Resguardo inicial

linux-7.2.3/tools/testing/vsock/.gitignore

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+*.d
+vsock_test
+vsock_diag_test
+vsock_perf
+vsock_uring_test

linux-7.2.3/tools/testing/vsock/Makefile

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0-only
+all: test vsock_perf
+test: vsock_test vsock_diag_test vsock_uring_test
+vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_zerocopy_common.o
+vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o
+vsock_perf: vsock_perf.o msg_zerocopy_common.o
+
+vsock_test: LDLIBS = -lpthread
+vsock_uring_test: LDLIBS = -luring
+vsock_uring_test: control.o util.o vsock_uring_test.o timeout.o msg_zerocopy_common.o
+
+CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE
+.PHONY: all test clean
+clean:
+	${RM} *.o *.d vsock_test vsock_diag_test vsock_perf vsock_uring_test
+-include *.d
+
+VSOCK_INSTALL_PATH ?=
+
+install: all
+ifdef VSOCK_INSTALL_PATH
+	mkdir -p $(VSOCK_INSTALL_PATH)
+	install -m 744 vsock_test $(VSOCK_INSTALL_PATH)
+	install -m 744 vsock_perf $(VSOCK_INSTALL_PATH)
+	install -m 744 vsock_diag_test $(VSOCK_INSTALL_PATH)
+	install -m 744 vsock_uring_test $(VSOCK_INSTALL_PATH)
+else
+	$(error Error: set VSOCK_INSTALL_PATH to use install)
+endif

linux-7.2.3/tools/testing/vsock/README

@@ -0,0 +1,86 @@
+AF_VSOCK test suite
+-------------------
+These tests exercise net/vmw_vsock/ host<->guest sockets for VMware, KVM, and
+Hyper-V.
+
+The following tests are available:
+
+  * vsock_test - core AF_VSOCK socket functionality
+  * vsock_diag_test - vsock_diag.ko module for listing open sockets
+
+The following prerequisite steps are not automated and must be performed prior
+to running tests:
+
+1. Build the kernel, make headers_install, and build these tests.
+2. Install the kernel and tests on the host.
+3. Install the kernel and tests inside the guest.
+4. Boot the guest and ensure that the AF_VSOCK transport is enabled.
+
+Invoke test binaries in both directions as follows:
+
+  # host=server, guest=client
+  (host)# $TEST_BINARY --mode=server \
+                       --control-port=1234 \
+                       --peer-cid=3
+  (guest)# $TEST_BINARY --mode=client \
+                        --control-host=$HOST_IP \
+                        --control-port=1234 \
+                        --peer-cid=2
+
+  # host=client, guest=server
+  (guest)# $TEST_BINARY --mode=server \
+                        --control-port=1234 \
+                        --peer-cid=2
+  (host)# $TEST_BINARY --mode=client \
+                       --control-port=$GUEST_IP \
+                       --control-port=1234 \
+                       --peer-cid=3
+
+Some tests are designed to produce kernel memory leaks. Leaks detection,
+however, is deferred to Kernel Memory Leak Detector. It is recommended to enable
+kmemleak (CONFIG_DEBUG_KMEMLEAK=y) and explicitly trigger a scan after each test
+suite run, e.g.
+
+  # echo clear > /sys/kernel/debug/kmemleak
+  # $TEST_BINARY ...
+  # echo "wait for any grace periods" && sleep 2
+  # echo scan > /sys/kernel/debug/kmemleak
+  # echo "wait for kmemleak" && sleep 5
+  # echo scan > /sys/kernel/debug/kmemleak
+  # cat /sys/kernel/debug/kmemleak
+
+For more information see Documentation/dev-tools/kmemleak.rst.
+
+vsock_perf utility
+-------------------
+'vsock_perf' is a simple tool to measure vsock performance. It works in
+sender/receiver modes: sender connect to peer at the specified port and
+starts data transmission to the receiver. After data processing is done,
+it prints several metrics(see below).
+
+Usage:
+# run as sender
+# connect to CID 2, port 1234, send 1G of data, tx buf size is 1M
+./vsock_perf --sender 2 --port 1234 --bytes 1G --buf-size 1M
+
+Output:
+tx performance: A Gbits/s
+
+Output explanation:
+A is calculated as "number of bits to send" / "time in tx loop"
+
+# run as receiver
+# listen port 1234, rx buf size is 1M, socket buf size is 1G, SO_RCVLOWAT is 64K
+./vsock_perf --port 1234 --buf-size 1M --vsk-size 1G --rcvlowat 64K
+
+Output:
+rx performance: A Gbits/s
+total in 'read()': B sec
+POLLIN wakeups: C
+average in 'read()': D ns
+
+Output explanation:
+A is calculated as "number of received bits" / "time in rx loop".
+B is time, spent in 'read()' system call(excluding 'poll()')
+C is number of 'poll()' wake ups with POLLIN bit set.
+D is B / C, e.g. average amount of time, spent in single 'read()'.

linux-7.2.3/tools/testing/vsock/control.c

@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Control socket for client/server test execution
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ */
+
+/* The client and server may need to coordinate to avoid race conditions like
+ * the client attempting to connect to a socket that the server is not
+ * listening on yet.  The control socket offers a communications channel for
+ * such coordination tasks.
+ *
+ * If the client calls control_expectln("LISTENING"), then it will block until
+ * the server calls control_writeln("LISTENING").  This provides a simple
+ * mechanism for coordinating between the client and the server.
+ */
+
+#include <errno.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "timeout.h"
+#include "control.h"
+#include "util.h"
+
+static int control_fd = -1;
+
+/* Open the control socket, either in server or client mode */
+void control_init(const char *control_host,
+		  const char *control_port,
+		  bool server)
+{
+	struct addrinfo hints = {
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *result = NULL;
+	struct addrinfo *ai;
+	int ret;
+
+	ret = getaddrinfo(control_host, control_port, &hints, &result);
+	if (ret != 0) {
+		fprintf(stderr, "%s\n", gai_strerror(ret));
+		exit(EXIT_FAILURE);
+	}
+
+	for (ai = result; ai; ai = ai->ai_next) {
+		int fd;
+
+		fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+		if (fd < 0)
+			continue;
+
+		if (!server) {
+			if (connect(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+				goto next;
+			control_fd = fd;
+			printf("Control socket connected to %s:%s.\n",
+			       control_host, control_port);
+			break;
+		}
+
+		setsockopt_int_check(fd, SOL_SOCKET, SO_REUSEADDR, 1,
+				     "setsockopt SO_REUSEADDR");
+
+		if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+			goto next;
+		if (listen(fd, 1) < 0)
+			goto next;
+
+		printf("Control socket listening on %s:%s\n",
+		       control_host, control_port);
+		fflush(stdout);
+
+		control_fd = accept(fd, NULL, 0);
+		close(fd);
+
+		if (control_fd < 0) {
+			perror("accept");
+			exit(EXIT_FAILURE);
+		}
+		printf("Control socket connection accepted...\n");
+		break;
+
+next:
+		close(fd);
+	}
+
+	if (control_fd < 0) {
+		fprintf(stderr, "Control socket initialization failed.  Invalid address %s:%s?\n",
+			control_host, control_port);
+		exit(EXIT_FAILURE);
+	}
+
+	freeaddrinfo(result);
+}
+
+/* Free resources */
+void control_cleanup(void)
+{
+	close(control_fd);
+	control_fd = -1;
+}
+
+/* Write a line to the control socket */
+void control_writeln(const char *str)
+{
+	ssize_t len = strlen(str);
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+
+	do {
+		ret = send(control_fd, str, len, MSG_MORE);
+		timeout_check("send");
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret != len) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	do {
+		ret = send(control_fd, "\n", 1, 0);
+		timeout_check("send");
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret != 1) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	timeout_end();
+}
+
+void control_writeulong(unsigned long value)
+{
+	char str[32];
+
+	if (snprintf(str, sizeof(str), "%lu", value) >= sizeof(str)) {
+		perror("snprintf");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln(str);
+}
+
+unsigned long control_readulong(void)
+{
+	unsigned long value;
+	char *str;
+
+	str = control_readln();
+
+	if (!str)
+		exit(EXIT_FAILURE);
+
+	value = strtoul(str, NULL, 10);
+	free(str);
+
+	return value;
+}
+
+/* Return the next line from the control socket (without the trailing newline).
+ *
+ * The program terminates if a timeout occurs.
+ *
+ * The caller must free() the returned string.
+ */
+char *control_readln(void)
+{
+	char *buf = NULL;
+	size_t idx = 0;
+	size_t buflen = 0;
+
+	timeout_begin(TIMEOUT);
+
+	for (;;) {
+		ssize_t ret;
+
+		if (idx >= buflen) {
+			char *new_buf;
+
+			new_buf = realloc(buf, buflen + 80);
+			if (!new_buf) {
+				perror("realloc");
+				exit(EXIT_FAILURE);
+			}
+
+			buf = new_buf;
+			buflen += 80;
+		}
+
+		do {
+			ret = recv(control_fd, &buf[idx], 1, 0);
+			timeout_check("recv");
+		} while (ret < 0 && errno == EINTR);
+
+		if (ret == 0) {
+			fprintf(stderr, "unexpected EOF on control socket\n");
+			exit(EXIT_FAILURE);
+		}
+
+		if (ret != 1) {
+			perror("recv");
+			exit(EXIT_FAILURE);
+		}
+
+		if (buf[idx] == '\n') {
+			buf[idx] = '\0';
+			break;
+		}
+
+		idx++;
+	}
+
+	timeout_end();
+
+	return buf;
+}
+
+/* Wait until a given line is received or a timeout occurs */
+void control_expectln(const char *str)
+{
+	char *line;
+
+	line = control_readln();
+
+	control_cmpln(line, str, true);
+
+	free(line);
+}
+
+bool control_cmpln(char *line, const char *str, bool fail)
+{
+	if (strcmp(str, line) == 0)
+		return true;
+
+	if (fail) {
+		fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n",
+			str, line);
+		exit(EXIT_FAILURE);
+	}
+
+	return false;
+}

linux-7.2.3/tools/testing/vsock/control.h

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef CONTROL_H
+#define CONTROL_H
+
+#include <stdbool.h>
+
+void control_init(const char *control_host, const char *control_port,
+		  bool server);
+void control_cleanup(void);
+void control_writeln(const char *str);
+char *control_readln(void);
+unsigned long control_readulong(void);
+void control_expectln(const char *str);
+bool control_cmpln(char *line, const char *str, bool fail);
+void control_writeulong(unsigned long value);
+
+#endif /* CONTROL_H */

linux-7.2.3/tools/testing/vsock/msg_zerocopy_common.c

@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Some common code for MSG_ZEROCOPY logic
+ *
+ * Copyright (C) 2023 SberDevices.
+ *
+ * Author: Arseniy Krasnov <avkrasnov@salutedevices.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <linux/errqueue.h>
+
+#include "msg_zerocopy_common.h"
+
+void vsock_recv_completion(int fd, const bool *zerocopied)
+{
+	struct sock_extended_err *serr;
+	struct msghdr msg = { 0 };
+	char cmsg_data[128];
+	struct cmsghdr *cm;
+	ssize_t res;
+
+	msg.msg_control = cmsg_data;
+	msg.msg_controllen = sizeof(cmsg_data);
+
+	res = recvmsg(fd, &msg, MSG_ERRQUEUE);
+	if (res) {
+		fprintf(stderr, "failed to read error queue: %zi\n", res);
+		exit(EXIT_FAILURE);
+	}
+
+	cm = CMSG_FIRSTHDR(&msg);
+	if (!cm) {
+		fprintf(stderr, "cmsg: no cmsg\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (cm->cmsg_level != SOL_VSOCK) {
+		fprintf(stderr, "cmsg: unexpected 'cmsg_level'\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (cm->cmsg_type != VSOCK_RECVERR) {
+		fprintf(stderr, "cmsg: unexpected 'cmsg_type'\n");
+		exit(EXIT_FAILURE);
+	}
+
+	serr = (void *)CMSG_DATA(cm);
+	if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+		fprintf(stderr, "serr: wrong origin: %u\n", serr->ee_origin);
+		exit(EXIT_FAILURE);
+	}
+
+	if (serr->ee_errno) {
+		fprintf(stderr, "serr: wrong error code: %u\n", serr->ee_errno);
+		exit(EXIT_FAILURE);
+	}
+
+	/* This flag is used for tests, to check that transmission was
+	 * performed as expected: zerocopy or fallback to copy. If NULL
+	 * - don't care.
+	 */
+	if (!zerocopied)
+		return;
+
+	if (*zerocopied && (serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED)) {
+		fprintf(stderr, "serr: was copy instead of zerocopy\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!*zerocopied && !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED)) {
+		fprintf(stderr, "serr: was zerocopy instead of copy\n");
+		exit(EXIT_FAILURE);
+	}
+}

linux-7.2.3/tools/testing/vsock/msg_zerocopy_common.h

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef MSG_ZEROCOPY_COMMON_H
+#define MSG_ZEROCOPY_COMMON_H
+
+#include <stdbool.h>
+
+#ifndef SOL_VSOCK
+#define SOL_VSOCK	287
+#endif
+
+#ifndef VSOCK_RECVERR
+#define VSOCK_RECVERR	1
+#endif
+
+void vsock_recv_completion(int fd, const bool *zerocopied);
+
+#endif /* MSG_ZEROCOPY_COMMON_H */

linux-7.2.3/tools/testing/vsock/timeout.c

@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Timeout API for single-threaded programs that use blocking
+ * syscalls (read/write/send/recv/connect/accept).
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ */
+
+/* Use the following pattern:
+ *
+ *   timeout_begin(TIMEOUT);
+ *   do {
+ *       ret = accept(...);
+ *       timeout_check("accept");
+ *   } while (ret < 0 && ret == EINTR);
+ *   timeout_end();
+ */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+#include "timeout.h"
+
+static volatile bool timeout;
+
+/* SIGALRM handler function.  Do not use sleep(2), alarm(2), or
+ * setitimer(2) while using this API - they may interfere with each
+ * other.
+ *
+ * If you need to sleep, please use timeout_sleep() provided by this API.
+ */
+void sigalrm(int signo)
+{
+	timeout = true;
+}
+
+/* Start a timeout.  Call timeout_check() to verify that the timeout hasn't
+ * expired.  timeout_end() must be called to stop the timeout.  Timeouts cannot
+ * be nested.
+ */
+void timeout_begin(unsigned int seconds)
+{
+	alarm(seconds);
+}
+
+/* Exit with an error message if the timeout has expired */
+void timeout_check(const char *operation)
+{
+	if (timeout) {
+		fprintf(stderr, "%s timed out\n", operation);
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Stop a timeout */
+void timeout_end(void)
+{
+	alarm(0);
+	timeout = false;
+}
+
+/* Sleep in a timeout section.
+ *
+ * nanosleep(2) can be used with this API since POSIX.1 explicitly
+ * specifies that it does not interact with signals.
+ */
+int timeout_usleep(useconds_t usec)
+{
+	struct timespec ts = {
+		.tv_sec = usec / 1000000,
+		.tv_nsec = (usec % 1000000) * 1000,
+	};
+
+	return nanosleep(&ts, NULL);
+}

linux-7.2.3/tools/testing/vsock/timeout.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef TIMEOUT_H
+#define TIMEOUT_H
+
+enum {
+	/* Default timeout */
+	TIMEOUT = 10 /* seconds */
+};
+
+void sigalrm(int signo);
+void timeout_begin(unsigned int seconds);
+void timeout_check(const char *operation);
+void timeout_end(void);
+int timeout_usleep(useconds_t usec);
+
+#endif /* TIMEOUT_H */

linux-7.2.3/tools/testing/vsock/util.c

@@ -0,0 +1,954 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vsock test utilities
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ */
+
+#include <ctype.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <assert.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <linux/sockios.h>
+
+#include "timeout.h"
+#include "control.h"
+#include "util.h"
+
+#define KALLSYMS_PATH		"/proc/kallsyms"
+#define KALLSYMS_LINE_LEN	512
+
+/* Install signal handlers */
+void init_signals(void)
+{
+	struct sigaction act = {
+		.sa_handler = sigalrm,
+	};
+
+	sigaction(SIGALRM, &act, NULL);
+	signal(SIGPIPE, SIG_IGN);
+}
+
+static unsigned int parse_uint(const char *str, const char *err_str)
+{
+	char *endptr = NULL;
+	unsigned long n;
+
+	errno = 0;
+	n = strtoul(str, &endptr, 10);
+	if (errno || *endptr != '\0') {
+		fprintf(stderr, "malformed %s \"%s\"\n", err_str, str);
+		exit(EXIT_FAILURE);
+	}
+	return n;
+}
+
+/* Parse a CID in string representation */
+unsigned int parse_cid(const char *str)
+{
+	return parse_uint(str, "CID");
+}
+
+/* Parse a port in string representation */
+unsigned int parse_port(const char *str)
+{
+	return parse_uint(str, "port");
+}
+
+/* Wait for the remote to close the connection */
+void vsock_wait_remote_close(int fd)
+{
+	struct epoll_event ev;
+	int epollfd, nfds;
+
+	epollfd = epoll_create1(0);
+	if (epollfd == -1) {
+		perror("epoll_create1");
+		exit(EXIT_FAILURE);
+	}
+
+	ev.events = EPOLLRDHUP | EPOLLHUP;
+	ev.data.fd = fd;
+	if (epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) {
+		perror("epoll_ctl");
+		exit(EXIT_FAILURE);
+	}
+
+	nfds = epoll_wait(epollfd, &ev, 1, TIMEOUT * 1000);
+	if (nfds == -1) {
+		perror("epoll_wait");
+		exit(EXIT_FAILURE);
+	}
+
+	if (nfds == 0) {
+		fprintf(stderr, "epoll_wait timed out\n");
+		exit(EXIT_FAILURE);
+	}
+
+	assert(nfds == 1);
+	assert(ev.events & (EPOLLRDHUP | EPOLLHUP));
+	assert(ev.data.fd == fd);
+
+	close(epollfd);
+}
+
+/* Wait until ioctl gives an expected int value.
+ * Return false if the op is not supported.
+ */
+bool vsock_ioctl_int(int fd, unsigned long op, int expected)
+{
+	int actual, ret;
+	char name[32];
+
+	snprintf(name, sizeof(name), "ioctl(%lu)", op);
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = ioctl(fd, op, &actual);
+		if (ret < 0) {
+			if (errno == EOPNOTSUPP || errno == ENOTTY)
+				break;
+
+			perror(name);
+			exit(EXIT_FAILURE);
+		}
+		timeout_check(name);
+	} while (actual != expected);
+	timeout_end();
+
+	return ret >= 0;
+}
+
+/* Wait until transport reports no data left to be sent.
+ * Return false if transport does not implement the unsent_bytes() callback.
+ */
+bool vsock_wait_sent(int fd)
+{
+	return vsock_ioctl_int(fd, SIOCOUTQ, 0);
+}
+
+/* Create socket <type>, bind to <cid, port>.
+ * Return the file descriptor, or -1 on error.
+ */
+int vsock_bind_try(unsigned int cid, unsigned int port, int type)
+{
+	struct sockaddr_vm sa = {
+		.svm_family = AF_VSOCK,
+		.svm_cid = cid,
+		.svm_port = port,
+	};
+	int fd, saved_errno;
+
+	fd = socket(AF_VSOCK, type, 0);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) {
+		saved_errno = errno;
+		close(fd);
+		errno = saved_errno;
+		fd = -1;
+	}
+
+	return fd;
+}
+
+/* Create socket <type>, bind to <cid, port> and return the file descriptor. */
+int vsock_bind(unsigned int cid, unsigned int port, int type)
+{
+	int fd;
+
+	fd = vsock_bind_try(cid, port, type);
+	if (fd < 0) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	return fd;
+}
+
+int vsock_connect_fd(int fd, unsigned int cid, unsigned int port)
+{
+	struct sockaddr_vm sa = {
+		.svm_family = AF_VSOCK,
+		.svm_cid = cid,
+		.svm_port = port,
+	};
+	int ret;
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa));
+		timeout_check("connect");
+	} while (ret < 0 && errno == EINTR);
+	timeout_end();
+
+	return ret;
+}
+
+/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */
+int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type)
+{
+	int client_fd;
+
+	client_fd = vsock_bind(VMADDR_CID_ANY, bind_port, type);
+
+	if (vsock_connect_fd(client_fd, cid, port)) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	return client_fd;
+}
+
+/* Connect to <cid, port> and return the file descriptor. */
+int vsock_connect(unsigned int cid, unsigned int port, int type)
+{
+	int fd;
+
+	control_expectln("LISTENING");
+
+	fd = socket(AF_VSOCK, type, 0);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	if (vsock_connect_fd(fd, cid, port)) {
+		int old_errno = errno;
+
+		close(fd);
+		fd = -1;
+		errno = old_errno;
+	}
+
+	return fd;
+}
+
+int vsock_stream_connect(unsigned int cid, unsigned int port)
+{
+	return vsock_connect(cid, port, SOCK_STREAM);
+}
+
+int vsock_seqpacket_connect(unsigned int cid, unsigned int port)
+{
+	return vsock_connect(cid, port, SOCK_SEQPACKET);
+}
+
+/* Listen on <cid, port> and return the file descriptor. */
+static int vsock_listen(unsigned int cid, unsigned int port, int type)
+{
+	int fd;
+
+	fd = vsock_bind(cid, port, type);
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		exit(EXIT_FAILURE);
+	}
+
+	return fd;
+}
+
+/* Listen on <cid, port> and return the first incoming connection.  The remote
+ * address is stored to clientaddrp.  clientaddrp may be NULL.
+ */
+int vsock_accept(unsigned int cid, unsigned int port,
+		 struct sockaddr_vm *clientaddrp, int type)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} clientaddr;
+	socklen_t clientaddr_len = sizeof(clientaddr.svm);
+	int fd, client_fd, old_errno;
+
+	fd = vsock_listen(cid, port, type);
+
+	control_writeln("LISTENING");
+
+	timeout_begin(TIMEOUT);
+	do {
+		client_fd = accept(fd, &clientaddr.sa, &clientaddr_len);
+		timeout_check("accept");
+	} while (client_fd < 0 && errno == EINTR);
+	timeout_end();
+
+	old_errno = errno;
+	close(fd);
+	errno = old_errno;
+
+	if (client_fd < 0)
+		return client_fd;
+
+	if (clientaddr_len != sizeof(clientaddr.svm)) {
+		fprintf(stderr, "unexpected addrlen from accept(2), %zu\n",
+			(size_t)clientaddr_len);
+		exit(EXIT_FAILURE);
+	}
+	if (clientaddr.sa.sa_family != AF_VSOCK) {
+		fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n",
+			clientaddr.sa.sa_family);
+		exit(EXIT_FAILURE);
+	}
+
+	if (clientaddrp)
+		*clientaddrp = clientaddr.svm;
+	return client_fd;
+}
+
+int vsock_stream_accept(unsigned int cid, unsigned int port,
+			struct sockaddr_vm *clientaddrp)
+{
+	return vsock_accept(cid, port, clientaddrp, SOCK_STREAM);
+}
+
+int vsock_stream_listen(unsigned int cid, unsigned int port)
+{
+	return vsock_listen(cid, port, SOCK_STREAM);
+}
+
+int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
+			   struct sockaddr_vm *clientaddrp)
+{
+	return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET);
+}
+
+/* Transmit bytes from a buffer and check the return value.
+ *
+ * expected_ret:
+ *  <0 Negative errno (for testing errors)
+ *   0 End-of-file
+ *  >0 Success (bytes successfully written)
+ */
+void send_buf(int fd, const void *buf, size_t len, int flags,
+	      ssize_t expected_ret)
+{
+	ssize_t nwritten = 0;
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = send(fd, buf + nwritten, len - nwritten, flags);
+		timeout_check("send");
+
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		nwritten += ret;
+	} while (nwritten < len);
+	timeout_end();
+
+	if (expected_ret < 0) {
+		if (ret != -1) {
+			fprintf(stderr, "bogus send(2) return value %zd (expected %zd)\n",
+				ret, expected_ret);
+			exit(EXIT_FAILURE);
+		}
+		if (errno != -expected_ret) {
+			perror("send");
+			exit(EXIT_FAILURE);
+		}
+		return;
+	}
+
+	if (ret < 0) {
+		perror("send");
+		exit(EXIT_FAILURE);
+	}
+
+	if (nwritten != expected_ret) {
+		if (ret == 0)
+			fprintf(stderr, "unexpected EOF while sending bytes\n");
+
+		fprintf(stderr, "bogus send(2) bytes written %zd (expected %zd)\n",
+			nwritten, expected_ret);
+		exit(EXIT_FAILURE);
+	}
+}
+
+#define RECV_PEEK_RETRY_USEC (10 * 1000)
+
+/* Receive bytes in a buffer and check the return value.
+ *
+ * When MSG_PEEK is set, recv() is retried until it returns at least
+ * expected_ret bytes. The function returns on error, EOF, or timeout
+ * as usual.
+ *
+ * expected_ret:
+ *  <0 Negative errno (for testing errors)
+ *   0 End-of-file
+ *  >0 Success (bytes successfully read)
+ */
+void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret)
+{
+	ssize_t nread = 0;
+	ssize_t ret;
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = recv(fd, buf + nread, len - nread, flags);
+		timeout_check("recv");
+
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		if (flags & MSG_PEEK) {
+			if (ret >= expected_ret) {
+				nread = ret;
+				break;
+			}
+			timeout_usleep(RECV_PEEK_RETRY_USEC);
+			continue;
+		}
+
+		nread += ret;
+	} while (nread < len);
+	timeout_end();
+
+	if (expected_ret < 0) {
+		if (ret != -1) {
+			fprintf(stderr, "bogus recv(2) return value %zd (expected %zd)\n",
+				ret, expected_ret);
+			exit(EXIT_FAILURE);
+		}
+		if (errno != -expected_ret) {
+			perror("recv");
+			exit(EXIT_FAILURE);
+		}
+		return;
+	}
+
+	if (ret < 0) {
+		perror("recv");
+		exit(EXIT_FAILURE);
+	}
+
+	if (nread != expected_ret) {
+		if (ret == 0)
+			fprintf(stderr, "unexpected EOF while receiving bytes\n");
+
+		fprintf(stderr, "bogus recv(2) bytes read %zd (expected %zd)\n",
+			nread, expected_ret);
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Transmit one byte and check the return value.
+ *
+ * expected_ret:
+ *  <0 Negative errno (for testing errors)
+ *   0 End-of-file
+ *   1 Success
+ */
+void send_byte(int fd, int expected_ret, int flags)
+{
+	static const uint8_t byte = 'A';
+
+	send_buf(fd, &byte, sizeof(byte), flags, expected_ret);
+}
+
+/* Receive one byte and check the return value.
+ *
+ * expected_ret:
+ *  <0 Negative errno (for testing errors)
+ *   0 End-of-file
+ *   1 Success
+ */
+void recv_byte(int fd, int expected_ret, int flags)
+{
+	uint8_t byte;
+
+	recv_buf(fd, &byte, sizeof(byte), flags, expected_ret);
+
+	if (byte != 'A') {
+		fprintf(stderr, "unexpected byte read 0x%02x\n", byte);
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Run test cases.  The program terminates if a failure occurs. */
+void run_tests(const struct test_case *test_cases,
+	       const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; test_cases[i].name; i++) {
+		void (*run)(const struct test_opts *opts);
+		char *line;
+
+		printf("%d - %s...", i, test_cases[i].name);
+		fflush(stdout);
+
+		/* Full barrier before executing the next test.  This
+		 * ensures that client and server are executing the
+		 * same test case.  In particular, it means whoever is
+		 * faster will not see the peer still executing the
+		 * last test.  This is important because port numbers
+		 * can be used by multiple test cases.
+		 */
+		if (test_cases[i].skip)
+			control_writeln("SKIP");
+		else
+			control_writeln("NEXT");
+
+		line = control_readln();
+		if (control_cmpln(line, "SKIP", false) || test_cases[i].skip) {
+
+			printf("skipped\n");
+
+			free(line);
+			continue;
+		}
+
+		control_cmpln(line, "NEXT", true);
+		free(line);
+
+		if (opts->mode == TEST_MODE_CLIENT)
+			run = test_cases[i].run_client;
+		else
+			run = test_cases[i].run_server;
+
+		if (run)
+			run(opts);
+
+		printf("ok\n");
+	}
+
+	printf("All tests have been executed. Waiting other peer...");
+	fflush(stdout);
+
+	/*
+	 * Final full barrier, to ensure that all tests have been run and
+	 * that even the last one has been successful on both sides.
+	 */
+	control_writeln("COMPLETED");
+	control_expectln("COMPLETED");
+
+	printf("ok\n");
+}
+
+void list_tests(const struct test_case *test_cases)
+{
+	int i;
+
+	printf("ID\tTest name\n");
+
+	for (i = 0; test_cases[i].name; i++)
+		printf("%d\t%s\n", i, test_cases[i].name);
+
+	exit(EXIT_FAILURE);
+}
+
+static unsigned long parse_test_id(const char *test_id_str, size_t test_cases_len)
+{
+	unsigned long test_id;
+	char *endptr = NULL;
+
+	errno = 0;
+	test_id = strtoul(test_id_str, &endptr, 10);
+	if (errno || *endptr != '\0') {
+		fprintf(stderr, "malformed test ID \"%s\"\n", test_id_str);
+		exit(EXIT_FAILURE);
+	}
+
+	if (test_id >= test_cases_len) {
+		fprintf(stderr, "test ID (%lu) larger than the max allowed (%lu)\n",
+			test_id, test_cases_len - 1);
+		exit(EXIT_FAILURE);
+	}
+
+	return test_id;
+}
+
+void skip_test(struct test_case *test_cases, size_t test_cases_len,
+	       const char *test_id_str)
+{
+	unsigned long test_id = parse_test_id(test_id_str, test_cases_len);
+	test_cases[test_id].skip = true;
+}
+
+void pick_test(struct test_case *test_cases, size_t test_cases_len,
+	       const char *test_id_str)
+{
+	static bool skip_all = true;
+	unsigned long test_id;
+
+	if (skip_all) {
+		unsigned long i;
+
+		for (i = 0; i < test_cases_len; ++i)
+			test_cases[i].skip = true;
+
+		skip_all = false;
+	}
+
+	test_id = parse_test_id(test_id_str, test_cases_len);
+	test_cases[test_id].skip = false;
+}
+
+unsigned long hash_djb2(const void *data, size_t len)
+{
+	unsigned long hash = 5381;
+	int i = 0;
+
+	while (i < len) {
+		hash = ((hash << 5) + hash) + ((unsigned char *)data)[i];
+		i++;
+	}
+
+	return hash;
+}
+
+size_t iovec_bytes(const struct iovec *iov, size_t iovnum)
+{
+	size_t bytes;
+	int i;
+
+	for (bytes = 0, i = 0; i < iovnum; i++)
+		bytes += iov[i].iov_len;
+
+	return bytes;
+}
+
+unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum)
+{
+	unsigned long hash;
+	size_t iov_bytes;
+	size_t offs;
+	void *tmp;
+	int i;
+
+	iov_bytes = iovec_bytes(iov, iovnum);
+
+	tmp = malloc(iov_bytes);
+	if (!tmp) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	for (offs = 0, i = 0; i < iovnum; i++) {
+		memcpy(tmp + offs, iov[i].iov_base, iov[i].iov_len);
+		offs += iov[i].iov_len;
+	}
+
+	hash = hash_djb2(tmp, iov_bytes);
+	free(tmp);
+
+	return hash;
+}
+
+/* Allocates and returns new 'struct iovec *' according pattern
+ * in the 'test_iovec'. For each element in the 'test_iovec' it
+ * allocates new element in the resulting 'iovec'. 'iov_len'
+ * of the new element is copied from 'test_iovec'. 'iov_base' is
+ * allocated depending on the 'iov_base' of 'test_iovec':
+ *
+ * 'iov_base' == NULL -> valid buf: mmap('iov_len').
+ *
+ * 'iov_base' == MAP_FAILED -> invalid buf:
+ *               mmap('iov_len'), then munmap('iov_len').
+ *               'iov_base' still contains result of
+ *               mmap().
+ *
+ * 'iov_base' == number -> unaligned valid buf:
+ *               mmap('iov_len') + number.
+ *
+ * 'iovnum' is number of elements in 'test_iovec'.
+ *
+ * Returns new 'iovec' or calls 'exit()' on error.
+ */
+struct iovec *alloc_test_iovec(const struct iovec *test_iovec, int iovnum)
+{
+	struct iovec *iovec;
+	int i;
+
+	iovec = malloc(sizeof(*iovec) * iovnum);
+	if (!iovec) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < iovnum; i++) {
+		iovec[i].iov_len = test_iovec[i].iov_len;
+
+		iovec[i].iov_base = mmap(NULL, iovec[i].iov_len,
+					 PROT_READ | PROT_WRITE,
+					 MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE,
+					 -1, 0);
+		if (iovec[i].iov_base == MAP_FAILED) {
+			perror("mmap");
+			exit(EXIT_FAILURE);
+		}
+
+		if (test_iovec[i].iov_base != MAP_FAILED)
+			iovec[i].iov_base += (uintptr_t)test_iovec[i].iov_base;
+	}
+
+	/* Unmap "invalid" elements. */
+	for (i = 0; i < iovnum; i++) {
+		if (test_iovec[i].iov_base == MAP_FAILED) {
+			if (munmap(iovec[i].iov_base, iovec[i].iov_len)) {
+				perror("munmap");
+				exit(EXIT_FAILURE);
+			}
+		}
+	}
+
+	for (i = 0; i < iovnum; i++) {
+		int j;
+
+		if (test_iovec[i].iov_base == MAP_FAILED)
+			continue;
+
+		for (j = 0; j < iovec[i].iov_len; j++)
+			((uint8_t *)iovec[i].iov_base)[j] = rand() & 0xff;
+	}
+
+	return iovec;
+}
+
+/* Frees 'iovec *', previously allocated by 'alloc_test_iovec()'.
+ * On error calls 'exit()'.
+ */
+void free_test_iovec(const struct iovec *test_iovec,
+		     struct iovec *iovec, int iovnum)
+{
+	int i;
+
+	for (i = 0; i < iovnum; i++) {
+		if (test_iovec[i].iov_base != MAP_FAILED) {
+			if (test_iovec[i].iov_base)
+				iovec[i].iov_base -= (uintptr_t)test_iovec[i].iov_base;
+
+			if (munmap(iovec[i].iov_base, iovec[i].iov_len)) {
+				perror("munmap");
+				exit(EXIT_FAILURE);
+			}
+		}
+	}
+
+	free(iovec);
+}
+
+/* Set "unsigned long long" socket option and check that it's indeed set */
+void setsockopt_ull_check(int fd, int level, int optname,
+			  unsigned long long val, char const *errmsg)
+{
+	unsigned long long chkval;
+	socklen_t chklen;
+	int err;
+
+	err = setsockopt(fd, level, optname, &val, sizeof(val));
+	if (err) {
+		fprintf(stderr, "setsockopt err: %s (%d)\n",
+			strerror(errno), errno);
+		goto fail;
+	}
+
+	chkval = ~val; /* just make storage != val */
+	chklen = sizeof(chkval);
+
+	err = getsockopt(fd, level, optname, &chkval, &chklen);
+	if (err) {
+		fprintf(stderr, "getsockopt err: %s (%d)\n",
+			strerror(errno), errno);
+		goto fail;
+	}
+
+	if (chklen != sizeof(chkval)) {
+		fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val),
+			chklen);
+		goto fail;
+	}
+
+	if (chkval != val) {
+		fprintf(stderr, "value mismatch: set %llu got %llu\n", val,
+			chkval);
+		goto fail;
+	}
+	return;
+fail:
+	fprintf(stderr, "%s  val %llu\n", errmsg, val);
+	exit(EXIT_FAILURE);
+}
+
+/* Set "int" socket option and check that it's indeed set */
+void setsockopt_int_check(int fd, int level, int optname, int val,
+			  char const *errmsg)
+{
+	int chkval;
+	socklen_t chklen;
+	int err;
+
+	err = setsockopt(fd, level, optname, &val, sizeof(val));
+	if (err) {
+		fprintf(stderr, "setsockopt err: %s (%d)\n",
+			strerror(errno), errno);
+		goto fail;
+	}
+
+	chkval = ~val; /* just make storage != val */
+	chklen = sizeof(chkval);
+
+	err = getsockopt(fd, level, optname, &chkval, &chklen);
+	if (err) {
+		fprintf(stderr, "getsockopt err: %s (%d)\n",
+			strerror(errno), errno);
+		goto fail;
+	}
+
+	if (chklen != sizeof(chkval)) {
+		fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val),
+			chklen);
+		goto fail;
+	}
+
+	if (chkval != val) {
+		fprintf(stderr, "value mismatch: set %d got %d\n", val, chkval);
+		goto fail;
+	}
+	return;
+fail:
+	fprintf(stderr, "%s val %d\n", errmsg, val);
+	exit(EXIT_FAILURE);
+}
+
+static void mem_invert(unsigned char *mem, size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		mem[i] = ~mem[i];
+}
+
+/* Set "timeval" socket option and check that it's indeed set */
+void setsockopt_timeval_check(int fd, int level, int optname,
+			      struct timeval val, char const *errmsg)
+{
+	struct timeval chkval;
+	socklen_t chklen;
+	int err;
+
+	err = setsockopt(fd, level, optname, &val, sizeof(val));
+	if (err) {
+		fprintf(stderr, "setsockopt err: %s (%d)\n",
+			strerror(errno), errno);
+		goto fail;
+	}
+
+	 /* just make storage != val */
+	chkval = val;
+	mem_invert((unsigned char *)&chkval, sizeof(chkval));
+	chklen = sizeof(chkval);
+
+	err = getsockopt(fd, level, optname, &chkval, &chklen);
+	if (err) {
+		fprintf(stderr, "getsockopt err: %s (%d)\n",
+			strerror(errno), errno);
+		goto fail;
+	}
+
+	if (chklen != sizeof(chkval)) {
+		fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val),
+			chklen);
+		goto fail;
+	}
+
+	if (memcmp(&chkval, &val, sizeof(val)) != 0) {
+		fprintf(stderr, "value mismatch: set %ld:%ld got %ld:%ld\n",
+			val.tv_sec, val.tv_usec, chkval.tv_sec, chkval.tv_usec);
+		goto fail;
+	}
+	return;
+fail:
+	fprintf(stderr, "%s val %ld:%ld\n", errmsg, val.tv_sec, val.tv_usec);
+	exit(EXIT_FAILURE);
+}
+
+void enable_so_zerocopy_check(int fd)
+{
+	setsockopt_int_check(fd, SOL_SOCKET, SO_ZEROCOPY, 1,
+			     "setsockopt SO_ZEROCOPY");
+}
+
+void enable_so_linger(int fd, int timeout)
+{
+	struct linger optval = {
+		.l_onoff = 1,
+		.l_linger = timeout
+	};
+
+	if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) {
+		perror("setsockopt(SO_LINGER)");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static int __get_transports(void)
+{
+	char buf[KALLSYMS_LINE_LEN];
+	const char *ksym;
+	int ret = 0;
+	FILE *f;
+
+	f = fopen(KALLSYMS_PATH, "r");
+	if (!f) {
+		perror("Can't open " KALLSYMS_PATH);
+		exit(EXIT_FAILURE);
+	}
+
+	while (fgets(buf, sizeof(buf), f)) {
+		char *match;
+		int i;
+
+		assert(buf[strlen(buf) - 1] == '\n');
+
+		for (i = 0; i < TRANSPORT_NUM; ++i) {
+			if (ret & BIT(i))
+				continue;
+
+			/* Match should be followed by '\t' or '\n'.
+			 * See kallsyms.c:s_show().
+			 */
+			ksym = transport_ksyms[i];
+			match = strstr(buf, ksym);
+			if (match && isspace(match[strlen(ksym)])) {
+				ret |= BIT(i);
+				break;
+			}
+		}
+	}
+
+	fclose(f);
+	return ret;
+}
+
+/* Return integer with TRANSPORT_* bit set for every (known) registered vsock
+ * transport.
+ */
+int get_transports(void)
+{
+	static int tr = -1;
+
+	if (tr == -1)
+		tr = __get_transports();
+
+	return tr;
+}

linux-7.2.3/tools/testing/vsock/util.h

@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef UTIL_H
+#define UTIL_H
+
+#include <sys/socket.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/vm_sockets.h>
+
+/* All known vsock transports, see callers of vsock_core_register() */
+#define KNOWN_TRANSPORTS(x)		\
+	x(LOOPBACK, "loopback")		\
+	x(VIRTIO, "virtio")		\
+	x(VHOST, "vhost")		\
+	x(VMCI, "vmci")			\
+	x(HYPERV, "hvs")
+
+enum transport {
+	TRANSPORT_COUNTER_BASE = __COUNTER__ + 1,
+	#define x(name, symbol)		\
+		TRANSPORT_##name = BIT(__COUNTER__ - TRANSPORT_COUNTER_BASE),
+	KNOWN_TRANSPORTS(x)
+	TRANSPORT_NUM = __COUNTER__ - TRANSPORT_COUNTER_BASE,
+	#undef x
+};
+
+static const char * const transport_ksyms[] = {
+	#define x(name, symbol) " " symbol "_transport",
+	KNOWN_TRANSPORTS(x)
+	#undef x
+};
+
+static_assert(ARRAY_SIZE(transport_ksyms) == TRANSPORT_NUM);
+static_assert(BITS_PER_TYPE(int) >= TRANSPORT_NUM);
+
+#define TRANSPORTS_G2H   (TRANSPORT_VIRTIO | TRANSPORT_VMCI | TRANSPORT_HYPERV)
+#define TRANSPORTS_H2G   (TRANSPORT_VHOST | TRANSPORT_VMCI)
+#define TRANSPORTS_LOCAL (TRANSPORT_LOOPBACK)
+
+/* Tests can either run as the client or the server */
+enum test_mode {
+	TEST_MODE_UNSET,
+	TEST_MODE_CLIENT,
+	TEST_MODE_SERVER
+};
+
+#define DEFAULT_PEER_PORT	1234
+
+/* Test runner options */
+struct test_opts {
+	enum test_mode mode;
+	unsigned int peer_cid;
+	unsigned int peer_port;
+};
+
+/* A test case definition.  Test functions must print failures to stderr and
+ * terminate with exit(EXIT_FAILURE).
+ */
+struct test_case {
+	const char *name; /* human-readable name */
+
+	/* Called when test mode is TEST_MODE_CLIENT */
+	void (*run_client)(const struct test_opts *opts);
+
+	/* Called when test mode is TEST_MODE_SERVER */
+	void (*run_server)(const struct test_opts *opts);
+
+	bool skip;
+};
+
+void init_signals(void);
+unsigned int parse_cid(const char *str);
+unsigned int parse_port(const char *str);
+int vsock_connect_fd(int fd, unsigned int cid, unsigned int port);
+int vsock_connect(unsigned int cid, unsigned int port, int type);
+int vsock_accept(unsigned int cid, unsigned int port,
+		 struct sockaddr_vm *clientaddrp, int type);
+int vsock_stream_connect(unsigned int cid, unsigned int port);
+int vsock_bind_try(unsigned int cid, unsigned int port, int type);
+int vsock_bind(unsigned int cid, unsigned int port, int type);
+int vsock_bind_connect(unsigned int cid, unsigned int port,
+		       unsigned int bind_port, int type);
+int vsock_seqpacket_connect(unsigned int cid, unsigned int port);
+int vsock_stream_accept(unsigned int cid, unsigned int port,
+			struct sockaddr_vm *clientaddrp);
+int vsock_stream_listen(unsigned int cid, unsigned int port);
+int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
+			   struct sockaddr_vm *clientaddrp);
+void vsock_wait_remote_close(int fd);
+bool vsock_ioctl_int(int fd, unsigned long op, int expected);
+bool vsock_wait_sent(int fd);
+void send_buf(int fd, const void *buf, size_t len, int flags,
+	      ssize_t expected_ret);
+void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret);
+void send_byte(int fd, int expected_ret, int flags);
+void recv_byte(int fd, int expected_ret, int flags);
+void run_tests(const struct test_case *test_cases,
+	       const struct test_opts *opts);
+void list_tests(const struct test_case *test_cases);
+void skip_test(struct test_case *test_cases, size_t test_cases_len,
+	       const char *test_id_str);
+void pick_test(struct test_case *test_cases, size_t test_cases_len,
+	       const char *test_id_str);
+unsigned long hash_djb2(const void *data, size_t len);
+size_t iovec_bytes(const struct iovec *iov, size_t iovnum);
+unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum);
+struct iovec *alloc_test_iovec(const struct iovec *test_iovec, int iovnum);
+void free_test_iovec(const struct iovec *test_iovec,
+		     struct iovec *iovec, int iovnum);
+void setsockopt_ull_check(int fd, int level, int optname,
+			  unsigned long long val, char const *errmsg);
+void setsockopt_int_check(int fd, int level, int optname, int val,
+			  char const *errmsg);
+void setsockopt_timeval_check(int fd, int level, int optname,
+			      struct timeval val, char const *errmsg);
+void enable_so_zerocopy_check(int fd);
+void enable_so_linger(int fd, int timeout);
+int get_transports(void);
+#endif /* UTIL_H */

linux-7.2.3/tools/testing/vsock/vsock_diag_test.c

@@ -0,0 +1,596 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vsock_diag_test - vsock_diag.ko test suite
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <linux/list.h>
+#include <linux/net.h>
+#include <linux/netlink.h>
+#include <linux/sock_diag.h>
+#include <linux/vm_sockets_diag.h>
+#include <netinet/tcp.h>
+
+#include "timeout.h"
+#include "control.h"
+#include "util.h"
+
+/* Per-socket status */
+struct vsock_stat {
+	struct list_head list;
+	struct vsock_diag_msg msg;
+};
+
+static const char *sock_type_str(int type)
+{
+	switch (type) {
+	case SOCK_DGRAM:
+		return "DGRAM";
+	case SOCK_STREAM:
+		return "STREAM";
+	case SOCK_SEQPACKET:
+		return "SEQPACKET";
+	default:
+		return "INVALID TYPE";
+	}
+}
+
+static const char *sock_state_str(int state)
+{
+	switch (state) {
+	case TCP_CLOSE:
+		return "UNCONNECTED";
+	case TCP_SYN_SENT:
+		return "CONNECTING";
+	case TCP_ESTABLISHED:
+		return "CONNECTED";
+	case TCP_CLOSING:
+		return "DISCONNECTING";
+	case TCP_LISTEN:
+		return "LISTEN";
+	default:
+		return "INVALID STATE";
+	}
+}
+
+static const char *sock_shutdown_str(int shutdown)
+{
+	switch (shutdown) {
+	case 1:
+		return "RCV_SHUTDOWN";
+	case 2:
+		return "SEND_SHUTDOWN";
+	case 3:
+		return "RCV_SHUTDOWN | SEND_SHUTDOWN";
+	default:
+		return "0";
+	}
+}
+
+static void print_vsock_addr(FILE *fp, unsigned int cid, unsigned int port)
+{
+	if (cid == VMADDR_CID_ANY)
+		fprintf(fp, "*:");
+	else
+		fprintf(fp, "%u:", cid);
+
+	if (port == VMADDR_PORT_ANY)
+		fprintf(fp, "*");
+	else
+		fprintf(fp, "%u", port);
+}
+
+static void print_vsock_stat(FILE *fp, struct vsock_stat *st)
+{
+	print_vsock_addr(fp, st->msg.vdiag_src_cid, st->msg.vdiag_src_port);
+	fprintf(fp, " ");
+	print_vsock_addr(fp, st->msg.vdiag_dst_cid, st->msg.vdiag_dst_port);
+	fprintf(fp, " %s %s %s %u\n",
+		sock_type_str(st->msg.vdiag_type),
+		sock_state_str(st->msg.vdiag_state),
+		sock_shutdown_str(st->msg.vdiag_shutdown),
+		st->msg.vdiag_ino);
+}
+
+static void print_vsock_stats(FILE *fp, struct list_head *head)
+{
+	struct vsock_stat *st;
+
+	list_for_each_entry(st, head, list)
+		print_vsock_stat(fp, st);
+}
+
+static struct vsock_stat *find_vsock_stat(struct list_head *head, int fd)
+{
+	struct vsock_stat *st;
+	struct stat stat;
+
+	if (fstat(fd, &stat) < 0) {
+		perror("fstat");
+		exit(EXIT_FAILURE);
+	}
+
+	list_for_each_entry(st, head, list)
+		if (st->msg.vdiag_ino == stat.st_ino)
+			return st;
+
+	fprintf(stderr, "cannot find fd %d\n", fd);
+	exit(EXIT_FAILURE);
+}
+
+static void check_no_sockets(struct list_head *head)
+{
+	if (!list_empty(head)) {
+		fprintf(stderr, "expected no sockets\n");
+		print_vsock_stats(stderr, head);
+		exit(1);
+	}
+}
+
+static void check_num_sockets(struct list_head *head, int expected)
+{
+	struct list_head *node;
+	int n = 0;
+
+	list_for_each(node, head)
+		n++;
+
+	if (n != expected) {
+		fprintf(stderr, "expected %d sockets, found %d\n",
+			expected, n);
+		print_vsock_stats(stderr, head);
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void check_socket_state(struct vsock_stat *st, __u8 state)
+{
+	if (st->msg.vdiag_state != state) {
+		fprintf(stderr, "expected socket state %#x, got %#x\n",
+			state, st->msg.vdiag_state);
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void send_req(int fd)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK,
+	};
+	struct {
+		struct nlmsghdr nlh;
+		struct vsock_diag_req vreq;
+	} req = {
+		.nlh = {
+			.nlmsg_len = sizeof(req),
+			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
+			.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP,
+		},
+		.vreq = {
+			.sdiag_family = AF_VSOCK,
+			.vdiag_states = ~(__u32)0,
+		},
+	};
+	struct iovec iov = {
+		.iov_base = &req,
+		.iov_len = sizeof(req),
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+
+	for (;;) {
+		if (sendmsg(fd, &msg, 0) < 0) {
+			if (errno == EINTR)
+				continue;
+
+			perror("sendmsg");
+			exit(EXIT_FAILURE);
+		}
+
+		return;
+	}
+}
+
+static ssize_t recv_resp(int fd, void *buf, size_t len)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK,
+	};
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = len,
+	};
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	ssize_t ret;
+
+	do {
+		ret = recvmsg(fd, &msg, 0);
+	} while (ret < 0 && errno == EINTR);
+
+	if (ret < 0) {
+		perror("recvmsg");
+		exit(EXIT_FAILURE);
+	}
+
+	return ret;
+}
+
+static void add_vsock_stat(struct list_head *sockets,
+			   const struct vsock_diag_msg *resp)
+{
+	struct vsock_stat *st;
+
+	st = malloc(sizeof(*st));
+	if (!st) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	st->msg = *resp;
+	list_add_tail(&st->list, sockets);
+}
+
+/*
+ * Read vsock stats into a list.
+ */
+static void read_vsock_stat(struct list_head *sockets)
+{
+	long buf[8192 / sizeof(long)];
+	int fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	send_req(fd);
+
+	for (;;) {
+		const struct nlmsghdr *h;
+		ssize_t ret;
+
+		ret = recv_resp(fd, buf, sizeof(buf));
+		if (ret == 0)
+			goto done;
+		if (ret < sizeof(*h)) {
+			fprintf(stderr, "short read of %zd bytes\n", ret);
+			exit(EXIT_FAILURE);
+		}
+
+		h = (struct nlmsghdr *)buf;
+
+		while (NLMSG_OK(h, ret)) {
+			if (h->nlmsg_type == NLMSG_DONE)
+				goto done;
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				const struct nlmsgerr *err = NLMSG_DATA(h);
+
+				if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
+					fprintf(stderr, "NLMSG_ERROR\n");
+				else {
+					errno = -err->error;
+					perror("NLMSG_ERROR");
+				}
+
+				exit(EXIT_FAILURE);
+			}
+
+			if (h->nlmsg_type != SOCK_DIAG_BY_FAMILY) {
+				fprintf(stderr, "unexpected nlmsg_type %#x\n",
+					h->nlmsg_type);
+				exit(EXIT_FAILURE);
+			}
+			if (h->nlmsg_len <
+			    NLMSG_LENGTH(sizeof(struct vsock_diag_msg))) {
+				fprintf(stderr, "short vsock_diag_msg\n");
+				exit(EXIT_FAILURE);
+			}
+
+			add_vsock_stat(sockets, NLMSG_DATA(h));
+
+			h = NLMSG_NEXT(h, ret);
+		}
+	}
+
+done:
+	close(fd);
+}
+
+static void free_sock_stat(struct list_head *sockets)
+{
+	struct vsock_stat *st;
+	struct vsock_stat *next;
+
+	list_for_each_entry_safe(st, next, sockets, list)
+		free(st);
+}
+
+static void test_no_sockets(const struct test_opts *opts)
+{
+	LIST_HEAD(sockets);
+
+	read_vsock_stat(&sockets);
+
+	check_no_sockets(&sockets);
+}
+
+static void test_listen_socket_server(const struct test_opts *opts)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = opts->peer_port,
+			.svm_cid = VMADDR_CID_ANY,
+		},
+	};
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+	int fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	if (listen(fd, 1) < 0) {
+		perror("listen");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, fd);
+	check_socket_state(st, TCP_LISTEN);
+
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static void test_connect_client(const struct test_opts *opts)
+{
+	int fd;
+	LIST_HEAD(sockets);
+	struct vsock_stat *st;
+
+	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, fd);
+	check_socket_state(st, TCP_ESTABLISHED);
+
+	control_expectln("DONE");
+	control_writeln("DONE");
+
+	close(fd);
+	free_sock_stat(&sockets);
+}
+
+static void test_connect_server(const struct test_opts *opts)
+{
+	struct vsock_stat *st;
+	LIST_HEAD(sockets);
+	int client_fd;
+
+	client_fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (client_fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	read_vsock_stat(&sockets);
+
+	check_num_sockets(&sockets, 1);
+	st = find_vsock_stat(&sockets, client_fd);
+	check_socket_state(st, TCP_ESTABLISHED);
+
+	control_writeln("DONE");
+	control_expectln("DONE");
+
+	close(client_fd);
+	free_sock_stat(&sockets);
+}
+
+static struct test_case test_cases[] = {
+	{
+		.name = "No sockets",
+		.run_server = test_no_sockets,
+	},
+	{
+		.name = "Listen socket",
+		.run_server = test_listen_socket_server,
+	},
+	{
+		.name = "Connect",
+		.run_client = test_connect_client,
+		.run_server = test_connect_server,
+	},
+	{},
+};
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "control-host",
+		.has_arg = required_argument,
+		.val = 'H',
+	},
+	{
+		.name = "control-port",
+		.has_arg = required_argument,
+		.val = 'P',
+	},
+	{
+		.name = "mode",
+		.has_arg = required_argument,
+		.val = 'm',
+	},
+	{
+		.name = "peer-cid",
+		.has_arg = required_argument,
+		.val = 'p',
+	},
+	{
+		.name = "peer-port",
+		.has_arg = required_argument,
+		.val = 'q',
+	},
+	{
+		.name = "list",
+		.has_arg = no_argument,
+		.val = 'l',
+	},
+	{
+		.name = "skip",
+		.has_arg = required_argument,
+		.val = 's',
+	},
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = '?',
+	},
+	{},
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--peer-port=<port>] [--list] [--skip=<test_id>]\n"
+		"\n"
+		"  Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n"
+		"  Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n"
+		"\n"
+		"Run vsock_diag.ko tests.  Must be launched in both\n"
+		"guest and host.  One side must use --mode=client and\n"
+		"the other side must use --mode=server.\n"
+		"\n"
+		"A TCP control socket connection is used to coordinate tests\n"
+		"between the client and the server.  The server requires a\n"
+		"listen address and the client requires an address to\n"
+		"connect to.\n"
+		"\n"
+		"The CID of the other side must be given with --peer-cid=<cid>.\n"
+		"\n"
+		"Options:\n"
+		"  --help                 This help message\n"
+		"  --control-host <host>  Server IP address to connect to\n"
+		"  --control-port <port>  Server port to listen on/connect to\n"
+		"  --mode client|server   Server or client mode\n"
+		"  --peer-cid <cid>       CID of the other side\n"
+		"  --peer-port <port>     AF_VSOCK port used for the test [default: %d]\n"
+		"  --list                 List of tests that will be executed\n"
+		"  --skip <test_id>       Test ID to skip;\n"
+		"                         use multiple --skip options to skip more tests\n",
+		DEFAULT_PEER_PORT
+		);
+	exit(EXIT_FAILURE);
+}
+
+int main(int argc, char **argv)
+{
+	const char *control_host = NULL;
+	const char *control_port = NULL;
+	struct test_opts opts = {
+		.mode = TEST_MODE_UNSET,
+		.peer_cid = VMADDR_CID_ANY,
+		.peer_port = DEFAULT_PEER_PORT,
+	};
+
+	init_signals();
+
+	for (;;) {
+		int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'H':
+			control_host = optarg;
+			break;
+		case 'm':
+			if (strcmp(optarg, "client") == 0)
+				opts.mode = TEST_MODE_CLIENT;
+			else if (strcmp(optarg, "server") == 0)
+				opts.mode = TEST_MODE_SERVER;
+			else {
+				fprintf(stderr, "--mode must be \"client\" or \"server\"\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'p':
+			opts.peer_cid = parse_cid(optarg);
+			break;
+		case 'q':
+			opts.peer_port = parse_port(optarg);
+			break;
+		case 'P':
+			control_port = optarg;
+			break;
+		case 'l':
+			list_tests(test_cases);
+			break;
+		case 's':
+			skip_test(test_cases, ARRAY_SIZE(test_cases) - 1,
+				  optarg);
+			break;
+		case '?':
+		default:
+			usage();
+		}
+	}
+
+	if (!control_port)
+		usage();
+	if (opts.mode == TEST_MODE_UNSET)
+		usage();
+	if (opts.peer_cid == VMADDR_CID_ANY)
+		usage();
+
+	if (!control_host) {
+		if (opts.mode != TEST_MODE_SERVER)
+			usage();
+		control_host = "0.0.0.0";
+	}
+
+	control_init(control_host, control_port,
+		     opts.mode == TEST_MODE_SERVER);
+
+	run_tests(test_cases, &opts);
+
+	control_cleanup();
+	return EXIT_SUCCESS;
+}

linux-7.2.3/tools/testing/vsock/vsock_perf.c

@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vsock_perf - benchmark utility for vsock.
+ *
+ * Copyright (C) 2022 SberDevices.
+ *
+ * Author: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
+ */
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <time.h>
+#include <stdint.h>
+#include <poll.h>
+#include <sys/socket.h>
+#include <linux/vm_sockets.h>
+#include <sys/mman.h>
+
+#include "msg_zerocopy_common.h"
+
+#define DEFAULT_BUF_SIZE_BYTES	(128 * 1024)
+#define DEFAULT_TO_SEND_BYTES	(64 * 1024)
+#define DEFAULT_VSOCK_BUF_BYTES (256 * 1024)
+#define DEFAULT_RCVLOWAT_BYTES	1
+#define DEFAULT_PORT		1234
+
+#define BYTES_PER_GB		(1024 * 1024 * 1024ULL)
+#define NSEC_PER_SEC		(1000000000ULL)
+
+static unsigned int port = DEFAULT_PORT;
+static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES;
+static unsigned long long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES;
+static bool zerocopy;
+
+static void error(const char *s)
+{
+	perror(s);
+	exit(EXIT_FAILURE);
+}
+
+static time_t current_nsec(void)
+{
+	struct timespec ts;
+
+	if (clock_gettime(CLOCK_REALTIME, &ts))
+		error("clock_gettime");
+
+	return (ts.tv_sec * NSEC_PER_SEC) + ts.tv_nsec;
+}
+
+/* From lib/cmdline.c. */
+static unsigned long memparse(const char *ptr)
+{
+	char *endptr;
+
+	unsigned long long ret = strtoull(ptr, &endptr, 0);
+
+	switch (*endptr) {
+	case 'E':
+	case 'e':
+		ret <<= 10;
+	case 'P':
+	case 'p':
+		ret <<= 10;
+	case 'T':
+	case 't':
+		ret <<= 10;
+	case 'G':
+	case 'g':
+		ret <<= 10;
+	case 'M':
+	case 'm':
+		ret <<= 10;
+	case 'K':
+	case 'k':
+		ret <<= 10;
+		endptr++;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static void vsock_increase_buf_size(int fd)
+{
+	if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE,
+		       &vsock_buf_bytes, sizeof(vsock_buf_bytes)))
+		error("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)");
+
+	if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
+		       &vsock_buf_bytes, sizeof(vsock_buf_bytes)))
+		error("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
+}
+
+static int vsock_connect(unsigned int cid, unsigned int port)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = port,
+			.svm_cid = cid,
+		},
+	};
+	int fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (fd < 0) {
+		perror("socket");
+		return -1;
+	}
+
+	if (connect(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+		perror("connect");
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+static float get_gbps(unsigned long bits, time_t ns_delta)
+{
+	return ((float)bits / 1000000000ULL) /
+	       ((float)ns_delta / NSEC_PER_SEC);
+}
+
+static void run_receiver(int rcvlowat_bytes)
+{
+	unsigned int read_cnt;
+	time_t rx_begin_ns;
+	time_t in_read_ns;
+	size_t total_recv;
+	int client_fd;
+	char *data;
+	int fd;
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} addr = {
+		.svm = {
+			.svm_family = AF_VSOCK,
+			.svm_port = port,
+			.svm_cid = VMADDR_CID_ANY,
+		},
+	};
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} clientaddr;
+
+	socklen_t clientaddr_len = sizeof(clientaddr.svm);
+
+	printf("Run as receiver\n");
+	printf("Listen port %u\n", port);
+	printf("RX buffer %lu bytes\n", buf_size_bytes);
+	printf("vsock buffer %llu bytes\n", vsock_buf_bytes);
+	printf("SO_RCVLOWAT %d bytes\n", rcvlowat_bytes);
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+	if (fd < 0)
+		error("socket");
+
+	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0)
+		error("bind");
+
+	if (listen(fd, 1) < 0)
+		error("listen");
+
+	client_fd = accept(fd, &clientaddr.sa, &clientaddr_len);
+
+	if (client_fd < 0)
+		error("accept");
+
+	vsock_increase_buf_size(client_fd);
+
+	if (setsockopt(client_fd, SOL_SOCKET, SO_RCVLOWAT,
+		       &rcvlowat_bytes,
+		       sizeof(rcvlowat_bytes)))
+		error("setsockopt(SO_RCVLOWAT)");
+
+	data = malloc(buf_size_bytes);
+
+	if (!data) {
+		fprintf(stderr, "'malloc()' failed\n");
+		exit(EXIT_FAILURE);
+	}
+
+	read_cnt = 0;
+	in_read_ns = 0;
+	total_recv = 0;
+	rx_begin_ns = current_nsec();
+
+	while (1) {
+		struct pollfd fds = { 0 };
+
+		fds.fd = client_fd;
+		fds.events = POLLIN | POLLERR |
+			     POLLHUP | POLLRDHUP;
+
+		if (poll(&fds, 1, -1) < 0)
+			error("poll");
+
+		if (fds.revents & POLLERR) {
+			fprintf(stderr, "'poll()' error\n");
+			exit(EXIT_FAILURE);
+		}
+
+		if (fds.revents & POLLIN) {
+			ssize_t bytes_read;
+			time_t t;
+
+			t = current_nsec();
+			bytes_read = read(fds.fd, data, buf_size_bytes);
+			in_read_ns += (current_nsec() - t);
+			read_cnt++;
+
+			if (!bytes_read)
+				break;
+
+			if (bytes_read < 0) {
+				perror("read");
+				exit(EXIT_FAILURE);
+			}
+
+			total_recv += bytes_read;
+		}
+
+		if (fds.revents & (POLLHUP | POLLRDHUP))
+			break;
+	}
+
+	printf("total bytes received: %zu\n", total_recv);
+	printf("rx performance: %f Gbits/s\n",
+	       get_gbps(total_recv * 8, current_nsec() - rx_begin_ns));
+	printf("total time in 'read()': %f sec\n", (float)in_read_ns / NSEC_PER_SEC);
+	printf("average time in 'read()': %f ns\n", (float)in_read_ns / read_cnt);
+	printf("POLLIN wakeups: %i\n", read_cnt);
+
+	free(data);
+	close(client_fd);
+	close(fd);
+}
+
+static void enable_so_zerocopy(int fd)
+{
+	int val = 1;
+
+	if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) {
+		perror("setsockopt");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void run_sender(int peer_cid, unsigned long to_send_bytes)
+{
+	time_t tx_begin_ns;
+	time_t tx_total_ns;
+	size_t total_send;
+	time_t time_in_send;
+	void *data;
+	int fd;
+
+	if (zerocopy)
+		printf("Run as sender MSG_ZEROCOPY\n");
+	else
+		printf("Run as sender\n");
+
+	printf("Connect to %i:%u\n", peer_cid, port);
+	printf("Send %lu bytes\n", to_send_bytes);
+	printf("TX buffer %lu bytes\n", buf_size_bytes);
+
+	fd = vsock_connect(peer_cid, port);
+
+	if (fd < 0)
+		exit(EXIT_FAILURE);
+
+	if (zerocopy) {
+		enable_so_zerocopy(fd);
+
+		data = mmap(NULL, buf_size_bytes, PROT_READ | PROT_WRITE,
+			    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (data == MAP_FAILED) {
+			perror("mmap");
+			exit(EXIT_FAILURE);
+		}
+	} else {
+		data = malloc(buf_size_bytes);
+
+		if (!data) {
+			fprintf(stderr, "'malloc()' failed\n");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	memset(data, 0, buf_size_bytes);
+	total_send = 0;
+	time_in_send = 0;
+	tx_begin_ns = current_nsec();
+
+	while (total_send < to_send_bytes) {
+		ssize_t sent;
+		size_t rest_bytes;
+		time_t before;
+
+		rest_bytes = to_send_bytes - total_send;
+
+		before = current_nsec();
+		sent = send(fd, data, (rest_bytes > buf_size_bytes) ?
+			    buf_size_bytes : rest_bytes,
+			    zerocopy ? MSG_ZEROCOPY : 0);
+		time_in_send += (current_nsec() - before);
+
+		if (sent <= 0)
+			error("write");
+
+		total_send += sent;
+
+		if (zerocopy) {
+			struct pollfd fds = { 0 };
+
+			fds.fd = fd;
+
+			if (poll(&fds, 1, -1) < 0) {
+				perror("poll");
+				exit(EXIT_FAILURE);
+			}
+
+			if (!(fds.revents & POLLERR)) {
+				fprintf(stderr, "POLLERR expected\n");
+				exit(EXIT_FAILURE);
+			}
+
+			vsock_recv_completion(fd, NULL);
+		}
+	}
+
+	tx_total_ns = current_nsec() - tx_begin_ns;
+
+	printf("total bytes sent: %zu\n", total_send);
+	printf("tx performance: %f Gbits/s\n",
+	       get_gbps(total_send * 8, time_in_send));
+	printf("total time in tx loop: %f sec\n",
+	       (float)tx_total_ns / NSEC_PER_SEC);
+	printf("time in 'send()': %f sec\n",
+	       (float)time_in_send / NSEC_PER_SEC);
+
+	close(fd);
+
+	if (zerocopy)
+		munmap(data, buf_size_bytes);
+	else
+		free(data);
+}
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = 'H',
+	},
+	{
+		.name = "sender",
+		.has_arg = required_argument,
+		.val = 'S',
+	},
+	{
+		.name = "port",
+		.has_arg = required_argument,
+		.val = 'P',
+	},
+	{
+		.name = "bytes",
+		.has_arg = required_argument,
+		.val = 'M',
+	},
+	{
+		.name = "buf-size",
+		.has_arg = required_argument,
+		.val = 'B',
+	},
+	{
+		.name = "vsk-size",
+		.has_arg = required_argument,
+		.val = 'V',
+	},
+	{
+		.name = "rcvlowat",
+		.has_arg = required_argument,
+		.val = 'R',
+	},
+	{
+		.name = "zerocopy",
+		.has_arg = no_argument,
+		.val = 'Z',
+	},
+	{},
+};
+
+static void usage(void)
+{
+	printf("Usage: ./vsock_perf [--help] [options]\n"
+	       "\n"
+	       "This is benchmarking utility, to test vsock performance.\n"
+	       "It runs in two modes: sender or receiver. In sender mode, it\n"
+	       "connects to the specified CID and starts data transmission.\n"
+	       "\n"
+	       "Options:\n"
+	       "  --help			This message\n"
+	       "  --sender   <cid>		Sender mode (receiver default)\n"
+	       "                                <cid> of the receiver to connect to\n"
+	       "  --zerocopy			Enable zerocopy (for sender mode only)\n"
+	       "  --port     <port>		Port (default %d)\n"
+	       "  --bytes    <bytes>KMG		Bytes to send (default %d)\n"
+	       "  --buf-size <bytes>KMG		Data buffer size (default %d). In sender mode\n"
+	       "                                it is the buffer size, passed to 'write()'. In\n"
+	       "                                receiver mode it is the buffer size passed to 'read()'.\n"
+	       "  --vsk-size <bytes>KMG		Socket buffer size (default %d)\n"
+	       "  --rcvlowat <bytes>KMG		SO_RCVLOWAT value (default %d)\n"
+	       "\n", DEFAULT_PORT, DEFAULT_TO_SEND_BYTES,
+	       DEFAULT_BUF_SIZE_BYTES, DEFAULT_VSOCK_BUF_BYTES,
+	       DEFAULT_RCVLOWAT_BYTES);
+	exit(EXIT_FAILURE);
+}
+
+static long strtolx(const char *arg)
+{
+	long value;
+	char *end;
+
+	value = strtol(arg, &end, 10);
+
+	if (end != arg + strlen(arg))
+		usage();
+
+	return value;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned long to_send_bytes = DEFAULT_TO_SEND_BYTES;
+	int rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES;
+	int peer_cid = -1;
+	bool sender = false;
+
+	while (1) {
+		int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'V': /* Peer buffer size. */
+			vsock_buf_bytes = memparse(optarg);
+			break;
+		case 'R': /* SO_RCVLOWAT value. */
+			rcvlowat_bytes = memparse(optarg);
+			break;
+		case 'P': /* Port to connect to. */
+			port = strtolx(optarg);
+			break;
+		case 'M': /* Bytes to send. */
+			to_send_bytes = memparse(optarg);
+			break;
+		case 'B': /* Size of rx/tx buffer. */
+			buf_size_bytes = memparse(optarg);
+			break;
+		case 'S': /* Sender mode. CID to connect to. */
+			peer_cid = strtolx(optarg);
+			sender = true;
+			break;
+		case 'H': /* Help. */
+			usage();
+			break;
+		case 'Z': /* Zerocopy. */
+			zerocopy = true;
+			break;
+		default:
+			usage();
+		}
+	}
+
+	if (!sender)
+		run_receiver(rcvlowat_bytes);
+	else
+		run_sender(peer_cid, to_send_bytes);
+
+	return 0;
+}

linux-7.2.3/tools/testing/vsock/vsock_test_zerocopy.c

@@ -0,0 +1,432 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* MSG_ZEROCOPY feature tests for vsock
+ *
+ * Copyright (C) 2023 SberDevices.
+ *
+ * Author: Arseniy Krasnov <avkrasnov@salutedevices.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <poll.h>
+#include <linux/errqueue.h>
+#include <linux/kernel.h>
+#include <linux/sockios.h>
+#include <linux/time64.h>
+#include <errno.h>
+
+#include "control.h"
+#include "timeout.h"
+#include "vsock_test_zerocopy.h"
+#include "msg_zerocopy_common.h"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE		4096
+#endif
+
+#define VSOCK_TEST_DATA_MAX_IOV 3
+
+struct vsock_test_data {
+	/* This test case if for SOCK_STREAM only. */
+	bool stream_only;
+	/* Data must be zerocopied. This field is checked against
+	 * field 'ee_code' of the 'struct sock_extended_err', which
+	 * contains bit to detect that zerocopy transmission was
+	 * fallbacked to copy mode.
+	 */
+	bool zerocopied;
+	/* Enable SO_ZEROCOPY option on the socket. Without enabled
+	 * SO_ZEROCOPY, every MSG_ZEROCOPY transmission will behave
+	 * like without MSG_ZEROCOPY flag.
+	 */
+	bool so_zerocopy;
+	/* 'errno' after 'sendmsg()' call. */
+	int sendmsg_errno;
+	/* Number of valid elements in 'vecs'. */
+	int vecs_cnt;
+	struct iovec vecs[VSOCK_TEST_DATA_MAX_IOV];
+};
+
+static struct vsock_test_data test_data_array[] = {
+	/* Last element has non-page aligned size. */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ NULL, PAGE_SIZE },
+			{ NULL, 200 }
+		}
+	},
+	/* All elements have page aligned base and size. */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ NULL, PAGE_SIZE * 2 },
+			{ NULL, PAGE_SIZE * 3 }
+		}
+	},
+	/* All elements have page aligned base and size. But
+	 * data length is bigger than 64Kb.
+	 */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE * 16 },
+			{ NULL, PAGE_SIZE * 16 },
+			{ NULL, PAGE_SIZE * 16 }
+		}
+	},
+	/* Middle element has both non-page aligned base and size. */
+	{
+		.zerocopied = true,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ (void *)1, 100 },
+			{ NULL, PAGE_SIZE }
+		}
+	},
+	/* Middle element is unmapped. */
+	{
+		.zerocopied = false,
+		.so_zerocopy = true,
+		.sendmsg_errno = ENOMEM,
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ MAP_FAILED, PAGE_SIZE },
+			{ NULL, PAGE_SIZE }
+		}
+	},
+	/* Valid data, but SO_ZEROCOPY is off. This
+	 * will trigger fallback to copy.
+	 */
+	{
+		.zerocopied = false,
+		.so_zerocopy = false,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 1,
+		{
+			{ NULL, PAGE_SIZE }
+		}
+	},
+	/* Valid data, but message is bigger than peer's
+	 * buffer, so this will trigger fallback to copy.
+	 * This test is for SOCK_STREAM only, because
+	 * for SOCK_SEQPACKET, 'sendmsg()' returns EMSGSIZE.
+	 */
+	{
+		.stream_only = true,
+		.zerocopied = false,
+		.so_zerocopy = true,
+		.sendmsg_errno = 0,
+		.vecs_cnt = 1,
+		{
+			{ NULL, 100 * PAGE_SIZE }
+		}
+	},
+};
+
+#define POLL_TIMEOUT_MS		100
+
+static void test_client(const struct test_opts *opts,
+			const struct vsock_test_data *test_data,
+			bool sock_seqpacket)
+{
+	struct pollfd fds = { 0 };
+	struct msghdr msg = { 0 };
+	ssize_t sendmsg_res;
+	struct iovec *iovec;
+	int fd;
+
+	if (sock_seqpacket)
+		fd = vsock_seqpacket_connect(opts->peer_cid, opts->peer_port);
+	else
+		fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (test_data->so_zerocopy)
+		enable_so_zerocopy_check(fd);
+
+	iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt);
+
+	msg.msg_iov = iovec;
+	msg.msg_iovlen = test_data->vecs_cnt;
+
+	errno = 0;
+
+	sendmsg_res = sendmsg(fd, &msg, MSG_ZEROCOPY);
+	if (errno != test_data->sendmsg_errno) {
+		fprintf(stderr, "expected 'errno' == %i, got %i\n",
+			test_data->sendmsg_errno, errno);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!errno) {
+		if (sendmsg_res != iovec_bytes(iovec, test_data->vecs_cnt)) {
+			fprintf(stderr, "expected 'sendmsg()' == %li, got %li\n",
+				iovec_bytes(iovec, test_data->vecs_cnt),
+				sendmsg_res);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	fds.fd = fd;
+	fds.events = 0;
+
+	if (poll(&fds, 1, POLL_TIMEOUT_MS) < 0) {
+		perror("poll");
+		exit(EXIT_FAILURE);
+	}
+
+	if (fds.revents & POLLERR) {
+		vsock_recv_completion(fd, &test_data->zerocopied);
+	} else if (test_data->so_zerocopy && !test_data->sendmsg_errno) {
+		/* If we don't have data in the error queue, but
+		 * SO_ZEROCOPY was enabled and 'sendmsg()' was
+		 * successful - this is an error.
+		 */
+		fprintf(stderr, "POLLERR expected\n");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!test_data->sendmsg_errno)
+		control_writeulong(iovec_hash_djb2(iovec, test_data->vecs_cnt));
+	else
+		control_writeulong(0);
+
+	control_writeln("DONE");
+	free_test_iovec(test_data->vecs, iovec, test_data->vecs_cnt);
+	close(fd);
+}
+
+void test_stream_msgzcopy_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		test_client(opts, &test_data_array[i], false);
+}
+
+void test_seqpacket_msgzcopy_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++) {
+		if (test_data_array[i].stream_only)
+			continue;
+
+		test_client(opts, &test_data_array[i], true);
+	}
+}
+
+static void test_server(const struct test_opts *opts,
+			const struct vsock_test_data *test_data,
+			bool sock_seqpacket)
+{
+	unsigned long remote_hash;
+	unsigned long local_hash;
+	ssize_t total_bytes_rec;
+	unsigned char *data;
+	size_t data_len;
+	int fd;
+
+	if (sock_seqpacket)
+		fd = vsock_seqpacket_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	else
+		fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	data_len = iovec_bytes(test_data->vecs, test_data->vecs_cnt);
+
+	data = malloc(data_len);
+	if (!data) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	total_bytes_rec = 0;
+
+	while (total_bytes_rec != data_len) {
+		ssize_t bytes_rec;
+
+		bytes_rec = read(fd, data + total_bytes_rec,
+				 data_len - total_bytes_rec);
+		if (bytes_rec <= 0)
+			break;
+
+		total_bytes_rec += bytes_rec;
+	}
+
+	if (test_data->sendmsg_errno == 0)
+		local_hash = hash_djb2(data, data_len);
+	else
+		local_hash = 0;
+
+	free(data);
+
+	/* Waiting for some result. */
+	remote_hash = control_readulong();
+	if (remote_hash != local_hash) {
+		fprintf(stderr, "hash mismatch\n");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("DONE");
+	close(fd);
+}
+
+void test_stream_msgzcopy_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		test_server(opts, &test_data_array[i], false);
+}
+
+void test_seqpacket_msgzcopy_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++) {
+		if (test_data_array[i].stream_only)
+			continue;
+
+		test_server(opts, &test_data_array[i], true);
+	}
+}
+
+void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts)
+{
+	struct msghdr msg = { 0 };
+	char cmsg_data[128];
+	ssize_t res;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	msg.msg_control = cmsg_data;
+	msg.msg_controllen = sizeof(cmsg_data);
+
+	res = recvmsg(fd, &msg, MSG_ERRQUEUE);
+	if (res != -1) {
+		fprintf(stderr, "expected 'recvmsg(2)' failure, got %zi\n",
+			res);
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("DONE");
+	close(fd);
+}
+
+void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("DONE");
+	close(fd);
+}
+
+#define GOOD_COPY_LEN	128	/* net/vmw_vsock/virtio_transport_common.c */
+
+void test_stream_msgzcopy_mangle_client(const struct test_opts *opts)
+{
+	char sbuf1[PAGE_SIZE + 1], sbuf2[GOOD_COPY_LEN];
+	unsigned long hash;
+	struct pollfd fds;
+	int fd, i;
+
+	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	enable_so_zerocopy_check(fd);
+
+	memset(sbuf1, 'x', sizeof(sbuf1));
+	send_buf(fd, sbuf1, sizeof(sbuf1), 0, sizeof(sbuf1));
+
+	for (i = 0; i < sizeof(sbuf2); i++)
+		sbuf2[i] = rand() & 0xff;
+
+	send_buf(fd, sbuf2, sizeof(sbuf2), MSG_ZEROCOPY, sizeof(sbuf2));
+
+	hash = hash_djb2(sbuf2, sizeof(sbuf2));
+	control_writeulong(hash);
+
+	fds.fd = fd;
+	fds.events = 0;
+
+	if (poll(&fds, 1, TIMEOUT * MSEC_PER_SEC) != 1 ||
+	    !(fds.revents & POLLERR)) {
+		perror("poll");
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}
+
+void test_stream_msgzcopy_mangle_server(const struct test_opts *opts)
+{
+	unsigned long local_hash, remote_hash;
+	char rbuf[PAGE_SIZE + 1];
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Wait, don't race the (buggy) skbs coalescence. */
+	vsock_ioctl_int(fd, SIOCINQ, PAGE_SIZE + 1 + GOOD_COPY_LEN);
+
+	/* Discard the first packet. */
+	recv_buf(fd, rbuf, PAGE_SIZE + 1, 0, PAGE_SIZE + 1);
+
+	recv_buf(fd, rbuf, GOOD_COPY_LEN, 0, GOOD_COPY_LEN);
+	remote_hash = control_readulong();
+	local_hash = hash_djb2(rbuf, GOOD_COPY_LEN);
+
+	if (local_hash != remote_hash) {
+		fprintf(stderr, "Data received corrupted\n");
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}

linux-7.2.3/tools/testing/vsock/vsock_test_zerocopy.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef VSOCK_TEST_ZEROCOPY_H
+#define VSOCK_TEST_ZEROCOPY_H
+#include "util.h"
+
+void test_stream_msgzcopy_client(const struct test_opts *opts);
+void test_stream_msgzcopy_server(const struct test_opts *opts);
+
+void test_seqpacket_msgzcopy_client(const struct test_opts *opts);
+void test_seqpacket_msgzcopy_server(const struct test_opts *opts);
+
+void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts);
+void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts);
+
+void test_stream_msgzcopy_mangle_client(const struct test_opts *opts);
+void test_stream_msgzcopy_mangle_server(const struct test_opts *opts);
+
+#endif /* VSOCK_TEST_ZEROCOPY_H */

linux-7.2.3/tools/testing/vsock/vsock_uring_test.c

@@ -0,0 +1,353 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* io_uring tests for vsock
+ *
+ * Copyright (C) 2023 SberDevices.
+ *
+ * Author: Arseniy Krasnov <avkrasnov@salutedevices.com>
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <liburing.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/kernel.h>
+#include <error.h>
+
+#include "util.h"
+#include "control.h"
+#include "msg_zerocopy_common.h"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE		4096
+#endif
+
+#define RING_ENTRIES_NUM	4
+
+#define VSOCK_TEST_DATA_MAX_IOV 3
+
+struct vsock_io_uring_test {
+	/* Number of valid elements in 'vecs'. */
+	int vecs_cnt;
+	struct iovec vecs[VSOCK_TEST_DATA_MAX_IOV];
+};
+
+static struct vsock_io_uring_test test_data_array[] = {
+	/* All elements have page aligned base and size. */
+	{
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ NULL, 2 * PAGE_SIZE },
+			{ NULL, 3 * PAGE_SIZE },
+		}
+	},
+	/* Middle element has both non-page aligned base and size. */
+	{
+		.vecs_cnt = 3,
+		{
+			{ NULL, PAGE_SIZE },
+			{ (void *)1, 200  },
+			{ NULL, 3 * PAGE_SIZE },
+		}
+	}
+};
+
+static void vsock_io_uring_client(const struct test_opts *opts,
+				  const struct vsock_io_uring_test *test_data,
+				  bool msg_zerocopy)
+{
+	struct io_uring_sqe *sqe;
+	struct io_uring_cqe *cqe;
+	struct io_uring ring;
+	struct iovec *iovec;
+	struct msghdr msg;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (msg_zerocopy)
+		enable_so_zerocopy_check(fd);
+
+	iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt);
+
+	if (io_uring_queue_init(RING_ENTRIES_NUM, &ring, 0))
+		error(1, errno, "io_uring_queue_init");
+
+	if (io_uring_register_buffers(&ring, iovec, test_data->vecs_cnt))
+		error(1, errno, "io_uring_register_buffers");
+
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = iovec;
+	msg.msg_iovlen = test_data->vecs_cnt;
+	sqe = io_uring_get_sqe(&ring);
+
+	if (msg_zerocopy)
+		io_uring_prep_sendmsg_zc(sqe, fd, &msg, 0);
+	else
+		io_uring_prep_sendmsg(sqe, fd, &msg, 0);
+
+	if (io_uring_submit(&ring) != 1)
+		error(1, errno, "io_uring_submit");
+
+	if (io_uring_wait_cqe(&ring, &cqe))
+		error(1, errno, "io_uring_wait_cqe");
+
+	io_uring_cqe_seen(&ring, cqe);
+
+	control_writeulong(iovec_hash_djb2(iovec, test_data->vecs_cnt));
+
+	control_writeln("DONE");
+	io_uring_queue_exit(&ring);
+	free_test_iovec(test_data->vecs, iovec, test_data->vecs_cnt);
+	close(fd);
+}
+
+static void vsock_io_uring_server(const struct test_opts *opts,
+				  const struct vsock_io_uring_test *test_data)
+{
+	unsigned long remote_hash;
+	unsigned long local_hash;
+	struct io_uring ring;
+	size_t data_len;
+	size_t recv_len;
+	void *data;
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	data_len = iovec_bytes(test_data->vecs, test_data->vecs_cnt);
+
+	data = malloc(data_len);
+	if (!data) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
+	if (io_uring_queue_init(RING_ENTRIES_NUM, &ring, 0))
+		error(1, errno, "io_uring_queue_init");
+
+	recv_len = 0;
+
+	while (recv_len < data_len) {
+		struct io_uring_sqe *sqe;
+		struct io_uring_cqe *cqe;
+		struct iovec iovec;
+
+		sqe = io_uring_get_sqe(&ring);
+		iovec.iov_base = data + recv_len;
+		iovec.iov_len = data_len;
+
+		io_uring_prep_readv(sqe, fd, &iovec, 1, 0);
+
+		if (io_uring_submit(&ring) != 1)
+			error(1, errno, "io_uring_submit");
+
+		if (io_uring_wait_cqe(&ring, &cqe))
+			error(1, errno, "io_uring_wait_cqe");
+
+		recv_len += cqe->res;
+		io_uring_cqe_seen(&ring, cqe);
+	}
+
+	if (recv_len != data_len) {
+		fprintf(stderr, "expected %zu, got %zu\n", data_len,
+			recv_len);
+		exit(EXIT_FAILURE);
+	}
+
+	local_hash = hash_djb2(data, data_len);
+
+	remote_hash = control_readulong();
+	if (remote_hash != local_hash) {
+		fprintf(stderr, "hash mismatch\n");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("DONE");
+	io_uring_queue_exit(&ring);
+	free(data);
+}
+
+void test_stream_uring_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_server(opts, &test_data_array[i]);
+}
+
+void test_stream_uring_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_client(opts, &test_data_array[i], false);
+}
+
+void test_stream_uring_msg_zc_server(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_server(opts, &test_data_array[i]);
+}
+
+void test_stream_uring_msg_zc_client(const struct test_opts *opts)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_data_array); i++)
+		vsock_io_uring_client(opts, &test_data_array[i], true);
+}
+
+static struct test_case test_cases[] = {
+	{
+		.name = "SOCK_STREAM io_uring test",
+		.run_server = test_stream_uring_server,
+		.run_client = test_stream_uring_client,
+	},
+	{
+		.name = "SOCK_STREAM io_uring MSG_ZEROCOPY test",
+		.run_server = test_stream_uring_msg_zc_server,
+		.run_client = test_stream_uring_msg_zc_client,
+	},
+	{},
+};
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "control-host",
+		.has_arg = required_argument,
+		.val = 'H',
+	},
+	{
+		.name = "control-port",
+		.has_arg = required_argument,
+		.val = 'P',
+	},
+	{
+		.name = "mode",
+		.has_arg = required_argument,
+		.val = 'm',
+	},
+	{
+		.name = "peer-cid",
+		.has_arg = required_argument,
+		.val = 'p',
+	},
+	{
+		.name = "peer-port",
+		.has_arg = required_argument,
+		.val = 'q',
+	},
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = '?',
+	},
+	{},
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: vsock_uring_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--peer-port=<port>]\n"
+		"\n"
+		"  Server: vsock_uring_test --control-port=1234 --mode=server --peer-cid=3\n"
+		"  Client: vsock_uring_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n"
+		"\n"
+		"Run transmission tests using io_uring. Usage is the same as\n"
+		"in ./vsock_test\n"
+		"\n"
+		"Options:\n"
+		"  --help                 This help message\n"
+		"  --control-host <host>  Server IP address to connect to\n"
+		"  --control-port <port>  Server port to listen on/connect to\n"
+		"  --mode client|server   Server or client mode\n"
+		"  --peer-cid <cid>       CID of the other side\n"
+		"  --peer-port <port>     AF_VSOCK port used for the test [default: %d]\n",
+		DEFAULT_PEER_PORT
+		);
+	exit(EXIT_FAILURE);
+}
+
+int main(int argc, char **argv)
+{
+	const char *control_host = NULL;
+	const char *control_port = NULL;
+	struct test_opts opts = {
+		.mode = TEST_MODE_UNSET,
+		.peer_cid = VMADDR_CID_ANY,
+		.peer_port = DEFAULT_PEER_PORT,
+	};
+
+	init_signals();
+
+	for (;;) {
+		int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+		if (opt == -1)
+			break;
+
+		switch (opt) {
+		case 'H':
+			control_host = optarg;
+			break;
+		case 'm':
+			if (strcmp(optarg, "client") == 0) {
+				opts.mode = TEST_MODE_CLIENT;
+			} else if (strcmp(optarg, "server") == 0) {
+				opts.mode = TEST_MODE_SERVER;
+			} else {
+				fprintf(stderr, "--mode must be \"client\" or \"server\"\n");
+				return EXIT_FAILURE;
+			}
+			break;
+		case 'p':
+			opts.peer_cid = parse_cid(optarg);
+			break;
+		case 'q':
+			opts.peer_port = parse_port(optarg);
+			break;
+		case 'P':
+			control_port = optarg;
+			break;
+		case '?':
+		default:
+			usage();
+		}
+	}
+
+	if (!control_port)
+		usage();
+	if (opts.mode == TEST_MODE_UNSET)
+		usage();
+	if (opts.peer_cid == VMADDR_CID_ANY)
+		usage();
+
+	if (!control_host) {
+		if (opts.mode != TEST_MODE_SERVER)
+			usage();
+		control_host = "0.0.0.0";
+	}
+
+	control_init(control_host, control_port,
+		     opts.mode == TEST_MODE_SERVER);
+
+	run_tests(test_cases, &opts);
+
+	control_cleanup();
+
+	return 0;
+}