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, 16 insertions, 5 deletions

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ba52f399a89..0f80dfc2f7f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -148,6 +148,13 @@ static const struct
 
 /* Release a nexthop info record */
 
+static void free_fib_info_rcu(struct rcu_head *head)
+{
+	struct fib_info *fi = container_of(head, struct fib_info, rcu);
+
+	kfree(fi);
+}
+
 void free_fib_info(struct fib_info *fi)
 {
 	if (fi->fib_dead == 0) {
@@ -161,7 +168,7 @@ void free_fib_info(struct fib_info *fi)
 	} endfor_nexthops(fi);
 	fib_info_cnt--;
 	release_net(fi->fib_net);
-	kfree(fi);
+	call_rcu(&fi->rcu, free_fib_info_rcu);
 }
 
 void fib_release_info(struct fib_info *fi)
@@ -553,6 +560,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			nh->nh_scope = RT_SCOPE_LINK;
 			return 0;
 		}
+		rcu_read_lock();
 		{
 			struct flowi fl = {
 				.nl_u = {
@@ -568,8 +576,10 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			if (fl.fl4_scope < RT_SCOPE_LINK)
 				fl.fl4_scope = RT_SCOPE_LINK;
 			err = fib_lookup(net, &fl, &res);
-			if (err)
+			if (err) {
+				rcu_read_unlock();
 				return err;
+			}
 		}
 		err = -EINVAL;
 		if (res.type != RTN_UNICAST && res.type != RTN_LOCAL)
@@ -585,7 +595,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			goto out;
 		err = 0;
 out:
-		fib_res_put(&res);
+		rcu_read_unlock();
 		return err;
 	} else {
 		struct in_device *in_dev;
@@ -879,7 +889,7 @@ failure:
 
 /* Note! fib_semantic_match intentionally uses  RCU list functions. */
 int fib_semantic_match(struct list_head *head, const struct flowi *flp,
-		       struct fib_result *res, int prefixlen)
+		       struct fib_result *res, int prefixlen, int fib_flags)
 {
 	struct fib_alias *fa;
 	int nh_sel = 0;
@@ -943,7 +953,8 @@ out_fill_res:
 	res->type = fa->fa_type;
 	res->scope = fa->fa_scope;
 	res->fi = fa->fa_info;
-	atomic_inc(&res->fi->fib_clntref);
+	if (!(fib_flags & FIB_LOOKUP_NOREF))
+		atomic_inc(&res->fi->fib_clntref);
 	return 0;
 }