tcp: fix zerocopy and notsent_lowat issues

My recent patch had at least three problems :

1) TX zerocopy wants notification when skb is acknowledged,
   thus we need to call skb_zcopy_clear() if the skb is
   cached into sk->sk_tx_skb_cache

2) Some applications might expect precise EPOLLOUT
   notifications, so we need to update sk->sk_wmem_queued
   and call sk_mem_uncharge() from sk_wmem_free_skb()
   in all cases. The SOCK_QUEUE_SHRUNK flag must also be set.

3) Reuse of saved skb should have used skb_cloned() instead
  of simply checking if the fast clone has been freed.

Fixes: 472c2e07ee ("tcp: add one skb cache for tx")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sock.h

@@ -1465,13 +1465,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
-	if (!sk->sk_tx_skb_cache) {
-		sk->sk_tx_skb_cache = skb;
-		return;
-	}
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	sk->sk_wmem_queued -= skb->truesize;
 	sk_mem_uncharge(sk, skb->truesize);
+	if (!sk->sk_tx_skb_cache) {
+		skb_zcopy_clear(skb, true);
+		sk->sk_tx_skb_cache = skb;
+		return;
+	}
 	__kfree_skb(skb);
 }
 

net/ipv4/tcp.c

@@ -865,14 +865,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 {
 	struct sk_buff *skb;
 
+	if (likely(!size)) {
 		skb = sk->sk_tx_skb_cache;
-	if (skb && !size) {
-		const struct sk_buff_fclones *fclones;
-
-		fclones = container_of(skb, struct sk_buff_fclones, skb1);
-		if (refcount_read(&fclones->fclone_ref) == 1) {
-			sk->sk_wmem_queued -= skb->truesize;
-			sk_mem_uncharge(sk, skb->truesize);
+		if (skb && !skb_cloned(skb)) {
 			skb->truesize -= skb->data_len;
 			sk->sk_tx_skb_cache = NULL;
 			pskb_trim(skb, 0);
@@ -2543,8 +2538,6 @@ void tcp_write_queue_purge(struct sock *sk)
 	tcp_rtx_queue_purge(sk);
 	skb = sk->sk_tx_skb_cache;
 	if (skb) {
-		sk->sk_wmem_queued -= skb->truesize;
-		sk_mem_uncharge(sk, skb->truesize);
 		__kfree_skb(skb);
 		sk->sk_tx_skb_cache = NULL;
 	}