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>

1 files changed, 13 insertions, 5 deletions

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 5e636365d33c..42c9c62d3417 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -112,6 +112,7 @@ static int dn_dst_gc(struct dst_ops *ops);
 static struct dst_entry *dn_dst_check(struct dst_entry *, __u32);
 static unsigned int dn_dst_default_advmss(const struct dst_entry *dst);
 static unsigned int dn_dst_default_mtu(const struct dst_entry *dst);
+static void dn_dst_destroy(struct dst_entry *);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
 static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu);
@@ -133,11 +134,18 @@ static struct dst_ops dn_dst_ops = {
 	.check =		dn_dst_check,
 	.default_advmss =	dn_dst_default_advmss,
 	.default_mtu =		dn_dst_default_mtu,
+	.cow_metrics =		dst_cow_metrics_generic,
+	.destroy =		dn_dst_destroy,
 	.negative_advice =	dn_dst_negative_advice,
 	.link_failure =		dn_dst_link_failure,
 	.update_pmtu =		dn_dst_update_pmtu,
 };
 
+static void dn_dst_destroy(struct dst_entry *dst)
+{
+	dst_destroy_metrics_generic(dst);
+}
+
 static __inline__ unsigned dn_hash(__le16 src, __le16 dst)
 {
 	__u16 tmp = (__u16 __force)(src ^ dst);
@@ -814,14 +822,14 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res)
 {
 	struct dn_fib_info *fi = res->fi;
 	struct net_device *dev = rt->dst.dev;
+	unsigned int mss_metric;
 	struct neighbour *n;
-	unsigned int metric;
 
 	if (fi) {
 		if (DN_FIB_RES_GW(*res) &&
 		    DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
 			rt->rt_gateway = DN_FIB_RES_GW(*res);
-		dst_import_metrics(&rt->dst, fi->fib_metrics);
+		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
 	}
 	rt->rt_type = res->type;
 
@@ -834,10 +842,10 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res)
 
 	if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu)
 		dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu);
-	metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS);
-	if (metric) {
+	mss_metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS);
+	if (mss_metric) {
 		unsigned int mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst));
-		if (metric > mss)
+		if (mss_metric > mss)
 			dst_metric_set(&rt->dst, RTAX_ADVMSS, mss);
 	}
 	return 0;