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

Pull networking updates from David Miller:

 1) Support offloading wireless authentication to userspace via
    NL80211_CMD_EXTERNAL_AUTH, from Srinivas Dasari.

 2) A lot of work on network namespace setup/teardown from Kirill Tkhai.
    Setup and cleanup of namespaces now all run asynchronously and thus
    performance is significantly increased.

 3) Add rx/tx timestamping support to mv88e6xxx driver, from Brandon
    Streiff.

 4) Support zerocopy on RDS sockets, from Sowmini Varadhan.

 5) Use denser instruction encoding in x86 eBPF JIT, from Daniel
    Borkmann.

 6) Support hw offload of vlan filtering in mvpp2 dreiver, from Maxime
    Chevallier.

 7) Support grafting of child qdiscs in mlxsw driver, from Nogah
    Frankel.

 8) Add packet forwarding tests to selftests, from Ido Schimmel.

 9) Deal with sub-optimal GSO packets better in BBR congestion control,
    from Eric Dumazet.

10) Support 5-tuple hashing in ipv6 multipath routing, from David Ahern.

11) Add path MTU tests to selftests, from Stefano Brivio.

12) Various bits of IPSEC offloading support for mlx5, from Aviad
    Yehezkel, Yossi Kuperman, and Saeed Mahameed.

13) Support RSS spreading on ntuple filters in SFC driver, from Edward
    Cree.

14) Lots of sockmap work from John Fastabend. Applications can use eBPF
    to filter sendmsg and sendpage operations.

15) In-kernel receive TLS support, from Dave Watson.

16) Add XDP support to ixgbevf, this is significant because it should
    allow optimized XDP usage in various cloud environments. From Tony
    Nguyen.

17) Add new Intel E800 series "ice" ethernet driver, from Anirudh
    Venkataramanan et al.

18) IP fragmentation match offload support in nfp driver, from Pieter
    Jansen van Vuuren.

19) Support XDP redirect in i40e driver, from Björn Töpel.

20) Add BPF_RAW_TRACEPOINT program type for accessing the arguments of
    tracepoints in their raw form, from Alexei Starovoitov.

21) Lots of striding RQ improvements to mlx5 driver with many
    performance improvements, from Tariq Toukan.

22) Use rhashtable for inet frag reassembly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1678 commits)
  net: mvneta: improve suspend/resume
  net: mvneta: split rxq/txq init and txq deinit into SW and HW parts
  ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh
  net: bgmac: Fix endian access in bgmac_dma_tx_ring_free()
  net: bgmac: Correctly annotate register space
  route: check sysctl_fib_multipath_use_neigh earlier than hash
  fix typo in command value in drivers/net/phy/mdio-bitbang.
  sky2: Increase D3 delay to sky2 stops working after suspend
  net/mlx5e: Set EQE based as default TX interrupt moderation mode
  ibmvnic: Disable irqs before exiting reset from closed state
  net: sched: do not emit messages while holding spinlock
  vlan: also check phy_driver ts_info for vlan's real device
  Bluetooth: Mark expected switch fall-throughs
  Bluetooth: Set HCI_QUIRK_SIMULTANEOUS_DISCOVERY for BTUSB_QCA_ROME
  Bluetooth: btrsi: remove unused including <linux/version.h>
  Bluetooth: hci_bcm: Remove DMI quirk for the MINIX Z83-4
  sh_eth: kill useless check in __sh_eth_get_regs()
  sh_eth: add sh_eth_cpu_data::no_xdfar flag
  ipv6: factorize sk_wmem_alloc updates done by __ip6_append_data()
  ipv4: factorize sk_wmem_alloc updates done by __ip_append_data()
  ...

1 files changed, 336 insertions, 24 deletions

diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c
index 7c25c0c112bc..6f2334912283 100644
--- a/samples/sockmap/sockmap_user.c
+++ b/samples/sockmap/sockmap_user.c
@@ -29,6 +29,7 @@
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
+#include <sys/sendfile.h>
 
 #include <linux/netlink.h>
 #include <linux/socket.h>
@@ -54,6 +55,18 @@ void running_handler(int a);
 /* global sockets */
 int s1, s2, c1, c2, p1, p2;
 
+int txmsg_pass;
+int txmsg_noisy;
+int txmsg_redir;
+int txmsg_redir_noisy;
+int txmsg_drop;
+int txmsg_apply;
+int txmsg_cork;
+int txmsg_start;
+int txmsg_end;
+int txmsg_ingress;
+int txmsg_skb;
+
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
 	{"cgroup",	required_argument,	NULL, 'c' },
@@ -62,6 +75,18 @@ static const struct option long_options[] = {
 	{"iov_count",	required_argument,	NULL, 'i' },
 	{"length",	required_argument,	NULL, 'l' },
 	{"test",	required_argument,	NULL, 't' },
+	{"data_test",   no_argument,		NULL, 'd' },
+	{"txmsg",		no_argument,	&txmsg_pass,  1  },
+	{"txmsg_noisy",		no_argument,	&txmsg_noisy, 1  },
+	{"txmsg_redir",		no_argument,	&txmsg_redir, 1  },
+	{"txmsg_redir_noisy",	no_argument,	&txmsg_redir_noisy, 1},
+	{"txmsg_drop",		no_argument,	&txmsg_drop, 1 },
+	{"txmsg_apply",	required_argument,	NULL, 'a'},
+	{"txmsg_cork",	required_argument,	NULL, 'k'},
+	{"txmsg_start", required_argument,	NULL, 's'},
+	{"txmsg_end",	required_argument,	NULL, 'e'},
+	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
+	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -195,19 +220,71 @@ struct msg_stats {
 	struct timespec end;
 };
 
+struct sockmap_options {
+	int verbose;
+	bool base;
+	bool sendpage;
+	bool data_test;
+	bool drop_expected;
+};
+
+static int msg_loop_sendpage(int fd, int iov_length, int cnt,
+			     struct msg_stats *s,
+			     struct sockmap_options *opt)
+{
+	bool drop = opt->drop_expected;
+	unsigned char k = 0;
+	FILE *file;
+	int i, fp;
+
+	file = fopen(".sendpage_tst.tmp", "w+");
+	for (i = 0; i < iov_length * cnt; i++, k++)
+		fwrite(&k, sizeof(char), 1, file);
+	fflush(file);
+	fseek(file, 0, SEEK_SET);
+	fclose(file);
+
+	fp = open(".sendpage_tst.tmp", O_RDONLY);
+	clock_gettime(CLOCK_MONOTONIC, &s->start);
+	for (i = 0; i < cnt; i++) {
+		int sent = sendfile(fd, fp, NULL, iov_length);
+
+		if (!drop && sent < 0) {
+			perror("send loop error:");
+			close(fp);
+			return sent;
+		} else if (drop && sent >= 0) {
+			printf("sendpage loop error expected: %i\n", sent);
+			close(fp);
+			return -EIO;
+		}
+
+		if (sent > 0)
+			s->bytes_sent += sent;
+	}
+	clock_gettime(CLOCK_MONOTONIC, &s->end);
+	close(fp);
+	return 0;
+}
+
 static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
-		    struct msg_stats *s, bool tx)
+		    struct msg_stats *s, bool tx,
+		    struct sockmap_options *opt)
 {
 	struct msghdr msg = {0};
 	int err, i, flags = MSG_NOSIGNAL;
 	struct iovec *iov;
+	unsigned char k;
+	bool data_test = opt->data_test;
+	bool drop = opt->drop_expected;
 
 	iov = calloc(iov_count, sizeof(struct iovec));
 	if (!iov)
 		return errno;
 
+	k = 0;
 	for (i = 0; i < iov_count; i++) {
-		char *d = calloc(iov_length, sizeof(char));
+		unsigned char *d = calloc(iov_length, sizeof(char));
 
 		if (!d) {
 			fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
@@ -215,21 +292,34 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		iov[i].iov_base = d;
 		iov[i].iov_len = iov_length;
+
+		if (data_test && tx) {
+			int j;
+
+			for (j = 0; j < iov_length; j++)
+				d[j] = k++;
+		}
 	}
 
 	msg.msg_iov = iov;
 	msg.msg_iovlen = iov_count;
+	k = 0;
 
 	if (tx) {
 		clock_gettime(CLOCK_MONOTONIC, &s->start);
 		for (i = 0; i < cnt; i++) {
 			int sent = sendmsg(fd, &msg, flags);
 
-			if (sent < 0) {
+			if (!drop && sent < 0) {
 				perror("send loop error:");
 				goto out_errno;
+			} else if (drop && sent >= 0) {
+				printf("send loop error expected: %i\n", sent);
+				errno = -EIO;
+				goto out_errno;
 			}
-			s->bytes_sent += sent;
+			if (sent > 0)
+				s->bytes_sent += sent;
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
@@ -272,6 +362,26 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 			}
 
 			s->bytes_recvd += recv;
+
+			if (data_test) {
+				int j;
+
+				for (i = 0; i < msg.msg_iovlen; i++) {
+					unsigned char *d = iov[i].iov_base;
+
+					for (j = 0;
+					     j < iov[i].iov_len && recv; j++) {
+						if (d[j] != k++) {
+							errno = -EIO;
+							fprintf(stderr,
+								"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
+								i, j, d[j], k - 1, d[j+1], k + 1);
+							goto out_errno;
+						}
+						recv--;
+					}
+				}
+			}
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	}
@@ -300,7 +410,7 @@ static inline float recvdBps(struct msg_stats s)
 }
 
 static int sendmsg_test(int iov_count, int iov_buf, int cnt,
-			int verbose, bool base)
+			struct sockmap_options *opt)
 {
 	float sent_Bps = 0, recvd_Bps = 0;
 	int rx_fd, txpid, rxpid, err = 0;
@@ -309,14 +419,20 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt,
 
 	errno = 0;
 
-	if (base)
+	if (opt->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 (opt->drop_expected)
+			exit(1);
+
+		if (opt->sendpage)
+			iov_count = 1;
+		err = msg_loop(rx_fd, iov_count, iov_buf,
+			       cnt, &s, false, opt);
 		if (err)
 			fprintf(stderr,
 				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
@@ -339,7 +455,12 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt,
 
 	txpid = fork();
 	if (txpid == 0) {
-		err = msg_loop(c1, iov_count, iov_buf, cnt, &s, true);
+		if (opt->sendpage)
+			err = msg_loop_sendpage(c1, iov_buf, cnt, &s, opt);
+		else
+			err = msg_loop(c1, iov_count, iov_buf,
+				       cnt, &s, true, opt);
+
 		if (err)
 			fprintf(stderr,
 				"msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
@@ -364,7 +485,7 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt,
 	return err;
 }
 
-static int forever_ping_pong(int rate, int verbose)
+static int forever_ping_pong(int rate, struct sockmap_options *opt)
 {
 	struct timeval timeout;
 	char buf[1024] = {0};
@@ -429,7 +550,7 @@ static int forever_ping_pong(int rate, int verbose)
 		if (rate)
 			sleep(rate);
 
-		if (verbose) {
+		if (opt->verbose) {
 			printf(".");
 			fflush(stdout);
 
@@ -443,20 +564,34 @@ enum {
 	PING_PONG,
 	SENDMSG,
 	BASE,
+	BASE_SENDPAGE,
+	SENDPAGE,
 };
 
 int main(int argc, char **argv)
 {
-	int iov_count = 1, length = 1024, rate = 1, verbose = 0;
+	int iov_count = 1, length = 1024, rate = 1, tx_prog_fd;
 	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
 	int opt, longindex, err, cg_fd = 0;
+	struct sockmap_options options = {0};
 	int test = PING_PONG;
 	char filename[256];
 
-	while ((opt = getopt_long(argc, argv, "hvc:r:i:l:t:",
+	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
-		/* Cgroup configuration */
+		case 's':
+			txmsg_start = atoi(optarg);
+			break;
+		case 'e':
+			txmsg_end = atoi(optarg);
+			break;
+		case 'a':
+			txmsg_apply = atoi(optarg);
+			break;
+		case 'k':
+			txmsg_cork = atoi(optarg);
+			break;
 		case 'c':
 			cg_fd = open(optarg, O_DIRECTORY, O_RDONLY);
 			if (cg_fd < 0) {
@@ -470,7 +605,7 @@ int main(int argc, char **argv)
 			rate = atoi(optarg);
 			break;
 		case 'v':
-			verbose = 1;
+			options.verbose = 1;
 			break;
 		case 'i':
 			iov_count = atoi(optarg);
@@ -478,6 +613,9 @@ int main(int argc, char **argv)
 		case 'l':
 			length = atoi(optarg);
 			break;
+		case 'd':
+			options.data_test = true;
+			break;
 		case 't':
 			if (strcmp(optarg, "ping") == 0) {
 				test = PING_PONG;
@@ -485,11 +623,17 @@ int main(int argc, char **argv)
 				test = SENDMSG;
 			} else if (strcmp(optarg, "base") == 0) {
 				test = BASE;
+			} else if (strcmp(optarg, "base_sendpage") == 0) {
+				test = BASE_SENDPAGE;
+			} else if (strcmp(optarg, "sendpage") == 0) {
+				test = SENDPAGE;
 			} else {
 				usage(argv);
 				return -1;
 			}
 			break;
+		case 0:
+			break;
 		case 'h':
 		default:
 			usage(argv);
@@ -515,16 +659,16 @@ 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;
 	}
 
+	/* If base test skip BPF setup */
+	if (test == BASE || test == BASE_SENDPAGE)
+		goto run;
+
 	/* Attach programs to sockmap */
 	err = bpf_prog_attach(prog_fd[0], map_fd[0],
 				BPF_SK_SKB_STREAM_PARSER, 0);
@@ -557,15 +701,183 @@ run:
 		goto out;
 	}
 
-	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);
+	/* Attach txmsg program to sockmap */
+	if (txmsg_pass)
+		tx_prog_fd = prog_fd[3];
+	else if (txmsg_noisy)
+		tx_prog_fd = prog_fd[4];
+	else if (txmsg_redir)
+		tx_prog_fd = prog_fd[5];
+	else if (txmsg_redir_noisy)
+		tx_prog_fd = prog_fd[6];
+	else if (txmsg_drop)
+		tx_prog_fd = prog_fd[9];
+	/* apply and cork must be last */
+	else if (txmsg_apply)
+		tx_prog_fd = prog_fd[7];
+	else if (txmsg_cork)
+		tx_prog_fd = prog_fd[8];
 	else
+		tx_prog_fd = 0;
+
+	if (tx_prog_fd) {
+		int redir_fd, i = 0;
+
+		err = bpf_prog_attach(tx_prog_fd,
+				      map_fd[1], BPF_SK_MSG_VERDICT, 0);
+		if (err) {
+			fprintf(stderr,
+				"ERROR: bpf_prog_attach (txmsg): %d (%s)\n",
+				err, strerror(errno));
+			return err;
+		}
+
+		err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY);
+		if (err) {
+			fprintf(stderr,
+				"ERROR: bpf_map_update_elem (txmsg):  %d (%s\n",
+				err, strerror(errno));
+			return err;
+		}
+
+		if (txmsg_redir || txmsg_redir_noisy)
+			redir_fd = c2;
+		else
+			redir_fd = c1;
+
+		err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY);
+		if (err) {
+			fprintf(stderr,
+				"ERROR: bpf_map_update_elem (txmsg):  %d (%s\n",
+				err, strerror(errno));
+			return err;
+		}
+
+		if (txmsg_apply) {
+			err = bpf_map_update_elem(map_fd[3],
+						  &i, &txmsg_apply, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (apply_bytes):  %d (%s\n",
+					err, strerror(errno));
+				return err;
+			}
+		}
+
+		if (txmsg_cork) {
+			err = bpf_map_update_elem(map_fd[4],
+						  &i, &txmsg_cork, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (cork_bytes):  %d (%s\n",
+					err, strerror(errno));
+				return err;
+			}
+		}
+
+		if (txmsg_start) {
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_start):  %d (%s)\n",
+					err, strerror(errno));
+				return err;
+			}
+		}
+
+		if (txmsg_end) {
+			i = 1;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_end, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_end):  %d (%s)\n",
+					err, strerror(errno));
+				return err;
+			}
+		}
+
+		if (txmsg_ingress) {
+			int in = BPF_F_INGRESS;
+
+			i = 0;
+			err = bpf_map_update_elem(map_fd[6], &i, &in, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n",
+					err, strerror(errno));
+			}
+			i = 1;
+			err = bpf_map_update_elem(map_fd[1], &i, &p1, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (p1 txmsg): %d (%s)\n",
+					err, strerror(errno));
+			}
+			err = bpf_map_update_elem(map_fd[2], &i, &p1, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (p1 redir): %d (%s)\n",
+					err, strerror(errno));
+			}
+
+			i = 2;
+			err = bpf_map_update_elem(map_fd[2], &i, &p2, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (p2 txmsg): %d (%s)\n",
+					err, strerror(errno));
+			}
+		}
+
+		if (txmsg_skb) {
+			int skb_fd = (test == SENDMSG || test == SENDPAGE) ? p2 : p1;
+			int ingress = BPF_F_INGRESS;
+
+			i = 0;
+			err = bpf_map_update_elem(map_fd[7], &i, &ingress, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n",
+					err, strerror(errno));
+			}
+
+			i = 3;
+			err = bpf_map_update_elem(map_fd[0], &i, &skb_fd, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n",
+					err, strerror(errno));
+			}
+		}
+	}
+
+	if (txmsg_drop)
+		options.drop_expected = true;
+
+	if (test == PING_PONG)
+		err = forever_ping_pong(rate, &options);
+	else if (test == SENDMSG) {
+		options.base = false;
+		options.sendpage = false;
+		err = sendmsg_test(iov_count, length, rate, &options);
+	} else if (test == SENDPAGE) {
+		options.base = false;
+		options.sendpage = true;
+		err = sendmsg_test(iov_count, length, rate, &options);
+	} else if (test == BASE) {
+		options.base = true;
+		options.sendpage = false;
+		err = sendmsg_test(iov_count, length, rate, &options);
+	} else if (test == BASE_SENDPAGE) {
+		options.base = true;
+		options.sendpage = true;
+		err = sendmsg_test(iov_count, length, rate, &options);
+	} else
 		fprintf(stderr, "unknown test\n");
 out:
+	bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
 	close(s1);
 	close(s2);
 	close(p1);