Merge branch 'mptcp-fixes-and-tracepoints'

Mat Martineau says:

====================
mptcp: Fixes and tracepoints from the mptcp tree

Here's one more batch of changes that we've tested out in the MPTCP tree.

Patch 1 makes the MPTCP KUnit config symbol more consistent with other
subsystems.

Patch 2 fixes a couple of format specifiers in pr_debug()s

Patches 3-7 add four helpful tracepoints for MPTCP.

Patch 8 is a one-line refactor to use an available helper macro.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

MAINTAINERS

@@ -12546,6 +12546,7 @@ W:	https://github.com/multipath-tcp/mptcp_net-next/wiki
 B:	https://github.com/multipath-tcp/mptcp_net-next/issues
 F:	Documentation/networking/mptcp-sysctl.rst
 F:	include/net/mptcp.h
+F:	include/trace/events/mptcp.h
 F:	include/uapi/linux/mptcp.h
 F:	net/mptcp/
 F:	tools/testing/selftests/net/mptcp/

include/trace/events/mptcp.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mptcp
+
+#if !defined(_TRACE_MPTCP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MPTCP_H
+
+#include <linux/tracepoint.h>
+
+#define show_mapping_status(status)					\
+	__print_symbolic(status,					\
+		{ 0, "MAPPING_OK" },					\
+		{ 1, "MAPPING_INVALID" },				\
+		{ 2, "MAPPING_EMPTY" },					\
+		{ 3, "MAPPING_DATA_FIN" },				\
+		{ 4, "MAPPING_DUMMY" })
+
+TRACE_EVENT(mptcp_subflow_get_send,
+
+	TP_PROTO(struct mptcp_subflow_context *subflow),
+
+	TP_ARGS(subflow),
+
+	TP_STRUCT__entry(
+		__field(bool, active)
+		__field(bool, free)
+		__field(u32, snd_wnd)
+		__field(u32, pace)
+		__field(u8, backup)
+		__field(u64, ratio)
+	),
+
+	TP_fast_assign(
+		struct sock *ssk;
+
+		__entry->active = mptcp_subflow_active(subflow);
+		__entry->backup = subflow->backup;
+
+		if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock))
+			__entry->free = sk_stream_memory_free(subflow->tcp_sock);
+		else
+			__entry->free = 0;
+
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		if (ssk && sk_fullsock(ssk)) {
+			__entry->snd_wnd = tcp_sk(ssk)->snd_wnd;
+			__entry->pace = ssk->sk_pacing_rate;
+		} else {
+			__entry->snd_wnd = 0;
+			__entry->pace = 0;
+		}
+
+		if (ssk && sk_fullsock(ssk) && __entry->pace)
+			__entry->ratio = div_u64((u64)ssk->sk_wmem_queued << 32, __entry->pace);
+		else
+			__entry->ratio = 0;
+	),
+
+	TP_printk("active=%d free=%d snd_wnd=%u pace=%u backup=%u ratio=%llu",
+		  __entry->active, __entry->free,
+		  __entry->snd_wnd, __entry->pace,
+		  __entry->backup, __entry->ratio)
+);
+
+DECLARE_EVENT_CLASS(mptcp_dump_mpext,
+
+	TP_PROTO(struct mptcp_ext *mpext),
+
+	TP_ARGS(mpext),
+
+	TP_STRUCT__entry(
+		__field(u64, data_ack)
+		__field(u64, data_seq)
+		__field(u32, subflow_seq)
+		__field(u16, data_len)
+		__field(u8, use_map)
+		__field(u8, dsn64)
+		__field(u8, data_fin)
+		__field(u8, use_ack)
+		__field(u8, ack64)
+		__field(u8, mpc_map)
+		__field(u8, frozen)
+		__field(u8, reset_transient)
+		__field(u8, reset_reason)
+	),
+
+	TP_fast_assign(
+		__entry->data_ack = mpext->ack64 ? mpext->data_ack : mpext->data_ack32;
+		__entry->data_seq = mpext->data_seq;
+		__entry->subflow_seq = mpext->subflow_seq;
+		__entry->data_len = mpext->data_len;
+		__entry->use_map = mpext->use_map;
+		__entry->dsn64 = mpext->dsn64;
+		__entry->data_fin = mpext->data_fin;
+		__entry->use_ack = mpext->use_ack;
+		__entry->ack64 = mpext->ack64;
+		__entry->mpc_map = mpext->mpc_map;
+		__entry->frozen = mpext->frozen;
+		__entry->reset_transient = mpext->reset_transient;
+		__entry->reset_reason = mpext->reset_reason;
+	),
+
+	TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u",
+		  __entry->data_ack, __entry->data_seq,
+		  __entry->subflow_seq, __entry->data_len,
+		  __entry->use_map, __entry->dsn64,
+		  __entry->data_fin, __entry->use_ack,
+		  __entry->ack64, __entry->mpc_map,
+		  __entry->frozen, __entry->reset_transient,
+		  __entry->reset_reason)
+);
+
+DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status,
+	TP_PROTO(struct mptcp_ext *mpext),
+	TP_ARGS(mpext));
+
+TRACE_EVENT(ack_update_msk,
+
+	TP_PROTO(u64 data_ack, u64 old_snd_una,
+		 u64 new_snd_una, u64 new_wnd_end,
+		 u64 msk_wnd_end),
+
+	TP_ARGS(data_ack, old_snd_una,
+		new_snd_una, new_wnd_end,
+		msk_wnd_end),
+
+	TP_STRUCT__entry(
+		__field(u64, data_ack)
+		__field(u64, old_snd_una)
+		__field(u64, new_snd_una)
+		__field(u64, new_wnd_end)
+		__field(u64, msk_wnd_end)
+	),
+
+	TP_fast_assign(
+		__entry->data_ack = data_ack;
+		__entry->old_snd_una = old_snd_una;
+		__entry->new_snd_una = new_snd_una;
+		__entry->new_wnd_end = new_wnd_end;
+		__entry->msk_wnd_end = msk_wnd_end;
+	),
+
+	TP_printk("data_ack=%llu old_snd_una=%llu new_snd_una=%llu new_wnd_end=%llu msk_wnd_end=%llu",
+		  __entry->data_ack, __entry->old_snd_una,
+		  __entry->new_snd_una, __entry->new_wnd_end,
+		  __entry->msk_wnd_end)
+);
+
+TRACE_EVENT(subflow_check_data_avail,
+
+	TP_PROTO(__u8 status, struct sk_buff *skb),
+
+	TP_ARGS(status, skb),
+
+	TP_STRUCT__entry(
+		__field(u8, status)
+		__field(const void *, skb)
+	),
+
+	TP_fast_assign(
+		__entry->status = status;
+		__entry->skb = skb;
+	),
+
+	TP_printk("mapping_status=%s, skb=%p",
+		  show_mapping_status(__entry->status),
+		  __entry->skb)
+);
+
+#endif /* _TRACE_MPTCP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

net/mptcp/Kconfig

@@ -22,7 +22,7 @@ config MPTCP_IPV6
 	depends on IPV6=y
 	default y
 
-config MPTCP_KUNIT_TESTS
+config MPTCP_KUNIT_TEST
 	tristate "This builds the MPTCP KUnit tests" if !KUNIT_ALL_TESTS
 	depends on KUNIT
 	default KUNIT_ALL_TESTS

net/mptcp/Makefile

@@ -9,4 +9,4 @@ obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
 
 mptcp_crypto_test-objs := crypto_test.o
 mptcp_token_test-objs := token_test.o
-obj-$(CONFIG_MPTCP_KUNIT_TESTS) += mptcp_crypto_test.o mptcp_token_test.o
+obj-$(CONFIG_MPTCP_KUNIT_TEST) += mptcp_crypto_test.o mptcp_token_test.o

net/mptcp/crypto.c

@@ -78,6 +78,6 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
 	sha256(input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE, hmac);
 }
 
-#if IS_MODULE(CONFIG_MPTCP_KUNIT_TESTS)
+#if IS_MODULE(CONFIG_MPTCP_KUNIT_TEST)
 EXPORT_SYMBOL_GPL(mptcp_crypto_hmac_sha);
 #endif

net/mptcp/options.c

@@ -13,6 +13,8 @@
 #include "protocol.h"
 #include "mib.h"
 
+#include <trace/events/mptcp.h>
+
 static bool mptcp_cap_flag_sha256(u8 flags)
 {
 	return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
@@ -943,6 +945,10 @@ static void ack_update_msk(struct mptcp_sock *msk,
 		__mptcp_data_acked(sk);
 	}
 	mptcp_data_unlock(sk);
+
+	trace_ack_update_msk(mp_opt->data_ack,
+			     old_snd_una, new_snd_una,
+			     new_wnd_end, msk->wnd_end);
 }
 
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)

net/mptcp/protocol.c

@@ -25,6 +25,9 @@
 #include "protocol.h"
 #include "mib.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/mptcp.h>
+
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 struct mptcp6_sock {
 	struct mptcp_sock msk;
@@ -399,18 +402,6 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
 	mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
 }
 
-static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
-{
-	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
-	if (subflow->request_join && !subflow->fully_established)
-		return false;
-
-	/* only send if our side has not closed yet */
-	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
-}
-
 static bool tcp_can_send_ack(const struct sock *ssk)
 {
 	return !((1 << inet_sk_state_load(ssk)) &
@@ -1294,7 +1285,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	int avail_size;
 	size_t ret = 0;
 
-	pr_debug("msk=%p ssk=%p sending dfrag at seq=%lld len=%d already sent=%d",
+	pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
 		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
 
 	/* compute send limit */
@@ -1422,6 +1413,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 		send_info[i].ratio = -1;
 	}
 	mptcp_for_each_subflow(msk, subflow) {
+		trace_mptcp_subflow_get_send(subflow);
 		ssk =  mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
 			continue;
@@ -1442,10 +1434,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 		}
 	}
 
-	pr_debug("msk=%p nr_active=%d ssk=%p:%lld backup=%p:%lld",
-		 msk, nr_active, send_info[0].ssk, send_info[0].ratio,
-		 send_info[1].ssk, send_info[1].ratio);
-
 	/* pick the best backup if no other subflow is active */
 	if (!nr_active)
 		send_info[0].ssk = send_info[1].ssk;
@@ -1712,7 +1700,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			if (!msk->first_pending)
 				WRITE_ONCE(msk->first_pending, dfrag);
 		}
-		pr_debug("msk=%p dfrag at seq=%lld len=%d sent=%d new=%d", msk,
+		pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk,
 			 dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
 			 !dfrag_collapsed);
 
@@ -2623,7 +2611,7 @@ static void mptcp_close(struct sock *sk, long timeout)
 cleanup:
 	/* orphan all the subflows */
 	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
-	list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) {
+	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast(ssk);
 

net/mptcp/protocol.h

@@ -544,6 +544,18 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
 
+static inline bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
+	if (subflow->request_join && !subflow->fully_established)
+		return false;
+
+	/* only send if our side has not closed yet */
+	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+
 static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
 					      struct mptcp_subflow_context *ctx)
 {

net/mptcp/subflow.c

@@ -25,6 +25,8 @@
 #include "protocol.h"
 #include "mib.h"
 
+#include <trace/events/mptcp.h>
+
 static void mptcp_subflow_ops_undo_override(struct sock *ssk);
 
 static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
@@ -862,9 +864,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		goto validate_seq;
 	}
 
-	pr_debug("seq=%llu is64=%d ssn=%u data_len=%u data_fin=%d",
-		 mpext->data_seq, mpext->dsn64, mpext->subflow_seq,
-		 mpext->data_len, mpext->data_fin);
+	trace_get_mapping_status(mpext);
 
 	data_len = mpext->data_len;
 	if (data_len == 0) {
@@ -1002,8 +1002,6 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	struct mptcp_sock *msk;
 	struct sk_buff *skb;
 
-	pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk,
-		 subflow->data_avail, skb_peek(&ssk->sk_receive_queue));
 	if (!skb_peek(&ssk->sk_receive_queue))
 		subflow->data_avail = 0;
 	if (subflow->data_avail)
@@ -1015,7 +1013,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		u64 old_ack;
 
 		status = get_mapping_status(ssk, msk);
-		pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status);
+		trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
 		if (status == MAPPING_INVALID) {
 			ssk->sk_err = EBADMSG;
 			goto fatal;

net/mptcp/token.c

@@ -402,7 +402,7 @@ void __init mptcp_token_init(void)
 	}
 }
 
-#if IS_MODULE(CONFIG_MPTCP_KUNIT_TESTS)
+#if IS_MODULE(CONFIG_MPTCP_KUNIT_TEST)
 EXPORT_SYMBOL_GPL(mptcp_token_new_request);
 EXPORT_SYMBOL_GPL(mptcp_token_new_connect);
 EXPORT_SYMBOL_GPL(mptcp_token_accept);