diff mbox

[net-next,1/6] fib: introduce FIB notification infrastructure

Message ID 1474458794-5512-2-git-send-email-jiri@resnulli.us
State Changes Requested, archived
Delegated to: David Miller
Headers show

Commit Message

Jiri Pirko Sept. 21, 2016, 11:53 a.m. UTC 
From: Jiri Pirko <jiri@mellanox.com>

This allows to pass information about added/deleted FIB entries/rules to
whoever is interested. This is done in a very similar way as devinet
notifies address additions/removals.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
 include/net/ip_fib.h    | 34 ++++++++++++++++++++++++---
 net/ipv4/fib_frontend.c | 16 ++++++-------
 net/ipv4/fib_rules.c    | 10 ++++++++
 net/ipv4/fib_trie.c     | 62 ++++++++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 108 insertions(+), 14 deletions(-)

Comments

Ido Schimmel Sept. 22, 2016, 5:13 a.m. UTC | #1 
On Wed, Sep 21, 2016 at 01:53:09PM +0200, Jiri Pirko wrote:
> From: Jiri Pirko <jiri@mellanox.com>
> 
> This allows to pass information about added/deleted FIB entries/rules to
> whoever is interested. This is done in a very similar way as devinet
> notifies address additions/removals.
> 
> Signed-off-by: Jiri Pirko <jiri@mellanox.com>

[...]

>  #include <linux/slab.h>
>  #include <linux/export.h>
>  #include <linux/vmalloc.h>
> +#include <linux/notifier.h>
>  #include <net/net_namespace.h>
>  #include <net/ip.h>
>  #include <net/protocol.h>
> @@ -84,6 +85,44 @@
>  #include <trace/events/fib.h>
>  #include "fib_lookup.h"
>  
> +static BLOCKING_NOTIFIER_HEAD(fib_chain);
> +
> +int register_fib_notifier(struct notifier_block *nb)
> +{
> +	return blocking_notifier_chain_register(&fib_chain, nb);
> +}
> +EXPORT_SYMBOL(register_fib_notifier);

If we remove and insert the switch driver, then the existing FIB entries
should be replayed when we register our notification block. Otherwise,
all of these entries will be missing from the switch's tables. I believe
it should be handled like register_netdevice_notifier(), where
"registration and up events are replayed".
Jiri Pirko Sept. 22, 2016, 9:43 a.m. UTC | #2 
Thu, Sep 22, 2016 at 07:13:50AM CEST, idosch@idosch.org wrote:
>On Wed, Sep 21, 2016 at 01:53:09PM +0200, Jiri Pirko wrote:
>> From: Jiri Pirko <jiri@mellanox.com>
>> 
>> This allows to pass information about added/deleted FIB entries/rules to
>> whoever is interested. This is done in a very similar way as devinet
>> notifies address additions/removals.
>> 
>> Signed-off-by: Jiri Pirko <jiri@mellanox.com>
>
>[...]
>
>>  #include <linux/slab.h>
>>  #include <linux/export.h>
>>  #include <linux/vmalloc.h>
>> +#include <linux/notifier.h>
>>  #include <net/net_namespace.h>
>>  #include <net/ip.h>
>>  #include <net/protocol.h>
>> @@ -84,6 +85,44 @@
>>  #include <trace/events/fib.h>
>>  #include "fib_lookup.h"
>>  
>> +static BLOCKING_NOTIFIER_HEAD(fib_chain);
>> +
>> +int register_fib_notifier(struct notifier_block *nb)
>> +{
>> +	return blocking_notifier_chain_register(&fib_chain, nb);
>> +}
>> +EXPORT_SYMBOL(register_fib_notifier);
>
>If we remove and insert the switch driver, then the existing FIB entries
>should be replayed when we register our notification block. Otherwise,
>all of these entries will be missing from the switch's tables. I believe
>it should be handled like register_netdevice_notifier(), where
>"registration and up events are replayed".

Agreed. This patchset does not change this behaviour as the original
switchdev solution has the same "ordering" issue. We should take care of
it as a part of yours ordering patchsets.
diff mbox

Patch

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 7d4a72e..116a9c0 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -22,6 +22,7 @@ 
 #include <net/fib_rules.h>
 #include <net/inetpeer.h>
 #include <linux/percpu.h>
+#include <linux/notifier.h>
 
 struct fib_config {
 	u8			fc_dst_len;
@@ -185,6 +186,33 @@  __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
 #define FIB_RES_PREFSRC(net, res)	((res).fi->fib_prefsrc ? : \
 					 FIB_RES_SADDR(net, res))
 
+struct fib_notifier_info {
+	struct net *net;
+};
+
+struct fib_entry_notifier_info {
+	struct fib_notifier_info info; /* must be first */
+	u32 dst;
+	int dst_len;
+	struct fib_info *fi;
+	u8 tos;
+	u8 type;
+	u32 tb_id;
+	u32 nlflags;
+};
+
+enum fib_event_type {
+	FIB_EVENT_ENTRY_ADD,
+	FIB_EVENT_ENTRY_DEL,
+	FIB_EVENT_RULE_ADD,
+	FIB_EVENT_RULE_DEL,
+};
+
+int register_fib_notifier(struct notifier_block *nb);
+int unregister_fib_notifier(struct notifier_block *nb);
+int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
+		       struct fib_notifier_info *info);
+
 struct fib_table {
 	struct hlist_node	tb_hlist;
 	u32			tb_id;
@@ -196,11 +224,11 @@  struct fib_table {
 
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags);
-int fib_table_insert(struct fib_table *, struct fib_config *);
-int fib_table_delete(struct fib_table *, struct fib_config *);
+int fib_table_insert(struct net *, struct fib_table *, struct fib_config *);
+int fib_table_delete(struct net *, struct fib_table *, struct fib_config *);
 int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 		   struct netlink_callback *cb);
-int fib_table_flush(struct fib_table *table);
+int fib_table_flush(struct net *net, struct fib_table *table);
 struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
 void fib_table_flush_external(struct fib_table *table);
 void fib_free_table(struct fib_table *tb);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4e56a4c..86c43dc 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -182,7 +182,7 @@  static void fib_flush(struct net *net)
 		struct fib_table *tb;
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
-			flushed += fib_table_flush(tb);
+			flushed += fib_table_flush(net, tb);
 	}
 
 	if (flushed)
@@ -590,13 +590,13 @@  int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 			if (cmd == SIOCDELRT) {
 				tb = fib_get_table(net, cfg.fc_table);
 				if (tb)
-					err = fib_table_delete(tb, &cfg);
+					err = fib_table_delete(net, tb, &cfg);
 				else
 					err = -ESRCH;
 			} else {
 				tb = fib_new_table(net, cfg.fc_table);
 				if (tb)
-					err = fib_table_insert(tb, &cfg);
+					err = fib_table_insert(net, tb, &cfg);
 				else
 					err = -ENOBUFS;
 			}
@@ -719,7 +719,7 @@  static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = fib_table_delete(tb, &cfg);
+	err = fib_table_delete(net, tb, &cfg);
 errout:
 	return err;
 }
@@ -741,7 +741,7 @@  static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 	}
 
-	err = fib_table_insert(tb, &cfg);
+	err = fib_table_insert(net, tb, &cfg);
 errout:
 	return err;
 }
@@ -828,9 +828,9 @@  static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad
 		cfg.fc_scope = RT_SCOPE_HOST;
 
 	if (cmd == RTM_NEWROUTE)
-		fib_table_insert(tb, &cfg);
+		fib_table_insert(net, tb, &cfg);
 	else
-		fib_table_delete(tb, &cfg);
+		fib_table_delete(net, tb, &cfg);
 }
 
 void fib_add_ifaddr(struct in_ifaddr *ifa)
@@ -1254,7 +1254,7 @@  static void ip_fib_net_exit(struct net *net)
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
 			hlist_del(&tb->tb_hlist);
-			fib_table_flush(tb);
+			fib_table_flush(net, tb);
 			fib_free_table(tb);
 		}
 	}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 770bebe..ebadf6b 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -164,6 +164,14 @@  static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
+static int call_fib_rule_notifiers(struct net *net,
+				   enum fib_event_type event_type)
+{
+	struct fib_notifier_info info;
+
+	return call_fib_notifiers(net, event_type, &info);
+}
+
 static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
 	FRA_GENERIC_POLICY,
 	[FRA_FLOW]	= { .type = NLA_U32 },
@@ -221,6 +229,7 @@  static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 
 	net->ipv4.fib_has_custom_rules = true;
 	fib_flush_external(rule->fr_net);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD);
 
 	err = 0;
 errout:
@@ -243,6 +252,7 @@  static int fib4_rule_delete(struct fib_rule *rule)
 #endif
 	net->ipv4.fib_has_custom_rules = true;
 	fib_flush_external(rule->fr_net);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL);
 errout:
 	return err;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 241f27b..51a4537 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -73,6 +73,7 @@ 
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/vmalloc.h>
+#include <linux/notifier.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/protocol.h>
@@ -84,6 +85,44 @@ 
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
+static BLOCKING_NOTIFIER_HEAD(fib_chain);
+
+int register_fib_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&fib_chain, nb);
+}
+EXPORT_SYMBOL(register_fib_notifier);
+
+int unregister_fib_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&fib_chain, nb);
+}
+EXPORT_SYMBOL(unregister_fib_notifier);
+
+int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
+		       struct fib_notifier_info *info)
+{
+	info->net = net;
+	return blocking_notifier_call_chain(&fib_chain, event_type, info);
+}
+
+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)
+{
+	struct fib_entry_notifier_info info = {
+		.dst = dst,
+		.dst_len = dst_len,
+		.fi = fi,
+		.tos = tos,
+		.type = type,
+		.tb_id = tb_id,
+		.nlflags = nlflags,
+	};
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
 #define MAX_STAT_DEPTH 32
 
 #define KEYLENGTH	(8*sizeof(t_key))
@@ -1076,7 +1115,8 @@  static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 }
 
 /* Caller must hold RTNL. */
-int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_insert(struct net *net, struct fib_table *tb,
+		     struct fib_config *cfg)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct fib_alias *fa, *new_fa;
@@ -1193,6 +1233,11 @@  int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			fib_release_info(fi_drop);
 			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);
 
@@ -1245,6 +1290,8 @@  int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 		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);
 	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
 		  &cfg->fc_nlinfo, nlflags);
 succeeded:
@@ -1490,7 +1537,8 @@  static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 }
 
 /* Caller must hold RTNL. */
-int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_delete(struct net *net, struct fib_table *tb,
+		     struct fib_config *cfg)
 {
 	struct trie *t = (struct trie *) tb->tb_data;
 	struct fib_alias *fa, *fa_to_delete;
@@ -1546,6 +1594,9 @@  int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 	switchdev_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
 			       cfg->fc_type, tb->tb_id);
 
+	call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen,
+				 fa_to_delete->fa_info, tos, cfg->fc_type,
+				 tb->tb_id, 0);
 	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
 		  &cfg->fc_nlinfo, 0);
 
@@ -1809,7 +1860,7 @@  void fib_table_flush_external(struct fib_table *tb)
 }
 
 /* Caller must hold RTNL. */
-int fib_table_flush(struct fib_table *tb)
+int fib_table_flush(struct net *net, struct fib_table *tb)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *pn = t->kv;
@@ -1861,6 +1912,11 @@  int fib_table_flush(struct fib_table *tb)
 			switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen,
 					       fi, fa->fa_tos, fa->fa_type,
 					       tb->tb_id);
+			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL,
+						 n->key,
+						 KEYLENGTH - fa->fa_slen,
+						 fi, fa->fa_tos, fa->fa_type,
+						 tb->tb_id, 0);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);