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 36/45] mptcp: queue data for mptcp level retransmission
Date: Wed,  2 Oct 2019 16:36:46 -0700	[thread overview]
Message-ID: <20191002233655.24323-37-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>

keep the send page fragment on an MPTCP level retransmission queue.
the queue entries are allocated inside the page frag allocator,
acquiring an additional reference to the page for each list entry.

Also switch to a custom page frag refill function, to ensure that
the current page fragment can always host an MPTCP rtx queue entry.

The MPTCP rtx queue is flushed at disconnect() and close() time

Note that now we need to call __mptcp_init_sock() regarless of mptcp
enable status, as the destructor will try to walk the rtx_queue.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/protocol.c | 131 ++++++++++++++++++++++++++++++++++++++++---
 net/mptcp/protocol.h |  20 +++++++
 2 files changed, 143 insertions(+), 8 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2c64435aedd8..c2e89e8cbc0e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -69,14 +69,74 @@ static inline bool mptcp_skb_can_collapse_to(const struct mptcp_sock *msk,
 	return mpext && mpext->data_seq + mpext->data_len == msk->write_seq;
 }
 
+static inline bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
+					      const struct page_frag *pfrag,
+					      const struct mptcp_data_frag *df)
+{
+	return df && pfrag->page == df->page &&
+		df->data_seq + df->data_len == msk->write_seq;
+}
+
+static void dfrag_clear(struct mptcp_data_frag *dfrag)
+{
+	list_del(&dfrag->list);
+	put_page(dfrag->page);
+}
+
+static void mptcp_clean_una(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_data_frag *dtmp, *dfrag;
+	u64 snd_una = atomic64_read(&msk->snd_una);
+
+	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
+		if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
+			break;
+
+		dfrag_clear(dfrag);
+	}
+}
+
+/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
+ * data
+ */
+bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+{
+	if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag),
+					pfrag, sk->sk_allocation)))
+		return true;
+
+	sk->sk_prot->enter_memory_pressure(sk);
+	sk_stream_moderate_sndbuf(sk);
+	return false;
+}
+
+static inline struct mptcp_data_frag *
+mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
+		      int orig_offset)
+{
+	int offset = ALIGN(orig_offset, sizeof(long));
+	struct mptcp_data_frag *dfrag;
+
+	dfrag = (struct mptcp_data_frag *)(page_to_virt(pfrag->page) + offset);
+	dfrag->data_len = 0;
+	dfrag->data_seq = msk->write_seq;
+	dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
+	dfrag->offset = offset + sizeof(struct mptcp_data_frag);
+	dfrag->page = pfrag->page;
+
+	return dfrag;
+}
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct msghdr *msg, long *timeo, int *pmss_now,
 			      int *ps_goal)
 {
-	int mss_now, avail_size, size_goal, ret;
+	int mss_now, avail_size, size_goal, offset, ret, frag_truesize = 0;
+	bool dfrag_collapsed, collapsed, can_collapse = false;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	bool collapsed, can_collapse = false;
 	struct mptcp_ext *mpext = NULL;
+	struct mptcp_data_frag *dfrag;
 	struct page_frag *pfrag;
 	struct sk_buff *skb;
 	size_t psize;
@@ -85,10 +145,15 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	 * from one substream to another, but do per subflow memory accounting
 	 */
 	pfrag = sk_page_frag(sk);
-	while (!sk_page_frag_refill(ssk, pfrag)) {
+	while (!mptcp_page_frag_refill(ssk, pfrag)) {
 		ret = sk_stream_wait_memory(ssk, timeo);
 		if (ret)
 			return ret;
+
+		/* id sk_stream_wait_memory() sleeps snd_una can change
+		 * significantly, refresh the rtx queue
+		 */
+		mptcp_clean_una(sk);
 	}
 
 	/* compute copy limit */
@@ -113,11 +178,23 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		else
 			avail_size = size_goal - skb->len;
 	}
-	psize = min_t(size_t, pfrag->size - pfrag->offset, avail_size);
+
+	/* reuse tail pfrag, if possible, or carve a new one from the page
+	 * allocator
+	 */
+	dfrag = mptcp_rtx_tail(sk);
+	offset = pfrag->offset;
+	dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
+	if (!dfrag_collapsed) {
+		dfrag = mptcp_carve_data_frag(msk, pfrag, offset);
+		offset = dfrag->offset;
+		frag_truesize = dfrag->overhead;
+	}
+	psize = min_t(size_t, pfrag->size - offset, avail_size);
 
 	/* Copy to page */
 	pr_debug("left=%zu", msg_data_left(msg));
-	psize = copy_page_from_iter(pfrag->page, pfrag->offset,
+	psize = copy_page_from_iter(pfrag->page, offset,
 				    min_t(size_t, msg_data_left(msg), psize),
 				    &msg->msg_iter);
 	pr_debug("left=%zu", msg_data_left(msg));
@@ -127,13 +204,24 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	/* tell the TCP stack to delay the push so that we can safely
 	 * access the skb after the sendpages call
 	 */
-	ret = do_tcp_sendpages(ssk, pfrag->page, pfrag->offset, psize,
+	ret = do_tcp_sendpages(ssk, pfrag->page, offset, psize,
 			       msg->msg_flags | MSG_SENDPAGE_NOTLAST);
 	if (ret <= 0)
 		return ret;
+
+	frag_truesize += ret;
 	if (unlikely(ret < psize))
 		iov_iter_revert(&msg->msg_iter, psize - ret);
 
+	/* send successful, keep track of sent data for mptcp-level
+	 * retransmission
+	 */
+	dfrag->data_len += ret;
+	if (!dfrag_collapsed) {
+		get_page(dfrag->page);
+		list_add_tail(&dfrag->list, &msk->rtx_queue);
+	}
+
 	collapsed = skb == tcp_write_queue_tail(ssk);
 	if (collapsed) {
 		WARN_ON_ONCE(!can_collapse);
@@ -162,7 +250,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	 */
 
 out:
-	pfrag->offset += ret;
+	pfrag->offset += frag_truesize;
 	msk->write_seq += ret;
 	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
 
@@ -209,6 +297,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	lock_sock(ssk);
+	mptcp_clean_una(sk);
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	while (msg_data_left(msg)) {
 		ret = mptcp_sendmsg_frag(sk, ssk, msg, &timeo, &mss_now,
@@ -596,16 +685,31 @@ static int __mptcp_init_sock(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	INIT_LIST_HEAD(&msk->conn_list);
+	INIT_LIST_HEAD(&msk->rtx_queue);
 
 	return 0;
 }
 
 static int mptcp_init_sock(struct sock *sk)
 {
+	int ret = __mptcp_init_sock(sk);
+
+	if (ret)
+		return ret;
+
 	if (!mptcp_is_enabled(sock_net(sk)))
 		return -ENOPROTOOPT;
 
-	return __mptcp_init_sock(sk);
+	return 0;
+}
+
+static void __mptcp_clear_xmit(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_data_frag *dtmp, *dfrag;
+
+	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
+		dfrag_clear(dfrag);
 }
 
 static void mptcp_close(struct sock *sk, long timeout)
@@ -634,10 +738,20 @@ static void mptcp_close(struct sock *sk, long timeout)
 		sock_release(mptcp_subflow_tcp_socket(subflow));
 	}
 
+	__mptcp_clear_xmit(sk);
 	release_sock(sk);
+
 	sk_common_release(sk);
 }
 
+static int mptcp_disconnect(struct sock *sk, int flags)
+{
+	lock_sock(sk);
+	__mptcp_clear_xmit(sk);
+	release_sock(sk);
+	return tcp_disconnect(sk, flags);
+}
+
 static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 				 bool kern)
 {
@@ -863,6 +977,7 @@ static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
 	.init		= mptcp_init_sock,
+	.disconnect	= mptcp_disconnect,
 	.close		= mptcp_close,
 	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 45646e38aa4c..e09db0f85bfc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -111,6 +111,15 @@ struct mptcp_pm_data {
 	u32	token;
 };
 
+struct mptcp_data_frag {
+	struct list_head list;
+	u64 data_seq;
+	int data_len;
+	int offset;
+	int overhead;
+	struct page *page;
+};
+
 /* MPTCP connection sock */
 struct mptcp_sock {
 	/* inet_connection_sock must be the first member */
@@ -124,6 +133,7 @@ struct mptcp_sock {
 	unsigned long	flags;
 	u16		dport;
 	struct list_head conn_list;
+	struct list_head rtx_queue;
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct mptcp_pm_data	pm;
 	u8		addr_signal;
@@ -137,6 +147,16 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
 	return (struct mptcp_sock *)sk;
 }
 
+static inline struct mptcp_data_frag *mptcp_rtx_tail(const struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (list_empty(&msk->rtx_queue))
+		return NULL;
+
+	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
+}
+
 struct mptcp_subflow_request_sock {
 	struct	tcp_request_sock sk;
 	u8	mp_capable : 1,
-- 
2.23.0


  parent reply	other threads:[~2019-10-02 23:37 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 ` [RFC PATCH v2 23/45] mptcp: sendmsg() do spool all the provided data Mat Martineau
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 ` Mat Martineau [this message]
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=20191002233655.24323-37-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 36/45] mptcp: queue data for mptcp level retransmission' \
    /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).