Network Event Notifier Mechanism
Subsystems (2)
cover Network Event Notifier Mechanism
This patch implements a mechanism that allows interested clients to register for notification of certain network events. The intended use is to allow RDMA devices (linux/drivers/infiniband) to be notified of neighbour updates, ICMP redirects, path MTU changes, and route changes.
The reason these devices need update events is because they typically cache this information in hardware and need to be notified when this information has been updated.
This approach is one of many possibilities and may be preferred because it uses an existing notification mechanism that has precedent in the stack. An alternative would be to add a netdev method to notify affect devices of these events.
This code does not yet implement path MTU change because the number of places in which this value is updated is large and if this mechanism seems reasonable, it would be probably be best to funnel these updates through a single function.
We would like to get this or similar functionality included in 2.6.19 and request comments.
This patchset consists of 2 patches:
1) New files implementing the Network Event Notifier
2) Core network changes to generate network event notifications
PATCH 1/2 Network Event Notifier Mechanism.
This patch uses notifier blocks to implement a network event notifier mechanism.
Clients register their callback function by calling register_netevent_notifier() like this:
static struct notifier_block nb = {
.notifier_call = my_callback_func
};
...
register_netevent_notifier(&nb);
---
include/net/netevent.h | 41 +++++++++++++++++++++++++++++ net/core/netevent.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 108 insertions(+), 0 deletions(-)
include/net/netevent.h new file +41 -0
@@ -0,0 +1,41 @@ +#ifndef _NET_EVENT_H +#define _NET_EVENT_H + +/* +* Generic netevent notifiers +* +* Authors: +* Tom Tucker <[email protected]> +* +* Changes: +*/ + +#ifdef __KERNEL__ + +#include <net/dst.h> + +struct netevent_redirect { +struct dst_entry *old; +struct dst_entry *new; +}; + +struct netevent_route_change { +int event; +struct fib_info *fib_info; +}; + +enum netevent_notif_type { +NETEVENT_NEIGH_UPDATE =1 ,/* arg is * struct neighbour */ +NETEVENT_ROUTE_UPDATE ,/* arg is * netevent_route_change */ +NETEVENT_PMTU_UPDATE , +NETEVENT_REDIRECT ,/* arg is * struct netevent_redirect */ +}; + +extern int register_netevent_notifier (struct notifier_block *nb); +extern int unregister_netevent_notifier (struct notifier_block *nb); +extern int call_netevent_notifiers (unsigned long val,void *v); + +#endif +#endif + +
net/core/netevent.c new file +67 -0
67 lines not on this page · raw message
PATCH 2/2 Core network changes to support network event notification.
In reply to Steve WiseThis patch adds event calls for neighbour change, route update, and routing redirect events.
TODO: PMTU change events.
---
net/core/Makefile | 2 +- net/core/neighbour.c | 8 ++++++++ net/ipv4/fib_semantics.c | 7 +++++++ net/ipv4/route.c | 6 ++++++ 4 files changed, 22 insertions(+), 1 deletions(-)
net/core/Makefile +1 -1
@@ -7,7 +7,7 @@ obj-y := sock.o request_sock.o skbuff.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o \ +obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o obj-$(CONFIG_XFRM) += flow.o
net/core/neighbour.c +8 -0
@@ -30,9 +30,11 @@ #include <linux/times.h>#include <net/neighbour.h> #include <net/dst.h> #include <net/sock.h> +#include <net/netevent.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> +#include <linux/notifier.h> #define NEIGH_DEBUG 1
@@ -755,6 +757,7 @@ #endif neigh->nud_state =NUD_STALE ; neigh->updated = jiffies;neigh_suspect (neigh); +call_netevent_notifiers (NETEVENT_NEIGH_UPDATE , neigh); } }else if (state &NUD_DELAY ) { if (time_before_eq(now,
@@ -763,6 +766,7 @@ #endif neigh->nud_state =NUD_REACHABLE ; neigh->updated = jiffies;neigh_connect (neigh); +call_netevent_notifiers (NETEVENT_NEIGH_UPDATE , neigh); next = neigh->confirmed + neigh->parms->reachable_time; }else {NEIGH_PRINTK2 ("neigh %p is probed.\n" , neigh);
@@ -783,6 +787,7 @@ #endif neigh->nud_state =NUD_FAILED ; neigh->updated = jiffies; notify =1 ; +call_netevent_notifiers (NETEVENT_NEIGH_UPDATE , neigh);NEIGH_CACHE_STAT_INC (neigh->tbl, res_failed);NEIGH_PRINTK2 ("neigh %p is failed.\n" , neigh);
@@ -1056,6 +1061,9 @@ out: (neigh->flags | NTF_ROUTER) : (neigh->flags & ~NTF_ROUTER ); } + +call_netevent_notifiers (NETEVENT_NEIGH_UPDATE , neigh); +write_unlock_bh (&neigh->lock);#ifdef CONFIG_ARPD if (notify && neigh->parms->app_probes)
net/ipv4/fib_semantics.c +7 -0
@@ -45,6 +45,7 @@ #include <net/tcp.h>#include <net/sock.h> #include <net/ip_fib.h> #include <net/ip_mp_alg.h> +#include <net/netevent.h> #include "fib_lookup.h"
@@ -278,9 +279,15 @@ void rtmsg_fib(int event, u32 key, struc struct nlmsghdr *n, struct netlink_skb_parms *req) { struct sk_buff *skb; +struct netevent_route_change rev; +u32 pid = req ? req->pid : n->nlmsg_pid;int size =NLMSG_SPACE (sizeof (struct rtmsg )+256 ); + rev.event = event; + rev.fib_info = fa->fa_info; +call_netevent_notifiers (NETEVENT_ROUTE_UPDATE , &rev); + skb =alloc_skb (size,GFP_KERNEL );if (!skb)return ;
net/ipv4/route.c +6 -0
@@ -105,6 +105,7 @@ #include <net/tcp.h>#include <net/icmp.h> #include <net/xfrm.h> #include <net/ip_mp_alg.h> +#include <net/netevent.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif
@@ -1120,6 +1121,7 @@ void ip_rt_redirect(u32 old_gw, u32 daddstruct rtable *rth, **rthp;u32 skeys[2 ] = { saddr,0 };int ikeys[2 ] = { dev->ifindex,0 }; +struct netevent_redirect netevent;if (!in_dev)return ;
@@ -1211,6 +1213,10 @@ void ip_rt_redirect(u32 old_gw, u32 daddrt_drop (rt); goto do_next; } + + netevent.old = &rth->u.dst; + netevent.new = &rt->u.dst; +call_netevent_notifiers (NETEVENT_REDIRECT , &netevent);rt_del (hash, rth);if (!rt_intern_hash (hash, rt, &rt))
David Miller
maintainerMost of the folks capable of reviewing networking changes listen in on the [email protected] mailing list, not here.
Thanks.