[PATCH Round 5 0/3] Network Event Notifier Mechanism

[PATCH Round 5 0/3] Network Event Notifier Mechanism

[Steve Wise]

Dave/Roland, is this patchset about ready to go?

Round 5 Changes:

- removed user-mode support
- removed route add/del events.

------

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, and path MTU changes.

RDMA devices need these network events because they typically
cache this information in hardware and need to be notified
when it changes.  To learn about RDMA internet protocols, see:
http://www.ietf.org/html.charters/rddp-charter.html.

The key events of interest are:

- neighbour mac address change 
- routing redirect (the next hop neighbour changes for a dst_entry)
- path mtu change (the path mtu for a dst_entry changes).

This patchset consists of 3 patches:

1) New files implementing the Network Event Notifier
2) Core network changes to generate netevents
3) Cleanup ib_addr modules to use the netevent patch

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>

[PATCH Round 5 1/3] Network Event Notifier Mechanism.

[Steve Wise]

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 |   33 +++++++++++++++++++++++
 net/core/netevent.c    |   69 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+), 0 deletions(-)

diff --git a/include/net/netevent.h b/include/net/netevent.h
new file mode 100644
index 0000000..e5d2162
--- /dev/null
+++ b/include/net/netevent.h
@@ -0,0 +1,33 @@
+#ifndef _NET_EVENT_H
+#define _NET_EVENT_H
+
+/*
+ *	Generic netevent notifiers
+ *
+ *	Authors:
+ *      Tom Tucker              <tom@opengridcomputing.com>
+ *      Steve Wise              <swise@opengridcomputing.com>
+ *
+ * 	Changes:
+ */
+#ifdef __KERNEL__
+
+#include <net/dst.h>
+
+struct netevent_redirect {
+	struct dst_entry *old;
+	struct dst_entry *new;
+};
+
+enum netevent_notif_type {
+	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
+	NETEVENT_PMTU_UPDATE,	   /* arg is struct dst_entry ptr */
+	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
+};
+
+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
diff --git a/net/core/netevent.c b/net/core/netevent.c
new file mode 100644
index 0000000..35d02c3
--- /dev/null
+++ b/net/core/netevent.c
@@ -0,0 +1,69 @@
+/*
+ *	Network event notifiers
+ *
+ *	Authors:
+ *      Tom Tucker             <tom@opengridcomputing.com>
+ *      Steve Wise             <swise@opengridcomputing.com>
+ *
+ *	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.
+ *
+ *	Fixes:
+ */
+
+#include <linux/rtnetlink.h>
+#include <linux/notifier.h>
+
+static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain);
+
+/**
+ *	register_netevent_notifier - register a netevent notifier block
+ *	@nb: notifier
+ *
+ *	Register a notifier to be called when a netevent occurs.
+ *	The notifier passed is linked into the kernel structures and must
+ *	not be reused until it has been unregistered. A negative errno code
+ *	is returned on a failure.
+ */
+int register_netevent_notifier(struct notifier_block *nb)
+{
+	int err;
+
+	err = atomic_notifier_chain_register(&netevent_notif_chain, nb);
+	return err;
+}
+
+/**
+ *	netevent_unregister_notifier - unregister a netevent notifier block
+ *	@nb: notifier
+ *
+ *	Unregister a notifier previously registered by
+ *	register_neigh_notifier(). The notifier is unlinked into the
+ *	kernel structures and may then be reused. A negative errno code
+ *	is returned on a failure.
+ */
+
+int unregister_netevent_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&netevent_notif_chain, nb);
+}
+
+/**
+ *	call_netevent_notifiers - call all netevent notifier blocks
+ *      @val: value passed unmodified to notifier function
+ *      @v:   pointer passed unmodified to notifier function
+ *
+ *	Call all neighbour notifier blocks.  Parameters and return value
+ *	are as for notifier_call_chain().
+ */
+
+int call_netevent_notifiers(unsigned long val, void *v)
+{
+	return atomic_notifier_call_chain(&netevent_notif_chain, val, v);
+}
+
+EXPORT_SYMBOL_GPL(register_netevent_notifier);
+EXPORT_SYMBOL_GPL(unregister_netevent_notifier);
+EXPORT_SYMBOL_GPL(call_netevent_notifiers);

[PATCH Round 5 2/3] Core net changes to generate netevents

[Steve Wise]

Generate netevents for:
- neighbour changes
- routing redirects
- pmtu changes
---

 net/core/Makefile    |    2 +-
 net/core/neighbour.c |   14 ++++++++------
 net/ipv4/route.c     |    8 ++++++++
 net/ipv6/route.c     |    7 +++++++
 4 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/net/core/Makefile b/net/core/Makefile
index e9bd246..2645ba4 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -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
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7ad681f..5130d2e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -29,6 +29,7 @@ #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>
@@ -754,6 +755,7 @@ #endif
 			neigh->nud_state = NUD_STALE;
 			neigh->updated = jiffies;
 			neigh_suspect(neigh);
+			notify = 1;
 		}
 	} else if (state & NUD_DELAY) {
 		if (time_before_eq(now, 
@@ -762,6 +764,7 @@ #endif
 			neigh->nud_state = NUD_REACHABLE;
 			neigh->updated = jiffies;
 			neigh_connect(neigh);
+			notify = 1;
 			next = neigh->confirmed + neigh->parms->reachable_time;
 		} else {
 			NEIGH_PRINTK2("neigh %p is probed.\n", neigh);
@@ -819,6 +822,8 @@ #endif
 out:
 		write_unlock(&neigh->lock);
 	}
+	if (notify)
+		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
 
 #ifdef CONFIG_ARPD
 	if (notify && neigh->parms->app_probes)
@@ -926,9 +931,7 @@ int neigh_update(struct neighbour *neigh
 {
 	u8 old;
 	int err;
-#ifdef CONFIG_ARPD
 	int notify = 0;
-#endif
 	struct net_device *dev;
 	int update_isrouter = 0;
 
@@ -948,9 +951,7 @@ #endif
 			neigh_suspect(neigh);
 		neigh->nud_state = new;
 		err = 0;
-#ifdef CONFIG_ARPD
 		notify = old & NUD_VALID;
-#endif
 		goto out;
 	}
 
@@ -1022,9 +1023,7 @@ #endif
 		if (!(new & NUD_CONNECTED))
 			neigh->confirmed = jiffies -
 				      (neigh->parms->base_reachable_time << 1);
-#ifdef CONFIG_ARPD
 		notify = 1;
-#endif
 	}
 	if (new == old)
 		goto out;
@@ -1056,6 +1055,9 @@ out:
 			(neigh->flags & ~NTF_ROUTER);
 	}
 	write_unlock_bh(&neigh->lock);
+
+	if (notify)
+		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
 #ifdef CONFIG_ARPD
 	if (notify && neigh->parms->app_probes)
 		neigh_app_notify(neigh);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2dc6dbb..19bd49d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -104,6 +104,7 @@ #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
@@ -1125,6 +1126,7 @@ void ip_rt_redirect(u32 old_gw, u32 dadd
 	struct rtable *rth, **rthp;
 	u32  skeys[2] = { saddr, 0 };
 	int  ikeys[2] = { dev->ifindex, 0 };
+	struct netevent_redirect netevent;
 
 	if (!in_dev)
 		return;
@@ -1216,6 +1218,11 @@ void ip_rt_redirect(u32 old_gw, u32 dadd
 					rt_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))
@@ -1452,6 +1459,7 @@ static void ip_rt_update_pmtu(struct dst
 		}
 		dst->metrics[RTAX_MTU-1] = mtu;
 		dst_set_expires(dst, ip_rt_mtu_expires);
+		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
 	}
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 87c39c9..4b16371 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -53,6 +53,7 @@ #include <net/tcp.h>
 #include <linux/rtnetlink.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
+#include <net/netevent.h>
 
 #include <asm/uaccess.h>
 
@@ -742,6 +743,7 @@ static void ip6_rt_update_pmtu(struct ds
 			dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
 		}
 		dst->metrics[RTAX_MTU-1] = mtu;
+		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
 	}
 }
 
@@ -1155,6 +1157,7 @@ void rt6_redirect(struct in6_addr *dest,
 	struct rt6_info *rt, *nrt = NULL;
 	int strict;
 	struct fib6_node *fn;
+	struct netevent_redirect netevent;
 
 	/*
 	 * Get the "current" route for this destination and
@@ -1252,6 +1255,10 @@ restart:
 	if (ip6_ins_rt(nrt, NULL, NULL, NULL))
 		goto out;
 
+	netevent.old = &rt->u.dst;
+	netevent.new = &nrt->u.dst;
+	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
+
 	if (rt->rt6i_flags&RTF_CACHE) {
 		ip6_del_rt(rt, NULL, NULL, NULL);
 		return;

[PATCH Round 5 3/3] Cleanup ib_addr module to use the netevents

[Steve Wise]

---

 drivers/infiniband/core/addr.c |   30 ++++++++++++++----------------
 1 files changed, 14 insertions(+), 16 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index d294bbc..1205e80 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -35,6 +35,7 @@ #include <linux/if_arp.h>
 #include <net/arp.h>
 #include <net/neighbour.h>
 #include <net/route.h>
+#include <net/netevent.h>
 #include <rdma/ib_addr.h>
 
 MODULE_AUTHOR("Sean Hefty");
@@ -326,25 +327,22 @@ void rdma_addr_cancel(struct rdma_dev_ad
 }
 EXPORT_SYMBOL(rdma_addr_cancel);
 
-static int addr_arp_recv(struct sk_buff *skb, struct net_device *dev,
-			 struct packet_type *pkt, struct net_device *orig_dev)
+static int netevent_callback(struct notifier_block *self, unsigned long event, 
+	void *ctx)
 {
-	struct arphdr *arp_hdr;
+	if (event == NETEVENT_NEIGH_UPDATE) {  
+		struct neighbour *neigh = ctx;
 
-	arp_hdr = (struct arphdr *) skb->nh.raw;
-
-	if (arp_hdr->ar_op == htons(ARPOP_REQUEST) ||
-	    arp_hdr->ar_op == htons(ARPOP_REPLY))
-		set_timeout(jiffies);
-
-	kfree_skb(skb);
+		if (neigh->dev->type == ARPHRD_INFINIBAND &&
+		    (neigh->nud_state & NUD_VALID)) {
+			set_timeout(jiffies);
+		}
+	}
 	return 0;
 }
 
-static struct packet_type addr_arp = {
-	.type           = __constant_htons(ETH_P_ARP),
-	.func           = addr_arp_recv,
-	.af_packet_priv = (void*) 1,
+static struct notifier_block nb = {
+	.notifier_call = netevent_callback
 };
 
 static int addr_init(void)
@@ -353,13 +351,13 @@ static int addr_init(void)
 	if (!addr_wq)
 		return -ENOMEM;
 
-	dev_add_pack(&addr_arp);
+	register_netevent_notifier(&nb);
 	return 0;
 }
 
 static void addr_cleanup(void)
 {
-	dev_remove_pack(&addr_arp);
+	unregister_netevent_notifier(&nb);
 	destroy_workqueue(addr_wq);
 }
 

Re: [PATCH Round 5 0/3] Network Event Notifier Mechanism

[David Miller]

From: Steve Wise <swise@opengridcomputing.com>
Date: Fri, 28 Jul 2006 13:28:49 -0500

> Dave/Roland, is this patchset about ready to go?

All 3 patches applied, thanks Steve.