Skip to contentSkip to conversation

mptcp: sync the msk->sndbuf at accept() time

PATCH Superseded Gang Yan 4 participants 7 messages Apr 7 – Apr 11

Subsystems (3)

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore

Gang Yan

author
#0 lore raw

v3 cover mptcp: sync the msk->sndbuf at accept() time

From: Gang Yan <[email protected]>

Changelog:
v3:
- Add a check in diag.sh to check the sndbuf of the server side.

Gang Yan (2):
mptcp: sync the msk->sndbuf at accept() time
selftests: mptcp: add a check for sndbuf of S/C

 net/mptcp/protocol.c                      |  1 +
 tools/testing/selftests/net/mptcp/diag.sh | 26 +++++++++++++++++++++++
 2 files changed, 27 insertions(+)
Signature · 1 line
2.43.0
author
#1 lore raw

PATCH v3 1/2 mptcp: sync the msk->sndbuf at accept() time

From: Gang Yan <[email protected]>

After an MPTCP connection is established, the sk_sndbuf of client's msk can be updated through 'subflow_finish_connect'. However, the newly accepted msk on the server side has a small sk_sndbuf than msk->first->sk_sndbuf:

'''
MPTCP: msk:00000000e55b09db, msk->sndbuf:20480, msk->first->sndbuf:2626560 '''

This patch synchronizes the sk_sndbuf by triggering its update during accept.

Fixes 8005184fd1ca ("mptcp: refactor sndbuf auto-tuning")
---
 net/mptcp/protocol.c | 1 +
 1 file changed, 1 insertion(+)
net/mptcp/protocol.c +1 -0
index 17b9a8c13ebf..6f6c8cabf74f 100644
@@ -4252,6 +4252,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 
 		mptcp_graft_subflows(newsk);
 		mptcp_rps_record_subflows(msk);
+		__mptcp_propagate_sndbuf(newsk, mptcp_subflow_tcp_sock(subflow));
 
 		/* Do late cleanup for the first subflow as necessary. Also
 		 * deal with bad peers not doing a complete shutdown.
Signature · 1 line
2.43.0
maintainer Acked-by on v3 1/2
#2 lore raw
Quoted 7 lines · Gang Yan

From: Gang Yan <[email protected]>

After an MPTCP connection is established, the sk_sndbuf of client's msk can be updated through 'subflow_finish_connect'. However, the newly accepted msk on the server side has a small sk_sndbuf than msk->first->sk_sndbuf:

Quoted 6 lines

'''
MPTCP: msk:00000000e55b09db, msk->sndbuf:20480, msk->first->sndbuf:2626560 '''

This patch synchronizes the sk_sndbuf by triggering its update during accept.

I finally could wrap my head around the root cause: tcp_child_process() -> tcp_init_transfer() -> tcp_sndbuf_expand() can and will grow the ssk sndbuf _after_ tcp_check_req() -> subflow_syn_recv_sock() -> mptcp_sk_clone_init() where __mptcp_propagate_sndbuf() is currently hooked.

I think the latter __mptcp_propagate_sndbuf() invocation can be removed, and the commit message expanded to capture some of the above.

With the above included feel free to add:

maintainer
#3 lore raw

Hi Paolo,

Quoted 20 lines · Paolo Abeni
Quoted 7 lines · Gang Yan

From: Gang Yan <[email protected]>

After an MPTCP connection is established, the sk_sndbuf of client's msk can be updated through 'subflow_finish_connect'. However, the newly accepted msk on the server side has a small sk_sndbuf than msk->first->sk_sndbuf:

Quoted 6 lines

'''
MPTCP: msk:00000000e55b09db, msk->sndbuf:20480, msk->first->sndbuf:2626560 '''

This patch synchronizes the sk_sndbuf by triggering its update during accept.

I finally could wrap my head around the root cause: tcp_child_process() -> tcp_init_transfer() -> tcp_sndbuf_expand() can and will grow the ssk sndbuf _after_ tcp_check_req() -> subflow_syn_recv_sock() -> mptcp_sk_clone_init() where __mptcp_propagate_sndbuf() is currently hooked.

Quoted 6 lines

I think the latter __mptcp_propagate_sndbuf() invocation can be removed, and the commit message expanded to capture some of the above.

With the above included feel free to add:

Thank you for this review!

Cheers,
Matt

Signature · 1 line
Sponsored by the NGI0 Core fund.
#4 lore raw
In reply to Paolo Abeni
Quoted 23 lines · Paolo Abeni
Quoted 8 lines · Gang Yan

From: Gang Yan <[email protected]>

After an MPTCP connection is established, the sk_sndbuf of client's msk can be updated through 'subflow_finish_connect'. However, the newly accepted msk on the server side has a small sk_sndbuf than msk->first->sk_sndbuf:

Quoted 7 lines

'''
MPTCP: msk:00000000e55b09db, msk->sndbuf:20480, msk->first->sndbuf:2626560 '''

This patch synchronizes the sk_sndbuf by triggering its update during accept.

I finally could wrap my head around the root cause: tcp_child_process() -> tcp_init_transfer() -> tcp_sndbuf_expand() can and will grow the ssk sndbuf _after_ tcp_check_req() -> subflow_syn_recv_sock() -> mptcp_sk_clone_init() where __mptcp_propagate_sndbuf() is currently hooked.

Quoted 6 lines

I think the latter __mptcp_propagate_sndbuf() invocation can be removed, and the commit message expanded to capture some of the above.

With the above included feel free to add:

Hi Paolo,

Thanks for your suggestions. The v4 code will be sent soon.

Cherrs,
Gang

Quoted 1 line
author
#5 lore raw

PATCH v3 2/2 selftests: mptcp: add a check for sndbuf of S/C

In reply to Gang Yan

From: Gang Yan <[email protected]>

Add a new chk_sndbuf() helper to diag.sh that extracts the sndbuf (the 'tb' field from 'ss -m' skmem output) for both server and client MPTCP sockets, and verifies they are equal.

Without the previous patch, it will fails:

'''

05 all listen sockets                                [ OK ]
06 after MPC handshake                               [ OK ]
07 ....chk sndbuf server/client                      [FAIL] server sndbuf=20480 != client sndbuf=2630656

'''

---
 tools/testing/selftests/net/mptcp/diag.sh | 26 +++++++++++++++++++++++
 1 file changed, 26 insertions(+)
tools/testing/selftests/net/mptcp/diag.sh +26 -0
index d847ff1737c3..aa01a1dd0bdd 100755
@@ -322,6 +322,31 @@ wait_connected()
 	done
 }
 
+chk_sndbuf()
+{
+	local server_sndbuf client_sndbuf msg
+	local port=${1}
+
+	msg="....chk sndbuf server/client"
+	server_sndbuf=$(ss -N "${ns}" -inmHM "sport" "${port}" | grep -oP 'tb\K\d+')
+	client_sndbuf=$(ss -N "${ns}" -inmHM "dport" "${port}" | grep -oP 'tb\K\d+')
+
+	mptcp_lib_print_title "${msg}"
+	if [ -z "${server_sndbuf}" ] || [ -z "${client_sndbuf}" ]; then
+		mptcp_lib_pr_fail "server sndbuf=${server_sndbuf} client sndbuf=${client_sndbuf}"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	elif [ "${server_sndbuf}" != "${client_sndbuf}" ]; then
+		mptcp_lib_pr_fail "server sndbuf=${server_sndbuf} != client sndbuf=${client_sndbuf}"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	else
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	fi
+}
+
+
 trap cleanup EXIT
 mptcp_lib_ns_init ns
 
@@ -341,6 +366,7 @@ echo "b" | \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10000
 chk_msk_nr 2 "after MPC handshake"
+chk_sndbuf 10000
 chk_last_time_info 10000
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
Signature · 1 line
2.43.0
#6 lore raw
In reply to Gang Yan

Hi Gang,

Thank you for your modifications, that's great!

Our CI did some validations and here is its report:

- KVM Validation: normal (except selftest_mptcp_join): Success! ✅
- KVM Validation: normal (only selftest_mptcp_join): Success! ✅
- KVM Validation: debug (except selftest_mptcp_join): Unstable: 1 failed test(s): packetdrill_sockopts ⚠️
- KVM Validation: debug (only selftest_mptcp_join): Success! ✅
- KVM Validation: btf-normal (only bpftest_all): Success! ✅
- KVM Validation: btf-debug (only bpftest_all): Success! ✅
- Task: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/24181789538

Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/7359a54dfdbd
Patchwork: https://patchwork.kernel.org/project/mptcp/list/?series=1078012

If there are some issues, you can reproduce them using the same environment as the one used by the CI thanks to a docker image, e.g.:

    $ cd [kernel source code]
    $ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
        --pull always mptcp/mptcp-upstream-virtme-docker:latest \
        auto-normal

For more details:

https://github.com/multipath-tcp/mptcp-upstream-virtme-docker

Please note that despite all the efforts that have been already done to have a stable tests suite when executed on a public CI like here, it is possible some reported issues are not due to your modifications. Still, do not hesitate to help us improve that ;-)

Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (NGI0 Core)