udp: Use hlist_nulls in UDP RCU code

This is a straightforward patch, using hlist_nulls infrastructure.

RCUification already done on UDP two weeks ago.

Using hlist_nulls permits us to avoid some memory barriers, both
at lookup time and delete time.

Patch is large because it adds new macros to include/net/sock.h.
These macros will be used by TCP & DCCP in next patch.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 47 insertions, 29 deletions

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 3ba2998b22b..e649bd3f2c9 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -383,22 +383,5 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
 		pos = rcu_dereference(pos->next))
 
-/**
- * hlist_for_each_entry_rcu_safenext - iterate over rcu list of given type
- * @tpos:	the type * to use as a loop cursor.
- * @pos:	the &struct hlist_node to use as a loop cursor.
- * @head:	the head for your list.
- * @member:	the name of the hlist_node within the struct.
- * @next:       the &struct hlist_node to use as a next cursor
- *
- * Special version of hlist_for_each_entry_rcu that make sure
- * each next pointer is fetched before each iteration.
- */
-#define hlist_for_each_entry_rcu_safenext(tpos, pos, head, member, next) \
-	for (pos = rcu_dereference((head)->first);			 \
-		pos && ({ next = pos->next; smp_rmb(); prefetch(next); 1; }) &&	\
-		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
-		pos = rcu_dereference(next))
-
 #endif	/* __KERNEL__ */
 #endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 8b2b82131b6..0a638948868 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -42,6 +42,7 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/list_nulls.h>
 #include <linux/timer.h>
 #include <linux/cache.h>
 #include <linux/module.h>
@@ -52,6 +53,7 @@
 #include <linux/security.h>
 
 #include <linux/filter.h>
+#include <linux/rculist_nulls.h>
 
 #include <asm/atomic.h>
 #include <net/dst.h>
@@ -106,6 +108,7 @@ struct net;
  *	@skc_reuse: %SO_REUSEADDR setting
  *	@skc_bound_dev_if: bound device index if != 0
  *	@skc_node: main hash linkage for various protocol lookup tables
+ *	@skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
  *	@skc_bind_node: bind hash linkage for various protocol lookup tables
  *	@skc_refcnt: reference count
  *	@skc_hash: hash value used with various protocol lookup tables
@@ -120,7 +123,10 @@ struct sock_common {
 	volatile unsigned char	skc_state;
 	unsigned char		skc_reuse;
 	int			skc_bound_dev_if;
-	struct hlist_node	skc_node;
+	union {
+		struct hlist_node	skc_node;
+		struct hlist_nulls_node skc_nulls_node;
+	};
 	struct hlist_node	skc_bind_node;
 	atomic_t		skc_refcnt;
 	unsigned int		skc_hash;
@@ -206,6 +212,7 @@ struct sock {
 #define sk_reuse		__sk_common.skc_reuse
 #define sk_bound_dev_if		__sk_common.skc_bound_dev_if
 #define sk_node			__sk_common.skc_node
+#define sk_nulls_node		__sk_common.skc_nulls_node
 #define sk_bind_node		__sk_common.skc_bind_node
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_hash			__sk_common.skc_hash
@@ -300,12 +307,30 @@ static inline struct sock *sk_head(const struct hlist_head *head)
 	return hlist_empty(head) ? NULL : __sk_head(head);
 }
 
+static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
+{
+	return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
+}
+
+static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
+{
+	return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
+}
+
 static inline struct sock *sk_next(const struct sock *sk)
 {
 	return sk->sk_node.next ?
 		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
 }
 
+static inline struct sock *sk_nulls_next(const struct sock *sk)
+{
+	return (!is_a_nulls(sk->sk_nulls_node.next)) ?
+		hlist_nulls_entry(sk->sk_nulls_node.next,
+				  struct sock, sk_nulls_node) :
+		NULL;
+}
+
 static inline int sk_unhashed(const struct sock *sk)
 {
 	return hlist_unhashed(&sk->sk_node);
@@ -321,6 +346,11 @@ static __inline__ void sk_node_init(struct hlist_node *node)
 	node->pprev = NULL;
 }
 
+static __inline__ void sk_nulls_node_init(struct hlist_nulls_node *node)
+{
+	node->pprev = NULL;
+}
+
 static __inline__ void __sk_del_node(struct sock *sk)
 {
 	__hlist_del(&sk->sk_node);
@@ -367,18 +397,18 @@ static __inline__ int sk_del_node_init(struct sock *sk)
 	return rc;
 }
 
-static __inline__ int __sk_del_node_init_rcu(struct sock *sk)
+static __inline__ int __sk_nulls_del_node_init_rcu(struct sock *sk)
 {
 	if (sk_hashed(sk)) {
-		hlist_del_init_rcu(&sk->sk_node);
+		hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
 		return 1;
 	}
 	return 0;
 }
 
-static __inline__ int sk_del_node_init_rcu(struct sock *sk)
+static __inline__ int sk_nulls_del_node_init_rcu(struct sock *sk)
 {
-	int rc = __sk_del_node_init_rcu(sk);
+	int rc = __sk_nulls_del_node_init_rcu(sk);
 
 	if (rc) {
 		/* paranoid for a while -acme */
@@ -399,15 +429,15 @@ static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list)
 	__sk_add_node(sk, list);
 }
 
-static __inline__ void __sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
+static __inline__ void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	hlist_add_head_rcu(&sk->sk_node, list);
+	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
-static __inline__ void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
+static __inline__ void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	sock_hold(sk);
-	__sk_add_node_rcu(sk, list);
+	__sk_nulls_add_node_rcu(sk, list);
 }
 
 static __inline__ void __sk_del_bind_node(struct sock *sk)
@@ -423,11 +453,16 @@ static __inline__ void sk_add_bind_node(struct sock *sk,
 
 #define sk_for_each(__sk, node, list) \
 	hlist_for_each_entry(__sk, node, list, sk_node)
-#define sk_for_each_rcu_safenext(__sk, node, list, next) \
-	hlist_for_each_entry_rcu_safenext(__sk, node, list, sk_node, next)
+#define sk_nulls_for_each(__sk, node, list) \
+	hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
+#define sk_nulls_for_each_rcu(__sk, node, list) \
+	hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
 #define sk_for_each_from(__sk, node) \
 	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
 		hlist_for_each_entry_from(__sk, node, sk_node)
+#define sk_nulls_for_each_from(__sk, node) \
+	if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
+		hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
 #define sk_for_each_continue(__sk, node) \
 	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
 		hlist_for_each_entry_continue(__sk, node, sk_node)
diff --git a/include/net/udp.h b/include/net/udp.h
index df2bfe54537..90e6ce56be6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -51,7 +51,7 @@ struct udp_skb_cb {
 #define UDP_SKB_CB(__skb)	((struct udp_skb_cb *)((__skb)->cb))
 
 struct udp_hslot {
-	struct hlist_head	head;
+	struct hlist_nulls_head	head;
 	spinlock_t		lock;
 } __attribute__((aligned(2 * sizeof(long))));
 struct udp_table {