From 44713b67db10c774f14280c129b0d5fd13c70cf2 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 4 Mar 2011 21:24:47 -0800
Subject: [PATCH] ipv4: Optimize flow initialization in output route lookup.
We burn a lot of useless cycles, cpu store buffer traffic, and
memory operations memset()'ing the on-stack flow used to perform
output route lookups in __ip_route_output_key().
Only the first half of the flow object members even matter for
output route lookups in this context, specifically:
FIB rules matching cares about:
dst, src, tos, iif, oif, mark
FIB trie lookup cares about:
dst
FIB semantic match cares about:
tos, scope, oif
Therefore only initialize these specific members and elide the
memset entirely.
On Niagara2 this kills about ~300 cycles from the output route
lookup path.
Likely, we can take things further, since all callers of output
route lookups essentially throw away the on-stack flow they use.
So they don't care if we use it as a scratch-pad to compute the
final flow key.
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/ipv4/route.c | 18 ++++++++++--------
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 432eee645648..6c8740362ef9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2431,14 +2431,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
const struct flowi *oldflp)
{
u32 tos = RT_FL_TOS(oldflp);
- struct flowi fl = { .fl4_dst = oldflp->fl4_dst,
- .fl4_src = oldflp->fl4_src,
- .fl4_tos = tos & IPTOS_RT_MASK,
- .fl4_scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK : RT_SCOPE_UNIVERSE),
- .mark = oldflp->mark,
- .iif = net->loopback_dev->ifindex,
- .oif = oldflp->oif };
+ struct flowi fl;
struct fib_result res;
unsigned int flags = 0;
struct net_device *dev_out = NULL;
@@ -2449,6 +2442,15 @@ static struct rtable *ip_route_output_slow(struct net *net,
res.r = NULL;
#endif
+ fl.oif = oldflp->oif;
+ fl.iif = net->loopback_dev->ifindex;
+ fl.mark = oldflp->mark;
+ fl.fl4_dst = oldflp->fl4_dst;
+ fl.fl4_src = oldflp->fl4_src;
+ fl.fl4_tos = tos & IPTOS_RT_MASK;
+ fl.fl4_scope = ((tos & RTO_ONLINK) ?
+ RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+
rcu_read_lock();
if (oldflp->fl4_src) {
rth = ERR_PTR(-EINVAL);
--
GitLab