Merge branch 'mlxsw-vrf'

Jiri Pirko says:

====================
mlxsw: Enable VRF offload

Ido says:

Packets received from netdevs enslaved to different VRF devices are
forwarded using different FIB tables. In the Spectrum ASIC this is
achieved by binding different router interfaces (RIFs) to different
virtual routers (VRs). Each RIF represents an enslaved netdev and each
VR has its own FIB table according to which packets are forwarded.

The first three patches add an helper to check if a FIB rule is a
default rule and extend the FIB notification chain to include the rule's
info as part of the RULE_{ADD,DEL} events. This allows offloading
drivers to sanitize the rules they don't support and flush their tables.

The fourth patch introduces a small change in the VRF driver to allow
capable drivers to more easily offload VRFs.

Finally, the last patches gradually add support for VRFs in the mlxsw
driver. First, on top of port netdevs, stacked LAG and VLAN devices and
then on top of bridges.

Some limitations I would like to point out:

1) The old model where 'oif' / 'iif' rules were programmed for each L3
master device isn't supported. Upon insertion of these rules the driver
will flush its tables and forwarding will be done by the kernel instead.
It's inferior in every way to the single 'l3mdev' rule, so this shouldn't
be an issue.

2) Inter-VRF routes pointing to a VRF device aren't offloaded. Packets
hitting these routes will be forwarded by the kernel. Inter-VRF routes
pointing to netdevs enslaved to a different VRF are offloaded.

3) There's a small discrepancy between the kernel's datapath and the
device's. By default, packets forwarded by the kernel first do a lookup
in the local table and then in the VRF's table (assuming no match). In
the device, lookup is done only in the VRF's table, which is probably
the intended behavior. Changes in v2 allow user to properly re-order the
default rules without triggering the abort mechanism.

Changes in v3:
* Remove 'l3mdev' from the matchall list, as it's related to the action
  and not the selector (David Ahern).
* Use container_of() instead of typecasting (David Ahern).
* Add David's Acked-by to the second patch.
* Add an helper in IPv4 code to check if rule is a default rule (David
  Ahern).

Changes in v2:
* Drop default rule indication and allow re-ordering of default rules
  (David Ahern).
* Remove ifdef around 'struct fib_rule_notifier_info' and drop redundant
  dependency on IP_MULTIPLE_TABLES from rocker and mlxsw.
* Add David's Acked-by to the fourth patch.
* Remove netif_is_vrf_master() and use netif_is_l3_master() instead
  (David Ahern).
====================

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

2 files changed, 59 insertions, 8 deletions

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b6791d94841d..816e3ccb0ec9 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = {
 	KUIDT_INIT(~0),
 };
 
+bool fib_rule_matchall(const struct fib_rule *rule)
+{
+	if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
+	    rule->flags)
+		return false;
+	if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
+		return false;
+	if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
+	    !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib_rule_matchall);
+
 int fib_default_rule_add(struct fib_rules_ops *ops,
 			 u32 pref, u32 table, u32 flags)
 {
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 289210903d58..778ecf977eb2 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,6 +47,27 @@ struct fib4_rule {
 #endif
 };
 
+static bool fib4_rule_matchall(const struct fib_rule *rule)
+{
+	struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
+
+	if (r->dst_len || r->src_len || r->tos)
+		return false;
+	return fib_rule_matchall(rule);
+}
+
+bool fib4_rule_default(const struct fib_rule *rule)
+{
+	if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+	    rule->l3mdev)
+		return false;
+	if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
+	    rule->table != RT_TABLE_DEFAULT)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib4_rule_default);
+
 int __fib_lookup(struct net *net, struct flowi4 *flp,
 		 struct fib_result *res, unsigned int flags)
 {
@@ -164,20 +185,36 @@ static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
+static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
+				  enum fib_event_type event_type,
+				  struct fib_rule *rule)
+{
+	struct fib_rule_notifier_info info = {
+		.rule = rule,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
 static int call_fib_rule_notifiers(struct net *net,
-				   enum fib_event_type event_type)
+				   enum fib_event_type event_type,
+				   struct fib_rule *rule)
 {
-	struct fib_notifier_info info;
+	struct fib_rule_notifier_info info = {
+		.rule = rule,
+	};
 
-	return call_fib_notifiers(net, event_type, &info);
+	return call_fib_notifiers(net, event_type, &info.info);
 }
 
+/* Called with rcu_read_lock() */
 void fib_rules_notify(struct net *net, struct notifier_block *nb)
 {
-	struct fib_notifier_info info;
+	struct fib_rules_ops *ops = net->ipv4.rules_ops;
+	struct fib_rule *rule;
 
-	if (net->ipv4.fib_has_custom_rules)
-		call_fib_notifier(nb, net, FIB_EVENT_RULE_ADD, &info);
+	list_for_each_entry_rcu(rule, &ops->rules_list, list)
+		call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule);
 }
 
 static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
@@ -236,7 +273,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule);
 
 	err = 0;
 errout:
@@ -258,7 +295,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule);
 errout:
 	return err;
 }