Merge branch 'tcp-tx-side-cleanups'

Eric Dumazet says:

====================
tcp: tx side cleanups

We no longer need to set skb->reserved_tailroom because
TCP sendmsg() do not put payload in skb->head anymore.

Also do some cleanups around skb->ip_summed/csum,
and CP_SKB_CB(skb)->sacked for fresh skbs.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/tcp.h

@@ -311,7 +311,7 @@ void tcp_shutdown(struct sock *sk, int how);
 int tcp_v4_early_demux(struct sk_buff *skb);
 int tcp_v4_rcv(struct sk_buff *skb);
 
-void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb);
+void tcp_remove_empty_skb(struct sock *sk);
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);

net/ipv4/tcp.c

@@ -658,10 +658,8 @@ void tcp_skb_entail(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
-	skb->csum    = 0;
 	tcb->seq     = tcb->end_seq = tp->write_seq;
 	tcb->tcp_flags = TCPHDR_ACK;
-	tcb->sacked  = 0;
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk_wmem_queued_add(sk, skb->truesize);
@@ -876,11 +874,7 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 		}
 		if (likely(mem_scheduled)) {
 			skb_reserve(skb, MAX_TCP_HEADER);
-			/*
-			 * Make sure that we have exactly size bytes
-			 * available to the caller, no more, no less.
-			 */
-			skb->reserved_tailroom = skb->end - skb->tail - size;
+			skb->ip_summed = CHECKSUM_PARTIAL;
 			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
@@ -933,8 +927,10 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
  * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
  * users.
  */
-void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+void tcp_remove_empty_skb(struct sock *sk)
 {
+	struct sk_buff *skb = tcp_write_queue_tail(sk);
+
 	if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		tcp_unlink_write_queue(skb, sk);
 		if (tcp_write_queue_empty(sk))
@@ -996,7 +992,6 @@ static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
 	skb->truesize += copy;
 	sk_wmem_queued_add(sk, copy);
 	sk_mem_charge(sk, copy);
-	skb->ip_summed = CHECKSUM_PARTIAL;
 	WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 	TCP_SKB_CB(skb)->end_seq += copy;
 	tcp_skb_pcount_set(skb, 0);
@@ -1087,7 +1082,7 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 	return copied;
 
 do_error:
-	tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
+	tcp_remove_empty_skb(sk);
 	if (copied)
 		goto out;
 out_err:
@@ -1292,7 +1287,6 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 				goto wait_for_space;
 
 			process_backlog++;
-			skb->ip_summed = CHECKSUM_PARTIAL;
 
 			tcp_skb_entail(sk, skb);
 			copy = size_goal;
@@ -1309,14 +1303,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		if (copy > msg_data_left(msg))
 			copy = msg_data_left(msg);
 
-		/* Where to copy to? */
-		if (skb_availroom(skb) > 0 && !zc) {
-			/* We have some space in skb head. Superb! */
-			copy = min_t(int, copy, skb_availroom(skb));
-			err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
-			if (err)
-				goto do_fault;
-		} else if (!zc) {
+		if (!zc) {
 			bool merge = true;
 			int i = skb_shinfo(skb)->nr_frags;
 			struct page_frag *pfrag = sk_page_frag(sk);
@@ -1415,9 +1402,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	return copied + copied_syn;
 
 do_error:
-	skb = tcp_write_queue_tail(sk);
-do_fault:
-	tcp_remove_empty_skb(sk, skb);
+	tcp_remove_empty_skb(sk);
 
 	if (copied + copied_syn)
 		goto out;

net/ipv4/tcp_output.c

@@ -394,7 +394,6 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
 	TCP_SKB_CB(skb)->tcp_flags = flags;
-	TCP_SKB_CB(skb)->sacked = 0;
 
 	tcp_skb_pcount_set(skb, 1);
 
@@ -1590,8 +1589,6 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 
 	skb_split(skb, buff, len);
 
-	buff->ip_summed = CHECKSUM_PARTIAL;
-
 	buff->tstamp = skb->tstamp;
 	tcp_fragment_tstamp(skb, buff);
 
@@ -1676,7 +1673,6 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	delta_truesize = __pskb_trim_head(skb, len);
 
 	TCP_SKB_CB(skb)->seq += len;
-	skb->ip_summed = CHECKSUM_PARTIAL;
 
 	if (delta_truesize) {
 		skb->truesize	   -= delta_truesize;
@@ -2142,12 +2138,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
 	TCP_SKB_CB(buff)->tcp_flags = flags;
 
-	/* This packet was never sent out yet, so no SACK bits. */
-	TCP_SKB_CB(buff)->sacked = 0;
-
 	tcp_skb_fragment_eor(skb, buff);
 
-	buff->ip_summed = CHECKSUM_PARTIAL;
 	skb_split(skb, buff, len);
 	tcp_fragment_tstamp(skb, buff);
 
@@ -2401,9 +2393,6 @@ static int tcp_mtu_probe(struct sock *sk)
 	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
 	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
 	TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK;
-	TCP_SKB_CB(nskb)->sacked = 0;
-	nskb->csum = 0;
-	nskb->ip_summed = CHECKSUM_PARTIAL;
 
 	tcp_insert_write_queue_before(nskb, skb, sk);
 	tcp_highest_sack_replace(sk, skb, nskb);
@@ -3045,13 +3034,9 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 
 	BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
 
-	if (next_skb_size) {
-		if (next_skb_size <= skb_availroom(skb))
-			skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size),
-				      next_skb_size);
-		else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size))
-			return false;
-	}
+	if (next_skb_size && !tcp_skb_shift(skb, next_skb, 1, next_skb_size))
+		return false;
+
 	tcp_highest_sack_replace(sk, next_skb, skb);
 
 	/* Update sequence range on original skb. */
@@ -3757,7 +3742,6 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	syn_data = tcp_stream_alloc_skb(sk, space, sk->sk_allocation, false);
 	if (!syn_data)
 		goto fallback;
-	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
 	if (space) {
 		int copied = copy_from_iter(skb_put(syn_data, space), space,

net/ipv6/tcp_ipv6.c

@@ -969,7 +969,6 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	fl6.flowlabel = label;
 
 	buff->ip_summed = CHECKSUM_PARTIAL;
-	buff->csum = 0;
 
 	__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
 

net/mptcp/protocol.c

@@ -1174,7 +1174,7 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
 	if (likely(skb)) {
 		if (likely(__mptcp_add_ext(skb, gfp))) {
 			skb_reserve(skb, MAX_TCP_HEADER);
-			skb->reserved_tailroom = skb->end - skb->tail;
+			skb->ip_summed = CHECKSUM_PARTIAL;
 			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
 			return skb;
 		}
@@ -1291,7 +1291,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
 		if (snd_una != msk->snd_nxt) {
-			tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk));
+			tcp_remove_empty_skb(ssk);
 			return 0;
 		}
 
@@ -1307,7 +1307,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 
 	copy = min_t(size_t, copy, info->limit - info->sent);
 	if (!sk_wmem_schedule(ssk, copy)) {
-		tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk));
+		tcp_remove_empty_skb(ssk);
 		return -ENOMEM;
 	}
 
@@ -1323,7 +1323,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	skb->truesize += copy;
 	sk_wmem_queued_add(ssk, copy);
 	sk_mem_charge(ssk, copy);
-	skb->ip_summed = CHECKSUM_PARTIAL;
 	WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy);
 	TCP_SKB_CB(skb)->end_seq += copy;
 	tcp_skb_pcount_set(skb, 0);