selftests/net: integrate packetdrill with ksft

Lay the groundwork to import into kselftests the over 150 packetdrill
TCP/IP conformance tests on github.com/google/packetdrill.

Florian recently added support for packetdrill tests in nf_conntrack,
in commit a8a388c2aa ("selftests: netfilter: add packetdrill based
conntrack tests").

This patch takes a slightly different approach. It relies on
ksft_runner.sh to run every *.pkt file in the directory.

Any future imports of packetdrill tests should require no additional
coding. Just add the *.pkt files.

Initially import only two features/directories from github. One with a
single script, and one with two. This was the only reason to pick
tcp/inq and tcp/md5.

The path replaces the directory hierarchy in github with a flat space
of files: $(subst /,_,$(wildcard tcp/**/*.pkt)). This is the most
straightforward option to integrate with kselftests. The Linked thread
reviewed two ways to maintain the hierarchy: TEST_PROGS_RECURSE and
PRESERVE_TEST_DIRS. But both introduce significant changes to
kselftest infra and with that risk to existing tests.

Implementation notes:
- restore alphabetical order when adding the new directory to
  tools/testing/selftests/Makefile
- imported *.pkt files and support verbatim from the github project,
  except for
    - update `source ./defaults.sh` path (to adjust for flat dir)
    - add SPDX headers
    - remove one author statement
    - Acknowledgment: drop an e (checkpatch)

Tested:
	make -C tools/testing/selftests \
	  TARGETS=net/packetdrill \
	  run_tests

	make -C tools/testing/selftests \
	  TARGETS=net/packetdrill \
	  install INSTALL_PATH=$KSFT_INSTALL_PATH

	# in virtme-ng
	./run_kselftest.sh -c net/packetdrill
	./run_kselftest.sh -t net/packetdrill:tcp_inq_client.pkt

Link: https://lore.kernel.org/netdev/20240827193417.2792223-1-willemdebruijn.kernel@gmail.com/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240905231653.2427327-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

tools/testing/selftests/Makefile

@@ -65,10 +65,11 @@ TARGETS += net/af_unix
 TARGETS += net/forwarding
 TARGETS += net/hsr
 TARGETS += net/mptcp
-TARGETS += net/openvswitch
-TARGETS += net/tcp_ao
 TARGETS += net/netfilter
+TARGETS += net/openvswitch
+TARGETS += net/packetdrill
 TARGETS += net/rds
+TARGETS += net/tcp_ao
 TARGETS += nsfs
 TARGETS += perf_events
 TARGETS += pidfd

tools/testing/selftests/net/packetdrill/Makefile

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+TEST_INCLUDES := ksft_runner.sh \
+		 defaults.sh \
+		 ../../kselftest/ktap_helpers.sh
+
+TEST_PROGS := $(wildcard *.pkt)
+
+include ../../lib.mk

tools/testing/selftests/net/packetdrill/config

@@ -0,0 +1,5 @@
+CONFIG_IPV6=y
+CONFIG_NET_SCH_FIFO=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_TUN=y

tools/testing/selftests/net/packetdrill/defaults.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Set standard production config values that relate to TCP behavior.
+
+# Flush old cached data (fastopen cookies).
+ip tcp_metrics flush all > /dev/null 2>&1
+
+# TCP min, default, and max receive and send buffer sizes.
+sysctl -q net.ipv4.tcp_rmem="4096 540000 $((15*1024*1024))"
+sysctl -q net.ipv4.tcp_wmem="4096 $((256*1024)) 4194304"
+
+# TCP timestamps.
+sysctl -q net.ipv4.tcp_timestamps=1
+
+# TCP SYN(ACK) retry thresholds
+sysctl -q net.ipv4.tcp_syn_retries=5
+sysctl -q net.ipv4.tcp_synack_retries=5
+
+# TCP Forward RTO-Recovery, RFC 5682.
+sysctl -q net.ipv4.tcp_frto=2
+
+# TCP Selective Acknowledgements (SACK)
+sysctl -q net.ipv4.tcp_sack=1
+
+# TCP Duplicate Selective Acknowledgements (DSACK)
+sysctl -q net.ipv4.tcp_dsack=1
+
+# TCP FACK (Forward Acknowldgement)
+sysctl -q net.ipv4.tcp_fack=0
+
+# TCP reordering degree ("dupthresh" threshold for entering Fast Recovery).
+sysctl -q net.ipv4.tcp_reordering=3
+
+# TCP congestion control.
+sysctl -q net.ipv4.tcp_congestion_control=cubic
+
+# TCP slow start after idle.
+sysctl -q net.ipv4.tcp_slow_start_after_idle=0
+
+# TCP RACK and TLP.
+sysctl -q net.ipv4.tcp_early_retrans=4 net.ipv4.tcp_recovery=1
+
+# TCP method for deciding when to defer sending to accumulate big TSO packets.
+sysctl -q net.ipv4.tcp_tso_win_divisor=3
+
+# TCP Explicit Congestion Notification (ECN)
+sysctl -q net.ipv4.tcp_ecn=0
+
+sysctl -q net.ipv4.tcp_pacing_ss_ratio=200
+sysctl -q net.ipv4.tcp_pacing_ca_ratio=120
+sysctl -q net.ipv4.tcp_notsent_lowat=4294967295 > /dev/null 2>&1
+
+sysctl -q net.ipv4.tcp_fastopen=0x70403
+sysctl -q net.ipv4.tcp_fastopen_key=a1a1a1a1-b2b2b2b2-c3c3c3c3-d4d4d4d4
+
+sysctl -q net.ipv4.tcp_syncookies=1
+
+# Override the default qdisc on the tun device.
+# Many tests fail with timing errors if the default
+# is FQ and that paces their flows.
+tc qdisc add dev tun0 root pfifo
+

tools/testing/selftests/net/packetdrill/ksft_runner.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source "$(dirname $(realpath $0))/../../kselftest/ktap_helpers.sh"
+
+readonly ipv4_args=('--ip_version=ipv4 '
+		    '--local_ip=192.168.0.1 '
+		    '--gateway_ip=192.168.0.1 '
+		    '--netmask_ip=255.255.0.0 '
+		    '--remote_ip=192.0.2.1 '
+		    '-D CMSG_LEVEL_IP=SOL_IP '
+		    '-D CMSG_TYPE_RECVERR=IP_RECVERR ')
+
+readonly ipv6_args=('--ip_version=ipv6 '
+		    '--mtu=1520 '
+		    '--local_ip=fd3d:0a0b:17d6::1 '
+		    '--gateway_ip=fd3d:0a0b:17d6:8888::1 '
+		    '--remote_ip=fd3d:fa7b:d17d::1 '
+		    '-D CMSG_LEVEL_IP=SOL_IPV6 '
+		    '-D CMSG_TYPE_RECVERR=IPV6_RECVERR ')
+
+if [ $# -ne 1 ]; then
+	ktap_exit_fail_msg "usage: $0 <script>"
+	exit "$KSFT_FAIL"
+fi
+script="$1"
+
+if [ -z "$(which packetdrill)" ]; then
+	ktap_skip_all "packetdrill not found in PATH"
+	exit "$KSFT_SKIP"
+fi
+
+ktap_print_header
+ktap_set_plan 2
+
+packetdrill ${ipv4_args[@]} $(basename $script) > /dev/null \
+	&& ktap_test_pass "ipv4" || ktap_test_fail "ipv4"
+packetdrill ${ipv6_args[@]} $(basename $script) > /dev/null \
+	&& ktap_test_pass "ipv6" || ktap_test_fail "ipv6"
+
+ktap_finished

tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP_INQ and TCP_CM_INQ on the client side.
+`./defaults.sh
+`
+
+// Create a socket and set it to non-blocking.
+    0	socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0	fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+   +0	fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+// Connect to the server and enable TCP_INQ.
+   +0	connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+   +0	setsockopt(3, SOL_TCP, TCP_INQ, [1], 4) = 0
+
+   +0	> S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.01	< S. 0:0(0) ack 1 win 5792 <mss 1460,sackOK,TS val 700 ecr 100,nop,wscale 7>
+   +0	> . 1:1(0) ack 1 <nop,nop,TS val 200 ecr 700>
+
+// Now we have 10K of data ready on the socket.
+   +0	< . 1:10001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 10001 <nop,nop,TS val 200 ecr 700>
+
+// We read 1K and we should have 9K ready to read.
+   +0	recvmsg(3, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 1000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=9000}]}, 0) = 1000
+// We read 9K and we should have no further data ready to read.
+   +0	recvmsg(3, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 9000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=0}]}, 0) = 9000
+
+// Server sends more data and closes the connections.
+   +0	< F. 10001:20001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 20002 <nop,nop,TS val 200 ecr 700>
+
+// We read 10K and we should have one "fake" byte because the connection is
+// closed.
+   +0	recvmsg(3, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 10000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=1}]}, 0) = 10000
+// Now, receive EOF.
+   +0	read(3, ..., 2000) = 0

tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP_INQ and TCP_CM_INQ on the server side.
+`./defaults.sh
+`
+
+// Initialize connection
+    0	socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0	setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0	bind(3, ..., ...) = 0
+   +0	listen(3, 1) = 0
+
+   +0	< S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+   +0	> S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01	< . 1:1(0) ack 1 win 514
+
+// Accept the connection and enable TCP_INQ.
+   +0	accept(3, ..., ...) = 4
+   +0	setsockopt(4, SOL_TCP, TCP_INQ, [1], 4) = 0
+
+// Now we have 10K of data ready on the socket.
+   +0	< . 1:10001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 10001
+
+// We read 2K and we should have 8K ready to read.
+   +0	recvmsg(4, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 2000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=8000}]}, 0) = 2000
+// We read 8K and we should have no further data ready to read.
+   +0	recvmsg(4, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 8000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=0}]}, 0) = 8000
+// Client sends more data and closes the connections.
+   +0	< F. 10001:20001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 20002
+
+// We read 10K and we should have one "fake" byte because the connection is
+// closed.
+   +0	recvmsg(4, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 10000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=1}]}, 0) = 10000
+// Now, receive error.
+   +0	read(3, ..., 2000) = -1 ENOTCONN (Transport endpoint is not connected)

tools/testing/selftests/net/packetdrill/tcp_md5_md5-only-on-client-ack.pkt

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test what happens when client does not provide MD5 on SYN,
+// but then does on the ACK that completes the three-way handshake.
+
+`./defaults.sh`
+
+// Establish a connection.
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+// Ooh, weird: client provides MD5 option on the ACK:
+ +.01 < . 1:1(0) ack 1 win 514 <md5 000102030405060708090a0b0c0d0e0f,nop,nop>
+ +.01 < . 1:1(0) ack 1 win 514 <md5 000102030405060708090a0b0c0d0e0f,nop,nop>
+
+// The TCP listener refcount should be 2, but on buggy kernels it can be 0:
+   +0 `grep " 0A " /proc/net/tcp /proc/net/tcp6 | grep ":1F90"`
+
+// Now here comes the legit ACK:
+ +.01 < . 1:1(0) ack 1 win 514
+
+// Make sure the connection is OK:
+   +0 accept(3, ..., ...) = 4
+
+ +.01 write(4, ..., 1000) = 1000