selftests: net: udpgso_bench_tx: Cater for pending datagrams zerocopy benchmarking

[ Upstream commit 329c9cd769 ]

The test tool can check that the zerocopy number of completions value is
valid taking into consideration the number of datagram send calls. This can
catch the system into a state where the datagrams are still in the system
(for example in a qdisk, waiting for the network interface to return a
completion notification, etc).

This change adds a retry logic of computing the number of completions up to
a configurable (via CLI) timeout (default: 2 seconds).

Fixes: 79ebc3c260 ("net/udpgso_bench_tx: options to exercise TX CMSG")
Signed-off-by: Andrei Gherzan <andrei.gherzan@canonical.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230201001612.515730-4-andrei.gherzan@canonical.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

tools/testing/selftests/net/udpgso_bench_tx.c

@@ -62,6 +62,7 @@ static int	cfg_payload_len	= (1472 * 42);
 static int	cfg_port	= 8000;
 static int	cfg_runtime_ms	= -1;
 static bool	cfg_poll;
+static int	cfg_poll_loop_timeout_ms = 2000;
 static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
@@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd)
 	}
 }
 
-static void flush_errqueue(int fd, const bool do_poll)
+static void flush_errqueue(int fd, const bool do_poll,
+			   unsigned long poll_timeout, const bool poll_err)
 {
 	if (do_poll) {
 		struct pollfd fds = {0};
 		int ret;
 
 		fds.fd = fd;
-		ret = poll(&fds, 1, 500);
+		ret = poll(&fds, 1, poll_timeout);
 		if (ret == 0) {
-			if (cfg_verbose)
+			if ((cfg_verbose) && (poll_err))
 				fprintf(stderr, "poll timeout\n");
 		} else if (ret < 0) {
 			error(1, errno, "poll");
@@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll)
 	flush_errqueue_recv(fd);
 }
 
+static void flush_errqueue_retry(int fd, unsigned long num_sends)
+{
+	unsigned long tnow, tstop;
+	bool first_try = true;
+
+	tnow = gettimeofday_ms();
+	tstop = tnow + cfg_poll_loop_timeout_ms;
+	do {
+		flush_errqueue(fd, true, tstop - tnow, first_try);
+		first_try = false;
+		tnow = gettimeofday_ms();
+	} while ((stat_zcopies != num_sends) && (tnow < tstop));
+}
+
 static int send_tcp(int fd, char *data)
 {
 	int ret, done = 0, count = 0;
@@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
+	error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] "
+		    "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) {
+	while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv)
 		case 'l':
 			cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
 			break;
+		case 'L':
+			cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000;
+			break;
 		case 'm':
 			cfg_sendmmsg = true;
 			break;
@@ -679,7 +699,7 @@ int main(int argc, char **argv)
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
 		if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp)
-			flush_errqueue(fd, cfg_poll);
+			flush_errqueue(fd, cfg_poll, 500, true);
 
 		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
 			break;
@@ -698,7 +718,7 @@ int main(int argc, char **argv)
 	} while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
 
 	if (cfg_zerocopy || cfg_tx_tstamp)
-		flush_errqueue(fd, true);
+		flush_errqueue_retry(fd, num_sends);
 
 	if (close(fd))
 		error(1, errno, "close");