Merge branch 'unified-tunnel-dst-caching'

Paolo Abeni says:

====================
net: unify dst caching for tunnel devices

This patch series try to unify the dst cache implementations currently
present in the kernel, namely in ip_tunnel.c and ip6_tunnel.c, introducing a
new generic implementation, replacing the existing ones, and then using
the new implementation in other tunnel devices which currently lack it.

The new dst implementation is compiled, as built-in, only if any device using
it is enabled.

Caching the dst for the tunnel remote address gives small, but measurable,
performance improvement when tunneling over ipv4 (in the 2%-4% range) and
significant ones when tunneling over ipv6 (roughly 60% when no
fragmentation/segmentation take place and the tunnel local address
is not specified).

v2:
- move the vxlan dst_cache usage inside the device lookup functions
- fix usage after free for lwt tunnel moving the dst cache storage inside
  the dst_metadata,
- sparse codying style cleanup
====================

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

5 files changed, 106 insertions, 19 deletions

diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
new file mode 100644
index 000000000000..151accae708b
--- /dev/null
+++ b/include/net/dst_cache.h
@@ -0,0 +1,97 @@
+#ifndef _NET_DST_CACHE_H
+#define _NET_DST_CACHE_H
+
+#include <linux/jiffies.h>
+#include <net/dst.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_fib.h>
+#endif
+
+struct dst_cache {
+	struct dst_cache_pcpu __percpu *cache;
+	unsigned long reset_ts;
+};
+
+/**
+ *	dst_cache_get - perform cache lookup
+ *	@dst_cache: the cache
+ *
+ *	The caller should use dst_cache_get_ip4() if it need to retrieve the
+ *	source address to be used when xmitting to the cached dst.
+ *	local BH must be disabled.
+ */
+struct dst_entry *dst_cache_get(struct dst_cache *dst_cache);
+
+/**
+ *	dst_cache_get_ip4 - perform cache lookup and fetch ipv4 source address
+ *	@dst_cache: the cache
+ *	@saddr: return value for the retrieved source address
+ *
+ *	local BH must be disabled.
+ */
+struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr);
+
+/**
+ *	dst_cache_set_ip4 - store the ipv4 dst into the cache
+ *	@dst_cache: the cache
+ *	@dst: the entry to be cached
+ *	@saddr: the source address to be stored inside the cache
+ *
+ *	local BH must be disabled.
+ */
+void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
+		       __be32 saddr);
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+/**
+ *	dst_cache_set_ip6 - store the ipv6 dst into the cache
+ *	@dst_cache: the cache
+ *	@dst: the entry to be cached
+ *	@saddr: the source address to be stored inside the cache
+ *
+ *	local BH must be disabled.
+ */
+void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
+		       const struct in6_addr *addr);
+
+/**
+ *	dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address
+ *	@dst_cache: the cache
+ *	@saddr: return value for the retrieved source address
+ *
+ *	local BH must be disabled.
+ */
+struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
+				    struct in6_addr *saddr);
+#endif
+
+/**
+ *	dst_cache_reset - invalidate the cache contents
+ *	@dst_cache: the cache
+ *
+ *	This do not free the cached dst to avoid races and contentions.
+ *	the dst will be freed on later cache lookup.
+ */
+static inline void dst_cache_reset(struct dst_cache *dst_cache)
+{
+	dst_cache->reset_ts = jiffies;
+}
+
+/**
+ *	dst_cache_init - initialize the cache, allocating the required storage
+ *	@dst_cache: the cache
+ *	@gfp: allocation flags
+ */
+int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp);
+
+/**
+ *	dst_cache_destroy - empty the cache and free the allocated storage
+ *	@dst_cache: the cache
+ *
+ *	No synchronization is enforced: it must be called only when the cache
+ *	is unsed.
+ */
+void dst_cache_destroy(struct dst_cache *dst_cache);
+
+#endif
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 30a56ab2ccfb..84b833af6882 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -62,6 +62,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
 		      sizeof(a->u.tun_info) + a->u.tun_info.options_len);
 }
 
+void metadata_dst_free(struct metadata_dst *);
 struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
 struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
 
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 0d0ce0b2d870..499a707765ea 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -6,6 +6,7 @@
 #include <linux/if_tunnel.h>
 #include <linux/ip6_tunnel.h>
 #include <net/ip_tunnels.h>
+#include <net/dst_cache.h>
 
 #define IP6TUNNEL_ERR_TIMEO (30*HZ)
 
@@ -33,12 +34,6 @@ struct __ip6_tnl_parm {
 	__be32			o_key;
 };
 
-struct ip6_tnl_dst {
-	seqlock_t lock;
-	struct dst_entry __rcu *dst;
-	u32 cookie;
-};
-
 /* IPv6 tunnel */
 struct ip6_tnl {
 	struct ip6_tnl __rcu *next;	/* next tunnel in list */
@@ -46,7 +41,7 @@ struct ip6_tnl {
 	struct net *net;	/* netns for packet i/o */
 	struct __ip6_tnl_parm parms;	/* tunnel configuration parameters */
 	struct flowi fl;	/* flowi template for xmit */
-	struct ip6_tnl_dst __percpu *dst_cache;	/* cached dst */
+	struct dst_cache dst_cache;	/* cached dst */
 
 	int err_count;
 	unsigned long err_time;
@@ -66,11 +61,6 @@ struct ipv6_tlv_tnl_enc_lim {
 	__u8 encap_limit;	/* tunnel encapsulation limit   */
 } __packed;
 
-struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t);
-int ip6_tnl_dst_init(struct ip6_tnl *t);
-void ip6_tnl_dst_destroy(struct ip6_tnl *t);
-void ip6_tnl_dst_reset(struct ip6_tnl *t);
-void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst);
 int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
 		const struct in6_addr *raddr);
 int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index bc439f32baa9..87408ab80856 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -13,6 +13,7 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/lwtunnel.h>
+#include <net/dst_cache.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -57,6 +58,9 @@ struct ip_tunnel_key {
 
 struct ip_tunnel_info {
 	struct ip_tunnel_key	key;
+#ifdef CONFIG_DST_CACHE
+	struct dst_cache	dst_cache;
+#endif
 	u8			options_len;
 	u8			mode;
 };
@@ -85,11 +89,6 @@ struct ip_tunnel_prl_entry {
 	struct rcu_head			rcu_head;
 };
 
-struct ip_tunnel_dst {
-	struct dst_entry __rcu 		*dst;
-	__be32				 saddr;
-};
-
 struct metadata_dst;
 
 struct ip_tunnel {
@@ -108,7 +107,7 @@ struct ip_tunnel {
 	int		tun_hlen;	/* Precalculated header length */
 	int		mlink;
 
-	struct ip_tunnel_dst __percpu *dst_cache;
+	struct dst_cache dst_cache;
 
 	struct ip_tunnel_parm parms;
 
@@ -247,7 +246,6 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p);
 void ip_tunnel_setup(struct net_device *dev, int net_id);
-void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 25bd919c9ef0..b314e4af89c5 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -148,6 +148,7 @@ struct vxlan_rdst {
 	u32			 remote_ifindex;
 	struct list_head	 list;
 	struct rcu_head		 rcu;
+	struct dst_cache	 dst_cache;
 };
 
 struct vxlan_config {