diff mbox series

[RFC,net-next,v1,2/5] selftests: ncdevmem: Implement devmem TCP TX

Message ID 20241221004236.2629280-3-almasrymina@google.com (mailing list archive)
State RFC
Delegated to: Netdev Maintainers
Headers show
Series Device memory TCP TX | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; GEN HAS DIFF 2 files changed, 115 insertions(+);
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success Errors and warnings before: 0 (+23) this patch: 0 (+23)
netdev/cc_maintainers success CCed 10 of 10 maintainers
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 81 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Mina Almasry Dec. 21, 2024, 12:42 a.m. UTC
Add support for devmem TX in ncdevmem.

This is a combination of the ncdevmem from the devmem TCP series RFCv1
which included the TX path, and work by Stan to include the netlink API
and refactored on top of his generic memory_provider support.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
---
 .../selftests/drivers/net/hw/ncdevmem.c       | 261 +++++++++++++++++-
 1 file changed, 259 insertions(+), 2 deletions(-)

Comments

Stanislav Fomichev Dec. 21, 2024, 4:57 a.m. UTC | #1
On 12/21, Mina Almasry wrote:
> Add support for devmem TX in ncdevmem.
> 
> This is a combination of the ncdevmem from the devmem TCP series RFCv1
> which included the TX path, and work by Stan to include the netlink API
> and refactored on top of his generic memory_provider support.

Do you plan to include python part for the non-rfc series [1]? Or should
I follow up separately?

1: https://github.com/fomichev/linux/commit/df5ef094db57f6c49603e6be5730782e379dd237
diff mbox series

Patch

diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 19a6969643f4..c1cbe2e11230 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -40,15 +40,18 @@ 
 #include <fcntl.h>
 #include <malloc.h>
 #include <error.h>
+#include <poll.h>
 
 #include <arpa/inet.h>
 #include <sys/socket.h>
 #include <sys/mman.h>
 #include <sys/ioctl.h>
 #include <sys/syscall.h>
+#include <sys/time.h>
 
 #include <linux/memfd.h>
 #include <linux/dma-buf.h>
+#include <linux/errqueue.h>
 #include <linux/udmabuf.h>
 #include <libmnl/libmnl.h>
 #include <linux/types.h>
@@ -80,6 +83,8 @@  static int num_queues = -1;
 static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
+static uint32_t tx_dmabuf_id;
+static int waittime_ms = 500;
 
 struct memory_buffer {
 	int fd;
@@ -93,6 +98,8 @@  struct memory_buffer {
 struct memory_provider {
 	struct memory_buffer *(*alloc)(size_t size);
 	void (*free)(struct memory_buffer *ctx);
+	void (*memcpy_to_device)(struct memory_buffer *dst, size_t off,
+				 void *src, int n);
 	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
 				   size_t off, int n);
 };
@@ -153,6 +160,20 @@  static void udmabuf_free(struct memory_buffer *ctx)
 	free(ctx);
 }
 
+static void udmabuf_memcpy_to_device(struct memory_buffer *dst, size_t off,
+				     void *src, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst->buf_mem + off, src, n);
+
+	sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
 static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
 				       size_t off, int n)
 {
@@ -170,6 +191,7 @@  static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
 static struct memory_provider udmabuf_memory_provider = {
 	.alloc = udmabuf_alloc,
 	.free = udmabuf_free,
+	.memcpy_to_device = udmabuf_memcpy_to_device,
 	.memcpy_from_device = udmabuf_memcpy_from_device,
 };
 
@@ -394,6 +416,49 @@  static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
 	return -1;
 }
 
+static int bind_tx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct ynl_sock **ys)
+{
+	struct netdev_bind_tx_req *req = NULL;
+	struct netdev_bind_tx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_tx_req_alloc();
+	netdev_bind_tx_req_set_ifindex(req, ifindex);
+	netdev_bind_tx_req_set_fd(req, dmabuf_fd);
+
+	rsp = netdev_bind_tx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_tx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	fprintf(stderr, "got tx dmabuf id=%d\n", rsp->id);
+	tx_dmabuf_id = rsp->id;
+
+	netdev_bind_tx_req_free(req);
+	netdev_bind_tx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_tx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
 static void enable_reuseaddr(int fd)
 {
 	int opt = 1;
@@ -432,7 +497,7 @@  static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
 	return 0;
 }
 
-int do_server(struct memory_buffer *mem)
+static int do_server(struct memory_buffer *mem)
 {
 	char ctrl_data[sizeof(int) * 20000];
 	struct netdev_queue_id *queues;
@@ -686,6 +751,198 @@  void run_devmem_tests(void)
 	provider->free(mem);
 }
 
+static unsigned long gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int do_poll(int fd)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.events = POLLERR;
+	pfd.revents = 0;
+	pfd.fd = fd;
+
+	ret = poll(&pfd, 1, waittime_ms);
+	if (ret == -1)
+		error(1, errno, "poll");
+
+	return ret && (pfd.revents & POLLERR);
+}
+
+static void wait_compl(int fd)
+{
+	int64_t tstop = gettimeofday_ms() + waittime_ms;
+	char control[CMSG_SPACE(100)] = {};
+	struct sock_extended_err *serr;
+	struct msghdr msg = {};
+	struct cmsghdr *cm;
+	int retries = 10;
+	__u32 hi, lo;
+	int ret;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	while (gettimeofday_ms() < tstop) {
+		if (!do_poll(fd))
+			continue;
+
+		ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				continue;
+			error(1, ret, "recvmsg(MSG_ERRQUEUE)");
+			return;
+		}
+		if (msg.msg_flags & MSG_CTRUNC)
+			error(1, 0, "MSG_CTRUNC\n");
+
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_IP &&
+			    cm->cmsg_level != SOL_IPV6)
+				continue;
+			if (cm->cmsg_level == SOL_IP &&
+			    cm->cmsg_type != IP_RECVERR)
+				continue;
+			if (cm->cmsg_level == SOL_IPV6 &&
+			    cm->cmsg_type != IPV6_RECVERR)
+				continue;
+
+			serr = (void *)CMSG_DATA(cm);
+			if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY)
+				error(1, 0, "wrong origin %u", serr->ee_origin);
+			if (serr->ee_errno != 0)
+				error(1, 0, "wrong errno %d", serr->ee_errno);
+
+			hi = serr->ee_data;
+			lo = serr->ee_info;
+
+			fprintf(stderr, "tx complete [%d,%d]\n", lo, hi);
+			return;
+		}
+	}
+
+	error(1, 0, "did not receive tx completion");
+}
+
+static int do_client(struct memory_buffer *mem)
+{
+	char ctrl_data[CMSG_SPACE(sizeof(struct dmabuf_tx_cmsg))];
+	struct sockaddr_in6 server_sin;
+	struct sockaddr_in6 client_sin;
+	struct dmabuf_tx_cmsg ddmabuf;
+	struct ynl_sock *ys = NULL;
+	struct msghdr msg = {};
+	ssize_t line_size = 0;
+	struct cmsghdr *cmsg;
+	uint64_t off = 100;
+	char *line = NULL;
+	struct iovec iov;
+	size_t len = 0;
+	int socket_fd;
+	int opt = 1;
+	int ret;
+
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0)
+		error(1, 0, "parse server address");
+
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (socket_fd < 0)
+		error(1, socket_fd, "create socket");
+
+	enable_reuseaddr(socket_fd);
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname,
+			 strlen(ifname) + 1);
+	if (ret)
+		error(1, ret, "bindtodevice");
+
+	if (bind_tx_queue(ifindex, mem->fd, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	ret = parse_address(client_ip, atoi(port), &client_sin);
+	if (ret < 0)
+		error(1, 0, "parse client address");
+
+	ret = bind(socket_fd, &client_sin, sizeof(client_sin));
+	if (ret)
+		error(1, ret, "bind");
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
+	if (ret)
+		error(1, ret, "set sock opt");
+
+	fprintf(stderr, "Connect to %s %d (via %s)\n", server_ip,
+		ntohs(server_sin.sin6_port), ifname);
+
+	ret = connect(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret)
+		error(1, ret, "connect");
+
+	while (1) {
+		free(line);
+		line = NULL;
+		line_size = getline(&line, &len, stdin);
+
+		if (line_size < 0)
+			break;
+
+		provider->memcpy_to_device(mem, off, line, line_size);
+
+		while (line_size) {
+			fprintf(stderr, "read line_size=%ld off=%d\n",
+				line_size, off);
+
+			iov.iov_base = NULL;
+			iov.iov_len = line_size;
+
+			msg.msg_iov = &iov;
+			msg.msg_iovlen = 1;
+
+			msg.msg_control = ctrl_data;
+			msg.msg_controllen = sizeof(ctrl_data);
+
+			cmsg = CMSG_FIRSTHDR(&msg);
+			cmsg->cmsg_level = SOL_SOCKET;
+			cmsg->cmsg_type = SCM_DEVMEM_DMABUF;
+			cmsg->cmsg_len = CMSG_LEN(sizeof(struct dmabuf_tx_cmsg));
+
+			ddmabuf.dmabuf_id = tx_dmabuf_id;
+			ddmabuf.dmabuf_offset = off;
+
+			*((struct dmabuf_tx_cmsg *)CMSG_DATA(cmsg)) = ddmabuf;
+
+			ret = sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
+			if (ret < 0)
+				error(1, errno, "Failed sendmsg");
+
+			fprintf(stderr, "sendmsg_ret=%d\n", ret);
+
+			off += ret;
+			line_size -= ret;
+
+			wait_compl(socket_fd);
+		}
+	}
+
+	fprintf(stderr, "%s: tx ok\n", TEST_PREFIX);
+
+	free(line);
+	close(socket_fd);
+
+	if (ys)
+		ynl_sock_destroy(ys);
+
+	return 0;
+}
+
 int main(int argc, char *argv[])
 {
 	struct memory_buffer *mem;
@@ -779,7 +1036,7 @@  int main(int argc, char *argv[])
 		error(1, 0, "Missing -p argument\n");
 
 	mem = provider->alloc(getpagesize() * NUM_PAGES);
-	ret = is_server ? do_server(mem) : 1;
+	ret = is_server ? do_server(mem) : do_client(mem);
 	provider->free(mem);
 
 	return ret;