net: dst: Prevent false sharing vs. dst_entry:: __refcnt

dst_entry::__refcnt is highly contended in scenarios where many connections
happen from and to the same IP. The reference count is an atomic_t, so the
reference count operations have to take the cache-line exclusive.

Aside of the unavoidable reference count contention there is another
significant problem which is caused by that: False sharing.

perf top identified two affected read accesses. dst_entry::lwtstate and
rtable::rt_genid.

dst_entry:__refcnt is located at offset 64 of dst_entry, which puts it into
a seperate cacheline vs. the read mostly members located at the beginning
of the struct.

That prevents false sharing vs. the struct members in the first 64
bytes of the structure, but there is also

  dst_entry::lwtstate

which is located after the reference count and in the same cache line. This
member is read after a reference count has been acquired.

struct rtable embeds a struct dst_entry at offset 0. struct dst_entry has a
size of 112 bytes, which means that the struct members of rtable which
follow the dst member share the same cache line as dst_entry::__refcnt.
Especially

  rtable::rt_genid

is also read by the contexts which have a reference count acquired
already.

When dst_entry:__refcnt is incremented or decremented via an atomic
operation these read accesses stall. This was found when analysing the
memtier benchmark in 1:100 mode, which amplifies the problem extremly.

Move the rt[6i]_uncached[_list] members out of struct rtable and struct
rt6_info into struct dst_entry to provide padding and move the lwtstate
member after that so it ends up in the same cache line.

The resulting improvement depends on the micro-architecture and the number
of CPUs. It ranges from +20% to +120% with a localhost memtier/memcached
benchmark.

[ tglx: Rearrange struct ]

Signed-off-by: Wangyang Guo <wangyang.guo@intel.com>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230323102800.042297517@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 12 insertions, 12 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a0a0bb452e9..2a3d14d95ada 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1508,20 +1508,20 @@ void rt_add_uncached_list(struct rtable *rt)
 {
 	struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
 
-	rt->rt_uncached_list = ul;
+	rt->dst.rt_uncached_list = ul;
 
 	spin_lock_bh(&ul->lock);
-	list_add_tail(&rt->rt_uncached, &ul->head);
+	list_add_tail(&rt->dst.rt_uncached, &ul->head);
 	spin_unlock_bh(&ul->lock);
 }
 
 void rt_del_uncached_list(struct rtable *rt)
 {
-	if (!list_empty(&rt->rt_uncached)) {
-		struct uncached_list *ul = rt->rt_uncached_list;
+	if (!list_empty(&rt->dst.rt_uncached)) {
+		struct uncached_list *ul = rt->dst.rt_uncached_list;
 
 		spin_lock_bh(&ul->lock);
-		list_del_init(&rt->rt_uncached);
+		list_del_init(&rt->dst.rt_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
 }
@@ -1546,13 +1546,13 @@ void rt_flush_dev(struct net_device *dev)
 			continue;
 
 		spin_lock_bh(&ul->lock);
-		list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) {
+		list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) {
 			if (rt->dst.dev != dev)
 				continue;
 			rt->dst.dev = blackhole_netdev;
 			netdev_ref_replace(dev, blackhole_netdev,
 					   &rt->dst.dev_tracker, GFP_ATOMIC);
-			list_move(&rt->rt_uncached, &ul->quarantine);
+			list_move(&rt->dst.rt_uncached, &ul->quarantine);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -1644,7 +1644,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_uses_gateway = 0;
 		rt->rt_gw_family = 0;
 		rt->rt_gw4 = 0;
-		INIT_LIST_HEAD(&rt->rt_uncached);
+		INIT_LIST_HEAD(&rt->dst.rt_uncached);
 
 		rt->dst.output = ip_output;
 		if (flags & RTCF_LOCAL)
@@ -1675,7 +1675,7 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
 			new_rt->rt_gw4 = rt->rt_gw4;
 		else if (rt->rt_gw_family == AF_INET6)
 			new_rt->rt_gw6 = rt->rt_gw6;
-		INIT_LIST_HEAD(&new_rt->rt_uncached);
+		INIT_LIST_HEAD(&new_rt->dst.rt_uncached);
 
 		new_rt->dst.input = rt->dst.input;
 		new_rt->dst.output = rt->dst.output;
@@ -2859,7 +2859,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		else if (rt->rt_gw_family == AF_INET6)
 			rt->rt_gw6 = ort->rt_gw6;
 
-		INIT_LIST_HEAD(&rt->rt_uncached);
+		INIT_LIST_HEAD(&rt->dst.rt_uncached);
 	}
 
 	dst_release(dst_orig);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 3d0dfa6cf9f9..47861c8b7340 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,7 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 		xdst->u.rt.rt_gw6 = rt->rt_gw6;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
-	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
+	INIT_LIST_HEAD(&xdst->u.rt.dst.rt_uncached);
 	rt_add_uncached_list(&xdst->u.rt);
 
 	return 0;
@@ -121,7 +121,7 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
 	dst_destroy_metrics_generic(dst);
-	if (xdst->u.rt.rt_uncached_list)
+	if (xdst->u.rt.dst.rt_uncached_list)
 		rt_del_uncached_list(&xdst->u.rt);
 	xfrm_dst_destroy(xdst);
 }