[RFC PATCH 0/2] tcp: factor out a couple of helpers

[RFC PATCH 0/2] tcp: factor out a couple of helpers

[Paolo Abeni]

Upcoming improvement in MPTCP subflows management will require to keep write
data enqueued at the MPTCP level. As a side effect, such data could be sent
via orphaned TCP subflows after close().

To implement the above MPTCP needs to cope directly with memory allocation
failures in do_tcp_sendpages(). The solution proposed in patch 1/2 
is to factor-out the relevant slice of do_tcp_sendpages().

Other possible alternatives could be:
- duplicating the relevant code inside MPTCP (will require exposing a few
  additional TCP helpers) 
or
- add an explicit check for orphaned socket in do_tcp_sendpages()

Additionally, due to the above, we will need to dispose of already orphaned
TCP subflows, avoiding racing with tcp_done(). We need to check the
subflow status and destroy it atomically. The solution proposed in patch 2/2
is to factor-out the unlocked body of tcp_close().

These changes are part of a quite larger MPTCP series, with all the other
patches touching only MPTCP code. To hopefully simplify the review, such
patches are not included here. Please advice if you prefer otherwise
- e.g. the whole series as RFC.

Paolo Abeni (2):
  tcp: factor out tcp_build_frag()
  tcp: factor out __tcp_close() helper

 include/net/tcp.h |   4 ++
 net/ipv4/tcp.c    | 128 +++++++++++++++++++++++++++-------------------
 2 files changed, 78 insertions(+), 54 deletions(-)

-- 
2.26.2

[RFC PATCH 1/2] tcp: factor out tcp_build_frag()

[Paolo Abeni]

Will be needed by the next patch, as MPTCP needs to handle
directly the error/memory-allocation-needed path.

No functional changes intended.

Additionally let MPTCP code access the tcp_remove_empty_skb()
helper.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp.h |   3 ++
 net/ipv4/tcp.c    | 119 ++++++++++++++++++++++++++--------------------
 2 files changed, 70 insertions(+), 52 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d4ef5bf94168..e41569e55d97 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -322,6 +322,7 @@ 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);
 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);
@@ -329,6 +330,8 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
 int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
 			size_t size, int flags);
+struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
+			       struct page *page, int offset, size_t *size);
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 		 size_t size, int flags);
 int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bae4284bf542..259dca2bd3dd 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -952,7 +952,7 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
  * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
  * users.
  */
-static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
 {
 	if (skb && !skb->len) {
 		tcp_unlink_write_queue(skb, sk);
@@ -962,6 +962,68 @@ static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
+struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
+			       struct page *page, int offset, size_t *size)
+{
+	struct sk_buff *skb = tcp_write_queue_tail(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	bool can_coalesce;
+	int copy, i;
+
+	if (!skb || (copy = size_goal - skb->len) <= 0 ||
+	    !tcp_skb_can_collapse_to(skb)) {
+new_segment:
+		if (!sk_stream_memory_free(sk))
+			return NULL;
+
+		skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
+				tcp_rtx_and_write_queues_empty(sk));
+		if (!skb)
+			return NULL;
+
+#ifdef CONFIG_TLS_DEVICE
+		skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
+		skb_entail(sk, skb);
+		copy = size_goal;
+	}
+
+	if (copy > *size)
+		copy = *size;
+
+	i = skb_shinfo(skb)->nr_frags;
+	can_coalesce = skb_can_coalesce(skb, i, page, offset);
+	if (!can_coalesce && i >= sysctl_max_skb_frags) {
+		tcp_mark_push(tp, skb);
+		goto new_segment;
+	}
+	if (!sk_wmem_schedule(sk, copy))
+		return NULL;
+
+	if (can_coalesce) {
+		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+	} else {
+		get_page(page);
+		skb_fill_page_desc(skb, i, page, offset, copy);
+	}
+
+	if (!(flags & MSG_NO_SHARED_FRAGS))
+		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+
+	skb->len += copy;
+	skb->data_len += copy;
+	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);
+
+	*size = copy;
+	return skb;
+}
+
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			 size_t size, int flags)
 {
@@ -997,60 +1059,13 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 		goto out_err;
 
 	while (size > 0) {
-		struct sk_buff *skb = tcp_write_queue_tail(sk);
-		int copy, i;
-		bool can_coalesce;
-
-		if (!skb || (copy = size_goal - skb->len) <= 0 ||
-		    !tcp_skb_can_collapse_to(skb)) {
-new_segment:
-			if (!sk_stream_memory_free(sk))
-				goto wait_for_space;
-
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
-					tcp_rtx_and_write_queues_empty(sk));
-			if (!skb)
-				goto wait_for_space;
-
-#ifdef CONFIG_TLS_DEVICE
-			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
-#endif
-			skb_entail(sk, skb);
-			copy = size_goal;
-		}
+		struct sk_buff *skb;
+		size_t copy = size;
 
-		if (copy > size)
-			copy = size;
-
-		i = skb_shinfo(skb)->nr_frags;
-		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= sysctl_max_skb_frags) {
-			tcp_mark_push(tp, skb);
-			goto new_segment;
-		}
-		if (!sk_wmem_schedule(sk, copy))
+		skb = tcp_build_frag(sk, size_goal, flags, page, offset, &copy);
+		if (!skb)
 			goto wait_for_space;
 
-		if (can_coalesce) {
-			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
-		} else {
-			get_page(page);
-			skb_fill_page_desc(skb, i, page, offset, copy);
-		}
-
-		if (!(flags & MSG_NO_SHARED_FRAGS))
-			skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
-
-		skb->len += copy;
-		skb->data_len += copy;
-		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);
-
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
-- 
2.26.2

[RFC PATCH 2/2] tcp: factor out __tcp_close() helper

[Paolo Abeni]

unlocked version of protocol level close, will be used by
MPTCP to allow decouple orphaning and subflow level close.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp.h | 1 +
 net/ipv4/tcp.c    | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e41569e55d97..75c5ee45aaa8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -395,6 +395,7 @@ void tcp_update_metrics(struct sock *sk);
 void tcp_init_metrics(struct sock *sk);
 void tcp_metrics_init(void);
 bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
+void __tcp_close(struct sock *sk, long timeout);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
 void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 259dca2bd3dd..046ac30bb041 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2418,13 +2418,12 @@ bool tcp_check_oom(struct sock *sk, int shift)
 	return too_many_orphans || out_of_socket_memory;
 }
 
-void tcp_close(struct sock *sk, long timeout)
+void __tcp_close(struct sock *sk, long timeout)
 {
 	struct sk_buff *skb;
 	int data_was_unread = 0;
 	int state;
 
-	lock_sock(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if (sk->sk_state == TCP_LISTEN) {
@@ -2588,6 +2587,12 @@ void tcp_close(struct sock *sk, long timeout)
 out:
 	bh_unlock_sock(sk);
 	local_bh_enable();
+}
+
+void tcp_close(struct sock *sk, long timeout)
+{
+	lock_sock(sk);
+	__tcp_close(sk, timeout);
 	release_sock(sk);
 	sock_put(sk);
 }
-- 
2.26.2