selftests/net: packetdrill: import tcp/ecn, tcp/close, tcp/sack, tcp/…

…tcp_info

Same as initial tests, import verbatim from
github.com/google/packetdrill, aside from:

- update `source ./defaults.sh` path to adjust for flat dir
- add SPDX headers
- remove author statements if any
- drop blank lines at EOF

Same test process as previous tests. Both with and without debug mode.
Recording the steps once:

make mrproper
vng --build \
--config tools/testing/selftests/net/packetdrill/config \
--config kernel/configs/debug.config
vng -v --run . --user root --cpus 4 -- \
make -C tools/testing/selftests TARGETS=net/packetdrill run_tests

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Soham Chakradeo <sohamch@google.com>
Link: https://patch.msgid.link/20241217185203.297935-2-sohamch.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test basic connection teardown where local process closes first:
+// the local process calls close() first, so we send a FIN, and receive an ACK.
+// Then we receive a FIN and ACK it.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +.01...0.011 connect(3, ..., ...) = 0
+   +0 >  S 0:0(0) <...>
+   +0 < S. 0:0(0) ack 1 win 32768 <mss 1000,nop,wscale 6,nop,nop,sackOK>
+   +0 >  . 1:1(0) ack 1
+
+   +0 write(3, ..., 1000) = 1000
+   +0 >  P. 1:1001(1000) ack 1
+   +0 < . 1:1(0) ack 1001 win 257
+
+   +0 close(3) = 0
+   +0 >  F. 1001:1001(0) ack 1
+   +0 < . 1:1(0) ack 1002 win 257
+
+   +0 < F. 1:1(0) ack 1002 win 257
+   +0 >  . 1002:1002(0) ack 2

tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test to make sure no RST is being sent when close()
+// is called on a socket with SYN_SENT state.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+   +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+   +0 > S 0:0(0) <...>
+
+// Application decideds to close the socket in SYN_SENT state
+// Make sure no RST is sent after close().
+   +0 close(3) = 0
+
+// Receive syn-ack to trigger the send side packet examination:
+// If a RESET were sent right after close(), it would have failed with
+// a mismatched timestamp.
+  +.1 < S. 0:0(0) ack 1 win 32000 <mss 1460,nop,wscale 7>
+   +0 > R 1:1(0)

tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt

@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+// Verify behavior for the sequence: remote side sends FIN, then we close().
+// Since the remote side (client) closes first, we test our LAST_ACK code path.
+
+`./defaults.sh`
+
+// Initialize a server socket.
+    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 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+// Client closes first.
+ +.01 < F. 1:1(0) ack 1 win 257
+   +0 > . 1:1(0) ack 2
+
+// App notices that client closed.
+   +0 read(4, ..., 1000) = 0
+
+// Then we close.
+ +.01 close(4) = 0
+   +0 > F. 1:1(0) ack 2
+
+// Client ACKs our FIN.
+ +.01 < . 2:2(0) ack 2 win 257
+
+// Verify that we send RST in response to any incoming segments
+// (because the kernel no longer has any record of this socket).
+ +.01 < . 2:2(0) ack 2 win 257
+   +0 > R 2:2(0)

tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test ECN: verify that Linux TCP ECN sending code uses ECT0 (not ECT1).
+//
+`./defaults.sh
+sysctl -q net.ipv4.tcp_ecn=1  # fully enabled
+`
+
+// Initialize connection
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+
+// ECN handshake: send EW flags in SYN packet, E flag in SYN-ACK response
++.002 ... 0.004 connect(4, ..., ...) = 0
+
+   +0 > SEW 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
++.002 < SE. 0:0(0) ack 1 win 32767 <mss 1000,nop,wscale 6,nop,nop,sackOK>
+   +0 > . 1:1(0) ack 1
+
+// Write 1 MSS.
++.002 write(4, ..., 1000) = 1000
+// Send 1 MSS with ect0.
+   +0 > [ect0] P. 1:1001(1000) ack 1

tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+// Verify that setsockopt calls that force a route refresh do not
+// cause problems matching SACKs with packets in the write queue.
+// This variant tests IP_TOS.
+
+`./defaults.sh`
+
+// Establish a connection.
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_IP, IP_MTU_DISCOVER, [IP_PMTUDISC_DONT], 1) = 0
+   +0...0.010 connect(3, ..., ...) = 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 65535 <mss 1460,nop,wscale 2,nop,nop,sackOK>
+   +0 > . 1:1(0) ack 1
+
+ +.01 write(3, ..., 5840) = 5840
+   +0 > P. 1:5841(5840) ack 1
+ +.01 < . 1:1(0) ack 5841 win 65535
+
+ +.01 write(3, ..., 5840) = 5840
+   +0 > P. 5841:11681(5840) ack 1
+ +.01 < . 1:1(0) ack 11681 win 65535
+
+ +.01 write(3, ..., 14600) = 14600
+   +0 > P. 11681:26281(14600) ack 1
+
+// Try the socket option that we know can force a route refresh.
+   +0 setsockopt(3, SOL_IP, IP_TOS, [4], 1) = 0
+// Then revert to avoid routing/mangling/etc implications of that setting.
+   +0 setsockopt(3, SOL_IP, IP_TOS, [0], 1) = 0
+
+// Verify that we do not retransmit the SACKed segments.
+ +.01 < . 1:1(0) ack 13141 win 65535 <sack 16061:17521 20441:26281,nop,nop>
+   +0 > . 13141:16061(2920) ack 1
+   +0 > P. 17521:20441(2920) ack 1
+ +.01 < . 1:1(0) ack 26281 win 65535

tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt

@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb.
+// This variant tests non-FACK SACK with SACKs coming in the order
+// 2 6 8 3 9, to test what happens when we get a new SACKed range
+// (for packet 3) that is on the right of an existing SACKed range
+// (for packet 2).
+
+`./defaults.sh`
+
+// Establish a connection and send 10 MSS.
+    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 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 1024
+   +0 accept(3, ..., ...) = 4
+
+   +0 write(4, ..., 10000) = 10000
+   +0 > P. 1:10001(10000) ack 1
+
+  +.1 < . 1:1(0) ack 1 win 257 <sack 2001:3001,nop,nop>
++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001,nop,nop>
++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001 8001:9001,nop,nop>
+
+// 3 SACKed packets, so we enter Fast Recovery.
+   +0 > . 1:1001(1000) ack 1
+   +0 %{ assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state }%
+   +0 %{ assert tcpi_lost == 6, tcpi_lost }%
+
+// SACK for 3001:4001.
+// This SACK for an adjacent range causes the sender to
+// shift the newly-SACKed range onto the previous skb.
++.007 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:9001,nop,nop>
+   +0 > . 1001:2001(1000) ack 1
+   +0 %{ assert tcpi_lost == 5, tcpi_lost }%
+   +0 %{ assert tcpi_reordering == 6, tcpi_reordering }%   // 8001:9001 -> 3001:4001 is 6
+
+// SACK for 9001:10001.
+ +.01 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop>
+   +0 %{ assert tcpi_lost == 5, tcpi_lost }%
+
+// ACK for 1:1001 as packets from t=0.303 arrive.
++.083 < . 1:1(0) ack 1001 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop>
+   +0 %{ assert tcpi_lost == 4,tcpi_lost }%
+
+// ACK for 1:4001 as packets from t=0.310 arrive.
++.017 < . 1:1(0) ack 4001 win 257 <sack 6001:7001 8001:10001,nop,nop>
+   +0 %{ assert tcpi_lost == 3,tcpi_lost }%
+
+// ACK for 1:7001 as packets from t=0.320 arrive.
+ +.01 < . 1:1(0) ack 7001 win 257 <sack 8001:10001,nop,nop>
+
+// ACK for all data as packets from t=0.403 arrive.
+  +.1 < . 1:1(0) ack 10001 win 257
+   +0 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_unacked == 0, tcpi_unacked
+assert tcpi_sacked == 0, tcpi_sacked
+assert tcpi_lost == 0, tcpi_lost
+assert tcpi_retrans == 0, tcpi_retrans
+}%

tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt

@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb.
+// This variant tests the case where we mark packets 0-4 lost, then
+// get a SACK for 3, and then a SACK for 4.
+
+`./defaults.sh`
+
+// Establish a connection and send 10 MSS.
+    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 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 1024
+   +0 accept(3, ..., ...) = 4
+
+   +0 write(4, ..., 10000) = 10000
+   +0 > P. 1:10001(10000) ack 1
+
+// SACK for 7001:8001. Using RACK we delay the fast retransmit.
+  +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop>
+// RACK reordering timer
++.027 > . 1:1001(1000) ack 1
+   +0 %{
+assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state
+assert tcpi_lost == 7, tcpi_lost  # RACK thinks 1:7001 are lost
+assert tcpi_reordering == 3, tcpi_reordering
+}%
+
+// SACK for 3001:4001.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:4001 7001:8001,nop,nop>
+   +0 > . 1001:2001(1000) ack 1
+   +0 %{
+assert tcpi_lost == 6, tcpi_lost              # since 3001:4001 is no longer lost
+assert tcpi_reordering == 5, tcpi_reordering  # 7001:8001 -> 3001:4001
+}%
+
+// SACK for 4001:5001.
+// This SACK for an adjacent range causes the sender to
+// shift the newly-SACKed range onto the previous skb.
+// It uses the RFC3517 algorithm to mark 1:3001 lost
+// because >=3 higher-sequence packets are SACKed.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:8001,nop,nop>
+   +0 > . 2001:3001(1000) ack 1
+   +0 %{
+assert tcpi_lost == 5,tcpi_lost         # SACK/RFC3517 thinks 1:3001 are lost
+}%
+
+// SACK for 8001:9001.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:9001,nop,nop>
+
+// SACK for 9001:10001.
++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:10001,nop,nop>
+   +0 > . 5001:6001(1000) ack 1
+
+// To simplify clean-up, say we get an ACK for all data.
+  +.1 < . 1:1(0) ack 10001 win 257
+   +0 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_unacked == 0, tcpi_unacked
+assert tcpi_sacked == 0, tcpi_sacked
+assert tcpi_lost == 0, tcpi_lost
+assert tcpi_retrans == 0, tcpi_retrans
+}%

tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt

@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb.
+// This variant tests the case where we mark packets 0-4 lost, then
+// get a SACK for 5, and then a SACK for 6.
+
+`./defaults.sh`
+
+// Establish a connection and send 10 MSS.
+    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 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 1024
+   +0 accept(3, ..., ...) = 4
+
+   +0 write(4, ..., 10000) = 10000
+   +0 > P. 1:10001(10000) ack 1
+
+// SACK for 7001:8001. Using RACK we delay a fast retransmit.
+  +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop>
++.027 > . 1:1001(1000) ack 1
+   +0 %{
+assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state
+assert tcpi_lost == 7,tcpi_lost         # RACK thinks 1:7001 are lost
+assert tcpi_reordering == 3, tcpi_reordering
+}%
+
+// SACK for 5001:6001.
+   +0 < . 1:1(0) ack 1 win 257 <sack 5001:6001 7001:8001,nop,nop>
+   +0 > . 1001:2001(1000) ack 1
+   +0 %{
+assert tcpi_lost == 6, tcpi_lost
+assert tcpi_reordering == 3, tcpi_reordering  # 7001:8001 -> 5001:6001 is 3
+}%
+
+// SACK for 6001:7001.
+// This SACK for an adjacent range causes the sender to
+// shift the newly-SACKed range onto the previous skb.
+   +0 < . 1:1(0) ack 1 win 257 <sack 5001:8001,nop,nop>
+   +0 > . 2001:3001(1000) ack 1
+   +0 %{ assert tcpi_lost == 5, tcpi_lost }%
+
+// SACK for 8001:9001.
+   +0 < . 1:1(0) ack 1 win 257 <sack 5001:9001,nop,nop>
+   +0 > . 3001:4001(1000) ack 1
+
+// SACK for 9001:10001.
+   +0 < . 1:1(0) ack 1 win 257 <sack 5001:10001,nop,nop>
+   +0 > . 4001:5001(1000) ack 1
+
+// To simplify clean-up, say we get an ACK for all data.
+  +.1 < . 1:1(0) ack 10001 win 257
+   +0 %{
+assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state
+assert tcpi_unacked == 0, tcpi_unacked
+assert tcpi_sacked == 0, tcpi_sacked
+assert tcpi_lost == 0, tcpi_lost
+assert tcpi_retrans == 0, tcpi_retrans
+}%

tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt

@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test tcpi_last_data_recv for active session
+`./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
+
++0    connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
++0    > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
++.030 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8>
++0    > . 1:1(0) ack 1
+
++1 %{ assert 990 <= tcpi_last_data_recv <= 1010, tcpi_last_data_recv }%
+
++0    < . 1:1001(1000) ack 1 win 300
++0    > . 1:1(0) ack 1001
+
++0 %{ assert tcpi_last_data_recv <= 10, tcpi_last_data_recv }%