ipv4: Add "offload" and "trap" indications to routes

When performing L3 offload, routes and nexthops are usually programmed
into two different tables in the underlying device. Therefore, the fact
that a nexthop resides in hardware does not necessarily mean that all
the associated routes also reside in hardware and vice-versa.

While the kernel can signal to user space the presence of a nexthop in
hardware (via 'RTNH_F_OFFLOAD'), it does not have a corresponding flag
for routes. In addition, the fact that a route resides in hardware does
not necessarily mean that the traffic is offloaded. For example,
unreachable routes (i.e., 'RTN_UNREACHABLE') are programmed to trap
packets to the CPU so that the kernel will be able to generate the
appropriate ICMP error packet.

This patch adds an "offload" and "trap" indications to IPv4 routes, so
that users will have better visibility into the offload process.

'struct fib_alias' is extended with two new fields that indicate if the
route resides in hardware or not and if it is offloading traffic from
the kernel or trapping packets to it. Note that the new fields are added
in the 6 bytes hole and therefore the struct still fits in a single
cache line [1].

Capable drivers are expected to invoke fib_alias_hw_flags_set() with the
route's key in order to set the flags.

The indications are dumped to user space via a new flags (i.e.,
'RTM_F_OFFLOAD' and 'RTM_F_TRAP') in the 'rtm_flags' field in the
ancillary header.

v2:
* Make use of 'struct fib_rt_info' in fib_alias_hw_flags_set()

[1]
struct fib_alias {
        struct hlist_node  fa_list;                      /*     0    16 */
        struct fib_info *          fa_info;              /*    16     8 */
        u8                         fa_tos;               /*    24     1 */
        u8                         fa_type;              /*    25     1 */
        u8                         fa_state;             /*    26     1 */
        u8                         fa_slen;              /*    27     1 */
        u32                        tb_id;                /*    28     4 */
        s16                        fa_default;           /*    32     2 */
        u8                         offload:1;            /*    34: 0  1 */
        u8                         trap:1;               /*    34: 1  1 */
        u8                         unused:6;             /*    34: 2  1 */

        /* XXX 5 bytes hole, try to pack */

        struct callback_head rcu __attribute__((__aligned__(8))); /*    40    16 */

        /* size: 56, cachelines: 1, members: 12 */
        /* sum members: 50, holes: 1, sum holes: 5 */
        /* sum bitfield members: 8 bits (1 bytes) */
        /* forced alignments: 1, forced holes: 1, sum forced holes: 5 */
        /* last cacheline: 56 bytes */
} __attribute__((__aligned__(8)));

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 81 insertions, 0 deletions

diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index a4b829358bfa..c092e9a55790 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -16,6 +16,9 @@ struct fib_alias {
 	u8			fa_slen;
 	u32			tb_id;
 	s16			fa_default;
+	u8			offload:1,
+				trap:1,
+				unused:6;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3ed1349be428..a803cdd9400a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -519,6 +519,8 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 	fri.dst_len = dst_len;
 	fri.tos = fa->fa_tos;
 	fri.type = fa->fa_type;
+	fri.offload = fa->offload;
+	fri.trap = fa->trap;
 	err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
@@ -1801,6 +1803,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 	}
 
+	if (fri->offload)
+		rtm->rtm_flags |= RTM_F_OFFLOAD;
+	if (fri->trap)
+		rtm->rtm_flags |= RTM_F_TRAP;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 75af3f8ae50e..6ce1f2bbffd0 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1012,6 +1012,52 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen,
 	return NULL;
 }
 
+static struct fib_alias *
+fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
+{
+	u8 slen = KEYLENGTH - fri->dst_len;
+	struct key_vector *l, *tp;
+	struct fib_table *tb;
+	struct fib_alias *fa;
+	struct trie *t;
+
+	tb = fib_get_table(net, fri->tb_id);
+	if (!tb)
+		return NULL;
+
+	t = (struct trie *)tb->tb_data;
+	l = fib_find_node(t, &tp, be32_to_cpu(fri->dst));
+	if (!l)
+		return NULL;
+
+	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		if (fa->fa_slen == slen && fa->tb_id == fri->tb_id &&
+		    fa->fa_tos == fri->tos && fa->fa_info == fri->fi &&
+		    fa->fa_type == fri->type)
+			return fa;
+	}
+
+	return NULL;
+}
+
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
+{
+	struct fib_alias *fa_match;
+
+	rcu_read_lock();
+
+	fa_match = fib_find_matching_alias(net, fri);
+	if (!fa_match)
+		goto out;
+
+	fa_match->offload = fri->offload;
+	fa_match->trap = fri->trap;
+
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set);
+
 static void trie_rebalance(struct trie *t, struct key_vector *tn)
 {
 	while (!IS_TRIE(tn))
@@ -1220,6 +1266,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 			new_fa->fa_slen = fa->fa_slen;
 			new_fa->tb_id = tb->tb_id;
 			new_fa->fa_default = -1;
+			new_fa->offload = 0;
+			new_fa->trap = 0;
 
 			hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
 
@@ -1278,6 +1326,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 	new_fa->fa_slen = slen;
 	new_fa->tb_id = tb->tb_id;
 	new_fa->fa_default = -1;
+	new_fa->offload = 0;
+	new_fa->trap = 0;
 
 	/* Insert new entry to the list. */
 	err = fib_insert_alias(t, tp, l, new_fa, fa, key);
@@ -2202,6 +2252,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 				fri.dst_len = KEYLENGTH - fa->fa_slen;
 				fri.tos = fa->fa_tos;
 				fri.type = fa->fa_type;
+				fri.offload = fa->offload;
+				fri.trap = fa->trap;
 				err = fib_dump_info(skb,
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 167a7357d12a..2010888e68ca 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3237,6 +3237,25 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		fri.dst_len = res.prefixlen;
 		fri.tos = fl4.flowi4_tos;
 		fri.type = rt->rt_type;
+		fri.offload = 0;
+		fri.trap = 0;
+		if (res.fa_head) {
+			struct fib_alias *fa;
+
+			hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) {
+				u8 slen = 32 - fri.dst_len;
+
+				if (fa->fa_slen == slen &&
+				    fa->tb_id == fri.tb_id &&
+				    fa->fa_tos == fri.tos &&
+				    fa->fa_info == res.fi &&
+				    fa->fa_type == fri.type) {
+					fri.offload = fa->offload;
+					fri.trap = fa->trap;
+					break;
+				}
+			}
+		}
 		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
 				    nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0);
 	} else {