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>

2 files changed, 6 insertions, 0 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 0c071c820e33..6a1ae49809de 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -211,6 +211,9 @@ struct fib_rt_info {
 	int			dst_len;
 	u8			tos;
 	u8			type;
+	u8			offload:1,
+				trap:1,
+				unused:6;
 };
 
 struct fib_entry_notifier_info {
@@ -473,6 +476,7 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap,
 void fib_nh_common_release(struct fib_nh_common *nhc);
 
 /* Exported by fib_trie.c */
+void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri);
 void fib_trie_init(void);
 struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
 
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 1418a8362bb7..cd43321d20dd 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -309,6 +309,8 @@ enum rt_scope_t {
 #define RTM_F_PREFIX		0x800	/* Prefix addresses		*/
 #define RTM_F_LOOKUP_TABLE	0x1000	/* set rtm_table to FIB lookup result */
 #define RTM_F_FIB_MATCH	        0x2000	/* return full fib lookup match */
+#define RTM_F_OFFLOAD		0x4000	/* route is offloaded */
+#define RTM_F_TRAP		0x8000	/* route is trapping packets */
 
 /* Reserved table identifiers */