selftests/net: packetdrill: import tcp/zerocopy

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 (new)

Also import set_sysctls.py, which many scripts depend on to set
sysctls and then restore them later. This is no longer strictly needed
for namespacified sysctl. But not all sysctls are namespacified, and
doesn't hurt if they are.

Signed-off-by: Willem de Bruijn <[email protected]>
Acked-by: Matthieu Baerts (NGI0) <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: wdebruij

tools/testing/selftests/net/packetdrill/Makefile

@@ -2,6 +2,7 @@
 
 TEST_INCLUDES := ksft_runner.sh \
 		 defaults.sh \
+		 set_sysctls.py \
 		 ../../kselftest/ktap_helpers.sh
 
 TEST_PROGS := $(wildcard *.pkt)

tools/testing/selftests/net/packetdrill/set_sysctls.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Sets sysctl values and writes a file that restores them.
+
+The arguments are of the form "<proc-file>=<val>" separated by spaces.
+The program first reads the current value of the proc-file and creates
+a shell script named "/tmp/sysctl_restore_${PACKETDRILL_PID}.sh" which
+restores the values when executed. It then sets the new values.
+
+PACKETDRILL_PID is set by packetdrill to the pid of itself, so a .pkt
+file could restore sysctls by running `/tmp/sysctl_restore_${PPID}.sh`
+at the end.
+"""
+
+import os
+import subprocess
+import sys
+
+filename = '/tmp/sysctl_restore_%s.sh' % os.environ['PACKETDRILL_PID']
+
+# Open file for restoring sysctl values
+restore_file = open(filename, 'w')
+print('#!/bin/bash', file=restore_file)
+
+for a in sys.argv[1:]:
+  sysctl = a.split('=')
+  # sysctl[0] contains the proc-file name, sysctl[1] the new value
+
+  # read current value and add restore command to file
+  cur_val = subprocess.check_output(['cat', sysctl[0]], universal_newlines=True)
+  print('echo "%s" > %s' % (cur_val.strip(), sysctl[0]), file=restore_file)
+
+  # set new value
+  cmd = 'echo "%s" > %s' % (sysctl[1], sysctl[0])
+  os.system(cmd)
+
+os.system('chmod u+x %s' % filename)

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

@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+// basic zerocopy test:
+//
+// send a packet with MSG_ZEROCOPY and receive the notification ID
+// repeat and verify IDs are consecutive
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [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
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=1,
+                                    ee_data=1}}
+                   ]}, MSG_ERRQUEUE) = 0

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

@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+// batch zerocopy test:
+//
+// send multiple packets, then read one range of all notifications.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [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
+   +0 setsockopt(4, SOL_SOCKET, SO_MARK, [666], 4) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=1}}
+                  ]}, MSG_ERRQUEUE) = 0

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

@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Minimal client-side zerocopy test
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0...0 connect(4, ..., ...) = 0
+
+   +0 > S 0:0(0) <mss 1460,sackOK,TS val 0 ecr 0,nop,wscale 8>
+   +0 < S. 0:0(0) ack 1 win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > . 1:1(0) ack 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0

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

@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+// send with MSG_ZEROCOPY on a non-established socket
+//
+// verify that a send in state TCP_CLOSE correctly aborts the zerocopy
+// operation, specifically it does not increment the zerocopy counter.
+//
+// First send on a closed socket and wait for (absent) notification.
+// Then connect and send and verify that notification nr. is zero.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = -1 EPIPE (Broken pipe)
+
+   +0.1 recvmsg(4, {msg_name(...)=...,
+                    msg_iov(1)=[{...,0}],
+                    msg_flags=MSG_ERRQUEUE,
+                    msg_control=[]}, MSG_ERRQUEUE) = -1 EAGAIN (Resource temporarily unavailable)
+
+   +0...0 connect(4, ..., ...) = 0
+
+   +0 > S 0:0(0) <mss 1460,sackOK,TS val 0 ecr 0,nop,wscale 8>
+   +0 < S. 0:0(0) ack 1 win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > . 1:1(0) ack 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0

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

@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+// epoll zerocopy test:
+//
+// EPOLLERR is known to be not edge-triggered unlike EPOLLIN and EPOLLOUT but
+// it is not level-triggered either.
+//
+// fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR
+// is correctly fired only once, when EPOLLET is set. send another packet with
+// MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [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
+
+   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 epoll_create(1) = 5
+   +0 epoll_ctl(5, EPOLL_CTL_ADD, 4, {events=EPOLLOUT|EPOLLET, fd=4}) = 0
+   +0 epoll_wait(5, {events=EPOLLOUT, fd=4}, 1, 0) = 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+// receive only one EPOLLERR for the two sends above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 8001:12001(4000) ack 1
+   +0 < . 1:1(0) ack 12001 win 257
+
+// receive only one EPOLLERR for the third send above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=2}}
+                   ]}, MSG_ERRQUEUE) = 0

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

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+// epoll zerocopy test:
+//
+// EPOLLERR is known to be not edge-triggered unlike EPOLLIN and EPOLLOUT but
+// it is not level-triggered either. this tests verify that the same behavior is
+// maintained when we have EPOLLEXCLUSIVE.
+//
+// fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR
+// is correctly fired only once, when EPOLLET is set. send another packet with
+// MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [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
+
+   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 epoll_create(1) = 5
+   +0 epoll_ctl(5, EPOLL_CTL_ADD, 4,
+		{events=EPOLLOUT|EPOLLET|EPOLLEXCLUSIVE, fd=4}) = 0
+   +0 epoll_wait(5, {events=EPOLLOUT, fd=4}, 1, 0) = 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+// receive only one EPOLLERR for the two sends above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 8001:12001(4000) ack 1
+   +0 < . 1:1(0) ack 12001 win 257
+
+// receive only one EPOLLERR for the third send above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=2}}
+                   ]}, MSG_ERRQUEUE) = 0