net: add dst_cache support

This patch add a generic, lockless dst cache implementation.
The need for lock is avoided updating the dst cache fields
only in per cpu scope, and requiring that the cache manipulation
functions are invoked with the local bh disabled.

The refresh_ts and reset_ts fields are used to ensure the cache
consistency in case of cuncurrent cache update (dst_cache_set*) and
reset operation (dst_cache_reset).

Consider the following scenario:

CPU1:                                   	CPU2:
  <cache lookup with emtpy cache: it fails>
  <get dst via uncached route lookup>
						<related configuration changes>
                                        	dst_cache_reset()
  dst_cache_set()

The dst entry set passed to dst_cache_set() should not be used
for later dst cache lookup, because it's obtained using old
configuration values.

Since the refresh_ts is updated only on dst_cache lookup, the
cached value in the above scenario will be discarded on the next
lookup.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Suggested-and-acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 173 insertions, 0 deletions

diff --git a/net/Kconfig b/net/Kconfig
index 174354618f8a..b80efecfc1a0 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -392,6 +392,10 @@ config LWTUNNEL
 	  weight tunnel endpoint. Tunnel encapsulation parameters are stored
 	  with light weight tunnel state associated with fib routes.
 
+config DST_CACHE
+	bool "dst cache"
+	default n
+
 endif   # if NET
 
 # Used by archs to tell that they support BPF_JIT
diff --git a/net/core/Makefile b/net/core/Makefile
index 0b835de04de3..7a8fb8aef992 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -24,3 +24,4 @@ obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
 obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
 obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
 obj-$(CONFIG_LWTUNNEL) += lwtunnel.o
+obj-$(CONFIG_DST_CACHE) += dst_cache.o
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
new file mode 100644
index 000000000000..3938f3f38d69
--- /dev/null
+++ b/net/core/dst_cache.c
@@ -0,0 +1,168 @@
+/*
+ * net/core/dst_cache.c - dst entry cache
+ *
+ * Copyright (c) 2016 Paolo Abeni <pabeni@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <net/dst_cache.h>
+#include <net/route.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_fib.h>
+#endif
+#include <uapi/linux/in.h>
+
+struct dst_cache_pcpu {
+	unsigned long refresh_ts;
+	struct dst_entry *dst;
+	u32 cookie;
+	union {
+		struct in_addr in_saddr;
+		struct in6_addr in6_saddr;
+	};
+};
+
+void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache,
+			       struct dst_entry *dst, u32 cookie)
+{
+	dst_release(dst_cache->dst);
+	if (dst)
+		dst_hold(dst);
+
+	dst_cache->cookie = cookie;
+	dst_cache->dst = dst;
+}
+
+struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache,
+					struct dst_cache_pcpu *idst)
+{
+	struct dst_entry *dst;
+
+	dst = idst->dst;
+	if (!dst)
+		goto fail;
+
+	/* the cache already hold a dst reference; it can't go away */
+	dst_hold(dst);
+
+	if (unlikely(!time_after(idst->refresh_ts, dst_cache->reset_ts) ||
+		     (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) {
+		dst_cache_per_cpu_dst_set(idst, NULL, 0);
+		dst_release(dst);
+		goto fail;
+	}
+	return dst;
+
+fail:
+	idst->refresh_ts = jiffies;
+	return NULL;
+}
+
+struct dst_entry *dst_cache_get(struct dst_cache *dst_cache)
+{
+	if (!dst_cache->cache)
+		return NULL;
+
+	return dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache));
+}
+EXPORT_SYMBOL_GPL(dst_cache_get);
+
+struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr)
+{
+	struct dst_cache_pcpu *idst;
+	struct dst_entry *dst;
+
+	if (!dst_cache->cache)
+		return NULL;
+
+	idst = this_cpu_ptr(dst_cache->cache);
+	dst = dst_cache_per_cpu_get(dst_cache, idst);
+	if (!dst)
+		return NULL;
+
+	*saddr = idst->in_saddr.s_addr;
+	return container_of(dst, struct rtable, dst);
+}
+EXPORT_SYMBOL_GPL(dst_cache_get_ip4);
+
+void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
+		       __be32 saddr)
+{
+	struct dst_cache_pcpu *idst;
+
+	if (!dst_cache->cache)
+		return;
+
+	idst = this_cpu_ptr(dst_cache->cache);
+	dst_cache_per_cpu_dst_set(idst, dst, 0);
+	idst->in_saddr.s_addr = saddr;
+}
+EXPORT_SYMBOL_GPL(dst_cache_set_ip4);
+
+#if IS_ENABLED(CONFIG_IPV6)
+void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
+		       const struct in6_addr *addr)
+{
+	struct dst_cache_pcpu *idst;
+
+	if (!dst_cache->cache)
+		return;
+
+	idst = this_cpu_ptr(dst_cache->cache);
+	dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst,
+				  rt6_get_cookie((struct rt6_info *)dst));
+	idst->in6_saddr = *addr;
+}
+EXPORT_SYMBOL_GPL(dst_cache_set_ip6);
+
+struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
+				    struct in6_addr *saddr)
+{
+	struct dst_cache_pcpu *idst;
+	struct dst_entry *dst;
+
+	if (!dst_cache->cache)
+		return NULL;
+
+	idst = this_cpu_ptr(dst_cache->cache);
+	dst = dst_cache_per_cpu_get(dst_cache, idst);
+	if (!dst)
+		return NULL;
+
+	*saddr = idst->in6_saddr;
+	return dst;
+}
+EXPORT_SYMBOL_GPL(dst_cache_get_ip6);
+#endif
+
+int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp)
+{
+	dst_cache->cache = alloc_percpu_gfp(struct dst_cache_pcpu,
+					    gfp | __GFP_ZERO);
+	if (!dst_cache->cache)
+		return -ENOMEM;
+
+	dst_cache_reset(dst_cache);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dst_cache_init);
+
+void dst_cache_destroy(struct dst_cache *dst_cache)
+{
+	int i;
+
+	if (!dst_cache->cache)
+		return;
+
+	for_each_possible_cpu(i)
+		dst_release(per_cpu_ptr(dst_cache->cache, i)->dst);
+
+	free_percpu(dst_cache->cache);
+}
+EXPORT_SYMBOL_GPL(dst_cache_destroy);