linux-stable/include/linux/inetdevice.h
James Prestwood fcdb44d08a 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 859bd2ef1f
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 19:57:14 -07:00

300 lines
9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_INETDEVICE_H
#define _LINUX_INETDEVICE_H
#ifdef __KERNEL__
#include <linux/bitmap.h>
#include <linux/if.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/rcupdate.h>
#include <linux/timer.h>
#include <linux/sysctl.h>
#include <linux/rtnetlink.h>
#include <linux/refcount.h>
struct ipv4_devconf {
void *sysctl;
int data[IPV4_DEVCONF_MAX];
DECLARE_BITMAP(state, IPV4_DEVCONF_MAX);
};
#define MC_HASH_SZ_LOG 9
struct in_device {
struct net_device *dev;
refcount_t refcnt;
int dead;
struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */
struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */
struct ip_mc_list __rcu * __rcu *mc_hash;
int mc_count; /* Number of installed mcasts */
spinlock_t mc_tomb_lock;
struct ip_mc_list *mc_tomb;
unsigned long mr_v1_seen;
unsigned long mr_v2_seen;
unsigned long mr_maxdelay;
unsigned long mr_qi; /* Query Interval */
unsigned long mr_qri; /* Query Response Interval */
unsigned char mr_qrv; /* Query Robustness Variable */
unsigned char mr_gq_running;
u32 mr_ifc_count;
struct timer_list mr_gq_timer; /* general query timer */
struct timer_list mr_ifc_timer; /* interface change timer */
struct neigh_parms *arp_parms;
struct ipv4_devconf cnf;
struct rcu_head rcu_head;
};
#define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1])
#define IPV4_DEVCONF_ALL(net, attr) \
IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr)
static inline int ipv4_devconf_get(struct in_device *in_dev, int index)
{
index--;
return in_dev->cnf.data[index];
}
static inline void ipv4_devconf_set(struct in_device *in_dev, int index,
int val)
{
index--;
set_bit(index, in_dev->cnf.state);
in_dev->cnf.data[index] = val;
}
static inline void ipv4_devconf_setall(struct in_device *in_dev)
{
bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX);
}
#define IN_DEV_CONF_GET(in_dev, attr) \
ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr)
#define IN_DEV_CONF_SET(in_dev, attr, val) \
ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val))
#define IN_DEV_ANDCONF(in_dev, attr) \
(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \
IN_DEV_CONF_GET((in_dev), attr))
#define IN_DEV_NET_ORCONF(in_dev, net, attr) \
(IPV4_DEVCONF_ALL(net, attr) || \
IN_DEV_CONF_GET((in_dev), attr))
#define IN_DEV_ORCONF(in_dev, attr) \
IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr)
#define IN_DEV_MAXCONF(in_dev, attr) \
(max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \
IN_DEV_CONF_GET((in_dev), attr)))
#define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING)
#define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING)
#define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING)
#define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER)
#define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK)
#define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \
ACCEPT_SOURCE_ROUTE)
#define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL)
#define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY)
#define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS)
#define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP)
#define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN)
#define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA)
#define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS)
#define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \
SECURE_REDIRECTS)
#define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG)
#define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID)
#define IN_DEV_PROMOTE_SECONDARIES(in_dev) \
IN_DEV_ORCONF((in_dev), \
PROMOTE_SECONDARIES)
#define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET)
#define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \
IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET)
#define IN_DEV_RX_REDIRECTS(in_dev) \
((IN_DEV_FORWARD(in_dev) && \
IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \
|| (!IN_DEV_FORWARD(in_dev) && \
IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS)))
#define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \
IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN)
#define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER)
#define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_ORCONF((in_dev), ARP_ACCEPT)
#define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE)
#define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE)
#define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY)
#define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \
ARP_EVICT_NOCARRIER)
struct in_ifaddr {
struct hlist_node hash;
struct in_ifaddr __rcu *ifa_next;
struct in_device *ifa_dev;
struct rcu_head rcu_head;
__be32 ifa_local;
__be32 ifa_address;
__be32 ifa_mask;
__u32 ifa_rt_priority;
__be32 ifa_broadcast;
unsigned char ifa_scope;
unsigned char ifa_prefixlen;
__u32 ifa_flags;
char ifa_label[IFNAMSIZ];
/* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */
__u32 ifa_valid_lft;
__u32 ifa_preferred_lft;
unsigned long ifa_cstamp; /* created timestamp */
unsigned long ifa_tstamp; /* updated timestamp */
};
struct in_validator_info {
__be32 ivi_addr;
struct in_device *ivi_dev;
struct netlink_ext_ack *extack;
};
int register_inetaddr_notifier(struct notifier_block *nb);
int unregister_inetaddr_notifier(struct notifier_block *nb);
int register_inetaddr_validator_notifier(struct notifier_block *nb);
int unregister_inetaddr_validator_notifier(struct notifier_block *nb);
void inet_netconf_notify_devconf(struct net *net, int event, int type,
int ifindex, struct ipv4_devconf *devconf);
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
{
return __ip_dev_find(net, addr, true);
}
int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b);
int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *);
#ifdef CONFIG_INET
int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size);
#else
static inline int inet_gifconf(struct net_device *dev, char __user *buf,
int len, int size)
{
return 0;
}
#endif
void devinet_init(void);
struct in_device *inetdev_by_index(struct net *, int);
__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope);
__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst,
__be32 local, int scope);
struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
__be32 mask);
struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr);
static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa)
{
return !((addr^ifa->ifa_address)&ifa->ifa_mask);
}
/*
* Check if a mask is acceptable.
*/
static __inline__ bool bad_mask(__be32 mask, __be32 addr)
{
__u32 hmask;
if (addr & (mask = ~mask))
return true;
hmask = ntohl(mask);
if (hmask & (hmask+1))
return true;
return false;
}
#define in_dev_for_each_ifa_rtnl(ifa, in_dev) \
for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \
ifa = rtnl_dereference(ifa->ifa_next))
#define in_dev_for_each_ifa_rcu(ifa, in_dev) \
for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \
ifa = rcu_dereference(ifa->ifa_next))
static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->ip_ptr);
}
static inline struct in_device *in_dev_get(const struct net_device *dev)
{
struct in_device *in_dev;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (in_dev)
refcount_inc(&in_dev->refcnt);
rcu_read_unlock();
return in_dev;
}
static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev)
{
return rtnl_dereference(dev->ip_ptr);
}
/* called with rcu_read_lock or rtnl held */
static inline bool ip_ignore_linkdown(const struct net_device *dev)
{
struct in_device *in_dev;
bool rc = false;
in_dev = rcu_dereference_rtnl(dev->ip_ptr);
if (in_dev &&
IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
rc = true;
return rc;
}
static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
return in_dev ? in_dev->arp_parms : NULL;
}
void in_dev_finish_destroy(struct in_device *idev);
static inline void in_dev_put(struct in_device *idev)
{
if (refcount_dec_and_test(&idev->refcnt))
in_dev_finish_destroy(idev);
}
#define __in_dev_put(idev) refcount_dec(&(idev)->refcnt)
#define in_dev_hold(idev) refcount_inc(&(idev)->refcnt)
#endif /* __KERNEL__ */
static __inline__ __be32 inet_make_mask(int logmask)
{
if (logmask)
return htonl(~((1U<<(32-logmask))-1));
return 0;
}
static __inline__ int inet_mask_len(__be32 mask)
{
__u32 hmask = ntohl(mask);
if (!hmask)
return 0;
return 32 - ffz(~hmask);
}
#endif /* _LINUX_INETDEVICE_H */