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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 292 insertions, 17 deletions

diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index 4074538b5df5..ada99496634a 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -5,6 +5,8 @@
 #include <arpa/inet.h>
 #include <errno.h>
 #include <error.h>
+#include <linux/errqueue.h>
+#include <linux/net_tstamp.h>
 #include <netinet/if_ether.h>
 #include <netinet/in.h>
 #include <netinet/ip.h>
@@ -19,9 +21,12 @@
 #include <string.h>
 #include <sys/socket.h>
 #include <sys/time.h>
+#include <sys/poll.h>
 #include <sys/types.h>
 #include <unistd.h>
 
+#include "../kselftest.h"
+
 #ifndef ETH_MAX_MTU
 #define ETH_MAX_MTU 0xFFFFU
 #endif
@@ -34,10 +39,18 @@
 #define SO_ZEROCOPY	60
 #endif
 
+#ifndef SO_EE_ORIGIN_ZEROCOPY
+#define SO_EE_ORIGIN_ZEROCOPY 5
+#endif
+
 #ifndef MSG_ZEROCOPY
 #define MSG_ZEROCOPY	0x4000000
 #endif
 
+#ifndef ENOTSUPP
+#define ENOTSUPP	524
+#endif
+
 #define NUM_PKT		100
 
 static bool	cfg_cache_trash;
@@ -48,12 +61,24 @@ static uint16_t	cfg_mss;
 static int	cfg_payload_len	= (1472 * 42);
 static int	cfg_port	= 8000;
 static int	cfg_runtime_ms	= -1;
+static bool	cfg_poll;
 static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
+static uint32_t	cfg_tx_ts = SOF_TIMESTAMPING_TX_SOFTWARE;
+static bool	cfg_tx_tstamp;
+static bool	cfg_audit;
+static bool	cfg_verbose;
 static bool	cfg_zerocopy;
 static int	cfg_msg_nr;
 static uint16_t	cfg_gso_size;
+static unsigned long total_num_msgs;
+static unsigned long total_num_sends;
+static unsigned long stat_tx_ts;
+static unsigned long stat_tx_ts_errors;
+static unsigned long tstart;
+static unsigned long tend;
+static unsigned long stat_zcopies;
 
 static socklen_t cfg_alen;
 static struct sockaddr_storage cfg_dst_addr;
@@ -110,23 +135,125 @@ static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
 	}
 }
 
-static void flush_zerocopy(int fd)
+static void flush_cmsg(struct cmsghdr *cmsg)
+{
+	struct sock_extended_err *err;
+	struct scm_timestamping *tss;
+	__u32 lo;
+	__u32 hi;
+	int i;
+
+	switch (cmsg->cmsg_level) {
+	case SOL_SOCKET:
+		if (cmsg->cmsg_type == SO_TIMESTAMPING) {
+			i = (cfg_tx_ts == SOF_TIMESTAMPING_TX_HARDWARE) ? 2 : 0;
+			tss = (struct scm_timestamping *)CMSG_DATA(cmsg);
+			if (tss->ts[i].tv_sec == 0)
+				stat_tx_ts_errors++;
+		} else {
+			error(1, 0, "unknown SOL_SOCKET cmsg type=%u\n",
+			      cmsg->cmsg_type);
+		}
+		break;
+	case SOL_IP:
+	case SOL_IPV6:
+		switch (cmsg->cmsg_type) {
+		case IP_RECVERR:
+		case IPV6_RECVERR:
+		{
+			err = (struct sock_extended_err *)CMSG_DATA(cmsg);
+			switch (err->ee_origin) {
+			case SO_EE_ORIGIN_TIMESTAMPING:
+				/* Got a TX timestamp from error queue */
+				stat_tx_ts++;
+				break;
+			case SO_EE_ORIGIN_ICMP:
+			case SO_EE_ORIGIN_ICMP6:
+				if (cfg_verbose)
+					fprintf(stderr,
+						"received ICMP error: type=%u, code=%u\n",
+						err->ee_type, err->ee_code);
+				break;
+			case SO_EE_ORIGIN_ZEROCOPY:
+			{
+				lo = err->ee_info;
+				hi = err->ee_data;
+				/* range of IDs acknowledged */
+				stat_zcopies += hi - lo + 1;
+				break;
+			}
+			case SO_EE_ORIGIN_LOCAL:
+				if (cfg_verbose)
+					fprintf(stderr,
+						"received packet with local origin: %u\n",
+						err->ee_origin);
+				break;
+			default:
+				error(0, 1, "received packet with origin: %u",
+				      err->ee_origin);
+			}
+			break;
+		}
+		default:
+			error(0, 1, "unknown IP msg type=%u\n",
+			      cmsg->cmsg_type);
+			break;
+		}
+		break;
+	default:
+		error(0, 1, "unknown cmsg level=%u\n",
+		      cmsg->cmsg_level);
+	}
+}
+
+static void flush_errqueue_recv(int fd)
 {
-	struct msghdr msg = {0};	/* flush */
+	char control[CMSG_SPACE(sizeof(struct scm_timestamping)) +
+		     CMSG_SPACE(sizeof(struct sock_extended_err)) +
+		     CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0};
+	struct msghdr msg = {0};
+	struct cmsghdr *cmsg;
 	int ret;
 
 	while (1) {
+		msg.msg_control = control;
+		msg.msg_controllen = sizeof(control);
 		ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
 		if (ret == -1 && errno == EAGAIN)
 			break;
 		if (ret == -1)
 			error(1, errno, "errqueue");
-		if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC))
+		if (msg.msg_flags != MSG_ERRQUEUE)
 			error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags);
+		if (cfg_audit) {
+			for (cmsg = CMSG_FIRSTHDR(&msg);
+					cmsg;
+					cmsg = CMSG_NXTHDR(&msg, cmsg))
+				flush_cmsg(cmsg);
+		}
 		msg.msg_flags = 0;
 	}
 }
 
+static void flush_errqueue(int fd, const bool do_poll)
+{
+	if (do_poll) {
+		struct pollfd fds = {0};
+		int ret;
+
+		fds.fd = fd;
+		ret = poll(&fds, 1, 500);
+		if (ret == 0) {
+			if (cfg_verbose)
+				fprintf(stderr, "poll timeout\n");
+		} else if (ret < 0) {
+			error(1, errno, "poll");
+		}
+	}
+
+	flush_errqueue_recv(fd);
+}
+
 static int send_tcp(int fd, char *data)
 {
 	int ret, done = 0, count = 0;
@@ -168,16 +295,40 @@ static int send_udp(int fd, char *data)
 	return count;
 }
 
+static void send_ts_cmsg(struct cmsghdr *cm)
+{
+	uint32_t *valp;
+
+	cm->cmsg_level = SOL_SOCKET;
+	cm->cmsg_type = SO_TIMESTAMPING;
+	cm->cmsg_len = CMSG_LEN(sizeof(cfg_tx_ts));
+	valp = (void *)CMSG_DATA(cm);
+	*valp = cfg_tx_ts;
+}
+
 static int send_udp_sendmmsg(int fd, char *data)
 {
+	char control[CMSG_SPACE(sizeof(cfg_tx_ts))] = {0};
 	const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN;
 	struct mmsghdr mmsgs[max_nr_msg];
 	struct iovec iov[max_nr_msg];
 	unsigned int off = 0, left;
+	size_t msg_controllen = 0;
 	int i = 0, ret;
 
 	memset(mmsgs, 0, sizeof(mmsgs));
 
+	if (cfg_tx_tstamp) {
+		struct msghdr msg = {0};
+		struct cmsghdr *cmsg;
+
+		msg.msg_control = control;
+		msg.msg_controllen = sizeof(control);
+		cmsg = CMSG_FIRSTHDR(&msg);
+		send_ts_cmsg(cmsg);
+		msg_controllen += CMSG_SPACE(sizeof(cfg_tx_ts));
+	}
+
 	left = cfg_payload_len;
 	while (left) {
 		if (i == max_nr_msg)
@@ -189,6 +340,13 @@ static int send_udp_sendmmsg(int fd, char *data)
 		mmsgs[i].msg_hdr.msg_iov = iov + i;
 		mmsgs[i].msg_hdr.msg_iovlen = 1;
 
+		mmsgs[i].msg_hdr.msg_name = (void *)&cfg_dst_addr;
+		mmsgs[i].msg_hdr.msg_namelen = cfg_alen;
+		if (msg_controllen) {
+			mmsgs[i].msg_hdr.msg_control = control;
+			mmsgs[i].msg_hdr.msg_controllen = msg_controllen;
+		}
+
 		off += iov[i].iov_len;
 		left -= iov[i].iov_len;
 		i++;
@@ -214,9 +372,12 @@ static void send_udp_segment_cmsg(struct cmsghdr *cm)
 
 static int send_udp_segment(int fd, char *data)
 {
-	char control[CMSG_SPACE(sizeof(cfg_gso_size))] = {0};
+	char control[CMSG_SPACE(sizeof(cfg_gso_size)) +
+		     CMSG_SPACE(sizeof(cfg_tx_ts))] = {0};
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
+	size_t msg_controllen;
+	struct cmsghdr *cmsg;
 	int ret;
 
 	iov.iov_base = data;
@@ -227,8 +388,16 @@ static int send_udp_segment(int fd, char *data)
 
 	msg.msg_control = control;
 	msg.msg_controllen = sizeof(control);
-	send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg));
+	cmsg = CMSG_FIRSTHDR(&msg);
+	send_udp_segment_cmsg(cmsg);
+	msg_controllen = CMSG_SPACE(sizeof(cfg_mss));
+	if (cfg_tx_tstamp) {
+		cmsg = CMSG_NXTHDR(&msg, cmsg);
+		send_ts_cmsg(cmsg);
+		msg_controllen += CMSG_SPACE(sizeof(cfg_tx_ts));
+	}
 
+	msg.msg_controllen = msg_controllen;
 	msg.msg_name = (void *)&cfg_dst_addr;
 	msg.msg_namelen = cfg_alen;
 
@@ -243,7 +412,7 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46cmtuz] [-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] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -252,7 +421,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46cC:D:l:mM:p:s:S:tuz")) != -1) {
+	while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -266,6 +435,9 @@ static void parse_opts(int argc, char **argv)
 			cfg_family = PF_INET6;
 			cfg_alen = sizeof(struct sockaddr_in6);
 			break;
+		case 'a':
+			cfg_audit = true;
+			break;
 		case 'c':
 			cfg_cache_trash = true;
 			break;
@@ -287,6 +459,9 @@ static void parse_opts(int argc, char **argv)
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
+		case 'P':
+			cfg_poll = true;
+			break;
 		case 's':
 			cfg_payload_len = strtoul(optarg, NULL, 0);
 			break;
@@ -294,12 +469,22 @@ static void parse_opts(int argc, char **argv)
 			cfg_gso_size = strtoul(optarg, NULL, 0);
 			cfg_segment = true;
 			break;
+		case 'H':
+			cfg_tx_ts = SOF_TIMESTAMPING_TX_HARDWARE;
+			cfg_tx_tstamp = true;
+			break;
 		case 't':
 			cfg_tcp = true;
 			break;
+		case 'T':
+			cfg_tx_tstamp = true;
+			break;
 		case 'u':
 			cfg_connected = false;
 			break;
+		case 'v':
+			cfg_verbose = true;
+			break;
 		case 'z':
 			cfg_zerocopy = true;
 			break;
@@ -315,6 +500,8 @@ static void parse_opts(int argc, char **argv)
 		error(1, 0, "connectionless tcp makes no sense");
 	if (cfg_segment && cfg_sendmmsg)
 		error(1, 0, "cannot combine segment offload and sendmmsg");
+	if (cfg_tx_tstamp && !(cfg_segment || cfg_sendmmsg))
+		error(1, 0, "Options -T and -H require either -S or -m option");
 
 	if (cfg_family == PF_INET)
 		hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr);
@@ -349,11 +536,80 @@ static void set_pmtu_discover(int fd, bool is_ipv4)
 		error(1, errno, "setsockopt path mtu");
 }
 
+static void set_tx_timestamping(int fd)
+{
+	int val = SOF_TIMESTAMPING_OPT_CMSG | SOF_TIMESTAMPING_OPT_ID |
+			SOF_TIMESTAMPING_OPT_TSONLY;
+
+	if (cfg_tx_ts == SOF_TIMESTAMPING_TX_SOFTWARE)
+		val |= SOF_TIMESTAMPING_SOFTWARE;
+	else
+		val |= SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)))
+		error(1, errno, "setsockopt tx timestamping");
+}
+
+static void print_audit_report(unsigned long num_msgs, unsigned long num_sends)
+{
+	unsigned long tdelta;
+
+	tdelta = tend - tstart;
+	if (!tdelta)
+		return;
+
+	fprintf(stderr, "Summary over %lu.%03lu seconds...\n",
+			tdelta / 1000, tdelta % 1000);
+	fprintf(stderr,
+		"sum %s tx: %6lu MB/s %10lu calls (%lu/s) %10lu msgs (%lu/s)\n",
+		cfg_tcp ? "tcp" : "udp",
+		((num_msgs * cfg_payload_len) >> 10) / tdelta,
+		num_sends, num_sends * 1000 / tdelta,
+		num_msgs, num_msgs * 1000 / tdelta);
+
+	if (cfg_tx_tstamp) {
+		if (stat_tx_ts_errors)
+			error(1, 0,
+			      "Expected clean TX Timestamps: %9lu msgs received %6lu errors",
+			      stat_tx_ts, stat_tx_ts_errors);
+		if (stat_tx_ts != num_sends)
+			error(1, 0,
+			      "Unexpected number of TX Timestamps: %9lu expected %9lu received",
+			      num_sends, stat_tx_ts);
+		fprintf(stderr,
+			"Tx Timestamps: %19lu received %17lu errors\n",
+			stat_tx_ts, stat_tx_ts_errors);
+	}
+
+	if (cfg_zerocopy) {
+		if (stat_zcopies != num_sends)
+			error(1, 0, "Unexpected number of Zerocopy completions: %9lu expected %9lu received",
+			      num_sends, stat_zcopies);
+		fprintf(stderr,
+			"Zerocopy acks: %19lu\n",
+			stat_zcopies);
+	}
+}
+
+static void print_report(unsigned long num_msgs, unsigned long num_sends)
+{
+	fprintf(stderr,
+		"%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n",
+		cfg_tcp ? "tcp" : "udp",
+		(num_msgs * cfg_payload_len) >> 20,
+		num_sends, num_msgs);
+
+	if (cfg_audit) {
+		total_num_msgs += num_msgs;
+		total_num_sends += num_sends;
+	}
+}
+
 int main(int argc, char **argv)
 {
 	unsigned long num_msgs, num_sends;
 	unsigned long tnow, treport, tstop;
-	int fd, i, val;
+	int fd, i, val, ret;
 
 	parse_opts(argc, argv);
 
@@ -373,8 +629,16 @@ int main(int argc, char **argv)
 
 	if (cfg_zerocopy) {
 		val = 1;
-		if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val)))
+
+		ret = setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY,
+				 &val, sizeof(val));
+		if (ret) {
+			if (errno == ENOPROTOOPT || errno == ENOTSUPP) {
+				fprintf(stderr, "SO_ZEROCOPY not supported");
+				exit(KSFT_SKIP);
+			}
 			error(1, errno, "setsockopt zerocopy");
+		}
 	}
 
 	if (cfg_connected &&
@@ -384,8 +648,13 @@ int main(int argc, char **argv)
 	if (cfg_segment)
 		set_pmtu_discover(fd, cfg_family == PF_INET);
 
+	if (cfg_tx_tstamp)
+		set_tx_timestamping(fd);
+
 	num_msgs = num_sends = 0;
 	tnow = gettimeofday_ms();
+	tstart = tnow;
+	tend = tnow;
 	tstop = tnow + cfg_runtime_ms;
 	treport = tnow + 1000;
 
@@ -400,19 +669,15 @@ int main(int argc, char **argv)
 		else
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
-		if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
-			flush_zerocopy(fd);
+		if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp)
+			flush_errqueue(fd, cfg_poll);
 
 		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
 			break;
 
 		tnow = gettimeofday_ms();
-		if (tnow > treport) {
-			fprintf(stderr,
-				"%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n",
-				cfg_tcp ? "tcp" : "udp",
-				(num_msgs * cfg_payload_len) >> 20,
-				num_sends, num_msgs);
+		if (tnow >= treport) {
+			print_report(num_msgs, num_sends);
 			num_msgs = num_sends = 0;
 			treport = tnow + 1000;
 		}
@@ -423,8 +688,18 @@ int main(int argc, char **argv)
 
 	} while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
 
+	if (cfg_zerocopy || cfg_tx_tstamp)
+		flush_errqueue(fd, true);
+
 	if (close(fd))
 		error(1, errno, "close");
 
+	if (cfg_audit) {
+		tend = tnow;
+		total_num_msgs += num_msgs;
+		total_num_sends += num_sends;
+		print_audit_report(total_num_msgs, total_num_sends);
+	}
+
 	return 0;
 }