net: Implement read-only protection and COW'ing of metrics.

Routing metrics are now copy-on-write.

Initially a route entry points it's metrics at a read-only location.
If a routing table entry exists, it will point there.  Else it will
point at the all zero metric place-holder called 'dst_default_metrics'.

The writeability state of the metrics is stored in the low bits of the
metrics pointer, we have two bits left to spare if we want to store
more states.

For the initial implementation, COW is implemented simply via kmalloc.
However future enhancements will change this to place the writable
metrics somewhere else, in order to increase sharing.  Very likely
this "somewhere else" will be the inetpeer cache.

Note also that this means that metrics updates may transiently fail
if we cannot COW the metrics successfully.

But even by itself, this patch should decrease memory usage and
increase cache locality especially for routing workloads.  In those
cases the read-only metric copies stay in place and never get written
to.

TCP workloads where metrics get updated, and those rare cases where
PMTU triggers occur, will take a very slight performance hit.  But
that hit will be alleviated when the long-term writable metrics
move to a more sharable location.

Since the metrics storage went from a u32 array of RTAX_MAX entries to
what is essentially a pointer, some retooling of the dst_entry layout
was necessary.

Most importantly, we need to preserve the alignment of the reference
count so that it doesn't share cache lines with the read-mostly state,
as per Eric Dumazet's alignment assertion checks.

The only non-trivial bit here is the move of the 'flags' member into
the writeable cacheline.  This is OK since we are always accessing the
flags around the same moment when we made a modification to the
reference count.

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 14 insertions, 3 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1534508f6c68..45fafa018f12 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -105,6 +105,7 @@ static struct dst_ops ip6_dst_ops_template = {
 	.check			=	ip6_dst_check,
 	.default_advmss		=	ip6_default_advmss,
 	.default_mtu		=	ip6_default_mtu,
+	.cow_metrics		=	dst_cow_metrics_generic,
 	.destroy		=	ip6_dst_destroy,
 	.ifdown			=	ip6_dst_ifdown,
 	.negative_advice	=	ip6_negative_advice,
@@ -125,6 +126,10 @@ static struct dst_ops ip6_dst_blackhole_ops = {
 	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
 };
 
+static const u32 ip6_template_metrics[RTAX_MAX] = {
+	[RTAX_HOPLIMIT - 1] = 255,
+};
+
 static struct rt6_info ip6_null_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
@@ -193,6 +198,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		rt->rt6i_idev = NULL;
 		in6_dev_put(idev);
 	}
+	dst_destroy_metrics_generic(dst);
 	if (peer) {
 		BUG_ON(!(rt->rt6i_flags & RTF_CACHE));
 		rt->rt6i_peer = NULL;
@@ -2681,7 +2687,8 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_null_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_null_entry;
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-	dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255);
+	dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
+			 ip6_template_metrics, true);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
@@ -2692,7 +2699,8 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_prohibit_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
 	net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-	dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255);
+	dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
+			 ip6_template_metrics, true);
 
 	net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
 					       sizeof(*net->ipv6.ip6_blk_hole_entry),
@@ -2702,7 +2710,8 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_blk_hole_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
 	net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-	dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255);
+	dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
+			 ip6_template_metrics, true);
 #endif
 
 	net->ipv6.sysctl.flush_delay = 0;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index da87428681cc..834dc02f1d4f 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -220,6 +220,7 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
+	dst_destroy_metrics_generic(dst);
 	if (likely(xdst->u.rt6.rt6i_peer))
 		inet_putpeer(xdst->u.rt6.rt6i_peer);
 	xfrm_dst_destroy(xdst);
@@ -257,6 +258,7 @@ static struct dst_ops xfrm6_dst_ops = {
 	.protocol =		cpu_to_be16(ETH_P_IPV6),
 	.gc =			xfrm6_garbage_collect,
 	.update_pmtu =		xfrm6_update_pmtu,
+	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm6_dst_destroy,
 	.ifdown =		xfrm6_dst_ifdown,
 	.local_out =		__ip6_local_out,