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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-07-13

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

We've added 36 non-merge commits during the last 7 day(s) which contain
a total of 62 files changed, 2242 insertions(+), 468 deletions(-).

The main changes are:

1) Avoid trace_printk warning banner by switching bpf_trace_printk to use
   its own tracing event, from Alan.

2) Better libbpf support on older kernels, from Andrii.

3) Additional AF_XDP stats, from Ciara.

4) build time resolution of BTF IDs, from Jiri.

5) BPF_CGROUP_INET_SOCK_RELEASE hook, from Stanislav.
====================

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

8 files changed, 392 insertions, 208 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 8403e4762306..f87ee02073ba 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -93,7 +93,7 @@ sampleip-objs := sampleip_user.o $(TRACE_HELPERS)
 tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o
-test_map_in_map-objs := bpf_load.o test_map_in_map_user.o
+test_map_in_map-objs := test_map_in_map_user.o
 per_socket_stats_example-objs := cookie_uid_helper_example.o
 xdp_redirect-objs := xdp_redirect_user.o
 xdp_redirect_map-objs := xdp_redirect_map_user.o
diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c
index d5992f787232..59f45fef5110 100644
--- a/samples/bpf/fds_example.c
+++ b/samples/bpf/fds_example.c
@@ -30,6 +30,8 @@
 #define BPF_M_MAP	1
 #define BPF_M_PROG	2
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void usage(void)
 {
 	printf("Usage: fds_example [...]\n");
@@ -57,7 +59,6 @@ static int bpf_prog_create(const char *object)
 		BPF_EXIT_INSN(),
 	};
 	size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn);
-	char bpf_log_buf[BPF_LOG_BUF_SIZE];
 	struct bpf_object *obj;
 	int prog_fd;
 
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 12e91ae64d4d..8773f22b6a98 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -9,95 +9,100 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_legacy.h"
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "trace_common.h"
 
 #define MAX_ENTRIES 1000
 #define MAX_NR_CPUS 1024
 
-struct bpf_map_def_legacy SEC("maps") hash_map = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+} hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 10000);
+} lru_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 10000);
+	__uint(map_flags, BPF_F_NO_COMMON_LRU);
+} nocommon_lru_hash_map SEC(".maps");
+
+struct inner_lru {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NUMA_NODE);
+	__uint(numa_node, 0);
+} inner_lru_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, MAX_NR_CPUS);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_lru); /* use inner_lru as inner map */
+} array_of_lru_hashs SEC(".maps") = {
+	/* statically initialize the first element */
+	.values = { &inner_lru_hash_map },
 };
 
-struct bpf_map_def_legacy SEC("maps") lru_hash_map = {
-	.type = BPF_MAP_TYPE_LRU_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 10000,
-};
-
-struct bpf_map_def_legacy SEC("maps") nocommon_lru_hash_map = {
-	.type = BPF_MAP_TYPE_LRU_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 10000,
-	.map_flags = BPF_F_NO_COMMON_LRU,
-};
-
-struct bpf_map_def_legacy SEC("maps") inner_lru_hash_map = {
-	.type = BPF_MAP_TYPE_LRU_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
-	.map_flags = BPF_F_NUMA_NODE,
-	.numa_node = 0,
-};
-
-struct bpf_map_def_legacy SEC("maps") array_of_lru_hashs = {
-	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
-	.key_size = sizeof(u32),
-	.max_entries = MAX_NR_CPUS,
-};
-
-struct bpf_map_def_legacy SEC("maps") percpu_hash_map = {
-	.type = BPF_MAP_TYPE_PERCPU_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
-};
-
-struct bpf_map_def_legacy SEC("maps") hash_map_alloc = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
-
-struct bpf_map_def_legacy SEC("maps") percpu_hash_map_alloc = {
-	.type = BPF_MAP_TYPE_PERCPU_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
-
-struct bpf_map_def_legacy SEC("maps") lpm_trie_map_alloc = {
-	.type = BPF_MAP_TYPE_LPM_TRIE,
-	.key_size = 8,
-	.value_size = sizeof(long),
-	.max_entries = 10000,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
-
-struct bpf_map_def_legacy SEC("maps") array_map = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
-};
-
-struct bpf_map_def_legacy SEC("maps") lru_hash_lookup_map = {
-	.type = BPF_MAP_TYPE_LRU_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = MAX_ENTRIES,
-};
-
-SEC("kprobe/sys_getuid")
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, MAX_ENTRIES);
+} percpu_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} hash_map_alloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} percpu_hash_map_alloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__uint(key_size, 8);
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, 10000);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} lpm_trie_map_alloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+} array_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+} lru_hash_lookup_map SEC(".maps");
+
+SEC("kprobe/" SYSCALL(sys_getuid))
 int stress_hmap(struct pt_regs *ctx)
 {
 	u32 key = bpf_get_current_pid_tgid();
@@ -112,7 +117,7 @@ int stress_hmap(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_geteuid")
+SEC("kprobe/" SYSCALL(sys_geteuid))
 int stress_percpu_hmap(struct pt_regs *ctx)
 {
 	u32 key = bpf_get_current_pid_tgid();
@@ -126,7 +131,7 @@ int stress_percpu_hmap(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getgid")
+SEC("kprobe/" SYSCALL(sys_getgid))
 int stress_hmap_alloc(struct pt_regs *ctx)
 {
 	u32 key = bpf_get_current_pid_tgid();
@@ -140,7 +145,7 @@ int stress_hmap_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getegid")
+SEC("kprobe/" SYSCALL(sys_getegid))
 int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 {
 	u32 key = bpf_get_current_pid_tgid();
@@ -154,9 +159,10 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_connect")
+SEC("kprobe/" SYSCALL(sys_connect))
 int stress_lru_hmap_alloc(struct pt_regs *ctx)
 {
+	struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
 	char fmt[] = "Failed at stress_lru_hmap_alloc. ret:%dn";
 	union {
 		u16 dst6[8];
@@ -175,8 +181,8 @@ int stress_lru_hmap_alloc(struct pt_regs *ctx)
 	long val = 1;
 	u32 key = 0;
 
-	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
-	addrlen = (int)PT_REGS_PARM3(ctx);
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs);
+	addrlen = (int)PT_REGS_PARM3_CORE(real_regs);
 
 	if (addrlen != sizeof(*in6))
 		return 0;
@@ -233,7 +239,7 @@ done:
 	return 0;
 }
 
-SEC("kprobe/sys_gettid")
+SEC("kprobe/" SYSCALL(sys_gettid))
 int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
 {
 	union {
@@ -255,7 +261,7 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getpgid")
+SEC("kprobe/" SYSCALL(sys_getpgid))
 int stress_hash_map_lookup(struct pt_regs *ctx)
 {
 	u32 key = 1, i;
@@ -268,7 +274,7 @@ int stress_hash_map_lookup(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getppid")
+SEC("kprobe/" SYSCALL(sys_getppid))
 int stress_array_map_lookup(struct pt_regs *ctx)
 {
 	u32 key = 1, i;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index fe5564bff39b..8b13230b4c46 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -11,7 +11,6 @@
 #include <sys/wait.h>
 #include <stdlib.h>
 #include <signal.h>
-#include <linux/bpf.h>
 #include <string.h>
 #include <time.h>
 #include <sys/resource.h>
@@ -19,7 +18,7 @@
 #include <errno.h>
 
 #include <bpf/bpf.h>
-#include "bpf_load.h"
+#include <bpf/libbpf.h>
 
 #define TEST_BIT(t) (1U << (t))
 #define MAX_NR_CPUS 1024
@@ -61,12 +60,18 @@ const char *test_map_names[NR_TESTS] = {
 	[LRU_HASH_LOOKUP] = "lru_hash_lookup_map",
 };
 
+enum map_idx {
+	array_of_lru_hashs_idx,
+	hash_map_alloc_idx,
+	lru_hash_lookup_idx,
+	NR_IDXES,
+};
+
+static int map_fd[NR_IDXES];
+
 static int test_flags = ~0;
 static uint32_t num_map_entries;
 static uint32_t inner_lru_hash_size;
-static int inner_lru_hash_idx = -1;
-static int array_of_lru_hashs_idx = -1;
-static int lru_hash_lookup_idx = -1;
 static int lru_hash_lookup_test_entries = 32;
 static uint32_t max_cnt = 1000000;
 
@@ -122,30 +127,30 @@ static void do_test_lru(enum test_type test, int cpu)
 	__u64 start_time;
 	int i, ret;
 
-	if (test == INNER_LRU_HASH_PREALLOC) {
+	if (test == INNER_LRU_HASH_PREALLOC && cpu) {
+		/* If CPU is not 0, create inner_lru hash map and insert the fd
+		 * value into the array_of_lru_hash map. In case of CPU 0,
+		 * 'inner_lru_hash_map' was statically inserted on the map init
+		 */
 		int outer_fd = map_fd[array_of_lru_hashs_idx];
 		unsigned int mycpu, mynode;
 
 		assert(cpu < MAX_NR_CPUS);
 
-		if (cpu) {
-			ret = syscall(__NR_getcpu, &mycpu, &mynode, NULL);
-			assert(!ret);
-
-			inner_lru_map_fds[cpu] =
-				bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH,
-						    test_map_names[INNER_LRU_HASH_PREALLOC],
-						    sizeof(uint32_t),
-						    sizeof(long),
-						    inner_lru_hash_size, 0,
-						    mynode);
-			if (inner_lru_map_fds[cpu] == -1) {
-				printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n",
-				       strerror(errno), errno);
-				exit(1);
-			}
-		} else {
-			inner_lru_map_fds[cpu] = map_fd[inner_lru_hash_idx];
+		ret = syscall(__NR_getcpu, &mycpu, &mynode, NULL);
+		assert(!ret);
+
+		inner_lru_map_fds[cpu] =
+			bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH,
+					    test_map_names[INNER_LRU_HASH_PREALLOC],
+					    sizeof(uint32_t),
+					    sizeof(long),
+					    inner_lru_hash_size, 0,
+					    mynode);
+		if (inner_lru_map_fds[cpu] == -1) {
+			printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n",
+			       strerror(errno), errno);
+			exit(1);
 		}
 
 		ret = bpf_map_update_elem(outer_fd, &cpu,
@@ -377,7 +382,8 @@ static void fill_lpm_trie(void)
 		key->data[1] = rand() & 0xff;
 		key->data[2] = rand() & 0xff;
 		key->data[3] = rand() & 0xff;
-		r = bpf_map_update_elem(map_fd[6], key, &value, 0);
+		r = bpf_map_update_elem(map_fd[hash_map_alloc_idx],
+					key, &value, 0);
 		assert(!r);
 	}
 
@@ -388,59 +394,52 @@ static void fill_lpm_trie(void)
 	key->data[3] = 1;
 	value = 128;
 
-	r = bpf_map_update_elem(map_fd[6], key, &value, 0);
+	r = bpf_map_update_elem(map_fd[hash_map_alloc_idx], key, &value, 0);
 	assert(!r);
 }
 
-static void fixup_map(struct bpf_map_data *map, int idx)
+static void fixup_map(struct bpf_object *obj)
 {
+	struct bpf_map *map;
 	int i;
 
-	if (!strcmp("inner_lru_hash_map", map->name)) {
-		inner_lru_hash_idx = idx;
-		inner_lru_hash_size = map->def.max_entries;
-	}
+	bpf_object__for_each_map(map, obj) {
+		const char *name = bpf_map__name(map);
 
-	if (!strcmp("array_of_lru_hashs", map->name)) {
-		if (inner_lru_hash_idx == -1) {
-			printf("inner_lru_hash_map must be defined before array_of_lru_hashs\n");
-			exit(1);
+		/* Only change the max_entries for the enabled test(s) */
+		for (i = 0; i < NR_TESTS; i++) {
+			if (!strcmp(test_map_names[i], name) &&
+			    (check_test_flags(i))) {
+				bpf_map__resize(map, num_map_entries);
+				continue;
+			}
 		}
-		map->def.inner_map_idx = inner_lru_hash_idx;
-		array_of_lru_hashs_idx = idx;
 	}
 
-	if (!strcmp("lru_hash_lookup_map", map->name))
-		lru_hash_lookup_idx = idx;
-
-	if (num_map_entries <= 0)
-		return;
-
 	inner_lru_hash_size = num_map_entries;
-
-	/* Only change the max_entries for the enabled test(s) */
-	for (i = 0; i < NR_TESTS; i++) {
-		if (!strcmp(test_map_names[i], map->name) &&
-		    (check_test_flags(i))) {
-			map->def.max_entries = num_map_entries;
-		}
-	}
 }
 
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	struct bpf_link *links[8];
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_map *map;
 	char filename[256];
-	int num_cpu = 8;
+	int i = 0;
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-	setrlimit(RLIMIT_MEMLOCK, &r);
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
 
 	if (argc > 1)
 		test_flags = atoi(argv[1]) ? : test_flags;
 
 	if (argc > 2)
-		num_cpu = atoi(argv[2]) ? : num_cpu;
+		nr_cpus = atoi(argv[2]) ? : nr_cpus;
 
 	if (argc > 3)
 		num_map_entries = atoi(argv[3]);
@@ -448,14 +447,61 @@ int main(int argc, char **argv)
 	if (argc > 4)
 		max_cnt = atoi(argv[4]);
 
-	if (load_bpf_file_fixup_map(filename, fixup_map)) {
-		printf("%s", bpf_log_buf);
-		return 1;
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "inner_lru_hash_map");
+	if (libbpf_get_error(map)) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	inner_lru_hash_size = bpf_map__max_entries(map);
+	if (!inner_lru_hash_size) {
+		fprintf(stderr, "ERROR: failed to get map attribute\n");
+		goto cleanup;
+	}
+
+	/* resize BPF map prior to loading */
+	if (num_map_entries > 0)
+		fixup_map(obj);
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "array_of_lru_hashs");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "hash_map_alloc");
+	map_fd[2] = bpf_object__find_map_fd_by_name(obj, "lru_hash_lookup_map");
+	if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[i] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
 	}
 
 	fill_lpm_trie();
 
-	run_perf_test(num_cpu);
+	run_perf_test(nr_cpus);
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
 
+	bpf_object__close(obj);
 	return 0;
 }
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index 6cee61e8ce9b..8def45c5b697 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -11,66 +11,67 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/in6.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_legacy.h"
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "trace_common.h"
 
 #define MAX_NR_PORTS 65536
 
 /* map #0 */
-struct bpf_map_def_legacy SEC("maps") port_a = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(int),
-	.max_entries = MAX_NR_PORTS,
-};
+struct inner_a {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, MAX_NR_PORTS);
+} port_a SEC(".maps");
 
 /* map #1 */
-struct bpf_map_def_legacy SEC("maps") port_h = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(int),
-	.max_entries = 1,
-};
+struct inner_h {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, 1);
+} port_h SEC(".maps");
 
 /* map #2 */
-struct bpf_map_def_legacy SEC("maps") reg_result_h = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(int),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, 1);
+} reg_result_h SEC(".maps");
 
 /* map #3 */
-struct bpf_map_def_legacy SEC("maps") inline_result_h = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(int),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, 1);
+} inline_result_h SEC(".maps");
 
 /* map #4 */ /* Test case #0 */
-struct bpf_map_def_legacy SEC("maps") a_of_port_a = {
-	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
-	.key_size = sizeof(u32),
-	.inner_map_idx = 0, /* map_fd[0] is port_a */
-	.max_entries = MAX_NR_PORTS,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, MAX_NR_PORTS);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_a); /* use inner_a as inner map */
+} a_of_port_a SEC(".maps");
 
 /* map #5 */ /* Test case #1 */
-struct bpf_map_def_legacy SEC("maps") h_of_port_a = {
-	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
-	.key_size = sizeof(u32),
-	.inner_map_idx = 0, /* map_fd[0] is port_a */
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_a); /* use inner_a as inner map */
+} h_of_port_a SEC(".maps");
 
 /* map #6 */ /* Test case #2 */
-struct bpf_map_def_legacy SEC("maps") h_of_port_h = {
-	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
-	.key_size = sizeof(u32),
-	.inner_map_idx = 1, /* map_fd[1] is port_h */
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_h); /* use inner_h as inner map */
+} h_of_port_h SEC(".maps");
 
 static __always_inline int do_reg_lookup(void *inner_map, u32 port)
 {
@@ -102,9 +103,10 @@ static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
 	return result ? *result : -ENOENT;
 }
 
-SEC("kprobe/sys_connect")
+SEC("kprobe/" SYSCALL(sys_connect))
 int trace_sys_connect(struct pt_regs *ctx)
 {
+	struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
 	struct sockaddr_in6 *in6;
 	u16 test_case, port, dst6[8];
 	int addrlen, ret, inline_ret, ret_key = 0;
@@ -112,8 +114,8 @@ int trace_sys_connect(struct pt_regs *ctx)
 	void *outer_map, *inner_map;
 	bool inline_hash = false;
 
-	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
-	addrlen = (int)PT_REGS_PARM3(ctx);
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs);
+	addrlen = (int)PT_REGS_PARM3_CORE(real_regs);
 
 	if (addrlen != sizeof(*in6))
 		return 0;
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
index eb29bcb76f3f..98656de56b83 100644
--- a/samples/bpf/test_map_in_map_user.c
+++ b/samples/bpf/test_map_in_map_user.c
@@ -11,7 +11,9 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <bpf/bpf.h>
-#include "bpf_load.h"
+#include <bpf/libbpf.h>
+
+static int map_fd[7];
 
 #define PORT_A		(map_fd[0])
 #define PORT_H		(map_fd[1])
@@ -113,18 +115,59 @@ static void test_map_in_map(void)
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
 	char filename[256];
 
-	assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
 
-	if (load_bpf_file(filename)) {
-		printf("%s", bpf_log_buf);
-		return 1;
+	prog = bpf_object__find_program_by_name(obj, "trace_sys_connect");
+	if (!prog) {
+		printf("finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "port_a");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "port_h");
+	map_fd[2] = bpf_object__find_map_fd_by_name(obj, "reg_result_h");
+	map_fd[3] = bpf_object__find_map_fd_by_name(obj, "inline_result_h");
+	map_fd[4] = bpf_object__find_map_fd_by_name(obj, "a_of_port_a");
+	map_fd[5] = bpf_object__find_map_fd_by_name(obj, "h_of_port_a");
+	map_fd[6] = bpf_object__find_map_fd_by_name(obj, "h_of_port_h");
+	if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0 ||
+	    map_fd[3] < 0 || map_fd[4] < 0 || map_fd[5] < 0 || map_fd[6] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach(prog);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+		link = NULL;
+		goto cleanup;
 	}
 
 	test_map_in_map();
 
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
 	return 0;
 }
diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c
index f033f36a13a3..fd651a65281e 100644
--- a/samples/bpf/test_probe_write_user_kern.c
+++ b/samples/bpf/test_probe_write_user_kern.c
@@ -10,6 +10,8 @@
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "trace_common.h"
 
 struct bpf_map_def SEC("maps") dnat_map = {
 	.type = BPF_MAP_TYPE_HASH,
@@ -26,13 +28,14 @@ struct bpf_map_def SEC("maps") dnat_map = {
  * This example sits on a syscall, and the syscall ABI is relatively stable
  * of course, across platforms, and over time, the ABI may change.
  */
-SEC("kprobe/sys_connect")
+SEC("kprobe/" SYSCALL(sys_connect))
 int bpf_prog1(struct pt_regs *ctx)
 {
+	struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
+	void *sockaddr_arg = (void *)PT_REGS_PARM2_CORE(real_regs);
+	int sockaddr_len = (int)PT_REGS_PARM3_CORE(real_regs);
 	struct sockaddr_in new_addr, orig_addr = {};
 	struct sockaddr_in *mapped_addr;
-	void *sockaddr_arg = (void *)PT_REGS_PARM2(ctx);
-	int sockaddr_len = (int)PT_REGS_PARM3(ctx);
 
 	if (sockaddr_len > sizeof(orig_addr))
 		return 0;
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index c91e91362a0c..19c679456a0e 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -77,6 +77,7 @@ static u32 opt_batch_size = 64;
 static int opt_pkt_count;
 static u16 opt_pkt_size = MIN_PKT_SIZE;
 static u32 opt_pkt_fill_pattern = 0x12345678;
+static bool opt_extra_stats;
 static int opt_poll;
 static int opt_interval = 1;
 static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
@@ -103,8 +104,20 @@ struct xsk_socket_info {
 	struct xsk_socket *xsk;
 	unsigned long rx_npkts;
 	unsigned long tx_npkts;
+	unsigned long rx_dropped_npkts;
+	unsigned long rx_invalid_npkts;
+	unsigned long tx_invalid_npkts;
+	unsigned long rx_full_npkts;
+	unsigned long rx_fill_empty_npkts;
+	unsigned long tx_empty_npkts;
 	unsigned long prev_rx_npkts;
 	unsigned long prev_tx_npkts;
+	unsigned long prev_rx_dropped_npkts;
+	unsigned long prev_rx_invalid_npkts;
+	unsigned long prev_tx_invalid_npkts;
+	unsigned long prev_rx_full_npkts;
+	unsigned long prev_rx_fill_empty_npkts;
+	unsigned long prev_tx_empty_npkts;
 	u32 outstanding_tx;
 };
 
@@ -147,6 +160,30 @@ static void print_benchmark(bool running)
 	}
 }
 
+static int xsk_get_xdp_stats(int fd, struct xsk_socket_info *xsk)
+{
+	struct xdp_statistics stats;
+	socklen_t optlen;
+	int err;
+
+	optlen = sizeof(stats);
+	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
+	if (err)
+		return err;
+
+	if (optlen == sizeof(struct xdp_statistics)) {
+		xsk->rx_dropped_npkts = stats.rx_dropped;
+		xsk->rx_invalid_npkts = stats.rx_invalid_descs;
+		xsk->tx_invalid_npkts = stats.tx_invalid_descs;
+		xsk->rx_full_npkts = stats.rx_ring_full;
+		xsk->rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs;
+		xsk->tx_empty_npkts = stats.tx_ring_empty_descs;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 static void dump_stats(void)
 {
 	unsigned long now = get_nsecs();
@@ -157,7 +194,8 @@ static void dump_stats(void)
 
 	for (i = 0; i < num_socks && xsks[i]; i++) {
 		char *fmt = "%-15s %'-11.0f %'-11lu\n";
-		double rx_pps, tx_pps;
+		double rx_pps, tx_pps, dropped_pps, rx_invalid_pps, full_pps, fill_empty_pps,
+			tx_invalid_pps, tx_empty_pps;
 
 		rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) *
 			 1000000000. / dt;
@@ -175,6 +213,46 @@ static void dump_stats(void)
 
 		xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts;
 		xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts;
+
+		if (opt_extra_stats) {
+			if (!xsk_get_xdp_stats(xsk_socket__fd(xsks[i]->xsk), xsks[i])) {
+				dropped_pps = (xsks[i]->rx_dropped_npkts -
+						xsks[i]->prev_rx_dropped_npkts) * 1000000000. / dt;
+				rx_invalid_pps = (xsks[i]->rx_invalid_npkts -
+						xsks[i]->prev_rx_invalid_npkts) * 1000000000. / dt;
+				tx_invalid_pps = (xsks[i]->tx_invalid_npkts -
+						xsks[i]->prev_tx_invalid_npkts) * 1000000000. / dt;
+				full_pps = (xsks[i]->rx_full_npkts -
+						xsks[i]->prev_rx_full_npkts) * 1000000000. / dt;
+				fill_empty_pps = (xsks[i]->rx_fill_empty_npkts -
+						xsks[i]->prev_rx_fill_empty_npkts)
+						* 1000000000. / dt;
+				tx_empty_pps = (xsks[i]->tx_empty_npkts -
+						xsks[i]->prev_tx_empty_npkts) * 1000000000. / dt;
+
+				printf(fmt, "rx dropped", dropped_pps,
+				       xsks[i]->rx_dropped_npkts);
+				printf(fmt, "rx invalid", rx_invalid_pps,
+				       xsks[i]->rx_invalid_npkts);
+				printf(fmt, "tx invalid", tx_invalid_pps,
+				       xsks[i]->tx_invalid_npkts);
+				printf(fmt, "rx queue full", full_pps,
+				       xsks[i]->rx_full_npkts);
+				printf(fmt, "fill ring empty", fill_empty_pps,
+				       xsks[i]->rx_fill_empty_npkts);
+				printf(fmt, "tx ring empty", tx_empty_pps,
+				       xsks[i]->tx_empty_npkts);
+
+				xsks[i]->prev_rx_dropped_npkts = xsks[i]->rx_dropped_npkts;
+				xsks[i]->prev_rx_invalid_npkts = xsks[i]->rx_invalid_npkts;
+				xsks[i]->prev_tx_invalid_npkts = xsks[i]->tx_invalid_npkts;
+				xsks[i]->prev_rx_full_npkts = xsks[i]->rx_full_npkts;
+				xsks[i]->prev_rx_fill_empty_npkts = xsks[i]->rx_fill_empty_npkts;
+				xsks[i]->prev_tx_empty_npkts = xsks[i]->tx_empty_npkts;
+			} else {
+				printf("%-15s\n", "Error retrieving extra stats");
+			}
+		}
 	}
 }
 
@@ -630,6 +708,7 @@ static struct option long_options[] = {
 	{"tx-pkt-count", required_argument, 0, 'C'},
 	{"tx-pkt-size", required_argument, 0, 's'},
 	{"tx-pkt-pattern", required_argument, 0, 'P'},
+	{"extra-stats", no_argument, 0, 'x'},
 	{0, 0, 0, 0}
 };
 
@@ -664,6 +743,7 @@ static void usage(const char *prog)
 		"			(Default: %d bytes)\n"
 		"			Min size: %d, Max size %d.\n"
 		"  -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n"
+		"  -x, --extra-stats	Display extra statistics.\n"
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE,
 		opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
@@ -679,7 +759,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:",
+		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:x",
 				long_options, &option_index);
 		if (c == -1)
 			break;
@@ -760,6 +840,9 @@ static void parse_command_line(int argc, char **argv)
 		case 'P':
 			opt_pkt_fill_pattern = strtol(optarg, NULL, 16);
 			break;
+		case 'x':
+			opt_extra_stats = 1;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}