fib: RCU conversion of fib_lookup()

fib_lookup() converted to be called in RCU protected context, no
reference taken and released on a contended cache line (fib_clntref)

fib_table_lookup() and fib_semantic_match() get an additional parameter.

struct fib_info gets an rcu_head field, and is freed after an rcu grace
period.

Stress test :
(Sending 160.000.000 UDP frames on same neighbour,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_HASH) (about same results for FIB_TRIE)

Before patch :

real	1m31.199s
user	0m13.761s
sys	23m24.780s

After patch:

real	1m5.375s
user	0m14.997s
sys	15m50.115s

Before patch Profile :

13044.00 15.4% __ip_route_output_key vmlinux
 8438.00 10.0% dst_destroy           vmlinux
 5983.00  7.1% fib_semantic_match    vmlinux
 5410.00  6.4% fib_rules_lookup      vmlinux
 4803.00  5.7% neigh_lookup          vmlinux
 4420.00  5.2% _raw_spin_lock        vmlinux
 3883.00  4.6% rt_set_nexthop        vmlinux
 3261.00  3.9% _raw_read_lock        vmlinux
 2794.00  3.3% fib_table_lookup      vmlinux
 2374.00  2.8% neigh_resolve_output  vmlinux
 2153.00  2.5% dst_alloc             vmlinux
 1502.00  1.8% _raw_read_lock_bh     vmlinux
 1484.00  1.8% kmem_cache_alloc      vmlinux
 1407.00  1.7% eth_header            vmlinux
 1406.00  1.7% ipv4_dst_destroy      vmlinux
 1298.00  1.5% __copy_from_user_ll   vmlinux
 1174.00  1.4% dev_queue_xmit        vmlinux
 1000.00  1.2% ip_output             vmlinux

After patch Profile :

13712.00 15.8% dst_destroy             vmlinux
 8548.00  9.9% __ip_route_output_key   vmlinux
 7017.00  8.1% neigh_lookup            vmlinux
 4554.00  5.3% fib_semantic_match      vmlinux
 4067.00  4.7% _raw_read_lock          vmlinux
 3491.00  4.0% dst_alloc               vmlinux
 3186.00  3.7% neigh_resolve_output    vmlinux
 3103.00  3.6% fib_table_lookup        vmlinux
 2098.00  2.4% _raw_read_lock_bh       vmlinux
 2081.00  2.4% kmem_cache_alloc        vmlinux
 2013.00  2.3% _raw_spin_lock          vmlinux
 1763.00  2.0% __copy_from_user_ll     vmlinux
 1763.00  2.0% ip_output               vmlinux
 1761.00  2.0% ipv4_dst_destroy        vmlinux
 1631.00  1.9% eth_header              vmlinux
 1440.00  1.7% _raw_read_unlock_bh     vmlinux

Reference results, if IP route cache is enabled :

real	0m29.718s
user	0m10.845s
sys	7m37.341s

25213.00 29.5% __ip_route_output_key   vmlinux
 9011.00 10.5% dst_release             vmlinux
 4817.00  5.6% ip_push_pending_frames  vmlinux
 4232.00  5.0% ip_finish_output        vmlinux
 3940.00  4.6% udp_sendmsg             vmlinux
 3730.00  4.4% __copy_from_user_ll     vmlinux
 3716.00  4.4% ip_route_output_flow    vmlinux
 2451.00  2.9% __xfrm_lookup           vmlinux
 2221.00  2.6% ip_append_data          vmlinux
 1718.00  2.0% _raw_spin_lock_bh       vmlinux
 1655.00  1.9% __alloc_skb             vmlinux
 1572.00  1.8% sock_wfree              vmlinux
 1345.00  1.6% kfree                   vmlinux

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 5 insertions, 5 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index a96e5ec211a..271c89bdf04 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1342,7 +1342,7 @@ err:
 /* should be called with rcu_read_lock */
 static int check_leaf(struct trie *t, struct leaf *l,
 		      t_key key,  const struct flowi *flp,
-		      struct fib_result *res)
+		      struct fib_result *res, int fib_flags)
 {
 	struct leaf_info *li;
 	struct hlist_head *hhead = &l->list;
@@ -1356,7 +1356,7 @@ static int check_leaf(struct trie *t, struct leaf *l,
 		if (l->key != (key & ntohl(mask)))
 			continue;
 
-		err = fib_semantic_match(&li->falh, flp, res, plen);
+		err = fib_semantic_match(&li->falh, flp, res, plen, fib_flags);
 
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 		if (err <= 0)
@@ -1372,7 +1372,7 @@ static int check_leaf(struct trie *t, struct leaf *l,
 }
 
 int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
-		     struct fib_result *res)
+		     struct fib_result *res, int fib_flags)
 {
 	struct trie *t = (struct trie *) tb->tb_data;
 	int ret;
@@ -1399,7 +1399,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
 
 	/* Just a leaf? */
 	if (IS_LEAF(n)) {
-		ret = check_leaf(t, (struct leaf *)n, key, flp, res);
+		ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags);
 		goto found;
 	}
 
@@ -1424,7 +1424,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
 		}
 
 		if (IS_LEAF(n)) {
-			ret = check_leaf(t, (struct leaf *)n, key, flp, res);
+			ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags);
 			if (ret > 0)
 				goto backtrace;
 			goto found;