Merge branch 'mlxsw-Add-support-for-offloading-IPv4-multicast-routes'

Jiri Pirko says:

====================
mlxsw: Add support for offloading IPv4 multicast routes

Yotam says:

This patch-set introduces offloading of the kernel IPv4 multicast router
logic in the Spectrum driver.

The first patch makes the Spectrum driver ignore FIB notifications that are
not of address family IPv4 or IPv6. This is needed in order to prevent
crashes while the next patches introduce the RTNL_FAMILY_IPMR FIB
notifications.

Patches 2-5 update ipmr to use the FIB notification chain for both MFC and
VIF notifications, and patches 8-12 update the Spectrum driver to register
to these notifications and offload the routes.

Similarly to IPv4 and IPv6, any failure will trigger the abort mechanism
which is updated in this patch-set to eject multicast route tables too.

At this stage, the following limitations apply:
 - A multicast MFC route will be offloaded by the driver if all the output
   interfaces are Spectrum router interfaces (RIFs). In any other case
   (which includes pimreg device, tunnel devices and management ports) the
   route will be trapped to the CPU and the packets will be forwarded by
   software.
 - ipmr proxy routes are not supported and will trigger the abort
   mechanism.
 - The MFC TTL values are currently treated as boolean: if the value is
   different than 255, the traffic is forwarded to the interface and if the
   value is 255 it is not forwarded. Dropping packets based on their TTL isn't
   currently supported.

To allow users to have visibility on which of the routes are offloaded and
which are not, patch 6 introduces a per-route offload indication similar to
IPv4 and IPv6 routes which is sent to the user via the RTNetlink interface.

The Spectrum driver multicast router offloading support, which is
introduced in patches 8 and 9, is divided into two parts:
 - The hardware logic which abstracts the Spectrum hardware and provides a
   simple API for the upper levels.
 - The offloading logic which gets the MFC and VIF notifications from the
   kernel and updates the hardware using the hardware logic part.

Finally, the last patch makes the Spectrum router logic not ignore the
multicast FIB notifications and call the corresponding functions in the
multicast router offloading logic.

---
v2->v3:
 - Move the ipmr_rule_default function definition to be inside the already
   existing CONFIG_IP_MROUTE_MULTIPLE_TABLES ifdef block (patch 6)
 - Remove double =0 initialization in spectrum_mr.c (patch 7)
 - Fix route4 allocation size (patch 7)
v1->v2:
 - Add comments for struct fields in mroute.h
 - Take the mrt_lock while dumping VIFs in the fib_notifier dump callback
 - Update the MFC lastuse field too
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 208 insertions, 5 deletions

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c9b3e6e069ae..292a8e80bdfa 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -264,6 +264,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
 	rtnl_unlock();
 }
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, RTNL_FAMILY_IPMR);
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
 #else
 #define ipmr_for_each_table(mrt, net) \
 	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
@@ -298,6 +314,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 	net->ipv4.mrt = NULL;
 	rtnl_unlock();
 }
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return 0;
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+	return 0;
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
 #endif
 
 static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -587,6 +619,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 }
 #endif
 
+static int call_ipmr_vif_entry_notifier(struct notifier_block *nb,
+					struct net *net,
+					enum fib_event_type event_type,
+					struct vif_device *vif,
+					vifi_t vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_vif_entry_notifiers(struct net *net,
+					 enum fib_event_type event_type,
+					 struct vif_device *vif,
+					 vifi_t vif_index, u32 tb_id)
+{
+	struct vif_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.dev = vif->dev,
+		.vif_index = vif_index,
+		.vif_flags = vif->flags,
+		.tb_id = tb_id,
+	};
+
+	ASSERT_RTNL();
+	net->ipv4.ipmr_seq++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb,
+					struct net *net,
+					enum fib_event_type event_type,
+					struct mfc_cache *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifiers(struct net *net,
+					 enum fib_event_type event_type,
+					 struct mfc_cache *mfc, u32 tb_id)
+{
+	struct mfc_entry_notifier_info info = {
+		.info = {
+			.family = RTNL_FAMILY_IPMR,
+			.net = net,
+		},
+		.mfc = mfc,
+		.tb_id = tb_id
+	};
+
+	ASSERT_RTNL();
+	net->ipv4.ipmr_seq++;
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 /**
  *	vif_delete - Delete a VIF entry
  *	@notify: Set to 1, if the caller is a notifier_call
@@ -594,6 +702,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 		      struct list_head *head)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct vif_device *v;
 	struct net_device *dev;
 	struct in_device *in_dev;
@@ -603,6 +712,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 
 	v = &mrt->vif_table[vifi];
 
+	if (VIF_EXISTS(mrt, vifi))
+		call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi,
+					      mrt->id);
+
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
 	v->dev = NULL;
@@ -652,10 +765,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head)
 	kmem_cache_free(mrt_cachep, c);
 }
 
-static inline void ipmr_cache_free(struct mfc_cache *c)
+void ipmr_cache_free(struct mfc_cache *c)
 {
 	call_rcu(&c->rcu, ipmr_cache_free_rcu);
 }
+EXPORT_SYMBOL(ipmr_cache_free);
 
 /* Destroy an unresolved cache entry, killing queued skbs
  * and reporting error to netlink readers.
@@ -851,6 +965,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 	if (vifi+1 > mrt->maxvif)
 		mrt->maxvif = vifi+1;
 	write_unlock_bh(&mrt_lock);
+	call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id);
 	return 0;
 }
 
@@ -949,6 +1064,7 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 	if (c) {
 		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+		refcount_set(&c->mfc_un.res.refcount, 1);
 	}
 	return c;
 }
@@ -1150,6 +1266,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
 
 static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c;
 
 	/* The entries are added/deleted only under RTNL */
@@ -1161,8 +1278,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 		return -ENOENT;
 	rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
 	list_del_rcu(&c->list);
+	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_DELROUTE);
-	ipmr_cache_free(c);
+	ipmr_cache_put(c);
 
 	return 0;
 }
@@ -1189,6 +1307,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
+		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c,
+					      mrt->id);
 		mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 		return 0;
 	}
@@ -1238,6 +1358,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		ipmr_cache_resolve(net, mrt, uc, c);
 		ipmr_cache_free(uc);
 	}
+	call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id);
 	mroute_netlink_event(mrt, c, RTM_NEWROUTE);
 	return 0;
 }
@@ -1245,6 +1366,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 /* Close the multicast socket, and clear the vif tables etc */
 static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c, *tmp;
 	LIST_HEAD(list);
 	int i;
@@ -1263,8 +1385,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 			continue;
 		rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
 		list_del_rcu(&c->list);
+		call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c,
+					      mrt->id);
 		mroute_netlink_event(mrt, c, RTM_DELROUTE);
-		ipmr_cache_free(c);
+		ipmr_cache_put(c);
 	}
 
 	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
@@ -2156,6 +2280,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	    nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
 		return -EMSGSIZE;
 
+	if (c->mfc_flags & MFC_OFFLOAD)
+		rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
 	if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH)))
 		return -EMSGSIZE;
 
@@ -3048,14 +3175,87 @@ static const struct net_protocol pim_protocol = {
 };
 #endif
 
+static unsigned int ipmr_seq_read(struct net *net)
+{
+	ASSERT_RTNL();
+
+	return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
+}
+
+static int ipmr_dump(struct net *net, struct notifier_block *nb)
+{
+	struct mr_table *mrt;
+	int err;
+
+	err = ipmr_rules_dump(net, nb);
+	if (err)
+		return err;
+
+	ipmr_for_each_table(mrt, net) {
+		struct vif_device *v = &mrt->vif_table[0];
+		struct mfc_cache *mfc;
+		int vifi;
+
+		/* Notifiy on table VIF entries */
+		read_lock(&mrt_lock);
+		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+			if (!v->dev)
+				continue;
+
+			call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
+						     v, vifi, mrt->id);
+		}
+		read_unlock(&mrt_lock);
+
+		/* Notify on table MFC entries */
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+			call_ipmr_mfc_entry_notifier(nb, net,
+						     FIB_EVENT_ENTRY_ADD, mfc,
+						     mrt->id);
+	}
+
+	return 0;
+}
+
+static const struct fib_notifier_ops ipmr_notifier_ops_template = {
+	.family		= RTNL_FAMILY_IPMR,
+	.fib_seq_read	= ipmr_seq_read,
+	.fib_dump	= ipmr_dump,
+	.owner		= THIS_MODULE,
+};
+
+int __net_init ipmr_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
+
+	net->ipv4.ipmr_seq = 0;
+
+	ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	net->ipv4.ipmr_notifier_ops = ops;
+
+	return 0;
+}
+
+static void __net_exit ipmr_notifier_exit(struct net *net)
+{
+	fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops);
+	net->ipv4.ipmr_notifier_ops = NULL;
+}
+
 /* Setup for IP multicast routing */
 static int __net_init ipmr_net_init(struct net *net)
 {
 	int err;
 
+	err = ipmr_notifier_init(net);
+	if (err)
+		goto ipmr_notifier_fail;
+
 	err = ipmr_rules_init(net);
 	if (err < 0)
-		goto fail;
+		goto ipmr_rules_fail;
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
@@ -3072,7 +3272,9 @@ proc_cache_fail:
 proc_vif_fail:
 	ipmr_rules_exit(net);
 #endif
-fail:
+ipmr_rules_fail:
+	ipmr_notifier_exit(net);
+ipmr_notifier_fail:
 	return err;
 }
 
@@ -3082,6 +3284,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	remove_proc_entry("ip_mr_cache", net->proc_net);
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 #endif
+	ipmr_notifier_exit(net);
 	ipmr_rules_exit(net);
 }