netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mat Martineau <mathew.j.martineau@linux.intel.com>
To: netdev@vger.kernel.org, edumazet@google.com
Cc: Paolo Abeni <pabeni@redhat.com>,
	cpaasch@apple.com, fw@strlen.de, peter.krystad@linux.intel.com,
	dcaratti@redhat.com, matthieu.baerts@tessares.net
Subject: [RFC PATCH v2 23/45] mptcp: sendmsg() do spool all the provided data
Date: Wed,  2 Oct 2019 16:36:33 -0700	[thread overview]
Message-ID: <20191002233655.24323-24-mathew.j.martineau@linux.intel.com> (raw)
In-Reply-To: <20191002233655.24323-1-mathew.j.martineau@linux.intel.com>

From: Paolo Abeni <pabeni@redhat.com>

This makes mptcp sendmsg() behaviour more consistent and
improves xmit performances.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/protocol.c | 126 ++++++++++++++++++++++++-------------------
 1 file changed, 71 insertions(+), 55 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index da983ea4fb5e..758369256f9b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -58,71 +58,37 @@ static struct sock *mptcp_subflow_get_ref(const struct mptcp_sock *msk)
 	return NULL;
 }
 
-static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+			      struct msghdr *msg, long *timeo)
 {
 	int mss_now = 0, size_goal = 0, ret = 0;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct socket *ssock;
-	struct sock *ssk;
 	struct mptcp_ext *mpext = NULL;
 	struct page_frag *pfrag;
 	struct sk_buff *skb;
 	size_t psize;
-	int poffset;
-	long timeo;
-
-	lock_sock(sk);
-	ssock = __mptcp_fallback_get_ref(msk);
-	if (ssock) {
-		release_sock(sk);
-		pr_debug("fallback passthrough");
-		ret = sock_sendmsg(ssock, msg);
-		sock_put(ssock->sk);
-		return ret;
-	}
-
-	ssk = mptcp_subflow_get_ref(msk);
-	if (!ssk) {
-		release_sock(sk);
-		return -ENOTCONN;
-	}
-
-	if (!msg_data_left(msg)) {
-		pr_debug("empty send");
-		ret = sock_sendmsg(ssk->sk_socket, msg);
-		goto put_out;
-	}
-
-	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) {
-		ret = -ENOTSUPP;
-		goto put_out;
-	}
-
-	lock_sock(ssk);
-	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	/* use the mptcp page cache so that we can easily move the data
 	 * from one substream to another, but do per subflow memory accounting
 	 */
 	pfrag = sk_page_frag(sk);
 	while (!sk_page_frag_refill(ssk, pfrag)) {
-		ret = sk_stream_wait_memory(ssk, &timeo);
+		ret = sk_stream_wait_memory(ssk, timeo);
 		if (ret)
-			goto put_out;
+			return ret;
 	}
 
-	/* Copy to page */
-	poffset = pfrag->offset;
+	/* compute copy limit */
+	mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
+	psize = min_t(int, pfrag->size - pfrag->offset, size_goal);
+
 	pr_debug("left=%zu", msg_data_left(msg));
-	psize = copy_page_from_iter(pfrag->page, poffset,
-				    min_t(size_t, msg_data_left(msg),
-					  pfrag->size - poffset),
+	psize = copy_page_from_iter(pfrag->page, pfrag->offset,
+				    min_t(size_t, msg_data_left(msg), psize),
 				    &msg->msg_iter);
 	pr_debug("left=%zu", msg_data_left(msg));
-	if (!psize) {
-		ret = -EINVAL;
-		goto put_out;
-	}
+	if (!psize)
+		return -EINVAL;
 
 	/* Mark the end of the previous write so the beginning of the
 	 * next write (with its own mptcp skb extension data) is not
@@ -132,20 +98,15 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (skb)
 		TCP_SKB_CB(skb)->eor = 1;
 
-	mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
-	psize = min_t(int, size_goal, psize);
-	ret = do_tcp_sendpages(ssk, pfrag->page, poffset, psize,
+	ret = do_tcp_sendpages(ssk, pfrag->page, pfrag->offset, psize,
 			       msg->msg_flags | MSG_SENDPAGE_NOTLAST);
 	if (ret <= 0)
-		goto put_out;
-
-	if (skb == tcp_write_queue_tail(ssk))
-		pr_err("no new skb %p/%p", sk, ssk);
+		return ret;
+	if (unlikely(ret < psize))
+		iov_iter_revert(&msg->msg_iter, psize - ret);
 
 	skb = tcp_write_queue_tail(ssk);
-
 	mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
-
 	if (mpext) {
 		memset(mpext, 0, sizeof(*mpext));
 		mpext->data_seq = msk->write_seq;
@@ -165,6 +126,61 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
 
 	tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle, size_goal);
+	return ret;
+}
+
+static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct socket *ssock;
+	size_t copied = 0;
+	struct sock *ssk;
+	int ret = 0;
+	long timeo;
+
+	lock_sock(sk);
+	ssock = __mptcp_fallback_get_ref(msk);
+	if (ssock) {
+		release_sock(sk);
+		pr_debug("fallback passthrough");
+		ret = sock_sendmsg(ssock, msg);
+		sock_put(ssock->sk);
+		return ret;
+	}
+
+	ssk = mptcp_subflow_get_ref(msk);
+	if (!ssk) {
+		release_sock(sk);
+		return -ENOTCONN;
+	}
+
+	if (!msg_data_left(msg)) {
+		pr_debug("empty send");
+		ret = sock_sendmsg(ssk->sk_socket, msg);
+		goto put_out;
+	}
+
+	pr_debug("conn_list->subflow=%p", ssk);
+
+	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) {
+		ret = -ENOTSUPP;
+		goto put_out;
+	}
+
+	lock_sock(ssk);
+	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+	while (msg_data_left(msg)) {
+		ret = mptcp_sendmsg_frag(sk, ssk, msg, &timeo);
+		if (ret < 0)
+			break;
+
+		copied += ret;
+	}
+
+	if (copied > 0)
+		ret = copied;
+
+	release_sock(ssk);
 
 put_out:
 	release_sock(sk);
-- 
2.23.0


  parent reply	other threads:[~2019-10-02 23:38 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-02 23:36 [RFC PATCH v2 00/45] Multipath TCP Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 01/45] tcp: Add MPTCP option number Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 02/45] net: Make sock protocol value checks more specific Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 03/45] sock: Make sk_protocol a 16-bit value Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 04/45] tcp: Define IPPROTO_MPTCP Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 05/45] mptcp: Add MPTCP socket stubs Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 06/45] mptcp: Handle MPTCP TCP options Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 07/45] mptcp: Associate MPTCP context with TCP socket Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 08/45] tcp: Expose tcp struct and routine for MPTCP Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 09/45] mptcp: Handle MP_CAPABLE options for outgoing connections Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 10/45] mptcp: add mptcp_poll Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 11/45] tcp, ulp: Add clone operation to tcp_ulp_ops Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 12/45] mptcp: Create SUBFLOW socket for incoming connections Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 13/45] mptcp: Add key generation and token tree Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 14/45] mptcp: Add shutdown() socket operation Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 15/45] mptcp: Add setsockopt()/getsockopt() socket operations Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 16/45] tcp: clean ext on tx recycle Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 17/45] mptcp: Add MPTCP to skb extensions Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 18/45] tcp: Prevent coalesce/collapse when skb has MPTCP extensions Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 19/45] tcp: Export low-level TCP functions Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 20/45] mptcp: Write MPTCP DSS headers to outgoing data packets Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 21/45] mptcp: Implement MPTCP receive path Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 22/45] mptcp: use sk_page_frag() in sendmsg Mat Martineau
2019-10-02 23:36 ` Mat Martineau [this message]
2019-10-02 23:36 ` [RFC PATCH v2 24/45] mptcp: allow collapsing consecutive sendpages on the same substream Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 25/45] tcp: Check for filled TCP option space before SACK Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 26/45] mptcp: Add path manager interface Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 27/45] mptcp: Add ADD_ADDR handling Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 28/45] mptcp: Add handling of incoming MP_JOIN requests Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 29/45] mptcp: harmonize locking on all socket operations Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 30/45] mptcp: new sysctl to control the activation per NS Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 31/45] mptcp: add basic kselftest for mptcp Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 32/45] mptcp: Add handling of outgoing MP_JOIN requests Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 33/45] mptcp: Implement path manager interface commands Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 34/45] mptcp: Make MPTCP socket block/wakeup ignore sk_receive_queue Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 35/45] mptcp: update per unacked sequence on pkt reception Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 36/45] mptcp: queue data for mptcp level retransmission Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 37/45] mptcp: introduce MPTCP retransmission timer Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 38/45] mptcp: implement memory accounting for mptcp rtx queue Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 39/45] mptcp: rework mptcp_sendmsg_frag to accept optional dfrag Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 40/45] mptcp: implement and use MPTCP-level retransmission Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 41/45] selftests: mptcp: make tc delays random Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 42/45] selftests: mptcp: extend mptcp_connect tool for ipv6 family Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 43/45] selftests: mptcp: add accept/getpeer checks Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 44/45] selftests: mptcp: add ipv6 connectivity Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 45/45] selftests: mptcp: random ethtool tweaking Mat Martineau
2019-10-02 23:53 ` [RFC PATCH v2 00/45] Multipath TCP Mat Martineau
2019-10-03  0:12 ` David Miller
2019-10-03  0:27   ` Mat Martineau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191002233655.24323-24-mathew.j.martineau@linux.intel.com \
    --to=mathew.j.martineau@linux.intel.com \
    --cc=cpaasch@apple.com \
    --cc=dcaratti@redhat.com \
    --cc=edumazet@google.com \
    --cc=fw@strlen.de \
    --cc=matthieu.baerts@tessares.net \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=peter.krystad@linux.intel.com \
    --subject='Re: [RFC PATCH v2 23/45] mptcp: sendmsg() do spool all the provided data' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).