[rds-devel] [PATCH net-next 7/7] selftests/net: add zerocopy support for PF_RDS test case

[Sowmini Varadhan]

Send a cookie with sendmsg() on PF_RDS sockets, and process the
returned batched cookies in do_recv_completion()

Signed-off-by: Sowmini Varadhan <sowmini.varadhan at oracle.com>
---
 tools/testing/selftests/net/msg_zerocopy.c |  119 ++++++++++++++++++++-------
 1 files changed, 88 insertions(+), 31 deletions(-)

diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 7a5b353..19d2b1a 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -168,7 +168,26 @@ static int do_accept(int fd)
 	return fd;
 }
 
-static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy)
+static void add_zcopy_cookie(struct msghdr *msg)
+{
+	int olen = msg->msg_controllen;
+	struct cmsghdr *cm;
+	static uint32_t cookie;
+
+	msg->msg_controllen += CMSG_SPACE(sizeof(cookie));
+	msg->msg_control = (struct cmsghdr *)realloc(msg->msg_control,
+						     msg->msg_controllen);
+	if (!msg->msg_control)
+		error(1, errno, "cannot allocate cmsghdr for cookie");
+	cm = (void *)msg->msg_control + olen;
+	cm->cmsg_len = CMSG_SPACE(sizeof(cookie));
+	cm->cmsg_level = SOL_RDS;
+	cm->cmsg_type = RDS_CMSG_ZCOPY_COOKIE;
+	++cookie;
+	memcpy(CMSG_DATA(cm), &cookie, sizeof(cookie));
+}
+
+static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy, int domain)
 {
 	int ret, len, i, flags;
 
@@ -177,8 +196,11 @@ static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy)
 		len += msg->msg_iov[i].iov_len;
 
 	flags = MSG_DONTWAIT;
-	if (do_zerocopy)
+	if (do_zerocopy) {
 		flags |= MSG_ZEROCOPY;
+		if (domain == PF_RDS)
+			add_zcopy_cookie(msg);
+	}
 
 	ret = sendmsg(fd, msg, flags);
 	if (ret == -1 && errno == EAGAIN)
@@ -194,6 +216,11 @@ static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy)
 		if (do_zerocopy && ret)
 			expected_completions++;
 	}
+	if (do_zerocopy && domain == PF_RDS) {
+		free(msg->msg_control);
+		msg->msg_control = NULL;
+		msg->msg_controllen = 0;
+	}
 
 	return true;
 }
@@ -220,7 +247,9 @@ static void do_sendmsg_corked(int fd, struct msghdr *msg)
 		msg->msg_iov[0].iov_len = payload_len + extra_len;
 		extra_len = 0;
 
-		do_sendmsg(fd, msg, do_zerocopy);
+		do_sendmsg(fd, msg, do_zerocopy,
+			   (cfg_dst_addr.ss_family == AF_INET ?
+			    PF_INET : PF_INET6));
 	}
 
 	do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0);
@@ -324,10 +353,17 @@ static bool do_recv_completion(int fd)
 	uint32_t hi, lo, range;
 	int ret, zerocopy;
 	char control[100];
+	uint32_t ckbuf[SO_EE_ORIGIN_MAX_ZCOOKIES];
+	struct iovec iov;
 
 	msg.msg_control = control;
 	msg.msg_controllen = sizeof(control);
 
+	iov.iov_base = ckbuf;
+	iov.iov_len = (SO_EE_ORIGIN_MAX_ZCOOKIES * sizeof(ckbuf[0]));
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
 	ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
 	if (ret == -1 && errno == EAGAIN)
 		return false;
@@ -346,36 +382,57 @@ static bool do_recv_completion(int fd)
 		      cm->cmsg_level, cm->cmsg_type);
 
 	serr = (void *) CMSG_DATA(cm);
-	if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY)
-		error(1, 0, "serr: wrong origin: %u", serr->ee_origin);
-	if (serr->ee_errno != 0)
-		error(1, 0, "serr: wrong error code: %u", serr->ee_errno);
 
-	hi = serr->ee_data;
-	lo = serr->ee_info;
-	range = hi - lo + 1;
+	switch (serr->ee_origin) {
+	case SO_EE_ORIGIN_ZEROCOPY: {
+		if (serr->ee_errno != 0)
+			error(1, 0, "serr: wrong error code: %u",
+			      serr->ee_errno);
+		hi = serr->ee_data;
+		lo = serr->ee_info;
+		range = hi - lo + 1;
+
+		/* Detect notification gaps. These should not happen often,
+		 * if at all.  Gaps can occur due to drops, reordering and
+		 * retransmissions.
+		 */
+		if (lo != next_completion)
+			fprintf(stderr, "gap: %u..%u does not append to %u\n",
+				lo, hi, next_completion);
+		next_completion = hi + 1;
+
+		zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED);
+		if (zerocopied == -1)
+			zerocopied = zerocopy;
+		else if (zerocopied != zerocopy) {
+			fprintf(stderr, "serr: inconsistent\n");
+			zerocopied = zerocopy;
+		}
+		if (cfg_verbose >= 2)
+			fprintf(stderr, "completed: %u (h=%u l=%u)\n",
+				range, hi, lo);
 
-	/* Detect notification gaps. These should not happen often, if at all.
-	 * Gaps can occur due to drops, reordering and retransmissions.
-	 */
-	if (lo != next_completion)
-		fprintf(stderr, "gap: %u..%u does not append to %u\n",
-			lo, hi, next_completion);
-	next_completion = hi + 1;
-
-	zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED);
-	if (zerocopied == -1)
-		zerocopied = zerocopy;
-	else if (zerocopied != zerocopy) {
-		fprintf(stderr, "serr: inconsistent\n");
-		zerocopied = zerocopy;
+		completions += range;
+		break;
+	}
+	case SO_EE_ORIGIN_ZCOOKIE: {
+		int ncookies, i;
+
+		if (serr->ee_errno != 0)
+			error(1, 0, "serr: wrong error code: %u",
+			      serr->ee_errno);
+		ncookies = serr->ee_data;
+		for (i = 0; i < ncookies; i++)
+			if (cfg_verbose >= 2)
+				fprintf(stderr, "%d\n", ckbuf[i]);
+		completions += ncookies;
+		zerocopied = 1;
+		break;
+	}
+	default:
+		error(1, 0, "serr: wrong origin: %u", serr->ee_origin);
 	}
 
-	if (cfg_verbose >= 2)
-		fprintf(stderr, "completed: %u (h=%u l=%u)\n",
-			range, hi, lo);
-
-	completions += range;
 	return true;
 }
 
@@ -470,7 +527,7 @@ static void do_tx(int domain, int type, int protocol)
 		if (cfg_cork)
 			do_sendmsg_corked(fd, &msg);
 		else
-			do_sendmsg(fd, &msg, cfg_zerocopy);
+			do_sendmsg(fd, &msg, cfg_zerocopy, domain);
 
 		while (!do_poll(fd, POLLOUT)) {
 			if (cfg_zerocopy)
-- 
1.7.1