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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-10-21

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Implement two new kind of BPF maps, that is, queue and stack
   map along with new peek, push and pop operations, from Mauricio.

2) Add support for MSG_PEEK flag when redirecting into an ingress
   psock sk_msg queue, and add a new helper bpf_msg_push_data() for
   insert data into the message, from John.

3) Allow for BPF programs of type BPF_PROG_TYPE_CGROUP_SKB to use
   direct packet access for __skb_buff, from Song.

4) Use more lightweight barriers for walking perf ring buffer for
   libbpf and perf tool as well. Also, various fixes and improvements
   from verifier side, from Daniel.

5) Add per-symbol visibility for DSO in libbpf and hide by default
   global symbols such as netlink related functions, from Andrey.

6) Two improvements to nfp's BPF offload to check vNIC capabilities
   in case prog is shared with multiple vNICs and to protect against
   mis-initializing atomic counters, from Jakub.

7) Fix for bpftool to use 4 context mode for the nfp disassembler,
   also from Jakub.

8) Fix a return value comparison in test_libbpf.sh and add several
   bpftool improvements in bash completion, documentation of bpf fs
   restrictions and batch mode summary print, from Quentin.

9) Fix a file resource leak in BPF selftest's load_kallsyms()
   helper, from Peng.

10) Fix an unused variable warning in map_lookup_and_delete_elem(),
    from Alexei.

11) Fix bpf_skb_adjust_room() signature in BPF UAPI helper doc,
    from Nicolas.

12) Add missing executables to .gitignore in BPF selftests, from Anders.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 177 insertions, 59 deletions

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 10a5fa83c75a..622ade0a0957 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -28,6 +28,7 @@
 #include <linux/sock_diag.h>
 #include <linux/bpf.h>
 #include <linux/if_link.h>
+#include <linux/tls.h>
 #include <assert.h>
 #include <libgen.h>
 
@@ -43,6 +44,13 @@
 int running;
 static void running_handler(int a);
 
+#ifndef TCP_ULP
+# define TCP_ULP 31
+#endif
+#ifndef SOL_TLS
+# define SOL_TLS 282
+#endif
+
 /* randomly selected ports for testing on lo */
 #define S1_PORT 10000
 #define S2_PORT 10001
@@ -69,9 +77,12 @@ int txmsg_apply;
 int txmsg_cork;
 int txmsg_start;
 int txmsg_end;
+int txmsg_start_push;
+int txmsg_end_push;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
+int peek_flag;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -91,9 +102,12 @@ static const struct option long_options[] = {
 	{"txmsg_cork",	required_argument,	NULL, 'k'},
 	{"txmsg_start", required_argument,	NULL, 's'},
 	{"txmsg_end",	required_argument,	NULL, 'e'},
+	{"txmsg_start_push", required_argument,	NULL, 'p'},
+	{"txmsg_end_push",   required_argument,	NULL, 'q'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
+	{"peek", no_argument,			&peek_flag, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -114,11 +128,6 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
-#define TCP_ULP 31
-#define TLS_TX 1
-#define TLS_RX 2
-#include <linux/tls.h>
-
 char *sock_to_string(int s)
 {
 	if (s == c1)
@@ -349,33 +358,40 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	return 0;
 }
 
-static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
-		    struct msg_stats *s, bool tx,
-		    struct sockmap_options *opt)
+static void msg_free_iov(struct msghdr *msg)
 {
-	struct msghdr msg = {0};
-	int err, i, flags = MSG_NOSIGNAL;
+	int i;
+
+	for (i = 0; i < msg->msg_iovlen; i++)
+		free(msg->msg_iov[i].iov_base);
+	free(msg->msg_iov);
+	msg->msg_iov = NULL;
+	msg->msg_iovlen = 0;
+}
+
+static int msg_alloc_iov(struct msghdr *msg,
+			 int iov_count, int iov_length,
+			 bool data, bool xmit)
+{
+	unsigned char k = 0;
 	struct iovec *iov;
-	unsigned char k;
-	bool data_test = opt->data_test;
-	bool drop = opt->drop_expected;
+	int i;
 
 	iov = calloc(iov_count, sizeof(struct iovec));
 	if (!iov)
 		return errno;
 
-	k = 0;
 	for (i = 0; i < iov_count; i++) {
 		unsigned char *d = calloc(iov_length, sizeof(char));
 
 		if (!d) {
 			fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
-			goto out_errno;
+			goto unwind_iov;
 		}
 		iov[i].iov_base = d;
 		iov[i].iov_len = iov_length;
 
-		if (data_test && tx) {
+		if (data && xmit) {
 			int j;
 
 			for (j = 0; j < iov_length; j++)
@@ -383,9 +399,60 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 	}
 
-	msg.msg_iov = iov;
-	msg.msg_iovlen = iov_count;
-	k = 0;
+	msg->msg_iov = iov;
+	msg->msg_iovlen = iov_count;
+
+	return 0;
+unwind_iov:
+	for (i--; i >= 0 ; i--)
+		free(msg->msg_iov[i].iov_base);
+	return -ENOMEM;
+}
+
+static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
+{
+	int i, j, bytes_cnt = 0;
+	unsigned char k = 0;
+
+	for (i = 0; i < msg->msg_iovlen; i++) {
+		unsigned char *d = msg->msg_iov[i].iov_base;
+
+		for (j = 0;
+		     j < msg->msg_iov[i].iov_len && size; j++) {
+			if (d[j] != k++) {
+				fprintf(stderr,
+					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
+					i, j, d[j], k - 1, d[j+1], k);
+				return -EIO;
+			}
+			bytes_cnt++;
+			if (bytes_cnt == chunk_sz) {
+				k = 0;
+				bytes_cnt = 0;
+			}
+			size--;
+		}
+	}
+	return 0;
+}
+
+static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+		    struct msg_stats *s, bool tx,
+		    struct sockmap_options *opt)
+{
+	struct msghdr msg = {0}, msg_peek = {0};
+	int err, i, flags = MSG_NOSIGNAL;
+	bool drop = opt->drop_expected;
+	bool data = opt->data_test;
+
+	err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx);
+	if (err)
+		goto out_errno;
+	if (peek_flag) {
+		err = msg_alloc_iov(&msg_peek, iov_count, iov_length, data, tx);
+		if (err)
+			goto out_errno;
+	}
 
 	if (tx) {
 		clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -405,19 +472,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
-		int slct, recv, max_fd = fd;
+		int slct, recvp = 0, recv, max_fd = fd;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
 		float total_bytes;
-		int bytes_cnt = 0;
-		int chunk_sz;
 		fd_set w;
 
-		if (opt->sendpage)
-			chunk_sz = iov_length * cnt;
-		else
-			chunk_sz = iov_length * iov_count;
-
 		fcntl(fd, fd_flags);
 		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -449,6 +509,19 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				goto out_errno;
 			}
 
+			errno = 0;
+			if (peek_flag) {
+				flags |= MSG_PEEK;
+				recvp = recvmsg(fd, &msg_peek, flags);
+				if (recvp < 0) {
+					if (errno != EWOULDBLOCK) {
+						clock_gettime(CLOCK_MONOTONIC, &s->end);
+						goto out_errno;
+					}
+				}
+				flags = 0;
+			}
+
 			recv = recvmsg(fd, &msg, flags);
 			if (recv < 0) {
 				if (errno != EWOULDBLOCK) {
@@ -460,27 +533,23 @@ 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;
+			if (data) {
+				int chunk_sz = opt->sendpage ?
+						iov_length * cnt :
+						iov_length * iov_count;
 
-					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);
-							goto out_errno;
-						}
-						bytes_cnt++;
-						if (bytes_cnt == chunk_sz) {
-							k = 0;
-							bytes_cnt = 0;
-						}
-						recv--;
+				errno = msg_verify_data(&msg, recv, chunk_sz);
+				if (errno) {
+					perror("data verify msg failed\n");
+					goto out_errno;
+				}
+				if (recvp) {
+					errno = msg_verify_data(&msg_peek,
+								recvp,
+								chunk_sz);
+					if (errno) {
+						perror("data verify msg_peek failed\n");
+						goto out_errno;
 					}
 				}
 			}
@@ -488,14 +557,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	}
 
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
-	return 0;
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
+	return err;
 out_errno:
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
 	return errno;
 }
 
@@ -562,9 +629,10 @@ static int sendmsg_test(struct sockmap_options *opt)
 		}
 		if (opt->verbose)
 			fprintf(stdout,
-				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s %s\n",
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
-				s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+				s.bytes_recvd, recvd_Bps, recvd_Bps/giga,
+				peek_flag ? "(peek_msg)" : "");
 		if (err && txmsg_cork)
 			err = 0;
 		exit(err ? 1 : 0);
@@ -839,6 +907,30 @@ run:
 			}
 		}
 
+		if (txmsg_start_push) {
+			i = 2;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_start_push):  %d (%s)\n",
+					err, strerror(errno));
+				goto out;
+			}
+		}
+
+		if (txmsg_end_push) {
+			i = 3;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_end_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem %i@%i (txmsg_end_push):  %d (%s)\n",
+					txmsg_end_push, i, err, strerror(errno));
+				goto out;
+			}
+		}
+
 		if (txmsg_ingress) {
 			int in = BPF_F_INGRESS;
 
@@ -996,6 +1088,8 @@ static void test_options(char *options)
 		strncat(options, "skb,", OPTSTRING);
 	if (ktls)
 		strncat(options, "ktls,", OPTSTRING);
+	if (peek_flag)
+		strncat(options, "peek,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
@@ -1169,6 +1263,8 @@ static int test_mixed(int cgrp)
 	txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
 	txmsg_apply = txmsg_cork = 0;
 	txmsg_start = txmsg_end = 0;
+	txmsg_start_push = txmsg_end_push = 0;
+
 	/* Test small and large iov_count values with pass/redir/apply/cork */
 	txmsg_pass = 1;
 	txmsg_redir = 0;
@@ -1285,6 +1381,8 @@ static int test_start_end(int cgrp)
 	/* Test basic start/end with lots of iov_count and iov_lengths */
 	txmsg_start = 1;
 	txmsg_end = 2;
+	txmsg_start_push = 1;
+	txmsg_end_push = 2;
 	err = test_txmsg(cgrp);
 	if (err)
 		goto out;
@@ -1298,6 +1396,8 @@ static int test_start_end(int cgrp)
 	for (i = 99; i <= 1600; i += 500) {
 		txmsg_start = 0;
 		txmsg_end = i;
+		txmsg_start_push = 0;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1307,6 +1407,8 @@ static int test_start_end(int cgrp)
 	for (i = 199; i <= 1600; i += 500) {
 		txmsg_start = 100;
 		txmsg_end = i;
+		txmsg_start_push = 100;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1315,6 +1417,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with cork pulling last sg entry */
 	txmsg_start = 1500;
 	txmsg_end = 1600;
+	txmsg_start_push = 1500;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1322,6 +1426,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end pull of single byte in last page */
 	txmsg_start = 1111;
 	txmsg_end = 1112;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 1112;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1329,6 +1435,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end < start */
 	txmsg_start = 1111;
 	txmsg_end = 0;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 0;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1336,6 +1444,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end > data */
 	txmsg_start = 0;
 	txmsg_end = 1601;
+	txmsg_start_push = 0;
+	txmsg_end_push = 1601;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1343,6 +1453,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with start > data */
 	txmsg_start = 1601;
 	txmsg_end = 1600;
+	txmsg_start_push = 1601;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 
 out:
@@ -1358,7 +1470,7 @@ char *map_names[] = {
 	"sock_map_redir",
 	"sock_apply_bytes",
 	"sock_cork_bytes",
-	"sock_pull_bytes",
+	"sock_bytes",
 	"sock_redir_flags",
 	"sock_skb_opts",
 };
@@ -1465,7 +1577,7 @@ static int __test_suite(int cg_fd, char *bpf_file)
 	}
 
 	/* Tests basic commands and APIs with range of iov values */
-	txmsg_start = txmsg_end = 0;
+	txmsg_start = txmsg_end = txmsg_start_push = txmsg_end_push = 0;
 	err = test_txmsg(cg_fd);
 	if (err)
 		goto out;
@@ -1514,7 +1626,7 @@ int main(int argc, char **argv)
 	if (argc < 2)
 		return test_suite(-1);
 
-	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
+	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:p:q:",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 's':
@@ -1523,6 +1635,12 @@ int main(int argc, char **argv)
 		case 'e':
 			txmsg_end = atoi(optarg);
 			break;
+		case 'p':
+			txmsg_start_push = atoi(optarg);
+			break;
+		case 'q':
+			txmsg_end_push = atoi(optarg);
+			break;
 		case 'a':
 			txmsg_apply = atoi(optarg);
 			break;