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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-03-04

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

The main changes are:

1) Add AF_XDP support to libbpf. Rationale is to facilitate writing
   AF_XDP applications by offering higher-level APIs that hide many
   of the details of the AF_XDP uapi. Sample programs are converted
   over to this new interface as well, from Magnus.

2) Introduce a new cant_sleep() macro for annotation of functions
   that cannot sleep and use it in BPF_PROG_RUN() to assert that
   BPF programs run under preemption disabled context, from Peter.

3) Introduce per BPF prog stats in order to monitor the usage
   of BPF; this is controlled by kernel.bpf_stats_enabled sysctl
   knob where monitoring tools can make use of this to efficiently
   determine the average cost of programs, from Alexei.

4) Split up BPF selftest's test_progs similarly as we already
   did with test_verifier. This allows to further reduce merge
   conflicts in future and to get more structure into our
   quickly growing BPF selftest suite, from Stanislav.

5) Fix a bug in BTF's dedup algorithm which can cause an infinite
   loop in some circumstances; also various BPF doc fixes and
   improvements, from Andrii.

6) Various BPF sample cleanups and migration to libbpf in order
   to further isolate the old sample loader code (so we can get
   rid of it at some point), from Jakub.

7) Add a new BPF helper for BPF cgroup skb progs that allows
   to set ECN CE code point and a Host Bandwidth Manager (HBM)
   sample program for limiting the bandwidth used by v2 cgroups,
   from Lawrence.

8) Enable write access to skb->queue_mapping from tc BPF egress
   programs in order to let BPF pick TX queue, from Jesper.

9) Fix a bug in BPF spinlock handling for map-in-map which did
   not propagate spin_lock_off to the meta map, from Yonghong.

10) Fix a bug in the new per-CPU BPF prog counters to properly
    initialize stats for each CPU, from Eric.

11) Add various BPF helper prototypes to selftest's bpf_helpers.h,
    from Willem.

12) Fix various BPF samples bugs in XDP and tracing progs,
    from Toke, Daniel and Yonghong.

13) Silence preemption splat in test_bpf after BPF_PROG_RUN()
    enforces it now everywhere, from Anders.

14) Fix a signedness bug in libbpf's btf_dedup_ref_type() to
    get error handling working, from Dan.

15) Fix bpftool documentation and auto-completion with regards
    to stream_{verdict,parser} attach types, from Alban.
====================

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

35 files changed, 2237 insertions, 1989 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index e47168d1257d..3b74d23fffab 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -14,6 +14,7 @@ feature
 test_libbpf_open
 test_sock
 test_sock_addr
+test_sock_fields
 urandom_read
 test_btf
 test_sockmap
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index ccffaa0a0787..518cd587cd63 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -165,7 +165,11 @@ $(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read
 $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(ALU32_BUILD_DIR) \
 						$(ALU32_BUILD_DIR)/urandom_read
 	$(CC) $(CFLAGS) -o $(ALU32_BUILD_DIR)/test_progs_32 $< \
-		trace_helpers.c $(OUTPUT)/libbpf.a $(LDLIBS)
+		trace_helpers.c prog_tests/*.c $(OUTPUT)/libbpf.a $(LDLIBS)
+
+$(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H)
+$(ALU32_BUILD_DIR)/test_progs_32: CFLAGS += -I$(OUTPUT)
+$(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c
 
 $(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \
 					$(ALU32_BUILD_DIR)/test_progs_32
@@ -196,6 +200,25 @@ ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
 endif
 
+PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h
+$(OUTPUT)/test_progs: $(PROG_TESTS_H)
+$(OUTPUT)/test_progs: CFLAGS += -I$(OUTPUT)
+$(OUTPUT)/test_progs: prog_tests/*.c
+
+PROG_TESTS_FILES := $(wildcard prog_tests/*.c)
+$(PROG_TESTS_H): $(PROG_TESTS_FILES)
+	$(shell ( cd prog_tests/
+		  echo '/* Generated header, do not edit */'; \
+		  echo '#ifdef DECLARE'; \
+		  ls *.c 2> /dev/null | \
+			sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \
+		  echo '#endif'; \
+		  echo '#ifdef CALL'; \
+		  ls *.c 2> /dev/null | \
+			sed -e 's@\([^\.]*\)\.c@test_\1();@'; \
+		  echo '#endif' \
+		 ) > $(PROG_TESTS_H))
+
 VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
 $(OUTPUT)/test_verifier: $(VERIFIER_TESTS_H)
 $(OUTPUT)/test_verifier: CFLAGS += -I$(OUTPUT)
@@ -211,4 +234,4 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TEST_FILES)
 		 ) > $(VERIFIER_TESTS_H))
 
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \
-	$(VERIFIER_TESTS_H)
+	$(VERIFIER_TESTS_H) $(PROG_TESTS_H)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index d9999f1ed1d2..c9433a496d54 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -180,6 +180,8 @@ static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_sk_fullsock;
 static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_tcp_sock;
+static int (*bpf_skb_ecn_set_ce)(void *ctx) =
+	(void *) BPF_FUNC_skb_ecn_set_ce;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
@@ -232,6 +234,36 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 	(void *) BPF_FUNC_skb_change_head;
 static int (*bpf_skb_pull_data)(void *, int len) =
 	(void *) BPF_FUNC_skb_pull_data;
+static unsigned int (*bpf_get_cgroup_classid)(void *ctx) =
+	(void *) BPF_FUNC_get_cgroup_classid;
+static unsigned int (*bpf_get_route_realm)(void *ctx) =
+	(void *) BPF_FUNC_get_route_realm;
+static int (*bpf_skb_change_proto)(void *ctx, __be16 proto, __u64 flags) =
+	(void *) BPF_FUNC_skb_change_proto;
+static int (*bpf_skb_change_type)(void *ctx, __u32 type) =
+	(void *) BPF_FUNC_skb_change_type;
+static unsigned int (*bpf_get_hash_recalc)(void *ctx) =
+	(void *) BPF_FUNC_get_hash_recalc;
+static unsigned long long (*bpf_get_current_task)(void *ctx) =
+	(void *) BPF_FUNC_get_current_task;
+static int (*bpf_skb_change_tail)(void *ctx, __u32 len, __u64 flags) =
+	(void *) BPF_FUNC_skb_change_tail;
+static long long (*bpf_csum_update)(void *ctx, __u32 csum) =
+	(void *) BPF_FUNC_csum_update;
+static void (*bpf_set_hash_invalid)(void *ctx) =
+	(void *) BPF_FUNC_set_hash_invalid;
+static int (*bpf_get_numa_node_id)(void) =
+	(void *) BPF_FUNC_get_numa_node_id;
+static int (*bpf_probe_read_str)(void *ctx, __u32 size,
+				 const void *unsafe_ptr) =
+	(void *) BPF_FUNC_probe_read_str;
+static unsigned int (*bpf_get_socket_uid)(void *ctx) =
+	(void *) BPF_FUNC_get_socket_uid;
+static unsigned int (*bpf_set_hash)(void *ctx, __u32 hash) =
+	(void *) BPF_FUNC_set_hash;
+static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
+				  unsigned long long flags) =
+	(void *) BPF_FUNC_skb_adjust_room;
 
 /* Scan the ARCH passed in from ARCH env variable (see Makefile) */
 #if defined(__TARGET_ARCH_x86)
diff --git a/tools/testing/selftests/bpf/prog_tests/.gitignore b/tools/testing/selftests/bpf/prog_tests/.gitignore
new file mode 100644
index 000000000000..45984a364647
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/.gitignore
@@ -0,0 +1 @@
+tests.h
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
new file mode 100644
index 000000000000..a64f7a02139c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+void test_bpf_obj_id(void)
+{
+	const __u64 array_magic_value = 0xfaceb00c;
+	const __u32 array_key = 0;
+	const int nr_iters = 2;
+	const char *file = "./test_obj_id.o";
+	const char *expected_prog_name = "test_obj_id";
+	const char *expected_map_name = "test_map_id";
+	const __u64 nsec_per_sec = 1000000000;
+
+	struct bpf_object *objs[nr_iters];
+	int prog_fds[nr_iters], map_fds[nr_iters];
+	/* +1 to test for the info_len returned by kernel */
+	struct bpf_prog_info prog_infos[nr_iters + 1];
+	struct bpf_map_info map_infos[nr_iters + 1];
+	/* Each prog only uses one map. +1 to test nr_map_ids
+	 * returned by kernel.
+	 */
+	__u32 map_ids[nr_iters + 1];
+	char jited_insns[128], xlated_insns[128], zeros[128];
+	__u32 i, next_id, info_len, nr_id_found, duration = 0;
+	struct timespec real_time_ts, boot_time_ts;
+	int err = 0;
+	__u64 array_value;
+	uid_t my_uid = getuid();
+	time_t now, load_time;
+
+	err = bpf_prog_get_fd_by_id(0);
+	CHECK(err >= 0 || errno != ENOENT,
+	      "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
+
+	err = bpf_map_get_fd_by_id(0);
+	CHECK(err >= 0 || errno != ENOENT,
+	      "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
+
+	for (i = 0; i < nr_iters; i++)
+		objs[i] = NULL;
+
+	/* Check bpf_obj_get_info_by_fd() */
+	bzero(zeros, sizeof(zeros));
+	for (i = 0; i < nr_iters; i++) {
+		now = time(NULL);
+		err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
+				    &objs[i], &prog_fds[i]);
+		/* test_obj_id.o is a dumb prog. It should never fail
+		 * to load.
+		 */
+		if (err)
+			error_cnt++;
+		assert(!err);
+
+		/* Insert a magic value to the map */
+		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
+		assert(map_fds[i] >= 0);
+		err = bpf_map_update_elem(map_fds[i], &array_key,
+					  &array_magic_value, 0);
+		assert(!err);
+
+		/* Check getting map info */
+		info_len = sizeof(struct bpf_map_info) * 2;
+		bzero(&map_infos[i], info_len);
+		err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
+					     &info_len);
+		if (CHECK(err ||
+			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
+			  map_infos[i].key_size != sizeof(__u32) ||
+			  map_infos[i].value_size != sizeof(__u64) ||
+			  map_infos[i].max_entries != 1 ||
+			  map_infos[i].map_flags != 0 ||
+			  info_len != sizeof(struct bpf_map_info) ||
+			  strcmp((char *)map_infos[i].name, expected_map_name),
+			  "get-map-info(fd)",
+			  "err %d errno %d type %d(%d) info_len %u(%Zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
+			  err, errno,
+			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
+			  info_len, sizeof(struct bpf_map_info),
+			  map_infos[i].key_size,
+			  map_infos[i].value_size,
+			  map_infos[i].max_entries,
+			  map_infos[i].map_flags,
+			  map_infos[i].name, expected_map_name))
+			goto done;
+
+		/* Check getting prog info */
+		info_len = sizeof(struct bpf_prog_info) * 2;
+		bzero(&prog_infos[i], info_len);
+		bzero(jited_insns, sizeof(jited_insns));
+		bzero(xlated_insns, sizeof(xlated_insns));
+		prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns);
+		prog_infos[i].jited_prog_len = sizeof(jited_insns);
+		prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
+		prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
+		prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
+		prog_infos[i].nr_map_ids = 2;
+		err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
+		assert(!err);
+		err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
+		assert(!err);
+		err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
+					     &info_len);
+		load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
+			+ (prog_infos[i].load_time / nsec_per_sec);
+		if (CHECK(err ||
+			  prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
+			  info_len != sizeof(struct bpf_prog_info) ||
+			  (jit_enabled && !prog_infos[i].jited_prog_len) ||
+			  (jit_enabled &&
+			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
+			  !prog_infos[i].xlated_prog_len ||
+			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
+			  load_time < now - 60 || load_time > now + 60 ||
+			  prog_infos[i].created_by_uid != my_uid ||
+			  prog_infos[i].nr_map_ids != 1 ||
+			  *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
+			  strcmp((char *)prog_infos[i].name, expected_prog_name),
+			  "get-prog-info(fd)",
+			  "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
+			  err, errno, i,
+			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
+			  info_len, sizeof(struct bpf_prog_info),
+			  jit_enabled,
+			  prog_infos[i].jited_prog_len,
+			  prog_infos[i].xlated_prog_len,
+			  !!memcmp(jited_insns, zeros, sizeof(zeros)),
+			  !!memcmp(xlated_insns, zeros, sizeof(zeros)),
+			  load_time, now,
+			  prog_infos[i].created_by_uid, my_uid,
+			  prog_infos[i].nr_map_ids, 1,
+			  *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
+			  prog_infos[i].name, expected_prog_name))
+			goto done;
+	}
+
+	/* Check bpf_prog_get_next_id() */
+	nr_id_found = 0;
+	next_id = 0;
+	while (!bpf_prog_get_next_id(next_id, &next_id)) {
+		struct bpf_prog_info prog_info = {};
+		__u32 saved_map_id;
+		int prog_fd;
+
+		info_len = sizeof(prog_info);
+
+		prog_fd = bpf_prog_get_fd_by_id(next_id);
+		if (prog_fd < 0 && errno == ENOENT)
+			/* The bpf_prog is in the dead row */
+			continue;
+		if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
+			  "prog_fd %d next_id %d errno %d\n",
+			  prog_fd, next_id, errno))
+			break;
+
+		for (i = 0; i < nr_iters; i++)
+			if (prog_infos[i].id == next_id)
+				break;
+
+		if (i == nr_iters)
+			continue;
+
+		nr_id_found++;
+
+		/* Negative test:
+		 * prog_info.nr_map_ids = 1
+		 * prog_info.map_ids = NULL
+		 */
+		prog_info.nr_map_ids = 1;
+		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+		if (CHECK(!err || errno != EFAULT,
+			  "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
+			  err, errno, EFAULT))
+			break;
+		bzero(&prog_info, sizeof(prog_info));
+		info_len = sizeof(prog_info);
+
+		saved_map_id = *(int *)((long)prog_infos[i].map_ids);
+		prog_info.map_ids = prog_infos[i].map_ids;
+		prog_info.nr_map_ids = 2;
+		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+		prog_infos[i].jited_prog_insns = 0;
+		prog_infos[i].xlated_prog_insns = 0;
+		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
+		      memcmp(&prog_info, &prog_infos[i], info_len) ||
+		      *(int *)(long)prog_info.map_ids != saved_map_id,
+		      "get-prog-info(next_id->fd)",
+		      "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n",
+		      err, errno, info_len, sizeof(struct bpf_prog_info),
+		      memcmp(&prog_info, &prog_infos[i], info_len),
+		      *(int *)(long)prog_info.map_ids, saved_map_id);
+		close(prog_fd);
+	}
+	CHECK(nr_id_found != nr_iters,
+	      "check total prog id found by get_next_id",
+	      "nr_id_found %u(%u)\n",
+	      nr_id_found, nr_iters);
+
+	/* Check bpf_map_get_next_id() */
+	nr_id_found = 0;
+	next_id = 0;
+	while (!bpf_map_get_next_id(next_id, &next_id)) {
+		struct bpf_map_info map_info = {};
+		int map_fd;
+
+		info_len = sizeof(map_info);
+
+		map_fd = bpf_map_get_fd_by_id(next_id);
+		if (map_fd < 0 && errno == ENOENT)
+			/* The bpf_map is in the dead row */
+			continue;
+		if (CHECK(map_fd < 0, "get-map-fd(next_id)",
+			  "map_fd %d next_id %u errno %d\n",
+			  map_fd, next_id, errno))
+			break;
+
+		for (i = 0; i < nr_iters; i++)
+			if (map_infos[i].id == next_id)
+				break;
+
+		if (i == nr_iters)
+			continue;
+
+		nr_id_found++;
+
+		err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
+		assert(!err);
+
+		err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+		CHECK(err || info_len != sizeof(struct bpf_map_info) ||
+		      memcmp(&map_info, &map_infos[i], info_len) ||
+		      array_value != array_magic_value,
+		      "check get-map-info(next_id->fd)",
+		      "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n",
+		      err, errno, info_len, sizeof(struct bpf_map_info),
+		      memcmp(&map_info, &map_infos[i], info_len),
+		      array_value, array_magic_value);
+
+		close(map_fd);
+	}
+	CHECK(nr_id_found != nr_iters,
+	      "check total map id found by get_next_id",
+	      "nr_id_found %u(%u)\n",
+	      nr_id_found, nr_iters);
+
+done:
+	for (i = 0; i < nr_iters; i++)
+		bpf_object__close(objs[i]);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
new file mode 100644
index 000000000000..bcbd928c96ab
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#define CHECK_FLOW_KEYS(desc, got, expected)				\
+	CHECK(memcmp(&got, &expected, sizeof(got)) != 0,		\
+	      desc,							\
+	      "nhoff=%u/%u "						\
+	      "thoff=%u/%u "						\
+	      "addr_proto=0x%x/0x%x "					\
+	      "is_frag=%u/%u "						\
+	      "is_first_frag=%u/%u "					\
+	      "is_encap=%u/%u "						\
+	      "n_proto=0x%x/0x%x "					\
+	      "sport=%u/%u "						\
+	      "dport=%u/%u\n",						\
+	      got.nhoff, expected.nhoff,				\
+	      got.thoff, expected.thoff,				\
+	      got.addr_proto, expected.addr_proto,			\
+	      got.is_frag, expected.is_frag,				\
+	      got.is_first_frag, expected.is_first_frag,		\
+	      got.is_encap, expected.is_encap,				\
+	      got.n_proto, expected.n_proto,				\
+	      got.sport, expected.sport,				\
+	      got.dport, expected.dport)
+
+static struct bpf_flow_keys pkt_v4_flow_keys = {
+	.nhoff = 0,
+	.thoff = sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct bpf_flow_keys pkt_v6_flow_keys = {
+	.nhoff = 0,
+	.thoff = sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
+void test_flow_dissector(void)
+{
+	struct bpf_flow_keys flow_keys;
+	struct bpf_object *obj;
+	__u32 duration, retval;
+	int err, prog_fd;
+	__u32 size;
+
+	err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
+			    "jmp_table", &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("ipv4_flow_keys", flow_keys, pkt_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_v6, sizeof(pkt_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
+
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
new file mode 100644
index 000000000000..d7bb5beb1c57
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#define MAX_CNT_RAWTP	10ull
+#define MAX_STACK_RAWTP	100
+struct get_stack_trace_t {
+	int pid;
+	int kern_stack_size;
+	int user_stack_size;
+	int user_stack_buildid_size;
+	__u64 kern_stack[MAX_STACK_RAWTP];
+	__u64 user_stack[MAX_STACK_RAWTP];
+	struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+static int get_stack_print_output(void *data, int size)
+{
+	bool good_kern_stack = false, good_user_stack = false;
+	const char *nonjit_func = "___bpf_prog_run";
+	struct get_stack_trace_t *e = data;
+	int i, num_stack;
+	static __u64 cnt;
+	struct ksym *ks;
+
+	cnt++;
+
+	if (size < sizeof(struct get_stack_trace_t)) {
+		__u64 *raw_data = data;
+		bool found = false;
+
+		num_stack = size / sizeof(__u64);
+		/* If jit is enabled, we do not have a good way to
+		 * verify the sanity of the kernel stack. So we
+		 * just assume it is good if the stack is not empty.
+		 * This could be improved in the future.
+		 */
+		if (jit_enabled) {
+			found = num_stack > 0;
+		} else {
+			for (i = 0; i < num_stack; i++) {
+				ks = ksym_search(raw_data[i]);
+				if (strcmp(ks->name, nonjit_func) == 0) {
+					found = true;
+					break;
+				}
+			}
+		}
+		if (found) {
+			good_kern_stack = true;
+			good_user_stack = true;
+		}
+	} else {
+		num_stack = e->kern_stack_size / sizeof(__u64);
+		if (jit_enabled) {
+			good_kern_stack = num_stack > 0;
+		} else {
+			for (i = 0; i < num_stack; i++) {
+				ks = ksym_search(e->kern_stack[i]);
+				if (strcmp(ks->name, nonjit_func) == 0) {
+					good_kern_stack = true;
+					break;
+				}
+			}
+		}
+		if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0)
+			good_user_stack = true;
+	}
+	if (!good_kern_stack || !good_user_stack)
+		return LIBBPF_PERF_EVENT_ERROR;
+
+	if (cnt == MAX_CNT_RAWTP)
+		return LIBBPF_PERF_EVENT_DONE;
+
+	return LIBBPF_PERF_EVENT_CONT;
+}
+
+void test_get_stack_raw_tp(void)
+{
+	const char *file = "./test_get_stack_rawtp.o";
+	int i, efd, err, prog_fd, pmu_fd, perfmap_fd;
+	struct perf_event_attr attr = {};
+	struct timespec tv = {0, 10};
+	__u32 key = 0, duration = 0;
+	struct bpf_object *obj;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+		return;
+
+	efd = bpf_raw_tracepoint_open("sys_enter", prog_fd);
+	if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+		goto close_prog;
+
+	perfmap_fd = bpf_find_map(__func__, obj, "perfmap");
+	if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
+		  perfmap_fd, errno))
+		goto close_prog;
+
+	err = load_kallsyms();
+	if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	attr.sample_type = PERF_SAMPLE_RAW;
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
+	pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/,
+			 -1/*group_fd*/, 0);
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
+		  errno))
+		goto close_prog;
+
+	err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY);
+	if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err,
+		  errno))
+		goto close_prog;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n",
+		  err, errno))
+		goto close_prog;
+
+	err = perf_event_mmap(pmu_fd);
+	if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	/* trigger some syscall action */
+	for (i = 0; i < MAX_CNT_RAWTP; i++)
+		nanosleep(&tv, NULL);
+
+	err = perf_event_poller(pmu_fd, get_stack_print_output);
+	if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	goto close_prog_noerr;
+close_prog:
+	error_cnt++;
+close_prog_noerr:
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
new file mode 100644
index 000000000000..20ddca830e68
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+static void test_l4lb(const char *file)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	struct vip key = {.protocol = 6};
+	struct vip_meta {
+		__u32 flags;
+		__u32 vip_num;
+	} value = {.vip_num = VIP_NUM};
+	__u32 stats_key = VIP_NUM;
+	struct vip_stats {
+		__u64 bytes;
+		__u64 pkts;
+	} stats[nr_cpus];
+	struct real_definition {
+		union {
+			__be32 dst;
+			__be32 dstv6[4];
+		};
+		__u8 flags;
+	} real_def = {.dst = MAGIC_VAL};
+	__u32 ch_key = 11, real_num = 3;
+	__u32 duration, retval, size;
+	int err, i, prog_fd, map_fd;
+	__u64 bytes = 0, pkts = 0;
+	struct bpf_object *obj;
+	char buf[128];
+	u32 *magic = (u32 *)buf;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	map_fd = bpf_find_map(__func__, obj, "vip_map");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &key, &value, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "ch_rings");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "reals");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+	      *magic != MAGIC_VAL, "ipv4",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+	      *magic != MAGIC_VAL, "ipv6",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	map_fd = bpf_find_map(__func__, obj, "stats");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_lookup_elem(map_fd, &stats_key, stats);
+	for (i = 0; i < nr_cpus; i++) {
+		bytes += stats[i].bytes;
+		pkts += stats[i].pkts;
+	}
+	if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
+		error_cnt++;
+		printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts);
+	}
+out:
+	bpf_object__close(obj);
+}
+
+void test_l4lb_all(void)
+{
+	const char *file1 = "./test_l4lb.o";
+	const char *file2 = "./test_l4lb_noinline.o";
+
+	test_l4lb(file1);
+	test_l4lb(file2);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c
new file mode 100644
index 000000000000..90f8a206340a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+static void *parallel_map_access(void *arg)
+{
+	int err, map_fd = *(u32 *) arg;
+	int vars[17], i, j, rnd, key = 0;
+
+	for