar_op == htons(ARPOP_REPLY))
is_garp =
/* IPv4 over IEEE 1394 doesn't provide target
* hardware address field in its ARP payload.
*/
tha &&
!memcmp(tha, sha, dev->addr_len);
if (is_garp) {
*addr_type = inet_addr_type_dev_table(net, dev, sip);
if (*addr_type != RTN_UNICAST)
is_garp = false;
}
return is_garp;
}
/*
* Process an arp request.
*/
static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct arphdr *arp;
unsigned char *arp_ptr;
struct rtable *rt;
unsigned char *sha;
unsigned char *tha = NULL;
__be32 sip, tip;
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
struct dst_entry *reply_dst = NULL;
bool is_garp = false;
/* arp_rcv below verifies the ARP header and verifies the device
* is ARP'able.
*/
if (!in_dev)
goto out_free_skb;
arp = arp_hdr(skb);
switch (dev_type) {
default:
if (arp->ar_pro != htons(ETH_P_IP) ||
htons(dev_type) != arp->ar_hrd)
goto out_free_skb;
break;
case ARPHRD_ETHER:
case ARPHRD_FDDI:
case ARPHRD_IEEE802:
/*
* ETHERNET, and Fibre Channel (which are IEEE 802
* devices, according to RFC 2625) devices will accept ARP
* hardware types of either 1 (Ethernet) or 6 (IEEE 802.2).
* This is the case also of FDDI, where the RFC 1390 says that
* FDDI devices should accept ARP hardware of (1) Ethernet,
* however, to be more robust, we'll accept both 1 (Ethernet)
* or 6 (IEEE 802.2)
*/
if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
arp->ar_pro != htons(ETH_P_IP))
goto out_free_skb;
break;
case ARPHRD_AX25:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_AX25))
goto out_free_skb;
break;
case ARPHRD_NETROM:
if (arp->ar_pro != htons(AX25_P_IP) ||
arp->ar_hrd != htons(ARPHRD_NETROM))
goto out_free_skb;
break;
}
/* Understand only these message types */
if (arp->ar_op != htons(ARPOP_REPLY) &&
arp->ar_op != htons(ARPOP_REQUEST))
goto out_free_skb;
/*
* Extract fields
*/
arp_ptr = (unsigned char *)(arp + 1);
sha = arp_ptr;
arp_ptr += dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection. Inspection of upper layer protocol is considered harmful, especially if it is about ARP or other stateful upper layer protocol; driver cannot (and should not) have full state of them. IPv4 over Firewire module used to inspect ARP (both in sending path and in receiving path), and record peer's GUID, max packet size, max speed and fifo address. This patch removes such inspection by extending our "hardware address" definition to include other information as well: max packet size, max speed and fifo. By doing this, The neighbour module in networking subsystem can cache them. Note: As we have started ignoring sspd and max_rec in ARP/NDP, those information will not be used in the driver when sending. When a packet is being sent, the IP layer fills our pseudo header with the extended "hardware address", including GUID and fifo. The driver can look-up node-id (the real but rather volatile low-level address) by GUID, and then the module can send the packet to the wire using parameters provided in the extendedn hardware address. This approach is realistic because IP over IEEE1394 (RFC2734) and IPv6 over IEEE1394 (RFC3146) share same "hardware address" format in their address resolution protocols. Here, extended "hardware address" is defined as follows: union fwnet_hwaddr { u8 u[16]; struct { __be64 uniq_id; /* EUI-64 */ u8 max_rec; /* max packet size */ u8 sspd; /* max speed */ __be16 fifo_hi; /* hi 16bits of FIFO addr */ __be32 fifo_lo; /* lo 32bits of FIFO addr */ } __packed uc; }; Note that Hardware address is declared as union, so that we can map full IP address into this, when implementing MCAP (Multicast Cannel Allocation Protocol) for IPv6, but IP and ARP subsystem do not need to know this format in detail. One difference between original ARP (RFC826) and 1394 ARP (RFC2734) is that 1394 ARP Request/Reply do not contain the target hardware address field (aka ar$tha). This difference is handled in the ARP subsystem. CC: Stephan Gatzka <stephan.gatzka@gmail.com> Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-25 08:26:16 +00:00
switch (dev_type) {
#if IS_ENABLED(CONFIG_FIREWIRE_NET)
case ARPHRD_IEEE1394:
break;
#endif
default:
tha = arp_ptr;
firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection. Inspection of upper layer protocol is considered harmful, especially if it is about ARP or other stateful upper layer protocol; driver cannot (and should not) have full state of them. IPv4 over Firewire module used to inspect ARP (both in sending path and in receiving path), and record peer's GUID, max packet size, max speed and fifo address. This patch removes such inspection by extending our "hardware address" definition to include other information as well: max packet size, max speed and fifo. By doing this, The neighbour module in networking subsystem can cache them. Note: As we have started ignoring sspd and max_rec in ARP/NDP, those information will not be used in the driver when sending. When a packet is being sent, the IP layer fills our pseudo header with the extended "hardware address", including GUID and fifo. The driver can look-up node-id (the real but rather volatile low-level address) by GUID, and then the module can send the packet to the wire using parameters provided in the extendedn hardware address. This approach is realistic because IP over IEEE1394 (RFC2734) and IPv6 over IEEE1394 (RFC3146) share same "hardware address" format in their address resolution protocols. Here, extended "hardware address" is defined as follows: union fwnet_hwaddr { u8 u[16]; struct { __be64 uniq_id; /* EUI-64 */ u8 max_rec; /* max packet size */ u8 sspd; /* max speed */ __be16 fifo_hi; /* hi 16bits of FIFO addr */ __be32 fifo_lo; /* lo 32bits of FIFO addr */ } __packed uc; }; Note that Hardware address is declared as union, so that we can map full IP address into this, when implementing MCAP (Multicast Cannel Allocation Protocol) for IPv6, but IP and ARP subsystem do not need to know this format in detail. One difference between original ARP (RFC826) and 1394 ARP (RFC2734) is that 1394 ARP Request/Reply do not contain the target hardware address field (aka ar$tha). This difference is handled in the ARP subsystem. CC: Stephan Gatzka <stephan.gatzka@gmail.com> Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-25 08:26:16 +00:00
arp_ptr += dev->addr_len;
}
memcpy(&tip, arp_ptr, 4);
/*
* Check for bad requests for 127.x.x.x and requests for multicast
* addresses. If this is one such, delete it.
*/
if (ipv4_is_multicast(tip) ||
(!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip)))
goto out_free_skb;
/*
* For some 802.11 wireless deployments (and possibly other networks),
* there will be an ARP proxy and gratuitous ARP frames are attacks
* and thus should not be accepted.
*/
if (sip == tip && IN_DEV_ORCONF(in_dev, DROP_GRATUITOUS_ARP))
goto out_free_skb;
/*
* Special case: We must set Frame Relay source Q.922 address
*/
if (dev_type == ARPHRD_DLCI)
sha = dev->broadcast;
/*
* Process entry. The idea here is we want to send a reply if it is a
* request for us or if it is a request for someone else that we hold
* a proxy for. We want to add an entry to our cache if it is a reply
* to us or if it is a request for our address.
* (The assumption for this last is that if someone is requesting our
* address, they are probably intending to talk to us, so it saves time
* if we cache their address. Their address is also probably not in
* our cache, since ours is not in their cache.)
*
* Putting this another way, we only care about replies if they are to
* us, in which case we add them to the cache. For requests, we care
* about those for us and those for our proxies. We reply to both,
* and in the case of requests for us we add the requester to the arp
* cache.
*/
if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb))
reply_dst = (struct dst_entry *)
iptunnel_metadata_reply(skb_metadata_dst(skb),
GFP_ATOMIC);
/* Special case: IPv4 duplicate address detection packet (RFC2131) */
if (sip == 0) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip,
sha, dev->dev_addr, sha, reply_dst);
goto out_consume_skb;
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
if (addr_type == RTN_LOCAL) {
int dont_send;
dont_send = arp_ignore(in_dev, sip, tip);
if (!dont_send && IN_DEV_ARPFILTER(in_dev))
dont_send = arp_filter(sip, tip, dev);
if (!dont_send) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n) {
arp_send_dst(ARPOP_REPLY, ETH_P_ARP,
sip, dev, tip, sha,
dev->dev_addr, sha,
reply_dst);
neigh_release(n);
}
}
goto out_consume_skb;
} else if (IN_DEV_FORWARD(in_dev)) {
if (addr_type == RTN_UNICAST &&
(arp_fwd_proxy(in_dev, dev, rt) ||
arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
(rt->dst.dev != dev &&
pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n)
neigh_release(n);
if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED ||
skb->pkt_type == PACKET_HOST ||
NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) {
arp_send_dst(ARPOP_REPLY, ETH_P_ARP,
sip, dev, tip, sha,
dev->dev_addr, sha,
reply_dst);
} else {
pneigh_enqueue(&arp_tbl,
in_dev->arp_parms, skb);
goto out_free_dst;
}
goto out_consume_skb;
}
}
}
/* Update our ARP tables */
n = __neigh_lookup(&arp_tbl, &sip, dev, 0);
addr_type = -1;
if (n || IN_DEV_ARP_ACCEPT(in_dev)) {
is_garp = arp_is_garp(net, dev, &addr_type, arp->ar_op,
sip, tip, sha, tha);
}
if (IN_DEV_ARP_ACCEPT(in_dev)) {
/* Unsolicited ARP is not accepted by default.
It is possible, that this option should be enabled for some
devices (strip is candidate)
*/
if (!n &&
(is_garp ||
(arp->ar_op == htons(ARPOP_REPLY) &&
(addr_type == RTN_UNICAST ||
(addr_type < 0 &&
/* postpone calculation to as late as possible */
inet_addr_type_dev_table(net, dev, sip) ==
RTN_UNICAST)))))
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
if (n) {
int state = NUD_REACHABLE;
int override;
/* If several different ARP replies follows back-to-back,
use the FIRST one. It is possible, if several proxy
agents are active. Taking the first reply prevents
arp trashing and chooses the fastest router.
*/
override = time_after(jiffies,
n->updated +
NEIGH_VAR(n->parms, LOCKTIME)) ||
is_garp;
/* Broadcast replies and request packets
do not assert neighbour reachability.
*/
if (arp->ar_op != htons(ARPOP_REPLY) ||
skb->pkt_type != PACKET_HOST)
state = NUD_STALE;
neigh_update(n, sha, state,
override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0);
neigh_release(n);
}
out_consume_skb:
consume_skb(skb);
out_free_dst:
dst_release(reply_dst);
return NET_RX_SUCCESS;
out_free_skb:
kfree_skb(skb);
return NET_RX_DROP;
}
static void parp_redo(struct sk_buff *skb)
{
arp_process(dev_net(skb->dev), NULL, skb);
}
static int arp_is_multicast(const void *pkey)
{
return ipv4_is_multicast(*((__be32 *)pkey));
}
/*
* Receive an arp request from the device layer.
*/
static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
const struct arphdr *arp;
/* do not tweak dropwatch on an ARP we will ignore */
if (dev->flags & IFF_NOARP ||
skb->pkt_type == PACKET_OTHERHOST ||
skb->pkt_type == PACKET_LOOPBACK)
goto consumeskb;
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb)
goto out_of_mem;
/* ARP header, plus 2 device addresses, plus 2 IP addresses. */
if (!pskb_may_pull(skb, arp_hdr_len(dev)))
goto freeskb;
arp = arp_hdr(skb);
if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4)
goto freeskb;
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
2015-09-16 01:04:16 +00:00
return NF_HOOK(NFPROTO_ARP, NF_ARP_IN,
dev_net(dev), NULL, skb, dev, NULL,
arp_process);
consumeskb:
consume_skb(skb);
return NET_RX_SUCCESS;
freeskb:
kfree_skb(skb);
out_of_mem:
return NET_RX_DROP;
}
/*
* User level interface (ioctl)
*/
/*
* Set (create) an ARP cache entry.
*/
static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on)
{
if (!dev) {
IPV4_DEVCONF_ALL(net, PROXY_ARP) = on;
return 0;
}
if (__in_dev_get_rtnl(dev)) {
IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on);
return 0;
}
return -ENXIO;
}
static int arp_req_set_public(struct net *net, struct arpreq *r,
struct net_device *dev)
{
__be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
__be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr;
if (mask && mask != htonl(0xFFFFFFFF))
return -EINVAL;
if (!dev && (r->arp_flags & ATF_COM)) {
dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family,
r->arp_ha.sa_data);
if (!dev)
return -ENODEV;
}
if (mask) {
if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1))
return -ENOBUFS;
return 0;
}
return arp_req_set_proxy(net, dev, 1);
}
static int arp_req_set(struct net *net, struct arpreq *r,
struct net_device *dev)
{
__be32 ip;
struct neighbour *neigh;
int err;
if (r->arp_flags & ATF_PUBL)
return arp_req_set_public(net, r, dev);
ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
if (r->arp_flags & ATF_PERM)
r->arp_flags |= ATF_COM;
if (!dev) {
struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
if (IS_ERR(rt))
return PTR_ERR(rt);
dev = rt->dst.dev;
ip_rt_put(rt);
if (!dev)
return -EINVAL;
}
switch (dev->type) {
#if IS_ENABLED(CONFIG_FDDI)
case ARPHRD_FDDI:
/*
* According to RFC 1390, FDDI devices should accept ARP
* hardware types of 1 (Ethernet). However, to be more
* robust, we'll accept hardware types of either 1 (Ethernet)
* or 6 (IEEE 802.2).
*/
if (r->arp_ha.sa_family != ARPHRD_FDDI &&
r->arp_ha.sa_family != ARPHRD_ETHER &&
r->arp_ha.sa_family != ARPHRD_IEEE802)
return -EINVAL;
break;
#endif
default:
if (r->arp_ha.sa_family != dev->type)
return -EINVAL;
break;
}
neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev);
err = PTR_ERR(neigh);
if (!IS_ERR(neigh)) {
unsigned int state = NUD_STALE;
if (r->arp_flags & ATF_PERM)
state = NUD_PERMANENT;
err = neigh_update(neigh, (r->arp_flags & ATF_COM) ?
r->arp_ha.sa_data : NULL, state,
NEIGH_UPDATE_F_OVERRIDE |
NEIGH_UPDATE_F_ADMIN, 0);
neigh_release(neigh);
}
return err;
}
static unsigned int arp_state_to_flags(struct neighbour *neigh)
{
if (neigh->nud_state&NUD_PERMANENT)
return ATF_PERM | ATF_COM;
else if (neigh->nud_state&NUD_VALID)
return ATF_COM;
else
return 0;
}
/*
* Get an ARP cache entry.
*/
static int arp_req_get(struct arpreq *r, struct net_device *dev)
{
__be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr;
struct neighbour *neigh;
int err = -ENXIO;
neigh = neigh_lookup(&arp_tbl, &ip, dev);
if (neigh) {
if (!(neigh->nud_state & NUD_NOARP)) {
read_lock_bh(&neigh->lock);
memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
r->arp_flags = arp_state_to_flags(neigh);
read_unlock_bh(&neigh->lock);
r->arp_ha.sa_family = dev->type;
strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
err = 0;
}
neigh_release(neigh);
}
return err;
}
int arp_invalidate(struct net_device *dev, __be32 ip, bool force)
{
struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
int err = -ENXIO;
struct neigh_table *tbl = &arp_tbl;
if (neigh) {
if ((neigh->nud_state & NUD_VALID) && !force) {
neigh_release(neigh);
return 0;
}
if (neigh->nud_state & ~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_ADMIN, 0);
write_lock_bh(&tbl->lock);
neigh_release(neigh);
neigh_remove_one(neigh, tbl);
write_unlock_bh(&tbl->lock);
}
return err;
}
static int arp_req_delete_public(struct net *net, struct arpreq *r,
struct net_device *dev)
{
__be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr;
__be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr;
if (mask == htonl(0xFFFFFFFF))
return pneigh_delete(&arp_tbl, net, &ip, dev);
if (mask)
return -EINVAL;
return arp_req_set_proxy(net, dev, 0);
}
static int arp_req_delete(struct net *net, struct arpreq *r,
struct net_device *dev)
{
__be32 ip;
if (r->arp_flags & ATF_PUBL)
return arp_req_delete_public(net, r, dev);
ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
if (!dev) {
struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
if (IS_ERR(rt))
return PTR_ERR(rt);
dev = rt->dst.dev;
ip_rt_put(rt);
if (!dev)
return -EINVAL;
}
return arp_invalidate(dev, ip, true);
}
/*
* Handle an ARP layer I/O control request.
*/
int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
int err;
struct arpreq r;
struct net_device *dev = NULL;
switch (cmd) {
case SIOCDARP:
case SIOCSARP:
net: Allow userns root to control ipv4 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow creating raw sockets. Allow the SIOCSARP ioctl to control the arp cache. Allow the SIOCSIFFLAG ioctl to allow setting network device flags. Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address. Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address. Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address. Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask. Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting gre tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipip tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipsec virtual tunnel interfaces. Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC, MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing sockets. Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and arbitrary ip options. Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option. Allow setting the IP_TRANSPARENT ipv4 socket option. Allow setting the TCP_REPAIR socket option. Allow setting the TCP_CONGESTION socket option. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 03:03:05 +00:00
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
fallthrough;
case SIOCGARP:
err = copy_from_user(&r, arg, sizeof(struct arpreq));
if (err)
return -EFAULT;
break;
default:
return -EINVAL;
}
if (r.arp_pa.sa_family != AF_INET)
return -EPFNOSUPPORT;
if (!(r.arp_flags & ATF_PUBL) &&
(r.arp_flags & (ATF_NETMASK | ATF_DONTPUB)))
return -EINVAL;
if (!(r.arp_flags & ATF_NETMASK))
((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr =
htonl(0xFFFFFFFFUL);
rtnl_lock();
if (r.arp_dev[0]) {
err = -ENODEV;
dev = __dev_get_by_name(net, r.arp_dev);
if (!dev)
goto out;
/* Mmmm... It is wrong... ARPHRD_NETROM==0 */
if (!r.arp_ha.sa_family)
r.arp_ha.sa_family = dev->type;
err = -EINVAL;
if ((r.arp_flags & ATF_COM) && r.arp_ha.sa_family != dev->type)
goto out;
} else if (cmd == SIOCGARP) {
err = -ENODEV;
goto out;
}
switch (cmd) {
case SIOCDARP:
err = arp_req_delete(net, &r, dev);
break;
case SIOCSARP:
err = arp_req_set(net, &r, dev);
break;
case SIOCGARP:
err = arp_req_get(&r, dev);
break;
}
out:
rtnl_unlock();
if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r)))
err = -EFAULT;
return err;
}
static int arp_netdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct netdev_notifier_change_info *change_info;
net: arp: introduce arp_evict_nocarrier sysctl parameter This change introduces a new sysctl parameter, arp_evict_nocarrier. When set (default) the ARP cache will be cleared on a NOCARRIER event. This new option has been defaulted to '1' which maintains existing behavior. Clearing the ARP cache on NOCARRIER is relatively new, introduced by: commit 859bd2ef1fc1110a8031b967ee656c53a6260a76 Author: David Ahern <dsahern@gmail.com> Date: Thu Oct 11 20:33:49 2018 -0700 net: Evict neighbor entries on carrier down The reason for this changes is to prevent the ARP cache from being cleared when a wireless device roams. Specifically for wireless roams the ARP cache should not be cleared because the underlying network has not changed. Clearing the ARP cache in this case can introduce significant delays sending out packets after a roam. A user reported such a situation here: https://lore.kernel.org/linux-wireless/CACsRnHWa47zpx3D1oDq9JYnZWniS8yBwW1h0WAVZ6vrbwL_S0w@mail.gmail.com/ After some investigation it was found that the kernel was holding onto packets until ARP finished which resulted in this 1 second delay. It was also found that the first ARP who-has was never responded to, which is actually what caues the delay. This change is more or less working around this behavior, but again, there is no reason to clear the cache on a roam anyways. As for the unanswered who-has, we know the packet made it OTA since it was seen while monitoring. Why it never received a response is unknown. In any case, since this is a problem on the AP side of things all that can be done is to work around it until it is solved. Some background on testing/reproducing the packet delay: Hardware: - 2 access points configured for Fast BSS Transition (Though I don't see why regular reassociation wouldn't have the same behavior) - Wireless station running IWD as supplicant - A device on network able to respond to pings (I used one of the APs) Procedure: - Connect to first AP - Ping once to establish an ARP entry - Start a tcpdump - Roam to second AP - Wait for operstate UP event, and note the timestamp - Start pinging Results: Below is the tcpdump after UP. It was recorded the interface went UP at 10:42:01.432875. 10:42:01.461871 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.497976 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.507162 ARP, Reply 192.168.254.1 is-at ac:86:74:55:b0:20, length 46 10:42:02.507185 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 1, length 64 10:42:02.507205 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 2, length 64 10:42:02.507212 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 3, length 64 10:42:02.507219 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 4, length 64 10:42:02.507225 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 5, length 64 10:42:02.507232 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 6, length 64 10:42:02.515373 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 1, length 64 10:42:02.521399 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 2, length 64 10:42:02.521612 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 3, length 64 10:42:02.521941 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 4, length 64 10:42:02.522419 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 5, length 64 10:42:02.523085 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 6, length 64 You can see the first ARP who-has went out very quickly after UP, but was never responded to. Nearly a second later the kernel retries and gets a response. Only then do the ping packets go out. If an ARP entry is manually added prior to UP (after the cache is cleared) it is seen that the first ping is never responded to, so its not only an issue with ARP but with data packets in general. As mentioned prior, the wireless interface was also monitored to verify the ping/ARP packet made it OTA which was observed to be true. Signed-off-by: James Prestwood <prestwoj@gmail.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-11-01 17:36:28 +00:00
struct in_device *in_dev;
bool evict_nocarrier;
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&arp_tbl, dev);
rt_cache_flush(dev_net(dev));
break;
case NETDEV_CHANGE:
change_info = ptr;
if (change_info->flags_changed & IFF_NOARP)
neigh_changeaddr(&arp_tbl, dev);
net: arp: introduce arp_evict_nocarrier sysctl parameter This change introduces a new sysctl parameter, arp_evict_nocarrier. When set (default) the ARP cache will be cleared on a NOCARRIER event. This new option has been defaulted to '1' which maintains existing behavior. Clearing the ARP cache on NOCARRIER is relatively new, introduced by: commit 859bd2ef1fc1110a8031b967ee656c53a6260a76 Author: David Ahern <dsahern@gmail.com> Date: Thu Oct 11 20:33:49 2018 -0700 net: Evict neighbor entries on carrier down The reason for this changes is to prevent the ARP cache from being cleared when a wireless device roams. Specifically for wireless roams the ARP cache should not be cleared because the underlying network has not changed. Clearing the ARP cache in this case can introduce significant delays sending out packets after a roam. A user reported such a situation here: https://lore.kernel.org/linux-wireless/CACsRnHWa47zpx3D1oDq9JYnZWniS8yBwW1h0WAVZ6vrbwL_S0w@mail.gmail.com/ After some investigation it was found that the kernel was holding onto packets until ARP finished which resulted in this 1 second delay. It was also found that the first ARP who-has was never responded to, which is actually what caues the delay. This change is more or less working around this behavior, but again, there is no reason to clear the cache on a roam anyways. As for the unanswered who-has, we know the packet made it OTA since it was seen while monitoring. Why it never received a response is unknown. In any case, since this is a problem on the AP side of things all that can be done is to work around it until it is solved. Some background on testing/reproducing the packet delay: Hardware: - 2 access points configured for Fast BSS Transition (Though I don't see why regular reassociation wouldn't have the same behavior) - Wireless station running IWD as supplicant - A device on network able to respond to pings (I used one of the APs) Procedure: - Connect to first AP - Ping once to establish an ARP entry - Start a tcpdump - Roam to second AP - Wait for operstate UP event, and note the timestamp - Start pinging Results: Below is the tcpdump after UP. It was recorded the interface went UP at 10:42:01.432875. 10:42:01.461871 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.497976 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.507162 ARP, Reply 192.168.254.1 is-at ac:86:74:55:b0:20, length 46 10:42:02.507185 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 1, length 64 10:42:02.507205 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 2, length 64 10:42:02.507212 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 3, length 64 10:42:02.507219 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 4, length 64 10:42:02.507225 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 5, length 64 10:42:02.507232 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 6, length 64 10:42:02.515373 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 1, length 64 10:42:02.521399 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 2, length 64 10:42:02.521612 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 3, length 64 10:42:02.521941 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 4, length 64 10:42:02.522419 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 5, length 64 10:42:02.523085 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 6, length 64 You can see the first ARP who-has went out very quickly after UP, but was never responded to. Nearly a second later the kernel retries and gets a response. Only then do the ping packets go out. If an ARP entry is manually added prior to UP (after the cache is cleared) it is seen that the first ping is never responded to, so its not only an issue with ARP but with data packets in general. As mentioned prior, the wireless interface was also monitored to verify the ping/ARP packet made it OTA which was observed to be true. Signed-off-by: James Prestwood <prestwoj@gmail.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-11-01 17:36:28 +00:00
in_dev = __in_dev_get_rtnl(dev);
if (!in_dev)
evict_nocarrier = true;
else
evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev);
if (evict_nocarrier && !netif_carrier_ok(dev))
neigh_carrier_down(&arp_tbl, dev);
break;
default:
break;
}
return NOTIFY_DONE;
}
static struct notifier_block arp_netdev_notifier = {
.notifier_call = arp_netdev_event,
};
/* Note, that it is not on notifier chain.
It is necessary, that this routine was called after route cache will be
flushed.
*/
void arp_ifdown(struct net_device *dev)
{
neigh_ifdown(&arp_tbl, dev);
}
/*
* Called once on startup.
*/
static struct packet_type arp_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_ARP),
.func = arp_rcv,
};
#ifdef CONFIG_PROC_FS
#if IS_ENABLED(CONFIG_AX25)
/*
* ax25 -> ASCII conversion
*/
static void ax2asc2(ax25_address *a, char *buf)
{
char c, *s;
int n;
for (n = 0, s = buf; n < 6; n++) {
c = (a->ax25_call[n] >> 1) & 0x7F;
if (c != ' ')
*s++ = c;
}
*s++ = '-';
n = (a->ax25_call[6] >> 1) & 0x0F;
if (n > 9) {
*s++ = '1';
n -= 10;
}
*s++ = n + '0';
*s++ = '\0';
if (*buf == '\0' || *buf == '-') {
buf[0] = '*';
buf[1] = '\0';
}
}
#endif /* CONFIG_AX25 */
#define HBUFFERLEN 30
static void arp_format_neigh_entry(struct seq_file *seq,
struct neighbour *n)
{
char hbuffer[HBUFFERLEN];
int k, j;
char tbuf[16];
struct net_device *dev = n->dev;
int hatype = dev->type;
read_lock(&n->lock);
/* Convert hardware address to XX:XX:XX:XX ... form. */
#if IS_ENABLED(CONFIG_AX25)
if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM)
ax2asc2((ax25_address *)n->ha, hbuffer);
else {
#endif
for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < dev->addr_len; j++) {
hbuffer[k++] = hex_asc_hi(n->ha[j]);
hbuffer[k++] = hex_asc_lo(n->ha[j]);
hbuffer[k++] = ':';
}
if (k != 0)
--k;
hbuffer[k] = 0;
#if IS_ENABLED(CONFIG_AX25)
}
#endif
sprintf(tbuf, "%pI4", n->primary_key);
seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n",
tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name);
read_unlock(&n->lock);
}
static void arp_format_pneigh_entry(struct seq_file *seq,
struct pneigh_entry *n)
{
struct net_device *dev = n->dev;
int hatype = dev ? dev->type : 0;
char tbuf[16];
sprintf(tbuf, "%pI4", n->key);
seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n",
tbuf, hatype, ATF_PUBL | ATF_PERM, "00:00:00:00:00:00",
dev ? dev->name : "*");
}
static int arp_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN) {
seq_puts(seq, "IP address HW type Flags "
"HW address Mask Device\n");
} else {
struct neigh_seq_state *state = seq->private;
if (state->flags & NEIGH_SEQ_IS_PNEIGH)
arp_format_pneigh_entry(seq, v);
else
arp_format_neigh_entry(seq, v);
}
return 0;
}
static void *arp_seq_start(struct seq_file *seq, loff_t *pos)
{
/* Don't want to confuse "arp -a" w/ magic entries,
* so we tell the generic iterator to skip NUD_NOARP.
*/
return neigh_seq_start(seq, pos, &arp_tbl, NEIGH_SEQ_SKIP_NOARP);
}
static const struct seq_operations arp_seq_ops = {
.start = arp_seq_start,
.next = neigh_seq_next,
.stop = neigh_seq_stop,
.show = arp_seq_show,
};
#endif /* CONFIG_PROC_FS */
static int __net_init arp_net_init(struct net *net)
{
if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops,
sizeof(struct neigh_seq_state)))
return -ENOMEM;
return 0;
}
static void __net_exit arp_net_exit(struct net *net)
{
remove_proc_entry("arp", net->proc_net);
}
static struct pernet_operations arp_net_ops = {
.init = arp_net_init,
.exit = arp_net_exit,
};
void __init arp_init(void)
{
neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl);
dev_add_pack(&arp_packet_type);
register_pernet_subsys(&arp_net_ops);
#ifdef CONFIG_SYSCTL
neigh_sysctl_register(NULL, &arp_tbl.parms, NULL);
#endif
register_netdevice_notifier(&arp_netdev_notifier);
}