diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-18 17:39:57 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-18 17:39:57 +0000 |
commit | dc50eab76b709d68175a358d6e23a5a3890764d3 (patch) | |
tree | c754d0390db060af0213ff994f0ac310e4cfd6e9 /tools/testing/vsock | |
parent | Adding debian version 6.6.15-2. (diff) | |
download | linux-dc50eab76b709d68175a358d6e23a5a3890764d3.tar.xz linux-dc50eab76b709d68175a358d6e23a5a3890764d3.zip |
Merging upstream version 6.7.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/testing/vsock')
-rw-r--r-- | tools/testing/vsock/.gitignore | 1 | ||||
-rw-r--r-- | tools/testing/vsock/Makefile | 11 | ||||
-rw-r--r-- | tools/testing/vsock/msg_zerocopy_common.c | 87 | ||||
-rw-r--r-- | tools/testing/vsock/msg_zerocopy_common.h | 18 | ||||
-rw-r--r-- | tools/testing/vsock/util.c | 344 | ||||
-rw-r--r-- | tools/testing/vsock/util.h | 11 | ||||
-rw-r--r-- | tools/testing/vsock/vsock_perf.c | 80 | ||||
-rw-r--r-- | tools/testing/vsock/vsock_test.c | 391 | ||||
-rw-r--r-- | tools/testing/vsock/vsock_test_zerocopy.c | 358 | ||||
-rw-r--r-- | tools/testing/vsock/vsock_test_zerocopy.h | 15 | ||||
-rw-r--r-- | tools/testing/vsock/vsock_uring_test.c | 342 |
11 files changed, 1436 insertions, 222 deletions
diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore index a8adcfdc29..d9f798713c 100644 --- a/tools/testing/vsock/.gitignore +++ b/tools/testing/vsock/.gitignore @@ -3,3 +3,4 @@ vsock_test vsock_diag_test vsock_perf +vsock_uring_test diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 21a98ba565..a7f56a09ca 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -1,12 +1,15 @@ # SPDX-License-Identifier: GPL-2.0-only all: test vsock_perf -test: vsock_test vsock_diag_test -vsock_test: vsock_test.o timeout.o control.o util.o +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 +vsock_perf: vsock_perf.o msg_zerocopy_common.o + +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 + ${RM} *.o *.d vsock_test vsock_diag_test vsock_perf vsock_uring_test -include *.d diff --git a/tools/testing/vsock/msg_zerocopy_common.c b/tools/testing/vsock/msg_zerocopy_common.c new file mode 100644 index 0000000000..5a4bdf7b51 --- /dev/null +++ b/tools/testing/vsock/msg_zerocopy_common.c @@ -0,0 +1,87 @@ +// 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 enable_so_zerocopy(int fd) +{ + int val = 1; + + if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) { + perror("setsockopt"); + exit(EXIT_FAILURE); + } +} + +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); + } +} diff --git a/tools/testing/vsock/msg_zerocopy_common.h b/tools/testing/vsock/msg_zerocopy_common.h new file mode 100644 index 0000000000..3763c5cced --- /dev/null +++ b/tools/testing/vsock/msg_zerocopy_common.h @@ -0,0 +1,18 @@ +/* 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 enable_so_zerocopy(int fd); +void vsock_recv_completion(int fd, const bool *zerocopied); + +#endif /* MSG_ZEROCOPY_COMMON_H */ diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 01b636d303..ae2b33c21c 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -11,10 +11,12 @@ #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/mman.h> #include "timeout.h" #include "control.h" @@ -83,6 +85,48 @@ void vsock_wait_remote_close(int fd) close(epollfd); } +/* 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) +{ + struct sockaddr_vm sa_client = { + .svm_family = AF_VSOCK, + .svm_cid = VMADDR_CID_ANY, + .svm_port = bind_port, + }; + struct sockaddr_vm sa_server = { + .svm_family = AF_VSOCK, + .svm_cid = cid, + .svm_port = port, + }; + + int client_fd, ret; + + client_fd = socket(AF_VSOCK, type, 0); + if (client_fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) { + perror("bind"); + exit(EXIT_FAILURE); + } + + timeout_begin(TIMEOUT); + do { + ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + return client_fd; +} + /* Connect to <cid, port> and return the file descriptor. */ static int vsock_connect(unsigned int cid, unsigned int port, int type) { @@ -102,6 +146,10 @@ static int vsock_connect(unsigned int cid, unsigned int port, int type) control_expectln("LISTENING"); fd = socket(AF_VSOCK, type, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } timeout_begin(TIMEOUT); do { @@ -130,11 +178,8 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port) return vsock_connect(cid, port, SOCK_SEQPACKET); } -/* Listen on <cid, port> and return the first incoming connection. The remote - * address is stored to clientaddrp. clientaddrp may be NULL. - */ -static int vsock_accept(unsigned int cid, unsigned int port, - struct sockaddr_vm *clientaddrp, int type) +/* Listen on <cid, port> and return the file descriptor. */ +static int vsock_listen(unsigned int cid, unsigned int port, int type) { union { struct sockaddr sa; @@ -146,16 +191,13 @@ static int vsock_accept(unsigned int cid, unsigned int port, .svm_cid = cid, }, }; - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } clientaddr; - socklen_t clientaddr_len = sizeof(clientaddr.svm); int fd; - int client_fd; - int old_errno; fd = socket(AF_VSOCK, type, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { perror("bind"); @@ -167,6 +209,24 @@ static int vsock_accept(unsigned int cid, unsigned int port, 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. + */ +static 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); @@ -205,108 +265,149 @@ int vsock_stream_accept(unsigned int cid, unsigned int port, 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 one byte and check the return value. +/* Transmit bytes from a buffer and check the return value. * * expected_ret: * <0 Negative errno (for testing errors) * 0 End-of-file - * 1 Success + * >0 Success (bytes successfully written) */ -void send_byte(int fd, int expected_ret, int flags) +void send_buf(int fd, const void *buf, size_t len, int flags, + ssize_t expected_ret) { - const uint8_t byte = 'A'; - ssize_t nwritten; + ssize_t nwritten = 0; + ssize_t ret; timeout_begin(TIMEOUT); do { - nwritten = send(fd, &byte, sizeof(byte), flags); - timeout_check("write"); - } while (nwritten < 0 && errno == EINTR); + ret = send(fd, buf + nwritten, len - nwritten, flags); + timeout_check("send"); + + if (ret == 0 || (ret < 0 && errno != EINTR)) + break; + + nwritten += ret; + } while (nwritten < len); timeout_end(); if (expected_ret < 0) { - if (nwritten != -1) { - fprintf(stderr, "bogus send(2) return value %zd\n", - nwritten); + 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("write"); + perror("send"); exit(EXIT_FAILURE); } return; } - if (nwritten < 0) { - perror("write"); + if (ret < 0) { + perror("send"); exit(EXIT_FAILURE); } - if (nwritten == 0) { - if (expected_ret == 0) - return; - fprintf(stderr, "unexpected EOF while sending byte\n"); - exit(EXIT_FAILURE); - } - if (nwritten != sizeof(byte)) { - fprintf(stderr, "bogus send(2) return value %zd\n", nwritten); + 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); } } -/* Receive one byte and check the return value. +/* Receive bytes in a buffer and check the return value. * * expected_ret: * <0 Negative errno (for testing errors) * 0 End-of-file - * 1 Success + * >0 Success (bytes successfully read) */ -void recv_byte(int fd, int expected_ret, int flags) +void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret) { - uint8_t byte; - ssize_t nread; + ssize_t nread = 0; + ssize_t ret; timeout_begin(TIMEOUT); do { - nread = recv(fd, &byte, sizeof(byte), flags); - timeout_check("read"); - } while (nread < 0 && errno == EINTR); + ret = recv(fd, buf + nread, len - nread, flags); + timeout_check("recv"); + + if (ret == 0 || (ret < 0 && errno != EINTR)) + break; + + nread += ret; + } while (nread < len); timeout_end(); if (expected_ret < 0) { - if (nread != -1) { - fprintf(stderr, "bogus recv(2) return value %zd\n", - nread); + 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("read"); + perror("recv"); exit(EXIT_FAILURE); } return; } - if (nread < 0) { - perror("read"); + if (ret < 0) { + perror("recv"); exit(EXIT_FAILURE); } - if (nread == 0) { - if (expected_ret == 0) - return; - fprintf(stderr, "unexpected EOF while receiving byte\n"); - exit(EXIT_FAILURE); - } - if (nread != sizeof(byte)) { - fprintf(stderr, "bogus recv(2) return value %zd\n", nread); + 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) +{ + 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 %c\n", byte); exit(EXIT_FAILURE); @@ -408,3 +509,134 @@ unsigned long hash_djb2(const void *data, size_t len) 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); +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index fb99208a95..03c88d0cb8 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -36,12 +36,18 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); int vsock_stream_connect(unsigned int cid, unsigned int port); +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); +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, @@ -50,4 +56,9 @@ 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); 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); #endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_perf.c b/tools/testing/vsock/vsock_perf.c index a72520338f..4e8578f815 100644 --- a/tools/testing/vsock/vsock_perf.c +++ b/tools/testing/vsock/vsock_perf.c @@ -18,6 +18,9 @@ #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) @@ -31,6 +34,7 @@ static unsigned int port = DEFAULT_PORT; static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES; static unsigned long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES; +static bool zerocopy; static void error(const char *s) { @@ -252,10 +256,15 @@ 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; - printf("Run as sender\n"); + 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); @@ -265,38 +274,82 @@ static void run_sender(int peer_cid, unsigned long to_send_bytes) if (fd < 0) exit(EXIT_FAILURE); - data = malloc(buf_size_bytes); + if (zerocopy) { + enable_so_zerocopy(fd); - if (!data) { - fprintf(stderr, "'malloc()' failed\n"); - exit(EXIT_FAILURE); + 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; - sent = write(fd, data, buf_size_bytes); + 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, tx_total_ns)); - printf("total time in 'write()': %f sec\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); - free(data); + + if (zerocopy) + munmap(data, buf_size_bytes); + else + free(data); } static const char optstring[] = ""; @@ -336,6 +389,11 @@ static const struct option longopts[] = { .has_arg = required_argument, .val = 'R', }, + { + .name = "zerocopy", + .has_arg = no_argument, + .val = 'Z', + }, {}, }; @@ -351,6 +409,7 @@ static void usage(void) " --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" @@ -413,6 +472,9 @@ int main(int argc, char **argv) case 'H': /* Help. */ usage(); break; + case 'Z': /* Zerocopy. */ + zerocopy = true; + break; default: usage(); } diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 5dc7767039..01fa816868 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -19,7 +19,9 @@ #include <time.h> #include <sys/mman.h> #include <poll.h> +#include <signal.h> +#include "vsock_test_zerocopy.h" #include "timeout.h" #include "control.h" #include "util.h" @@ -261,7 +263,6 @@ static void test_msg_peek_client(const struct test_opts *opts, bool seqpacket) { unsigned char buf[MSG_PEEK_BUF_LEN]; - ssize_t send_size; int fd; int i; @@ -280,17 +281,7 @@ static void test_msg_peek_client(const struct test_opts *opts, control_expectln("SRVREADY"); - send_size = send(fd, buf, sizeof(buf), 0); - - if (send_size < 0) { - perror("send"); - exit(EXIT_FAILURE); - } - - if (send_size != sizeof(buf)) { - fprintf(stderr, "Invalid send size %zi\n", send_size); - exit(EXIT_FAILURE); - } + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); close(fd); } @@ -301,7 +292,6 @@ static void test_msg_peek_server(const struct test_opts *opts, unsigned char buf_half[MSG_PEEK_BUF_LEN / 2]; unsigned char buf_normal[MSG_PEEK_BUF_LEN]; unsigned char buf_peek[MSG_PEEK_BUF_LEN]; - ssize_t res; int fd; if (seqpacket) @@ -315,34 +305,16 @@ static void test_msg_peek_server(const struct test_opts *opts, } /* Peek from empty socket. */ - res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK | MSG_DONTWAIT); - if (res != -1) { - fprintf(stderr, "expected recv(2) failure, got %zi\n", res); - exit(EXIT_FAILURE); - } - - if (errno != EAGAIN) { - perror("EAGAIN expected"); - exit(EXIT_FAILURE); - } + recv_buf(fd, buf_peek, sizeof(buf_peek), MSG_PEEK | MSG_DONTWAIT, + -EAGAIN); control_writeln("SRVREADY"); /* Peek part of data. */ - res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK); - if (res != sizeof(buf_half)) { - fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n", - sizeof(buf_half), res); - exit(EXIT_FAILURE); - } + recv_buf(fd, buf_half, sizeof(buf_half), MSG_PEEK, sizeof(buf_half)); /* Peek whole data. */ - res = recv(fd, buf_peek, sizeof(buf_peek), MSG_PEEK); - if (res != sizeof(buf_peek)) { - fprintf(stderr, "recv(2) + MSG_PEEK, expected %zu, got %zi\n", - sizeof(buf_peek), res); - exit(EXIT_FAILURE); - } + recv_buf(fd, buf_peek, sizeof(buf_peek), MSG_PEEK, sizeof(buf_peek)); /* Compare partial and full peek. */ if (memcmp(buf_half, buf_peek, sizeof(buf_half))) { @@ -355,22 +327,11 @@ static void test_msg_peek_server(const struct test_opts *opts, * so check it with MSG_PEEK. We must get length * of the message. */ - res = recv(fd, buf_half, sizeof(buf_half), MSG_PEEK | - MSG_TRUNC); - if (res != sizeof(buf_peek)) { - fprintf(stderr, - "recv(2) + MSG_PEEK | MSG_TRUNC, exp %zu, got %zi\n", - sizeof(buf_half), res); - exit(EXIT_FAILURE); - } + recv_buf(fd, buf_half, sizeof(buf_half), MSG_PEEK | MSG_TRUNC, + sizeof(buf_peek)); } - res = recv(fd, buf_normal, sizeof(buf_normal), 0); - if (res != sizeof(buf_normal)) { - fprintf(stderr, "recv(2), expected %zu, got %zi\n", - sizeof(buf_normal), res); - exit(EXIT_FAILURE); - } + recv_buf(fd, buf_normal, sizeof(buf_normal), 0, sizeof(buf_normal)); /* Compare full peek and normal read. */ if (memcmp(buf_peek, buf_normal, sizeof(buf_peek))) { @@ -417,7 +378,6 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) msg_count = SOCK_BUF_SIZE / max_msg_size; for (int i = 0; i < msg_count; i++) { - ssize_t send_size; size_t buf_size; int flags; void *buf; @@ -445,17 +405,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) flags = 0; } - send_size = send(fd, buf, buf_size, flags); - - if (send_size < 0) { - perror("send"); - exit(EXIT_FAILURE); - } - - if (send_size != buf_size) { - fprintf(stderr, "Invalid send size\n"); - exit(EXIT_FAILURE); - } + send_buf(fd, buf, buf_size, flags, buf_size); /* * Hash sum is computed at both client and server in @@ -561,10 +511,7 @@ static void test_seqpacket_msg_trunc_client(const struct test_opts *opts) exit(EXIT_FAILURE); } - if (send(fd, buf, sizeof(buf), 0) != sizeof(buf)) { - perror("send failed"); - exit(EXIT_FAILURE); - } + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); control_writeln("SENDDONE"); close(fd); @@ -686,7 +633,6 @@ static void test_seqpacket_timeout_server(const struct test_opts *opts) static void test_seqpacket_bigmsg_client(const struct test_opts *opts) { unsigned long sock_buf_size; - ssize_t send_size; socklen_t len; void *data; int fd; @@ -713,18 +659,7 @@ static void test_seqpacket_bigmsg_client(const struct test_opts *opts) exit(EXIT_FAILURE); } - send_size = send(fd, data, sock_buf_size, 0); - if (send_size != -1) { - fprintf(stderr, "expected 'send(2)' failure, got %zi\n", - send_size); - exit(EXIT_FAILURE); - } - - if (errno != EMSGSIZE) { - fprintf(stderr, "expected EMSGSIZE in 'errno', got %i\n", - errno); - exit(EXIT_FAILURE); - } + send_buf(fd, data, sock_buf_size, 0, -EMSGSIZE); control_writeln("CLISENT"); @@ -778,15 +713,9 @@ static void test_seqpacket_invalid_rec_buffer_client(const struct test_opts *opt memset(buf1, BUF_PATTERN_1, buf_size); memset(buf2, BUF_PATTERN_2, buf_size); - if (send(fd, buf1, buf_size, 0) != buf_size) { - perror("send failed"); - exit(EXIT_FAILURE); - } + send_buf(fd, buf1, buf_size, 0, buf_size); - if (send(fd, buf2, buf_size, 0) != buf_size) { - perror("send failed"); - exit(EXIT_FAILURE); - } + send_buf(fd, buf2, buf_size, 0, buf_size); close(fd); } @@ -907,7 +836,6 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) unsigned long lowat_val = RCVLOWAT_BUF_SIZE; char buf[RCVLOWAT_BUF_SIZE]; struct pollfd fds; - ssize_t read_res; short poll_flags; int fd; @@ -962,12 +890,7 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) /* Use MSG_DONTWAIT, if call is going to wait, EAGAIN * will be returned. */ - read_res = recv(fd, buf, sizeof(buf), MSG_DONTWAIT); - if (read_res != RCVLOWAT_BUF_SIZE) { - fprintf(stderr, "Unexpected recv result %zi\n", - read_res); - exit(EXIT_FAILURE); - } + recv_buf(fd, buf, sizeof(buf), MSG_DONTWAIT, RCVLOWAT_BUF_SIZE); control_writeln("POLLDONE"); @@ -979,7 +902,7 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) static void test_inv_buf_client(const struct test_opts *opts, bool stream) { unsigned char data[INV_BUF_TEST_DATA_LEN] = {0}; - ssize_t ret; + ssize_t expected_ret; int fd; if (stream) @@ -995,39 +918,18 @@ static void test_inv_buf_client(const struct test_opts *opts, bool stream) control_expectln("SENDDONE"); /* Use invalid buffer here. */ - ret = recv(fd, NULL, sizeof(data), 0); - if (ret != -1) { - fprintf(stderr, "expected recv(2) failure, got %zi\n", ret); - exit(EXIT_FAILURE); - } - - if (errno != EFAULT) { - fprintf(stderr, "unexpected recv(2) errno %d\n", errno); - exit(EXIT_FAILURE); - } - - ret = recv(fd, data, sizeof(data), MSG_DONTWAIT); + recv_buf(fd, NULL, sizeof(data), 0, -EFAULT); if (stream) { /* For SOCK_STREAM we must continue reading. */ - if (ret != sizeof(data)) { - fprintf(stderr, "expected recv(2) success, got %zi\n", ret); - exit(EXIT_FAILURE); - } - /* Don't check errno in case of success. */ + expected_ret = sizeof(data); } else { /* For SOCK_SEQPACKET socket's queue must be empty. */ - if (ret != -1) { - fprintf(stderr, "expected recv(2) failure, got %zi\n", ret); - exit(EXIT_FAILURE); - } - - if (errno != EAGAIN) { - fprintf(stderr, "unexpected recv(2) errno %d\n", errno); - exit(EXIT_FAILURE); - } + expected_ret = -EAGAIN; } + recv_buf(fd, data, sizeof(data), MSG_DONTWAIT, expected_ret); + control_writeln("DONE"); close(fd); @@ -1036,7 +938,6 @@ static void test_inv_buf_client(const struct test_opts *opts, bool stream) static void test_inv_buf_server(const struct test_opts *opts, bool stream) { unsigned char data[INV_BUF_TEST_DATA_LEN] = {0}; - ssize_t res; int fd; if (stream) @@ -1049,11 +950,7 @@ static void test_inv_buf_server(const struct test_opts *opts, bool stream) exit(EXIT_FAILURE); } - res = send(fd, data, sizeof(data), 0); - if (res != sizeof(data)) { - fprintf(stderr, "unexpected send(2) result %zi\n", res); - exit(EXIT_FAILURE); - } + send_buf(fd, data, sizeof(data), 0, sizeof(data)); control_writeln("SENDDONE"); @@ -1087,7 +984,6 @@ static void test_seqpacket_inv_buf_server(const struct test_opts *opts) static void test_stream_virtio_skb_merge_client(const struct test_opts *opts) { - ssize_t res; int fd; fd = vsock_stream_connect(opts->peer_cid, 1234); @@ -1097,22 +993,14 @@ static void test_stream_virtio_skb_merge_client(const struct test_opts *opts) } /* Send first skbuff. */ - res = send(fd, HELLO_STR, strlen(HELLO_STR), 0); - if (res != strlen(HELLO_STR)) { - fprintf(stderr, "unexpected send(2) result %zi\n", res); - exit(EXIT_FAILURE); - } + send_buf(fd, HELLO_STR, strlen(HELLO_STR), 0, strlen(HELLO_STR)); control_writeln("SEND0"); /* Peer reads part of first skbuff. */ control_expectln("REPLY0"); /* Send second skbuff, it will be appended to the first. */ - res = send(fd, WORLD_STR, strlen(WORLD_STR), 0); - if (res != strlen(WORLD_STR)) { - fprintf(stderr, "unexpected send(2) result %zi\n", res); - exit(EXIT_FAILURE); - } + send_buf(fd, WORLD_STR, strlen(WORLD_STR), 0, strlen(WORLD_STR)); control_writeln("SEND1"); /* Peer reads merged skbuff packet. */ @@ -1123,8 +1011,8 @@ static void test_stream_virtio_skb_merge_client(const struct test_opts *opts) static void test_stream_virtio_skb_merge_server(const struct test_opts *opts) { + size_t read = 0, to_read; unsigned char buf[64]; - ssize_t res; int fd; fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); @@ -1136,26 +1024,21 @@ static void test_stream_virtio_skb_merge_server(const struct test_opts *opts) control_expectln("SEND0"); /* Read skbuff partially. */ - res = recv(fd, buf, 2, 0); - if (res != 2) { - fprintf(stderr, "expected recv(2) returns 2 bytes, got %zi\n", res); - exit(EXIT_FAILURE); - } + to_read = 2; + recv_buf(fd, buf + read, to_read, 0, to_read); + read += to_read; control_writeln("REPLY0"); control_expectln("SEND1"); - res = recv(fd, buf + 2, sizeof(buf) - 2, 0); - if (res != 8) { - fprintf(stderr, "expected recv(2) returns 8 bytes, got %zi\n", res); - exit(EXIT_FAILURE); - } + /* Read the rest of both buffers */ + to_read = strlen(HELLO_STR WORLD_STR) - read; + recv_buf(fd, buf + read, to_read, 0, to_read); + read += to_read; - res = recv(fd, buf, sizeof(buf) - 8 - 2, MSG_DONTWAIT); - if (res != -1) { - fprintf(stderr, "expected recv(2) failure, got %zi\n", res); - exit(EXIT_FAILURE); - } + /* No more bytes should be there */ + to_read = sizeof(buf) - read; + recv_buf(fd, buf + read, to_read, MSG_DONTWAIT, -EAGAIN); if (memcmp(buf, HELLO_STR WORLD_STR, strlen(HELLO_STR WORLD_STR))) { fprintf(stderr, "pattern mismatch\n"); @@ -1177,6 +1060,178 @@ static void test_seqpacket_msg_peek_server(const struct test_opts *opts) return test_msg_peek_server(opts, true); } +static sig_atomic_t have_sigpipe; + +static void sigpipe(int signo) +{ + have_sigpipe = 1; +} + +static void test_stream_check_sigpipe(int fd) +{ + ssize_t res; + + have_sigpipe = 0; + + res = send(fd, "A", 1, 0); + if (res != -1) { + fprintf(stderr, "expected send(2) failure, got %zi\n", res); + exit(EXIT_FAILURE); + } + + if (!have_sigpipe) { + fprintf(stderr, "SIGPIPE expected\n"); + exit(EXIT_FAILURE); + } + + have_sigpipe = 0; + + res = send(fd, "A", 1, MSG_NOSIGNAL); + if (res != -1) { + fprintf(stderr, "expected send(2) failure, got %zi\n", res); + exit(EXIT_FAILURE); + } + + if (have_sigpipe) { + fprintf(stderr, "SIGPIPE not expected\n"); + exit(EXIT_FAILURE); + } +} + +static void test_stream_shutwr_client(const struct test_opts *opts) +{ + int fd; + + struct sigaction act = { + .sa_handler = sigpipe, + }; + + sigaction(SIGPIPE, &act, NULL); + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (shutdown(fd, SHUT_WR)) { + perror("shutdown"); + exit(EXIT_FAILURE); + } + + test_stream_check_sigpipe(fd); + + control_writeln("CLIENTDONE"); + + close(fd); +} + +static void test_stream_shutwr_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("CLIENTDONE"); + + close(fd); +} + +static void test_stream_shutrd_client(const struct test_opts *opts) +{ + int fd; + + struct sigaction act = { + .sa_handler = sigpipe, + }; + + sigaction(SIGPIPE, &act, NULL); + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + control_expectln("SHUTRDDONE"); + + test_stream_check_sigpipe(fd); + + control_writeln("CLIENTDONE"); + + close(fd); +} + +static void test_stream_shutrd_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + if (shutdown(fd, SHUT_RD)) { + perror("shutdown"); + exit(EXIT_FAILURE); + } + + control_writeln("SHUTRDDONE"); + control_expectln("CLIENTDONE"); + + close(fd); +} + +static void test_double_bind_connect_server(const struct test_opts *opts) +{ + int listen_fd, client_fd, i; + struct sockaddr_vm sa_client; + socklen_t socklen_client = sizeof(sa_client); + + listen_fd = vsock_stream_listen(VMADDR_CID_ANY, 1234); + + for (i = 0; i < 2; i++) { + control_writeln("LISTENING"); + + timeout_begin(TIMEOUT); + do { + client_fd = accept(listen_fd, (struct sockaddr *)&sa_client, + &socklen_client); + timeout_check("accept"); + } while (client_fd < 0 && errno == EINTR); + timeout_end(); + + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Waiting for remote peer to close connection */ + vsock_wait_remote_close(client_fd); + } + + close(listen_fd); +} + +static void test_double_bind_connect_client(const struct test_opts *opts) +{ + int i, client_fd; + + for (i = 0; i < 2; i++) { + /* Wait until server is ready to accept a new connection */ + control_expectln("LISTENING"); + + client_fd = vsock_bind_connect(opts->peer_cid, 1234, 4321, SOCK_STREAM); + + close(client_fd); + } +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1257,6 +1312,36 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_msg_peek_client, .run_server = test_seqpacket_msg_peek_server, }, + { + .name = "SOCK_STREAM SHUT_WR", + .run_client = test_stream_shutwr_client, + .run_server = test_stream_shutwr_server, + }, + { + .name = "SOCK_STREAM SHUT_RD", + .run_client = test_stream_shutrd_client, + .run_server = test_stream_shutrd_server, + }, + { + .name = "SOCK_STREAM MSG_ZEROCOPY", + .run_client = test_stream_msgzcopy_client, + .run_server = test_stream_msgzcopy_server, + }, + { + .name = "SOCK_SEQPACKET MSG_ZEROCOPY", + .run_client = test_seqpacket_msgzcopy_client, + .run_server = test_seqpacket_msgzcopy_server, + }, + { + .name = "SOCK_STREAM MSG_ZEROCOPY empty MSG_ERRQUEUE", + .run_client = test_stream_msgzcopy_empty_errq_client, + .run_server = test_stream_msgzcopy_empty_errq_server, + }, + { + .name = "SOCK_STREAM double bind connect", + .run_client = test_double_bind_connect_client, + .run_server = test_double_bind_connect_server, + }, {}, }; diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c new file mode 100644 index 0000000000..a16ff76484 --- /dev/null +++ b/tools/testing/vsock/vsock_test_zerocopy.c @@ -0,0 +1,358 @@ +// 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/mman.h> +#include <unistd.h> +#include <poll.h> +#include <linux/errqueue.h> +#include <linux/kernel.h> +#include <errno.h> + +#include "control.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, 1234); + else + fd = vsock_stream_connect(opts->peer_cid, 1234); + + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (test_data->so_zerocopy) + enable_so_zerocopy(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, 1234, NULL); + else + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, 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, 1234); + 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, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("DONE"); + close(fd); +} diff --git a/tools/testing/vsock/vsock_test_zerocopy.h b/tools/testing/vsock/vsock_test_zerocopy.h new file mode 100644 index 0000000000..3ef2579e02 --- /dev/null +++ b/tools/testing/vsock/vsock_test_zerocopy.h @@ -0,0 +1,15 @@ +/* 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); + +#endif /* VSOCK_TEST_ZEROCOPY_H */ diff --git a/tools/testing/vsock/vsock_uring_test.c b/tools/testing/vsock/vsock_uring_test.c new file mode 100644 index 0000000000..d976d35f0b --- /dev/null +++ b/tools/testing/vsock/vsock_uring_test.c @@ -0,0 +1,342 @@ +// 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, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (msg_zerocopy) + enable_so_zerocopy(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, 1234, 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 = "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>\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" + ); + 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, + }; + + 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 '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; +} |