Merge branch 'rfs-lockless-annotate'

Eric Dumazet says:

====================
rfs: annotate lockless accesses

rfs runs without locks held, so we should annotate
read and writes to shared variables.

It should prevent compilers forcing writes
in the following situation:

  if (var != val)
     var = val;

A compiler could indeed simply avoid the conditional:

    var = val;

This matters if var is shared between many cpus.

v2: aligns one closing bracket (Simon)
    adds Fixes: tags (Jakub)
====================

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

3 files changed, 22 insertions, 9 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 08fbd4622ccf..e6f22b7403d0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -768,8 +768,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
 		/* We only give a hint, preemption can change CPU under us */
 		val |= raw_smp_processor_id();
 
-		if (table->ents[index] != val)
-			table->ents[index] = val;
+		/* The following WRITE_ONCE() is paired with the READ_ONCE()
+		 * here, and another one in get_rps_cpu().
+		 */
+		if (READ_ONCE(table->ents[index]) != val)
+			WRITE_ONCE(table->ents[index], val);
 	}
 }
 
diff --git a/include/net/sock.h b/include/net/sock.h
index b418425d7230..6f428a7f3567 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1152,8 +1152,12 @@ static inline void sock_rps_record_flow(const struct sock *sk)
 		 * OR	an additional socket flag
 		 * [1] : sk_state and sk_prot are in the same cache line.
 		 */
-		if (sk->sk_state == TCP_ESTABLISHED)
-			sock_rps_record_flow_hash(sk->sk_rxhash);
+		if (sk->sk_state == TCP_ESTABLISHED) {
+			/* This READ_ONCE() is paired with the WRITE_ONCE()
+			 * from sock_rps_save_rxhash() and sock_rps_reset_rxhash().
+			 */
+			sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash));
+		}
 	}
 #endif
 }
@@ -1162,15 +1166,19 @@ static inline void sock_rps_save_rxhash(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_RPS
-	if (unlikely(sk->sk_rxhash != skb->hash))
-		sk->sk_rxhash = skb->hash;
+	/* The following WRITE_ONCE() is paired with the READ_ONCE()
+	 * here, and another one in sock_rps_record_flow().
+	 */
+	if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash))
+		WRITE_ONCE(sk->sk_rxhash, skb->hash);
 #endif
 }
 
 static inline void sock_rps_reset_rxhash(struct sock *sk)
 {
 #ifdef CONFIG_RPS
-	sk->sk_rxhash = 0;
+	/* Paired with READ_ONCE() in sock_rps_record_flow() */
+	WRITE_ONCE(sk->sk_rxhash, 0);
 #endif
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index b3c13e041935..1495f8aff288 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4471,8 +4471,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		u32 next_cpu;
 		u32 ident;
 
-		/* First check into global flow table if there is a match */
-		ident = sock_flow_table->ents[hash & sock_flow_table->mask];
+		/* First check into global flow table if there is a match.
+		 * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow().
+		 */
+		ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]);
 		if ((ident ^ hash) & ~rps_cpu_mask)
 			goto try_rps;