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, 13 insertions, 14 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b05c23b05a9f..919f2ad19b49 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -168,8 +168,11 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
         struct fib_result res = { 0 };
         struct net_device *dev = NULL;
 
-        if (fib_lookup(net, &fl, &res))
+        rcu_read_lock();
+        if (fib_lookup(net, &fl, &res)) {
+                rcu_read_unlock();
                 return NULL;
+        }
         if (res.type != RTN_LOCAL)
                 goto out;
         dev = FIB_RES_DEV(res);
@@ -177,7 +180,7 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
         if (dev && devref)
                 dev_hold(dev);
 out:
-        fib_res_put(&res);
+        rcu_read_unlock();
         return dev;
 }
 EXPORT_SYMBOL(__ip_dev_find);
@@ -207,11 +210,12 @@ static inline unsigned __inet_dev_addr_type(struct net *net,
         local_table = fib_get_table(net, RT_TABLE_LOCAL);
         if (local_table) {
                 ret = RTN_UNICAST;
-                if (!fib_table_lookup(local_table, &fl, &res)) {
+                rcu_read_lock();
+                if (!fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) {
                         if (!dev || dev == res.fi->fib_dev)
                                 ret = res.type;
-                        fib_res_put(&res);
                 }
+                rcu_read_unlock();
         }
         return ret;
 }
@@ -235,6 +239,7 @@ EXPORT_SYMBOL(inet_dev_addr_type);
  * - figure out what "logical" interface this packet arrived
  *   and calculate "specific destination" address.
  * - check, that packet arrived from expected physical interface.
+ * called with rcu_read_lock()
  */
 int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
                         struct net_device *dev, __be32 *spec_dst,
@@ -259,7 +264,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
         struct net *net;
 
         no_addr = rpf = accept_local = 0;
-        rcu_read_lock();
         in_dev = __in_dev_get_rcu(dev);
         if (in_dev) {
                 no_addr = in_dev->ifa_list == NULL;
@@ -268,7 +272,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
                 if (mark && !IN_DEV_SRC_VMARK(in_dev))
                         fl.mark = 0;
         }
-        rcu_read_unlock();
 
         if (in_dev == NULL)
                 goto e_inval;
@@ -278,7 +281,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
                 goto last_resort;
         if (res.type != RTN_UNICAST) {
                 if (res.type != RTN_LOCAL || !accept_local)
-                        goto e_inval_res;
+                        goto e_inval;
         }
         *spec_dst = FIB_RES_PREFSRC(res);
         fib_combine_itag(itag, &res);
@@ -299,10 +302,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 #endif
         if (dev_match) {
                 ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
-                fib_res_put(&res);
                 return ret;
         }
-        fib_res_put(&res);
         if (no_addr)
                 goto last_resort;
         if (rpf == 1)
@@ -315,7 +316,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
                         *spec_dst = FIB_RES_PREFSRC(res);
                         ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
                 }
-                fib_res_put(&res);
         }
         return ret;
 
@@ -326,8 +326,6 @@ last_resort:
         *itag = 0;
         return 0;
 
-e_inval_res:
-        fib_res_put(&res);
 e_inval:
         return -EINVAL;
 e_rpf:
@@ -873,15 +871,16 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
                 local_bh_disable();
 
                 frn->tb_id = tb->tb_id;
-                frn->err = fib_table_lookup(tb, &fl, &res);
+                rcu_read_lock();
+                frn->err = fib_table_lookup(tb, &fl, &res, FIB_LOOKUP_NOREF);
 
                 if (!frn->err) {
                         frn->prefixlen = res.prefixlen;
                         frn->nh_sel = res.nh_sel;
                         frn->type = res.type;
                         frn->scope = res.scope;
-                        fib_res_put(&res);
                 }
+                rcu_read_unlock();
                 local_bh_enable();
         }
 }