From d9cd27b8cd191133e287e5de107f971136abe8a2 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@linux.dev>
Date: Fri, 22 Dec 2023 13:47:22 +0100
Subject: [PATCH 1/4] mptcp: add CurrEstab MIB counter support
Add a new MIB counter named MPTCP_MIB_CURRESTAB to count current
established MPTCP connections, similar to TCP_MIB_CURRESTAB. This is
useful to quickly list the number of MPTCP connections without having to
iterate over all of them.
This patch adds a new helper function mptcp_set_state(): if the state
switches from or to ESTABLISHED state, this newly added counter is
incremented. This helper is going to be used in the following patch.
Similar to MPTCP_INC_STATS(), a new helper called MPTCP_DEC_STATS() is
also needed to decrement a MIB counter.
Signed-off-by: Geliang Tang <geliang.tang@linux.dev>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/mib.c | 1 +
net/mptcp/mib.h | 8 ++++++++
net/mptcp/protocol.c | 18 ++++++++++++++++++
net/mptcp/protocol.h | 1 +
4 files changed, 28 insertions(+)
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index a0990c365a2e..c30405e76833 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -66,6 +66,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED),
SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE),
SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT),
+ SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB),
SNMP_MIB_SENTINEL
};
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index cae71d947252..dd7fd1f246b5 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -65,6 +65,7 @@ enum linux_mptcp_mib_field {
* conflict with another subflow while updating msk rcv wnd
*/
MPTCP_MIB_RCVWNDCONFLICT, /* Conflict with while updating msk rcv wnd */
+ MPTCP_MIB_CURRESTAB, /* Current established MPTCP connections */
__MPTCP_MIB_MAX
};
@@ -95,4 +96,11 @@ static inline void __MPTCP_INC_STATS(struct net *net,
__SNMP_INC_STATS(net->mib.mptcp_statistics, field);
}
+static inline void MPTCP_DEC_STATS(struct net *net,
+ enum linux_mptcp_mib_field field)
+{
+ if (likely(net->mib.mptcp_statistics))
+ SNMP_DEC_STATS(net->mib.mptcp_statistics, field);
+}
+
bool mptcp_mib_alloc(struct net *net);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 91e5845d80a9..a77a609b4470 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2871,6 +2871,24 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
release_sock(ssk);
}
+void mptcp_set_state(struct sock *sk, int state)
+{
+ int oldstate = sk->sk_state;
+
+ switch (state) {
+ case TCP_ESTABLISHED:
+ if (oldstate != TCP_ESTABLISHED)
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
+ break;
+
+ default:
+ if (oldstate == TCP_ESTABLISHED)
+ MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
+ }
+
+ inet_sk_state_store(sk, state);
+}
+
static const unsigned char new_state[16] = {
/* current state: new state: action: */
[0 /* (Invalid) */] = TCP_CLOSE,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 1240268f9e9e..3517f2d24a22 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -641,6 +641,7 @@ bool __mptcp_close(struct sock *sk, long timeout);
void mptcp_cancel_work(struct sock *sk);
void __mptcp_unaccepted_force_close(struct sock *sk);
void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);
+void mptcp_set_state(struct sock *sk, int state);
bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
const struct mptcp_addr_info *b, bool use_port);
From c693a8516429908da3ea111b0caa3c042ab1e6e9 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@linux.dev>
Date: Fri, 22 Dec 2023 13:47:23 +0100
Subject: [PATCH 2/4] mptcp: use mptcp_set_state
This patch replaces all the 'inet_sk_state_store()' calls under net/mptcp
with the new helper mptcp_set_state().
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/460
Signed-off-by: Geliang Tang <geliang.tang@linux.dev>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/pm_netlink.c | 5 +++++
net/mptcp/protocol.c | 38 +++++++++++++++++++-------------------
net/mptcp/subflow.c | 2 +-
3 files changed, 25 insertions(+), 20 deletions(-)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 272e93be1aad..287a60381eae 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1048,6 +1048,11 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
if (err)
return err;
+ /* We don't use mptcp_set_state() here because it needs to be called
+ * under the msk socket lock. For the moment, that will not bring
+ * anything more than only calling inet_sk_state_store(), because the
+ * old status is known (TCP_CLOSE).
+ */
inet_sk_state_store(newsk, TCP_LISTEN);
lock_sock(ssk);
err = __inet_listen_sk(ssk, backlog);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a77a609b4470..3ed4709a7509 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -429,11 +429,11 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
switch (sk->sk_state) {
case TCP_FIN_WAIT1:
- inet_sk_state_store(sk, TCP_FIN_WAIT2);
+ mptcp_set_state(sk, TCP_FIN_WAIT2);
break;
case TCP_CLOSING:
case TCP_LAST_ACK:
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
break;
}
@@ -594,13 +594,13 @@ static bool mptcp_check_data_fin(struct sock *sk)
switch (sk->sk_state) {
case TCP_ESTABLISHED:
- inet_sk_state_store(sk, TCP_CLOSE_WAIT);
+ mptcp_set_state(sk, TCP_CLOSE_WAIT);
break;
case TCP_FIN_WAIT1:
- inet_sk_state_store(sk, TCP_CLOSING);
+ mptcp_set_state(sk, TCP_CLOSING);
break;
case TCP_FIN_WAIT2:
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
break;
default:
/* Other states not expected */
@@ -775,7 +775,7 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk)
*/
ssk_state = inet_sk_state_load(ssk);
if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
- inet_sk_state_store(sk, ssk_state);
+ mptcp_set_state(sk, ssk_state);
WRITE_ONCE(sk->sk_err, -err);
/* This barrier is coupled with smp_rmb() in mptcp_poll() */
@@ -2463,7 +2463,7 @@ out:
inet_sk_state_load(msk->first) == TCP_CLOSE) {
if (sk->sk_state != TCP_ESTABLISHED ||
msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) {
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
mptcp_close_wake_up(sk);
} else {
mptcp_start_tout_timer(sk);
@@ -2558,7 +2558,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
WRITE_ONCE(sk->sk_err, ECONNRESET);
}
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
@@ -2693,7 +2693,7 @@ static void mptcp_do_fastclose(struct sock *sk)
struct mptcp_subflow_context *subflow, *tmp;
struct mptcp_sock *msk = mptcp_sk(sk);
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
mptcp_for_each_subflow_safe(msk, subflow, tmp)
__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
subflow, MPTCP_CF_FASTCLOSE);
@@ -2911,7 +2911,7 @@ static int mptcp_close_state(struct sock *sk)
int next = (int)new_state[sk->sk_state];
int ns = next & TCP_STATE_MASK;
- inet_sk_state_store(sk, ns);
+ mptcp_set_state(sk, ns);
return next & TCP_ACTION_FIN;
}
@@ -3022,7 +3022,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
mptcp_check_listen_stop(sk);
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
goto cleanup;
}
@@ -3065,7 +3065,7 @@ cleanup:
* state, let's not keep resources busy for no reasons
*/
if (subflows_alive == 0)
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
sock_hold(sk);
pr_debug("msk=%p state=%d", sk, sk->sk_state);
@@ -3131,7 +3131,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
return -EBUSY;
mptcp_check_listen_stop(sk);
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
mptcp_stop_rtx_timer(sk);
mptcp_stop_tout_timer(sk);
@@ -3219,7 +3219,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
/* this can't race with mptcp_close(), as the msk is
* not yet exposted to user-space
*/
- inet_sk_state_store(nsk, TCP_ESTABLISHED);
+ mptcp_set_state(nsk, TCP_ESTABLISHED);
/* The msk maintain a ref to each subflow in the connections list */
WRITE_ONCE(msk->first, ssk);
@@ -3640,7 +3640,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (IS_ERR(ssk))
return PTR_ERR(ssk);
- inet_sk_state_store(sk, TCP_SYN_SENT);
+ mptcp_set_state(sk, TCP_SYN_SENT);
subflow = mptcp_subflow_ctx(ssk);
#ifdef CONFIG_TCP_MD5SIG
/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -3690,7 +3690,7 @@ out:
if (unlikely(err)) {
/* avoid leaving a dangling token in an unconnected socket */
mptcp_token_destroy(msk);
- inet_sk_state_store(sk, TCP_CLOSE);
+ mptcp_set_state(sk, TCP_CLOSE);
return err;
}
@@ -3779,13 +3779,13 @@ static int mptcp_listen(struct socket *sock, int backlog)
goto unlock;
}
- inet_sk_state_store(sk, TCP_LISTEN);
+ mptcp_set_state(sk, TCP_LISTEN);
sock_set_flag(sk, SOCK_RCU_FREE);
lock_sock(ssk);
err = __inet_listen_sk(ssk, backlog);
release_sock(ssk);
- inet_sk_state_store(sk, inet_sk_state_load(ssk));
+ mptcp_set_state(sk, inet_sk_state_load(ssk));
if (!err) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -3863,7 +3863,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
__mptcp_close_ssk(newsk, msk->first,
mptcp_subflow_ctx(msk->first), 0);
if (unlikely(list_is_singular(&msk->conn_list)))
- inet_sk_state_store(newsk, TCP_CLOSE);
+ mptcp_set_state(newsk, TCP_CLOSE);
}
} else {
MPTCP_INC_STATS(sock_net(ssk),
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6d7684c35e93..1ef28642afc4 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -425,7 +425,7 @@ void __mptcp_sync_state(struct sock *sk, int state)
__mptcp_propagate_sndbuf(sk, msk->first);
if (sk->sk_state == TCP_SYN_SENT) {
- inet_sk_state_store(sk, state);
+ mptcp_set_state(sk, state);
sk->sk_state_change(sk);
}
}
From 0bd962dd86b2e5d097fc42c7411818851eca2995 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@linux.dev>
Date: Fri, 22 Dec 2023 13:47:24 +0100
Subject: [PATCH 3/4] selftests: mptcp: join: check CURRESTAB counters
This patch adds a new helper chk_cestab_nr() to check the current
established connections counter MIB_CURRESTAB. Set the newly added
variables cestab_ns1 and cestab_ns2 to indicate how many connections
are expected in ns1 or ns2.
Invoke check_cestab() to check the counter during the connection in
do_transfer() and invoke chk_cestab_nr() to re-check it when the
connection closed. These checks are embedded in add_tests().
Signed-off-by: Geliang Tang <geliang.tang@linux.dev>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../testing/selftests/net/mptcp/mptcp_join.sh | 46 +++++++++++++++++--
1 file changed, 41 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 87590a43b50d..3a5b63026191 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -56,6 +56,8 @@ unset FAILING_LINKS
unset test_linkfail
unset addr_nr_ns1
unset addr_nr_ns2
+unset cestab_ns1
+unset cestab_ns2
unset sflags
unset fastclose
unset fullmesh
@@ -976,6 +978,34 @@ pm_nl_set_endpoint()
fi
}
+chk_cestab_nr()
+{
+ local ns=$1
+ local cestab=$2
+ local count
+
+ print_check "cestab $cestab"
+ count=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPCurrEstab")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$cestab" ]; then
+ fail_test "got $count current establish[s] expected $cestab"
+ else
+ print_ok
+ fi
+}
+
+# $1 namespace 1, $2 namespace 2
+check_cestab()
+{
+ if [ -n "${cestab_ns1}" ]; then
+ chk_cestab_nr ${1} ${cestab_ns1}
+ fi
+ if [ -n "${cestab_ns2}" ]; then
+ chk_cestab_nr ${2} ${cestab_ns2}
+ fi
+}
+
do_transfer()
{
local listener_ns="$1"
@@ -1089,6 +1119,7 @@ do_transfer()
local cpid=$!
pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr
+ check_cestab $listener_ns $connector_ns
wait $cpid
local retc=$?
@@ -2477,47 +2508,52 @@ add_tests()
if reset "add single subflow"; then
pm_nl_set_limits $ns1 0 1
pm_nl_set_limits $ns2 0 1
- addr_nr_ns2=1 speed=slow \
+ addr_nr_ns2=1 speed=slow cestab_ns2=1 \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
+ chk_cestab_nr $ns2 0
fi
# add signal address
if reset "add signal address"; then
pm_nl_set_limits $ns1 0 1
pm_nl_set_limits $ns2 1 1
- addr_nr_ns1=1 speed=slow \
+ addr_nr_ns1=1 speed=slow cestab_ns1=1 \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
chk_add_nr 1 1
+ chk_cestab_nr $ns1 0
fi
# add multiple subflows
if reset "add multiple subflows"; then
pm_nl_set_limits $ns1 0 2
pm_nl_set_limits $ns2 0 2
- addr_nr_ns2=2 speed=slow \
+ addr_nr_ns2=2 speed=slow cestab_ns2=1 \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 2 2 2
+ chk_cestab_nr $ns2 0
fi
# add multiple subflows IPv6
if reset "add multiple subflows IPv6"; then
pm_nl_set_limits $ns1 0 2
pm_nl_set_limits $ns2 0 2
- addr_nr_ns2=2 speed=slow \
+ addr_nr_ns2=2 speed=slow cestab_ns2=1 \
run_tests $ns1 $ns2 dead:beef:1::1
chk_join_nr 2 2 2
+ chk_cestab_nr $ns2 0
fi
# add multiple addresses IPv6
if reset "add multiple addresses IPv6"; then
pm_nl_set_limits $ns1 0 2
pm_nl_set_limits $ns2 2 2
- addr_nr_ns1=2 speed=slow \
+ addr_nr_ns1=2 speed=slow cestab_ns1=1 \
run_tests $ns1 $ns2 dead:beef:1::1
chk_join_nr 2 2 2
chk_add_nr 2 2
+ chk_cestab_nr $ns1 0
fi
}
From 81ab772819da408977ac79c0a17d8be57283379f Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@linux.dev>
Date: Fri, 22 Dec 2023 13:47:25 +0100
Subject: [PATCH 4/4] selftests: mptcp: diag: check CURRESTAB counters
This patch adds a new helper chk_msk_cestab() to check the current
established connections counter MIB_CURRESTAB in diag.sh. Invoke it
to check the counter during the connection after every chk_msk_inuse().
Signed-off-by: Geliang Tang <geliang.tang@linux.dev>
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/mptcp/diag.sh | 17 ++++++++++++++++-
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 95b498efacd1..04fcb8a077c9 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -56,7 +56,7 @@ __chk_nr()
local command="$1"
local expected=$2
local msg="$3"
- local skip="${4:-SKIP}"
+ local skip="${4-SKIP}"
local nr
nr=$(eval $command)
@@ -182,6 +182,15 @@ chk_msk_inuse()
__chk_nr get_msk_inuse $expected "$msg" 0
}
+# $1: cestab nr
+chk_msk_cestab()
+{
+ local cestab=$1
+
+ __chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \
+ "${cestab}" "....chk ${cestab} cestab" ""
+}
+
wait_connected()
{
local listener_ns="${1}"
@@ -219,9 +228,11 @@ chk_msk_nr 2 "after MPC handshake "
chk_msk_remote_key_nr 2 "....chk remote_key"
chk_msk_fallback_nr 0 "....chk no fallback"
chk_msk_inuse 2 "....chk 2 msk in use"
+chk_msk_cestab 2
flush_pids
chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_cestab 0
echo "a" | \
timeout ${timeout_test} \
@@ -237,9 +248,11 @@ echo "b" | \
wait_connected $ns 10001
chk_msk_fallback_nr 1 "check fallback"
chk_msk_inuse 1 "....chk 1 msk in use"
+chk_msk_cestab 1
flush_pids
chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_cestab 0
NR_CLIENTS=100
for I in `seq 1 $NR_CLIENTS`; do
@@ -261,9 +274,11 @@ done
wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use"
+chk_msk_cestab $((NR_CLIENTS*2))
flush_pids
chk_msk_inuse 0 "....chk 0 msk in use after flush"
+chk_msk_cestab 0
mptcp_lib_result_print_all_tap
exit $ret