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 <[e-mail]>
Signed-off-by: Arjan van de Ven <[e-mail]>
Signed-off-by: Thomas Gleixner <[e-mail]>
Reviewed-by: Eric Dumazet <[e-mail]>
Reviewed-by: David Ahern <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/net/dst.h

···
 #endif
 	int			__use;
 	unsigned long		lastuse;
-	struct lwtunnel_state   *lwtstate;
 	struct rcu_head		rcu_head;
 	short			error;
 	short			__pad;
 	__u32			tclassid;
 #ifndef CONFIG_64BIT
+	struct lwtunnel_state   *lwtstate;
 	atomic_t		__refcnt;	/* 32-bit offset 64 */
 #endif
 	netdevice_tracker	dev_tracker;
+
+	/*
+	 * Used by rtable and rt6_info. Moves lwtstate into the next cache
+	 * line on 64bit so that lwtstate does not cause false sharing with
+	 * __refcnt under contention of __refcnt. This also puts the
+	 * frequently accessed members of rtable and rt6_info out of the
+	 * __refcnt cache line.
+	 */
+	struct list_head	rt_uncached;
+	struct uncached_list	*rt_uncached_list;
+#ifdef CONFIG_64BIT
+	struct lwtunnel_state   *lwtstate;
+#endif
 };
 
 struct dst_metrics {

include/net/ip6_fib.h

···
 	struct inet6_dev		*rt6i_idev;
 	u32				rt6i_flags;
 
-	struct list_head		rt6i_uncached;
-	struct uncached_list		*rt6i_uncached_list;
-
 	/* more non-fragment space at head required */
 	unsigned short			rt6i_nfheader_len;
 };

include/net/ip6_route.h

···
 static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags)
 {
 	if (!(flags & RT6_LOOKUP_F_DST_NOREF) ||
-	    !list_empty(&rt->rt6i_uncached))
+	    !list_empty(&rt->dst.rt_uncached))
 		ip6_rt_put(rt);
 }
 

include/net/route.h

···
 	/* Miscellaneous cached information */
 	u32			rt_mtu_locked:1,
 				rt_pmtu:31;
-
-	struct list_head	rt_uncached;
-	struct uncached_list	*rt_uncached_list;
 };
 
 static inline bool rt_is_input_route(const struct rtable *rt)

net/ipv4/route.c

···
 {
 	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);
 	}
 }
···
 			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);
 	}
···
 		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)
···
 			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;
···
 		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);

net/ipv4/xfrm4_policy.c

···
 		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;
···
 	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);
 }

net/ipv6/route.c

···
 {
 	struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
 
-	rt->rt6i_uncached_list = ul;
+	rt->dst.rt_uncached_list = ul;
 
 	spin_lock_bh(&ul->lock);
-	list_add_tail(&rt->rt6i_uncached, &ul->head);
+	list_add_tail(&rt->dst.rt_uncached, &ul->head);
 	spin_unlock_bh(&ul->lock);
 }
 
 void rt6_uncached_list_del(struct rt6_info *rt)
 {
-	if (!list_empty(&rt->rt6i_uncached)) {
-		struct uncached_list *ul = rt->rt6i_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->rt6i_uncached);
+		list_del_init(&rt->dst.rt_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
 }
···
 			continue;
 
 		spin_lock_bh(&ul->lock);
-		list_for_each_entry_safe(rt, safe, &ul->head, rt6i_uncached) {
+		list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) {
 			struct inet6_dev *rt_idev = rt->rt6i_idev;
 			struct net_device *rt_dev = rt->dst.dev;
 			bool handled = false;
···
 				handled = true;
 			}
 			if (handled)
-				list_move(&rt->rt6i_uncached,
+				list_move(&rt->dst.rt_uncached,
 					  &ul->quarantine);
 		}
 		spin_unlock_bh(&ul->lock);
···
 static void rt6_info_init(struct rt6_info *rt)
 {
 	memset_after(rt, 0, dst);
-	INIT_LIST_HEAD(&rt->rt6i_uncached);
+	INIT_LIST_HEAD(&rt->dst.rt_uncached);
 }
 
 /* allocate dst with ip6_dst_ops */
···
 	dst = ip6_route_output_flags_noref(net, sk, fl6, flags);
 	rt6 = (struct rt6_info *)dst;
 	/* For dst cached in uncached_list, refcnt is already taken. */
-	if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) {
+	if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) {
 		dst = &net->ipv6.ip6_null_entry->dst;
 		dst_hold(dst);
 	}
···
 	from = rcu_dereference(rt->from);
 
 	if (from && (rt->rt6i_flags & RTF_PCPU ||
-	    unlikely(!list_empty(&rt->rt6i_uncached))))
+	    unlikely(!list_empty(&rt->dst.rt_uncached))))
 		dst_ret = rt6_dst_from_check(rt, from, cookie);
 	else
 		dst_ret = rt6_check(rt, from, cookie);
···
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
 			 ip6_template_metrics, true);
-	INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->rt6i_uncached);
+	INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	net->ipv6.fib6_has_custom_rules = false;
···
 	net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
 			 ip6_template_metrics, true);
-	INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->rt6i_uncached);
+	INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached);
 
 	net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
 					       sizeof(*net->ipv6.ip6_blk_hole_entry),
···
 	net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
 			 ip6_template_metrics, true);
-	INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->rt6i_uncached);
+	INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached);
 #ifdef CONFIG_IPV6_SUBTREES
 	net->ipv6.fib6_routes_require_src = 0;
 #endif

net/ipv6/xfrm6_policy.c

···
 	xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
 	xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
 	xdst->u.rt6.rt6i_src = rt->rt6i_src;
-	INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached);
+	INIT_LIST_HEAD(&xdst->u.rt6.dst.rt_uncached);
 	rt6_uncached_list_add(&xdst->u.rt6);
 
 	return 0;
···
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
 	dst_destroy_metrics_generic(dst);
-	if (xdst->u.rt6.rt6i_uncached_list)
+	if (xdst->u.rt6.dst.rt_uncached_list)
 		rt6_uncached_list_del(&xdst->u.rt6);
 	xfrm_dst_destroy(xdst);
 }