[PATCH net-next v8 01/11] net: dst_cache: add noref versions for dst_cache

[Marek Mietus <mmietus97@yahoo.com>]

Implement noref variants for existing dst_cache helpers
interacting with dst_entry. This is required for implementing
noref flows, which avoid redundant atomic operations.

Signed-off-by: Marek Mietus <mmietus97@yahoo.com>
---
 include/net/dst_cache.h |  71 +++++++++++++++++++++
 net/core/dst_cache.c    | 133 +++++++++++++++++++++++++++++++++++++---
 2 files changed, 194 insertions(+), 10 deletions(-)

diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 1961699598e2..8d425cd75fd3 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -23,6 +23,23 @@ struct dst_cache {
  */
 struct dst_entry *dst_cache_get(struct dst_cache *dst_cache);
 
+/**
+ * dst_cache_get_rcu - perform cache lookup under RCU
+ * @dst_cache: the cache
+ *
+ * Perform cache lookup without taking a reference on the dst.
+ * Must be called with local BH disabled, and within an rcu read side
+ * critical section.
+ *
+ * The caller should use dst_cache_get_ip4_rcu() if it need to retrieve the
+ * source address to be used when xmitting to the cached dst.
+ * local BH must be disabled.
+ *
+ * Return: Pointer to retrieved rtable if cache is initialized and
+ * cached dst is valid, NULL otherwise.
+ */
+struct dst_entry *dst_cache_get_rcu(struct dst_cache *dst_cache);
+
 /**
  *	dst_cache_get_ip4 - perform cache lookup and fetch ipv4 source address
  *	@dst_cache: the cache
@@ -32,6 +49,21 @@ struct dst_entry *dst_cache_get(struct dst_cache *dst_cache);
  */
 struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr);
 
+/**
+ * dst_cache_get_ip4_rcu - lookup cache and ipv4 source under RCU
+ * @dst_cache: the cache
+ * @saddr: return value for the retrieved source address
+ *
+ * Perform cache lookup and fetch ipv4 source without taking a
+ * reference on the dst.
+ * Must be called with local BH disabled, and within an rcu read side
+ * critical section.
+ *
+ * Return: Pointer to retrieved rtable if cache is initialized and
+ * cached dst is valid, NULL otherwise.
+ */
+struct rtable *dst_cache_get_ip4_rcu(struct dst_cache *dst_cache, __be32 *saddr);
+
 /**
  *	dst_cache_set_ip4 - store the ipv4 dst into the cache
  *	@dst_cache: the cache
@@ -43,6 +75,17 @@ struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr);
 void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
 		       __be32 saddr);
 
+/**
+ * dst_cache_steal_ip4 - store the ipv4 dst into the cache and steal its
+ * reference
+ * @dst_cache: the cache
+ * @dst: the entry to be cached whose reference will be stolen
+ * @saddr: the source address to be stored inside the cache
+ *
+ * local BH must be disabled
+ */
+void dst_cache_steal_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
+			 __be32 saddr);
 #if IS_ENABLED(CONFIG_IPV6)
 
 /**
@@ -56,6 +99,18 @@ void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
 void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
 		       const struct in6_addr *saddr);
 
+/**
+ * dst_cache_steal_ip6 - store the ipv6 dst into the cache and steal its
+ * reference
+ * @dst_cache: the cache
+ * @dst: the entry to be cached whose reference will be stolen
+ * @saddr: the source address to be stored inside the cache
+ *
+ * local BH must be disabled
+ */
+void dst_cache_steal_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
+			 const struct in6_addr *saddr);
+
 /**
  *	dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address
  *	@dst_cache: the cache
@@ -65,6 +120,22 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
  */
 struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
 				    struct in6_addr *saddr);
+
+/**
+ * dst_cache_get_ip6_rcu - lookup cache and ipv6 source under RCU
+ * @dst_cache: the cache
+ * @saddr: return value for the retrieved source address
+ *
+ * Perform cache lookup and fetch ipv6 source without taking a
+ * reference on the dst.
+ * Must be called with local BH disabled, and within an rcu read side
+ * critical section.
+ *
+ * Return: Pointer to retrieved dst_entry if cache is initialized and
+ * cached dst is valid, NULL otherwise.
+ */
+struct dst_entry *dst_cache_get_ip6_rcu(struct dst_cache *dst_cache,
+					struct in6_addr *saddr);
 #endif
 
 /**
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index 9ab4902324e1..52418cfb9b8a 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -25,20 +25,27 @@ struct dst_cache_pcpu {
 	};
 };
 
-static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache,
-				      struct dst_entry *dst, u32 cookie)
+static void __dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache,
+					struct dst_entry *dst, u32 cookie)
 {
 	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
 	dst_release(dst_cache->dst);
-	if (dst)
-		dst_hold(dst);
 
 	dst_cache->cookie = cookie;
 	dst_cache->dst = dst;
 }
 
-static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache,
-					       struct dst_cache_pcpu *idst)
+static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache,
+				      struct dst_entry *dst, u32 cookie)
+{
+	if (dst)
+		dst_hold(dst);
+
+	__dst_cache_per_cpu_dst_set(dst_cache, dst, cookie);
+}
+
+static struct dst_entry *__dst_cache_per_cpu_get(struct dst_cache *dst_cache,
+						 struct dst_cache_pcpu *idst)
 {
 	struct dst_entry *dst;
 
@@ -47,14 +54,10 @@ static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache,
 	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,
 				 READ_ONCE(dst_cache->reset_ts)) ||
 		     (READ_ONCE(dst->obsolete) && !dst->ops->check(dst, idst->cookie)))) {
 		dst_cache_per_cpu_dst_set(idst, NULL, 0);
-		dst_release(dst);
 		goto fail;
 	}
 	return dst;
@@ -64,6 +67,18 @@ static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache,
 	return NULL;
 }
 
+static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache,
+					       struct dst_cache_pcpu *idst)
+{
+	struct dst_entry *dst;
+
+	dst = __dst_cache_per_cpu_get(dst_cache, idst);
+	if (dst)
+		/* the cache already hold a dst reference; it can't go away */
+		dst_hold(dst);
+	return dst;
+}
+
 struct dst_entry *dst_cache_get(struct dst_cache *dst_cache)
 {
 	struct dst_entry *dst;
@@ -78,6 +93,20 @@ struct dst_entry *dst_cache_get(struct dst_cache *dst_cache)
 }
 EXPORT_SYMBOL_GPL(dst_cache_get);
 
+struct dst_entry *dst_cache_get_rcu(struct dst_cache *dst_cache)
+{
+	struct dst_entry *dst;
+
+	if (!dst_cache->cache)
+		return NULL;
+
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+	dst = __dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache));
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+	return dst;
+}
+EXPORT_SYMBOL_GPL(dst_cache_get_rcu);
+
 struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr)
 {
 	struct dst_cache_pcpu *idst;
@@ -100,6 +129,28 @@ struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr)
 }
 EXPORT_SYMBOL_GPL(dst_cache_get_ip4);
 
+struct rtable *dst_cache_get_ip4_rcu(struct dst_cache *dst_cache, __be32 *saddr)
+{
+	struct dst_cache_pcpu *idst;
+	struct dst_entry *dst;
+
+	if (!dst_cache->cache)
+		return NULL;
+
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+	idst = this_cpu_ptr(dst_cache->cache);
+	dst = __dst_cache_per_cpu_get(dst_cache, idst);
+	if (!dst) {
+		local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+		return NULL;
+	}
+
+	*saddr = idst->in_saddr.s_addr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+	return dst_rtable(dst);
+}
+EXPORT_SYMBOL_GPL(dst_cache_get_ip4_rcu);
+
 void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
 		       __be32 saddr)
 {
@@ -116,6 +167,24 @@ void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
 }
 EXPORT_SYMBOL_GPL(dst_cache_set_ip4);
 
+void dst_cache_steal_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
+			 __be32 saddr)
+{
+	struct dst_cache_pcpu *idst;
+
+	if (!dst_cache->cache) {
+		dst_release(dst);
+		return;
+	}
+
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+	idst = this_cpu_ptr(dst_cache->cache);
+	__dst_cache_per_cpu_dst_set(idst, dst, 0);
+	idst->in_saddr.s_addr = saddr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+}
+EXPORT_SYMBOL_GPL(dst_cache_steal_ip4);
+
 #if IS_ENABLED(CONFIG_IPV6)
 void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
 		       const struct in6_addr *saddr)
@@ -135,6 +204,26 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
 }
 EXPORT_SYMBOL_GPL(dst_cache_set_ip6);
 
+void dst_cache_steal_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
+			 const struct in6_addr *saddr)
+{
+	struct dst_cache_pcpu *idst;
+
+	if (!dst_cache->cache) {
+		dst_release(dst);
+		return;
+	}
+
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+
+	idst = this_cpu_ptr(dst_cache->cache);
+	__dst_cache_per_cpu_dst_set(idst, dst,
+				    rt6_get_cookie(dst_rt6_info(dst)));
+	idst->in6_saddr = *saddr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+}
+EXPORT_SYMBOL_GPL(dst_cache_steal_ip6);
+
 struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
 				    struct in6_addr *saddr)
 {
@@ -158,6 +247,30 @@ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
 	return dst;
 }
 EXPORT_SYMBOL_GPL(dst_cache_get_ip6);
+
+struct dst_entry *dst_cache_get_ip6_rcu(struct dst_cache *dst_cache,
+					struct in6_addr *saddr)
+{
+	struct dst_cache_pcpu *idst;
+	struct dst_entry *dst;
+
+	if (!dst_cache->cache)
+		return NULL;
+
+	local_lock_nested_bh(&dst_cache->cache->bh_lock);
+
+	idst = this_cpu_ptr(dst_cache->cache);
+	dst = __dst_cache_per_cpu_get(dst_cache, idst);
+	if (!dst) {
+		local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+		return NULL;
+	}
+
+	*saddr = idst->in6_saddr;
+	local_unlock_nested_bh(&dst_cache->cache->bh_lock);
+	return dst;
+}
+EXPORT_SYMBOL_GPL(dst_cache_get_ip6_rcu);
 #endif
 
 int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp)
-- 
2.51.0