Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 340 insertions, 52 deletions

diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c
index 7cc9d22..7c25c0c 100644
--- a/samples/sockmap/sockmap_user.c
+++ b/samples/sockmap/sockmap_user.c
@@ -23,8 +23,11 @@
 #include <stdbool.h>
 #include <signal.h>
 #include <fcntl.h>
+#include <sys/wait.h>
+#include <time.h>
 
 #include <sys/time.h>
+#include <sys/resource.h>
 #include <sys/types.h>
 
 #include <linux/netlink.h>
@@ -35,6 +38,8 @@
 #include <assert.h>
 #include <libgen.h>
 
+#include <getopt.h>
+
 #include "../bpf/bpf_load.h"
 #include "../bpf/bpf_util.h"
 #include "../bpf/libbpf.h"
@@ -46,15 +51,42 @@ void running_handler(int a);
 #define S1_PORT 10000
 #define S2_PORT 10001
 
-static int sockmap_test_sockets(int rate, int dot)
+/* global sockets */
+int s1, s2, c1, c2, p1, p2;
+
+static const struct option long_options[] = {
+	{"help",	no_argument,		NULL, 'h' },
+	{"cgroup",	required_argument,	NULL, 'c' },
+	{"rate",	required_argument,	NULL, 'r' },
+	{"verbose",	no_argument,		NULL, 'v' },
+	{"iov_count",	required_argument,	NULL, 'i' },
+	{"length",	required_argument,	NULL, 'l' },
+	{"test",	required_argument,	NULL, 't' },
+	{0, 0, NULL, 0 }
+};
+
+static void usage(char *argv[])
+{
+	int i;
+
+	printf(" Usage: %s --cgroup <cgroup_path>\n", argv[0]);
+	printf(" options:\n");
+	for (i = 0; long_options[i].name != 0; i++) {
+		printf(" --%-12s", long_options[i].name);
+		if (long_options[i].flag != NULL)
+			printf(" flag (internal value:%d)\n",
+				*long_options[i].flag);
+		else
+			printf(" -%c\n", long_options[i].val);
+	}
+	printf("\n");
+}
+
+static int sockmap_init_sockets(void)
 {
-	int i, sc, err, max_fd, one = 1;
-	int s1, s2, c1, c2, p1, p2;
+	int i, err, one = 1;
 	struct sockaddr_in addr;
-	struct timeval timeout;
-	char buf[1024] = {0};
 	int *fds[4] = {&s1, &s2, &c1, &c2};
-	fd_set w;
 
 	s1 = s2 = p1 = p2 = c1 = c2 = 0;
 
@@ -63,8 +95,7 @@ static int sockmap_test_sockets(int rate, int dot)
 		*fds[i] = socket(AF_INET, SOCK_STREAM, 0);
 		if (*fds[i] < 0) {
 			perror("socket s1 failed()");
-			err = *fds[i];
-			goto out;
+			return errno;
 		}
 	}
 
@@ -74,16 +105,16 @@ static int sockmap_test_sockets(int rate, int dot)
 				 (char *)&one, sizeof(one));
 		if (err) {
 			perror("setsockopt failed()");
-			goto out;
+			return errno;
 		}
 	}
 
 	/* Non-blocking sockets */
-	for (i = 0; i < 4; i++) {
+	for (i = 0; i < 2; i++) {
 		err = ioctl(*fds[i], FIONBIO, (char *)&one);
 		if (err < 0) {
 			perror("ioctl s1 failed()");
-			goto out;
+			return errno;
 		}
 	}
 
@@ -96,14 +127,14 @@ static int sockmap_test_sockets(int rate, int dot)
 	err = bind(s1, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
 		perror("bind s1 failed()\n");
-		goto out;
+		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = bind(s2, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
 		perror("bind s2 failed()\n");
-		goto out;
+		return errno;
 	}
 
 	/* Listen server sockets */
@@ -111,14 +142,14 @@ static int sockmap_test_sockets(int rate, int dot)
 	err = listen(s1, 32);
 	if (err < 0) {
 		perror("listen s1 failed()\n");
-		goto out;
+		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = listen(s2, 32);
 	if (err < 0) {
 		perror("listen s1 failed()\n");
-		goto out;
+		return errno;
 	}
 
 	/* Initiate Connect */
@@ -126,46 +157,232 @@ static int sockmap_test_sockets(int rate, int dot)
 	err = connect(c1, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0 && errno != EINPROGRESS) {
 		perror("connect c1 failed()\n");
-		goto out;
+		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = connect(c2, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0 && errno != EINPROGRESS) {
 		perror("connect c2 failed()\n");
-		goto out;
+		return errno;
+	} else if (err < 0) {
+		err = 0;
 	}
 
 	/* Accept Connecrtions */
 	p1 = accept(s1, NULL, NULL);
 	if (p1 < 0) {
 		perror("accept s1 failed()\n");
-		goto out;
+		return errno;
 	}
 
 	p2 = accept(s2, NULL, NULL);
 	if (p2 < 0) {
 		perror("accept s1 failed()\n");
-		goto out;
+		return errno;
 	}
 
-	max_fd = p2;
-	timeout.tv_sec = 10;
-	timeout.tv_usec = 0;
-
 	printf("connected sockets: c1 <-> p1, c2 <-> p2\n");
 	printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n",
 		c1, s1, c2, s2);
+	return 0;
+}
+
+struct msg_stats {
+	size_t bytes_sent;
+	size_t bytes_recvd;
+	struct timespec start;
+	struct timespec end;
+};
+
+static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+		    struct msg_stats *s, bool tx)
+{
+	struct msghdr msg = {0};
+	int err, i, flags = MSG_NOSIGNAL;
+	struct iovec *iov;
+
+	iov = calloc(iov_count, sizeof(struct iovec));
+	if (!iov)
+		return errno;
+
+	for (i = 0; i < iov_count; i++) {
+		char *d = calloc(iov_length, sizeof(char));
+
+		if (!d) {
+			fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
+			goto out_errno;
+		}
+		iov[i].iov_base = d;
+		iov[i].iov_len = iov_length;
+	}
+
+	msg.msg_iov = iov;
+	msg.msg_iovlen = iov_count;
+
+	if (tx) {
+		clock_gettime(CLOCK_MONOTONIC, &s->start);
+		for (i = 0; i < cnt; i++) {
+			int sent = sendmsg(fd, &msg, flags);
+
+			if (sent < 0) {
+				perror("send loop error:");
+				goto out_errno;
+			}
+			s->bytes_sent += sent;
+		}
+		clock_gettime(CLOCK_MONOTONIC, &s->end);
+	} else {
+		int slct, recv, max_fd = fd;
+		struct timeval timeout;
+		float total_bytes;
+		fd_set w;
+
+		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
+		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
+		if (err < 0)
+			perror("recv start time: ");
+		while (s->bytes_recvd < total_bytes) {
+			timeout.tv_sec = 1;
+			timeout.tv_usec = 0;
+
+			/* FD sets */
+			FD_ZERO(&w);
+			FD_SET(fd, &w);
+
+			slct = select(max_fd + 1, &w, NULL, NULL, &timeout);
+			if (slct == -1) {
+				perror("select()");
+				clock_gettime(CLOCK_MONOTONIC, &s->end);
+				goto out_errno;
+			} else if (!slct) {
+				fprintf(stderr, "unexpected timeout\n");
+				errno = -EIO;
+				clock_gettime(CLOCK_MONOTONIC, &s->end);
+				goto out_errno;
+			}
+
+			recv = recvmsg(fd, &msg, flags);
+			if (recv < 0) {
+				if (errno != EWOULDBLOCK) {
+					clock_gettime(CLOCK_MONOTONIC, &s->end);
+					perror("recv failed()\n");
+					goto out_errno;
+				}
+			}
+
+			s->bytes_recvd += recv;
+		}
+		clock_gettime(CLOCK_MONOTONIC, &s->end);
+	}
+
+	for (i = 0; i < iov_count; i++)
+		free(iov[i].iov_base);
+	free(iov);
+	return 0;
+out_errno:
+	for (i = 0; i < iov_count; i++)
+		free(iov[i].iov_base);
+	free(iov);
+	return errno;
+}
+
+static float giga = 1000000000;
+
+static inline float sentBps(struct msg_stats s)
+{
+	return s.bytes_sent / (s.end.tv_sec - s.start.tv_sec);
+}
+
+static inline float recvdBps(struct msg_stats s)
+{
+	return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec);
+}
+
+static int sendmsg_test(int iov_count, int iov_buf, int cnt,
+			int verbose, bool base)
+{
+	float sent_Bps = 0, recvd_Bps = 0;
+	int rx_fd, txpid, rxpid, err = 0;
+	struct msg_stats s = {0};
+	int status;
+
+	errno = 0;
+
+	if (base)
+		rx_fd = p1;
+	else
+		rx_fd = p2;
+
+	rxpid = fork();
+	if (rxpid == 0) {
+		err = msg_loop(rx_fd, iov_count, iov_buf, cnt, &s, false);
+		if (err)
+			fprintf(stderr,
+				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
+				iov_count, iov_buf, cnt, err);
+		shutdown(p2, SHUT_RDWR);
+		shutdown(p1, SHUT_RDWR);
+		if (s.end.tv_sec - s.start.tv_sec) {
+			sent_Bps = sentBps(s);
+			recvd_Bps = recvdBps(s);
+		}
+		fprintf(stdout,
+			"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+			s.bytes_sent, sent_Bps, sent_Bps/giga,
+			s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+		exit(1);
+	} else if (rxpid == -1) {
+		perror("msg_loop_rx: ");
+		return errno;
+	}
+
+	txpid = fork();
+	if (txpid == 0) {
+		err = msg_loop(c1, iov_count, iov_buf, cnt, &s, true);
+		if (err)
+			fprintf(stderr,
+				"msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
+				iov_count, iov_buf, cnt, err);
+		shutdown(c1, SHUT_RDWR);
+		if (s.end.tv_sec - s.start.tv_sec) {
+			sent_Bps = sentBps(s);
+			recvd_Bps = recvdBps(s);
+		}
+		fprintf(stdout,
+			"tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n",
+			s.bytes_sent, sent_Bps, sent_Bps/giga,
+			s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+		exit(1);
+	} else if (txpid == -1) {
+		perror("msg_loop_tx: ");
+		return errno;
+	}
+
+	assert(waitpid(rxpid, &status, 0) == rxpid);
+	assert(waitpid(txpid, &status, 0) == txpid);
+	return err;
+}
+
+static int forever_ping_pong(int rate, int verbose)
+{
+	struct timeval timeout;
+	char buf[1024] = {0};
+	int sc;
+
+	timeout.tv_sec = 10;
+	timeout.tv_usec = 0;
 
 	/* Ping/Pong data from client to server */
 	sc = send(c1, buf, sizeof(buf), 0);
 	if (sc < 0) {
 		perror("send failed()\n");
-		goto out;
+		return sc;
 	}
 
 	do {
-		int s, rc, i;
+		int s, rc, i, max_fd = p2;
+		fd_set w;
 
 		/* FD sets */
 		FD_ZERO(&w);
@@ -193,7 +410,7 @@ static int sockmap_test_sockets(int rate, int dot)
 			if (rc < 0) {
 				if (errno != EWOULDBLOCK) {
 					perror("recv failed()\n");
-					break;
+					return rc;
 				}
 			}
 
@@ -205,35 +422,92 @@ static int sockmap_test_sockets(int rate, int dot)
 			sc = send(i, buf, rc, 0);
 			if (sc < 0) {
 				perror("send failed()\n");
-				break;
+				return sc;
 			}
 		}
-		sleep(rate);
-		if (dot) {
+
+		if (rate)
+			sleep(rate);
+
+		if (verbose) {
 			printf(".");
 			fflush(stdout);
 
 		}
 	} while (running);
 
-out:
-	close(s1);
-	close(s2);
-	close(p1);
-	close(p2);
-	close(c1);
-	close(c2);
-	return err;
+	return 0;
 }
 
+enum {
+	PING_PONG,
+	SENDMSG,
+	BASE,
+};
+
 int main(int argc, char **argv)
 {
-	int rate = 1, dot = 1;
+	int iov_count = 1, length = 1024, rate = 1, verbose = 0;
+	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+	int opt, longindex, err, cg_fd = 0;
+	int test = PING_PONG;
 	char filename[256];
-	int err, cg_fd;
-	char *cg_path;
 
-	cg_path = argv[argc - 1];
+	while ((opt = getopt_long(argc, argv, "hvc:r:i:l:t:",
+				  long_options, &longindex)) != -1) {
+		switch (opt) {
+		/* Cgroup configuration */
+		case 'c':
+			cg_fd = open(optarg, O_DIRECTORY, O_RDONLY);
+			if (cg_fd < 0) {
+				fprintf(stderr,
+					"ERROR: (%i) open cg path failed: %s\n",
+					cg_fd, optarg);
+				return cg_fd;
+			}
+			break;
+		case 'r':
+			rate = atoi(optarg);
+			break;
+		case 'v':
+			verbose = 1;
+			break;
+		case 'i':
+			iov_count = atoi(optarg);
+			break;
+		case 'l':
+			length = atoi(optarg);
+			break;
+		case 't':
+			if (strcmp(optarg, "ping") == 0) {
+				test = PING_PONG;
+			} else if (strcmp(optarg, "sendmsg") == 0) {
+				test = SENDMSG;
+			} else if (strcmp(optarg, "base") == 0) {
+				test = BASE;
+			} else {
+				usage(argv);
+				return -1;
+			}
+			break;
+		case 'h':
+		default:
+			usage(argv);
+			return -1;
+		}
+	}
+
+	if (!cg_fd) {
+		fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
+			argv[0]);
+		return -1;
+	}
+
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
+
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 
 	running = 1;
@@ -241,20 +515,16 @@ int main(int argc, char **argv)
 	/* catch SIGINT */
 	signal(SIGINT, running_handler);
 
+	/* If base test skip BPF setup */
+	if (test == BASE)
+		goto run;
+
 	if (load_bpf_file(filename)) {
 		fprintf(stderr, "load_bpf_file: (%s) %s\n",
 			filename, strerror(errno));
 		return 1;
 	}
 
-	/* Cgroup configuration */
-	cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY);
-	if (cg_fd < 0) {
-		fprintf(stderr, "ERROR: (%i) open cg path failed: %s\n",
-			cg_fd, cg_path);
-		return cg_fd;
-	}
-
 	/* Attach programs to sockmap */
 	err = bpf_prog_attach(prog_fd[0], map_fd[0],
 				BPF_SK_SKB_STREAM_PARSER, 0);
@@ -280,12 +550,30 @@ int main(int argc, char **argv)
 		return err;
 	}
 
-	err = sockmap_test_sockets(rate, dot);
+run:
+	err = sockmap_init_sockets();
 	if (err) {
 		fprintf(stderr, "ERROR: test socket failed: %d\n", err);
-		return err;
+		goto out;
 	}
-	return 0;
+
+	if (test == PING_PONG)
+		err = forever_ping_pong(rate, verbose);
+	else if (test == SENDMSG)
+		err = sendmsg_test(iov_count, length, rate, verbose, false);
+	else if (test == BASE)
+		err = sendmsg_test(iov_count, length, rate, verbose, true);
+	else
+		fprintf(stderr, "unknown test\n");
+out:
+	close(s1);
+	close(s2);
+	close(p1);
+	close(p2);
+	close(c1);
+	close(c2);
+	close(cg_fd);
+	return err;
 }
 
 void running_handler(int a)