Merge branch 'mlxsw-identical-routes-handling'

Jiri Pirko says:

====================
mlxsw: Identical routes handling

Ido says:

The kernel can store several FIB aliases that share the same prefix and
length. These aliases can differ in other parameters such as TOS and
metric, which are taken into account during lookup.

Offloading devices might not have the same flexibility, allowing only a
single route with the same prefix and length to be reflected. mlxsw is
one such device.

This patchset aims to correctly handle this situation in the mlxsw
driver. The first four patches introduce small changes in the IPv4 FIB
code, so that listeners of the FIB notification chain will be able to
correctly handle identical routes.

The last three patches build on top of previous work and introduce the
necessary changes in the mlxsw driver. The biggest change is the
introduction of a FIB node, where identical routes are chained, instead
of a primitive reference counting. This is explained in detail in the
fifth patch.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip_fib.h

@@ -211,7 +211,6 @@ struct fib_entry_notifier_info {
 	u8 tos;
 	u8 type;
 	u32 tb_id;
-	u32 nlflags;
 };
 
 struct fib_nh_notifier_info {
@@ -220,6 +219,8 @@ struct fib_nh_notifier_info {
 };
 
 enum fib_event_type {
+	FIB_EVENT_ENTRY_REPLACE,
+	FIB_EVENT_ENTRY_APPEND,
 	FIB_EVENT_ENTRY_ADD,
 	FIB_EVENT_ENTRY_DEL,
 	FIB_EVENT_RULE_ADD,

net/ipv4/fib_trie.c

@@ -124,7 +124,7 @@ static void fib_notify(struct net *net, struct notifier_block *nb,
 static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 				   enum fib_event_type event_type, u32 dst,
 				   int dst_len, struct fib_info *fi,
-				   u8 tos, u8 type, u32 tb_id, u32 nlflags)
+				   u8 tos, u8 type, u32 tb_id)
 {
 	struct fib_entry_notifier_info info = {
 		.dst = dst,
@@ -133,7 +133,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 		.tos = tos,
 		.type = type,
 		.tb_id = tb_id,
-		.nlflags = nlflags,
 	};
 	return call_fib_notifier(nb, net, event_type, &info.info);
 }
@@ -197,7 +196,7 @@ int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
 static int call_fib_entry_notifiers(struct net *net,
 				    enum fib_event_type event_type, u32 dst,
 				    int dst_len, struct fib_info *fi,
-				    u8 tos, u8 type, u32 tb_id, u32 nlflags)
+				    u8 tos, u8 type, u32 tb_id)
 {
 	struct fib_entry_notifier_info info = {
 		.dst = dst,
@@ -206,7 +205,6 @@ static int call_fib_entry_notifiers(struct net *net,
 		.tos = tos,
 		.type = type,
 		.tb_id = tb_id,
-		.nlflags = nlflags,
 	};
 	return call_fib_notifiers(net, event_type, &info.info);
 }
@@ -1198,6 +1196,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 int fib_table_insert(struct net *net, struct fib_table *tb,
 		     struct fib_config *cfg)
 {
+	enum fib_event_type event = FIB_EVENT_ENTRY_ADD;
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct fib_alias *fa, *new_fa;
 	struct key_vector *l, *tp;
@@ -1295,6 +1294,13 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 			new_fa->tb_id = tb->tb_id;
 			new_fa->fa_default = -1;
 
+			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
+						 key, plen, fi,
+						 new_fa->fa_tos, cfg->fc_type,
+						 tb->tb_id);
+			rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
+				  tb->tb_id, &cfg->fc_nlinfo, nlflags);
+
 			hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
 
 			alias_free_mem_rcu(fa);
@@ -1303,13 +1309,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 			if (state & FA_S_ACCESSED)
 				rt_cache_flush(cfg->fc_nlinfo.nl_net);
 
-			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_ADD,
-						 key, plen, fi,
-						 new_fa->fa_tos, cfg->fc_type,
-						 tb->tb_id, cfg->fc_nlflags);
-			rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
-				tb->tb_id, &cfg->fc_nlinfo, nlflags);
-
 			goto succeeded;
 		}
 		/* Error if we find a perfect match which
@@ -1319,11 +1318,13 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 		if (fa_match)
 			goto out;
 
-		if (cfg->fc_nlflags & NLM_F_APPEND)
+		if (cfg->fc_nlflags & NLM_F_APPEND) {
+			event = FIB_EVENT_ENTRY_APPEND;
 			nlflags |= NLM_F_APPEND;
-		else
+		} else {
 			fa = fa_first;
 		}
+	}
 	err = -ENOENT;
 	if (!(cfg->fc_nlflags & NLM_F_CREATE))
 		goto out;
@@ -1351,8 +1352,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 		tb->tb_num_default++;
 
 	rt_cache_flush(cfg->fc_nlinfo.nl_net);
-	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, key, plen, fi, tos,
-				 cfg->fc_type, tb->tb_id, cfg->fc_nlflags);
+	call_fib_entry_notifiers(net, event, key, plen, fi, tos, cfg->fc_type,
+				 tb->tb_id);
 	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
 		  &cfg->fc_nlinfo, nlflags);
 succeeded:
@@ -1653,8 +1654,8 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
 		return -ESRCH;
 
 	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
-				 fa_to_delete->fa_info, tos, cfg->fc_type,
-				 tb->tb_id, 0);
+				 fa_to_delete->fa_info, tos,
+				 fa_to_delete->fa_type, tb->tb_id);
 	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 
@@ -1963,7 +1964,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
 			struct fib_info *fi = fa->fa_info;
 
-			if (!fi || !(fi->fib_flags & RTNH_F_DEAD)) {
+			if (!fi || !(fi->fib_flags & RTNH_F_DEAD) ||
+			    tb->tb_id != fa->tb_id) {
 				slen = fa->fa_slen;
 				continue;
 			}
@@ -1972,7 +1974,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 						 n->key,
 						 KEYLENGTH - fa->fa_slen,
 						 fi, fa->fa_tos, fa->fa_type,
-						 tb->tb_id, 0);
+						 tb->tb_id);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);
@@ -2012,7 +2014,7 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
 
 		call_fib_entry_notifier(nb, net, event_type, l->key,
 					KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
-					fa->fa_type, fa->tb_id, 0);
+					fa->fa_type, fa->tb_id);
 	}
 }